diff options
58 files changed, 10005 insertions, 2776 deletions
@@ -4714,6 +4714,7 @@ lib/unicore/SpecialCasing.txt Unicode character database lib/unicore/StandardizedVariants.txt Unicode character database lib/unicore/UnicodeData.txt Unicode character database lib/unicore/version The version of the Unicode +lib/unicore/VerticalOrientation.txt Unicode character database lib/UNIVERSAL.pm Base class for ALL classes lib/User/grent.pm By-name interface to Perl's builtin getgr* lib/User/grent.t See if User::grwent works diff --git a/charclass_invlists.h b/charclass_invlists.h index 2f56895916..ed7bf466ce 100644 --- a/charclass_invlists.h +++ b/charclass_invlists.h @@ -43,7 +43,7 @@ static const UV ASCII_invlist[] = { /* for ASCII/Latin1 */ }; static const UV Assigned_invlist[] = { /* for ASCII/Latin1 */ - 1276, /* Number of elements */ + 1298, /* Number of elements */ 148565664, /* Version and data structure type */ 0, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -93,6 +93,8 @@ static const UV Assigned_invlist[] = { /* for ASCII/Latin1 */ 0x85C, 0x85E, 0x85F, + 0x860, + 0x86B, 0x8A0, 0x8B5, 0x8B6, @@ -124,7 +126,7 @@ static const UV Assigned_invlist[] = { /* for ASCII/Latin1 */ 0x9DF, 0x9E4, 0x9E6, - 0x9FC, + 0x9FE, 0xA01, 0xA04, 0xA05, @@ -184,7 +186,7 @@ static const UV Assigned_invlist[] = { /* for ASCII/Latin1 */ 0xAE6, 0xAF2, 0xAF9, - 0xAFA, + 0xB00, 0xB01, 0xB04, 0xB05, @@ -297,15 +299,13 @@ static const UV Assigned_invlist[] = { /* for ASCII/Latin1 */ 0xCF0, 0xCF1, 0xCF3, - 0xD01, + 0xD00, 0xD04, 0xD05, 0xD0D, 0xD0E, 0xD11, 0xD12, - 0xD3B, - 0xD3D, 0xD45, 0xD46, 0xD49, @@ -518,11 +518,9 @@ static const UV Assigned_invlist[] = { /* for ASCII/Latin1 */ 0x1CC0, 0x1CC8, 0x1CD0, - 0x1CF7, - 0x1CF8, 0x1CFA, 0x1D00, - 0x1DF6, + 0x1DFA, 0x1DFB, 0x1F16, 0x1F18, @@ -564,14 +562,12 @@ static const UV Assigned_invlist[] = { /* for ASCII/Latin1 */ 0x2090, 0x209D, 0x20A0, - 0x20BF, + 0x20C0, 0x20D0, 0x20F1, 0x2100, 0x218C, 0x2190, - 0x23FF, - 0x2400, 0x2427, 0x2440, 0x244B, @@ -584,7 +580,7 @@ static const UV Assigned_invlist[] = { /* for ASCII/Latin1 */ 0x2BBD, 0x2BC9, 0x2BCA, - 0x2BD2, + 0x2BD3, 0x2BEC, 0x2BF0, 0x2C00, @@ -622,7 +618,7 @@ static const UV Assigned_invlist[] = { /* for ASCII/Latin1 */ 0x2DD8, 0x2DDF, 0x2DE0, - 0x2E45, + 0x2E4A, 0x2E80, 0x2E9A, 0x2E9B, @@ -638,7 +634,7 @@ static const UV Assigned_invlist[] = { /* for ASCII/Latin1 */ 0x3099, 0x3100, 0x3105, - 0x312E, + 0x312F, 0x3131, 0x318F, 0x3190, @@ -652,7 +648,7 @@ static const UV Assigned_invlist[] = { /* for ASCII/Latin1 */ 0x3300, 0x4DB6, 0x4DC0, - 0x9FD6, + 0x9FEB, 0xA000, 0xA48D, 0xA490, @@ -811,7 +807,7 @@ static const UV Assigned_invlist[] = { /* for ASCII/Latin1 */ 0x102FC, 0x10300, 0x10324, - 0x10330, + 0x1032D, 0x1034B, 0x10350, 0x1037B, @@ -1019,6 +1015,14 @@ static const UV Assigned_invlist[] = { /* for ASCII/Latin1 */ 0x118F3, 0x118FF, 0x11900, + 0x11A00, + 0x11A48, + 0x11A50, + 0x11A84, + 0x11A86, + 0x11A9D, + 0x11A9E, + 0x11AA3, 0x11AC0, 0x11AF9, 0x11C00, @@ -1035,6 +1039,20 @@ static const UV Assigned_invlist[] = { /* for ASCII/Latin1 */ 0x11CA8, 0x11CA9, 0x11CB7, + 0x11D00, + 0x11D07, + 0x11D08, + 0x11D0A, + 0x11D0B, + 0x11D37, + 0x11D3A, + 0x11D3B, + 0x11D3C, + 0x11D3E, + 0x11D3F, + 0x11D48, + 0x11D50, + 0x11D5A, 0x12000, 0x1239A, 0x12400, @@ -1076,13 +1094,15 @@ static const UV Assigned_invlist[] = { /* for ASCII/Latin1 */ 0x16F8F, 0x16FA0, 0x16FE0, - 0x16FE1, + 0x16FE2, 0x17000, 0x187ED, 0x18800, 0x18AF3, 0x1B000, - 0x1B002, + 0x1B11F, + 0x1B170, + 0x1B2FC, 0x1BC00, 0x1BC6B, 0x1BC70, @@ -1267,12 +1287,14 @@ static const UV Assigned_invlist[] = { /* for ASCII/Latin1 */ 0x1F249, 0x1F250, 0x1F252, + 0x1F260, + 0x1F266, 0x1F300, - 0x1F6D3, + 0x1F6D5, 0x1F6E0, 0x1F6ED, 0x1F6F0, - 0x1F6F7, + 0x1F6F9, 0x1F700, 0x1F774, 0x1F780, @@ -1287,22 +1309,20 @@ static const UV Assigned_invlist[] = { /* for ASCII/Latin1 */ 0x1F888, 0x1F890, 0x1F8AE, + 0x1F900, + 0x1F90C, 0x1F910, - 0x1F91F, - 0x1F920, - 0x1F928, - 0x1F930, - 0x1F931, - 0x1F933, 0x1F93F, 0x1F940, - 0x1F94C, + 0x1F94D, 0x1F950, - 0x1F95F, + 0x1F96C, 0x1F980, - 0x1F992, + 0x1F998, 0x1F9C0, 0x1F9C1, + 0x1F9D0, + 0x1F9E7, 0x20000, 0x2A6D7, 0x2A700, @@ -1311,6 +1331,8 @@ static const UV Assigned_invlist[] = { /* for ASCII/Latin1 */ 0x2B81E, 0x2B820, 0x2CEA2, + 0x2CEB0, + 0x2EBE1, 0x2F800, 0x2FA1E, 0xE0001, @@ -1990,7 +2012,7 @@ static const UV _Perl_Folds_To_Multi_Char_invlist[] = { /* for ASCII/Latin1 */ #if defined(PERL_IN_PERL_C) static const UV _Perl_GCB_invlist[] = { /* for ASCII/Latin1 */ - 1615, /* Number of elements */ + 1690, /* Number of elements */ 148565664, /* Version and data structure type */ 0, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -2128,6 +2150,8 @@ static const UV _Perl_GCB_invlist[] = { /* for ASCII/Latin1 */ 0xACE, 0xAE2, 0xAE4, + 0xAFA, + 0xB00, 0xB01, 0xB02, 0xB04, @@ -2195,9 +2219,11 @@ static const UV _Perl_GCB_invlist[] = { /* for ASCII/Latin1 */ 0xCD7, 0xCE2, 0xCE4, - 0xD01, + 0xD00, 0xD02, 0xD04, + 0xD3B, + 0xD3D, 0xD3E, 0xD3F, 0xD41, @@ -2400,10 +2426,11 @@ static const UV _Perl_GCB_invlist[] = { /* for ASCII/Latin1 */ 0x1CF2, 0x1CF4, 0x1CF5, + 0x1CF7, 0x1CF8, 0x1CFA, 0x1DC0, - 0x1DF6, + 0x1DFA, 0x1DFB, 0x1E00, 0x200B, @@ -2419,8 +2446,16 @@ static const UV _Perl_GCB_invlist[] = { /* for ASCII/Latin1 */ 0x20F1, 0x261D, 0x261E, + 0x2640, + 0x2641, + 0x2642, + 0x2643, + 0x2695, + 0x2697, 0x26F9, 0x26FA, + 0x2708, + 0x2709, 0x270A, 0x270E, 0x2764, @@ -3474,6 +3509,26 @@ static const UV _Perl_GCB_invlist[] = { /* for ASCII/Latin1 */ 0x11726, 0x11727, 0x1172C, + 0x11A01, + 0x11A07, + 0x11A09, + 0x11A0B, + 0x11A33, + 0x11A39, + 0x11A3A, + 0x11A3B, + 0x11A3F, + 0x11A47, + 0x11A48, + 0x11A51, + 0x11A57, + 0x11A59, + 0x11A5C, + 0x11A86, + 0x11A8A, + 0x11A97, + 0x11A98, + 0x11A9A, 0x11C2F, 0x11C30, 0x11C37, @@ -3490,6 +3545,16 @@ static const UV _Perl_GCB_invlist[] = { /* for ASCII/Latin1 */ 0x11CB4, 0x11CB5, 0x11CB7, + 0x11D31, + 0x11D37, + 0x11D3A, + 0x11D3B, + 0x11D3C, + 0x11D3E, + 0x11D3F, + 0x11D46, + 0x11D47, + 0x11D48, 0x16AF0, 0x16AF5, 0x16B30, @@ -3545,12 +3610,30 @@ static const UV _Perl_GCB_invlist[] = { /* for ASCII/Latin1 */ 0x1E94B, 0x1F1E6, 0x1F200, + 0x1F308, + 0x1F309, + 0x1F33E, + 0x1F33F, + 0x1F373, + 0x1F374, 0x1F385, 0x1F386, - 0x1F3C3, + 0x1F393, + 0x1F394, + 0x1F3A4, + 0x1F3A5, + 0x1F3A8, + 0x1F3A9, + 0x1F3C2, 0x1F3C5, + 0x1F3C7, + 0x1F3C8, 0x1F3CA, - 0x1F3CC, + 0x1F3CD, + 0x1F3EB, + 0x1F3EC, + 0x1F3ED, + 0x1F3EE, 0x1F3FB, 0x1F400, 0x1F442, @@ -3573,7 +3656,13 @@ static const UV _Perl_GCB_invlist[] = { /* for ASCII/Latin1 */ 0x1F48C, 0x1F4AA, 0x1F4AB, - 0x1F575, + 0x1F4BB, + 0x1F4BD, + 0x1F527, + 0x1F528, + 0x1F52C, + 0x1F52D, + 0x1F574, 0x1F576, 0x1F57A, 0x1F57B, @@ -3587,22 +3676,30 @@ static const UV _Perl_GCB_invlist[] = { /* for ASCII/Latin1 */ 0x1F648, 0x1F64B, 0x1F650, + 0x1F680, + 0x1F681, + 0x1F692, + 0x1F693, 0x1F6A3, 0x1F6A4, 0x1F6B4, 0x1F6B7, 0x1F6C0, 0x1F6C1, + 0x1F6CC, + 0x1F6CD, 0x1F918, - 0x1F91F, + 0x1F91D, + 0x1F91E, + 0x1F920, 0x1F926, 0x1F927, 0x1F930, - 0x1F931, - 0x1F933, 0x1F93A, - 0x1F93C, + 0x1F93D, 0x1F93F, + 0x1F9D1, + 0x1F9DE, 0xE0000, 0xE0020, 0xE0080, @@ -3775,6 +3872,8 @@ static const GCB_enum _Perl_GCB_invmap[] = { /* for ASCII/Latin1 */ GCB_Extend, GCB_Other, GCB_Extend, + GCB_Other, + GCB_Extend, GCB_SpacingMark, GCB_Other, GCB_Extend, @@ -3845,6 +3944,8 @@ static const GCB_enum _Perl_GCB_invmap[] = { /* for ASCII/Latin1 */ GCB_SpacingMark, GCB_Other, GCB_Extend, + GCB_Other, + GCB_Extend, GCB_SpacingMark, GCB_Extend, GCB_Other, @@ -4046,6 +4147,7 @@ static const GCB_enum _Perl_GCB_invmap[] = { /* for ASCII/Latin1 */ GCB_SpacingMark, GCB_Extend, GCB_Other, + GCB_SpacingMark, GCB_Extend, GCB_Other, GCB_Extend, @@ -4065,8 +4167,16 @@ static const GCB_enum _Perl_GCB_invmap[] = { /* for ASCII/Latin1 */ GCB_Other, GCB_E_Base, GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, GCB_E_Base, GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, GCB_E_Base, GCB_Other, GCB_Glue_After_Zwj, @@ -5120,6 +5230,26 @@ static const GCB_enum _Perl_GCB_invmap[] = { /* for ASCII/Latin1 */ GCB_SpacingMark, GCB_Extend, GCB_Other, + GCB_Extend, + GCB_SpacingMark, + GCB_Extend, + GCB_Other, + GCB_Extend, + GCB_SpacingMark, + GCB_Prepend, + GCB_Extend, + GCB_Other, + GCB_Extend, + GCB_Other, + GCB_Extend, + GCB_SpacingMark, + GCB_Extend, + GCB_Other, + GCB_Prepend, + GCB_Extend, + GCB_SpacingMark, + GCB_Extend, + GCB_Other, GCB_SpacingMark, GCB_Extend, GCB_Other, @@ -5140,6 +5270,16 @@ static const GCB_enum _Perl_GCB_invmap[] = { /* for ASCII/Latin1 */ GCB_Other, GCB_Extend, GCB_Other, + GCB_Extend, + GCB_Other, + GCB_Extend, + GCB_Prepend, + GCB_Extend, + GCB_Other, + GCB_Extend, + GCB_Other, + GCB_Extend, + GCB_Other, GCB_SpacingMark, GCB_Other, GCB_Extend, @@ -5191,12 +5331,30 @@ static const GCB_enum _Perl_GCB_invmap[] = { /* for ASCII/Latin1 */ GCB_Other, GCB_Regional_Indicator, GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_E_Base, + GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, GCB_E_Base, GCB_Other, GCB_E_Base, GCB_Other, GCB_E_Base, GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, GCB_E_Modifier, GCB_Other, GCB_E_Base, @@ -5219,16 +5377,30 @@ static const GCB_enum _Perl_GCB_invmap[] = { /* for ASCII/Latin1 */ GCB_Other, GCB_E_Base, GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_E_Base, + GCB_Other, + GCB_E_Base, + GCB_Other, GCB_E_Base, GCB_Other, GCB_E_Base, GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, GCB_E_Base, GCB_Other, GCB_E_Base, GCB_Other, GCB_Glue_After_Zwj, GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, GCB_E_Base, GCB_Other, GCB_E_Base, @@ -5262,7 +5434,7 @@ static const GCB_enum _Perl_GCB_invmap[] = { /* for ASCII/Latin1 */ #if defined(PERL_IN_UTF8_C) static const UV _Perl_IDCont_invlist[] = { /* for ASCII/Latin1 */ - 1367, /* Number of elements */ + 1393, /* Number of elements */ 148565664, /* Version and data structure type */ 1, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -5365,6 +5537,8 @@ static const UV _Perl_IDCont_invlist[] = { /* for ASCII/Latin1 */ 0x82E, 0x840, 0x85C, + 0x860, + 0x86B, 0x8A0, 0x8B5, 0x8B6, @@ -5403,6 +5577,8 @@ static const UV _Perl_IDCont_invlist[] = { /* for ASCII/Latin1 */ 0x9E4, 0x9E6, 0x9F2, + 0x9FC, + 0x9FD, 0xA01, 0xA04, 0xA05, @@ -5462,7 +5638,7 @@ static const UV _Perl_IDCont_invlist[] = { /* for ASCII/Latin1 */ 0xAE6, 0xAF0, 0xAF9, - 0xAFA, + 0xB00, 0xB01, 0xB04, 0xB05, @@ -5577,15 +5753,13 @@ static const UV _Perl_IDCont_invlist[] = { /* for ASCII/Latin1 */ 0xCF0, 0xCF1, 0xCF3, - 0xD01, + 0xD00, 0xD04, 0xD05, 0xD0D, 0xD0E, 0xD11, 0xD12, - 0xD3B, - 0xD3D, 0xD45, 0xD46, 0xD49, @@ -5832,11 +6006,9 @@ static const UV _Perl_IDCont_invlist[] = { /* for ASCII/Latin1 */ 0x1CD0, 0x1CD3, 0x1CD4, - 0x1CF7, - 0x1CF8, 0x1CFA, 0x1D00, - 0x1DF6, + 0x1DFA, 0x1DFB, 0x1F16, 0x1F18, @@ -5976,7 +6148,7 @@ static const UV _Perl_IDCont_invlist[] = { /* for ASCII/Latin1 */ 0x30FC, 0x3100, 0x3105, - 0x312E, + 0x312F, 0x3131, 0x318F, 0x31A0, @@ -5986,7 +6158,7 @@ static const UV _Perl_IDCont_invlist[] = { /* for ASCII/Latin1 */ 0x3400, 0x4DB6, 0x4E00, - 0x9FD6, + 0x9FEB, 0xA000, 0xA48D, 0xA4D0, @@ -6175,7 +6347,7 @@ static const UV _Perl_IDCont_invlist[] = { /* for ASCII/Latin1 */ 0x102E1, 0x10300, 0x10320, - 0x10330, + 0x1032D, 0x1034B, 0x10350, 0x1037B, @@ -6381,6 +6553,14 @@ static const UV _Perl_IDCont_invlist[] = { /* for ASCII/Latin1 */ 0x118EA, 0x118FF, 0x11900, + 0x11A00, + 0x11A3F, + 0x11A47, + 0x11A48, + 0x11A50, + 0x11A84, + 0x11A86, + 0x11A9A, 0x11AC0, 0x11AF9, 0x11C00, @@ -6397,6 +6577,20 @@ static const UV _Perl_IDCont_invlist[] = { /* for ASCII/Latin1 */ 0x11CA8, 0x11CA9, 0x11CB7, + 0x11D00, + 0x11D07, + 0x11D08, + 0x11D0A, + 0x11D0B, + 0x11D37, + 0x11D3A, + 0x11D3B, + 0x11D3C, + 0x11D3E, + 0x11D3F, + 0x11D48, + 0x11D50, + 0x11D5A, 0x12000, 0x1239A, 0x12400, @@ -6434,13 +6628,15 @@ static const UV _Perl_IDCont_invlist[] = { /* for ASCII/Latin1 */ 0x16F8F, 0x16FA0, 0x16FE0, - 0x16FE1, + 0x16FE2, 0x17000, 0x187ED, 0x18800, 0x18AF3, 0x1B000, - 0x1B002, + 0x1B11F, + 0x1B170, + 0x1B2FC, 0x1BC00, 0x1BC6B, 0x1BC70, @@ -6629,6 +6825,8 @@ static const UV _Perl_IDCont_invlist[] = { /* for ASCII/Latin1 */ 0x2B81E, 0x2B820, 0x2CEA2, + 0x2CEB0, + 0x2EBE1, 0x2F800, 0x2FA1E, 0xE0100, @@ -6636,7 +6834,7 @@ static const UV _Perl_IDCont_invlist[] = { /* for ASCII/Latin1 */ }; static const UV _Perl_IDStart_invlist[] = { /* for ASCII/Latin1 */ - 1161, /* Number of elements */ + 1189, /* Number of elements */ 148565664, /* Version and data structure type */ 1, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -6739,6 +6937,8 @@ static const UV _Perl_IDStart_invlist[] = { /* for ASCII/Latin1 */ 0x829, 0x840, 0x859, + 0x860, + 0x86B, 0x8A0, 0x8B5, 0x8B6, @@ -6775,6 +6975,8 @@ static const UV _Perl_IDStart_invlist[] = { /* for ASCII/Latin1 */ 0x9E2, 0x9F0, 0x9F2, + 0x9FC, + 0x9FD, 0xA05, 0xA0B, 0xA0F, @@ -7234,7 +7436,7 @@ static const UV _Perl_IDStart_invlist[] = { /* for ASCII/Latin1 */ 0x30FC, 0x3100, 0x3105, - 0x312E, + 0x312F, 0x3131, 0x318F, 0x31A0, @@ -7244,7 +7446,7 @@ static const UV _Perl_IDStart_invlist[] = { /* for ASCII/Latin1 */ 0x3400, 0x4DB6, 0x4E00, - 0x9FD6, + 0x9FEB, 0xA000, 0xA48D, 0xA4D0, @@ -7439,7 +7641,7 @@ static const UV _Perl_IDStart_invlist[] = { /* for ASCII/Latin1 */ 0x102D1, 0x10300, 0x10320, - 0x10330, + 0x1032D, 0x1034B, 0x10350, 0x10376, @@ -7605,6 +7807,18 @@ static const UV _Perl_IDStart_invlist[] = { /* for ASCII/Latin1 */ 0x118E0, 0x118FF, 0x11900, + 0x11A00, + 0x11A01, + 0x11A0B, + 0x11A33, + 0x11A3A, + 0x11A3B, + 0x11A50, + 0x11A51, + 0x11A5C, + 0x11A84, + 0x11A86, + 0x11A8A, 0x11AC0, 0x11AF9, 0x11C00, @@ -7615,6 +7829,14 @@ static const UV _Perl_IDStart_invlist[] = { /* for ASCII/Latin1 */ 0x11C41, 0x11C72, 0x11C90, + 0x11D00, + 0x11D07, + 0x11D08, + 0x11D0A, + 0x11D0B, + 0x11D31, + 0x11D46, + 0x11D47, 0x12000, 0x1239A, 0x12400, @@ -7646,13 +7868,15 @@ static const UV _Perl_IDStart_invlist[] = { /* for ASCII/Latin1 */ 0x16F93, 0x16FA0, 0x16FE0, - 0x16FE1, + 0x16FE2, 0x17000, 0x187ED, 0x18800, 0x18AF3, 0x1B000, - 0x1B002, + 0x1B11F, + 0x1B170, + 0x1B2FC, 0x1BC00, 0x1BC6B, 0x1BC70, @@ -7799,6 +8023,8 @@ static const UV _Perl_IDStart_invlist[] = { /* for ASCII/Latin1 */ 0x2B81E, 0x2B820, 0x2CEA2, + 0x2CEB0, + 0x2EBE1, 0x2F800, 0x2FA1E }; @@ -7808,7 +8034,7 @@ static const UV _Perl_IDStart_invlist[] = { /* for ASCII/Latin1 */ #if defined(PERL_IN_PERL_C) static const UV _Perl_LB_invlist[] = { /* for ASCII/Latin1 */ - 2267, /* Number of elements */ + 2313, /* Number of elements */ 148565664, /* Version and data structure type */ 0, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -8023,6 +8249,8 @@ static const UV _Perl_LB_invlist[] = { /* for ASCII/Latin1 */ 0xAF0, 0xAF1, 0xAF2, + 0xAFA, + 0xB00, 0xB01, 0xB04, 0xB3C, @@ -8083,8 +8311,10 @@ static const UV _Perl_LB_invlist[] = { /* for ASCII/Latin1 */ 0xCE4, 0xCE6, 0xCF0, - 0xD01, + 0xD00, 0xD04, + 0xD3B, + 0xD3D, 0xD3E, 0xD45, 0xD46, @@ -8315,10 +8545,10 @@ static const UV _Perl_LB_invlist[] = { /* for ASCII/Latin1 */ 0x1CEE, 0x1CF2, 0x1CF5, - 0x1CF8, + 0x1CF7, 0x1CFA, 0x1DC0, - 0x1DF6, + 0x1DFA, 0x1DFB, 0x1E00, 0x1FFD, @@ -8557,7 +8787,7 @@ static const UV _Perl_LB_invlist[] = { /* for ASCII/Latin1 */ 0x2E40, 0x2E42, 0x2E43, - 0x2E45, + 0x2E4A, 0x2E80, 0x2E9A, 0x2E9B, @@ -8652,7 +8882,7 @@ static const UV _Perl_LB_invlist[] = { /* for ASCII/Latin1 */ 0x30FF, 0x3100, 0x3105, - 0x312E, + 0x312F, 0x3131, 0x318F, 0x3190, @@ -9852,6 +10082,26 @@ static const UV _Perl_LB_invlist[] = { /* for ASCII/Latin1 */ 0x1173F, 0x118E0, 0x118EA, + 0x11A01, + 0x11A0B, + 0x11A33, + 0x11A3A, + 0x11A3B, + 0x11A3F, + 0x11A40, + 0x11A41, + 0x11A45, + 0x11A46, + 0x11A47, + 0x11A48, + 0x11A51, + 0x11A5C, + 0x11A8A, + 0x11A9A, + 0x11A9D, + 0x11A9E, + 0x11AA1, + 0x11AA3, 0x11C2F, 0x11C37, 0x11C38, @@ -9867,6 +10117,18 @@ static const UV _Perl_LB_invlist[] = { /* for ASCII/Latin1 */ 0x11CA8, 0x11CA9, 0x11CB7, + 0x11D31, + 0x11D37, + 0x11D3A, + 0x11D3B, + 0x11D3C, + 0x11D3E, + 0x11D3F, + 0x11D46, + 0x11D47, + 0x11D48, + 0x11D50, + 0x11D5A, 0x12470, 0x12475, 0x13258, @@ -9904,13 +10166,15 @@ static const UV _Perl_LB_invlist[] = { /* for ASCII/Latin1 */ 0x16F8F, 0x16F93, 0x16FE0, - 0x16FE1, + 0x16FE2, 0x17000, 0x187ED, 0x18800, 0x18AF3, 0x1B000, - 0x1B002, + 0x1B11F, + 0x1B170, + 0x1B2FC, 0x1BC9D, 0x1BC9F, 0x1BCA0, @@ -9978,10 +10242,12 @@ static const UV _Perl_LB_invlist[] = { /* for ASCII/Latin1 */ 0x1F3B7, 0x1F3BC, 0x1F3BD, - 0x1F3C3, + 0x1F3C2, 0x1F3C5, + 0x1F3C7, + 0x1F3C8, 0x1F3CA, - 0x1F3CC, + 0x1F3CD, 0x1F3FB, 0x1F400, 0x1F442, @@ -10018,7 +10284,7 @@ static const UV _Perl_LB_invlist[] = { /* for ASCII/Latin1 */ 0x1F525, 0x1F532, 0x1F54A, - 0x1F575, + 0x1F574, 0x1F576, 0x1F57A, 0x1F57B, @@ -10044,6 +10310,8 @@ static const UV _Perl_LB_invlist[] = { /* for ASCII/Latin1 */ 0x1F6B7, 0x1F6C0, 0x1F6C1, + 0x1F6CC, + 0x1F6CD, 0x1F700, 0x1F774, 0x1F780, @@ -10058,16 +10326,20 @@ static const UV _Perl_LB_invlist[] = { /* for ASCII/Latin1 */ 0x1F888, 0x1F890, 0x1F8AE, + 0x1F900, + 0x1F90C, 0x1F918, - 0x1F91F, + 0x1F91D, + 0x1F91E, + 0x1F920, 0x1F926, 0x1F927, 0x1F930, - 0x1F931, - 0x1F933, 0x1F93A, - 0x1F93C, + 0x1F93D, 0x1F93F, + 0x1F9D1, + 0x1F9DE, 0x1FFFE, 0x20000, 0x2FFFE, @@ -10355,6 +10627,8 @@ static const LB_enum _Perl_LB_invmap[] = { /* for ASCII/Latin1 */ LB_Alphabetic, LB_Combining_Mark, LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, LB_Numeric, LB_Alphabetic, LB_Combining_Mark, @@ -10413,6 +10687,8 @@ static const LB_enum _Perl_LB_invmap[] = { /* for ASCII/Latin1 */ LB_Alphabetic, LB_Combining_Mark, LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, LB_Numeric, LB_Alphabetic, LB_Postfix_Numeric, @@ -12174,6 +12450,26 @@ static const LB_enum _Perl_LB_invmap[] = { /* for ASCII/Latin1 */ LB_Alphabetic, LB_Combining_Mark, LB_Alphabetic, + LB_Combining_Mark, + LB_Break_Before, + LB_Alphabetic, + LB_Break_After, + LB_Break_Before, + LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, + LB_Combining_Mark, + LB_Break_After, + LB_Alphabetic, + LB_Break_Before, + LB_Break_After, + LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, LB_Break_After, LB_Alphabetic, LB_Numeric, @@ -12185,6 +12481,18 @@ static const LB_enum _Perl_LB_invmap[] = { /* for ASCII/Latin1 */ LB_Alphabetic, LB_Combining_Mark, LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, + LB_Numeric, + LB_Alphabetic, LB_Break_After, LB_Alphabetic, LB_Open_Punctuation, @@ -12229,6 +12537,8 @@ static const LB_enum _Perl_LB_invmap[] = { /* for ASCII/Latin1 */ LB_Alphabetic, LB_Ideographic, LB_Alphabetic, + LB_Ideographic, + LB_Alphabetic, LB_Combining_Mark, LB_Break_After, LB_Combining_Mark, @@ -12300,6 +12610,8 @@ static const LB_enum _Perl_LB_invmap[] = { /* for ASCII/Latin1 */ LB_Ideographic, LB_E_Base, LB_Ideographic, + LB_E_Base, + LB_Ideographic, LB_E_Modifier, LB_Ideographic, LB_E_Base, @@ -12362,6 +12674,8 @@ static const LB_enum _Perl_LB_invmap[] = { /* for ASCII/Latin1 */ LB_Ideographic, LB_E_Base, LB_Ideographic, + LB_E_Base, + LB_Ideographic, LB_Alphabetic, LB_Ideographic, LB_Alphabetic, @@ -12376,6 +12690,10 @@ static const LB_enum _Perl_LB_invmap[] = { /* for ASCII/Latin1 */ LB_Ideographic, LB_Alphabetic, LB_Ideographic, + LB_Alphabetic, + LB_Ideographic, + LB_E_Base, + LB_Ideographic, LB_E_Base, LB_Ideographic, LB_E_Base, @@ -12404,7 +12722,7 @@ static const LB_enum _Perl_LB_invmap[] = { /* for ASCII/Latin1 */ #if defined(PERL_IN_PERL_C) static const UV _Perl_SB_invlist[] = { /* for ASCII/Latin1 */ - 2957, /* Number of elements */ + 3002, /* Number of elements */ 148565664, /* Version and data structure type */ 0, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -13109,6 +13427,8 @@ static const UV _Perl_SB_invlist[] = { /* for ASCII/Latin1 */ 0x840, 0x859, 0x85C, + 0x860, + 0x86B, 0x8A0, 0x8B5, 0x8B6, @@ -13161,6 +13481,8 @@ static const UV _Perl_SB_invlist[] = { /* for ASCII/Latin1 */ 0x9E6, 0x9F0, 0x9F2, + 0x9FC, + 0x9FD, 0xA01, 0xA04, 0xA05, @@ -13227,6 +13549,7 @@ static const UV _Perl_SB_invlist[] = { /* for ASCII/Latin1 */ 0xAF0, 0xAF9, 0xAFA, + 0xB00, 0xB01, 0xB04, 0xB05, @@ -13351,7 +13674,7 @@ static const UV _Perl_SB_invlist[] = { /* for ASCII/Latin1 */ 0xCF0, 0xCF1, 0xCF3, - 0xD01, + 0xD00, 0xD04, 0xD05, 0xD0D, @@ -13692,11 +14015,10 @@ static const UV _Perl_SB_invlist[] = { /* for ASCII/Latin1 */ 0x1CF2, 0x1CF5, 0x1CF7, - 0x1CF8, 0x1CFA, 0x1D00, 0x1DC0, - 0x1DF6, + 0x1DFA, 0x1DFB, 0x1E00, 0x1E01, @@ -14306,7 +14628,7 @@ static const UV _Perl_SB_invlist[] = { /* for ASCII/Latin1 */ 0x30FC, 0x3100, 0x3105, - 0x312E, + 0x312F, 0x3131, 0x318F, 0x31A0, @@ -14316,7 +14638,7 @@ static const UV _Perl_SB_invlist[] = { /* for ASCII/Latin1 */ 0x3400, 0x4DB6, 0x4E00, - 0x9FD6, + 0x9FEB, 0xA000, 0xA48D, 0xA4D0, @@ -14794,7 +15116,7 @@ static const UV _Perl_SB_invlist[] = { /* for ASCII/Latin1 */ 0x102E1, 0x10300, 0x10320, - 0x10330, + 0x1032D, 0x1034B, 0x10350, 0x10376, @@ -15055,6 +15377,26 @@ static const UV _Perl_SB_invlist[] = { /* for ASCII/Latin1 */ 0x118EA, 0x118FF, 0x11900, + 0x11A00, + 0x11A01, + 0x11A0B, + 0x11A33, + 0x11A3A, + 0x11A3B, + 0x11A3F, + 0x11A42, + 0x11A44, + 0x11A47, + 0x11A48, + 0x11A50, + 0x11A51, + 0x11A5C, + 0x11A84, + 0x11A86, + 0x11A8A, + 0x11A9A, + 0x11A9B, + 0x11A9D, 0x11AC0, 0x11AF9, 0x11C00, @@ -15074,6 +15416,23 @@ static const UV _Perl_SB_invlist[] = { /* for ASCII/Latin1 */ 0x11CA8, 0x11CA9, 0x11CB7, + 0x11D00, + 0x11D07, + 0x11D08, + 0x11D0A, + 0x11D0B, + 0x11D31, + 0x11D37, + 0x11D3A, + 0x11D3B, + 0x11D3C, + 0x11D3E, + 0x11D3F, + 0x11D46, + 0x11D47, + 0x11D48, + 0x11D50, + 0x11D5A, 0x12000, 0x1239A, 0x12400, @@ -15119,13 +15478,15 @@ static const UV _Perl_SB_invlist[] = { /* for ASCII/Latin1 */ 0x16F93, 0x16FA0, 0x16FE0, - 0x16FE1, + 0x16FE2, 0x17000, 0x187ED, 0x18800, 0x18AF3, 0x1B000, - 0x1B002, + 0x1B11F, + 0x1B170, + 0x1B2FC, 0x1BC00, 0x1BC6B, 0x1BC70, @@ -15357,6 +15718,8 @@ static const UV _Perl_SB_invlist[] = { /* for ASCII/Latin1 */ 0x2B81E, 0x2B820, 0x2CEA2, + 0x2CEB0, + 0x2EBE1, 0x2F800, 0x2FA1E, 0xE0001, @@ -16098,6 +16461,8 @@ static const SB_enum _Perl_SB_invmap[] = { /* for ASCII/Latin1 */ SB_Other, SB_OLetter, SB_Other, + SB_OLetter, + SB_Other, SB_Extend, SB_Format, SB_Extend, @@ -16146,6 +16511,8 @@ static const SB_enum _Perl_SB_invmap[] = { /* for ASCII/Latin1 */ SB_Numeric, SB_OLetter, SB_Other, + SB_OLetter, + SB_Other, SB_Extend, SB_Other, SB_OLetter, @@ -16211,6 +16578,7 @@ static const SB_enum _Perl_SB_invmap[] = { /* for ASCII/Latin1 */ SB_Numeric, SB_Other, SB_OLetter, + SB_Extend, SB_Other, SB_Extend, SB_Other, @@ -16343,7 +16711,7 @@ static const SB_enum _Perl_SB_invmap[] = { /* for ASCII/Latin1 */ SB_OLetter, SB_Other, SB_OLetter, - SB_Other, + SB_Extend, SB_OLetter, SB_Extend, SB_Other, @@ -16676,7 +17044,6 @@ static const SB_enum _Perl_SB_invmap[] = { /* for ASCII/Latin1 */ SB_OLetter, SB_Extend, SB_OLetter, - SB_Other, SB_Extend, SB_Other, SB_Lower, @@ -18041,6 +18408,26 @@ static const SB_enum _Perl_SB_invmap[] = { /* for ASCII/Latin1 */ SB_OLetter, SB_Other, SB_OLetter, + SB_Extend, + SB_OLetter, + SB_Extend, + SB_OLetter, + SB_Extend, + SB_Other, + SB_STerm, + SB_Other, + SB_Extend, + SB_Other, + SB_OLetter, + SB_Extend, + SB_OLetter, + SB_Other, + SB_OLetter, + SB_Extend, + SB_Other, + SB_STerm, + SB_Other, + SB_OLetter, SB_Other, SB_OLetter, SB_Other, @@ -18064,6 +18451,23 @@ static const SB_enum _Perl_SB_invmap[] = { /* for ASCII/Latin1 */ SB_OLetter, SB_Other, SB_OLetter, + SB_Extend, + SB_Other, + SB_Extend, + SB_Other, + SB_Extend, + SB_Other, + SB_Extend, + SB_OLetter, + SB_Extend, + SB_Other, + SB_Numeric, + SB_Other, + SB_OLetter, + SB_Other, + SB_OLetter, + SB_Other, + SB_OLetter, SB_Other, SB_OLetter, SB_Other, @@ -18119,6 +18523,8 @@ static const SB_enum _Perl_SB_invmap[] = { /* for ASCII/Latin1 */ SB_Other, SB_OLetter, SB_Other, + SB_OLetter, + SB_Other, SB_Extend, SB_STerm, SB_Format, @@ -18344,6 +18750,8 @@ static const SB_enum _Perl_SB_invmap[] = { /* for ASCII/Latin1 */ SB_Other, SB_OLetter, SB_Other, + SB_OLetter, + SB_Other, SB_Format, SB_Other, SB_Extend, @@ -18357,7 +18765,7 @@ static const SB_enum _Perl_SB_invmap[] = { /* for ASCII/Latin1 */ #if defined(PERL_IN_PERL_C) static const UV _Perl_WB_invlist[] = { /* for ASCII/Latin1 */ - 1657, /* Number of elements */ + 1721, /* Number of elements */ 148565664, /* Version and data structure type */ 0, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -18406,17 +18814,10 @@ static const UV _Perl_WB_invlist[] = { /* for ASCII/Latin1 */ 0xD8, 0xF7, 0xF8, - 0x2C2, - 0x2C6, - 0x2D2, - 0x2D7, 0x2D8, - 0x2E0, + 0x2DE, 0x2E5, 0x2EC, - 0x2ED, - 0x2EE, - 0x2EF, 0x300, 0x370, 0x375, @@ -18530,6 +18931,8 @@ static const UV _Perl_WB_invlist[] = { /* for ASCII/Latin1 */ 0x840, 0x859, 0x85C, + 0x860, + 0x86B, 0x8A0, 0x8B5, 0x8B6, @@ -18582,6 +18985,8 @@ static const UV _Perl_WB_invlist[] = { /* for ASCII/Latin1 */ 0x9E6, 0x9F0, 0x9F2, + 0x9FC, + 0x9FD, 0xA01, 0xA04, 0xA05, @@ -18648,6 +19053,7 @@ static const UV _Perl_WB_invlist[] = { /* for ASCII/Latin1 */ 0xAF0, 0xAF9, 0xAFA, + 0xB00, 0xB01, 0xB04, 0xB05, @@ -18772,7 +19178,7 @@ static const UV _Perl_WB_invlist[] = { /* for ASCII/Latin1 */ 0xCF0, 0xCF1, 0xCF3, - 0xD01, + 0xD00, 0xD04, 0xD05, 0xD0D, @@ -19044,11 +19450,10 @@ static const UV _Perl_WB_invlist[] = { /* for ASCII/Latin1 */ 0x1CF2, 0x1CF5, 0x1CF7, - 0x1CF8, 0x1CFA, 0x1D00, 0x1DC0, - 0x1DF6, + 0x1DFA, 0x1DFB, 0x1E00, 0x1F16, @@ -19154,8 +19559,16 @@ static const UV _Perl_WB_invlist[] = { /* for ASCII/Latin1 */ 0x24EA, 0x261D, 0x261E, + 0x2640, + 0x2641, + 0x2642, + 0x2643, + 0x2695, + 0x2697, 0x26F9, 0x26FA, + 0x2708, + 0x2709, 0x270A, 0x270E, 0x2764, @@ -19221,7 +19634,7 @@ static const UV _Perl_WB_invlist[] = { /* for ASCII/Latin1 */ 0x30FC, 0x3100, 0x3105, - 0x312E, + 0x312F, 0x3131, 0x318F, 0x31A0, @@ -19253,10 +19666,6 @@ static const UV _Perl_WB_invlist[] = { /* for ASCII/Latin1 */ 0xA6F0, 0xA6F2, 0xA717, - 0xA720, - 0xA722, - 0xA789, - 0xA78B, 0xA7AF, 0xA7B0, 0xA7B8, @@ -19343,8 +19752,6 @@ static const UV _Perl_WB_invlist[] = { /* for ASCII/Latin1 */ 0xAB28, 0xAB2F, 0xAB30, - 0xAB5B, - 0xAB5C, 0xAB66, 0xAB70, 0xABE3, @@ -19467,7 +19874,7 @@ static const UV _Perl_WB_invlist[] = { /* for ASCII/Latin1 */ 0x102E1, 0x10300, 0x10320, - 0x10330, + 0x1032D, 0x1034B, 0x10350, 0x10376, @@ -19702,6 +20109,22 @@ static const UV _Perl_WB_invlist[] = { /* for ASCII/Latin1 */ 0x118EA, 0x118FF, 0x11900, + 0x11A00, + 0x11A01, + 0x11A0B, + 0x11A33, + 0x11A3A, + 0x11A3B, + 0x11A3F, + 0x11A47, + 0x11A48, + 0x11A50, + 0x11A51, + 0x11A5C, + 0x11A84, + 0x11A86, + 0x11A8A, + 0x11A9A, 0x11AC0, 0x11AF9, 0x11C00, @@ -19720,6 +20143,23 @@ static const UV _Perl_WB_invlist[] = { /* for ASCII/Latin1 */ 0x11CA8, 0x11CA9, 0x11CB7, + 0x11D00, + 0x11D07, + 0x11D08, + 0x11D0A, + 0x11D0B, + 0x11D31, + 0x11D37, + 0x11D3A, + 0x11D3B, + 0x11D3C, + 0x11D3E, + 0x11D3F, + 0x11D46, + 0x11D47, + 0x11D48, + 0x11D50, + 0x11D5A, 0x12000, 0x1239A, 0x12400, @@ -19760,7 +20200,7 @@ static const UV _Perl_WB_invlist[] = { /* for ASCII/Latin1 */ 0x16F93, 0x16FA0, 0x16FE0, - 0x16FE1, + 0x16FE2, 0x1B000, 0x1B001, 0x1BC00, @@ -19954,12 +20394,30 @@ static const UV _Perl_WB_invlist[] = { /* for ASCII/Latin1 */ 0x1F18A, 0x1F1E6, 0x1F200, + 0x1F308, + 0x1F309, + 0x1F33E, + 0x1F33F, + 0x1F373, + 0x1F374, 0x1F385, 0x1F386, - 0x1F3C3, + 0x1F393, + 0x1F394, + 0x1F3A4, + 0x1F3A5, + 0x1F3A8, + 0x1F3A9, + 0x1F3C2, 0x1F3C5, + 0x1F3C7, + 0x1F3C8, 0x1F3CA, - 0x1F3CC, + 0x1F3CD, + 0x1F3EB, + 0x1F3EC, + 0x1F3ED, + 0x1F3EE, 0x1F3FB, 0x1F400, 0x1F442, @@ -19982,7 +20440,13 @@ static const UV _Perl_WB_invlist[] = { /* for ASCII/Latin1 */ 0x1F48C, 0x1F4AA, 0x1F4AB, - 0x1F575, + 0x1F4BB, + 0x1F4BD, + 0x1F527, + 0x1F528, + 0x1F52C, + 0x1F52D, + 0x1F574, 0x1F576, 0x1F57A, 0x1F57B, @@ -19996,22 +20460,30 @@ static const UV _Perl_WB_invlist[] = { /* for ASCII/Latin1 */ 0x1F648, 0x1F64B, 0x1F650, + 0x1F680, + 0x1F681, + 0x1F692, + 0x1F693, 0x1F6A3, 0x1F6A4, 0x1F6B4, 0x1F6B7, 0x1F6C0, 0x1F6C1, + 0x1F6CC, + 0x1F6CD, 0x1F918, - 0x1F91F, + 0x1F91D, + 0x1F91E, + 0x1F920, 0x1F926, 0x1F927, 0x1F930, - 0x1F931, - 0x1F933, 0x1F93A, - 0x1F93C, + 0x1F93D, 0x1F93F, + 0x1F9D1, + 0x1F9DE, 0xE0001, 0xE0002, 0xE0020, @@ -20103,14 +20575,7 @@ static const WB_enum _Perl_WB_invmap[] = { /* for ASCII/Latin1 */ WB_Other, WB_ALetter, WB_Other, - WB_MidLetter, - WB_Other, - WB_ALetter, - WB_Other, WB_ALetter, - WB_Other, - WB_ALetter, - WB_Other, WB_Extend, WB_ALetter, WB_Other, @@ -20228,6 +20693,8 @@ static const WB_enum _Perl_WB_invmap[] = { /* for ASCII/Latin1 */ WB_Other, WB_ALetter, WB_Other, + WB_ALetter, + WB_Other, WB_Extend, WB_Format, WB_Extend, @@ -20276,6 +20743,8 @@ static const WB_enum _Perl_WB_invmap[] = { /* for ASCII/Latin1 */ WB_Numeric, WB_ALetter, WB_Other, + WB_ALetter, + WB_Other, WB_Extend, WB_Other, WB_ALetter, @@ -20341,6 +20810,7 @@ static const WB_enum _Perl_WB_invmap[] = { /* for ASCII/Latin1 */ WB_Numeric, WB_Other, WB_ALetter, + WB_Extend, WB_Other, WB_Extend, WB_Other, @@ -20473,7 +20943,7 @@ static const WB_enum _Perl_WB_invmap[] = { /* for ASCII/Latin1 */ WB_ALetter, WB_Other, WB_ALetter, - WB_Other, + WB_Extend, WB_ALetter, WB_Extend, WB_Other, @@ -20737,7 +21207,6 @@ static const WB_enum _Perl_WB_invmap[] = { /* for ASCII/Latin1 */ WB_ALetter, WB_Extend, WB_ALetter, - WB_Other, WB_Extend, WB_Other, WB_ALetter, @@ -20848,8 +21317,16 @@ static const WB_enum _Perl_WB_invmap[] = { /* for ASCII/Latin1 */ WB_Other, WB_E_Base, WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_Glue_After_Zwj, + WB_Other, WB_E_Base, WB_Other, + WB_Glue_After_Zwj, + WB_Other, WB_E_Base, WB_Other, WB_Glue_After_Zwj, @@ -20951,10 +21428,6 @@ static const WB_enum _Perl_WB_invmap[] = { /* for ASCII/Latin1 */ WB_ALetter, WB_Other, WB_ALetter, - WB_Other, - WB_ALetter, - WB_Other, - WB_ALetter, WB_Extend, WB_ALetter, WB_Extend, @@ -21039,8 +21512,6 @@ static const WB_enum _Perl_WB_invmap[] = { /* for ASCII/Latin1 */ WB_ALetter, WB_Other, WB_ALetter, - WB_Other, - WB_ALetter, WB_Extend, WB_Other, WB_Extend, @@ -21397,6 +21868,22 @@ static const WB_enum _Perl_WB_invmap[] = { /* for ASCII/Latin1 */ WB_ALetter, WB_Other, WB_ALetter, + WB_Extend, + WB_ALetter, + WB_Extend, + WB_ALetter, + WB_Extend, + WB_Other, + WB_Extend, + WB_Other, + WB_ALetter, + WB_Extend, + WB_ALetter, + WB_Other, + WB_ALetter, + WB_Extend, + WB_Other, + WB_ALetter, WB_Other, WB_ALetter, WB_Other, @@ -21419,6 +21906,23 @@ static const WB_enum _Perl_WB_invmap[] = { /* for ASCII/Latin1 */ WB_ALetter, WB_Other, WB_ALetter, + WB_Extend, + WB_Other, + WB_Extend, + WB_Other, + WB_Extend, + WB_Other, + WB_Extend, + WB_ALetter, + WB_Extend, + WB_Other, + WB_Numeric, + WB_Other, + WB_ALetter, + WB_Other, + WB_ALetter, + WB_Other, + WB_ALetter, WB_Other, WB_ALetter, WB_Other, @@ -21648,12 +22152,30 @@ static const WB_enum _Perl_WB_invmap[] = { /* for ASCII/Latin1 */ WB_Other, WB_Regional_Indicator, WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_E_Base, + WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_Glue_After_Zwj, + WB_Other, WB_E_Base, WB_Other, WB_E_Base, WB_Other, WB_E_Base, WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_Glue_After_Zwj, + WB_Other, WB_E_Modifier, WB_Other, WB_E_Base, @@ -21676,16 +22198,30 @@ static const WB_enum _Perl_WB_invmap[] = { /* for ASCII/Latin1 */ WB_Other, WB_E_Base, WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_E_Base, + WB_Other, + WB_E_Base, + WB_Other, WB_E_Base, WB_Other, WB_E_Base, WB_Other, + WB_Glue_After_Zwj, + WB_Other, WB_E_Base, WB_Other, WB_E_Base, WB_Other, WB_Glue_After_Zwj, WB_Other, + WB_Glue_After_Zwj, + WB_Other, WB_E_Base, WB_Other, WB_E_Base, @@ -21775,7 +22311,7 @@ static const UV XPerlSpace_invlist[] = { /* for ASCII/Latin1 */ }; static const UV XPosixAlnum_invlist[] = { /* for ASCII/Latin1 */ - 1357, /* Number of elements */ + 1391, /* Number of elements */ 148565664, /* Version and data structure type */ 1, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -21882,6 +22418,8 @@ static const UV XPosixAlnum_invlist[] = { /* for ASCII/Latin1 */ 0x82D, 0x840, 0x859, + 0x860, + 0x86B, 0x8A0, 0x8B5, 0x8B6, @@ -21930,6 +22468,8 @@ static const UV XPosixAlnum_invlist[] = { /* for ASCII/Latin1 */ 0x9E4, 0x9E6, 0x9F2, + 0x9FC, + 0x9FD, 0xA01, 0xA04, 0xA05, @@ -21987,7 +22527,7 @@ static const UV XPosixAlnum_invlist[] = { /* for ASCII/Latin1 */ 0xAE6, 0xAF0, 0xAF9, - 0xAFA, + 0xAFD, 0xB01, 0xB04, 0xB05, @@ -22102,7 +22642,7 @@ static const UV XPosixAlnum_invlist[] = { /* for ASCII/Latin1 */ 0xCF0, 0xCF1, 0xCF3, - 0xD01, + 0xD00, 0xD04, 0xD05, 0xD0D, @@ -22507,7 +23047,7 @@ static const UV XPosixAlnum_invlist[] = { /* for ASCII/Latin1 */ 0x30FC, 0x3100, 0x3105, - 0x312E, + 0x312F, 0x3131, 0x318F, 0x31A0, @@ -22517,7 +23057,7 @@ static const UV XPosixAlnum_invlist[] = { /* for ASCII/Latin1 */ 0x3400, 0x4DB6, 0x4E00, - 0x9FD6, + 0x9FEB, 0xA000, 0xA48D, 0xA4D0, @@ -22696,7 +23236,7 @@ static const UV XPosixAlnum_invlist[] = { /* for ASCII/Latin1 */ 0x102D1, 0x10300, 0x10320, - 0x10330, + 0x1032D, 0x1034B, 0x10350, 0x1037B, @@ -22904,6 +23444,14 @@ static const UV XPosixAlnum_invlist[] = { /* for ASCII/Latin1 */ 0x118EA, 0x118FF, 0x11900, + 0x11A00, + 0x11A33, + 0x11A35, + 0x11A3F, + 0x11A50, + 0x11A84, + 0x11A86, + 0x11A98, 0x11AC0, 0x11AF9, 0x11C00, @@ -22922,6 +23470,24 @@ static const UV XPosixAlnum_invlist[] = { /* for ASCII/Latin1 */ 0x11CA8, 0x11CA9, 0x11CB7, + 0x11D00, + 0x11D07, + 0x11D08, + 0x11D0A, + 0x11D0B, + 0x11D37, + 0x11D3A, + 0x11D3B, + 0x11D3C, + 0x11D3E, + 0x11D3F, + 0x11D42, + 0x11D43, + 0x11D44, + 0x11D46, + 0x11D48, + 0x11D50, + 0x11D5A, 0x12000, 0x1239A, 0x12400, @@ -22957,13 +23523,15 @@ static const UV XPosixAlnum_invlist[] = { /* for ASCII/Latin1 */ 0x16F93, 0x16FA0, 0x16FE0, - 0x16FE1, + 0x16FE2, 0x17000, 0x187ED, 0x18800, 0x18AF3, 0x1B000, - 0x1B002, + 0x1B11F, + 0x1B170, + 0x1B2FC, 0x1BC00, 0x1BC6B, 0x1BC70, @@ -23134,12 +23702,14 @@ static const UV XPosixAlnum_invlist[] = { /* for ASCII/Latin1 */ 0x2B81E, 0x2B820, 0x2CEA2, + 0x2CEB0, + 0x2EBE1, 0x2F800, 0x2FA1E }; static const UV XPosixAlpha_invlist[] = { /* for ASCII/Latin1 */ - 1289, /* Number of elements */ + 1321, /* Number of elements */ 148565664, /* Version and data structure type */ 1, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -23246,6 +23816,8 @@ static const UV XPosixAlpha_invlist[] = { /* for ASCII/Latin1 */ 0x82D, 0x840, 0x859, + 0x860, + 0x86B, 0x8A0, 0x8B5, 0x8B6, @@ -23292,6 +23864,8 @@ static const UV XPosixAlpha_invlist[] = { /* for ASCII/Latin1 */ 0x9E4, 0x9F0, 0x9F2, + 0x9FC, + 0x9FD, 0xA01, 0xA04, 0xA05, @@ -23347,7 +23921,7 @@ static const UV XPosixAlpha_invlist[] = { /* for ASCII/Latin1 */ 0xAE0, 0xAE4, 0xAF9, - 0xAFA, + 0xAFD, 0xB01, 0xB04, 0xB05, @@ -23454,7 +24028,7 @@ static const UV XPosixAlpha_invlist[] = { /* for ASCII/Latin1 */ 0xCE4, 0xCF1, 0xCF3, - 0xD01, + 0xD00, 0xD04, 0xD05, 0xD0D, @@ -23837,7 +24411,7 @@ static const UV XPosixAlpha_invlist[] = { /* for ASCII/Latin1 */ 0x30FC, 0x3100, 0x3105, - 0x312E, + 0x312F, 0x3131, 0x318F, 0x31A0, @@ -23847,7 +24421,7 @@ static const UV XPosixAlpha_invlist[] = { /* for ASCII/Latin1 */ 0x3400, 0x4DB6, 0x4E00, - 0x9FD6, + 0x9FEB, 0xA000, 0xA48D, 0xA4D0, @@ -24022,7 +24596,7 @@ static const UV XPosixAlpha_invlist[] = { /* for ASCII/Latin1 */ 0x102D1, 0x10300, 0x10320, - 0x10330, + 0x1032D, 0x1034B, 0x10350, 0x1037B, @@ -24210,6 +24784,14 @@ static const UV XPosixAlpha_invlist[] = { /* for ASCII/Latin1 */ 0x118E0, 0x118FF, 0x11900, + 0x11A00, + 0x11A33, + 0x11A35, + 0x11A3F, + 0x11A50, + 0x11A84, + 0x11A86, + 0x11A98, 0x11AC0, 0x11AF9, 0x11C00, @@ -24226,6 +24808,22 @@ static const UV XPosixAlpha_invlist[] = { /* for ASCII/Latin1 */ 0x11CA8, 0x11CA9, 0x11CB7, + 0x11D00, + 0x11D07, + 0x11D08, + 0x11D0A, + 0x11D0B, + 0x11D37, + 0x11D3A, + 0x11D3B, + 0x11D3C, + 0x11D3E, + 0x11D3F, + 0x11D42, + 0x11D43, + 0x11D44, + 0x11D46, + 0x11D48, 0x12000, 0x1239A, 0x12400, @@ -24257,13 +24855,15 @@ static const UV XPosixAlpha_invlist[] = { /* for ASCII/Latin1 */ 0x16F93, 0x16FA0, 0x16FE0, - 0x16FE1, + 0x16FE2, 0x17000, 0x187ED, 0x18800, 0x18AF3, 0x1B000, - 0x1B002, + 0x1B11F, + 0x1B170, + 0x1B2FC, 0x1BC00, 0x1BC6B, 0x1BC70, @@ -24430,6 +25030,8 @@ static const UV XPosixAlpha_invlist[] = { /* for ASCII/Latin1 */ 0x2B81E, 0x2B820, 0x2CEA2, + 0x2CEB0, + 0x2EBE1, 0x2F800, 0x2FA1E }; @@ -24470,7 +25072,7 @@ static const UV XPosixCntrl_invlist[] = { /* for ASCII/Latin1 */ }; static const UV XPosixDigit_invlist[] = { /* for ASCII/Latin1 */ - 109, /* Number of elements */ + 111, /* Number of elements */ 148565664, /* Version and data structure type */ 1, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -24575,6 +25177,8 @@ static const UV XPosixDigit_invlist[] = { /* for ASCII/Latin1 */ 0x118EA, 0x11C50, 0x11C5A, + 0x11D50, + 0x11D5A, 0x16A60, 0x16A6A, 0x16B50, @@ -24586,7 +25190,7 @@ static const UV XPosixDigit_invlist[] = { /* for ASCII/Latin1 */ }; static const UV XPosixGraph_invlist[] = { /* for ASCII/Latin1 */ - 1287, /* Number of elements */ + 1309, /* Number of elements */ 148565664, /* Version and data structure type */ 1, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -24639,6 +25243,8 @@ static const UV XPosixGraph_invlist[] = { /* for ASCII/Latin1 */ 0x85C, 0x85E, 0x85F, + 0x860, + 0x86B, 0x8A0, 0x8B5, 0x8B6, @@ -24670,7 +25276,7 @@ static const UV XPosixGraph_invlist[] = { /* for ASCII/Latin1 */ 0x9DF, 0x9E4, 0x9E6, - 0x9FC, + 0x9FE, 0xA01, 0xA04, 0xA05, @@ -24730,7 +25336,7 @@ static const UV XPosixGraph_invlist[] = { /* for ASCII/Latin1 */ 0xAE6, 0xAF2, 0xAF9, - 0xAFA, + 0xB00, 0xB01, 0xB04, 0xB05, @@ -24843,15 +25449,13 @@ static const UV XPosixGraph_invlist[] = { /* for ASCII/Latin1 */ 0xCF0, 0xCF1, 0xCF3, - 0xD01, + 0xD00, 0xD04, 0xD05, 0xD0D, 0xD0E, 0xD11, 0xD12, - 0xD3B, - 0xD3D, 0xD45, 0xD46, 0xD49, @@ -25066,11 +25670,9 @@ static const UV XPosixGraph_invlist[] = { /* for ASCII/Latin1 */ 0x1CC0, 0x1CC8, 0x1CD0, - 0x1CF7, - 0x1CF8, 0x1CFA, 0x1D00, - 0x1DF6, + 0x1DFA, 0x1DFB, 0x1F16, 0x1F18, @@ -25118,14 +25720,12 @@ static const UV XPosixGraph_invlist[] = { /* for ASCII/Latin1 */ 0x2090, 0x209D, 0x20A0, - 0x20BF, + 0x20C0, 0x20D0, 0x20F1, 0x2100, 0x218C, 0x2190, - 0x23FF, - 0x2400, 0x2427, 0x2440, 0x244B, @@ -25138,7 +25738,7 @@ static const UV XPosixGraph_invlist[] = { /* for ASCII/Latin1 */ 0x2BBD, 0x2BC9, 0x2BCA, - 0x2BD2, + 0x2BD3, 0x2BEC, 0x2BF0, 0x2C00, @@ -25176,7 +25776,7 @@ static const UV XPosixGraph_invlist[] = { /* for ASCII/Latin1 */ 0x2DD8, 0x2DDF, 0x2DE0, - 0x2E45, + 0x2E4A, 0x2E80, 0x2E9A, 0x2E9B, @@ -25192,7 +25792,7 @@ static const UV XPosixGraph_invlist[] = { /* for ASCII/Latin1 */ 0x3099, 0x3100, 0x3105, - 0x312E, + 0x312F, 0x3131, 0x318F, 0x3190, @@ -25206,7 +25806,7 @@ static const UV XPosixGraph_invlist[] = { /* for ASCII/Latin1 */ 0x3300, 0x4DB6, 0x4DC0, - 0x9FD6, + 0x9FEB, 0xA000, 0xA48D, 0xA490, @@ -25365,7 +25965,7 @@ static const UV XPosixGraph_invlist[] = { /* for ASCII/Latin1 */ 0x102FC, 0x10300, 0x10324, - 0x10330, + 0x1032D, 0x1034B, 0x10350, 0x1037B, @@ -25573,6 +26173,14 @@ static const UV XPosixGraph_invlist[] = { /* for ASCII/Latin1 */ 0x118F3, 0x118FF, 0x11900, + 0x11A00, + 0x11A48, + 0x11A50, + 0x11A84, + 0x11A86, + 0x11A9D, + 0x11A9E, + 0x11AA3, 0x11AC0, 0x11AF9, 0x11C00, @@ -25589,6 +26197,20 @@ static const UV XPosixGraph_invlist[] = { /* for ASCII/Latin1 */ 0x11CA8, 0x11CA9, 0x11CB7, + 0x11D00, + 0x11D07, + 0x11D08, + 0x11D0A, + 0x11D0B, + 0x11D37, + 0x11D3A, + 0x11D3B, + 0x11D3C, + 0x11D3E, + 0x11D3F, + 0x11D48, + 0x11D50, + 0x11D5A, 0x12000, 0x1239A, 0x12400, @@ -25630,13 +26252,15 @@ static const UV XPosixGraph_invlist[] = { /* for ASCII/Latin1 */ 0x16F8F, 0x16FA0, 0x16FE0, - 0x16FE1, + 0x16FE2, 0x17000, 0x187ED, 0x18800, 0x18AF3, 0x1B000, - 0x1B002, + 0x1B11F, + 0x1B170, + 0x1B2FC, 0x1BC00, 0x1BC6B, 0x1BC70, @@ -25821,12 +26445,14 @@ static const UV XPosixGraph_invlist[] = { /* for ASCII/Latin1 */ 0x1F249, 0x1F250, 0x1F252, + 0x1F260, + 0x1F266, 0x1F300, - 0x1F6D3, + 0x1F6D5, 0x1F6E0, 0x1F6ED, 0x1F6F0, - 0x1F6F7, + 0x1F6F9, 0x1F700, 0x1F774, 0x1F780, @@ -25841,22 +26467,20 @@ static const UV XPosixGraph_invlist[] = { /* for ASCII/Latin1 */ 0x1F888, 0x1F890, 0x1F8AE, + 0x1F900, + 0x1F90C, 0x1F910, - 0x1F91F, - 0x1F920, - 0x1F928, - 0x1F930, - 0x1F931, - 0x1F933, 0x1F93F, 0x1F940, - 0x1F94C, + 0x1F94D, 0x1F950, - 0x1F95F, + 0x1F96C, 0x1F980, - 0x1F992, + 0x1F998, 0x1F9C0, 0x1F9C1, + 0x1F9D0, + 0x1F9E7, 0x20000, 0x2A6D7, 0x2A700, @@ -25865,6 +26489,8 @@ static const UV XPosixGraph_invlist[] = { /* for ASCII/Latin1 */ 0x2B81E, 0x2B820, 0x2CEA2, + 0x2CEB0, + 0x2EBE1, 0x2F800, 0x2FA1E, 0xE0001, @@ -27168,7 +27794,7 @@ static const UV XPosixLower_invlist[] = { /* for ASCII/Latin1 */ }; static const UV XPosixPrint_invlist[] = { /* for ASCII/Latin1 */ - 1281, /* Number of elements */ + 1303, /* Number of elements */ 148565664, /* Version and data structure type */ 1, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -27221,6 +27847,8 @@ static const UV XPosixPrint_invlist[] = { /* for ASCII/Latin1 */ 0x85C, 0x85E, 0x85F, + 0x860, + 0x86B, 0x8A0, 0x8B5, 0x8B6, @@ -27252,7 +27880,7 @@ static const UV XPosixPrint_invlist[] = { /* for ASCII/Latin1 */ 0x9DF, 0x9E4, 0x9E6, - 0x9FC, + 0x9FE, 0xA01, 0xA04, 0xA05, @@ -27312,7 +27940,7 @@ static const UV XPosixPrint_invlist[] = { /* for ASCII/Latin1 */ 0xAE6, 0xAF2, 0xAF9, - 0xAFA, + 0xB00, 0xB01, 0xB04, 0xB05, @@ -27425,15 +28053,13 @@ static const UV XPosixPrint_invlist[] = { /* for ASCII/Latin1 */ 0xCF0, 0xCF1, 0xCF3, - 0xD01, + 0xD00, 0xD04, 0xD05, 0xD0D, 0xD0E, 0xD11, 0xD12, - 0xD3B, - 0xD3D, 0xD45, 0xD46, 0xD49, @@ -27646,11 +28272,9 @@ static const UV XPosixPrint_invlist[] = { /* for ASCII/Latin1 */ 0x1CC0, 0x1CC8, 0x1CD0, - 0x1CF7, - 0x1CF8, 0x1CFA, 0x1D00, - 0x1DF6, + 0x1DFA, 0x1DFB, 0x1F16, 0x1F18, @@ -27694,14 +28318,12 @@ static const UV XPosixPrint_invlist[] = { /* for ASCII/Latin1 */ 0x2090, 0x209D, 0x20A0, - 0x20BF, + 0x20C0, 0x20D0, 0x20F1, 0x2100, 0x218C, 0x2190, - 0x23FF, - 0x2400, 0x2427, 0x2440, 0x244B, @@ -27714,7 +28336,7 @@ static const UV XPosixPrint_invlist[] = { /* for ASCII/Latin1 */ 0x2BBD, 0x2BC9, 0x2BCA, - 0x2BD2, + 0x2BD3, 0x2BEC, 0x2BF0, 0x2C00, @@ -27752,7 +28374,7 @@ static const UV XPosixPrint_invlist[] = { /* for ASCII/Latin1 */ 0x2DD8, 0x2DDF, 0x2DE0, - 0x2E45, + 0x2E4A, 0x2E80, 0x2E9A, 0x2E9B, @@ -27768,7 +28390,7 @@ static const UV XPosixPrint_invlist[] = { /* for ASCII/Latin1 */ 0x3099, 0x3100, 0x3105, - 0x312E, + 0x312F, 0x3131, 0x318F, 0x3190, @@ -27782,7 +28404,7 @@ static const UV XPosixPrint_invlist[] = { /* for ASCII/Latin1 */ 0x3300, 0x4DB6, 0x4DC0, - 0x9FD6, + 0x9FEB, 0xA000, 0xA48D, 0xA490, @@ -27941,7 +28563,7 @@ static const UV XPosixPrint_invlist[] = { /* for ASCII/Latin1 */ 0x102FC, 0x10300, 0x10324, - 0x10330, + 0x1032D, 0x1034B, 0x10350, 0x1037B, @@ -28149,6 +28771,14 @@ static const UV XPosixPrint_invlist[] = { /* for ASCII/Latin1 */ 0x118F3, 0x118FF, 0x11900, + 0x11A00, + 0x11A48, + 0x11A50, + 0x11A84, + 0x11A86, + 0x11A9D, + 0x11A9E, + 0x11AA3, 0x11AC0, 0x11AF9, 0x11C00, @@ -28165,6 +28795,20 @@ static const UV XPosixPrint_invlist[] = { /* for ASCII/Latin1 */ 0x11CA8, 0x11CA9, 0x11CB7, + 0x11D00, + 0x11D07, + 0x11D08, + 0x11D0A, + 0x11D0B, + 0x11D37, + 0x11D3A, + 0x11D3B, + 0x11D3C, + 0x11D3E, + 0x11D3F, + 0x11D48, + 0x11D50, + 0x11D5A, 0x12000, 0x1239A, 0x12400, @@ -28206,13 +28850,15 @@ static const UV XPosixPrint_invlist[] = { /* for ASCII/Latin1 */ 0x16F8F, 0x16FA0, 0x16FE0, - 0x16FE1, + 0x16FE2, 0x17000, 0x187ED, 0x18800, 0x18AF3, 0x1B000, - 0x1B002, + 0x1B11F, + 0x1B170, + 0x1B2FC, 0x1BC00, 0x1BC6B, 0x1BC70, @@ -28397,12 +29043,14 @@ static const UV XPosixPrint_invlist[] = { /* for ASCII/Latin1 */ 0x1F249, 0x1F250, 0x1F252, + 0x1F260, + 0x1F266, 0x1F300, - 0x1F6D3, + 0x1F6D5, 0x1F6E0, 0x1F6ED, 0x1F6F0, - 0x1F6F7, + 0x1F6F9, 0x1F700, 0x1F774, 0x1F780, @@ -28417,22 +29065,20 @@ static const UV XPosixPrint_invlist[] = { /* for ASCII/Latin1 */ 0x1F888, 0x1F890, 0x1F8AE, + 0x1F900, + 0x1F90C, 0x1F910, - 0x1F91F, - 0x1F920, - 0x1F928, - 0x1F930, - 0x1F931, - 0x1F933, 0x1F93F, 0x1F940, - 0x1F94C, + 0x1F94D, 0x1F950, - 0x1F95F, + 0x1F96C, 0x1F980, - 0x1F992, + 0x1F998, 0x1F9C0, 0x1F9C1, + 0x1F9D0, + 0x1F9E7, 0x20000, 0x2A6D7, 0x2A700, @@ -28441,6 +29087,8 @@ static const UV XPosixPrint_invlist[] = { /* for ASCII/Latin1 */ 0x2B81E, 0x2B820, 0x2CEA2, + 0x2CEB0, + 0x2EBE1, 0x2F800, 0x2FA1E, 0xE0001, @@ -28456,7 +29104,7 @@ static const UV XPosixPrint_invlist[] = { /* for ASCII/Latin1 */ }; static const UV XPosixPunct_invlist[] = { /* for ASCII/Latin1 */ - 327, /* Number of elements */ + 335, /* Number of elements */ 148565664, /* Version and data structure type */ 1, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -28523,6 +29171,8 @@ static const UV XPosixPunct_invlist[] = { /* for ASCII/Latin1 */ 0x966, 0x970, 0x971, + 0x9FD, + 0x9FE, 0xAF0, 0xAF1, 0xDF4, @@ -28622,7 +29272,7 @@ static const UV XPosixPunct_invlist[] = { /* for ASCII/Latin1 */ 0x2E00, 0x2E2F, 0x2E30, - 0x2E45, + 0x2E4A, 0x3001, 0x3004, 0x3008, @@ -28767,6 +29417,12 @@ static const UV XPosixPunct_invlist[] = { /* for ASCII/Latin1 */ 0x1166D, 0x1173C, 0x1173F, + 0x11A3F, + 0x11A47, + 0x11A9A, + 0x11A9D, + 0x11A9E, + 0x11AA3, 0x11C41, 0x11C46, 0x11C70, @@ -30090,7 +30746,7 @@ static const UV XPosixUpper_invlist[] = { /* for ASCII/Latin1 */ }; static const UV XPosixWord_invlist[] = { /* for ASCII/Latin1 */ - 1361, /* Number of elements */ + 1387, /* Number of elements */ 148565664, /* Version and data structure type */ 1, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -30191,6 +30847,8 @@ static const UV XPosixWord_invlist[] = { /* for ASCII/Latin1 */ 0x82E, 0x840, 0x85C, + 0x860, + 0x86B, 0x8A0, 0x8B5, 0x8B6, @@ -30229,6 +30887,8 @@ static const UV XPosixWord_invlist[] = { /* for ASCII/Latin1 */ 0x9E4, 0x9E6, 0x9F2, + 0x9FC, + 0x9FD, 0xA01, 0xA04, 0xA05, @@ -30288,7 +30948,7 @@ static const UV XPosixWord_invlist[] = { /* for ASCII/Latin1 */ 0xAE6, 0xAF0, 0xAF9, - 0xAFA, + 0xB00, 0xB01, 0xB04, 0xB05, @@ -30403,15 +31063,13 @@ static const UV XPosixWord_invlist[] = { /* for ASCII/Latin1 */ 0xCF0, 0xCF1, 0xCF3, - 0xD01, + 0xD00, 0xD04, 0xD05, 0xD0D, 0xD0E, 0xD11, 0xD12, - 0xD3B, - 0xD3D, 0xD45, 0xD46, 0xD49, @@ -30658,11 +31316,9 @@ static const UV XPosixWord_invlist[] = { /* for ASCII/Latin1 */ 0x1CD0, 0x1CD3, 0x1CD4, - 0x1CF7, - 0x1CF8, 0x1CFA, 0x1D00, - 0x1DF6, + 0x1DFA, 0x1DFB, 0x1F16, 0x1F18, @@ -30804,7 +31460,7 @@ static const UV XPosixWord_invlist[] = { /* for ASCII/Latin1 */ 0x30FC, 0x3100, 0x3105, - 0x312E, + 0x312F, 0x3131, 0x318F, 0x31A0, @@ -30814,7 +31470,7 @@ static const UV XPosixWord_invlist[] = { /* for ASCII/Latin1 */ 0x3400, 0x4DB6, 0x4E00, - 0x9FD6, + 0x9FEB, 0xA000, 0xA48D, 0xA4D0, @@ -30991,7 +31647,7 @@ static const UV XPosixWord_invlist[] = { /* for ASCII/Latin1 */ 0x102E1, 0x10300, 0x10320, - 0x10330, + 0x1032D, 0x1034B, 0x10350, 0x1037B, @@ -31197,6 +31853,14 @@ static const UV XPosixWord_invlist[] = { /* for ASCII/Latin1 */ 0x118EA, 0x118FF, 0x11900, + 0x11A00, + 0x11A3F, + 0x11A47, + 0x11A48, + 0x11A50, + 0x11A84, + 0x11A86, + 0x11A9A, 0x11AC0, 0x11AF9, 0x11C00, @@ -31213,6 +31877,20 @@ static const UV XPosixWord_invlist[] = { /* for ASCII/Latin1 */ 0x11CA8, 0x11CA9, 0x11CB7, + 0x11D00, + 0x11D07, + 0x11D08, + 0x11D0A, + 0x11D0B, + 0x11D37, + 0x11D3A, + 0x11D3B, + 0x11D3C, + 0x11D3E, + 0x11D3F, + 0x11D48, + 0x11D50, + 0x11D5A, 0x12000, 0x1239A, 0x12400, @@ -31250,13 +31928,15 @@ static const UV XPosixWord_invlist[] = { /* for ASCII/Latin1 */ 0x16F8F, 0x16FA0, 0x16FE0, - 0x16FE1, + 0x16FE2, 0x17000, 0x187ED, 0x18800, 0x18AF3, 0x1B000, - 0x1B002, + 0x1B11F, + 0x1B170, + 0x1B2FC, 0x1BC00, 0x1BC6B, 0x1BC70, @@ -31451,6 +32131,8 @@ static const UV XPosixWord_invlist[] = { /* for ASCII/Latin1 */ 0x2B81E, 0x2B820, 0x2CEA2, + 0x2CEB0, + 0x2EBE1, 0x2F800, 0x2FA1E, 0xE0100, @@ -31550,7 +32232,7 @@ static const UV ASCII_invlist[] = { /* for EBCDIC 1047 */ }; static const UV Assigned_invlist[] = { /* for EBCDIC 1047 */ - 1276, /* Number of elements */ + 1298, /* Number of elements */ 148565664, /* Version and data structure type */ 0, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -31600,6 +32282,8 @@ static const UV Assigned_invlist[] = { /* for EBCDIC 1047 */ 0x85C, 0x85E, 0x85F, + 0x860, + 0x86B, 0x8A0, 0x8B5, 0x8B6, @@ -31631,7 +32315,7 @@ static const UV Assigned_invlist[] = { /* for EBCDIC 1047 */ 0x9DF, 0x9E4, 0x9E6, - 0x9FC, + 0x9FE, 0xA01, 0xA04, 0xA05, @@ -31691,7 +32375,7 @@ static const UV Assigned_invlist[] = { /* for EBCDIC 1047 */ 0xAE6, 0xAF2, 0xAF9, - 0xAFA, + 0xB00, 0xB01, 0xB04, 0xB05, @@ -31804,15 +32488,13 @@ static const UV Assigned_invlist[] = { /* for EBCDIC 1047 */ 0xCF0, 0xCF1, 0xCF3, - 0xD01, + 0xD00, 0xD04, 0xD05, 0xD0D, 0xD0E, 0xD11, 0xD12, - 0xD3B, - 0xD3D, 0xD45, 0xD46, 0xD49, @@ -32025,11 +32707,9 @@ static const UV Assigned_invlist[] = { /* for EBCDIC 1047 */ 0x1CC0, 0x1CC8, 0x1CD0, - 0x1CF7, - 0x1CF8, 0x1CFA, 0x1D00, - 0x1DF6, + 0x1DFA, 0x1DFB, 0x1F16, 0x1F18, @@ -32071,14 +32751,12 @@ static const UV Assigned_invlist[] = { /* for EBCDIC 1047 */ 0x2090, 0x209D, 0x20A0, - 0x20BF, + 0x20C0, 0x20D0, 0x20F1, 0x2100, 0x218C, 0x2190, - 0x23FF, - 0x2400, 0x2427, 0x2440, 0x244B, @@ -32091,7 +32769,7 @@ static const UV Assigned_invlist[] = { /* for EBCDIC 1047 */ 0x2BBD, 0x2BC9, 0x2BCA, - 0x2BD2, + 0x2BD3, 0x2BEC, 0x2BF0, 0x2C00, @@ -32129,7 +32807,7 @@ static const UV Assigned_invlist[] = { /* for EBCDIC 1047 */ 0x2DD8, 0x2DDF, 0x2DE0, - 0x2E45, + 0x2E4A, 0x2E80, 0x2E9A, 0x2E9B, @@ -32145,7 +32823,7 @@ static const UV Assigned_invlist[] = { /* for EBCDIC 1047 */ 0x3099, 0x3100, 0x3105, - 0x312E, + 0x312F, 0x3131, 0x318F, 0x3190, @@ -32159,7 +32837,7 @@ static const UV Assigned_invlist[] = { /* for EBCDIC 1047 */ 0x3300, 0x4DB6, 0x4DC0, - 0x9FD6, + 0x9FEB, 0xA000, 0xA48D, 0xA490, @@ -32318,7 +32996,7 @@ static const UV Assigned_invlist[] = { /* for EBCDIC 1047 */ 0x102FC, 0x10300, 0x10324, - 0x10330, + 0x1032D, 0x1034B, 0x10350, 0x1037B, @@ -32526,6 +33204,14 @@ static const UV Assigned_invlist[] = { /* for EBCDIC 1047 */ 0x118F3, 0x118FF, 0x11900, + 0x11A00, + 0x11A48, + 0x11A50, + 0x11A84, + 0x11A86, + 0x11A9D, + 0x11A9E, + 0x11AA3, 0x11AC0, 0x11AF9, 0x11C00, @@ -32542,6 +33228,20 @@ static const UV Assigned_invlist[] = { /* for EBCDIC 1047 */ 0x11CA8, 0x11CA9, 0x11CB7, + 0x11D00, + 0x11D07, + 0x11D08, + 0x11D0A, + 0x11D0B, + 0x11D37, + 0x11D3A, + 0x11D3B, + 0x11D3C, + 0x11D3E, + 0x11D3F, + 0x11D48, + 0x11D50, + 0x11D5A, 0x12000, 0x1239A, 0x12400, @@ -32583,13 +33283,15 @@ static const UV Assigned_invlist[] = { /* for EBCDIC 1047 */ 0x16F8F, 0x16FA0, 0x16FE0, - 0x16FE1, + 0x16FE2, 0x17000, 0x187ED, 0x18800, 0x18AF3, 0x1B000, - 0x1B002, + 0x1B11F, + 0x1B170, + 0x1B2FC, 0x1BC00, 0x1BC6B, 0x1BC70, @@ -32774,12 +33476,14 @@ static const UV Assigned_invlist[] = { /* for EBCDIC 1047 */ 0x1F249, 0x1F250, 0x1F252, + 0x1F260, + 0x1F266, 0x1F300, - 0x1F6D3, + 0x1F6D5, 0x1F6E0, 0x1F6ED, 0x1F6F0, - 0x1F6F7, + 0x1F6F9, 0x1F700, 0x1F774, 0x1F780, @@ -32794,22 +33498,20 @@ static const UV Assigned_invlist[] = { /* for EBCDIC 1047 */ 0x1F888, 0x1F890, 0x1F8AE, + 0x1F900, + 0x1F90C, 0x1F910, - 0x1F91F, - 0x1F920, - 0x1F928, - 0x1F930, - 0x1F931, - 0x1F933, 0x1F93F, 0x1F940, - 0x1F94C, + 0x1F94D, 0x1F950, - 0x1F95F, + 0x1F96C, 0x1F980, - 0x1F992, + 0x1F998, 0x1F9C0, 0x1F9C1, + 0x1F9D0, + 0x1F9E7, 0x20000, 0x2A6D7, 0x2A700, @@ -32818,6 +33520,8 @@ static const UV Assigned_invlist[] = { /* for EBCDIC 1047 */ 0x2B81E, 0x2B820, 0x2CEA2, + 0x2CEB0, + 0x2EBE1, 0x2F800, 0x2FA1E, 0xE0001, @@ -33555,7 +34259,7 @@ static const UV _Perl_Folds_To_Multi_Char_invlist[] = { /* for EBCDIC 1047 */ #if defined(PERL_IN_PERL_C) static const UV _Perl_GCB_invlist[] = { /* for EBCDIC 1047 */ - 1615, /* Number of elements */ + 1690, /* Number of elements */ 148565664, /* Version and data structure type */ 0, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -33693,6 +34397,8 @@ static const UV _Perl_GCB_invlist[] = { /* for EBCDIC 1047 */ 0xACE, 0xAE2, 0xAE4, + 0xAFA, + 0xB00, 0xB01, 0xB02, 0xB04, @@ -33760,9 +34466,11 @@ static const UV _Perl_GCB_invlist[] = { /* for EBCDIC 1047 */ 0xCD7, 0xCE2, 0xCE4, - 0xD01, + 0xD00, 0xD02, 0xD04, + 0xD3B, + 0xD3D, 0xD3E, 0xD3F, 0xD41, @@ -33965,10 +34673,11 @@ static const UV _Perl_GCB_invlist[] = { /* for EBCDIC 1047 */ 0x1CF2, 0x1CF4, 0x1CF5, + 0x1CF7, 0x1CF8, 0x1CFA, 0x1DC0, - 0x1DF6, + 0x1DFA, 0x1DFB, 0x1E00, 0x200B, @@ -33984,8 +34693,16 @@ static const UV _Perl_GCB_invlist[] = { /* for EBCDIC 1047 */ 0x20F1, 0x261D, 0x261E, + 0x2640, + 0x2641, + 0x2642, + 0x2643, + 0x2695, + 0x2697, 0x26F9, 0x26FA, + 0x2708, + 0x2709, 0x270A, 0x270E, 0x2764, @@ -35039,6 +35756,26 @@ static const UV _Perl_GCB_invlist[] = { /* for EBCDIC 1047 */ 0x11726, 0x11727, 0x1172C, + 0x11A01, + 0x11A07, + 0x11A09, + 0x11A0B, + 0x11A33, + 0x11A39, + 0x11A3A, + 0x11A3B, + 0x11A3F, + 0x11A47, + 0x11A48, + 0x11A51, + 0x11A57, + 0x11A59, + 0x11A5C, + 0x11A86, + 0x11A8A, + 0x11A97, + 0x11A98, + 0x11A9A, 0x11C2F, 0x11C30, 0x11C37, @@ -35055,6 +35792,16 @@ static const UV _Perl_GCB_invlist[] = { /* for EBCDIC 1047 */ 0x11CB4, 0x11CB5, 0x11CB7, + 0x11D31, + 0x11D37, + 0x11D3A, + 0x11D3B, + 0x11D3C, + 0x11D3E, + 0x11D3F, + 0x11D46, + 0x11D47, + 0x11D48, 0x16AF0, 0x16AF5, 0x16B30, @@ -35110,12 +35857,30 @@ static const UV _Perl_GCB_invlist[] = { /* for EBCDIC 1047 */ 0x1E94B, 0x1F1E6, 0x1F200, + 0x1F308, + 0x1F309, + 0x1F33E, + 0x1F33F, + 0x1F373, + 0x1F374, 0x1F385, 0x1F386, - 0x1F3C3, + 0x1F393, + 0x1F394, + 0x1F3A4, + 0x1F3A5, + 0x1F3A8, + 0x1F3A9, + 0x1F3C2, 0x1F3C5, + 0x1F3C7, + 0x1F3C8, 0x1F3CA, - 0x1F3CC, + 0x1F3CD, + 0x1F3EB, + 0x1F3EC, + 0x1F3ED, + 0x1F3EE, 0x1F3FB, 0x1F400, 0x1F442, @@ -35138,7 +35903,13 @@ static const UV _Perl_GCB_invlist[] = { /* for EBCDIC 1047 */ 0x1F48C, 0x1F4AA, 0x1F4AB, - 0x1F575, + 0x1F4BB, + 0x1F4BD, + 0x1F527, + 0x1F528, + 0x1F52C, + 0x1F52D, + 0x1F574, 0x1F576, 0x1F57A, 0x1F57B, @@ -35152,22 +35923,30 @@ static const UV _Perl_GCB_invlist[] = { /* for EBCDIC 1047 */ 0x1F648, 0x1F64B, 0x1F650, + 0x1F680, + 0x1F681, + 0x1F692, + 0x1F693, 0x1F6A3, 0x1F6A4, 0x1F6B4, 0x1F6B7, 0x1F6C0, 0x1F6C1, + 0x1F6CC, + 0x1F6CD, 0x1F918, - 0x1F91F, + 0x1F91D, + 0x1F91E, + 0x1F920, 0x1F926, 0x1F927, 0x1F930, - 0x1F931, - 0x1F933, 0x1F93A, - 0x1F93C, + 0x1F93D, 0x1F93F, + 0x1F9D1, + 0x1F9DE, 0xE0000, 0xE0020, 0xE0080, @@ -35340,6 +36119,8 @@ static const GCB_enum _Perl_GCB_invmap[] = { /* for EBCDIC 1047 */ GCB_Extend, GCB_Other, GCB_Extend, + GCB_Other, + GCB_Extend, GCB_SpacingMark, GCB_Other, GCB_Extend, @@ -35410,6 +36191,8 @@ static const GCB_enum _Perl_GCB_invmap[] = { /* for EBCDIC 1047 */ GCB_SpacingMark, GCB_Other, GCB_Extend, + GCB_Other, + GCB_Extend, GCB_SpacingMark, GCB_Extend, GCB_Other, @@ -35611,6 +36394,7 @@ static const GCB_enum _Perl_GCB_invmap[] = { /* for EBCDIC 1047 */ GCB_SpacingMark, GCB_Extend, GCB_Other, + GCB_SpacingMark, GCB_Extend, GCB_Other, GCB_Extend, @@ -35630,8 +36414,16 @@ static const GCB_enum _Perl_GCB_invmap[] = { /* for EBCDIC 1047 */ GCB_Other, GCB_E_Base, GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, GCB_E_Base, GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, GCB_E_Base, GCB_Other, GCB_Glue_After_Zwj, @@ -36685,6 +37477,26 @@ static const GCB_enum _Perl_GCB_invmap[] = { /* for EBCDIC 1047 */ GCB_SpacingMark, GCB_Extend, GCB_Other, + GCB_Extend, + GCB_SpacingMark, + GCB_Extend, + GCB_Other, + GCB_Extend, + GCB_SpacingMark, + GCB_Prepend, + GCB_Extend, + GCB_Other, + GCB_Extend, + GCB_Other, + GCB_Extend, + GCB_SpacingMark, + GCB_Extend, + GCB_Other, + GCB_Prepend, + GCB_Extend, + GCB_SpacingMark, + GCB_Extend, + GCB_Other, GCB_SpacingMark, GCB_Extend, GCB_Other, @@ -36705,6 +37517,16 @@ static const GCB_enum _Perl_GCB_invmap[] = { /* for EBCDIC 1047 */ GCB_Other, GCB_Extend, GCB_Other, + GCB_Extend, + GCB_Other, + GCB_Extend, + GCB_Prepend, + GCB_Extend, + GCB_Other, + GCB_Extend, + GCB_Other, + GCB_Extend, + GCB_Other, GCB_SpacingMark, GCB_Other, GCB_Extend, @@ -36756,12 +37578,30 @@ static const GCB_enum _Perl_GCB_invmap[] = { /* for EBCDIC 1047 */ GCB_Other, GCB_Regional_Indicator, GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_E_Base, + GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, GCB_E_Base, GCB_Other, GCB_E_Base, GCB_Other, GCB_E_Base, GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, GCB_E_Modifier, GCB_Other, GCB_E_Base, @@ -36784,16 +37624,30 @@ static const GCB_enum _Perl_GCB_invmap[] = { /* for EBCDIC 1047 */ GCB_Other, GCB_E_Base, GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_E_Base, + GCB_Other, + GCB_E_Base, + GCB_Other, GCB_E_Base, GCB_Other, GCB_E_Base, GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, GCB_E_Base, GCB_Other, GCB_E_Base, GCB_Other, GCB_Glue_After_Zwj, GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, GCB_E_Base, GCB_Other, GCB_E_Base, @@ -36827,7 +37681,7 @@ static const GCB_enum _Perl_GCB_invmap[] = { /* for EBCDIC 1047 */ #if defined(PERL_IN_UTF8_C) static const UV _Perl_IDCont_invlist[] = { /* for EBCDIC 1047 */ - 1391, /* Number of elements */ + 1417, /* Number of elements */ 148565664, /* Version and data structure type */ 1, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -36954,6 +37808,8 @@ static const UV _Perl_IDCont_invlist[] = { /* for EBCDIC 1047 */ 0x82E, 0x840, 0x85C, + 0x860, + 0x86B, 0x8A0, 0x8B5, 0x8B6, @@ -36992,6 +37848,8 @@ static const UV _Perl_IDCont_invlist[] = { /* for EBCDIC 1047 */ 0x9E4, 0x9E6, 0x9F2, + 0x9FC, + 0x9FD, 0xA01, 0xA04, 0xA05, @@ -37051,7 +37909,7 @@ static const UV _Perl_IDCont_invlist[] = { /* for EBCDIC 1047 */ 0xAE6, 0xAF0, 0xAF9, - 0xAFA, + 0xB00, 0xB01, 0xB04, 0xB05, @@ -37166,15 +38024,13 @@ static const UV _Perl_IDCont_invlist[] = { /* for EBCDIC 1047 */ 0xCF0, 0xCF1, 0xCF3, - 0xD01, + 0xD00, 0xD04, 0xD05, 0xD0D, 0xD0E, 0xD11, 0xD12, - 0xD3B, - 0xD3D, 0xD45, 0xD46, 0xD49, @@ -37421,11 +38277,9 @@ static const UV _Perl_IDCont_invlist[] = { /* for EBCDIC 1047 */ 0x1CD0, 0x1CD3, 0x1CD4, - 0x1CF7, - 0x1CF8, 0x1CFA, 0x1D00, - 0x1DF6, + 0x1DFA, 0x1DFB, 0x1F16, 0x1F18, @@ -37565,7 +38419,7 @@ static const UV _Perl_IDCont_invlist[] = { /* for EBCDIC 1047 */ 0x30FC, 0x3100, 0x3105, - 0x312E, + 0x312F, 0x3131, 0x318F, 0x31A0, @@ -37575,7 +38429,7 @@ static const UV _Perl_IDCont_invlist[] = { /* for EBCDIC 1047 */ 0x3400, 0x4DB6, 0x4E00, - 0x9FD6, + 0x9FEB, 0xA000, 0xA48D, 0xA4D0, @@ -37764,7 +38618,7 @@ static const UV _Perl_IDCont_invlist[] = { /* for EBCDIC 1047 */ 0x102E1, 0x10300, 0x10320, - 0x10330, + 0x1032D, 0x1034B, 0x10350, 0x1037B, @@ -37970,6 +38824,14 @@ static const UV _Perl_IDCont_invlist[] = { /* for EBCDIC 1047 */ 0x118EA, 0x118FF, 0x11900, + 0x11A00, + 0x11A3F, + 0x11A47, + 0x11A48, + 0x11A50, + 0x11A84, + 0x11A86, + 0x11A9A, 0x11AC0, 0x11AF9, 0x11C00, @@ -37986,6 +38848,20 @@ static const UV _Perl_IDCont_invlist[] = { /* for EBCDIC 1047 */ 0x11CA8, 0x11CA9, 0x11CB7, + 0x11D00, + 0x11D07, + 0x11D08, + 0x11D0A, + 0x11D0B, + 0x11D37, + 0x11D3A, + 0x11D3B, + 0x11D3C, + 0x11D3E, + 0x11D3F, + 0x11D48, + 0x11D50, + 0x11D5A, 0x12000, 0x1239A, 0x12400, @@ -38023,13 +38899,15 @@ static const UV _Perl_IDCont_invlist[] = { /* for EBCDIC 1047 */ 0x16F8F, 0x16FA0, 0x16FE0, - 0x16FE1, + 0x16FE2, 0x17000, 0x187ED, 0x18800, 0x18AF3, 0x1B000, - 0x1B002, + 0x1B11F, + 0x1B170, + 0x1B2FC, 0x1BC00, 0x1BC6B, 0x1BC70, @@ -38218,6 +39096,8 @@ static const UV _Perl_IDCont_invlist[] = { /* for EBCDIC 1047 */ 0x2B81E, 0x2B820, 0x2CEA2, + 0x2CEB0, + 0x2EBE1, 0x2F800, 0x2FA1E, 0xE0100, @@ -38225,7 +39105,7 @@ static const UV _Perl_IDCont_invlist[] = { /* for EBCDIC 1047 */ }; static const UV _Perl_IDStart_invlist[] = { /* for EBCDIC 1047 */ - 1187, /* Number of elements */ + 1215, /* Number of elements */ 148565664, /* Version and data structure type */ 1, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -38354,6 +39234,8 @@ static const UV _Perl_IDStart_invlist[] = { /* for EBCDIC 1047 */ 0x829, 0x840, 0x859, + 0x860, + 0x86B, 0x8A0, 0x8B5, 0x8B6, @@ -38390,6 +39272,8 @@ static const UV _Perl_IDStart_invlist[] = { /* for EBCDIC 1047 */ 0x9E2, 0x9F0, 0x9F2, + 0x9FC, + 0x9FD, 0xA05, 0xA0B, 0xA0F, @@ -38849,7 +39733,7 @@ static const UV _Perl_IDStart_invlist[] = { /* for EBCDIC 1047 */ 0x30FC, 0x3100, 0x3105, - 0x312E, + 0x312F, 0x3131, 0x318F, 0x31A0, @@ -38859,7 +39743,7 @@ static const UV _Perl_IDStart_invlist[] = { /* for EBCDIC 1047 */ 0x3400, 0x4DB6, 0x4E00, - 0x9FD6, + 0x9FEB, 0xA000, 0xA48D, 0xA4D0, @@ -39054,7 +39938,7 @@ static const UV _Perl_IDStart_invlist[] = { /* for EBCDIC 1047 */ 0x102D1, 0x10300, 0x10320, - 0x10330, + 0x1032D, 0x1034B, 0x10350, 0x10376, @@ -39220,6 +40104,18 @@ static const UV _Perl_IDStart_invlist[] = { /* for EBCDIC 1047 */ 0x118E0, 0x118FF, 0x11900, + 0x11A00, + 0x11A01, + 0x11A0B, + 0x11A33, + 0x11A3A, + 0x11A3B, + 0x11A50, + 0x11A51, + 0x11A5C, + 0x11A84, + 0x11A86, + 0x11A8A, 0x11AC0, 0x11AF9, 0x11C00, @@ -39230,6 +40126,14 @@ static const UV _Perl_IDStart_invlist[] = { /* for EBCDIC 1047 */ 0x11C41, 0x11C72, 0x11C90, + 0x11D00, + 0x11D07, + 0x11D08, + 0x11D0A, + 0x11D0B, + 0x11D31, + 0x11D46, + 0x11D47, 0x12000, 0x1239A, 0x12400, @@ -39261,13 +40165,15 @@ static const UV _Perl_IDStart_invlist[] = { /* for EBCDIC 1047 */ 0x16F93, 0x16FA0, 0x16FE0, - 0x16FE1, + 0x16FE2, 0x17000, 0x187ED, 0x18800, 0x18AF3, 0x1B000, - 0x1B002, + 0x1B11F, + 0x1B170, + 0x1B2FC, 0x1BC00, 0x1BC6B, 0x1BC70, @@ -39414,6 +40320,8 @@ static const UV _Perl_IDStart_invlist[] = { /* for EBCDIC 1047 */ 0x2B81E, 0x2B820, 0x2CEA2, + 0x2CEB0, + 0x2EBE1, 0x2F800, 0x2FA1E }; @@ -39423,7 +40331,7 @@ static const UV _Perl_IDStart_invlist[] = { /* for EBCDIC 1047 */ #if defined(PERL_IN_PERL_C) static const UV _Perl_LB_invlist[] = { /* for EBCDIC 1047 */ - 2279, /* Number of elements */ + 2325, /* Number of elements */ 148565664, /* Version and data structure type */ 0, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -39650,6 +40558,8 @@ static const UV _Perl_LB_invlist[] = { /* for EBCDIC 1047 */ 0xAF0, 0xAF1, 0xAF2, + 0xAFA, + 0xB00, 0xB01, 0xB04, 0xB3C, @@ -39710,8 +40620,10 @@ static const UV _Perl_LB_invlist[] = { /* for EBCDIC 1047 */ 0xCE4, 0xCE6, 0xCF0, - 0xD01, + 0xD00, 0xD04, + 0xD3B, + 0xD3D, 0xD3E, 0xD45, 0xD46, @@ -39942,10 +40854,10 @@ static const UV _Perl_LB_invlist[] = { /* for EBCDIC 1047 */ 0x1CEE, 0x1CF2, 0x1CF5, - 0x1CF8, + 0x1CF7, 0x1CFA, 0x1DC0, - 0x1DF6, + 0x1DFA, 0x1DFB, 0x1E00, 0x1FFD, @@ -40184,7 +41096,7 @@ static const UV _Perl_LB_invlist[] = { /* for EBCDIC 1047 */ 0x2E40, 0x2E42, 0x2E43, - 0x2E45, + 0x2E4A, 0x2E80, 0x2E9A, 0x2E9B, @@ -40279,7 +41191,7 @@ static const UV _Perl_LB_invlist[] = { /* for EBCDIC 1047 */ 0x30FF, 0x3100, 0x3105, - 0x312E, + 0x312F, 0x3131, 0x318F, 0x3190, @@ -41479,6 +42391,26 @@ static const UV _Perl_LB_invlist[] = { /* for EBCDIC 1047 */ 0x1173F, 0x118E0, 0x118EA, + 0x11A01, + 0x11A0B, + 0x11A33, + 0x11A3A, + 0x11A3B, + 0x11A3F, + 0x11A40, + 0x11A41, + 0x11A45, + 0x11A46, + 0x11A47, + 0x11A48, + 0x11A51, + 0x11A5C, + 0x11A8A, + 0x11A9A, + 0x11A9D, + 0x11A9E, + 0x11AA1, + 0x11AA3, 0x11C2F, 0x11C37, 0x11C38, @@ -41494,6 +42426,18 @@ static const UV _Perl_LB_invlist[] = { /* for EBCDIC 1047 */ 0x11CA8, 0x11CA9, 0x11CB7, + 0x11D31, + 0x11D37, + 0x11D3A, + 0x11D3B, + 0x11D3C, + 0x11D3E, + 0x11D3F, + 0x11D46, + 0x11D47, + 0x11D48, + 0x11D50, + 0x11D5A, 0x12470, 0x12475, 0x13258, @@ -41531,13 +42475,15 @@ static const UV _Perl_LB_invlist[] = { /* for EBCDIC 1047 */ 0x16F8F, 0x16F93, 0x16FE0, - 0x16FE1, + 0x16FE2, 0x17000, 0x187ED, 0x18800, 0x18AF3, 0x1B000, - 0x1B002, + 0x1B11F, + 0x1B170, + 0x1B2FC, 0x1BC9D, 0x1BC9F, 0x1BCA0, @@ -41605,10 +42551,12 @@ static const UV _Perl_LB_invlist[] = { /* for EBCDIC 1047 */ 0x1F3B7, 0x1F3BC, 0x1F3BD, - 0x1F3C3, + 0x1F3C2, 0x1F3C5, + 0x1F3C7, + 0x1F3C8, 0x1F3CA, - 0x1F3CC, + 0x1F3CD, 0x1F3FB, 0x1F400, 0x1F442, @@ -41645,7 +42593,7 @@ static const UV _Perl_LB_invlist[] = { /* for EBCDIC 1047 */ 0x1F525, 0x1F532, 0x1F54A, - 0x1F575, + 0x1F574, 0x1F576, 0x1F57A, 0x1F57B, @@ -41671,6 +42619,8 @@ static const UV _Perl_LB_invlist[] = { /* for EBCDIC 1047 */ 0x1F6B7, 0x1F6C0, 0x1F6C1, + 0x1F6CC, + 0x1F6CD, 0x1F700, 0x1F774, 0x1F780, @@ -41685,16 +42635,20 @@ static const UV _Perl_LB_invlist[] = { /* for EBCDIC 1047 */ 0x1F888, 0x1F890, 0x1F8AE, + 0x1F900, + 0x1F90C, 0x1F918, - 0x1F91F, + 0x1F91D, + 0x1F91E, + 0x1F920, 0x1F926, 0x1F927, 0x1F930, - 0x1F931, - 0x1F933, 0x1F93A, - 0x1F93C, + 0x1F93D, 0x1F93F, + 0x1F9D1, + 0x1F9DE, 0x1FFFE, 0x20000, 0x2FFFE, @@ -41994,6 +42948,8 @@ static const LB_enum _Perl_LB_invmap[] = { /* for EBCDIC 1047 */ LB_Alphabetic, LB_Combining_Mark, LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, LB_Numeric, LB_Alphabetic, LB_Combining_Mark, @@ -42052,6 +43008,8 @@ static const LB_enum _Perl_LB_invmap[] = { /* for EBCDIC 1047 */ LB_Alphabetic, LB_Combining_Mark, LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, LB_Numeric, LB_Alphabetic, LB_Postfix_Numeric, @@ -43813,6 +44771,26 @@ static const LB_enum _Perl_LB_invmap[] = { /* for EBCDIC 1047 */ LB_Alphabetic, LB_Combining_Mark, LB_Alphabetic, + LB_Combining_Mark, + LB_Break_Before, + LB_Alphabetic, + LB_Break_After, + LB_Break_Before, + LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, + LB_Combining_Mark, + LB_Break_After, + LB_Alphabetic, + LB_Break_Before, + LB_Break_After, + LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, LB_Break_After, LB_Alphabetic, LB_Numeric, @@ -43824,6 +44802,18 @@ static const LB_enum _Perl_LB_invmap[] = { /* for EBCDIC 1047 */ LB_Alphabetic, LB_Combining_Mark, LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, + LB_Numeric, + LB_Alphabetic, LB_Break_After, LB_Alphabetic, LB_Open_Punctuation, @@ -43868,6 +44858,8 @@ static const LB_enum _Perl_LB_invmap[] = { /* for EBCDIC 1047 */ LB_Alphabetic, LB_Ideographic, LB_Alphabetic, + LB_Ideographic, + LB_Alphabetic, LB_Combining_Mark, LB_Break_After, LB_Combining_Mark, @@ -43939,6 +44931,8 @@ static const LB_enum _Perl_LB_invmap[] = { /* for EBCDIC 1047 */ LB_Ideographic, LB_E_Base, LB_Ideographic, + LB_E_Base, + LB_Ideographic, LB_E_Modifier, LB_Ideographic, LB_E_Base, @@ -44001,6 +44995,8 @@ static const LB_enum _Perl_LB_invmap[] = { /* for EBCDIC 1047 */ LB_Ideographic, LB_E_Base, LB_Ideographic, + LB_E_Base, + LB_Ideographic, LB_Alphabetic, LB_Ideographic, LB_Alphabetic, @@ -44015,6 +45011,10 @@ static const LB_enum _Perl_LB_invmap[] = { /* for EBCDIC 1047 */ LB_Ideographic, LB_Alphabetic, LB_Ideographic, + LB_Alphabetic, + LB_Ideographic, + LB_E_Base, + LB_Ideographic, LB_E_Base, LB_Ideographic, LB_E_Base, @@ -44043,7 +45043,7 @@ static const LB_enum _Perl_LB_invmap[] = { /* for EBCDIC 1047 */ #if defined(PERL_IN_PERL_C) static const UV _Perl_SB_invlist[] = { /* for EBCDIC 1047 */ - 2981, /* Number of elements */ + 3026, /* Number of elements */ 148565664, /* Version and data structure type */ 0, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -44772,6 +45772,8 @@ static const UV _Perl_SB_invlist[] = { /* for EBCDIC 1047 */ 0x840, 0x859, 0x85C, + 0x860, + 0x86B, 0x8A0, 0x8B5, 0x8B6, @@ -44824,6 +45826,8 @@ static const UV _Perl_SB_invlist[] = { /* for EBCDIC 1047 */ 0x9E6, 0x9F0, 0x9F2, + 0x9FC, + 0x9FD, 0xA01, 0xA04, 0xA05, @@ -44890,6 +45894,7 @@ static const UV _Perl_SB_invlist[] = { /* for EBCDIC 1047 */ 0xAF0, 0xAF9, 0xAFA, + 0xB00, 0xB01, 0xB04, 0xB05, @@ -45014,7 +46019,7 @@ static const UV _Perl_SB_invlist[] = { /* for EBCDIC 1047 */ 0xCF0, 0xCF1, 0xCF3, - 0xD01, + 0xD00, 0xD04, 0xD05, 0xD0D, @@ -45355,11 +46360,10 @@ static const UV _Perl_SB_invlist[] = { /* for EBCDIC 1047 */ 0x1CF2, 0x1CF5, 0x1CF7, - 0x1CF8, 0x1CFA, 0x1D00, 0x1DC0, - 0x1DF6, + 0x1DFA, 0x1DFB, 0x1E00, 0x1E01, @@ -45969,7 +46973,7 @@ static const UV _Perl_SB_invlist[] = { /* for EBCDIC 1047 */ 0x30FC, 0x3100, 0x3105, - 0x312E, + 0x312F, 0x3131, 0x318F, 0x31A0, @@ -45979,7 +46983,7 @@ static const UV _Perl_SB_invlist[] = { /* for EBCDIC 1047 */ 0x3400, 0x4DB6, 0x4E00, - 0x9FD6, + 0x9FEB, 0xA000, 0xA48D, 0xA4D0, @@ -46457,7 +47461,7 @@ static const UV _Perl_SB_invlist[] = { /* for EBCDIC 1047 */ 0x102E1, 0x10300, 0x10320, - 0x10330, + 0x1032D, 0x1034B, 0x10350, 0x10376, @@ -46718,6 +47722,26 @@ static const UV _Perl_SB_invlist[] = { /* for EBCDIC 1047 */ 0x118EA, 0x118FF, 0x11900, + 0x11A00, + 0x11A01, + 0x11A0B, + 0x11A33, + 0x11A3A, + 0x11A3B, + 0x11A3F, + 0x11A42, + 0x11A44, + 0x11A47, + 0x11A48, + 0x11A50, + 0x11A51, + 0x11A5C, + 0x11A84, + 0x11A86, + 0x11A8A, + 0x11A9A, + 0x11A9B, + 0x11A9D, 0x11AC0, 0x11AF9, 0x11C00, @@ -46737,6 +47761,23 @@ static const UV _Perl_SB_invlist[] = { /* for EBCDIC 1047 */ 0x11CA8, 0x11CA9, 0x11CB7, + 0x11D00, + 0x11D07, + 0x11D08, + 0x11D0A, + 0x11D0B, + 0x11D31, + 0x11D37, + 0x11D3A, + 0x11D3B, + 0x11D3C, + 0x11D3E, + 0x11D3F, + 0x11D46, + 0x11D47, + 0x11D48, + 0x11D50, + 0x11D5A, 0x12000, 0x1239A, 0x12400, @@ -46782,13 +47823,15 @@ static const UV _Perl_SB_invlist[] = { /* for EBCDIC 1047 */ 0x16F93, 0x16FA0, 0x16FE0, - 0x16FE1, + 0x16FE2, 0x17000, 0x187ED, 0x18800, 0x18AF3, 0x1B000, - 0x1B002, + 0x1B11F, + 0x1B170, + 0x1B2FC, 0x1BC00, 0x1BC6B, 0x1BC70, @@ -47020,6 +48063,8 @@ static const UV _Perl_SB_invlist[] = { /* for EBCDIC 1047 */ 0x2B81E, 0x2B820, 0x2CEA2, + 0x2CEB0, + 0x2EBE1, 0x2F800, 0x2FA1E, 0xE0001, @@ -47785,6 +48830,8 @@ static const SB_enum _Perl_SB_invmap[] = { /* for EBCDIC 1047 */ SB_Other, SB_OLetter, SB_Other, + SB_OLetter, + SB_Other, SB_Extend, SB_Format, SB_Extend, @@ -47833,6 +48880,8 @@ static const SB_enum _Perl_SB_invmap[] = { /* for EBCDIC 1047 */ SB_Numeric, SB_OLetter, SB_Other, + SB_OLetter, + SB_Other, SB_Extend, SB_Other, SB_OLetter, @@ -47898,6 +48947,7 @@ static const SB_enum _Perl_SB_invmap[] = { /* for EBCDIC 1047 */ SB_Numeric, SB_Other, SB_OLetter, + SB_Extend, SB_Other, SB_Extend, SB_Other, @@ -48030,7 +49080,7 @@ static const SB_enum _Perl_SB_invmap[] = { /* for EBCDIC 1047 */ SB_OLetter, SB_Other, SB_OLetter, - SB_Other, + SB_Extend, SB_OLetter, SB_Extend, SB_Other, @@ -48363,7 +49413,6 @@ static const SB_enum _Perl_SB_invmap[] = { /* for EBCDIC 1047 */ SB_OLetter, SB_Extend, SB_OLetter, - SB_Other, SB_Extend, SB_Other, SB_Lower, @@ -49728,6 +50777,26 @@ static const SB_enum _Perl_SB_invmap[] = { /* for EBCDIC 1047 */ SB_OLetter, SB_Other, SB_OLetter, + SB_Extend, + SB_OLetter, + SB_Extend, + SB_OLetter, + SB_Extend, + SB_Other, + SB_STerm, + SB_Other, + SB_Extend, + SB_Other, + SB_OLetter, + SB_Extend, + SB_OLetter, + SB_Other, + SB_OLetter, + SB_Extend, + SB_Other, + SB_STerm, + SB_Other, + SB_OLetter, SB_Other, SB_OLetter, SB_Other, @@ -49751,6 +50820,23 @@ static const SB_enum _Perl_SB_invmap[] = { /* for EBCDIC 1047 */ SB_OLetter, SB_Other, SB_OLetter, + SB_Extend, + SB_Other, + SB_Extend, + SB_Other, + SB_Extend, + SB_Other, + SB_Extend, + SB_OLetter, + SB_Extend, + SB_Other, + SB_Numeric, + SB_Other, + SB_OLetter, + SB_Other, + SB_OLetter, + SB_Other, + SB_OLetter, SB_Other, SB_OLetter, SB_Other, @@ -49806,6 +50892,8 @@ static const SB_enum _Perl_SB_invmap[] = { /* for EBCDIC 1047 */ SB_Other, SB_OLetter, SB_Other, + SB_OLetter, + SB_Other, SB_Extend, SB_STerm, SB_Format, @@ -50031,6 +51119,8 @@ static const SB_enum _Perl_SB_invmap[] = { /* for EBCDIC 1047 */ SB_Other, SB_OLetter, SB_Other, + SB_OLetter, + SB_Other, SB_Format, SB_Other, SB_Extend, @@ -50044,7 +51134,7 @@ static const SB_enum _Perl_SB_invmap[] = { /* for EBCDIC 1047 */ #if defined(PERL_IN_PERL_C) static const UV _Perl_WB_invlist[] = { /* for EBCDIC 1047 */ - 1680, /* Number of elements */ + 1744, /* Number of elements */ 148565664, /* Version and data structure type */ 0, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -50116,17 +51206,10 @@ static const UV _Perl_WB_invlist[] = { /* for EBCDIC 1047 */ 0xFB, 0xFF, 0x100, - 0x2C2, - 0x2C6, - 0x2D2, - 0x2D7, 0x2D8, - 0x2E0, + 0x2DE, 0x2E5, 0x2EC, - 0x2ED, - 0x2EE, - 0x2EF, 0x300, 0x370, 0x375, @@ -50240,6 +51323,8 @@ static const UV _Perl_WB_invlist[] = { /* for EBCDIC 1047 */ 0x840, 0x859, 0x85C, + 0x860, + 0x86B, 0x8A0, 0x8B5, 0x8B6, @@ -50292,6 +51377,8 @@ static const UV _Perl_WB_invlist[] = { /* for EBCDIC 1047 */ 0x9E6, 0x9F0, 0x9F2, + 0x9FC, + 0x9FD, 0xA01, 0xA04, 0xA05, @@ -50358,6 +51445,7 @@ static const UV _Perl_WB_invlist[] = { /* for EBCDIC 1047 */ 0xAF0, 0xAF9, 0xAFA, + 0xB00, 0xB01, 0xB04, 0xB05, @@ -50482,7 +51570,7 @@ static const UV _Perl_WB_invlist[] = { /* for EBCDIC 1047 */ 0xCF0, 0xCF1, 0xCF3, - 0xD01, + 0xD00, 0xD04, 0xD05, 0xD0D, @@ -50754,11 +51842,10 @@ static const UV _Perl_WB_invlist[] = { /* for EBCDIC 1047 */ 0x1CF2, 0x1CF5, 0x1CF7, - 0x1CF8, 0x1CFA, 0x1D00, 0x1DC0, - 0x1DF6, + 0x1DFA, 0x1DFB, 0x1E00, 0x1F16, @@ -50864,8 +51951,16 @@ static const UV _Perl_WB_invlist[] = { /* for EBCDIC 1047 */ 0x24EA, 0x261D, 0x261E, + 0x2640, + 0x2641, + 0x2642, + 0x2643, + 0x2695, + 0x2697, 0x26F9, 0x26FA, + 0x2708, + 0x2709, 0x270A, 0x270E, 0x2764, @@ -50931,7 +52026,7 @@ static const UV _Perl_WB_invlist[] = { /* for EBCDIC 1047 */ 0x30FC, 0x3100, 0x3105, - 0x312E, + 0x312F, 0x3131, 0x318F, 0x31A0, @@ -50963,10 +52058,6 @@ static const UV _Perl_WB_invlist[] = { /* for EBCDIC 1047 */ 0xA6F0, 0xA6F2, 0xA717, - 0xA720, - 0xA722, - 0xA789, - 0xA78B, 0xA7AF, 0xA7B0, 0xA7B8, @@ -51053,8 +52144,6 @@ static const UV _Perl_WB_invlist[] = { /* for EBCDIC 1047 */ 0xAB28, 0xAB2F, 0xAB30, - 0xAB5B, - 0xAB5C, 0xAB66, 0xAB70, 0xABE3, @@ -51177,7 +52266,7 @@ static const UV _Perl_WB_invlist[] = { /* for EBCDIC 1047 */ 0x102E1, 0x10300, 0x10320, - 0x10330, + 0x1032D, 0x1034B, 0x10350, 0x10376, @@ -51412,6 +52501,22 @@ static const UV _Perl_WB_invlist[] = { /* for EBCDIC 1047 */ 0x118EA, 0x118FF, 0x11900, + 0x11A00, + 0x11A01, + 0x11A0B, + 0x11A33, + 0x11A3A, + 0x11A3B, + 0x11A3F, + 0x11A47, + 0x11A48, + 0x11A50, + 0x11A51, + 0x11A5C, + 0x11A84, + 0x11A86, + 0x11A8A, + 0x11A9A, 0x11AC0, 0x11AF9, 0x11C00, @@ -51430,6 +52535,23 @@ static const UV _Perl_WB_invlist[] = { /* for EBCDIC 1047 */ 0x11CA8, 0x11CA9, 0x11CB7, + 0x11D00, + 0x11D07, + 0x11D08, + 0x11D0A, + 0x11D0B, + 0x11D31, + 0x11D37, + 0x11D3A, + 0x11D3B, + 0x11D3C, + 0x11D3E, + 0x11D3F, + 0x11D46, + 0x11D47, + 0x11D48, + 0x11D50, + 0x11D5A, 0x12000, 0x1239A, 0x12400, @@ -51470,7 +52592,7 @@ static const UV _Perl_WB_invlist[] = { /* for EBCDIC 1047 */ 0x16F93, 0x16FA0, 0x16FE0, - 0x16FE1, + 0x16FE2, 0x1B000, 0x1B001, 0x1BC00, @@ -51664,12 +52786,30 @@ static const UV _Perl_WB_invlist[] = { /* for EBCDIC 1047 */ 0x1F18A, 0x1F1E6, 0x1F200, + 0x1F308, + 0x1F309, + 0x1F33E, + 0x1F33F, + 0x1F373, + 0x1F374, 0x1F385, 0x1F386, - 0x1F3C3, + 0x1F393, + 0x1F394, + 0x1F3A4, + 0x1F3A5, + 0x1F3A8, + 0x1F3A9, + 0x1F3C2, 0x1F3C5, + 0x1F3C7, + 0x1F3C8, 0x1F3CA, - 0x1F3CC, + 0x1F3CD, + 0x1F3EB, + 0x1F3EC, + 0x1F3ED, + 0x1F3EE, 0x1F3FB, 0x1F400, 0x1F442, @@ -51692,7 +52832,13 @@ static const UV _Perl_WB_invlist[] = { /* for EBCDIC 1047 */ 0x1F48C, 0x1F4AA, 0x1F4AB, - 0x1F575, + 0x1F4BB, + 0x1F4BD, + 0x1F527, + 0x1F528, + 0x1F52C, + 0x1F52D, + 0x1F574, 0x1F576, 0x1F57A, 0x1F57B, @@ -51706,22 +52852,30 @@ static const UV _Perl_WB_invlist[] = { /* for EBCDIC 1047 */ 0x1F648, 0x1F64B, 0x1F650, + 0x1F680, + 0x1F681, + 0x1F692, + 0x1F693, 0x1F6A3, 0x1F6A4, 0x1F6B4, 0x1F6B7, 0x1F6C0, 0x1F6C1, + 0x1F6CC, + 0x1F6CD, 0x1F918, - 0x1F91F, + 0x1F91D, + 0x1F91E, + 0x1F920, 0x1F926, 0x1F927, 0x1F930, - 0x1F931, - 0x1F933, 0x1F93A, - 0x1F93C, + 0x1F93D, 0x1F93F, + 0x1F9D1, + 0x1F9DE, 0xE0001, 0xE0002, 0xE0020, @@ -51836,14 +52990,7 @@ static const WB_enum _Perl_WB_invmap[] = { /* for EBCDIC 1047 */ WB_Other, WB_ALetter, WB_Other, - WB_MidLetter, - WB_Other, - WB_ALetter, - WB_Other, WB_ALetter, - WB_Other, - WB_ALetter, - WB_Other, WB_Extend, WB_ALetter, WB_Other, @@ -51961,6 +53108,8 @@ static const WB_enum _Perl_WB_invmap[] = { /* for EBCDIC 1047 */ WB_Other, WB_ALetter, WB_Other, + WB_ALetter, + WB_Other, WB_Extend, WB_Format, WB_Extend, @@ -52009,6 +53158,8 @@ static const WB_enum _Perl_WB_invmap[] = { /* for EBCDIC 1047 */ WB_Numeric, WB_ALetter, WB_Other, + WB_ALetter, + WB_Other, WB_Extend, WB_Other, WB_ALetter, @@ -52074,6 +53225,7 @@ static const WB_enum _Perl_WB_invmap[] = { /* for EBCDIC 1047 */ WB_Numeric, WB_Other, WB_ALetter, + WB_Extend, WB_Other, WB_Extend, WB_Other, @@ -52206,7 +53358,7 @@ static const WB_enum _Perl_WB_invmap[] = { /* for EBCDIC 1047 */ WB_ALetter, WB_Other, WB_ALetter, - WB_Other, + WB_Extend, WB_ALetter, WB_Extend, WB_Other, @@ -52470,7 +53622,6 @@ static const WB_enum _Perl_WB_invmap[] = { /* for EBCDIC 1047 */ WB_ALetter, WB_Extend, WB_ALetter, - WB_Other, WB_Extend, WB_Other, WB_ALetter, @@ -52581,8 +53732,16 @@ static const WB_enum _Perl_WB_invmap[] = { /* for EBCDIC 1047 */ WB_Other, WB_E_Base, WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_Glue_After_Zwj, + WB_Other, WB_E_Base, WB_Other, + WB_Glue_After_Zwj, + WB_Other, WB_E_Base, WB_Other, WB_Glue_After_Zwj, @@ -52684,10 +53843,6 @@ static const WB_enum _Perl_WB_invmap[] = { /* for EBCDIC 1047 */ WB_ALetter, WB_Other, WB_ALetter, - WB_Other, - WB_ALetter, - WB_Other, - WB_ALetter, WB_Extend, WB_ALetter, WB_Extend, @@ -52772,8 +53927,6 @@ static const WB_enum _Perl_WB_invmap[] = { /* for EBCDIC 1047 */ WB_ALetter, WB_Other, WB_ALetter, - WB_Other, - WB_ALetter, WB_Extend, WB_Other, WB_Extend, @@ -53130,6 +54283,22 @@ static const WB_enum _Perl_WB_invmap[] = { /* for EBCDIC 1047 */ WB_ALetter, WB_Other, WB_ALetter, + WB_Extend, + WB_ALetter, + WB_Extend, + WB_ALetter, + WB_Extend, + WB_Other, + WB_Extend, + WB_Other, + WB_ALetter, + WB_Extend, + WB_ALetter, + WB_Other, + WB_ALetter, + WB_Extend, + WB_Other, + WB_ALetter, WB_Other, WB_ALetter, WB_Other, @@ -53152,6 +54321,23 @@ static const WB_enum _Perl_WB_invmap[] = { /* for EBCDIC 1047 */ WB_ALetter, WB_Other, WB_ALetter, + WB_Extend, + WB_Other, + WB_Extend, + WB_Other, + WB_Extend, + WB_Other, + WB_Extend, + WB_ALetter, + WB_Extend, + WB_Other, + WB_Numeric, + WB_Other, + WB_ALetter, + WB_Other, + WB_ALetter, + WB_Other, + WB_ALetter, WB_Other, WB_ALetter, WB_Other, @@ -53381,12 +54567,30 @@ static const WB_enum _Perl_WB_invmap[] = { /* for EBCDIC 1047 */ WB_Other, WB_Regional_Indicator, WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_E_Base, + WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_Glue_After_Zwj, + WB_Other, WB_E_Base, WB_Other, WB_E_Base, WB_Other, WB_E_Base, WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_Glue_After_Zwj, + WB_Other, WB_E_Modifier, WB_Other, WB_E_Base, @@ -53409,6 +54613,12 @@ static const WB_enum _Perl_WB_invmap[] = { /* for EBCDIC 1047 */ WB_Other, WB_E_Base, WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_Glue_After_Zwj, + WB_Other, WB_E_Base, WB_Other, WB_E_Base, @@ -53423,6 +54633,14 @@ static const WB_enum _Perl_WB_invmap[] = { /* for EBCDIC 1047 */ WB_Other, WB_E_Base, WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_E_Base, + WB_Other, + WB_E_Base, + WB_Other, WB_E_Base, WB_Other, WB_E_Base, @@ -53564,7 +54782,7 @@ static const UV XPerlSpace_invlist[] = { /* for EBCDIC 1047 */ }; static const UV XPosixAlnum_invlist[] = { /* for EBCDIC 1047 */ - 1381, /* Number of elements */ + 1415, /* Number of elements */ 148565664, /* Version and data structure type */ 1, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -53695,6 +54913,8 @@ static const UV XPosixAlnum_invlist[] = { /* for EBCDIC 1047 */ 0x82D, 0x840, 0x859, + 0x860, + 0x86B, 0x8A0, 0x8B5, 0x8B6, @@ -53743,6 +54963,8 @@ static const UV XPosixAlnum_invlist[] = { /* for EBCDIC 1047 */ 0x9E4, 0x9E6, 0x9F2, + 0x9FC, + 0x9FD, 0xA01, 0xA04, 0xA05, @@ -53800,7 +55022,7 @@ static const UV XPosixAlnum_invlist[] = { /* for EBCDIC 1047 */ 0xAE6, 0xAF0, 0xAF9, - 0xAFA, + 0xAFD, 0xB01, 0xB04, 0xB05, @@ -53915,7 +55137,7 @@ static const UV XPosixAlnum_invlist[] = { /* for EBCDIC 1047 */ 0xCF0, 0xCF1, 0xCF3, - 0xD01, + 0xD00, 0xD04, 0xD05, 0xD0D, @@ -54320,7 +55542,7 @@ static const UV XPosixAlnum_invlist[] = { /* for EBCDIC 1047 */ 0x30FC, 0x3100, 0x3105, - 0x312E, + 0x312F, 0x3131, 0x318F, 0x31A0, @@ -54330,7 +55552,7 @@ static const UV XPosixAlnum_invlist[] = { /* for EBCDIC 1047 */ 0x3400, 0x4DB6, 0x4E00, - 0x9FD6, + 0x9FEB, 0xA000, 0xA48D, 0xA4D0, @@ -54509,7 +55731,7 @@ static const UV XPosixAlnum_invlist[] = { /* for EBCDIC 1047 */ 0x102D1, 0x10300, 0x10320, - 0x10330, + 0x1032D, 0x1034B, 0x10350, 0x1037B, @@ -54717,6 +55939,14 @@ static const UV XPosixAlnum_invlist[] = { /* for EBCDIC 1047 */ 0x118EA, 0x118FF, 0x11900, + 0x11A00, + 0x11A33, + 0x11A35, + 0x11A3F, + 0x11A50, + 0x11A84, + 0x11A86, + 0x11A98, 0x11AC0, 0x11AF9, 0x11C00, @@ -54735,6 +55965,24 @@ static const UV XPosixAlnum_invlist[] = { /* for EBCDIC 1047 */ 0x11CA8, 0x11CA9, 0x11CB7, + 0x11D00, + 0x11D07, + 0x11D08, + 0x11D0A, + 0x11D0B, + 0x11D37, + 0x11D3A, + 0x11D3B, + 0x11D3C, + 0x11D3E, + 0x11D3F, + 0x11D42, + 0x11D43, + 0x11D44, + 0x11D46, + 0x11D48, + 0x11D50, + 0x11D5A, 0x12000, 0x1239A, 0x12400, @@ -54770,13 +56018,15 @@ static const UV XPosixAlnum_invlist[] = { /* for EBCDIC 1047 */ 0x16F93, 0x16FA0, 0x16FE0, - 0x16FE1, + 0x16FE2, 0x17000, 0x187ED, 0x18800, 0x18AF3, 0x1B000, - 0x1B002, + 0x1B11F, + 0x1B170, + 0x1B2FC, 0x1BC00, 0x1BC6B, 0x1BC70, @@ -54947,12 +56197,14 @@ static const UV XPosixAlnum_invlist[] = { /* for EBCDIC 1047 */ 0x2B81E, 0x2B820, 0x2CEA2, + 0x2CEB0, + 0x2EBE1, 0x2F800, 0x2FA1E }; static const UV XPosixAlpha_invlist[] = { /* for EBCDIC 1047 */ - 1315, /* Number of elements */ + 1347, /* Number of elements */ 148565664, /* Version and data structure type */ 1, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -55085,6 +56337,8 @@ static const UV XPosixAlpha_invlist[] = { /* for EBCDIC 1047 */ 0x82D, 0x840, 0x859, + 0x860, + 0x86B, 0x8A0, 0x8B5, 0x8B6, @@ -55131,6 +56385,8 @@ static const UV XPosixAlpha_invlist[] = { /* for EBCDIC 1047 */ 0x9E4, 0x9F0, 0x9F2, + 0x9FC, + 0x9FD, 0xA01, 0xA04, 0xA05, @@ -55186,7 +56442,7 @@ static const UV XPosixAlpha_invlist[] = { /* for EBCDIC 1047 */ 0xAE0, 0xAE4, 0xAF9, - 0xAFA, + 0xAFD, 0xB01, 0xB04, 0xB05, @@ -55293,7 +56549,7 @@ static const UV XPosixAlpha_invlist[] = { /* for EBCDIC 1047 */ 0xCE4, 0xCF1, 0xCF3, - 0xD01, + 0xD00, 0xD04, 0xD05, 0xD0D, @@ -55676,7 +56932,7 @@ static const UV XPosixAlpha_invlist[] = { /* for EBCDIC 1047 */ 0x30FC, 0x3100, 0x3105, - 0x312E, + 0x312F, 0x3131, 0x318F, 0x31A0, @@ -55686,7 +56942,7 @@ static const UV XPosixAlpha_invlist[] = { /* for EBCDIC 1047 */ 0x3400, 0x4DB6, 0x4E00, - 0x9FD6, + 0x9FEB, 0xA000, 0xA48D, 0xA4D0, @@ -55861,7 +57117,7 @@ static const UV XPosixAlpha_invlist[] = { /* for EBCDIC 1047 */ 0x102D1, 0x10300, 0x10320, - 0x10330, + 0x1032D, 0x1034B, 0x10350, 0x1037B, @@ -56049,6 +57305,14 @@ static const UV XPosixAlpha_invlist[] = { /* for EBCDIC 1047 */ 0x118E0, 0x118FF, 0x11900, + 0x11A00, + 0x11A33, + 0x11A35, + 0x11A3F, + 0x11A50, + 0x11A84, + 0x11A86, + 0x11A98, 0x11AC0, 0x11AF9, 0x11C00, @@ -56065,6 +57329,22 @@ static const UV XPosixAlpha_invlist[] = { /* for EBCDIC 1047 */ 0x11CA8, 0x11CA9, 0x11CB7, + 0x11D00, + 0x11D07, + 0x11D08, + 0x11D0A, + 0x11D0B, + 0x11D37, + 0x11D3A, + 0x11D3B, + 0x11D3C, + 0x11D3E, + 0x11D3F, + 0x11D42, + 0x11D43, + 0x11D44, + 0x11D46, + 0x11D48, 0x12000, 0x1239A, 0x12400, @@ -56096,13 +57376,15 @@ static const UV XPosixAlpha_invlist[] = { /* for EBCDIC 1047 */ 0x16F93, 0x16FA0, 0x16FE0, - 0x16FE1, + 0x16FE2, 0x17000, 0x187ED, 0x18800, 0x18AF3, 0x1B000, - 0x1B002, + 0x1B11F, + 0x1B170, + 0x1B2FC, 0x1BC00, 0x1BC6B, 0x1BC70, @@ -56269,6 +57551,8 @@ static const UV XPosixAlpha_invlist[] = { /* for EBCDIC 1047 */ 0x2B81E, 0x2B820, 0x2CEA2, + 0x2CEB0, + 0x2EBE1, 0x2F800, 0x2FA1E }; @@ -56307,7 +57591,7 @@ static const UV XPosixCntrl_invlist[] = { /* for EBCDIC 1047 */ }; static const UV XPosixDigit_invlist[] = { /* for EBCDIC 1047 */ - 109, /* Number of elements */ + 111, /* Number of elements */ 148565664, /* Version and data structure type */ 1, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -56412,6 +57696,8 @@ static const UV XPosixDigit_invlist[] = { /* for EBCDIC 1047 */ 0x118EA, 0x11C50, 0x11C5A, + 0x11D50, + 0x11D5A, 0x16A60, 0x16A6A, 0x16B50, @@ -56423,7 +57709,7 @@ static const UV XPosixDigit_invlist[] = { /* for EBCDIC 1047 */ }; static const UV XPosixGraph_invlist[] = { /* for EBCDIC 1047 */ - 1287, /* Number of elements */ + 1309, /* Number of elements */ 148565664, /* Version and data structure type */ 1, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -56476,6 +57762,8 @@ static const UV XPosixGraph_invlist[] = { /* for EBCDIC 1047 */ 0x85C, 0x85E, 0x85F, + 0x860, + 0x86B, 0x8A0, 0x8B5, 0x8B6, @@ -56507,7 +57795,7 @@ static const UV XPosixGraph_invlist[] = { /* for EBCDIC 1047 */ 0x9DF, 0x9E4, 0x9E6, - 0x9FC, + 0x9FE, 0xA01, 0xA04, 0xA05, @@ -56567,7 +57855,7 @@ static const UV XPosixGraph_invlist[] = { /* for EBCDIC 1047 */ 0xAE6, 0xAF2, 0xAF9, - 0xAFA, + 0xB00, 0xB01, 0xB04, 0xB05, @@ -56680,15 +57968,13 @@ static const UV XPosixGraph_invlist[] = { /* for EBCDIC 1047 */ 0xCF0, 0xCF1, 0xCF3, - 0xD01, + 0xD00, 0xD04, 0xD05, 0xD0D, 0xD0E, 0xD11, 0xD12, - 0xD3B, - 0xD3D, 0xD45, 0xD46, 0xD49, @@ -56903,11 +58189,9 @@ static const UV XPosixGraph_invlist[] = { /* for EBCDIC 1047 */ 0x1CC0, 0x1CC8, 0x1CD0, - 0x1CF7, - 0x1CF8, 0x1CFA, 0x1D00, - 0x1DF6, + 0x1DFA, 0x1DFB, 0x1F16, 0x1F18, @@ -56955,14 +58239,12 @@ static const UV XPosixGraph_invlist[] = { /* for EBCDIC 1047 */ 0x2090, 0x209D, 0x20A0, - 0x20BF, + 0x20C0, 0x20D0, 0x20F1, 0x2100, 0x218C, 0x2190, - 0x23FF, - 0x2400, 0x2427, 0x2440, 0x244B, @@ -56975,7 +58257,7 @@ static const UV XPosixGraph_invlist[] = { /* for EBCDIC 1047 */ 0x2BBD, 0x2BC9, 0x2BCA, - 0x2BD2, + 0x2BD3, 0x2BEC, 0x2BF0, 0x2C00, @@ -57013,7 +58295,7 @@ static const UV XPosixGraph_invlist[] = { /* for EBCDIC 1047 */ 0x2DD8, 0x2DDF, 0x2DE0, - 0x2E45, + 0x2E4A, 0x2E80, 0x2E9A, 0x2E9B, @@ -57029,7 +58311,7 @@ static const UV XPosixGraph_invlist[] = { /* for EBCDIC 1047 */ 0x3099, 0x3100, 0x3105, - 0x312E, + 0x312F, 0x3131, 0x318F, 0x3190, @@ -57043,7 +58325,7 @@ static const UV XPosixGraph_invlist[] = { /* for EBCDIC 1047 */ 0x3300, 0x4DB6, 0x4DC0, - 0x9FD6, + 0x9FEB, 0xA000, 0xA48D, 0xA490, @@ -57202,7 +58484,7 @@ static const UV XPosixGraph_invlist[] = { /* for EBCDIC 1047 */ 0x102FC, 0x10300, 0x10324, - 0x10330, + 0x1032D, 0x1034B, 0x10350, 0x1037B, @@ -57410,6 +58692,14 @@ static const UV XPosixGraph_invlist[] = { /* for EBCDIC 1047 */ 0x118F3, 0x118FF, 0x11900, + 0x11A00, + 0x11A48, + 0x11A50, + 0x11A84, + 0x11A86, + 0x11A9D, + 0x11A9E, + 0x11AA3, 0x11AC0, 0x11AF9, 0x11C00, @@ -57426,6 +58716,20 @@ static const UV XPosixGraph_invlist[] = { /* for EBCDIC 1047 */ 0x11CA8, 0x11CA9, 0x11CB7, + 0x11D00, + 0x11D07, + 0x11D08, + 0x11D0A, + 0x11D0B, + 0x11D37, + 0x11D3A, + 0x11D3B, + 0x11D3C, + 0x11D3E, + 0x11D3F, + 0x11D48, + 0x11D50, + 0x11D5A, 0x12000, 0x1239A, 0x12400, @@ -57467,13 +58771,15 @@ static const UV XPosixGraph_invlist[] = { /* for EBCDIC 1047 */ 0x16F8F, 0x16FA0, 0x16FE0, - 0x16FE1, + 0x16FE2, 0x17000, 0x187ED, 0x18800, 0x18AF3, 0x1B000, - 0x1B002, + 0x1B11F, + 0x1B170, + 0x1B2FC, 0x1BC00, 0x1BC6B, 0x1BC70, @@ -57658,12 +58964,14 @@ static const UV XPosixGraph_invlist[] = { /* for EBCDIC 1047 */ 0x1F249, 0x1F250, 0x1F252, + 0x1F260, + 0x1F266, 0x1F300, - 0x1F6D3, + 0x1F6D5, 0x1F6E0, 0x1F6ED, 0x1F6F0, - 0x1F6F7, + 0x1F6F9, 0x1F700, 0x1F774, 0x1F780, @@ -57678,22 +58986,20 @@ static const UV XPosixGraph_invlist[] = { /* for EBCDIC 1047 */ 0x1F888, 0x1F890, 0x1F8AE, + 0x1F900, + 0x1F90C, 0x1F910, - 0x1F91F, - 0x1F920, - 0x1F928, - 0x1F930, - 0x1F931, - 0x1F933, 0x1F93F, 0x1F940, - 0x1F94C, + 0x1F94D, 0x1F950, - 0x1F95F, + 0x1F96C, 0x1F980, - 0x1F992, + 0x1F998, 0x1F9C0, 0x1F9C1, + 0x1F9D0, + 0x1F9E7, 0x20000, 0x2A6D7, 0x2A700, @@ -57702,6 +59008,8 @@ static const UV XPosixGraph_invlist[] = { /* for EBCDIC 1047 */ 0x2B81E, 0x2B820, 0x2CEA2, + 0x2CEB0, + 0x2EBE1, 0x2F800, 0x2FA1E, 0xE0001, @@ -59013,7 +60321,7 @@ static const UV XPosixLower_invlist[] = { /* for EBCDIC 1047 */ }; static const UV XPosixPrint_invlist[] = { /* for EBCDIC 1047 */ - 1281, /* Number of elements */ + 1303, /* Number of elements */ 148565664, /* Version and data structure type */ 1, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -59066,6 +60374,8 @@ static const UV XPosixPrint_invlist[] = { /* for EBCDIC 1047 */ 0x85C, 0x85E, 0x85F, + 0x860, + 0x86B, 0x8A0, 0x8B5, 0x8B6, @@ -59097,7 +60407,7 @@ static const UV XPosixPrint_invlist[] = { /* for EBCDIC 1047 */ 0x9DF, 0x9E4, 0x9E6, - 0x9FC, + 0x9FE, 0xA01, 0xA04, 0xA05, @@ -59157,7 +60467,7 @@ static const UV XPosixPrint_invlist[] = { /* for EBCDIC 1047 */ 0xAE6, 0xAF2, 0xAF9, - 0xAFA, + 0xB00, 0xB01, 0xB04, 0xB05, @@ -59270,15 +60580,13 @@ static const UV XPosixPrint_invlist[] = { /* for EBCDIC 1047 */ 0xCF0, 0xCF1, 0xCF3, - 0xD01, + 0xD00, 0xD04, 0xD05, 0xD0D, 0xD0E, 0xD11, 0xD12, - 0xD3B, - 0xD3D, 0xD45, 0xD46, 0xD49, @@ -59491,11 +60799,9 @@ static const UV XPosixPrint_invlist[] = { /* for EBCDIC 1047 */ 0x1CC0, 0x1CC8, 0x1CD0, - 0x1CF7, - 0x1CF8, 0x1CFA, 0x1D00, - 0x1DF6, + 0x1DFA, 0x1DFB, 0x1F16, 0x1F18, @@ -59539,14 +60845,12 @@ static const UV XPosixPrint_invlist[] = { /* for EBCDIC 1047 */ 0x2090, 0x209D, 0x20A0, - 0x20BF, + 0x20C0, 0x20D0, 0x20F1, 0x2100, 0x218C, 0x2190, - 0x23FF, - 0x2400, 0x2427, 0x2440, 0x244B, @@ -59559,7 +60863,7 @@ static const UV XPosixPrint_invlist[] = { /* for EBCDIC 1047 */ 0x2BBD, 0x2BC9, 0x2BCA, - 0x2BD2, + 0x2BD3, 0x2BEC, 0x2BF0, 0x2C00, @@ -59597,7 +60901,7 @@ static const UV XPosixPrint_invlist[] = { /* for EBCDIC 1047 */ 0x2DD8, 0x2DDF, 0x2DE0, - 0x2E45, + 0x2E4A, 0x2E80, 0x2E9A, 0x2E9B, @@ -59613,7 +60917,7 @@ static const UV XPosixPrint_invlist[] = { /* for EBCDIC 1047 */ 0x3099, 0x3100, 0x3105, - 0x312E, + 0x312F, 0x3131, 0x318F, 0x3190, @@ -59627,7 +60931,7 @@ static const UV XPosixPrint_invlist[] = { /* for EBCDIC 1047 */ 0x3300, 0x4DB6, 0x4DC0, - 0x9FD6, + 0x9FEB, 0xA000, 0xA48D, 0xA490, @@ -59786,7 +61090,7 @@ static const UV XPosixPrint_invlist[] = { /* for EBCDIC 1047 */ 0x102FC, 0x10300, 0x10324, - 0x10330, + 0x1032D, 0x1034B, 0x10350, 0x1037B, @@ -59994,6 +61298,14 @@ static const UV XPosixPrint_invlist[] = { /* for EBCDIC 1047 */ 0x118F3, 0x118FF, 0x11900, + 0x11A00, + 0x11A48, + 0x11A50, + 0x11A84, + 0x11A86, + 0x11A9D, + 0x11A9E, + 0x11AA3, 0x11AC0, 0x11AF9, 0x11C00, @@ -60010,6 +61322,20 @@ static const UV XPosixPrint_invlist[] = { /* for EBCDIC 1047 */ 0x11CA8, 0x11CA9, 0x11CB7, + 0x11D00, + 0x11D07, + 0x11D08, + 0x11D0A, + 0x11D0B, + 0x11D37, + 0x11D3A, + 0x11D3B, + 0x11D3C, + 0x11D3E, + 0x11D3F, + 0x11D48, + 0x11D50, + 0x11D5A, 0x12000, 0x1239A, 0x12400, @@ -60051,13 +61377,15 @@ static const UV XPosixPrint_invlist[] = { /* for EBCDIC 1047 */ 0x16F8F, 0x16FA0, 0x16FE0, - 0x16FE1, + 0x16FE2, 0x17000, 0x187ED, 0x18800, 0x18AF3, 0x1B000, - 0x1B002, + 0x1B11F, + 0x1B170, + 0x1B2FC, 0x1BC00, 0x1BC6B, 0x1BC70, @@ -60242,12 +61570,14 @@ static const UV XPosixPrint_invlist[] = { /* for EBCDIC 1047 */ 0x1F249, 0x1F250, 0x1F252, + 0x1F260, + 0x1F266, 0x1F300, - 0x1F6D3, + 0x1F6D5, 0x1F6E0, 0x1F6ED, 0x1F6F0, - 0x1F6F7, + 0x1F6F9, 0x1F700, 0x1F774, 0x1F780, @@ -60262,22 +61592,20 @@ static const UV XPosixPrint_invlist[] = { /* for EBCDIC 1047 */ 0x1F888, 0x1F890, 0x1F8AE, + 0x1F900, + 0x1F90C, 0x1F910, - 0x1F91F, - 0x1F920, - 0x1F928, - 0x1F930, - 0x1F931, - 0x1F933, 0x1F93F, 0x1F940, - 0x1F94C, + 0x1F94D, 0x1F950, - 0x1F95F, + 0x1F96C, 0x1F980, - 0x1F992, + 0x1F998, 0x1F9C0, 0x1F9C1, + 0x1F9D0, + 0x1F9E7, 0x20000, 0x2A6D7, 0x2A700, @@ -60286,6 +61614,8 @@ static const UV XPosixPrint_invlist[] = { /* for EBCDIC 1047 */ 0x2B81E, 0x2B820, 0x2CEA2, + 0x2CEB0, + 0x2EBE1, 0x2F800, 0x2FA1E, 0xE0001, @@ -60301,7 +61631,7 @@ static const UV XPosixPrint_invlist[] = { /* for EBCDIC 1047 */ }; static const UV XPosixPunct_invlist[] = { /* for EBCDIC 1047 */ - 335, /* Number of elements */ + 343, /* Number of elements */ 148565664, /* Version and data structure type */ 1, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -60376,6 +61706,8 @@ static const UV XPosixPunct_invlist[] = { /* for EBCDIC 1047 */ 0x966, 0x970, 0x971, + 0x9FD, + 0x9FE, 0xAF0, 0xAF1, 0xDF4, @@ -60475,7 +61807,7 @@ static const UV XPosixPunct_invlist[] = { /* for EBCDIC 1047 */ 0x2E00, 0x2E2F, 0x2E30, - 0x2E45, + 0x2E4A, 0x3001, 0x3004, 0x3008, @@ -60620,6 +61952,12 @@ static const UV XPosixPunct_invlist[] = { /* for EBCDIC 1047 */ 0x1166D, 0x1173C, 0x1173F, + 0x11A3F, + 0x11A47, + 0x11A9A, + 0x11A9D, + 0x11A9E, + 0x11AA3, 0x11C41, 0x11C46, 0x11C70, @@ -61963,7 +63301,7 @@ static const UV XPosixUpper_invlist[] = { /* for EBCDIC 1047 */ }; static const UV XPosixWord_invlist[] = { /* for EBCDIC 1047 */ - 1385, /* Number of elements */ + 1411, /* Number of elements */ 148565664, /* Version and data structure type */ 1, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -62088,6 +63426,8 @@ static const UV XPosixWord_invlist[] = { /* for EBCDIC 1047 */ 0x82E, 0x840, 0x85C, + 0x860, + 0x86B, 0x8A0, 0x8B5, 0x8B6, @@ -62126,6 +63466,8 @@ static const UV XPosixWord_invlist[] = { /* for EBCDIC 1047 */ 0x9E4, 0x9E6, 0x9F2, + 0x9FC, + 0x9FD, 0xA01, 0xA04, 0xA05, @@ -62185,7 +63527,7 @@ static const UV XPosixWord_invlist[] = { /* for EBCDIC 1047 */ 0xAE6, 0xAF0, 0xAF9, - 0xAFA, + 0xB00, 0xB01, 0xB04, 0xB05, @@ -62300,15 +63642,13 @@ static const UV XPosixWord_invlist[] = { /* for EBCDIC 1047 */ 0xCF0, 0xCF1, 0xCF3, - 0xD01, + 0xD00, 0xD04, 0xD05, 0xD0D, 0xD0E, 0xD11, 0xD12, - 0xD3B, - 0xD3D, 0xD45, 0xD46, 0xD49, @@ -62555,11 +63895,9 @@ static const UV XPosixWord_invlist[] = { /* for EBCDIC 1047 */ 0x1CD0, 0x1CD3, 0x1CD4, - 0x1CF7, - 0x1CF8, 0x1CFA, 0x1D00, - 0x1DF6, + 0x1DFA, 0x1DFB, 0x1F16, 0x1F18, @@ -62701,7 +64039,7 @@ static const UV XPosixWord_invlist[] = { /* for EBCDIC 1047 */ 0x30FC, 0x3100, 0x3105, - 0x312E, + 0x312F, 0x3131, 0x318F, 0x31A0, @@ -62711,7 +64049,7 @@ static const UV XPosixWord_invlist[] = { /* for EBCDIC 1047 */ 0x3400, 0x4DB6, 0x4E00, - 0x9FD6, + 0x9FEB, 0xA000, 0xA48D, 0xA4D0, @@ -62888,7 +64226,7 @@ static const UV XPosixWord_invlist[] = { /* for EBCDIC 1047 */ 0x102E1, 0x10300, 0x10320, - 0x10330, + 0x1032D, 0x1034B, 0x10350, 0x1037B, @@ -63094,6 +64432,14 @@ static const UV XPosixWord_invlist[] = { /* for EBCDIC 1047 */ 0x118EA, 0x118FF, 0x11900, + 0x11A00, + 0x11A3F, + 0x11A47, + 0x11A48, + 0x11A50, + 0x11A84, + 0x11A86, + 0x11A9A, 0x11AC0, 0x11AF9, 0x11C00, @@ -63110,6 +64456,20 @@ static const UV XPosixWord_invlist[] = { /* for EBCDIC 1047 */ 0x11CA8, 0x11CA9, 0x11CB7, + 0x11D00, + 0x11D07, + 0x11D08, + 0x11D0A, + 0x11D0B, + 0x11D37, + 0x11D3A, + 0x11D3B, + 0x11D3C, + 0x11D3E, + 0x11D3F, + 0x11D48, + 0x11D50, + 0x11D5A, 0x12000, 0x1239A, 0x12400, @@ -63147,13 +64507,15 @@ static const UV XPosixWord_invlist[] = { /* for EBCDIC 1047 */ 0x16F8F, 0x16FA0, 0x16FE0, - 0x16FE1, + 0x16FE2, 0x17000, 0x187ED, 0x18800, 0x18AF3, 0x1B000, - 0x1B002, + 0x1B11F, + 0x1B170, + 0x1B2FC, 0x1BC00, 0x1BC6B, 0x1BC70, @@ -63348,6 +64710,8 @@ static const UV XPosixWord_invlist[] = { /* for EBCDIC 1047 */ 0x2B81E, 0x2B820, 0x2CEA2, + 0x2CEB0, + 0x2EBE1, 0x2F800, 0x2FA1E, 0xE0100, @@ -63449,7 +64813,7 @@ static const UV ASCII_invlist[] = { /* for EBCDIC 037 */ }; static const UV Assigned_invlist[] = { /* for EBCDIC 037 */ - 1276, /* Number of elements */ + 1298, /* Number of elements */ 148565664, /* Version and data structure type */ 0, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -63499,6 +64863,8 @@ static const UV Assigned_invlist[] = { /* for EBCDIC 037 */ 0x85C, 0x85E, 0x85F, + 0x860, + 0x86B, 0x8A0, 0x8B5, 0x8B6, @@ -63530,7 +64896,7 @@ static const UV Assigned_invlist[] = { /* for EBCDIC 037 */ 0x9DF, 0x9E4, 0x9E6, - 0x9FC, + 0x9FE, 0xA01, 0xA04, 0xA05, @@ -63590,7 +64956,7 @@ static const UV Assigned_invlist[] = { /* for EBCDIC 037 */ 0xAE6, 0xAF2, 0xAF9, - 0xAFA, + 0xB00, 0xB01, 0xB04, 0xB05, @@ -63703,15 +65069,13 @@ static const UV Assigned_invlist[] = { /* for EBCDIC 037 */ 0xCF0, 0xCF1, 0xCF3, - 0xD01, + 0xD00, 0xD04, 0xD05, 0xD0D, 0xD0E, 0xD11, 0xD12, - 0xD3B, - 0xD3D, 0xD45, 0xD46, 0xD49, @@ -63924,11 +65288,9 @@ static const UV Assigned_invlist[] = { /* for EBCDIC 037 */ 0x1CC0, 0x1CC8, 0x1CD0, - 0x1CF7, - 0x1CF8, 0x1CFA, 0x1D00, - 0x1DF6, + 0x1DFA, 0x1DFB, 0x1F16, 0x1F18, @@ -63970,14 +65332,12 @@ static const UV Assigned_invlist[] = { /* for EBCDIC 037 */ 0x2090, 0x209D, 0x20A0, - 0x20BF, + 0x20C0, 0x20D0, 0x20F1, 0x2100, 0x218C, 0x2190, - 0x23FF, - 0x2400, 0x2427, 0x2440, 0x244B, @@ -63990,7 +65350,7 @@ static const UV Assigned_invlist[] = { /* for EBCDIC 037 */ 0x2BBD, 0x2BC9, 0x2BCA, - 0x2BD2, + 0x2BD3, 0x2BEC, 0x2BF0, 0x2C00, @@ -64028,7 +65388,7 @@ static const UV Assigned_invlist[] = { /* for EBCDIC 037 */ 0x2DD8, 0x2DDF, 0x2DE0, - 0x2E45, + 0x2E4A, 0x2E80, 0x2E9A, 0x2E9B, @@ -64044,7 +65404,7 @@ static const UV Assigned_invlist[] = { /* for EBCDIC 037 */ 0x3099, 0x3100, 0x3105, - 0x312E, + 0x312F, 0x3131, 0x318F, 0x3190, @@ -64058,7 +65418,7 @@ static const UV Assigned_invlist[] = { /* for EBCDIC 037 */ 0x3300, 0x4DB6, 0x4DC0, - 0x9FD6, + 0x9FEB, 0xA000, 0xA48D, 0xA490, @@ -64217,7 +65577,7 @@ static const UV Assigned_invlist[] = { /* for EBCDIC 037 */ 0x102FC, 0x10300, 0x10324, - 0x10330, + 0x1032D, 0x1034B, 0x10350, 0x1037B, @@ -64425,6 +65785,14 @@ static const UV Assigned_invlist[] = { /* for EBCDIC 037 */ 0x118F3, 0x118FF, 0x11900, + 0x11A00, + 0x11A48, + 0x11A50, + 0x11A84, + 0x11A86, + 0x11A9D, + 0x11A9E, + 0x11AA3, 0x11AC0, 0x11AF9, 0x11C00, @@ -64441,6 +65809,20 @@ static const UV Assigned_invlist[] = { /* for EBCDIC 037 */ 0x11CA8, 0x11CA9, 0x11CB7, + 0x11D00, + 0x11D07, + 0x11D08, + 0x11D0A, + 0x11D0B, + 0x11D37, + 0x11D3A, + 0x11D3B, + 0x11D3C, + 0x11D3E, + 0x11D3F, + 0x11D48, + 0x11D50, + 0x11D5A, 0x12000, 0x1239A, 0x12400, @@ -64482,13 +65864,15 @@ static const UV Assigned_invlist[] = { /* for EBCDIC 037 */ 0x16F8F, 0x16FA0, 0x16FE0, - 0x16FE1, + 0x16FE2, 0x17000, 0x187ED, 0x18800, 0x18AF3, 0x1B000, - 0x1B002, + 0x1B11F, + 0x1B170, + 0x1B2FC, 0x1BC00, 0x1BC6B, 0x1BC70, @@ -64673,12 +66057,14 @@ static const UV Assigned_invlist[] = { /* for EBCDIC 037 */ 0x1F249, 0x1F250, 0x1F252, + 0x1F260, + 0x1F266, 0x1F300, - 0x1F6D3, + 0x1F6D5, 0x1F6E0, 0x1F6ED, 0x1F6F0, - 0x1F6F7, + 0x1F6F9, 0x1F700, 0x1F774, 0x1F780, @@ -64693,22 +66079,20 @@ static const UV Assigned_invlist[] = { /* for EBCDIC 037 */ 0x1F888, 0x1F890, 0x1F8AE, + 0x1F900, + 0x1F90C, 0x1F910, - 0x1F91F, - 0x1F920, - 0x1F928, - 0x1F930, - 0x1F931, - 0x1F933, 0x1F93F, 0x1F940, - 0x1F94C, + 0x1F94D, 0x1F950, - 0x1F95F, + 0x1F96C, 0x1F980, - 0x1F992, + 0x1F998, 0x1F9C0, 0x1F9C1, + 0x1F9D0, + 0x1F9E7, 0x20000, 0x2A6D7, 0x2A700, @@ -64717,6 +66101,8 @@ static const UV Assigned_invlist[] = { /* for EBCDIC 037 */ 0x2B81E, 0x2B820, 0x2CEA2, + 0x2CEB0, + 0x2EBE1, 0x2F800, 0x2FA1E, 0xE0001, @@ -65446,7 +66832,7 @@ static const UV _Perl_Folds_To_Multi_Char_invlist[] = { /* for EBCDIC 037 */ #if defined(PERL_IN_PERL_C) static const UV _Perl_GCB_invlist[] = { /* for EBCDIC 037 */ - 1615, /* Number of elements */ + 1690, /* Number of elements */ 148565664, /* Version and data structure type */ 0, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -65584,6 +66970,8 @@ static const UV _Perl_GCB_invlist[] = { /* for EBCDIC 037 */ 0xACE, 0xAE2, 0xAE4, + 0xAFA, + 0xB00, 0xB01, 0xB02, 0xB04, @@ -65651,9 +67039,11 @@ static const UV _Perl_GCB_invlist[] = { /* for EBCDIC 037 */ 0xCD7, 0xCE2, 0xCE4, - 0xD01, + 0xD00, 0xD02, 0xD04, + 0xD3B, + 0xD3D, 0xD3E, 0xD3F, 0xD41, @@ -65856,10 +67246,11 @@ static const UV _Perl_GCB_invlist[] = { /* for EBCDIC 037 */ 0x1CF2, 0x1CF4, 0x1CF5, + 0x1CF7, 0x1CF8, 0x1CFA, 0x1DC0, - 0x1DF6, + 0x1DFA, 0x1DFB, 0x1E00, 0x200B, @@ -65875,8 +67266,16 @@ static const UV _Perl_GCB_invlist[] = { /* for EBCDIC 037 */ 0x20F1, 0x261D, 0x261E, + 0x2640, + 0x2641, + 0x2642, + 0x2643, + 0x2695, + 0x2697, 0x26F9, 0x26FA, + 0x2708, + 0x2709, 0x270A, 0x270E, 0x2764, @@ -66930,6 +68329,26 @@ static const UV _Perl_GCB_invlist[] = { /* for EBCDIC 037 */ 0x11726, 0x11727, 0x1172C, + 0x11A01, + 0x11A07, + 0x11A09, + 0x11A0B, + 0x11A33, + 0x11A39, + 0x11A3A, + 0x11A3B, + 0x11A3F, + 0x11A47, + 0x11A48, + 0x11A51, + 0x11A57, + 0x11A59, + 0x11A5C, + 0x11A86, + 0x11A8A, + 0x11A97, + 0x11A98, + 0x11A9A, 0x11C2F, 0x11C30, 0x11C37, @@ -66946,6 +68365,16 @@ static const UV _Perl_GCB_invlist[] = { /* for EBCDIC 037 */ 0x11CB4, 0x11CB5, 0x11CB7, + 0x11D31, + 0x11D37, + 0x11D3A, + 0x11D3B, + 0x11D3C, + 0x11D3E, + 0x11D3F, + 0x11D46, + 0x11D47, + 0x11D48, 0x16AF0, 0x16AF5, 0x16B30, @@ -67001,12 +68430,30 @@ static const UV _Perl_GCB_invlist[] = { /* for EBCDIC 037 */ 0x1E94B, 0x1F1E6, 0x1F200, + 0x1F308, + 0x1F309, + 0x1F33E, + 0x1F33F, + 0x1F373, + 0x1F374, 0x1F385, 0x1F386, - 0x1F3C3, + 0x1F393, + 0x1F394, + 0x1F3A4, + 0x1F3A5, + 0x1F3A8, + 0x1F3A9, + 0x1F3C2, 0x1F3C5, + 0x1F3C7, + 0x1F3C8, 0x1F3CA, - 0x1F3CC, + 0x1F3CD, + 0x1F3EB, + 0x1F3EC, + 0x1F3ED, + 0x1F3EE, 0x1F3FB, 0x1F400, 0x1F442, @@ -67029,7 +68476,13 @@ static const UV _Perl_GCB_invlist[] = { /* for EBCDIC 037 */ 0x1F48C, 0x1F4AA, 0x1F4AB, - 0x1F575, + 0x1F4BB, + 0x1F4BD, + 0x1F527, + 0x1F528, + 0x1F52C, + 0x1F52D, + 0x1F574, 0x1F576, 0x1F57A, 0x1F57B, @@ -67043,22 +68496,30 @@ static const UV _Perl_GCB_invlist[] = { /* for EBCDIC 037 */ 0x1F648, 0x1F64B, 0x1F650, + 0x1F680, + 0x1F681, + 0x1F692, + 0x1F693, 0x1F6A3, 0x1F6A4, 0x1F6B4, 0x1F6B7, 0x1F6C0, 0x1F6C1, + 0x1F6CC, + 0x1F6CD, 0x1F918, - 0x1F91F, + 0x1F91D, + 0x1F91E, + 0x1F920, 0x1F926, 0x1F927, 0x1F930, - 0x1F931, - 0x1F933, 0x1F93A, - 0x1F93C, + 0x1F93D, 0x1F93F, + 0x1F9D1, + 0x1F9DE, 0xE0000, 0xE0020, 0xE0080, @@ -67231,6 +68692,8 @@ static const GCB_enum _Perl_GCB_invmap[] = { /* for EBCDIC 037 */ GCB_Extend, GCB_Other, GCB_Extend, + GCB_Other, + GCB_Extend, GCB_SpacingMark, GCB_Other, GCB_Extend, @@ -67301,6 +68764,8 @@ static const GCB_enum _Perl_GCB_invmap[] = { /* for EBCDIC 037 */ GCB_SpacingMark, GCB_Other, GCB_Extend, + GCB_Other, + GCB_Extend, GCB_SpacingMark, GCB_Extend, GCB_Other, @@ -67502,6 +68967,7 @@ static const GCB_enum _Perl_GCB_invmap[] = { /* for EBCDIC 037 */ GCB_SpacingMark, GCB_Extend, GCB_Other, + GCB_SpacingMark, GCB_Extend, GCB_Other, GCB_Extend, @@ -67521,8 +68987,16 @@ static const GCB_enum _Perl_GCB_invmap[] = { /* for EBCDIC 037 */ GCB_Other, GCB_E_Base, GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, GCB_E_Base, GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, GCB_E_Base, GCB_Other, GCB_Glue_After_Zwj, @@ -68576,6 +70050,26 @@ static const GCB_enum _Perl_GCB_invmap[] = { /* for EBCDIC 037 */ GCB_SpacingMark, GCB_Extend, GCB_Other, + GCB_Extend, + GCB_SpacingMark, + GCB_Extend, + GCB_Other, + GCB_Extend, + GCB_SpacingMark, + GCB_Prepend, + GCB_Extend, + GCB_Other, + GCB_Extend, + GCB_Other, + GCB_Extend, + GCB_SpacingMark, + GCB_Extend, + GCB_Other, + GCB_Prepend, + GCB_Extend, + GCB_SpacingMark, + GCB_Extend, + GCB_Other, GCB_SpacingMark, GCB_Extend, GCB_Other, @@ -68596,6 +70090,16 @@ static const GCB_enum _Perl_GCB_invmap[] = { /* for EBCDIC 037 */ GCB_Other, GCB_Extend, GCB_Other, + GCB_Extend, + GCB_Other, + GCB_Extend, + GCB_Prepend, + GCB_Extend, + GCB_Other, + GCB_Extend, + GCB_Other, + GCB_Extend, + GCB_Other, GCB_SpacingMark, GCB_Other, GCB_Extend, @@ -68647,12 +70151,30 @@ static const GCB_enum _Perl_GCB_invmap[] = { /* for EBCDIC 037 */ GCB_Other, GCB_Regional_Indicator, GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_E_Base, + GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, GCB_E_Base, GCB_Other, GCB_E_Base, GCB_Other, GCB_E_Base, GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, GCB_E_Modifier, GCB_Other, GCB_E_Base, @@ -68675,16 +70197,30 @@ static const GCB_enum _Perl_GCB_invmap[] = { /* for EBCDIC 037 */ GCB_Other, GCB_E_Base, GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_E_Base, + GCB_Other, GCB_E_Base, GCB_Other, GCB_E_Base, GCB_Other, GCB_E_Base, GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_E_Base, + GCB_Other, GCB_E_Base, GCB_Other, GCB_Glue_After_Zwj, GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, GCB_E_Base, GCB_Other, GCB_E_Base, @@ -68718,7 +70254,7 @@ static const GCB_enum _Perl_GCB_invmap[] = { /* for EBCDIC 037 */ #if defined(PERL_IN_UTF8_C) static const UV _Perl_IDCont_invlist[] = { /* for EBCDIC 037 */ - 1387, /* Number of elements */ + 1413, /* Number of elements */ 148565664, /* Version and data structure type */ 1, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -68841,6 +70377,8 @@ static const UV _Perl_IDCont_invlist[] = { /* for EBCDIC 037 */ 0x82E, 0x840, 0x85C, + 0x860, + 0x86B, 0x8A0, 0x8B5, 0x8B6, @@ -68879,6 +70417,8 @@ static const UV _Perl_IDCont_invlist[] = { /* for EBCDIC 037 */ 0x9E4, 0x9E6, 0x9F2, + 0x9FC, + 0x9FD, 0xA01, 0xA04, 0xA05, @@ -68938,7 +70478,7 @@ static const UV _Perl_IDCont_invlist[] = { /* for EBCDIC 037 */ 0xAE6, 0xAF0, 0xAF9, - 0xAFA, + 0xB00, 0xB01, 0xB04, 0xB05, @@ -69053,15 +70593,13 @@ static const UV _Perl_IDCont_invlist[] = { /* for EBCDIC 037 */ 0xCF0, 0xCF1, 0xCF3, - 0xD01, + 0xD00, 0xD04, 0xD05, 0xD0D, 0xD0E, 0xD11, 0xD12, - 0xD3B, - 0xD3D, 0xD45, 0xD46, 0xD49, @@ -69308,11 +70846,9 @@ static const UV _Perl_IDCont_invlist[] = { /* for EBCDIC 037 */ 0x1CD0, 0x1CD3, 0x1CD4, - 0x1CF7, - 0x1CF8, 0x1CFA, 0x1D00, - 0x1DF6, + 0x1DFA, 0x1DFB, 0x1F16, 0x1F18, @@ -69452,7 +70988,7 @@ static const UV _Perl_IDCont_invlist[] = { /* for EBCDIC 037 */ 0x30FC, 0x3100, 0x3105, - 0x312E, + 0x312F, 0x3131, 0x318F, 0x31A0, @@ -69462,7 +70998,7 @@ static const UV _Perl_IDCont_invlist[] = { /* for EBCDIC 037 */ 0x3400, 0x4DB6, 0x4E00, - 0x9FD6, + 0x9FEB, 0xA000, 0xA48D, 0xA4D0, @@ -69651,7 +71187,7 @@ static const UV _Perl_IDCont_invlist[] = { /* for EBCDIC 037 */ 0x102E1, 0x10300, 0x10320, - 0x10330, + 0x1032D, 0x1034B, 0x10350, 0x1037B, @@ -69857,6 +71393,14 @@ static const UV _Perl_IDCont_invlist[] = { /* for EBCDIC 037 */ 0x118EA, 0x118FF, 0x11900, + 0x11A00, + 0x11A3F, + 0x11A47, + 0x11A48, + 0x11A50, + 0x11A84, + 0x11A86, + 0x11A9A, 0x11AC0, 0x11AF9, 0x11C00, @@ -69873,6 +71417,20 @@ static const UV _Perl_IDCont_invlist[] = { /* for EBCDIC 037 */ 0x11CA8, 0x11CA9, 0x11CB7, + 0x11D00, + 0x11D07, + 0x11D08, + 0x11D0A, + 0x11D0B, + 0x11D37, + 0x11D3A, + 0x11D3B, + 0x11D3C, + 0x11D3E, + 0x11D3F, + 0x11D48, + 0x11D50, + 0x11D5A, 0x12000, 0x1239A, 0x12400, @@ -69910,13 +71468,15 @@ static const UV _Perl_IDCont_invlist[] = { /* for EBCDIC 037 */ 0x16F8F, 0x16FA0, 0x16FE0, - 0x16FE1, + 0x16FE2, 0x17000, 0x187ED, 0x18800, 0x18AF3, 0x1B000, - 0x1B002, + 0x1B11F, + 0x1B170, + 0x1B2FC, 0x1BC00, 0x1BC6B, 0x1BC70, @@ -70105,6 +71665,8 @@ static const UV _Perl_IDCont_invlist[] = { /* for EBCDIC 037 */ 0x2B81E, 0x2B820, 0x2CEA2, + 0x2CEB0, + 0x2EBE1, 0x2F800, 0x2FA1E, 0xE0100, @@ -70112,7 +71674,7 @@ static const UV _Perl_IDCont_invlist[] = { /* for EBCDIC 037 */ }; static const UV _Perl_IDStart_invlist[] = { /* for EBCDIC 037 */ - 1183, /* Number of elements */ + 1211, /* Number of elements */ 148565664, /* Version and data structure type */ 1, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -70237,6 +71799,8 @@ static const UV _Perl_IDStart_invlist[] = { /* for EBCDIC 037 */ 0x829, 0x840, 0x859, + 0x860, + 0x86B, 0x8A0, 0x8B5, 0x8B6, @@ -70273,6 +71837,8 @@ static const UV _Perl_IDStart_invlist[] = { /* for EBCDIC 037 */ 0x9E2, 0x9F0, 0x9F2, + 0x9FC, + 0x9FD, 0xA05, 0xA0B, 0xA0F, @@ -70732,7 +72298,7 @@ static const UV _Perl_IDStart_invlist[] = { /* for EBCDIC 037 */ 0x30FC, 0x3100, 0x3105, - 0x312E, + 0x312F, 0x3131, 0x318F, 0x31A0, @@ -70742,7 +72308,7 @@ static const UV _Perl_IDStart_invlist[] = { /* for EBCDIC 037 */ 0x3400, 0x4DB6, 0x4E00, - 0x9FD6, + 0x9FEB, 0xA000, 0xA48D, 0xA4D0, @@ -70937,7 +72503,7 @@ static const UV _Perl_IDStart_invlist[] = { /* for EBCDIC 037 */ 0x102D1, 0x10300, 0x10320, - 0x10330, + 0x1032D, 0x1034B, 0x10350, 0x10376, @@ -71103,6 +72669,18 @@ static const UV _Perl_IDStart_invlist[] = { /* for EBCDIC 037 */ 0x118E0, 0x118FF, 0x11900, + 0x11A00, + 0x11A01, + 0x11A0B, + 0x11A33, + 0x11A3A, + 0x11A3B, + 0x11A50, + 0x11A51, + 0x11A5C, + 0x11A84, + 0x11A86, + 0x11A8A, 0x11AC0, 0x11AF9, 0x11C00, @@ -71113,6 +72691,14 @@ static const UV _Perl_IDStart_invlist[] = { /* for EBCDIC 037 */ 0x11C41, 0x11C72, 0x11C90, + 0x11D00, + 0x11D07, + 0x11D08, + 0x11D0A, + 0x11D0B, + 0x11D31, + 0x11D46, + 0x11D47, 0x12000, 0x1239A, 0x12400, @@ -71144,13 +72730,15 @@ static const UV _Perl_IDStart_invlist[] = { /* for EBCDIC 037 */ 0x16F93, 0x16FA0, 0x16FE0, - 0x16FE1, + 0x16FE2, 0x17000, 0x187ED, 0x18800, 0x18AF3, 0x1B000, - 0x1B002, + 0x1B11F, + 0x1B170, + 0x1B2FC, 0x1BC00, 0x1BC6B, 0x1BC70, @@ -71297,6 +72885,8 @@ static const UV _Perl_IDStart_invlist[] = { /* for EBCDIC 037 */ 0x2B81E, 0x2B820, 0x2CEA2, + 0x2CEB0, + 0x2EBE1, 0x2F800, 0x2FA1E }; @@ -71306,7 +72896,7 @@ static const UV _Perl_IDStart_invlist[] = { /* for EBCDIC 037 */ #if defined(PERL_IN_PERL_C) static const UV _Perl_LB_invlist[] = { /* for EBCDIC 037 */ - 2279, /* Number of elements */ + 2325, /* Number of elements */ 148565664, /* Version and data structure type */ 0, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -71533,6 +73123,8 @@ static const UV _Perl_LB_invlist[] = { /* for EBCDIC 037 */ 0xAF0, 0xAF1, 0xAF2, + 0xAFA, + 0xB00, 0xB01, 0xB04, 0xB3C, @@ -71593,8 +73185,10 @@ static const UV _Perl_LB_invlist[] = { /* for EBCDIC 037 */ 0xCE4, 0xCE6, 0xCF0, - 0xD01, + 0xD00, 0xD04, + 0xD3B, + 0xD3D, 0xD3E, 0xD45, 0xD46, @@ -71825,10 +73419,10 @@ static const UV _Perl_LB_invlist[] = { /* for EBCDIC 037 */ 0x1CEE, 0x1CF2, 0x1CF5, - 0x1CF8, + 0x1CF7, 0x1CFA, 0x1DC0, - 0x1DF6, + 0x1DFA, 0x1DFB, 0x1E00, 0x1FFD, @@ -72067,7 +73661,7 @@ static const UV _Perl_LB_invlist[] = { /* for EBCDIC 037 */ 0x2E40, 0x2E42, 0x2E43, - 0x2E45, + 0x2E4A, 0x2E80, 0x2E9A, 0x2E9B, @@ -72162,7 +73756,7 @@ static const UV _Perl_LB_invlist[] = { /* for EBCDIC 037 */ 0x30FF, 0x3100, 0x3105, - 0x312E, + 0x312F, 0x3131, 0x318F, 0x3190, @@ -73362,6 +74956,26 @@ static const UV _Perl_LB_invlist[] = { /* for EBCDIC 037 */ 0x1173F, 0x118E0, 0x118EA, + 0x11A01, + 0x11A0B, + 0x11A33, + 0x11A3A, + 0x11A3B, + 0x11A3F, + 0x11A40, + 0x11A41, + 0x11A45, + 0x11A46, + 0x11A47, + 0x11A48, + 0x11A51, + 0x11A5C, + 0x11A8A, + 0x11A9A, + 0x11A9D, + 0x11A9E, + 0x11AA1, + 0x11AA3, 0x11C2F, 0x11C37, 0x11C38, @@ -73377,6 +74991,18 @@ static const UV _Perl_LB_invlist[] = { /* for EBCDIC 037 */ 0x11CA8, 0x11CA9, 0x11CB7, + 0x11D31, + 0x11D37, + 0x11D3A, + 0x11D3B, + 0x11D3C, + 0x11D3E, + 0x11D3F, + 0x11D46, + 0x11D47, + 0x11D48, + 0x11D50, + 0x11D5A, 0x12470, 0x12475, 0x13258, @@ -73414,13 +75040,15 @@ static const UV _Perl_LB_invlist[] = { /* for EBCDIC 037 */ 0x16F8F, 0x16F93, 0x16FE0, - 0x16FE1, + 0x16FE2, 0x17000, 0x187ED, 0x18800, 0x18AF3, 0x1B000, - 0x1B002, + 0x1B11F, + 0x1B170, + 0x1B2FC, 0x1BC9D, 0x1BC9F, 0x1BCA0, @@ -73488,10 +75116,12 @@ static const UV _Perl_LB_invlist[] = { /* for EBCDIC 037 */ 0x1F3B7, 0x1F3BC, 0x1F3BD, - 0x1F3C3, + 0x1F3C2, 0x1F3C5, + 0x1F3C7, + 0x1F3C8, 0x1F3CA, - 0x1F3CC, + 0x1F3CD, 0x1F3FB, 0x1F400, 0x1F442, @@ -73528,7 +75158,7 @@ static const UV _Perl_LB_invlist[] = { /* for EBCDIC 037 */ 0x1F525, 0x1F532, 0x1F54A, - 0x1F575, + 0x1F574, 0x1F576, 0x1F57A, 0x1F57B, @@ -73554,6 +75184,8 @@ static const UV _Perl_LB_invlist[] = { /* for EBCDIC 037 */ 0x1F6B7, 0x1F6C0, 0x1F6C1, + 0x1F6CC, + 0x1F6CD, 0x1F700, 0x1F774, 0x1F780, @@ -73568,16 +75200,20 @@ static const UV _Perl_LB_invlist[] = { /* for EBCDIC 037 */ 0x1F888, 0x1F890, 0x1F8AE, + 0x1F900, + 0x1F90C, 0x1F918, - 0x1F91F, + 0x1F91D, + 0x1F91E, + 0x1F920, 0x1F926, 0x1F927, 0x1F930, - 0x1F931, - 0x1F933, 0x1F93A, - 0x1F93C, + 0x1F93D, 0x1F93F, + 0x1F9D1, + 0x1F9DE, 0x1FFFE, 0x20000, 0x2FFFE, @@ -73877,6 +75513,8 @@ static const LB_enum _Perl_LB_invmap[] = { /* for EBCDIC 037 */ LB_Alphabetic, LB_Combining_Mark, LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, LB_Numeric, LB_Alphabetic, LB_Combining_Mark, @@ -73935,6 +75573,8 @@ static const LB_enum _Perl_LB_invmap[] = { /* for EBCDIC 037 */ LB_Alphabetic, LB_Combining_Mark, LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, LB_Numeric, LB_Alphabetic, LB_Postfix_Numeric, @@ -75696,6 +77336,26 @@ static const LB_enum _Perl_LB_invmap[] = { /* for EBCDIC 037 */ LB_Alphabetic, LB_Combining_Mark, LB_Alphabetic, + LB_Combining_Mark, + LB_Break_Before, + LB_Alphabetic, + LB_Break_After, + LB_Break_Before, + LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, + LB_Combining_Mark, + LB_Break_After, + LB_Alphabetic, + LB_Break_Before, + LB_Break_After, + LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, LB_Break_After, LB_Alphabetic, LB_Numeric, @@ -75707,6 +77367,18 @@ static const LB_enum _Perl_LB_invmap[] = { /* for EBCDIC 037 */ LB_Alphabetic, LB_Combining_Mark, LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, + LB_Numeric, + LB_Alphabetic, LB_Break_After, LB_Alphabetic, LB_Open_Punctuation, @@ -75751,6 +77423,8 @@ static const LB_enum _Perl_LB_invmap[] = { /* for EBCDIC 037 */ LB_Alphabetic, LB_Ideographic, LB_Alphabetic, + LB_Ideographic, + LB_Alphabetic, LB_Combining_Mark, LB_Break_After, LB_Combining_Mark, @@ -75822,6 +77496,8 @@ static const LB_enum _Perl_LB_invmap[] = { /* for EBCDIC 037 */ LB_Ideographic, LB_E_Base, LB_Ideographic, + LB_E_Base, + LB_Ideographic, LB_E_Modifier, LB_Ideographic, LB_E_Base, @@ -75884,6 +77560,10 @@ static const LB_enum _Perl_LB_invmap[] = { /* for EBCDIC 037 */ LB_Ideographic, LB_E_Base, LB_Ideographic, + LB_E_Base, + LB_Ideographic, + LB_Alphabetic, + LB_Ideographic, LB_Alphabetic, LB_Ideographic, LB_Alphabetic, @@ -75908,6 +77588,8 @@ static const LB_enum _Perl_LB_invmap[] = { /* for EBCDIC 037 */ LB_Ideographic, LB_E_Base, LB_Ideographic, + LB_E_Base, + LB_Ideographic, LB_Alphabetic, LB_Ideographic, LB_Alphabetic, @@ -75926,7 +77608,7 @@ static const LB_enum _Perl_LB_invmap[] = { /* for EBCDIC 037 */ #if defined(PERL_IN_PERL_C) static const UV _Perl_SB_invlist[] = { /* for EBCDIC 037 */ - 2977, /* Number of elements */ + 3022, /* Number of elements */ 148565664, /* Version and data structure type */ 0, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -76651,6 +78333,8 @@ static const UV _Perl_SB_invlist[] = { /* for EBCDIC 037 */ 0x840, 0x859, 0x85C, + 0x860, + 0x86B, 0x8A0, 0x8B5, 0x8B6, @@ -76703,6 +78387,8 @@ static const UV _Perl_SB_invlist[] = { /* for EBCDIC 037 */ 0x9E6, 0x9F0, 0x9F2, + 0x9FC, + 0x9FD, 0xA01, 0xA04, 0xA05, @@ -76769,6 +78455,7 @@ static const UV _Perl_SB_invlist[] = { /* for EBCDIC 037 */ 0xAF0, 0xAF9, 0xAFA, + 0xB00, 0xB01, 0xB04, 0xB05, @@ -76893,7 +78580,7 @@ static const UV _Perl_SB_invlist[] = { /* for EBCDIC 037 */ 0xCF0, 0xCF1, 0xCF3, - 0xD01, + 0xD00, 0xD04, 0xD05, 0xD0D, @@ -77234,11 +78921,10 @@ static const UV _Perl_SB_invlist[] = { /* for EBCDIC 037 */ 0x1CF2, 0x1CF5, 0x1CF7, - 0x1CF8, 0x1CFA, 0x1D00, 0x1DC0, - 0x1DF6, + 0x1DFA, 0x1DFB, 0x1E00, 0x1E01, @@ -77848,7 +79534,7 @@ static const UV _Perl_SB_invlist[] = { /* for EBCDIC 037 */ 0x30FC, 0x3100, 0x3105, - 0x312E, + 0x312F, 0x3131, 0x318F, 0x31A0, @@ -77858,7 +79544,7 @@ static const UV _Perl_SB_invlist[] = { /* for EBCDIC 037 */ 0x3400, 0x4DB6, 0x4E00, - 0x9FD6, + 0x9FEB, 0xA000, 0xA48D, 0xA4D0, @@ -78336,7 +80022,7 @@ static const UV _Perl_SB_invlist[] = { /* for EBCDIC 037 */ 0x102E1, 0x10300, 0x10320, - 0x10330, + 0x1032D, 0x1034B, 0x10350, 0x10376, @@ -78597,6 +80283,26 @@ static const UV _Perl_SB_invlist[] = { /* for EBCDIC 037 */ 0x118EA, 0x118FF, 0x11900, + 0x11A00, + 0x11A01, + 0x11A0B, + 0x11A33, + 0x11A3A, + 0x11A3B, + 0x11A3F, + 0x11A42, + 0x11A44, + 0x11A47, + 0x11A48, + 0x11A50, + 0x11A51, + 0x11A5C, + 0x11A84, + 0x11A86, + 0x11A8A, + 0x11A9A, + 0x11A9B, + 0x11A9D, 0x11AC0, 0x11AF9, 0x11C00, @@ -78616,6 +80322,23 @@ static const UV _Perl_SB_invlist[] = { /* for EBCDIC 037 */ 0x11CA8, 0x11CA9, 0x11CB7, + 0x11D00, + 0x11D07, + 0x11D08, + 0x11D0A, + 0x11D0B, + 0x11D31, + 0x11D37, + 0x11D3A, + 0x11D3B, + 0x11D3C, + 0x11D3E, + 0x11D3F, + 0x11D46, + 0x11D47, + 0x11D48, + 0x11D50, + 0x11D5A, 0x12000, 0x1239A, 0x12400, @@ -78661,13 +80384,15 @@ static const UV _Perl_SB_invlist[] = { /* for EBCDIC 037 */ 0x16F93, 0x16FA0, 0x16FE0, - 0x16FE1, + 0x16FE2, 0x17000, 0x187ED, 0x18800, 0x18AF3, 0x1B000, - 0x1B002, + 0x1B11F, + 0x1B170, + 0x1B2FC, 0x1BC00, 0x1BC6B, 0x1BC70, @@ -78899,6 +80624,8 @@ static const UV _Perl_SB_invlist[] = { /* for EBCDIC 037 */ 0x2B81E, 0x2B820, 0x2CEA2, + 0x2CEB0, + 0x2EBE1, 0x2F800, 0x2FA1E, 0xE0001, @@ -79660,6 +81387,8 @@ static const SB_enum _Perl_SB_invmap[] = { /* for EBCDIC 037 */ SB_Other, SB_OLetter, SB_Other, + SB_OLetter, + SB_Other, SB_Extend, SB_Format, SB_Extend, @@ -79708,6 +81437,8 @@ static const SB_enum _Perl_SB_invmap[] = { /* for EBCDIC 037 */ SB_Numeric, SB_OLetter, SB_Other, + SB_OLetter, + SB_Other, SB_Extend, SB_Other, SB_OLetter, @@ -79773,6 +81504,7 @@ static const SB_enum _Perl_SB_invmap[] = { /* for EBCDIC 037 */ SB_Numeric, SB_Other, SB_OLetter, + SB_Extend, SB_Other, SB_Extend, SB_Other, @@ -79905,7 +81637,7 @@ static const SB_enum _Perl_SB_invmap[] = { /* for EBCDIC 037 */ SB_OLetter, SB_Other, SB_OLetter, - SB_Other, + SB_Extend, SB_OLetter, SB_Extend, SB_Other, @@ -80238,7 +81970,6 @@ static const SB_enum _Perl_SB_invmap[] = { /* for EBCDIC 037 */ SB_OLetter, SB_Extend, SB_OLetter, - SB_Other, SB_Extend, SB_Other, SB_Lower, @@ -81603,6 +83334,26 @@ static const SB_enum _Perl_SB_invmap[] = { /* for EBCDIC 037 */ SB_OLetter, SB_Other, SB_OLetter, + SB_Extend, + SB_OLetter, + SB_Extend, + SB_OLetter, + SB_Extend, + SB_Other, + SB_STerm, + SB_Other, + SB_Extend, + SB_Other, + SB_OLetter, + SB_Extend, + SB_OLetter, + SB_Other, + SB_OLetter, + SB_Extend, + SB_Other, + SB_STerm, + SB_Other, + SB_OLetter, SB_Other, SB_OLetter, SB_Other, @@ -81626,6 +83377,23 @@ static const SB_enum _Perl_SB_invmap[] = { /* for EBCDIC 037 */ SB_OLetter, SB_Other, SB_OLetter, + SB_Extend, + SB_Other, + SB_Extend, + SB_Other, + SB_Extend, + SB_Other, + SB_Extend, + SB_OLetter, + SB_Extend, + SB_Other, + SB_Numeric, + SB_Other, + SB_OLetter, + SB_Other, + SB_OLetter, + SB_Other, + SB_OLetter, SB_Other, SB_OLetter, SB_Other, @@ -81681,6 +83449,8 @@ static const SB_enum _Perl_SB_invmap[] = { /* for EBCDIC 037 */ SB_Other, SB_OLetter, SB_Other, + SB_OLetter, + SB_Other, SB_Extend, SB_STerm, SB_Format, @@ -81906,6 +83676,8 @@ static const SB_enum _Perl_SB_invmap[] = { /* for EBCDIC 037 */ SB_Other, SB_OLetter, SB_Other, + SB_OLetter, + SB_Other, SB_Format, SB_Other, SB_Extend, @@ -81919,7 +83691,7 @@ static const SB_enum _Perl_SB_invmap[] = { /* for EBCDIC 037 */ #if defined(PERL_IN_PERL_C) static const UV _Perl_WB_invlist[] = { /* for EBCDIC 037 */ - 1676, /* Number of elements */ + 1740, /* Number of elements */ 148565664, /* Version and data structure type */ 0, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -81987,17 +83759,10 @@ static const UV _Perl_WB_invlist[] = { /* for EBCDIC 037 */ 0xFB, 0xFF, 0x100, - 0x2C2, - 0x2C6, - 0x2D2, - 0x2D7, 0x2D8, - 0x2E0, + 0x2DE, 0x2E5, 0x2EC, - 0x2ED, - 0x2EE, - 0x2EF, 0x300, 0x370, 0x375, @@ -82111,6 +83876,8 @@ static const UV _Perl_WB_invlist[] = { /* for EBCDIC 037 */ 0x840, 0x859, 0x85C, + 0x860, + 0x86B, 0x8A0, 0x8B5, 0x8B6, @@ -82163,6 +83930,8 @@ static const UV _Perl_WB_invlist[] = { /* for EBCDIC 037 */ 0x9E6, 0x9F0, 0x9F2, + 0x9FC, + 0x9FD, 0xA01, 0xA04, 0xA05, @@ -82229,6 +83998,7 @@ static const UV _Perl_WB_invlist[] = { /* for EBCDIC 037 */ 0xAF0, 0xAF9, 0xAFA, + 0xB00, 0xB01, 0xB04, 0xB05, @@ -82353,7 +84123,7 @@ static const UV _Perl_WB_invlist[] = { /* for EBCDIC 037 */ 0xCF0, 0xCF1, 0xCF3, - 0xD01, + 0xD00, 0xD04, 0xD05, 0xD0D, @@ -82625,11 +84395,10 @@ static const UV _Perl_WB_invlist[] = { /* for EBCDIC 037 */ 0x1CF2, 0x1CF5, 0x1CF7, - 0x1CF8, 0x1CFA, 0x1D00, 0x1DC0, - 0x1DF6, + 0x1DFA, 0x1DFB, 0x1E00, 0x1F16, @@ -82735,8 +84504,16 @@ static const UV _Perl_WB_invlist[] = { /* for EBCDIC 037 */ 0x24EA, 0x261D, 0x261E, + 0x2640, + 0x2641, + 0x2642, + 0x2643, + 0x2695, + 0x2697, 0x26F9, 0x26FA, + 0x2708, + 0x2709, 0x270A, 0x270E, 0x2764, @@ -82802,7 +84579,7 @@ static const UV _Perl_WB_invlist[] = { /* for EBCDIC 037 */ 0x30FC, 0x3100, 0x3105, - 0x312E, + 0x312F, 0x3131, 0x318F, 0x31A0, @@ -82834,10 +84611,6 @@ static const UV _Perl_WB_invlist[] = { /* for EBCDIC 037 */ 0xA6F0, 0xA6F2, 0xA717, - 0xA720, - 0xA722, - 0xA789, - 0xA78B, 0xA7AF, 0xA7B0, 0xA7B8, @@ -82924,8 +84697,6 @@ static const UV _Perl_WB_invlist[] = { /* for EBCDIC 037 */ 0xAB28, 0xAB2F, 0xAB30, - 0xAB5B, - 0xAB5C, 0xAB66, 0xAB70, 0xABE3, @@ -83048,7 +84819,7 @@ static const UV _Perl_WB_invlist[] = { /* for EBCDIC 037 */ 0x102E1, 0x10300, 0x10320, - 0x10330, + 0x1032D, 0x1034B, 0x10350, 0x10376, @@ -83283,6 +85054,22 @@ static const UV _Perl_WB_invlist[] = { /* for EBCDIC 037 */ 0x118EA, 0x118FF, 0x11900, + 0x11A00, + 0x11A01, + 0x11A0B, + 0x11A33, + 0x11A3A, + 0x11A3B, + 0x11A3F, + 0x11A47, + 0x11A48, + 0x11A50, + 0x11A51, + 0x11A5C, + 0x11A84, + 0x11A86, + 0x11A8A, + 0x11A9A, 0x11AC0, 0x11AF9, 0x11C00, @@ -83301,6 +85088,23 @@ static const UV _Perl_WB_invlist[] = { /* for EBCDIC 037 */ 0x11CA8, 0x11CA9, 0x11CB7, + 0x11D00, + 0x11D07, + 0x11D08, + 0x11D0A, + 0x11D0B, + 0x11D31, + 0x11D37, + 0x11D3A, + 0x11D3B, + 0x11D3C, + 0x11D3E, + 0x11D3F, + 0x11D46, + 0x11D47, + 0x11D48, + 0x11D50, + 0x11D5A, 0x12000, 0x1239A, 0x12400, @@ -83341,7 +85145,7 @@ static const UV _Perl_WB_invlist[] = { /* for EBCDIC 037 */ 0x16F93, 0x16FA0, 0x16FE0, - 0x16FE1, + 0x16FE2, 0x1B000, 0x1B001, 0x1BC00, @@ -83535,12 +85339,30 @@ static const UV _Perl_WB_invlist[] = { /* for EBCDIC 037 */ 0x1F18A, 0x1F1E6, 0x1F200, + 0x1F308, + 0x1F309, + 0x1F33E, + 0x1F33F, + 0x1F373, + 0x1F374, 0x1F385, 0x1F386, - 0x1F3C3, + 0x1F393, + 0x1F394, + 0x1F3A4, + 0x1F3A5, + 0x1F3A8, + 0x1F3A9, + 0x1F3C2, 0x1F3C5, + 0x1F3C7, + 0x1F3C8, 0x1F3CA, - 0x1F3CC, + 0x1F3CD, + 0x1F3EB, + 0x1F3EC, + 0x1F3ED, + 0x1F3EE, 0x1F3FB, 0x1F400, 0x1F442, @@ -83563,7 +85385,13 @@ static const UV _Perl_WB_invlist[] = { /* for EBCDIC 037 */ 0x1F48C, 0x1F4AA, 0x1F4AB, - 0x1F575, + 0x1F4BB, + 0x1F4BD, + 0x1F527, + 0x1F528, + 0x1F52C, + 0x1F52D, + 0x1F574, 0x1F576, 0x1F57A, 0x1F57B, @@ -83577,22 +85405,30 @@ static const UV _Perl_WB_invlist[] = { /* for EBCDIC 037 */ 0x1F648, 0x1F64B, 0x1F650, + 0x1F680, + 0x1F681, + 0x1F692, + 0x1F693, 0x1F6A3, 0x1F6A4, 0x1F6B4, 0x1F6B7, 0x1F6C0, 0x1F6C1, + 0x1F6CC, + 0x1F6CD, 0x1F918, - 0x1F91F, + 0x1F91D, + 0x1F91E, + 0x1F920, 0x1F926, 0x1F927, 0x1F930, - 0x1F931, - 0x1F933, 0x1F93A, - 0x1F93C, + 0x1F93D, 0x1F93F, + 0x1F9D1, + 0x1F9DE, 0xE0001, 0xE0002, 0xE0020, @@ -83703,14 +85539,7 @@ static const WB_enum _Perl_WB_invmap[] = { /* for EBCDIC 037 */ WB_Other, WB_ALetter, WB_Other, - WB_MidLetter, - WB_Other, WB_ALetter, - WB_Other, - WB_ALetter, - WB_Other, - WB_ALetter, - WB_Other, WB_Extend, WB_ALetter, WB_Other, @@ -83828,6 +85657,8 @@ static const WB_enum _Perl_WB_invmap[] = { /* for EBCDIC 037 */ WB_Other, WB_ALetter, WB_Other, + WB_ALetter, + WB_Other, WB_Extend, WB_Format, WB_Extend, @@ -83876,6 +85707,8 @@ static const WB_enum _Perl_WB_invmap[] = { /* for EBCDIC 037 */ WB_Numeric, WB_ALetter, WB_Other, + WB_ALetter, + WB_Other, WB_Extend, WB_Other, WB_ALetter, @@ -83941,6 +85774,7 @@ static const WB_enum _Perl_WB_invmap[] = { /* for EBCDIC 037 */ WB_Numeric, WB_Other, WB_ALetter, + WB_Extend, WB_Other, WB_Extend, WB_Other, @@ -84073,7 +85907,7 @@ static const WB_enum _Perl_WB_invmap[] = { /* for EBCDIC 037 */ WB_ALetter, WB_Other, WB_ALetter, - WB_Other, + WB_Extend, WB_ALetter, WB_Extend, WB_Other, @@ -84337,7 +86171,6 @@ static const WB_enum _Perl_WB_invmap[] = { /* for EBCDIC 037 */ WB_ALetter, WB_Extend, WB_ALetter, - WB_Other, WB_Extend, WB_Other, WB_ALetter, @@ -84448,8 +86281,16 @@ static const WB_enum _Perl_WB_invmap[] = { /* for EBCDIC 037 */ WB_Other, WB_E_Base, WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_Glue_After_Zwj, + WB_Other, WB_E_Base, WB_Other, + WB_Glue_After_Zwj, + WB_Other, WB_E_Base, WB_Other, WB_Glue_After_Zwj, @@ -84551,10 +86392,6 @@ static const WB_enum _Perl_WB_invmap[] = { /* for EBCDIC 037 */ WB_ALetter, WB_Other, WB_ALetter, - WB_Other, - WB_ALetter, - WB_Other, - WB_ALetter, WB_Extend, WB_ALetter, WB_Extend, @@ -84639,8 +86476,6 @@ static const WB_enum _Perl_WB_invmap[] = { /* for EBCDIC 037 */ WB_ALetter, WB_Other, WB_ALetter, - WB_Other, - WB_ALetter, WB_Extend, WB_Other, WB_Extend, @@ -84997,6 +86832,22 @@ static const WB_enum _Perl_WB_invmap[] = { /* for EBCDIC 037 */ WB_ALetter, WB_Other, WB_ALetter, + WB_Extend, + WB_ALetter, + WB_Extend, + WB_ALetter, + WB_Extend, + WB_Other, + WB_Extend, + WB_Other, + WB_ALetter, + WB_Extend, + WB_ALetter, + WB_Other, + WB_ALetter, + WB_Extend, + WB_Other, + WB_ALetter, WB_Other, WB_ALetter, WB_Other, @@ -85019,6 +86870,23 @@ static const WB_enum _Perl_WB_invmap[] = { /* for EBCDIC 037 */ WB_ALetter, WB_Other, WB_ALetter, + WB_Extend, + WB_Other, + WB_Extend, + WB_Other, + WB_Extend, + WB_Other, + WB_Extend, + WB_ALetter, + WB_Extend, + WB_Other, + WB_Numeric, + WB_Other, + WB_ALetter, + WB_Other, + WB_ALetter, + WB_Other, + WB_ALetter, WB_Other, WB_ALetter, WB_Other, @@ -85248,12 +87116,30 @@ static const WB_enum _Perl_WB_invmap[] = { /* for EBCDIC 037 */ WB_Other, WB_Regional_Indicator, WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_E_Base, + WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_Glue_After_Zwj, + WB_Other, WB_E_Base, WB_Other, WB_E_Base, WB_Other, WB_E_Base, WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_Glue_After_Zwj, + WB_Other, WB_E_Modifier, WB_Other, WB_E_Base, @@ -85276,16 +87162,30 @@ static const WB_enum _Perl_WB_invmap[] = { /* for EBCDIC 037 */ WB_Other, WB_E_Base, WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_E_Base, + WB_Other, + WB_E_Base, + WB_Other, WB_E_Base, WB_Other, WB_E_Base, WB_Other, + WB_Glue_After_Zwj, + WB_Other, WB_E_Base, WB_Other, WB_E_Base, WB_Other, WB_Glue_After_Zwj, WB_Other, + WB_Glue_After_Zwj, + WB_Other, WB_E_Base, WB_Other, WB_E_Base, @@ -85433,7 +87333,7 @@ static const UV XPerlSpace_invlist[] = { /* for EBCDIC 037 */ }; static const UV XPosixAlnum_invlist[] = { /* for EBCDIC 037 */ - 1377, /* Number of elements */ + 1411, /* Number of elements */ 148565664, /* Version and data structure type */ 1, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -85560,6 +87460,8 @@ static const UV XPosixAlnum_invlist[] = { /* for EBCDIC 037 */ 0x82D, 0x840, 0x859, + 0x860, + 0x86B, 0x8A0, 0x8B5, 0x8B6, @@ -85608,6 +87510,8 @@ static const UV XPosixAlnum_invlist[] = { /* for EBCDIC 037 */ 0x9E4, 0x9E6, 0x9F2, + 0x9FC, + 0x9FD, 0xA01, 0xA04, 0xA05, @@ -85665,7 +87569,7 @@ static const UV XPosixAlnum_invlist[] = { /* for EBCDIC 037 */ 0xAE6, 0xAF0, 0xAF9, - 0xAFA, + 0xAFD, 0xB01, 0xB04, 0xB05, @@ -85780,7 +87684,7 @@ static const UV XPosixAlnum_invlist[] = { /* for EBCDIC 037 */ 0xCF0, 0xCF1, 0xCF3, - 0xD01, + 0xD00, 0xD04, 0xD05, 0xD0D, @@ -86185,7 +88089,7 @@ static const UV XPosixAlnum_invlist[] = { /* for EBCDIC 037 */ 0x30FC, 0x3100, 0x3105, - 0x312E, + 0x312F, 0x3131, 0x318F, 0x31A0, @@ -86195,7 +88099,7 @@ static const UV XPosixAlnum_invlist[] = { /* for EBCDIC 037 */ 0x3400, 0x4DB6, 0x4E00, - 0x9FD6, + 0x9FEB, 0xA000, 0xA48D, 0xA4D0, @@ -86374,7 +88278,7 @@ static const UV XPosixAlnum_invlist[] = { /* for EBCDIC 037 */ 0x102D1, 0x10300, 0x10320, - 0x10330, + 0x1032D, 0x1034B, 0x10350, 0x1037B, @@ -86582,6 +88486,14 @@ static const UV XPosixAlnum_invlist[] = { /* for EBCDIC 037 */ 0x118EA, 0x118FF, 0x11900, + 0x11A00, + 0x11A33, + 0x11A35, + 0x11A3F, + 0x11A50, + 0x11A84, + 0x11A86, + 0x11A98, 0x11AC0, 0x11AF9, 0x11C00, @@ -86600,6 +88512,24 @@ static const UV XPosixAlnum_invlist[] = { /* for EBCDIC 037 */ 0x11CA8, 0x11CA9, 0x11CB7, + 0x11D00, + 0x11D07, + 0x11D08, + 0x11D0A, + 0x11D0B, + 0x11D37, + 0x11D3A, + 0x11D3B, + 0x11D3C, + 0x11D3E, + 0x11D3F, + 0x11D42, + 0x11D43, + 0x11D44, + 0x11D46, + 0x11D48, + 0x11D50, + 0x11D5A, 0x12000, 0x1239A, 0x12400, @@ -86635,13 +88565,15 @@ static const UV XPosixAlnum_invlist[] = { /* for EBCDIC 037 */ 0x16F93, 0x16FA0, 0x16FE0, - 0x16FE1, + 0x16FE2, 0x17000, 0x187ED, 0x18800, 0x18AF3, 0x1B000, - 0x1B002, + 0x1B11F, + 0x1B170, + 0x1B2FC, 0x1BC00, 0x1BC6B, 0x1BC70, @@ -86812,12 +88744,14 @@ static const UV XPosixAlnum_invlist[] = { /* for EBCDIC 037 */ 0x2B81E, 0x2B820, 0x2CEA2, + 0x2CEB0, + 0x2EBE1, 0x2F800, 0x2FA1E }; static const UV XPosixAlpha_invlist[] = { /* for EBCDIC 037 */ - 1311, /* Number of elements */ + 1343, /* Number of elements */ 148565664, /* Version and data structure type */ 1, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -86946,6 +88880,8 @@ static const UV XPosixAlpha_invlist[] = { /* for EBCDIC 037 */ 0x82D, 0x840, 0x859, + 0x860, + 0x86B, 0x8A0, 0x8B5, 0x8B6, @@ -86992,6 +88928,8 @@ static const UV XPosixAlpha_invlist[] = { /* for EBCDIC 037 */ 0x9E4, 0x9F0, 0x9F2, + 0x9FC, + 0x9FD, 0xA01, 0xA04, 0xA05, @@ -87047,7 +88985,7 @@ static const UV XPosixAlpha_invlist[] = { /* for EBCDIC 037 */ 0xAE0, 0xAE4, 0xAF9, - 0xAFA, + 0xAFD, 0xB01, 0xB04, 0xB05, @@ -87154,7 +89092,7 @@ static const UV XPosixAlpha_invlist[] = { /* for EBCDIC 037 */ 0xCE4, 0xCF1, 0xCF3, - 0xD01, + 0xD00, 0xD04, 0xD05, 0xD0D, @@ -87537,7 +89475,7 @@ static const UV XPosixAlpha_invlist[] = { /* for EBCDIC 037 */ 0x30FC, 0x3100, 0x3105, - 0x312E, + 0x312F, 0x3131, 0x318F, 0x31A0, @@ -87547,7 +89485,7 @@ static const UV XPosixAlpha_invlist[] = { /* for EBCDIC 037 */ 0x3400, 0x4DB6, 0x4E00, - 0x9FD6, + 0x9FEB, 0xA000, 0xA48D, 0xA4D0, @@ -87722,7 +89660,7 @@ static const UV XPosixAlpha_invlist[] = { /* for EBCDIC 037 */ 0x102D1, 0x10300, 0x10320, - 0x10330, + 0x1032D, 0x1034B, 0x10350, 0x1037B, @@ -87910,6 +89848,14 @@ static const UV XPosixAlpha_invlist[] = { /* for EBCDIC 037 */ 0x118E0, 0x118FF, 0x11900, + 0x11A00, + 0x11A33, + 0x11A35, + 0x11A3F, + 0x11A50, + 0x11A84, + 0x11A86, + 0x11A98, 0x11AC0, 0x11AF9, 0x11C00, @@ -87926,6 +89872,22 @@ static const UV XPosixAlpha_invlist[] = { /* for EBCDIC 037 */ 0x11CA8, 0x11CA9, 0x11CB7, + 0x11D00, + 0x11D07, + 0x11D08, + 0x11D0A, + 0x11D0B, + 0x11D37, + 0x11D3A, + 0x11D3B, + 0x11D3C, + 0x11D3E, + 0x11D3F, + 0x11D42, + 0x11D43, + 0x11D44, + 0x11D46, + 0x11D48, 0x12000, 0x1239A, 0x12400, @@ -87957,13 +89919,15 @@ static const UV XPosixAlpha_invlist[] = { /* for EBCDIC 037 */ 0x16F93, 0x16FA0, 0x16FE0, - 0x16FE1, + 0x16FE2, 0x17000, 0x187ED, 0x18800, 0x18AF3, 0x1B000, - 0x1B002, + 0x1B11F, + 0x1B170, + 0x1B2FC, 0x1BC00, 0x1BC6B, 0x1BC70, @@ -88130,6 +90094,8 @@ static const UV XPosixAlpha_invlist[] = { /* for EBCDIC 037 */ 0x2B81E, 0x2B820, 0x2CEA2, + 0x2CEB0, + 0x2EBE1, 0x2F800, 0x2FA1E }; @@ -88168,7 +90134,7 @@ static const UV XPosixCntrl_invlist[] = { /* for EBCDIC 037 */ }; static const UV XPosixDigit_invlist[] = { /* for EBCDIC 037 */ - 109, /* Number of elements */ + 111, /* Number of elements */ 148565664, /* Version and data structure type */ 1, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -88273,6 +90239,8 @@ static const UV XPosixDigit_invlist[] = { /* for EBCDIC 037 */ 0x118EA, 0x11C50, 0x11C5A, + 0x11D50, + 0x11D5A, 0x16A60, 0x16A6A, 0x16B50, @@ -88284,7 +90252,7 @@ static const UV XPosixDigit_invlist[] = { /* for EBCDIC 037 */ }; static const UV XPosixGraph_invlist[] = { /* for EBCDIC 037 */ - 1287, /* Number of elements */ + 1309, /* Number of elements */ 148565664, /* Version and data structure type */ 1, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -88337,6 +90305,8 @@ static const UV XPosixGraph_invlist[] = { /* for EBCDIC 037 */ 0x85C, 0x85E, 0x85F, + 0x860, + 0x86B, 0x8A0, 0x8B5, 0x8B6, @@ -88368,7 +90338,7 @@ static const UV XPosixGraph_invlist[] = { /* for EBCDIC 037 */ 0x9DF, 0x9E4, 0x9E6, - 0x9FC, + 0x9FE, 0xA01, 0xA04, 0xA05, @@ -88428,7 +90398,7 @@ static const UV XPosixGraph_invlist[] = { /* for EBCDIC 037 */ 0xAE6, 0xAF2, 0xAF9, - 0xAFA, + 0xB00, 0xB01, 0xB04, 0xB05, @@ -88541,15 +90511,13 @@ static const UV XPosixGraph_invlist[] = { /* for EBCDIC 037 */ 0xCF0, 0xCF1, 0xCF3, - 0xD01, + 0xD00, 0xD04, 0xD05, 0xD0D, 0xD0E, 0xD11, 0xD12, - 0xD3B, - 0xD3D, 0xD45, 0xD46, 0xD49, @@ -88764,11 +90732,9 @@ static const UV XPosixGraph_invlist[] = { /* for EBCDIC 037 */ 0x1CC0, 0x1CC8, 0x1CD0, - 0x1CF7, - 0x1CF8, 0x1CFA, 0x1D00, - 0x1DF6, + 0x1DFA, 0x1DFB, 0x1F16, 0x1F18, @@ -88816,14 +90782,12 @@ static const UV XPosixGraph_invlist[] = { /* for EBCDIC 037 */ 0x2090, 0x209D, 0x20A0, - 0x20BF, + 0x20C0, 0x20D0, 0x20F1, 0x2100, 0x218C, 0x2190, - 0x23FF, - 0x2400, 0x2427, 0x2440, 0x244B, @@ -88836,7 +90800,7 @@ static const UV XPosixGraph_invlist[] = { /* for EBCDIC 037 */ 0x2BBD, 0x2BC9, 0x2BCA, - 0x2BD2, + 0x2BD3, 0x2BEC, 0x2BF0, 0x2C00, @@ -88874,7 +90838,7 @@ static const UV XPosixGraph_invlist[] = { /* for EBCDIC 037 */ 0x2DD8, 0x2DDF, 0x2DE0, - 0x2E45, + 0x2E4A, 0x2E80, 0x2E9A, 0x2E9B, @@ -88890,7 +90854,7 @@ static const UV XPosixGraph_invlist[] = { /* for EBCDIC 037 */ 0x3099, 0x3100, 0x3105, - 0x312E, + 0x312F, 0x3131, 0x318F, 0x3190, @@ -88904,7 +90868,7 @@ static const UV XPosixGraph_invlist[] = { /* for EBCDIC 037 */ 0x3300, 0x4DB6, 0x4DC0, - 0x9FD6, + 0x9FEB, 0xA000, 0xA48D, 0xA490, @@ -89063,7 +91027,7 @@ static const UV XPosixGraph_invlist[] = { /* for EBCDIC 037 */ 0x102FC, 0x10300, 0x10324, - 0x10330, + 0x1032D, 0x1034B, 0x10350, 0x1037B, @@ -89271,6 +91235,14 @@ static const UV XPosixGraph_invlist[] = { /* for EBCDIC 037 */ 0x118F3, 0x118FF, 0x11900, + 0x11A00, + 0x11A48, + 0x11A50, + 0x11A84, + 0x11A86, + 0x11A9D, + 0x11A9E, + 0x11AA3, 0x11AC0, 0x11AF9, 0x11C00, @@ -89287,6 +91259,20 @@ static const UV XPosixGraph_invlist[] = { /* for EBCDIC 037 */ 0x11CA8, 0x11CA9, 0x11CB7, + 0x11D00, + 0x11D07, + 0x11D08, + 0x11D0A, + 0x11D0B, + 0x11D37, + 0x11D3A, + 0x11D3B, + 0x11D3C, + 0x11D3E, + 0x11D3F, + 0x11D48, + 0x11D50, + 0x11D5A, 0x12000, 0x1239A, 0x12400, @@ -89328,13 +91314,15 @@ static const UV XPosixGraph_invlist[] = { /* for EBCDIC 037 */ 0x16F8F, 0x16FA0, 0x16FE0, - 0x16FE1, + 0x16FE2, 0x17000, 0x187ED, 0x18800, 0x18AF3, 0x1B000, - 0x1B002, + 0x1B11F, + 0x1B170, + 0x1B2FC, 0x1BC00, 0x1BC6B, 0x1BC70, @@ -89519,12 +91507,14 @@ static const UV XPosixGraph_invlist[] = { /* for EBCDIC 037 */ 0x1F249, 0x1F250, 0x1F252, + 0x1F260, + 0x1F266, 0x1F300, - 0x1F6D3, + 0x1F6D5, 0x1F6E0, 0x1F6ED, 0x1F6F0, - 0x1F6F7, + 0x1F6F9, 0x1F700, 0x1F774, 0x1F780, @@ -89539,22 +91529,20 @@ static const UV XPosixGraph_invlist[] = { /* for EBCDIC 037 */ 0x1F888, 0x1F890, 0x1F8AE, + 0x1F900, + 0x1F90C, 0x1F910, - 0x1F91F, - 0x1F920, - 0x1F928, - 0x1F930, - 0x1F931, - 0x1F933, 0x1F93F, 0x1F940, - 0x1F94C, + 0x1F94D, 0x1F950, - 0x1F95F, + 0x1F96C, 0x1F980, - 0x1F992, + 0x1F998, 0x1F9C0, 0x1F9C1, + 0x1F9D0, + 0x1F9E7, 0x20000, 0x2A6D7, 0x2A700, @@ -89563,6 +91551,8 @@ static const UV XPosixGraph_invlist[] = { /* for EBCDIC 037 */ 0x2B81E, 0x2B820, 0x2CEA2, + 0x2CEB0, + 0x2EBE1, 0x2F800, 0x2FA1E, 0xE0001, @@ -90874,7 +92864,7 @@ static const UV XPosixLower_invlist[] = { /* for EBCDIC 037 */ }; static const UV XPosixPrint_invlist[] = { /* for EBCDIC 037 */ - 1281, /* Number of elements */ + 1303, /* Number of elements */ 148565664, /* Version and data structure type */ 1, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -90927,6 +92917,8 @@ static const UV XPosixPrint_invlist[] = { /* for EBCDIC 037 */ 0x85C, 0x85E, 0x85F, + 0x860, + 0x86B, 0x8A0, 0x8B5, 0x8B6, @@ -90958,7 +92950,7 @@ static const UV XPosixPrint_invlist[] = { /* for EBCDIC 037 */ 0x9DF, 0x9E4, 0x9E6, - 0x9FC, + 0x9FE, 0xA01, 0xA04, 0xA05, @@ -91018,7 +93010,7 @@ static const UV XPosixPrint_invlist[] = { /* for EBCDIC 037 */ 0xAE6, 0xAF2, 0xAF9, - 0xAFA, + 0xB00, 0xB01, 0xB04, 0xB05, @@ -91131,15 +93123,13 @@ static const UV XPosixPrint_invlist[] = { /* for EBCDIC 037 */ 0xCF0, 0xCF1, 0xCF3, - 0xD01, + 0xD00, 0xD04, 0xD05, 0xD0D, 0xD0E, 0xD11, 0xD12, - 0xD3B, - 0xD3D, 0xD45, 0xD46, 0xD49, @@ -91352,11 +93342,9 @@ static const UV XPosixPrint_invlist[] = { /* for EBCDIC 037 */ 0x1CC0, 0x1CC8, 0x1CD0, - 0x1CF7, - 0x1CF8, 0x1CFA, 0x1D00, - 0x1DF6, + 0x1DFA, 0x1DFB, 0x1F16, 0x1F18, @@ -91400,14 +93388,12 @@ static const UV XPosixPrint_invlist[] = { /* for EBCDIC 037 */ 0x2090, 0x209D, 0x20A0, - 0x20BF, + 0x20C0, 0x20D0, 0x20F1, 0x2100, 0x218C, 0x2190, - 0x23FF, - 0x2400, 0x2427, 0x2440, 0x244B, @@ -91420,7 +93406,7 @@ static const UV XPosixPrint_invlist[] = { /* for EBCDIC 037 */ 0x2BBD, 0x2BC9, 0x2BCA, - 0x2BD2, + 0x2BD3, 0x2BEC, 0x2BF0, 0x2C00, @@ -91458,7 +93444,7 @@ static const UV XPosixPrint_invlist[] = { /* for EBCDIC 037 */ 0x2DD8, 0x2DDF, 0x2DE0, - 0x2E45, + 0x2E4A, 0x2E80, 0x2E9A, 0x2E9B, @@ -91474,7 +93460,7 @@ static const UV XPosixPrint_invlist[] = { /* for EBCDIC 037 */ 0x3099, 0x3100, 0x3105, - 0x312E, + 0x312F, 0x3131, 0x318F, 0x3190, @@ -91488,7 +93474,7 @@ static const UV XPosixPrint_invlist[] = { /* for EBCDIC 037 */ 0x3300, 0x4DB6, 0x4DC0, - 0x9FD6, + 0x9FEB, 0xA000, 0xA48D, 0xA490, @@ -91647,7 +93633,7 @@ static const UV XPosixPrint_invlist[] = { /* for EBCDIC 037 */ 0x102FC, 0x10300, 0x10324, - 0x10330, + 0x1032D, 0x1034B, 0x10350, 0x1037B, @@ -91855,6 +93841,14 @@ static const UV XPosixPrint_invlist[] = { /* for EBCDIC 037 */ 0x118F3, 0x118FF, 0x11900, + 0x11A00, + 0x11A48, + 0x11A50, + 0x11A84, + 0x11A86, + 0x11A9D, + 0x11A9E, + 0x11AA3, 0x11AC0, 0x11AF9, 0x11C00, @@ -91871,6 +93865,20 @@ static const UV XPosixPrint_invlist[] = { /* for EBCDIC 037 */ 0x11CA8, 0x11CA9, 0x11CB7, + 0x11D00, + 0x11D07, + 0x11D08, + 0x11D0A, + 0x11D0B, + 0x11D37, + 0x11D3A, + 0x11D3B, + 0x11D3C, + 0x11D3E, + 0x11D3F, + 0x11D48, + 0x11D50, + 0x11D5A, 0x12000, 0x1239A, 0x12400, @@ -91912,13 +93920,15 @@ static const UV XPosixPrint_invlist[] = { /* for EBCDIC 037 */ 0x16F8F, 0x16FA0, 0x16FE0, - 0x16FE1, + 0x16FE2, 0x17000, 0x187ED, 0x18800, 0x18AF3, 0x1B000, - 0x1B002, + 0x1B11F, + 0x1B170, + 0x1B2FC, 0x1BC00, 0x1BC6B, 0x1BC70, @@ -92103,12 +94113,14 @@ static const UV XPosixPrint_invlist[] = { /* for EBCDIC 037 */ 0x1F249, 0x1F250, 0x1F252, + 0x1F260, + 0x1F266, 0x1F300, - 0x1F6D3, + 0x1F6D5, 0x1F6E0, 0x1F6ED, 0x1F6F0, - 0x1F6F7, + 0x1F6F9, 0x1F700, 0x1F774, 0x1F780, @@ -92123,22 +94135,20 @@ static const UV XPosixPrint_invlist[] = { /* for EBCDIC 037 */ 0x1F888, 0x1F890, 0x1F8AE, + 0x1F900, + 0x1F90C, 0x1F910, - 0x1F91F, - 0x1F920, - 0x1F928, - 0x1F930, - 0x1F931, - 0x1F933, 0x1F93F, 0x1F940, - 0x1F94C, + 0x1F94D, 0x1F950, - 0x1F95F, + 0x1F96C, 0x1F980, - 0x1F992, + 0x1F998, 0x1F9C0, 0x1F9C1, + 0x1F9D0, + 0x1F9E7, 0x20000, 0x2A6D7, 0x2A700, @@ -92147,6 +94157,8 @@ static const UV XPosixPrint_invlist[] = { /* for EBCDIC 037 */ 0x2B81E, 0x2B820, 0x2CEA2, + 0x2CEB0, + 0x2EBE1, 0x2F800, 0x2FA1E, 0xE0001, @@ -92162,7 +94174,7 @@ static const UV XPosixPrint_invlist[] = { /* for EBCDIC 037 */ }; static const UV XPosixPunct_invlist[] = { /* for EBCDIC 037 */ - 337, /* Number of elements */ + 345, /* Number of elements */ 148565664, /* Version and data structure type */ 1, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -92239,6 +94251,8 @@ static const UV XPosixPunct_invlist[] = { /* for EBCDIC 037 */ 0x966, 0x970, 0x971, + 0x9FD, + 0x9FE, 0xAF0, 0xAF1, 0xDF4, @@ -92338,7 +94352,7 @@ static const UV XPosixPunct_invlist[] = { /* for EBCDIC 037 */ 0x2E00, 0x2E2F, 0x2E30, - 0x2E45, + 0x2E4A, 0x3001, 0x3004, 0x3008, @@ -92483,6 +94497,12 @@ static const UV XPosixPunct_invlist[] = { /* for EBCDIC 037 */ 0x1166D, 0x1173C, 0x1173F, + 0x11A3F, + 0x11A47, + 0x11A9A, + 0x11A9D, + 0x11A9E, + 0x11AA3, 0x11C41, 0x11C46, 0x11C70, @@ -93822,7 +95842,7 @@ static const UV XPosixUpper_invlist[] = { /* for EBCDIC 037 */ }; static const UV XPosixWord_invlist[] = { /* for EBCDIC 037 */ - 1381, /* Number of elements */ + 1407, /* Number of elements */ 148565664, /* Version and data structure type */ 1, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -93943,6 +95963,8 @@ static const UV XPosixWord_invlist[] = { /* for EBCDIC 037 */ 0x82E, 0x840, 0x85C, + 0x860, + 0x86B, 0x8A0, 0x8B5, 0x8B6, @@ -93981,6 +96003,8 @@ static const UV XPosixWord_invlist[] = { /* for EBCDIC 037 */ 0x9E4, 0x9E6, 0x9F2, + 0x9FC, + 0x9FD, 0xA01, 0xA04, 0xA05, @@ -94040,7 +96064,7 @@ static const UV XPosixWord_invlist[] = { /* for EBCDIC 037 */ 0xAE6, 0xAF0, 0xAF9, - 0xAFA, + 0xB00, 0xB01, 0xB04, 0xB05, @@ -94155,15 +96179,13 @@ static const UV XPosixWord_invlist[] = { /* for EBCDIC 037 */ 0xCF0, 0xCF1, 0xCF3, - 0xD01, + 0xD00, 0xD04, 0xD05, 0xD0D, 0xD0E, 0xD11, 0xD12, - 0xD3B, - 0xD3D, 0xD45, 0xD46, 0xD49, @@ -94410,11 +96432,9 @@ static const UV XPosixWord_invlist[] = { /* for EBCDIC 037 */ 0x1CD0, 0x1CD3, 0x1CD4, - 0x1CF7, - 0x1CF8, 0x1CFA, 0x1D00, - 0x1DF6, + 0x1DFA, 0x1DFB, 0x1F16, 0x1F18, @@ -94556,7 +96576,7 @@ static const UV XPosixWord_invlist[] = { /* for EBCDIC 037 */ 0x30FC, 0x3100, 0x3105, - 0x312E, + 0x312F, 0x3131, 0x318F, 0x31A0, @@ -94566,7 +96586,7 @@ static const UV XPosixWord_invlist[] = { /* for EBCDIC 037 */ 0x3400, 0x4DB6, 0x4E00, - 0x9FD6, + 0x9FEB, 0xA000, 0xA48D, 0xA4D0, @@ -94743,7 +96763,7 @@ static const UV XPosixWord_invlist[] = { /* for EBCDIC 037 */ 0x102E1, 0x10300, 0x10320, - 0x10330, + 0x1032D, 0x1034B, 0x10350, 0x1037B, @@ -94949,6 +96969,14 @@ static const UV XPosixWord_invlist[] = { /* for EBCDIC 037 */ 0x118EA, 0x118FF, 0x11900, + 0x11A00, + 0x11A3F, + 0x11A47, + 0x11A48, + 0x11A50, + 0x11A84, + 0x11A86, + 0x11A9A, 0x11AC0, 0x11AF9, 0x11C00, @@ -94965,6 +96993,20 @@ static const UV XPosixWord_invlist[] = { /* for EBCDIC 037 */ 0x11CA8, 0x11CA9, 0x11CB7, + 0x11D00, + 0x11D07, + 0x11D08, + 0x11D0A, + 0x11D0B, + 0x11D37, + 0x11D3A, + 0x11D3B, + 0x11D3C, + 0x11D3E, + 0x11D3F, + 0x11D48, + 0x11D50, + 0x11D5A, 0x12000, 0x1239A, 0x12400, @@ -95002,13 +97044,15 @@ static const UV XPosixWord_invlist[] = { /* for EBCDIC 037 */ 0x16F8F, 0x16FA0, 0x16FE0, - 0x16FE1, + 0x16FE2, 0x17000, 0x187ED, 0x18800, 0x18AF3, 0x1B000, - 0x1B002, + 0x1B11F, + 0x1B170, + 0x1B2FC, 0x1BC00, 0x1BC6B, 0x1BC70, @@ -95203,6 +97247,8 @@ static const UV XPosixWord_invlist[] = { /* for EBCDIC 037 */ 0x2B81E, 0x2B820, 0x2CEA2, + 0x2CEB0, + 0x2EBE1, 0x2F800, 0x2FA1E, 0xE0100, @@ -95365,50 +97411,51 @@ static const U8 WB_table[24][24] = { /* Generated from: * 59e717586b720a821ee0d7397679d5322e38b49f6fb7840545aedf669c733b70 lib/Unicode/UCD.pm - * 47cb62a53beea6d0263e2147331c7e751853c9327225d95bbe2d9e1dc3e1aa44 lib/unicore/ArabicShaping.txt - * 153f0a100c315f9f3945e78f57137611d36c44b3a975919c499fd403413fede8 lib/unicore/BidiBrackets.txt - * fbe806975c1bf9fc9960bbaa39ff6290c42c7da8315f9cd459109b024cc1c485 lib/unicore/BidiMirroring.txt - * 612127d4889032e55d82522e4a0c19793bda8aa8da14ecb3c696d17c83e6be13 lib/unicore/Blocks.txt - * 37d40cf8c2c35637f4a04e746814e1fc4eb764c272bed9238a87ee96a4866857 lib/unicore/CaseFolding.txt - * 5623df16856ad4007c60bdfff6f054e087521becd24cb4006be69c3a1d851aee lib/unicore/CompositionExclusions.txt - * 5cb15b04693c43df16e0d304deca049e93b001445d163184e0ff1b7c8c852146 lib/unicore/DAge.txt - * 6662c7e30b572df5d948c092692f52bcc79ab36d49a063a73d6435042db6fb3b lib/unicore/DCoreProperties.txt - * 02d8e12cea7c61a9f3cc5fbf8eaceadf8da23fe83d60c64cf647088830b810cc lib/unicore/DNormalizationProps.txt - * 3382cb4980e0021e9d4312f2d099315cfab6100ce0ff63a22d6937bfa720bcb7 lib/unicore/EastAsianWidth.txt - * cb02ff25c375e78c82afffc852180eae7fc17c2f4434e697107720d05c52b26e lib/unicore/HangulSyllableType.txt - * 850043bc9db08eddb271e43ed9176b865df76745a5fb6e9a4a1d9e54e5036471 lib/unicore/IndicPositionalCategory.txt - * 90a3a00a5f5810850986c9279849b03c2f3133cfeeefb0554e851dd5ad7324dc lib/unicore/IndicSyllabicCategory.txt - * bbd36a8d27f76e0fe0f2b0ca2827ac80da4b4a8d5247f0b0670fcaaac68ae6e1 lib/unicore/Jamo.txt - * e2698584982ccd96e0c688bbcd4d2c48a23805baa0a0084388ef2e50ebd30aad lib/unicore/LineBreak.txt - * 9d5353b1d318e72a63a49aa6a6a051d350382ea44b2cf31fe925bb94ce7e129b lib/unicore/NameAliases.txt - * 009477f536f63016d901aeb1a4c820ad291e30e72ee9eb9ac1dfb6294a8a9bcc lib/unicore/NamedSequences.txt - * f413ea8dbd3858de72f3148b47dd0586019761357d1481e3b65f3a025bc27f82 lib/unicore/PropList.txt - * 56582d9875c1997876cf09305ccfc83448195de5d84d6374c78efaffeca4dfd7 lib/unicore/PropValueAliases.txt - * 047ab0f815b6d1b30a863d6fcbd49e6358e168a3bd6c7189e80ab9863957d222 lib/unicore/PropertyAliases.txt - * cde011921972dffe3e30dcbc7afbf069bf2eb01269097111dd7533b4c524caac lib/unicore/ScriptExtensions.txt - * fba415952f5654145acad220dc2b878f815c673474d2bb4928934e3ba6ccca1d lib/unicore/Scripts.txt - * dfc4f159c5c68328114ff17cd520451714a72ff48657287e5fe2f64344980695 lib/unicore/SpecialCasing.txt - * 68dfc414d28257b9b5d6ddbb8b466c768c00ebdf6cbf7784364a9b6cad55ee8f lib/unicore/UnicodeData.txt - * c76e7ed44a602f85161758ec54d2bcbcb7baf38f97720605a3e81ce02af47061 lib/unicore/auxiliary/GCBTest.txt - * 4bb8931857e0a698fd2ec4a51a84c6de33e48a50d8b4bf0b57d960c41d77a191 lib/unicore/auxiliary/GraphemeBreakProperty.txt - * 0c609ae4a32a89905c004010ef29885df3c60a941311a1a6e16003333d7fcdc8 lib/unicore/auxiliary/LBTest.txt - * 26afdd5f38561167807b0f191af55b05761029ae6be2b7fe85b88f28effc66b5 lib/unicore/auxiliary/SBTest.txt - * 53982766eeaf26674e7e2ec956c52846d52992ea9f4f1a202d488fb5cd76dd10 lib/unicore/auxiliary/SentenceBreakProperty.txt - * 7f60beacc5ec5671edb56db36defc90cfc0016de4fd2bdfde7a3e4ec209840ce lib/unicore/auxiliary/WBTest.txt - * cb2db065c77287e0f1d35b8c9b473d848b7566a1670439f67c357ca393084043 lib/unicore/auxiliary/WordBreakProperty.txt - * 73573a4bee7f7377d936bc1710cd578001d00ba516e72ee54e906ae51a8c1fcb lib/unicore/extracted/DBidiClass.txt - * ae8f55d8bb2bb69a63f70eef38cf5921fc3ba8e06d4d88f37950d32313a14754 lib/unicore/extracted/DBinaryProperties.txt - * cf263ac4848d47264300139f97ed15c2c22896d2cef411483cbe292098c08bea lib/unicore/extracted/DCombiningClass.txt - * 5bac89caf8d1fa23fcbbbf4d49ea0699b680ef1a73cbfa0daaac38c993906a74 lib/unicore/extracted/DDecompositionType.txt - * e17138d36cd91f0e0d16437780a887c5ac637bde0de370b96f08a3424fcc322f lib/unicore/extracted/DEastAsianWidth.txt - * fad25c183f4d439622c6be33c22ed709cdc4ac19feef0250527cf319a06952fe lib/unicore/extracted/DGeneralCategory.txt - * c0d080b188fbe67dead10a3897dd2ca23da862c7f0b03508a92dcf27cd7e1f41 lib/unicore/extracted/DJoinGroup.txt - * 3a8f8642084ed23b0de52af72dea0ff3d0b6928e6c7442832c663899e2b85e9d lib/unicore/extracted/DJoinType.txt - * 37f6186253da9824bdb27f4ad867bfe8c25d4dc6bdb2f05585e40a034675a348 lib/unicore/extracted/DLineBreak.txt - * ef24061b5a5dc93d7e90c2e34530ec757180ee75d872cba65ffc946e52624ae8 lib/unicore/extracted/DNumType.txt - * a197371fec9a1b517058b440841f60f9378d81682084eef8db22a88cb2f96e90 lib/unicore/extracted/DNumValues.txt + * ff4404ec64f308bdf7714c50f9fdf0d1d0bf3c34db4d0a67e58ef0c6f88e818f lib/unicore/ArabicShaping.txt + * 292171a0a1c13d7e581e8781eb4cdf248243b1ab267354a63c7a14429dea2740 lib/unicore/BidiBrackets.txt + * 8f2695cc42989a79a715ab0d2892bd0c998759180cfdfb998674447f48231940 lib/unicore/BidiMirroring.txt + * 5ae1649a42ed8ae8cb885af79563f00a9ae17e602405a56ed8aca214da14eea7 lib/unicore/Blocks.txt + * 97b43ed3f4b80572c2114200e5e43a6b923d984c74a6caaf27de5b8462c04cb0 lib/unicore/CaseFolding.txt + * eedcf6932b4081ee65878454588c803af910a5aed7c8c67e3c38701cbee9b9e4 lib/unicore/CompositionExclusions.txt + * 90e48995643f45b08f0ef67fb90de3bb18e26765272bcc0c35c840cbc10b37c1 lib/unicore/DAge.txt + * e6ca152259189ec4bc2297e93c6c88f86e162cc52814198263497f3c9b46cbe9 lib/unicore/DCoreProperties.txt + * 3e255ccdff4b00cfe0be53bbd583e4fe2e7d4039138579543548a5ecfce45242 lib/unicore/DNormalizationProps.txt + * 9f34e2d3ea27ca82f4f14b62411861d1f07c4b9e296d54da112a09cad5b9a48d lib/unicore/EastAsianWidth.txt + * 983810c739b56b9ff0fcb5db018c67d584ee515e8a5f4d9348c79ee85167ec37 lib/unicore/HangulSyllableType.txt + * 7d514a779ee4baf91262bd83c400cb502c3e435dba4b880c876506be32b8e1d0 lib/unicore/IndicPositionalCategory.txt + * f6acead8f84df5c72f3fb70dfc9375279926e4d8ef3480ffff3723095e9804aa lib/unicore/IndicSyllabicCategory.txt + * c8ed526f70443535ca6b705980a08c774017ff17e921202dcb7b71ae554047b6 lib/unicore/Jamo.txt + * 6b204c3727b77699d04a574b22b1e44facab038642095b8565b49762970d9bf8 lib/unicore/LineBreak.txt + * f2357d2bd3526b9e830de72ab038dcfc65a2dff24bcb4c6325c92071eb341f88 lib/unicore/NameAliases.txt + * 6c3e6bd1e58b640076a23b83318a8bf6a691d7fc2b2106114d77c5c5a898bced lib/unicore/NamedSequences.txt + * 58dbf8fedbd5bf67a3bd5c10eda2f2acf2eae59df5f77884a6f158e98f75cf8c lib/unicore/PropList.txt + * a6b0467c3cc7aa4e57d4e5cc7f6e9562b79cf4426dfe438517c28b368ed3e673 lib/unicore/PropValueAliases.txt + * 9ca521224e08d30696516ae6bc3d4434659c45df16047c0d31e440783c163a3b lib/unicore/PropertyAliases.txt + * 3fd0d744a816ddfd06809f92151ae4a73ec970ac2006806c269732d8951f3911 lib/unicore/ScriptExtensions.txt + * d02e24e4c516e9090b6bc9c2d2c8f4c89510b6ed8c5e859d0a861b0dc5cf372d lib/unicore/Scripts.txt + * e9947a0e86f27353f0e776403c4826675001210bd39d7114118a8864a57f7472 lib/unicore/SpecialCasing.txt + * 52423e4d7492167b62f518f68d54db88930abbbff7f11edfcaec8f726498cab1 lib/unicore/UnicodeData.txt + * f28caf260635cebf25fd58124bdc9aa22af08ba4d039ffc584365fb41a31cda5 lib/unicore/VerticalOrientation.txt + * 718d174957712410bfad782b10d557e1047574d7ef1642d6bb122f8ca5662c82 lib/unicore/auxiliary/GCBTest.txt + * 3b66caefc4fa877d0e50dbbbfa39658c86e29b26c6f206f68d7aec192d4c59b6 lib/unicore/auxiliary/GraphemeBreakProperty.txt + * 2aad3836c37fc4c2fa2a24f21586fb3a931dacaf0a1c845a6dc6395f30bd79a7 lib/unicore/auxiliary/LBTest.txt + * eacc03e39dddc60cc59ec9bd274b8ac8dfa25d61745ef0d5c8aa1c151a5b68ba lib/unicore/auxiliary/SBTest.txt + * e45fa8195bb413b901cc1e3772dfea2cead86805d46a51e3480a5a256e8c24d9 lib/unicore/auxiliary/SentenceBreakProperty.txt + * 95789f62e3b1e781dc9ed78f3983d39ff1a5e36ff0b497d6e610446df902b0f6 lib/unicore/auxiliary/WBTest.txt + * c207e8ebd06ee591a27b1087f2971f4cd93e960103c453d85d1d9ba26fb8b202 lib/unicore/auxiliary/WordBreakProperty.txt + * a3c0839826a30166b2bb06ba58df403547b8c3d9eae995ef889d20d115f4b223 lib/unicore/extracted/DBidiClass.txt + * 280afe22f6c4d56566d17d6d1400f33465a979c96f3d99ff3bff9bd14d17e734 lib/unicore/extracted/DBinaryProperties.txt + * db7fd6a5e6f068c47dbc3b74fb633fb1d09d17073410fe435295d05ce925c5f6 lib/unicore/extracted/DCombiningClass.txt + * 8204c07a7c217bdf22525030ad7b4fb991edf463bffcca7e6dba46b9992e0d99 lib/unicore/extracted/DDecompositionType.txt + * e343113719b660bdd81217ec101ce751f844fca0e8d6f15fb21c8ee7dfe7c14c lib/unicore/extracted/DEastAsianWidth.txt + * 07c55b0ed7271fe1a5f4d68059291288b1a8ad61940602d18956fd87390c2d9e lib/unicore/extracted/DGeneralCategory.txt + * d788b9362ec7681e98f8b9d6ef276546e1a6207dda05317ede55bd686b0940a9 lib/unicore/extracted/DJoinGroup.txt + * ebbea3c93eeb7431378885aebac0490d77f6900239c9176f90b6fee030903d96 lib/unicore/extracted/DJoinType.txt + * be0f129691d479aa38646e4ca0ec1ee576ae7f75b0300a5624a7fa862fa8abba lib/unicore/extracted/DLineBreak.txt + * 92449d354d9f6b6f2f97a292ebb59f6344ffdeb83d120d7d23e569c43ba67cd5 lib/unicore/extracted/DNumType.txt + * e3a319527153b0c6c0c549b40fc6f3a01a7a0dcd6620784391db25901df3b154 lib/unicore/extracted/DNumValues.txt * fd5dda65f76b9209787c5d0bb99f4cde8708c0bf86bcefe344d2d474a0306e28 lib/unicore/mktables - * cdecb300baad839a6f62791229f551a4fa33f3cbdca08e378dc976466354e778 lib/unicore/version + * 21653d2744fdd071f9ef138c805393901bb9547cf3e777ebf50215a191f986ea lib/unicore/version * 913d2f93f3cb6cdf1664db888bf840bc4eb074eef824e082fceda24a9445e60c regen/charset_translations.pl * 48418cbf454eb9ef35c73468ed5ef72ad8603490eabe74181ce4fae42ec72579 regen/mk_invlists.pl * ex: set ro: */ diff --git a/lib/Unicode/UCD.t b/lib/Unicode/UCD.t index a7bb666483..32f01086bc 100644 --- a/lib/Unicode/UCD.t +++ b/lib/Unicode/UCD.t @@ -19,7 +19,7 @@ use Test::More; use Unicode::UCD qw(charinfo charprop charprops_all); -my $expected_version = '9.0.0'; +my $expected_version = '10.0.0'; my $current_version = Unicode::UCD::UnicodeVersion; my $v_unicode_version = pack "C*", split /\./, $current_version; my $unknown_script = ($v_unicode_version lt v5.0.0) diff --git a/lib/unicore/ArabicShaping.txt b/lib/unicore/ArabicShaping.txt index cddc5b4016..f2ef1fad74 100644 --- a/lib/unicore/ArabicShaping.txt +++ b/lib/unicore/ArabicShaping.txt @@ -1,6 +1,6 @@ -# ArabicShaping-9.0.0.txt -# Date: 2016-02-24, 22:25:00 GMT [RP] -# © 2016 Unicode®, Inc. +# ArabicShaping-10.0.0.txt +# Date: 2017-02-16, 00:00:00 GMT [RP, KW] +# © 2017 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html # @@ -86,7 +86,7 @@ # Note: Code points that are not explicitly listed in this file are # either of joining type T or U: # -# - Those that not explicitly listed that are of General Category Mn, Me, or Cf +# - Those that are not explicitly listed and that are of General Category Mn, Me, or Cf # have joining type T. # - All others not explicitly listed have joining type U. # @@ -413,6 +413,20 @@ 0857; MANDAIC KAD; U; No_Joining_Group 0858; MANDAIC AIN; U; No_Joining_Group +# Syriac Supplement Characters + +0860; MALAYALAM NGA; D; MALAYALAM NGA +0861; MALAYALAM JA; U; MALAYALAM JA +0862; MALAYALAM NYA; D; MALAYALAM NYA +0863; MALAYALAM TTA; D; MALAYALAM TTA +0864; MALAYALAM NNA; D; MALAYALAM NNA +0865; MALAYALAM NNNA; D; MALAYALAM NNNA +0866; MALAYALAM BHA; U; MALAYALAM BHA +0867; MALAYALAM RA; R; MALAYALAM RA +0868; MALAYALAM LLA; D; MALAYALAM LLA +0869; MALAYALAM LLLA; R; MALAYALAM LLLA +086A; MALAYALAM SSA; R; MALAYALAM SSA + # Arabic Extended-A Characters 08A0; DOTLESS BEH WITH V BELOW; D; BEH diff --git a/lib/unicore/BidiBrackets.txt b/lib/unicore/BidiBrackets.txt index eb02a24bfc..2114e632b9 100644 --- a/lib/unicore/BidiBrackets.txt +++ b/lib/unicore/BidiBrackets.txt @@ -1,6 +1,6 @@ -# BidiBrackets-9.0.0.txt -# Date: 2016-06-07, 22:30:00 GMT [AG, LI, KW] -# © 2016 Unicode®, Inc. +# BidiBrackets-10.0.0.txt +# Date: 2017-04-12, 17:30:00 GMT [AG, LI, KW] +# © 2017 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html # @@ -8,7 +8,7 @@ # For documentation, see http://www.unicode.org/reports/tr44/ # # Bidi_Paired_Bracket and Bidi_Paired_Bracket_Type Properties -# +# # This file is a normative contributory data file in the Unicode # Character Database. # diff --git a/lib/unicore/BidiMirroring.txt b/lib/unicore/BidiMirroring.txt index 68142c5e32..cbb61c4b57 100644 --- a/lib/unicore/BidiMirroring.txt +++ b/lib/unicore/BidiMirroring.txt @@ -1,13 +1,13 @@ -# BidiMirroring-9.0.0.txt -# Date: 2016-01-21, 22:00:00 GMT [KW, LI] -# © 2016 Unicode®, Inc. +# BidiMirroring-10.0.0.txt +# Date: 2017-04-12, 17:30:00 GMT [KW, LI] +# © 2017 Unicode®, Inc. # For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database # For documentation, see http://www.unicode.org/reports/tr44/ # # Bidi_Mirroring_Glyph Property -# +# # This file is an informative contributory data file in the # Unicode Character Database. # @@ -15,20 +15,20 @@ # value, for which there is another Unicode character that typically has a glyph # that is the mirror image of the original character's glyph. # -# The repertoire covered by the file is Unicode 9.0.0. -# +# The repertoire covered by the file is Unicode 10.0.0. +# # The file contains a list of lines with mappings from one code point # to another one for character-based mirroring. # Note that for "real" mirroring, a rendering engine needs to select # appropriate alternative glyphs, and that many Unicode characters do not # have a mirror-image Unicode character. -# +# # Each mapping line contains two fields, separated by a semicolon (';'). # Each of the two fields contains a code point represented as a # variable-length hexadecimal value with 4 to 6 digits. # A comment indicates where the characters are "BEST FIT" mirroring. -# -# Code points for which Bidi_Mirrored=Yes, but for which no appropriate +# +# Code points for which Bidi_Mirrored=Yes, but for which no appropriate # characters exist with mirrored glyphs, are # listed as comments at the end of the file. # @@ -38,14 +38,14 @@ # point has the default value for the Bidi_Mirroring_Glyph property, # that means that no other character exists whose glyph is suitable # for character-based mirroring. -# +# # For information on bidi mirroring, see UAX #9: Unicode Bidirectional Algorithm, # at http://www.unicode.org/unicode/reports/tr9/ -# +# # This file was originally created by Markus Scherer. # Extended for Unicode 3.2, 4.0, 4.1, 5.0, 5.1, 5.2, and 6.0 by Ken Whistler, # and for subsequent versions by Ken Whistler and Laurentiu Iancu. -# +# # ############################################################ # # Property: Bidi_Mirroring_Glyph diff --git a/lib/unicore/Blocks.txt b/lib/unicore/Blocks.txt index 74c41e58a8..a4f851b14a 100644 --- a/lib/unicore/Blocks.txt +++ b/lib/unicore/Blocks.txt @@ -1,6 +1,6 @@ -# Blocks-9.0.0.txt -# Date: 2016-02-05, 23:48:00 GMT [KW] -# © 2016 Unicode®, Inc. +# Blocks-10.0.0.txt +# Date: 2017-04-12, 17:30:00 GMT [KW] +# © 2017 Unicode®, Inc. # For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database @@ -14,12 +14,12 @@ # Note: When comparing block names, casing, whitespace, hyphens, # and underbars are ignored. # For example, "Latin Extended-A" and "latin extended a" are equivalent. -# For more information on the comparison of property values, +# For more information on the comparison of property values, # see UAX #44: http://www.unicode.org/reports/tr44/ # # All block ranges start with a value where (cp MOD 16) = 0, # and end with a value where (cp MOD 16) = 15. In other words, -# the last hexadecimal digit of the start of range is ...0 +# the last hexadecimal digit of the start of range is ...0 # and the last hexadecimal digit of the end of range is ...F. # This constraint on block ranges guarantees that allocations # are done in terms of whole columns, and that code chart display @@ -51,6 +51,7 @@ 07C0..07FF; NKo 0800..083F; Samaritan 0840..085F; Mandaic +0860..086F; Syriac Supplement 08A0..08FF; Arabic Extended-A 0900..097F; Devanagari 0980..09FF; Bengali @@ -253,9 +254,12 @@ FFF0..FFFF; Specials 11680..116CF; Takri 11700..1173F; Ahom 118A0..118FF; Warang Citi +11A00..11A4F; Zanabazar Square +11A50..11AAF; Soyombo 11AC0..11AFF; Pau Cin Hau 11C00..11C6F; Bhaiksuki 11C70..11CBF; Marchen +11D00..11D5F; Masaram Gondi 12000..123FF; Cuneiform 12400..1247F; Cuneiform Numbers and Punctuation 12480..1254F; Early Dynastic Cuneiform @@ -270,6 +274,8 @@ FFF0..FFFF; Specials 17000..187FF; Tangut 18800..18AFF; Tangut Components 1B000..1B0FF; Kana Supplement +1B100..1B12F; Kana Extended-A +1B170..1B2FF; Nushu 1BC00..1BC9F; Duployan 1BCA0..1BCAF; Shorthand Format Controls 1D000..1D0FF; Byzantine Musical Symbols @@ -300,6 +306,7 @@ FFF0..FFFF; Specials 2A700..2B73F; CJK Unified Ideographs Extension C 2B740..2B81F; CJK Unified Ideographs Extension D 2B820..2CEAF; CJK Unified Ideographs Extension E +2CEB0..2EBEF; CJK Unified Ideographs Extension F 2F800..2FA1F; CJK Compatibility Ideographs Supplement E0000..E007F; Tags E0100..E01EF; Variation Selectors Supplement diff --git a/lib/unicore/CJKRadicals.txt b/lib/unicore/CJKRadicals.txt index e68bd1e3bc..62865efbae 100644 --- a/lib/unicore/CJKRadicals.txt +++ b/lib/unicore/CJKRadicals.txt @@ -1,6 +1,6 @@ -# CJKRadicals-9.0.0.txt -# Date: 2016-01-22, 06:00:00 GMT [RC, KW, LI] -# © 2016 Unicode®, Inc. +# CJKRadicals-10.0.0.txt +# Date: 2017-02-15, 00:00:00 GMT [RC, KW, LI] +# © 2017 Unicode®, Inc. # For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database diff --git a/lib/unicore/CaseFolding.txt b/lib/unicore/CaseFolding.txt index 372ee68bd8..efdf18e441 100644 --- a/lib/unicore/CaseFolding.txt +++ b/lib/unicore/CaseFolding.txt @@ -1,6 +1,6 @@ -# CaseFolding-9.0.0.txt -# Date: 2016-03-02, 18:54:54 GMT -# © 2016 Unicode®, Inc. +# CaseFolding-10.0.0.txt +# Date: 2017-04-14, 05:40:18 GMT +# © 2017 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html # @@ -24,7 +24,7 @@ # # NOTE: case folding does not preserve normalization formats! # -# For information on case folding, including how to have case folding +# For information on case folding, including how to have case folding # preserve normalization formats, see Section 3.13 Default Case Algorithms in # The Unicode Standard. # diff --git a/lib/unicore/CompositionExclusions.txt b/lib/unicore/CompositionExclusions.txt index 1999ed1328..ff42508686 100644 --- a/lib/unicore/CompositionExclusions.txt +++ b/lib/unicore/CompositionExclusions.txt @@ -1,6 +1,6 @@ -# CompositionExclusions-9.0.0.txt -# Date: 2016-01-21, 22:00:00 GMT [KW, LI] -# © 2016 Unicode®, Inc. +# CompositionExclusions-10.0.0.txt +# Date: 2017-02-15, 00:00:00 GMT [KW, LI] +# © 2017 Unicode®, Inc. # For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database diff --git a/lib/unicore/DAge.txt b/lib/unicore/DAge.txt index e9c7cd65f7..917afd413c 100644 --- a/lib/unicore/DAge.txt +++ b/lib/unicore/DAge.txt @@ -1,6 +1,6 @@ -# DerivedAge-9.0.0.txt -# Date: 2016-03-02, 18:54:54 GMT -# © 2016 Unicode®, Inc. +# DerivedAge-10.0.0.txt +# Date: 2017-04-14, 05:40:18 GMT +# © 2017 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html # @@ -13,7 +13,7 @@ # Notes: # # - The term 'assigned' means that a previously reserved code point was assigned -# to be a character (graphic, format, control, or private-use); +# to be a character (graphic, format, control, or private-use); # a noncharacter code point; or a surrogate code point. # For more information, see The Unicode Standard Section 2.4 # @@ -1598,4 +1598,53 @@ A8C5 ; 9.0 # SAURASHTRA SIGN CANDRABINDU # Total code points: 7500 +# ================================================ + +# Age=V10_0 + +# Newly assigned in Unicode 10.0.0 (June, 2017) + +0860..086A ; 10.0 # [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA +09FC..09FD ; 10.0 # [2] BENGALI LETTER VEDIC ANUSVARA..BENGALI ABBREVIATION SIGN +0AFA..0AFF ; 10.0 # [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE +0D00 ; 10.0 # MALAYALAM SIGN COMBINING ANUSVARA ABOVE +0D3B..0D3C ; 10.0 # [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA +1CF7 ; 10.0 # VEDIC SIGN ATIKRAMA +1DF6..1DF9 ; 10.0 # [4] COMBINING KAVYKA ABOVE RIGHT..COMBINING WIDE INVERTED BRIDGE BELOW +20BF ; 10.0 # BITCOIN SIGN +23FF ; 10.0 # OBSERVER EYE SYMBOL +2BD2 ; 10.0 # GROUP MARK +2E45..2E49 ; 10.0 # [5] INVERTED LOW KAVYKA..DOUBLE STACKED COMMA +312E ; 10.0 # BOPOMOFO LETTER O WITH DOT ABOVE +9FD6..9FEA ; 10.0 # [21] CJK UNIFIED IDEOGRAPH-9FD6..CJK UNIFIED IDEOGRAPH-9FEA +1032D..1032F ; 10.0 # [3] OLD ITALIC LETTER YE..OLD ITALIC LETTER SOUTHERN TSE +11A00..11A47 ; 10.0 # [72] ZANABAZAR SQUARE LETTER A..ZANABAZAR SQUARE SUBJOINER +11A50..11A83 ; 10.0 # [52] SOYOMBO LETTER A..SOYOMBO LETTER KSSA +11A86..11A9C ; 10.0 # [23] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO MARK DOUBLE SHAD +11A9E..11AA2 ; 10.0 # [5] SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME..SOYOMBO TERMINAL MARK-2 +11D00..11D06 ; 10.0 # [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E +11D08..11D09 ; 10.0 # [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O +11D0B..11D36 ; 10.0 # [44] MASARAM GONDI LETTER AU..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; 10.0 # MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; 10.0 # [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D47 ; 10.0 # [9] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI RA-KARA +11D50..11D59 ; 10.0 # [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE +16FE1 ; 10.0 # NUSHU ITERATION MARK +1B002..1B11E ; 10.0 # [285] HENTAIGANA LETTER A-1..HENTAIGANA LETTER N-MU-MO-2 +1B170..1B2FB ; 10.0 # [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB +1F260..1F265 ; 10.0 # [6] ROUNDED SYMBOL FOR FU..ROUNDED SYMBOL FOR CAI +1F6D3..1F6D4 ; 10.0 # [2] STUPA..PAGODA +1F6F7..1F6F8 ; 10.0 # [2] SLED..FLYING SAUCER +1F900..1F90B ; 10.0 # [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT +1F91F ; 10.0 # I LOVE YOU HAND SIGN +1F928..1F92F ; 10.0 # [8] FACE WITH ONE EYEBROW RAISED..SHOCKED FACE WITH EXPLODING HEAD +1F931..1F932 ; 10.0 # [2] BREAST-FEEDING..PALMS UP TOGETHER +1F94C ; 10.0 # CURLING STONE +1F95F..1F96B ; 10.0 # [13] DUMPLING..CANNED FOOD +1F992..1F997 ; 10.0 # [6] GIRAFFE FACE..CRICKET +1F9D0..1F9E6 ; 10.0 # [23] FACE WITH MONOCLE..SOCKS +2CEB0..2EBE0 ; 10.0 # [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 + +# Total code points: 8518 + # EOF diff --git a/lib/unicore/DCoreProperties.txt b/lib/unicore/DCoreProperties.txt index 0db031db01..16cd9b88bf 100644 --- a/lib/unicore/DCoreProperties.txt +++ b/lib/unicore/DCoreProperties.txt @@ -1,6 +1,6 @@ -# DerivedCoreProperties-9.0.0.txt -# Date: 2016-06-01, 10:34:24 GMT -# © 2016 Unicode®, Inc. +# DerivedCoreProperties-10.0.0.txt +# Date: 2017-03-19, 00:05:15 GMT +# © 2017 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html # @@ -340,6 +340,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 0828 ; Alphabetic # Lm SAMARITAN MODIFIER LETTER I 0829..082C ; Alphabetic # Mn [4] SAMARITAN VOWEL SIGN LONG I..SAMARITAN VOWEL SIGN SUKUN 0840..0858 ; Alphabetic # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN +0860..086A ; Alphabetic # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 08A0..08B4 ; Alphabetic # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW 08B6..08BD ; Alphabetic # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON 08D4..08DF ; Alphabetic # Mn [12] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH WORD WAQFA @@ -379,6 +380,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 09DF..09E1 ; Alphabetic # Lo [3] BENGALI LETTER YYA..BENGALI LETTER VOCALIC LL 09E2..09E3 ; Alphabetic # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL 09F0..09F1 ; Alphabetic # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL +09FC ; Alphabetic # Lo BENGALI LETTER VEDIC ANUSVARA 0A01..0A02 ; Alphabetic # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI 0A03 ; Alphabetic # Mc GURMUKHI SIGN VISARGA 0A05..0A0A ; Alphabetic # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU @@ -416,6 +418,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 0AE0..0AE1 ; Alphabetic # Lo [2] GUJARATI LETTER VOCALIC RR..GUJARATI LETTER VOCALIC LL 0AE2..0AE3 ; Alphabetic # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL 0AF9 ; Alphabetic # Lo GUJARATI LETTER ZHA +0AFA..0AFC ; Alphabetic # Mn [3] GUJARATI SIGN SUKUN..GUJARATI SIGN MADDAH 0B01 ; Alphabetic # Mn ORIYA SIGN CANDRABINDU 0B02..0B03 ; Alphabetic # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA 0B05..0B0C ; Alphabetic # Lo [8] ORIYA LETTER A..ORIYA LETTER VOCALIC L @@ -491,7 +494,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 0CE0..0CE1 ; Alphabetic # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CE2..0CE3 ; Alphabetic # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL 0CF1..0CF2 ; Alphabetic # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA -0D01 ; Alphabetic # Mn MALAYALAM SIGN CANDRABINDU +0D00..0D01 ; Alphabetic # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU 0D02..0D03 ; Alphabetic # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA 0D05..0D0C ; Alphabetic # Lo [8] MALAYALAM LETTER A..MALAYALAM LETTER VOCALIC L 0D0E..0D10 ; Alphabetic # Lo [3] MALAYALAM LETTER E..MALAYALAM LETTER AI @@ -792,12 +795,12 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 30A1..30FA ; Alphabetic # Lo [90] KATAKANA LETTER SMALL A..KATAKANA LETTER VO 30FC..30FE ; Alphabetic # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK 30FF ; Alphabetic # Lo KATAKANA DIGRAPH KOTO -3105..312D ; Alphabetic # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH +3105..312E ; Alphabetic # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE 3131..318E ; Alphabetic # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE 31A0..31BA ; Alphabetic # Lo [27] BOPOMOFO LETTER BU..BOPOMOFO LETTER ZY 31F0..31FF ; Alphabetic # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO 3400..4DB5 ; Alphabetic # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 -4E00..9FD5 ; Alphabetic # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5 +4E00..9FEA ; Alphabetic # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA A000..A014 ; Alphabetic # Lo [21] YI SYLLABLE IT..YI SYLLABLE E A015 ; Alphabetic # Lm YI SYLLABLE WU A016..A48C ; Alphabetic # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR @@ -955,7 +958,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 10280..1029C ; Alphabetic # Lo [29] LYCIAN LETTER A..LYCIAN LETTER X 102A0..102D0 ; Alphabetic # Lo [49] CARIAN LETTER A..CARIAN LETTER UUU3 10300..1031F ; Alphabetic # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS -10330..10340 ; Alphabetic # Lo [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA +1032D..10340 ; Alphabetic # Lo [20] OLD ITALIC LETTER YE..GOTHIC LETTER PAIRTHRA 10341 ; Alphabetic # Nl GOTHIC LETTER NINETY 10342..10349 ; Alphabetic # Lo [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL 1034A ; Alphabetic # Nl GOTHIC LETTER NINE HUNDRED @@ -1115,6 +1118,23 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 11727..1172A ; Alphabetic # Mn [4] AHOM VOWEL SIGN AW..AHOM VOWEL SIGN AM 118A0..118DF ; Alphabetic # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 118FF ; Alphabetic # Lo WARANG CITI OM +11A00 ; Alphabetic # Lo ZANABAZAR SQUARE LETTER A +11A01..11A06 ; Alphabetic # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O +11A07..11A08 ; Alphabetic # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU +11A09..11A0A ; Alphabetic # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A0B..11A32 ; Alphabetic # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA +11A35..11A38 ; Alphabetic # Mn [4] ZANABAZAR SQUARE SIGN CANDRABINDU..ZANABAZAR SQUARE SIGN ANUSVARA +11A39 ; Alphabetic # Mc ZANABAZAR SQUARE SIGN VISARGA +11A3A ; Alphabetic # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA +11A3B..11A3E ; Alphabetic # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A50 ; Alphabetic # Lo SOYOMBO LETTER A +11A51..11A56 ; Alphabetic # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A57..11A58 ; Alphabetic # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU +11A59..11A5B ; Alphabetic # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A5C..11A83 ; Alphabetic # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA +11A86..11A89 ; Alphabetic # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA +11A8A..11A96 ; Alphabetic # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A97 ; Alphabetic # Mc SOYOMBO SIGN VISARGA 11AC0..11AF8 ; Alphabetic # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL 11C00..11C08 ; Alphabetic # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E ; Alphabetic # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA @@ -1131,6 +1151,16 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 11CB2..11CB3 ; Alphabetic # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E 11CB4 ; Alphabetic # Mc MARCHEN VOWEL SIGN O 11CB5..11CB6 ; Alphabetic # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D00..11D06 ; Alphabetic # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E +11D08..11D09 ; Alphabetic # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O +11D0B..11D30 ; Alphabetic # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA +11D31..11D36 ; Alphabetic # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; Alphabetic # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; Alphabetic # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D41 ; Alphabetic # Mn [3] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI SIGN VISARGA +11D43 ; Alphabetic # Mn MASARAM GONDI SIGN CANDRA +11D46 ; Alphabetic # Lo MASARAM GONDI REPHA +11D47 ; Alphabetic # Mn MASARAM GONDI RA-KARA 12000..12399 ; Alphabetic # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; Alphabetic # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12480..12543 ; Alphabetic # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU @@ -1148,10 +1178,11 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 16F50 ; Alphabetic # Lo MIAO LETTER NASALIZATION 16F51..16F7E ; Alphabetic # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG 16F93..16F9F ; Alphabetic # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 -16FE0 ; Alphabetic # Lm TANGUT ITERATION MARK +16FE0..16FE1 ; Alphabetic # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK 17000..187EC ; Alphabetic # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC 18800..18AF2 ; Alphabetic # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755 -1B000..1B001 ; Alphabetic # Lo [2] KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE +1B000..1B11E ; Alphabetic # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1B170..1B2FB ; Alphabetic # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 1BC00..1BC6A ; Alphabetic # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M 1BC70..1BC7C ; Alphabetic # Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK 1BC80..1BC88 ; Alphabetic # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL @@ -1235,9 +1266,10 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 2A700..2B734 ; Alphabetic # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 2B740..2B81D ; Alphabetic # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; Alphabetic # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 +2CEB0..2EBE0 ; Alphabetic # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; Alphabetic # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D -# Total code points: 118240 +# Total code points: 126629 # ================================================ @@ -2798,6 +2830,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 0AC7..0AC8 ; Case_Ignorable # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI 0ACD ; Case_Ignorable # Mn GUJARATI SIGN VIRAMA 0AE2..0AE3 ; Case_Ignorable # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0AFA..0AFF ; Case_Ignorable # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE 0B01 ; Case_Ignorable # Mn ORIYA SIGN CANDRABINDU 0B3C ; Case_Ignorable # Mn ORIYA SIGN NUKTA 0B3F ; Case_Ignorable # Mn ORIYA VOWEL SIGN I @@ -2820,7 +2853,8 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 0CC6 ; Case_Ignorable # Mn KANNADA VOWEL SIGN E 0CCC..0CCD ; Case_Ignorable # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA 0CE2..0CE3 ; Case_Ignorable # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL -0D01 ; Case_Ignorable # Mn MALAYALAM SIGN CANDRABINDU +0D00..0D01 ; Case_Ignorable # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU +0D3B..0D3C ; Case_Ignorable # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA 0D41..0D44 ; Case_Ignorable # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR 0D4D ; Case_Ignorable # Mn MALAYALAM SIGN VIRAMA 0D62..0D63 ; Case_Ignorable # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL @@ -2916,7 +2950,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 1D2C..1D6A ; Case_Ignorable # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI 1D78 ; Case_Ignorable # Lm MODIFIER LETTER CYRILLIC EN 1D9B..1DBF ; Case_Ignorable # Lm [37] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL THETA -1DC0..1DF5 ; Case_Ignorable # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE +1DC0..1DF9 ; Case_Ignorable # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW 1DFB..1DFF ; Case_Ignorable # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 1FBD ; Case_Ignorable # Sk GREEK KORONIS 1FBF..1FC1 ; Case_Ignorable # Sk [3] GREEK PSILI..GREEK DIALYTIKA AND PERISPOMENI @@ -3078,6 +3112,15 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 1171D..1171F ; Case_Ignorable # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA 11722..11725 ; Case_Ignorable # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU 11727..1172B ; Case_Ignorable # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER +11A01..11A06 ; Case_Ignorable # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O +11A09..11A0A ; Case_Ignorable # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A33..11A38 ; Case_Ignorable # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A3B..11A3E ; Case_Ignorable # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A47 ; Case_Ignorable # Mn ZANABAZAR SQUARE SUBJOINER +11A51..11A56 ; Case_Ignorable # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A59..11A5B ; Case_Ignorable # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A8A..11A96 ; Case_Ignorable # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A98..11A99 ; Case_Ignorable # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER 11C30..11C36 ; Case_Ignorable # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L 11C38..11C3D ; Case_Ignorable # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA 11C3F ; Case_Ignorable # Mn BHAIKSUKI SIGN VIRAMA @@ -3085,12 +3128,17 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 11CAA..11CB0 ; Case_Ignorable # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA 11CB2..11CB3 ; Case_Ignorable # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E 11CB5..11CB6 ; Case_Ignorable # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D31..11D36 ; Case_Ignorable # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; Case_Ignorable # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; Case_Ignorable # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45 ; Case_Ignorable # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D47 ; Case_Ignorable # Mn MASARAM GONDI RA-KARA 16AF0..16AF4 ; Case_Ignorable # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; Case_Ignorable # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM 16B40..16B43 ; Case_Ignorable # Lm [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM 16F8F..16F92 ; Case_Ignorable # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW 16F93..16F9F ; Case_Ignorable # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 -16FE0 ; Case_Ignorable # Lm TANGUT ITERATION MARK +16FE0..16FE1 ; Case_Ignorable # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK 1BC9D..1BC9E ; Case_Ignorable # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK 1BCA0..1BCA3 ; Case_Ignorable # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP 1D167..1D169 ; Case_Ignorable # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 @@ -3117,7 +3165,7 @@ E0001 ; Case_Ignorable # Cf LANGUAGE TAG E0020..E007F ; Case_Ignorable # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Case_Ignorable # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2240 +# Total code points: 2314 # ================================================ @@ -5763,6 +5811,7 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 0824 ; ID_Start # Lm SAMARITAN MODIFIER LETTER SHORT A 0828 ; ID_Start # Lm SAMARITAN MODIFIER LETTER I 0840..0858 ; ID_Start # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN +0860..086A ; ID_Start # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 08A0..08B4 ; ID_Start # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW 08B6..08BD ; ID_Start # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON 0904..0939 ; ID_Start # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA @@ -5782,6 +5831,7 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 09DC..09DD ; ID_Start # Lo [2] BENGALI LETTER RRA..BENGALI LETTER RHA 09DF..09E1 ; ID_Start # Lo [3] BENGALI LETTER YYA..BENGALI LETTER VOCALIC LL 09F0..09F1 ; ID_Start # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL +09FC ; ID_Start # Lo BENGALI LETTER VEDIC ANUSVARA 0A05..0A0A ; ID_Start # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU 0A0F..0A10 ; ID_Start # Lo [2] GURMUKHI LETTER EE..GURMUKHI LETTER AI 0A13..0A28 ; ID_Start # Lo [22] GURMUKHI LETTER OO..GURMUKHI LETTER NA @@ -6039,12 +6089,12 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 30A1..30FA ; ID_Start # Lo [90] KATAKANA LETTER SMALL A..KATAKANA LETTER VO 30FC..30FE ; ID_Start # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK 30FF ; ID_Start # Lo KATAKANA DIGRAPH KOTO -3105..312D ; ID_Start # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH +3105..312E ; ID_Start # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE 3131..318E ; ID_Start # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE 31A0..31BA ; ID_Start # Lo [27] BOPOMOFO LETTER BU..BOPOMOFO LETTER ZY 31F0..31FF ; ID_Start # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO 3400..4DB5 ; ID_Start # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 -4E00..9FD5 ; ID_Start # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5 +4E00..9FEA ; ID_Start # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA A000..A014 ; ID_Start # Lo [21] YI SYLLABLE IT..YI SYLLABLE E A015 ; ID_Start # Lm YI SYLLABLE WU A016..A48C ; ID_Start # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR @@ -6162,7 +6212,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 10280..1029C ; ID_Start # Lo [29] LYCIAN LETTER A..LYCIAN LETTER X 102A0..102D0 ; ID_Start # Lo [49] CARIAN LETTER A..CARIAN LETTER UUU3 10300..1031F ; ID_Start # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS -10330..10340 ; ID_Start # Lo [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA +1032D..10340 ; ID_Start # Lo [20] OLD ITALIC LETTER YE..GOTHIC LETTER PAIRTHRA 10341 ; ID_Start # Nl GOTHIC LETTER NINETY 10342..10349 ; ID_Start # Lo [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL 1034A ; ID_Start # Nl GOTHIC LETTER NINE HUNDRED @@ -6249,11 +6299,21 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 11700..11719 ; ID_Start # Lo [26] AHOM LETTER KA..AHOM LETTER JHA 118A0..118DF ; ID_Start # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 118FF ; ID_Start # Lo WARANG CITI OM +11A00 ; ID_Start # Lo ZANABAZAR SQUARE LETTER A +11A0B..11A32 ; ID_Start # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA +11A3A ; ID_Start # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA +11A50 ; ID_Start # Lo SOYOMBO LETTER A +11A5C..11A83 ; ID_Start # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA +11A86..11A89 ; ID_Start # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA 11AC0..11AF8 ; ID_Start # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL 11C00..11C08 ; ID_Start # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E ; ID_Start # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA 11C40 ; ID_Start # Lo BHAIKSUKI SIGN AVAGRAHA 11C72..11C8F ; ID_Start # Lo [30] MARCHEN LETTER KA..MARCHEN LETTER A +11D00..11D06 ; ID_Start # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E +11D08..11D09 ; ID_Start # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O +11D0B..11D30 ; ID_Start # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA +11D46 ; ID_Start # Lo MASARAM GONDI REPHA 12000..12399 ; ID_Start # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; ID_Start # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12480..12543 ; ID_Start # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU @@ -6269,10 +6329,11 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 16F00..16F44 ; ID_Start # Lo [69] MIAO LETTER PA..MIAO LETTER HHA 16F50 ; ID_Start # Lo MIAO LETTER NASALIZATION 16F93..16F9F ; ID_Start # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 -16FE0 ; ID_Start # Lm TANGUT ITERATION MARK +16FE0..16FE1 ; ID_Start # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK 17000..187EC ; ID_Start # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC 18800..18AF2 ; ID_Start # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755 -1B000..1B001 ; ID_Start # Lo [2] KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE +1B000..1B11E ; ID_Start # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1B170..1B2FB ; ID_Start # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 1BC00..1BC6A ; ID_Start # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M 1BC70..1BC7C ; ID_Start # Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK 1BC80..1BC88 ; ID_Start # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL @@ -6346,9 +6407,10 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 2A700..2B734 ; ID_Start # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 2B740..2B81D ; ID_Start # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; ID_Start # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 +2CEB0..2EBE0 ; ID_Start # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; ID_Start # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D -# Total code points: 117007 +# Total code points: 125334 # ================================================ @@ -6451,6 +6513,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 0829..082D ; ID_Continue # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA 0840..0858 ; ID_Continue # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 0859..085B ; ID_Continue # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK +0860..086A ; ID_Continue # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 08A0..08B4 ; ID_Continue # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW 08B6..08BD ; ID_Continue # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON 08D4..08E1 ; ID_Continue # Mn [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA @@ -6495,6 +6558,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 09E2..09E3 ; ID_Continue # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL 09E6..09EF ; ID_Continue # Nd [10] BENGALI DIGIT ZERO..BENGALI DIGIT NINE 09F0..09F1 ; ID_Continue # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL +09FC ; ID_Continue # Lo BENGALI LETTER VEDIC ANUSVARA 0A01..0A02 ; ID_Continue # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI 0A03 ; ID_Continue # Mc GURMUKHI SIGN VISARGA 0A05..0A0A ; ID_Continue # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU @@ -6537,6 +6601,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 0AE2..0AE3 ; ID_Continue # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL 0AE6..0AEF ; ID_Continue # Nd [10] GUJARATI DIGIT ZERO..GUJARATI DIGIT NINE 0AF9 ; ID_Continue # Lo GUJARATI LETTER ZHA +0AFA..0AFF ; ID_Continue # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE 0B01 ; ID_Continue # Mn ORIYA SIGN CANDRABINDU 0B02..0B03 ; ID_Continue # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA 0B05..0B0C ; ID_Continue # Lo [8] ORIYA LETTER A..ORIYA LETTER VOCALIC L @@ -6620,11 +6685,12 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 0CE2..0CE3 ; ID_Continue # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL 0CE6..0CEF ; ID_Continue # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE 0CF1..0CF2 ; ID_Continue # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA -0D01 ; ID_Continue # Mn MALAYALAM SIGN CANDRABINDU +0D00..0D01 ; ID_Continue # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU 0D02..0D03 ; ID_Continue # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA 0D05..0D0C ; ID_Continue # Lo [8] MALAYALAM LETTER A..MALAYALAM LETTER VOCALIC L 0D0E..0D10 ; ID_Continue # Lo [3] MALAYALAM LETTER E..MALAYALAM LETTER AI 0D12..0D3A ; ID_Continue # Lo [41] MALAYALAM LETTER O..MALAYALAM LETTER TTTA +0D3B..0D3C ; ID_Continue # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA 0D3D ; ID_Continue # Lo MALAYALAM SIGN AVAGRAHA 0D3E..0D40 ; ID_Continue # Mc [3] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN II 0D41..0D44 ; ID_Continue # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR @@ -6888,6 +6954,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1CF2..1CF3 ; ID_Continue # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA 1CF4 ; ID_Continue # Mn VEDIC TONE CANDRA ABOVE 1CF5..1CF6 ; ID_Continue # Lo [2] VEDIC SIGN JIHVAMULIYA..VEDIC SIGN UPADHMANIYA +1CF7 ; ID_Continue # Mc VEDIC SIGN ATIKRAMA 1CF8..1CF9 ; ID_Continue # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE 1D00..1D2B ; ID_Continue # L& [44] LATIN LETTER SMALL CAPITAL A..CYRILLIC LETTER SMALL CAPITAL EL 1D2C..1D6A ; ID_Continue # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI @@ -6895,7 +6962,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1D78 ; ID_Continue # Lm MODIFIER LETTER CYRILLIC EN 1D79..1D9A ; ID_Continue # L& [34] LATIN SMALL LETTER INSULAR G..LATIN SMALL LETTER EZH WITH RETROFLEX HOOK 1D9B..1DBF ; ID_Continue # Lm [37] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL THETA -1DC0..1DF5 ; ID_Continue # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE +1DC0..1DF9 ; ID_Continue # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW 1DFB..1DFF ; ID_Continue # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 1E00..1F15 ; ID_Continue # L& [278] LATIN CAPITAL LETTER A WITH RING BELOW..GREEK SMALL LETTER EPSILON WITH DASIA AND OXIA 1F18..1F1D ; ID_Continue # L& [6] GREEK CAPITAL LETTER EPSILON WITH PSILI..GREEK CAPITAL LETTER EPSILON WITH DASIA AND OXIA @@ -6986,12 +7053,12 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 30A1..30FA ; ID_Continue # Lo [90] KATAKANA LETTER SMALL A..KATAKANA LETTER VO 30FC..30FE ; ID_Continue # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK 30FF ; ID_Continue # Lo KATAKANA DIGRAPH KOTO -3105..312D ; ID_Continue # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH +3105..312E ; ID_Continue # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE 3131..318E ; ID_Continue # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE 31A0..31BA ; ID_Continue # Lo [27] BOPOMOFO LETTER BU..BOPOMOFO LETTER ZY 31F0..31FF ; ID_Continue # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO 3400..4DB5 ; ID_Continue # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 -4E00..9FD5 ; ID_Continue # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5 +4E00..9FEA ; ID_Continue # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA A000..A014 ; ID_Continue # Lo [21] YI SYLLABLE IT..YI SYLLABLE E A015 ; ID_Continue # Lm YI SYLLABLE WU A016..A48C ; ID_Continue # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR @@ -7179,7 +7246,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 102A0..102D0 ; ID_Continue # Lo [49] CARIAN LETTER A..CARIAN LETTER UUU3 102E0 ; ID_Continue # Mn COPTIC EPACT THOUSANDS MARK 10300..1031F ; ID_Continue # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS -10330..10340 ; ID_Continue # Lo [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA +1032D..10340 ; ID_Continue # Lo [20] OLD ITALIC LETTER YE..GOTHIC LETTER PAIRTHRA 10341 ; ID_Continue # Nl GOTHIC LETTER NINETY 10342..10349 ; ID_Continue # Lo [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL 1034A ; ID_Continue # Nl GOTHIC LETTER NINE HUNDRED @@ -7367,6 +7434,25 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 118A0..118DF ; ID_Continue # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 118E0..118E9 ; ID_Continue # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE 118FF ; ID_Continue # Lo WARANG CITI OM +11A00 ; ID_Continue # Lo ZANABAZAR SQUARE LETTER A +11A01..11A06 ; ID_Continue # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O +11A07..11A08 ; ID_Continue # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU +11A09..11A0A ; ID_Continue # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A0B..11A32 ; ID_Continue # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA +11A33..11A38 ; ID_Continue # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A39 ; ID_Continue # Mc ZANABAZAR SQUARE SIGN VISARGA +11A3A ; ID_Continue # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA +11A3B..11A3E ; ID_Continue # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A47 ; ID_Continue # Mn ZANABAZAR SQUARE SUBJOINER +11A50 ; ID_Continue # Lo SOYOMBO LETTER A +11A51..11A56 ; ID_Continue # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A57..11A58 ; ID_Continue # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU +11A59..11A5B ; ID_Continue # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A5C..11A83 ; ID_Continue # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA +11A86..11A89 ; ID_Continue # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA +11A8A..11A96 ; ID_Continue # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A97 ; ID_Continue # Mc SOYOMBO SIGN VISARGA +11A98..11A99 ; ID_Continue # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER 11AC0..11AF8 ; ID_Continue # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL 11C00..11C08 ; ID_Continue # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E ; ID_Continue # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA @@ -7385,6 +7471,16 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 11CB2..11CB3 ; ID_Continue # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E 11CB4 ; ID_Continue # Mc MARCHEN VOWEL SIGN O 11CB5..11CB6 ; ID_Continue # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D00..11D06 ; ID_Continue # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E +11D08..11D09 ; ID_Continue # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O +11D0B..11D30 ; ID_Continue # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA +11D31..11D36 ; ID_Continue # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; ID_Continue # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; ID_Continue # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45 ; ID_Continue # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D46 ; ID_Continue # Lo MASARAM GONDI REPHA +11D47 ; ID_Continue # Mn MASARAM GONDI RA-KARA +11D50..11D59 ; ID_Continue # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE 12000..12399 ; ID_Continue # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; ID_Continue # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12480..12543 ; ID_Continue # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU @@ -7406,10 +7502,11 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 16F51..16F7E ; ID_Continue # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG 16F8F..16F92 ; ID_Continue # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW 16F93..16F9F ; ID_Continue # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 -16FE0 ; ID_Continue # Lm TANGUT ITERATION MARK +16FE0..16FE1 ; ID_Continue # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK 17000..187EC ; ID_Continue # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC 18800..18AF2 ; ID_Continue # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755 -1B000..1B001 ; ID_Continue # Lo [2] KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE +1B000..1B11E ; ID_Continue # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1B170..1B2FB ; ID_Continue # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 1BC00..1BC6A ; ID_Continue # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M 1BC70..1BC7C ; ID_Continue # Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK 1BC80..1BC88 ; ID_Continue # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL @@ -7506,10 +7603,11 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 2A700..2B734 ; ID_Continue # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 2B740..2B81D ; ID_Continue # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; ID_Continue # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 +2CEB0..2EBE0 ; ID_Continue # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; ID_Continue # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 119691 +# Total code points: 128108 # ================================================ @@ -7578,6 +7676,7 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 0824 ; XID_Start # Lm SAMARITAN MODIFIER LETTER SHORT A 0828 ; XID_Start # Lm SAMARITAN MODIFIER LETTER I 0840..0858 ; XID_Start # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN +0860..086A ; XID_Start # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 08A0..08B4 ; XID_Start # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW 08B6..08BD ; XID_Start # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON 0904..0939 ; XID_Start # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA @@ -7597,6 +7696,7 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 09DC..09DD ; XID_Start # Lo [2] BENGALI LETTER RRA..BENGALI LETTER RHA 09DF..09E1 ; XID_Start # Lo [3] BENGALI LETTER YYA..BENGALI LETTER VOCALIC LL 09F0..09F1 ; XID_Start # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL +09FC ; XID_Start # Lo BENGALI LETTER VEDIC ANUSVARA 0A05..0A0A ; XID_Start # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU 0A0F..0A10 ; XID_Start # Lo [2] GURMUKHI LETTER EE..GURMUKHI LETTER AI 0A13..0A28 ; XID_Start # Lo [22] GURMUKHI LETTER OO..GURMUKHI LETTER NA @@ -7853,12 +7953,12 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 30A1..30FA ; XID_Start # Lo [90] KATAKANA LETTER SMALL A..KATAKANA LETTER VO 30FC..30FE ; XID_Start # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK 30FF ; XID_Start # Lo KATAKANA DIGRAPH KOTO -3105..312D ; XID_Start # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH +3105..312E ; XID_Start # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE 3131..318E ; XID_Start # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE 31A0..31BA ; XID_Start # Lo [27] BOPOMOFO LETTER BU..BOPOMOFO LETTER ZY 31F0..31FF ; XID_Start # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO 3400..4DB5 ; XID_Start # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 -4E00..9FD5 ; XID_Start # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5 +4E00..9FEA ; XID_Start # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA A000..A014 ; XID_Start # Lo [21] YI SYLLABLE IT..YI SYLLABLE E A015 ; XID_Start # Lm YI SYLLABLE WU A016..A48C ; XID_Start # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR @@ -7981,7 +8081,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 10280..1029C ; XID_Start # Lo [29] LYCIAN LETTER A..LYCIAN LETTER X 102A0..102D0 ; XID_Start # Lo [49] CARIAN LETTER A..CARIAN LETTER UUU3 10300..1031F ; XID_Start # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS -10330..10340 ; XID_Start # Lo [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA +1032D..10340 ; XID_Start # Lo [20] OLD ITALIC LETTER YE..GOTHIC LETTER PAIRTHRA 10341 ; XID_Start # Nl GOTHIC LETTER NINETY 10342..10349 ; XID_Start # Lo [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL 1034A ; XID_Start # Nl GOTHIC LETTER NINE HUNDRED @@ -8068,11 +8168,21 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 11700..11719 ; XID_Start # Lo [26] AHOM LETTER KA..AHOM LETTER JHA 118A0..118DF ; XID_Start # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 118FF ; XID_Start # Lo WARANG CITI OM +11A00 ; XID_Start # Lo ZANABAZAR SQUARE LETTER A +11A0B..11A32 ; XID_Start # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA +11A3A ; XID_Start # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA +11A50 ; XID_Start # Lo SOYOMBO LETTER A +11A5C..11A83 ; XID_Start # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA +11A86..11A89 ; XID_Start # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA 11AC0..11AF8 ; XID_Start # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL 11C00..11C08 ; XID_Start # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E ; XID_Start # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA 11C40 ; XID_Start # Lo BHAIKSUKI SIGN AVAGRAHA 11C72..11C8F ; XID_Start # Lo [30] MARCHEN LETTER KA..MARCHEN LETTER A +11D00..11D06 ; XID_Start # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E +11D08..11D09 ; XID_Start # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O +11D0B..11D30 ; XID_Start # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA +11D46 ; XID_Start # Lo MASARAM GONDI REPHA 12000..12399 ; XID_Start # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; XID_Start # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12480..12543 ; XID_Start # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU @@ -8088,10 +8198,11 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 16F00..16F44 ; XID_Start # Lo [69] MIAO LETTER PA..MIAO LETTER HHA 16F50 ; XID_Start # Lo MIAO LETTER NASALIZATION 16F93..16F9F ; XID_Start # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 -16FE0 ; XID_Start # Lm TANGUT ITERATION MARK +16FE0..16FE1 ; XID_Start # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK 17000..187EC ; XID_Start # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC 18800..18AF2 ; XID_Start # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755 -1B000..1B001 ; XID_Start # Lo [2] KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE +1B000..1B11E ; XID_Start # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1B170..1B2FB ; XID_Start # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 1BC00..1BC6A ; XID_Start # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M 1BC70..1BC7C ; XID_Start # Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK 1BC80..1BC88 ; XID_Start # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL @@ -8165,9 +8276,10 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 2A700..2B734 ; XID_Start # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 2B740..2B81D ; XID_Start # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; XID_Start # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 +2CEB0..2EBE0 ; XID_Start # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; XID_Start # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D -# Total code points: 116984 +# Total code points: 125311 # ================================================ @@ -8266,6 +8378,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 0829..082D ; XID_Continue # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA 0840..0858 ; XID_Continue # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 0859..085B ; XID_Continue # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK +0860..086A ; XID_Continue # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 08A0..08B4 ; XID_Continue # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW 08B6..08BD ; XID_Continue # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON 08D4..08E1 ; XID_Continue # Mn [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA @@ -8310,6 +8423,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 09E2..09E3 ; XID_Continue # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL 09E6..09EF ; XID_Continue # Nd [10] BENGALI DIGIT ZERO..BENGALI DIGIT NINE 09F0..09F1 ; XID_Continue # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL +09FC ; XID_Continue # Lo BENGALI LETTER VEDIC ANUSVARA 0A01..0A02 ; XID_Continue # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI 0A03 ; XID_Continue # Mc GURMUKHI SIGN VISARGA 0A05..0A0A ; XID_Continue # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU @@ -8352,6 +8466,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 0AE2..0AE3 ; XID_Continue # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL 0AE6..0AEF ; XID_Continue # Nd [10] GUJARATI DIGIT ZERO..GUJARATI DIGIT NINE 0AF9 ; XID_Continue # Lo GUJARATI LETTER ZHA +0AFA..0AFF ; XID_Continue # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE 0B01 ; XID_Continue # Mn ORIYA SIGN CANDRABINDU 0B02..0B03 ; XID_Continue # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA 0B05..0B0C ; XID_Continue # Lo [8] ORIYA LETTER A..ORIYA LETTER VOCALIC L @@ -8435,11 +8550,12 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 0CE2..0CE3 ; XID_Continue # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL 0CE6..0CEF ; XID_Continue # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE 0CF1..0CF2 ; XID_Continue # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA -0D01 ; XID_Continue # Mn MALAYALAM SIGN CANDRABINDU +0D00..0D01 ; XID_Continue # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU 0D02..0D03 ; XID_Continue # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA 0D05..0D0C ; XID_Continue # Lo [8] MALAYALAM LETTER A..MALAYALAM LETTER VOCALIC L 0D0E..0D10 ; XID_Continue # Lo [3] MALAYALAM LETTER E..MALAYALAM LETTER AI 0D12..0D3A ; XID_Continue # Lo [41] MALAYALAM LETTER O..MALAYALAM LETTER TTTA +0D3B..0D3C ; XID_Continue # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA 0D3D ; XID_Continue # Lo MALAYALAM SIGN AVAGRAHA 0D3E..0D40 ; XID_Continue # Mc [3] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN II 0D41..0D44 ; XID_Continue # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR @@ -8703,6 +8819,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 1CF2..1CF3 ; XID_Continue # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA 1CF4 ; XID_Continue # Mn VEDIC TONE CANDRA ABOVE 1CF5..1CF6 ; XID_Continue # Lo [2] VEDIC SIGN JIHVAMULIYA..VEDIC SIGN UPADHMANIYA +1CF7 ; XID_Continue # Mc VEDIC SIGN ATIKRAMA 1CF8..1CF9 ; XID_Continue # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE 1D00..1D2B ; XID_Continue # L& [44] LATIN LETTER SMALL CAPITAL A..CYRILLIC LETTER SMALL CAPITAL EL 1D2C..1D6A ; XID_Continue # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI @@ -8710,7 +8827,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 1D78 ; XID_Continue # Lm MODIFIER LETTER CYRILLIC EN 1D79..1D9A ; XID_Continue # L& [34] LATIN SMALL LETTER INSULAR G..LATIN SMALL LETTER EZH WITH RETROFLEX HOOK 1D9B..1DBF ; XID_Continue # Lm [37] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL THETA -1DC0..1DF5 ; XID_Continue # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE +1DC0..1DF9 ; XID_Continue # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW 1DFB..1DFF ; XID_Continue # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 1E00..1F15 ; XID_Continue # L& [278] LATIN CAPITAL LETTER A WITH RING BELOW..GREEK SMALL LETTER EPSILON WITH DASIA AND OXIA 1F18..1F1D ; XID_Continue # L& [6] GREEK CAPITAL LETTER EPSILON WITH PSILI..GREEK CAPITAL LETTER EPSILON WITH DASIA AND OXIA @@ -8800,12 +8917,12 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 30A1..30FA ; XID_Continue # Lo [90] KATAKANA LETTER SMALL A..KATAKANA LETTER VO 30FC..30FE ; XID_Continue # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK 30FF ; XID_Continue # Lo KATAKANA DIGRAPH KOTO -3105..312D ; XID_Continue # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH +3105..312E ; XID_Continue # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE 3131..318E ; XID_Continue # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE 31A0..31BA ; XID_Continue # Lo [27] BOPOMOFO LETTER BU..BOPOMOFO LETTER ZY 31F0..31FF ; XID_Continue # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO 3400..4DB5 ; XID_Continue # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 -4E00..9FD5 ; XID_Continue # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5 +4E00..9FEA ; XID_Continue # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA A000..A014 ; XID_Continue # Lo [21] YI SYLLABLE IT..YI SYLLABLE E A015 ; XID_Continue # Lm YI SYLLABLE WU A016..A48C ; XID_Continue # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR @@ -8999,7 +9116,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 102A0..102D0 ; XID_Continue # Lo [49] CARIAN LETTER A..CARIAN LETTER UUU3 102E0 ; XID_Continue # Mn COPTIC EPACT THOUSANDS MARK 10300..1031F ; XID_Continue # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS -10330..10340 ; XID_Continue # Lo [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA +1032D..10340 ; XID_Continue # Lo [20] OLD ITALIC LETTER YE..GOTHIC LETTER PAIRTHRA 10341 ; XID_Continue # Nl GOTHIC LETTER NINETY 10342..10349 ; XID_Continue # Lo [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL 1034A ; XID_Continue # Nl GOTHIC LETTER NINE HUNDRED @@ -9187,6 +9304,25 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 118A0..118DF ; XID_Continue # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 118E0..118E9 ; XID_Continue # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE 118FF ; XID_Continue # Lo WARANG CITI OM +11A00 ; XID_Continue # Lo ZANABAZAR SQUARE LETTER A +11A01..11A06 ; XID_Continue # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O +11A07..11A08 ; XID_Continue # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU +11A09..11A0A ; XID_Continue # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A0B..11A32 ; XID_Continue # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA +11A33..11A38 ; XID_Continue # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A39 ; XID_Continue # Mc ZANABAZAR SQUARE SIGN VISARGA +11A3A ; XID_Continue # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA +11A3B..11A3E ; XID_Continue # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A47 ; XID_Continue # Mn ZANABAZAR SQUARE SUBJOINER +11A50 ; XID_Continue # Lo SOYOMBO LETTER A +11A51..11A56 ; XID_Continue # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A57..11A58 ; XID_Continue # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU +11A59..11A5B ; XID_Continue # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A5C..11A83 ; XID_Continue # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA +11A86..11A89 ; XID_Continue # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA +11A8A..11A96 ; XID_Continue # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A97 ; XID_Continue # Mc SOYOMBO SIGN VISARGA +11A98..11A99 ; XID_Continue # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER 11AC0..11AF8 ; XID_Continue # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL 11C00..11C08 ; XID_Continue # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E ; XID_Continue # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA @@ -9205,6 +9341,16 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 11CB2..11CB3 ; XID_Continue # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E 11CB4 ; XID_Continue # Mc MARCHEN VOWEL SIGN O 11CB5..11CB6 ; XID_Continue # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D00..11D06 ; XID_Continue # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E +11D08..11D09 ; XID_Continue # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O +11D0B..11D30 ; XID_Continue # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA +11D31..11D36 ; XID_Continue # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; XID_Continue # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; XID_Continue # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45 ; XID_Continue # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D46 ; XID_Continue # Lo MASARAM GONDI REPHA +11D47 ; XID_Continue # Mn MASARAM GONDI RA-KARA +11D50..11D59 ; XID_Continue # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE 12000..12399 ; XID_Continue # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; XID_Continue # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12480..12543 ; XID_Continue # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU @@ -9226,10 +9372,11 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 16F51..16F7E ; XID_Continue # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG 16F8F..16F92 ; XID_Continue # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW 16F93..16F9F ; XID_Continue # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 -16FE0 ; XID_Continue # Lm TANGUT ITERATION MARK +16FE0..16FE1 ; XID_Continue # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK 17000..187EC ; XID_Continue # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC 18800..18AF2 ; XID_Continue # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755 -1B000..1B001 ; XID_Continue # Lo [2] KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE +1B000..1B11E ; XID_Continue # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1B170..1B2FB ; XID_Continue # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 1BC00..1BC6A ; XID_Continue # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M 1BC70..1BC7C ; XID_Continue # Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK 1BC80..1BC88 ; XID_Continue # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL @@ -9326,10 +9473,11 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 2A700..2B734 ; XID_Continue # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 2B740..2B81D ; XID_Continue # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; XID_Continue # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 +2CEB0..2EBE0 ; XID_Continue # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; XID_Continue # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 119672 +# Total code points: 128089 # ================================================ @@ -9339,8 +9487,8 @@ E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTO # + Cf (Format characters) # + Variation_Selector # - White_Space -# - FFF9..FFFB (Annotation Characters) -# - 0600..0605, 06DD, 070F, 08E2, 110BD (exceptional Cf characters that should be visible) +# - FFF9..FFFB (Annotation characters) +# - Prepended_Concatenation_Mark (Exceptional format characters that should be visible) 00AD ; Default_Ignorable_Code_Point # Cf SOFT HYPHEN 034F ; Default_Ignorable_Code_Point # Mn COMBINING GRAPHEME JOINER @@ -9431,6 +9579,7 @@ E01F0..E0FFF ; Default_Ignorable_Code_Point # Cn [3600] <reserved-E01F0>..<rese 0AC7..0AC8 ; Grapheme_Extend # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI 0ACD ; Grapheme_Extend # Mn GUJARATI SIGN VIRAMA 0AE2..0AE3 ; Grapheme_Extend # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0AFA..0AFF ; Grapheme_Extend # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE 0B01 ; Grapheme_Extend # Mn ORIYA SIGN CANDRABINDU 0B3C ; Grapheme_Extend # Mn ORIYA SIGN NUKTA 0B3E ; Grapheme_Extend # Mc ORIYA VOWEL SIGN AA @@ -9459,7 +9608,8 @@ E01F0..E0FFF ; Default_Ignorable_Code_Point # Cn [3600] <reserved-E01F0>..<rese 0CCC..0CCD ; Grapheme_Extend # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA 0CD5..0CD6 ; Grapheme_Extend # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK 0CE2..0CE3 ; Grapheme_Extend # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL -0D01 ; Grapheme_Extend # Mn MALAYALAM SIGN CANDRABINDU +0D00..0D01 ; Grapheme_Extend # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU +0D3B..0D3C ; Grapheme_Extend # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA 0D3E ; Grapheme_Extend # Mc MALAYALAM VOWEL SIGN AA 0D41..0D44 ; Grapheme_Extend # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR 0D4D ; Grapheme_Extend # Mn MALAYALAM SIGN VIRAMA @@ -9548,7 +9698,7 @@ E01F0..E0FFF ; Default_Ignorable_Code_Point # Cn [3600] <reserved-E01F0>..<rese 1CED ; Grapheme_Extend # Mn VEDIC SIGN TIRYAK 1CF4 ; Grapheme_Extend # Mn VEDIC TONE CANDRA ABOVE 1CF8..1CF9 ; Grapheme_Extend # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE -1DC0..1DF5 ; Grapheme_Extend # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE +1DC0..1DF9 ; Grapheme_Extend # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW 1DFB..1DFF ; Grapheme_Extend # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 200C ; Grapheme_Extend # Cf ZERO WIDTH NON-JOINER 20D0..20DC ; Grapheme_Extend # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE @@ -9658,6 +9808,15 @@ FF9E..FF9F ; Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK. 1171D..1171F ; Grapheme_Extend # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA 11722..11725 ; Grapheme_Extend # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU 11727..1172B ; Grapheme_Extend # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER +11A01..11A06 ; Grapheme_Extend # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O +11A09..11A0A ; Grapheme_Extend # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A33..11A38 ; Grapheme_Extend # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A3B..11A3E ; Grapheme_Extend # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A47 ; Grapheme_Extend # Mn ZANABAZAR SQUARE SUBJOINER +11A51..11A56 ; Grapheme_Extend # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A59..11A5B ; Grapheme_Extend # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A8A..11A96 ; Grapheme_Extend # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A98..11A99 ; Grapheme_Extend # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER 11C30..11C36 ; Grapheme_Extend # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L 11C38..11C3D ; Grapheme_Extend # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA 11C3F ; Grapheme_Extend # Mn BHAIKSUKI SIGN VIRAMA @@ -9665,6 +9824,11 @@ FF9E..FF9F ; Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK. 11CAA..11CB0 ; Grapheme_Extend # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA 11CB2..11CB3 ; Grapheme_Extend # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E 11CB5..11CB6 ; Grapheme_Extend # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D31..11D36 ; Grapheme_Extend # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; Grapheme_Extend # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; Grapheme_Extend # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45 ; Grapheme_Extend # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D47 ; Grapheme_Extend # Mn MASARAM GONDI RA-KARA 16AF0..16AF4 ; Grapheme_Extend # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; Grapheme_Extend # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM 16F8F..16F92 ; Grapheme_Extend # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW @@ -9692,7 +9856,7 @@ FF9E..FF9F ; Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK. E0020..E007F ; Grapheme_Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 1828 +# Total code points: 1901 # ================================================ @@ -9849,6 +10013,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 0830..083E ; Grapheme_Base # Po [15] SAMARITAN PUNCTUATION NEQUDAA..SAMARITAN PUNCTUATION ANNAAU 0840..0858 ; Grapheme_Base # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 085E ; Grapheme_Base # Po MANDAIC PUNCTUATION +0860..086A ; Grapheme_Base # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 08A0..08B4 ; Grapheme_Base # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW 08B6..08BD ; Grapheme_Base # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON 0903 ; Grapheme_Base # Mc DEVANAGARI SIGN VISARGA @@ -9885,6 +10050,8 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 09F4..09F9 ; Grapheme_Base # No [6] BENGALI CURRENCY NUMERATOR ONE..BENGALI CURRENCY DENOMINATOR SIXTEEN 09FA ; Grapheme_Base # So BENGALI ISSHAR 09FB ; Grapheme_Base # Sc BENGALI GANDA MARK +09FC ; Grapheme_Base # Lo BENGALI LETTER VEDIC ANUSVARA +09FD ; Grapheme_Base # Po BENGALI ABBREVIATION SIGN 0A03 ; Grapheme_Base # Mc GURMUKHI SIGN VISARGA 0A05..0A0A ; Grapheme_Base # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU 0A0F..0A10 ; Grapheme_Base # Lo [2] GURMUKHI LETTER EE..GURMUKHI LETTER AI @@ -10227,6 +10394,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 1CEE..1CF1 ; Grapheme_Base # Lo [4] VEDIC SIGN HEXIFORM LONG ANUSVARA..VEDIC SIGN ANUSVARA UBHAYATO MUKHA 1CF2..1CF3 ; Grapheme_Base # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA 1CF5..1CF6 ; Grapheme_Base # Lo [2] VEDIC SIGN JIHVAMULIYA..VEDIC SIGN UPADHMANIYA +1CF7 ; Grapheme_Base # Mc VEDIC SIGN ATIKRAMA 1D00..1D2B ; Grapheme_Base # L& [44] LATIN LETTER SMALL CAPITAL A..CYRILLIC LETTER SMALL CAPITAL EL 1D2C..1D6A ; Grapheme_Base # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI 1D6B..1D77 ; Grapheme_Base # L& [13] LATIN SMALL LETTER UE..LATIN SMALL LETTER TURNED G @@ -10297,7 +10465,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 208D ; Grapheme_Base # Ps SUBSCRIPT LEFT PARENTHESIS 208E ; Grapheme_Base # Pe SUBSCRIPT RIGHT PARENTHESIS 2090..209C ; Grapheme_Base # Lm [13] LATIN SUBSCRIPT SMALL LETTER A..LATIN SUBSCRIPT SMALL LETTER T -20A0..20BE ; Grapheme_Base # Sc [31] EURO-CURRENCY SIGN..LARI SIGN +20A0..20BF ; Grapheme_Base # Sc [32] EURO-CURRENCY SIGN..BITCOIN SIGN 2100..2101 ; Grapheme_Base # So [2] ACCOUNT OF..ADDRESSED TO THE SUBJECT 2102 ; Grapheme_Base # L& DOUBLE-STRUCK CAPITAL C 2103..2106 ; Grapheme_Base # So [4] DEGREE CELSIUS..CADA UNA @@ -10371,8 +10539,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 239B..23B3 ; Grapheme_Base # Sm [25] LEFT PARENTHESIS UPPER HOOK..SUMMATION BOTTOM 23B4..23DB ; Grapheme_Base # So [40] TOP SQUARE BRACKET..FUSE 23DC..23E1 ; Grapheme_Base # Sm [6] TOP PARENTHESIS..BOTTOM TORTOISE SHELL BRACKET -23E2..23FE ; Grapheme_Base # So [29] WHITE TRAPEZIUM..POWER SLEEP SYMBOL -2400..2426 ; Grapheme_Base # So [39] SYMBOL FOR NULL..SYMBOL FOR SUBSTITUTE FORM TWO +23E2..2426 ; Grapheme_Base # So [69] WHITE TRAPEZIUM..SYMBOL FOR SUBSTITUTE FORM TWO 2440..244A ; Grapheme_Base # So [11] OCR HOOK..OCR DOUBLE BACKSLASH 2460..249B ; Grapheme_Base # No [60] CIRCLED DIGIT ONE..NUMBER TWENTY FULL STOP 249C..24E9 ; Grapheme_Base # So [78] PARENTHESIZED LATIN SMALL LETTER A..CIRCLED LATIN SMALL LETTER Z @@ -10458,7 +10625,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 2B76..2B95 ; Grapheme_Base # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW 2B98..2BB9 ; Grapheme_Base # So [34] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..UP ARROWHEAD IN A RECTANGLE BOX 2BBD..2BC8 ; Grapheme_Base # So [12] BALLOT BOX WITH LIGHT X..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED -2BCA..2BD1 ; Grapheme_Base # So [8] TOP HALF BLACK CIRCLE..UNCERTAINTY SIGN +2BCA..2BD2 ; Grapheme_Base # So [9] TOP HALF BLACK CIRCLE..GROUP MARK 2BEC..2BEF ; Grapheme_Base # So [4] LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS..DOWNWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS 2C00..2C2E ; Grapheme_Base # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE 2C30..2C5E ; Grapheme_Base # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE @@ -10523,7 +10690,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 2E40 ; Grapheme_Base # Pd DOUBLE HYPHEN 2E41 ; Grapheme_Base # Po REVERSED COMMA 2E42 ; Grapheme_Base # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK -2E43..2E44 ; Grapheme_Base # Po [2] DASH WITH LEFT UPTURN..DOUBLE SUSPENSION MARK +2E43..2E49 ; Grapheme_Base # Po [7] DASH WITH LEFT UPTURN..DOUBLE STACKED COMMA 2E80..2E99 ; Grapheme_Base # So [26] CJK RADICAL REPEAT..CJK RADICAL RAP 2E9B..2EF3 ; Grapheme_Base # So [89] CJK RADICAL CHOKE..CJK RADICAL C-SIMPLIFIED TURTLE 2F00..2FD5 ; Grapheme_Base # So [214] KANGXI RADICAL ONE..KANGXI RADICAL FLUTE @@ -10575,7 +10742,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 30FB ; Grapheme_Base # Po KATAKANA MIDDLE DOT 30FC..30FE ; Grapheme_Base # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK 30FF ; Grapheme_Base # Lo KATAKANA DIGRAPH KOTO -3105..312D ; Grapheme_Base # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH +3105..312E ; Grapheme_Base # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE 3131..318E ; Grapheme_Base # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE 3190..3191 ; Grapheme_Base # So [2] IDEOGRAPHIC ANNOTATION LINKING MARK..IDEOGRAPHIC ANNOTATION REVERSE MARK 3192..3195 ; Grapheme_Base # No [4] IDEOGRAPHIC ANNOTATION ONE MARK..IDEOGRAPHIC ANNOTATION FOUR MARK @@ -10597,7 +10764,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 3300..33FF ; Grapheme_Base # So [256] SQUARE APAATO..SQUARE GAL 3400..4DB5 ; Grapheme_Base # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 4DC0..4DFF ; Grapheme_Base # So [64] HEXAGRAM FOR THE CREATIVE HEAVEN..HEXAGRAM FOR BEFORE COMPLETION -4E00..9FD5 ; Grapheme_Base # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5 +4E00..9FEA ; Grapheme_Base # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA A000..A014 ; Grapheme_Base # Lo [21] YI SYLLABLE IT..YI SYLLABLE E A015 ; Grapheme_Base # Lm YI SYLLABLE WU A016..A48C ; Grapheme_Base # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR @@ -10871,7 +11038,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 102E1..102FB ; Grapheme_Base # No [27] COPTIC EPACT DIGIT ONE..COPTIC EPACT NUMBER NINE HUNDRED 10300..1031F ; Grapheme_Base # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS 10320..10323 ; Grapheme_Base # No [4] OLD ITALIC NUMERAL ONE..OLD ITALIC NUMERAL FIFTY -10330..10340 ; Grapheme_Base # Lo [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA +1032D..10340 ; Grapheme_Base # Lo [20] OLD ITALIC LETTER YE..GOTHIC LETTER PAIRTHRA 10341 ; Grapheme_Base # Nl GOTHIC LETTER NINETY 10342..10349 ; Grapheme_Base # Lo [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL 1034A ; Grapheme_Base # Nl GOTHIC LETTER NINE HUNDRED @@ -11062,6 +11229,19 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 118E0..118E9 ; Grapheme_Base # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE 118EA..118F2 ; Grapheme_Base # No [9] WARANG CITI NUMBER TEN..WARANG CITI NUMBER NINETY 118FF ; Grapheme_Base # Lo WARANG CITI OM +11A00 ; Grapheme_Base # Lo ZANABAZAR SQUARE LETTER A +11A07..11A08 ; Grapheme_Base # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU +11A0B..11A32 ; Grapheme_Base # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA +11A39 ; Grapheme_Base # Mc ZANABAZAR SQUARE SIGN VISARGA +11A3A ; Grapheme_Base # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA +11A3F..11A46 ; Grapheme_Base # Po [8] ZANABAZAR SQUARE INITIAL HEAD MARK..ZANABAZAR SQUARE CLOSING DOUBLE-LINED HEAD MARK +11A50 ; Grapheme_Base # Lo SOYOMBO LETTER A +11A57..11A58 ; Grapheme_Base # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU +11A5C..11A83 ; Grapheme_Base # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA +11A86..11A89 ; Grapheme_Base # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA +11A97 ; Grapheme_Base # Mc SOYOMBO SIGN VISARGA +11A9A..11A9C ; Grapheme_Base # Po [3] SOYOMBO MARK TSHEG..SOYOMBO MARK DOUBLE SHAD +11A9E..11AA2 ; Grapheme_Base # Po [5] SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME..SOYOMBO TERMINAL MARK-2 11AC0..11AF8 ; Grapheme_Base # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL 11C00..11C08 ; Grapheme_Base # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E ; Grapheme_Base # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA @@ -11076,6 +11256,11 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 11CA9 ; Grapheme_Base # Mc MARCHEN SUBJOINED LETTER YA 11CB1 ; Grapheme_Base # Mc MARCHEN VOWEL SIGN I 11CB4 ; Grapheme_Base # Mc MARCHEN VOWEL SIGN O +11D00..11D06 ; Grapheme_Base # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E +11D08..11D09 ; Grapheme_Base # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O +11D0B..11D30 ; Grapheme_Base # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA +11D46 ; Grapheme_Base # Lo MASARAM GONDI REPHA +11D50..11D59 ; Grapheme_Base # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE 12000..12399 ; Grapheme_Base # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; Grapheme_Base # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12470..12474 ; Grapheme_Base # Po [5] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON @@ -11102,10 +11287,11 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 16F50 ; Grapheme_Base # Lo MIAO LETTER NASALIZATION 16F51..16F7E ; Grapheme_Base # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG 16F93..16F9F ; Grapheme_Base # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 -16FE0 ; Grapheme_Base # Lm TANGUT ITERATION MARK +16FE0..16FE1 ; Grapheme_Base # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK 17000..187EC ; Grapheme_Base # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC 18800..18AF2 ; Grapheme_Base # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755 -1B000..1B001 ; Grapheme_Base # Lo [2] KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE +1B000..1B11E ; Grapheme_Base # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1B170..1B2FB ; Grapheme_Base # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 1BC00..1BC6A ; Grapheme_Base # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M 1BC70..1BC7C ; Grapheme_Base # Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK 1BC80..1BC88 ; Grapheme_Base # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL @@ -11225,11 +11411,12 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 1F210..1F23B ; Grapheme_Base # So [44] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-914D 1F240..1F248 ; Grapheme_Base # So [9] TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C..TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557 1F250..1F251 ; Grapheme_Base # So [2] CIRCLED IDEOGRAPH ADVANTAGE..CIRCLED IDEOGRAPH ACCEPT +1F260..1F265 ; Grapheme_Base # So [6] ROUNDED SYMBOL FOR FU..ROUNDED SYMBOL FOR CAI 1F300..1F3FA ; Grapheme_Base # So [251] CYCLONE..AMPHORA 1F3FB..1F3FF ; Grapheme_Base # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6 -1F400..1F6D2 ; Grapheme_Base # So [723] RAT..SHOPPING TROLLEY +1F400..1F6D4 ; Grapheme_Base # So [725] RAT..PAGODA 1F6E0..1F6EC ; Grapheme_Base # So [13] HAMMER AND WRENCH..AIRPLANE ARRIVING -1F6F0..1F6F6 ; Grapheme_Base # So [7] SATELLITE..CANOE +1F6F0..1F6F8 ; Grapheme_Base # So [9] SATELLITE..FLYING SAUCER 1F700..1F773 ; Grapheme_Base # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE 1F780..1F7D4 ; Grapheme_Base # So [85] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..HEAVY TWELVE POINTED PINWHEEL STAR 1F800..1F80B ; Grapheme_Base # So [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD @@ -11237,21 +11424,21 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 1F850..1F859 ; Grapheme_Base # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW 1F860..1F887 ; Grapheme_Base # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW 1F890..1F8AD ; Grapheme_Base # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS -1F910..1F91E ; Grapheme_Base # So [15] ZIPPER-MOUTH FACE..HAND WITH INDEX AND MIDDLE FINGERS CROSSED -1F920..1F927 ; Grapheme_Base # So [8] FACE WITH COWBOY HAT..SNEEZING FACE -1F930 ; Grapheme_Base # So PREGNANT WOMAN -1F933..1F93E ; Grapheme_Base # So [12] SELFIE..HANDBALL -1F940..1F94B ; Grapheme_Base # So [12] WILTED FLOWER..MARTIAL ARTS UNIFORM -1F950..1F95E ; Grapheme_Base # So [15] CROISSANT..PANCAKES -1F980..1F991 ; Grapheme_Base # So [18] CRAB..SQUID +1F900..1F90B ; Grapheme_Base # So [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT +1F910..1F93E ; Grapheme_Base # So [47] ZIPPER-MOUTH FACE..HANDBALL +1F940..1F94C ; Grapheme_Base # So [13] WILTED FLOWER..CURLING STONE +1F950..1F96B ; Grapheme_Base # So [28] CROISSANT..CANNED FOOD +1F980..1F997 ; Grapheme_Base # So [24] CRAB..CRICKET 1F9C0 ; Grapheme_Base # So CHEESE WEDGE +1F9D0..1F9E6 ; Grapheme_Base # So [23] FACE WITH MONOCLE..SOCKS 20000..2A6D6 ; Grapheme_Base # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6 2A700..2B734 ; Grapheme_Base # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 2B740..2B81D ; Grapheme_Base # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; Grapheme_Base # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 +2CEB0..2EBE0 ; Grapheme_Base # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; Grapheme_Base # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D -# Total code points: 126288 +# Total code points: 134733 # ================================================ @@ -11267,6 +11454,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 0BCD ; Grapheme_Link # Mn TAMIL SIGN VIRAMA 0C4D ; Grapheme_Link # Mn TELUGU SIGN VIRAMA 0CCD ; Grapheme_Link # Mn KANNADA SIGN VIRAMA +0D3B..0D3C ; Grapheme_Link # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA 0D4D ; Grapheme_Link # Mn MALAYALAM SIGN VIRAMA 0DCA ; Grapheme_Link # Mn SINHALA SIGN AL-LAKUNA 0E3A ; Grapheme_Link # Mn THAI CHARACTER PHINTHU @@ -11302,8 +11490,12 @@ ABED ; Grapheme_Link # Mn MEETEI MAYEK APUN IYEK 1163F ; Grapheme_Link # Mn MODI SIGN VIRAMA 116B6 ; Grapheme_Link # Mc TAKRI SIGN VIRAMA 1172B ; Grapheme_Link # Mn AHOM SIGN KILLER +11A34 ; Grapheme_Link # Mn ZANABAZAR SQUARE SIGN VIRAMA +11A47 ; Grapheme_Link # Mn ZANABAZAR SQUARE SUBJOINER +11A99 ; Grapheme_Link # Mn SOYOMBO SUBJOINER 11C3F ; Grapheme_Link # Mn BHAIKSUKI SIGN VIRAMA +11D44..11D45 ; Grapheme_Link # Mn [2] MASARAM GONDI SIGN HALANTA..MASARAM GONDI VIRAMA -# Total code points: 47 +# Total code points: 54 # EOF diff --git a/lib/unicore/DNormalizationProps.txt b/lib/unicore/DNormalizationProps.txt index 089bd42abe..941c310b96 100644 --- a/lib/unicore/DNormalizationProps.txt +++ b/lib/unicore/DNormalizationProps.txt @@ -1,6 +1,6 @@ -# DerivedNormalizationProps-9.0.0.txt -# Date: 2016-03-02, 18:54:59 GMT -# © 2016 Unicode®, Inc. +# DerivedNormalizationProps-10.0.0.txt +# Date: 2017-02-14, 04:26:07 GMT +# © 2017 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html # diff --git a/lib/unicore/EastAsianWidth.txt b/lib/unicore/EastAsianWidth.txt index 5a2ede5d59..0d3129bb0a 100644 --- a/lib/unicore/EastAsianWidth.txt +++ b/lib/unicore/EastAsianWidth.txt @@ -1,6 +1,6 @@ -# EastAsianWidth-9.0.0.txt -# Date: 2016-05-27, 17:00:00 GMT [KW, LI] -# © 2016 Unicode®, Inc. +# EastAsianWidth-10.0.0.txt +# Date: 2017-03-08, 02:00:00 GMT [KW, LI] +# © 2017 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html # @@ -328,6 +328,7 @@ 0840..0858;N # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 0859..085B;N # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK 085E;N # Po MANDAIC PUNCTUATION +0860..086A;N # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 08A0..08B4;N # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW 08B6..08BD;N # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON 08D4..08E1;N # Mn [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA @@ -381,6 +382,8 @@ 09F4..09F9;N # No [6] BENGALI CURRENCY NUMERATOR ONE..BENGALI CURRENCY DENOMINATOR SIXTEEN 09FA;N # So BENGALI ISSHAR 09FB;N # Sc BENGALI GANDA MARK +09FC;N # Lo BENGALI LETTER VEDIC ANUSVARA +09FD;N # Po BENGALI ABBREVIATION SIGN 0A01..0A02;N # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI 0A03;N # Mc GURMUKHI SIGN VISARGA 0A05..0A0A;N # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU @@ -425,6 +428,7 @@ 0AF0;N # Po GUJARATI ABBREVIATION SIGN 0AF1;N # Sc GUJARATI RUPEE SIGN 0AF9;N # Lo GUJARATI LETTER ZHA +0AFA..0AFF;N # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE 0B01;N # Mn ORIYA SIGN CANDRABINDU 0B02..0B03;N # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA 0B05..0B0C;N # Lo [8] ORIYA LETTER A..ORIYA LETTER VOCALIC L @@ -516,11 +520,12 @@ 0CE2..0CE3;N # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL 0CE6..0CEF;N # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE 0CF1..0CF2;N # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA -0D01;N # Mn MALAYALAM SIGN CANDRABINDU +0D00..0D01;N # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU 0D02..0D03;N # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA 0D05..0D0C;N # Lo [8] MALAYALAM LETTER A..MALAYALAM LETTER VOCALIC L 0D0E..0D10;N # Lo [3] MALAYALAM LETTER E..MALAYALAM LETTER AI 0D12..0D3A;N # Lo [41] MALAYALAM LETTER O..MALAYALAM LETTER TTTA +0D3B..0D3C;N # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA 0D3D;N # Lo MALAYALAM SIGN AVAGRAHA 0D3E..0D40;N # Mc [3] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN II 0D41..0D44;N # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR @@ -853,6 +858,7 @@ 1CF2..1CF3;N # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA 1CF4;N # Mn VEDIC TONE CANDRA ABOVE 1CF5..1CF6;N # Lo [2] VEDIC SIGN JIHVAMULIYA..VEDIC SIGN UPADHMANIYA +1CF7;N # Mc VEDIC SIGN ATIKRAMA 1CF8..1CF9;N # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE 1D00..1D2B;N # Ll [44] LATIN LETTER SMALL CAPITAL A..CYRILLIC LETTER SMALL CAPITAL EL 1D2C..1D6A;N # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI @@ -861,7 +867,7 @@ 1D79..1D7F;N # Ll [7] LATIN SMALL LETTER INSULAR G..LATIN SMALL LETTER UPSILON WITH STROKE 1D80..1D9A;N # Ll [27] LATIN SMALL LETTER B WITH PALATAL HOOK..LATIN SMALL LETTER EZH WITH RETROFLEX HOOK 1D9B..1DBF;N # Lm [37] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL THETA -1DC0..1DF5;N # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE +1DC0..1DF9;N # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW 1DFB..1DFF;N # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 1E00..1EFF;N # L& [256] LATIN CAPITAL LETTER A WITH RING BELOW..LATIN SMALL LETTER Y WITH LOOP 1F00..1F15;N # L& [22] GREEK SMALL LETTER ALPHA WITH PSILI..GREEK SMALL LETTER EPSILON WITH DASIA AND OXIA @@ -954,7 +960,7 @@ 20A9;H # Sc WON SIGN 20AA..20AB;N # Sc [2] NEW SHEQEL SIGN..DONG SIGN 20AC;A # Sc EURO SIGN -20AD..20BE;N # Sc [18] KIP SIGN..LARI SIGN +20AD..20BF;N # Sc [19] KIP SIGN..BITCOIN SIGN 20D0..20DC;N # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE 20DD..20E0;N # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH 20E1;N # Mn COMBINING LEFT RIGHT ARROW ABOVE @@ -1120,7 +1126,7 @@ 23F0;W # So ALARM CLOCK 23F1..23F2;N # So [2] STOPWATCH..TIMER CLOCK 23F3;W # So HOURGLASS WITH FLOWING SAND -23F4..23FE;N # So [11] BLACK MEDIUM LEFT-POINTING TRIANGLE..POWER SLEEP SYMBOL +23F4..23FF;N # So [12] BLACK MEDIUM LEFT-POINTING TRIANGLE..OBSERVER EYE SYMBOL 2400..2426;N # So [39] SYMBOL FOR NULL..SYMBOL FOR SUBSTITUTE FORM TWO 2440..244A;N # So [11] OCR HOOK..OCR DOUBLE BACKSLASH 2460..249B;A # No [60] CIRCLED DIGIT ONE..NUMBER TWENTY FULL STOP @@ -1328,7 +1334,7 @@ 2B76..2B95;N # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW 2B98..2BB9;N # So [34] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..UP ARROWHEAD IN A RECTANGLE BOX 2BBD..2BC8;N # So [12] BALLOT BOX WITH LIGHT X..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED -2BCA..2BD1;N # So [8] TOP HALF BLACK CIRCLE..UNCERTAINTY SIGN +2BCA..2BD2;N # So [9] TOP HALF BLACK CIRCLE..GROUP MARK 2BEC..2BEF;N # So [4] LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS..DOWNWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS 2C00..2C2E;N # Lu [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE 2C30..2C5E;N # Ll [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE @@ -1397,7 +1403,7 @@ 2E40;N # Pd DOUBLE HYPHEN 2E41;N # Po REVERSED COMMA 2E42;N # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK -2E43..2E44;N # Po [2] DASH WITH LEFT UPTURN..DOUBLE SUSPENSION MARK +2E43..2E49;N # Po [7] DASH WITH LEFT UPTURN..DOUBLE STACKED COMMA 2E80..2E99;W # So [26] CJK RADICAL REPEAT..CJK RADICAL RAP 2E9B..2EF3;W # So [89] CJK RADICAL CHOKE..CJK RADICAL C-SIMPLIFIED TURTLE 2F00..2FD5;W # So [214] KANGXI RADICAL ONE..KANGXI RADICAL FLUTE @@ -1453,7 +1459,7 @@ 30FB;W # Po KATAKANA MIDDLE DOT 30FC..30FE;W # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK 30FF;W # Lo KATAKANA DIGRAPH KOTO -3105..312D;W # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH +3105..312E;W # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE 3131..318E;W # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE 3190..3191;W # So [2] IDEOGRAPHIC ANNOTATION LINKING MARK..IDEOGRAPHIC ANNOTATION REVERSE MARK 3192..3195;W # No [4] IDEOGRAPHIC ANNOTATION ONE MARK..IDEOGRAPHIC ANNOTATION FOUR MARK @@ -1476,8 +1482,8 @@ 3400..4DB5;W # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 4DB6..4DBF;W # Cn [10] <reserved-4DB6>..<reserved-4DBF> 4DC0..4DFF;N # So [64] HEXAGRAM FOR THE CREATIVE HEAVEN..HEXAGRAM FOR BEFORE COMPLETION -4E00..9FD5;W # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5 -9FD6..9FFF;W # Cn [42] <reserved-9FD6>..<reserved-9FFF> +4E00..9FEA;W # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA +9FEB..9FFF;W # Cn [21] <reserved-9FEB>..<reserved-9FFF> A000..A014;W # Lo [21] YI SYLLABLE IT..YI SYLLABLE E A015;W # Lm YI SYLLABLE WU A016..A48C;W # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR @@ -1803,6 +1809,7 @@ FFFD;A # So REPLACEMENT CHARACTER 102E1..102FB;N # No [27] COPTIC EPACT DIGIT ONE..COPTIC EPACT NUMBER NINE HUNDRED 10300..1031F;N # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS 10320..10323;N # No [4] OLD ITALIC NUMERAL ONE..OLD ITALIC NUMERAL FIFTY +1032D..1032F;N # Lo [3] OLD ITALIC LETTER YE..OLD ITALIC LETTER SOUTHERN TSE 10330..10340;N # Lo [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA 10341;N # Nl GOTHIC LETTER NINETY 10342..10349;N # Lo [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL @@ -2050,6 +2057,28 @@ FFFD;A # So REPLACEMENT CHARACTER 118E0..118E9;N # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE 118EA..118F2;N # No [9] WARANG CITI NUMBER TEN..WARANG CITI NUMBER NINETY 118FF;N # Lo WARANG CITI OM +11A00;N # Lo ZANABAZAR SQUARE LETTER A +11A01..11A06;N # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O +11A07..11A08;N # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU +11A09..11A0A;N # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A0B..11A32;N # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA +11A33..11A38;N # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A39;N # Mc ZANABAZAR SQUARE SIGN VISARGA +11A3A;N # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA +11A3B..11A3E;N # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A3F..11A46;N # Po [8] ZANABAZAR SQUARE INITIAL HEAD MARK..ZANABAZAR SQUARE CLOSING DOUBLE-LINED HEAD MARK +11A47;N # Mn ZANABAZAR SQUARE SUBJOINER +11A50;N # Lo SOYOMBO LETTER A +11A51..11A56;N # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A57..11A58;N # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU +11A59..11A5B;N # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A5C..11A83;N # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA +11A86..11A89;N # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA +11A8A..11A96;N # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A97;N # Mc SOYOMBO SIGN VISARGA +11A98..11A99;N # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER +11A9A..11A9C;N # Po [3] SOYOMBO MARK TSHEG..SOYOMBO MARK DOUBLE SHAD +11A9E..11AA2;N # Po [5] SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME..SOYOMBO TERMINAL MARK-2 11AC0..11AF8;N # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL 11C00..11C08;N # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E;N # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA @@ -2071,6 +2100,16 @@ FFFD;A # So REPLACEMENT CHARACTER 11CB2..11CB3;N # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E 11CB4;N # Mc MARCHEN VOWEL SIGN O 11CB5..11CB6;N # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D00..11D06;N # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E +11D08..11D09;N # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O +11D0B..11D30;N # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA +11D31..11D36;N # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A;N # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D;N # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45;N # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D46;N # Lo MASARAM GONDI REPHA +11D47;N # Mn MASARAM GONDI RA-KARA +11D50..11D59;N # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE 12000..12399;N # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E;N # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12470..12474;N # Po [5] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON @@ -2100,10 +2139,12 @@ FFFD;A # So REPLACEMENT CHARACTER 16F51..16F7E;N # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG 16F8F..16F92;N # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW 16F93..16F9F;N # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 -16FE0;W # Lm TANGUT ITERATION MARK +16FE0..16FE1;W # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK 17000..187EC;W # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC 18800..18AF2;W # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755 -1B000..1B001;W # Lo [2] KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE +1B000..1B0FF;W # Lo [256] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER RE-2 +1B100..1B11E;W # Lo [31] HENTAIGANA LETTER RE-3..HENTAIGANA LETTER N-MU-MO-2 +1B170..1B2FB;W # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 1BC00..1BC6A;N # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M 1BC70..1BC7C;N # Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK 1BC80..1BC88;N # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL @@ -2255,6 +2296,7 @@ FFFD;A # So REPLACEMENT CHARACTER 1F210..1F23B;W # So [44] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-914D 1F240..1F248;W # So [9] TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C..TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557 1F250..1F251;W # So [2] CIRCLED IDEOGRAPH ADVANTAGE..CIRCLED IDEOGRAPH ACCEPT +1F260..1F265;W # So [6] ROUNDED SYMBOL FOR FU..ROUNDED SYMBOL FOR CAI 1F300..1F320;W # So [33] CYCLONE..SHOOTING STAR 1F321..1F32C;N # So [12] THERMOMETER..WIND BLOWING FACE 1F32D..1F335;W # So [9] HOT DOG..CACTUS @@ -2299,10 +2341,11 @@ FFFD;A # So REPLACEMENT CHARACTER 1F6CC;W # So SLEEPING ACCOMMODATION 1F6CD..1F6CF;N # So [3] SHOPPING BAGS..BED 1F6D0..1F6D2;W # So [3] PLACE OF WORSHIP..SHOPPING TROLLEY +1F6D3..1F6D4;N # So [2] STUPA..PAGODA 1F6E0..1F6EA;N # So [11] HAMMER AND WRENCH..NORTHEAST-POINTING AIRPLANE 1F6EB..1F6EC;W # So [2] AIRPLANE DEPARTURE..AIRPLANE ARRIVING 1F6F0..1F6F3;N # So [4] SATELLITE..PASSENGER SHIP -1F6F4..1F6F6;W # So [3] SCOOTER..CANOE +1F6F4..1F6F8;W # So [5] SCOOTER..FLYING SAUCER 1F700..1F773;N # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE 1F780..1F7D4;N # So [85] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..HEAVY TWELVE POINTED PINWHEEL STAR 1F800..1F80B;N # So [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD @@ -2310,14 +2353,13 @@ FFFD;A # So REPLACEMENT CHARACTER 1F850..1F859;N # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW 1F860..1F887;N # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW 1F890..1F8AD;N # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS -1F910..1F91E;W # So [15] ZIPPER-MOUTH FACE..HAND WITH INDEX AND MIDDLE FINGERS CROSSED -1F920..1F927;W # So [8] FACE WITH COWBOY HAT..SNEEZING FACE -1F930;W # So PREGNANT WOMAN -1F933..1F93E;W # So [12] SELFIE..HANDBALL -1F940..1F94B;W # So [12] WILTED FLOWER..MARTIAL ARTS UNIFORM -1F950..1F95E;W # So [15] CROISSANT..PANCAKES -1F980..1F991;W # So [18] CRAB..SQUID +1F900..1F90B;N # So [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT +1F910..1F93E;W # So [47] ZIPPER-MOUTH FACE..HANDBALL +1F940..1F94C;W # So [13] WILTED FLOWER..CURLING STONE +1F950..1F96B;W # So [28] CROISSANT..CANNED FOOD +1F980..1F997;W # So [24] CRAB..CRICKET 1F9C0;W # So CHEESE WEDGE +1F9D0..1F9E6;W # So [23] FACE WITH MONOCLE..SOCKS 20000..2A6D6;W # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6 2A6D7..2A6FF;W # Cn [41] <reserved-2A6D7>..<reserved-2A6FF> 2A700..2B734;W # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 @@ -2325,7 +2367,9 @@ FFFD;A # So REPLACEMENT CHARACTER 2B740..2B81D;W # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B81E..2B81F;W # Cn [2] <reserved-2B81E>..<reserved-2B81F> 2B820..2CEA1;W # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 -2CEA2..2F7FF;W # Cn [10590] <reserved-2CEA2>..<reserved-2F7FF> +2CEA2..2CEAF;W # Cn [14] <reserved-2CEA2>..<reserved-2CEAF> +2CEB0..2EBE0;W # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 +2EBE1..2F7FF;W # Cn [3103] <reserved-2EBE1>..<reserved-2F7FF> 2F800..2FA1D;W # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D 2FA1E..2FFFD;W # Cn [1504] <reserved-2FA1E>..<reserved-2FFFD> 30000..3FFFD;W # Cn [65534] <reserved-30000>..<reserved-3FFFD> diff --git a/lib/unicore/EmojiSources.txt b/lib/unicore/EmojiSources.txt index 39255f1568..228665b52b 100644 --- a/lib/unicore/EmojiSources.txt +++ b/lib/unicore/EmojiSources.txt @@ -1,25 +1,22 @@ -# EmojiSources-9.0.0.txt -# Date: 2016-01-21, 22:00:00 GMT [MS, KW] -# © 2016 Unicode®, Inc. +# EmojiSources-10.0.0.txt +# Date: 2017-02-04, 00:00:00 GMT [MS, KW] +# © 2017 Unicode®, Inc. # For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database # For documentation, see http://www.unicode.org/reports/tr44/ # -# This file provides mappings between Unicode code points and sequences on one hand +# This file provides historical mappings between Unicode code points and sequences on one hand # and Shift-JIS codes for cell phone carrier symbols on the other hand. # Each mapping is symmetric ("round trip"), for equivalent Unicode and carrier # symbols or sequences. This file does not include best-fit ("fallback") # mappings to similar but not equivalent symbols in either mapping direction. # -# Note: It is possible that future versions of this file will include -# additional data columns providing mappings for additional vendors. -# # Created for Unicode 6.0 by Markus Scherer. # Updated for subsequent versions by Ken Whistler (no changes to mappings). # # Format: Semicolon-delimited file with a fixed number of fields. -# The number of fields may increase in the future. +# Note that the format, including the number of fields, may change in the future. # # Fields: # 0: Unicode code point or sequence @@ -30,6 +27,15 @@ # Each field 1..3 contains a code if and only if the vendor character set # has a symbol which is equivalent to the Unicode character or sequence. +# ================================================ + +# Keycap sequences for telephone keypad. +# The following 11 mappings are historical. The combining character sequences +# in these mappings do not include variation selectors for emoji presentation. +# Thus they do not match the named character sequences with keycaps listed in +# NamedSequences.txt. +# For modern data used in emoji support, see http://www.unicode.org/Public/emoji/latest/ + 0023 20E3;F985;F489;F7B0 0030 20E3;F990;F7C9;F7C5 0031 20E3;F987;F6FB;F7BC @@ -41,6 +47,7 @@ 0037 20E3;F98D;F744;F7C2 0038 20E3;F98E;F745;F7C3 0039 20E3;F98F;F746;F7C4 + 00A9;F9D6;F774;F7EE 00AE;F9DB;F775;F7EF 2002;;F7AA; diff --git a/lib/unicore/HangulSyllableType.txt b/lib/unicore/HangulSyllableType.txt index 951787bc0c..9c990d7aba 100644 --- a/lib/unicore/HangulSyllableType.txt +++ b/lib/unicore/HangulSyllableType.txt @@ -1,6 +1,6 @@ -# HangulSyllableType-9.0.0.txt -# Date: 2016-03-02, 18:55:01 GMT -# © 2016 Unicode®, Inc. +# HangulSyllableType-10.0.0.txt +# Date: 2017-02-14, 04:26:11 GMT +# © 2017 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html # diff --git a/lib/unicore/Index.txt b/lib/unicore/Index.txt index 7cf6d0a8c1..d9277822e3 100644 --- a/lib/unicore/Index.txt +++ b/lib/unicore/Index.txt @@ -545,6 +545,7 @@ BIOHAZARD SIGN 2623 BIRD 1F426 BIRGA, MONGOLIAN 1800 BISMILLAH AR-RAHMAN AR-RAHEEM, ARABIC LIGATURE FDFD +BITCOIN SIGN 20BF BLACK CIRCLE 25CF BLACK CIRCLE, MEDIUM 26AB BLACK FLAG 2691 @@ -856,6 +857,7 @@ Chinese Bopomofo 3100 Chinese Bopomofo Extensions 31A0 chinese fifth or neutral tone, mandarin 02D9 chinese first tone, mandarin 02C9 +Chinese Folk Religion Symbols 1F260 chinese fourth tone, mandarin 02CB chinese second tone, mandarin 02CA chinese third tone, mandarin 02C7 @@ -941,6 +943,7 @@ CJK Unified Ideographs Extension B 20000 CJK Unified Ideographs Extension C 2A700 CJK Unified Ideographs Extension D 2B740 CJK Unified Ideographs Extension E 2B820 +CJK Unified Ideographs Extension F 2CEB0 CLAPPING HANDS SIGN 1F44F claudian antisigma 2183 claudian digamma inversum 2132 @@ -2078,6 +2081,7 @@ FLOOR, RIGHT 230B FLOPPY DISK 1F4BE FLORAL HEART BULLET, REVERSED ROTATED 2619 florin currency symbol 0192 +FLYING SAUCER 1F6F8 folder 0192 FONGMAN, THAI CHARACTER 0E4F food available symbol 1F37D @@ -2470,6 +2474,8 @@ hedera 2767 HEH WITH YEH ABOVE, ARABIC LETTER 06C0 HELM SYMBOL 2388 HELMET WITH WHITE CROSS 26D1 +Hentaigana 1B002 +Hentaigana 1B100 HERMES, STAFF OF 269A HERMITIAN CONJUGATE MATRIX 22B9 Hexagram Symbols, Yijing / I Ching 4DC0 @@ -2545,6 +2551,7 @@ I Ching / Yijing Hexagram Symbols 4DC0 I Ching / Yijing Monogram and Digram Symbols 268A I Ching / Yijing Trigram Symbols 2630 i dot, latin capital letter 0130 +I LOVE YOU HAND SIGN 1F91F I WITH ACUTE, LATIN CAPITAL LETTER 00CD I WITH ACUTE, LATIN SMALL LETTER 00ED I WITH BREVE, LATIN SMALL LETTER 012D @@ -2808,6 +2815,7 @@ K, LATIN SUBSCRIPT SMALL LETTER 2096 KA, HIRAGANA LETTER SMALL 3095 kabusiki-gaisya 337F Kaithi 11080 +Kana Extended-A 1B100 Kana Repeat Marks 3031 Kana Supplement 1B000 Kanbun Ideographic Annotation, Japanese 3190 @@ -3214,6 +3222,7 @@ LOOP, CURLY 27B0 LOOP, DOUBLE CURLY 27BF LORRAINE, CROSS OF 2628 lorry, black 26DF +love, hand sign 1F91F LOW ACUTE ACCENT, MODIFIER LETTER 02CF LOW ASTERISK 204E low double comma quotation mark 201E @@ -3320,6 +3329,7 @@ marque de commerce 1F16A marque deposee 1F16B MARRIAGE SYMBOL 26AD mars 2642 +Masaram Gondi 11D00 MASCULINE ORDINAL INDICATOR 00BA masks of comedy and tragedy 1F3AD MASU MARK 303C @@ -3686,6 +3696,7 @@ NUMERATOR ONE, FRACTION 215F Numeric Symbols for Divination, Khmer 17F0 numerics lock 21ED NUMERO SIGN 2116 +Nushu 1B170 nut 2002 o bar, latin capital letter 019F o bar, latin small letter 0275 @@ -4082,6 +4093,7 @@ POP DIRECTIONAL ISOLATE 2069 pork (on menus) 1F416 Portrait and Role Symbols 1F464 Portrait and Role Symbols 1F930 +Portrait and Role Symbols 1F9D0 POSITION INDICATOR 2316 POSITION INDICATOR, SQUARE 2BD0 positive difference or sum 2A24 @@ -4521,6 +4533,7 @@ rofl 1F923 Role Symbols 1F481 Role Symbols, Portrait and 1F464 Role Symbols, Portrait and 1F930 +Role Symbols, Portrait and 1F9D0 ROLLING ON THE FLOOR LAUGHING 1F923 Roman Numerals 2160 Roman Numerals, Archaic 2185 @@ -4857,6 +4870,7 @@ Sora Sompeng 110D0 sound 1F50A SOUND RECORDING COPYRIGHT 2117 SOURCE, INFORMATION 2139 +Soyombo 11A50 SPACE 0020 SPACE MARK, OGHAM 1680 SPACE, EM 2003 @@ -5248,6 +5262,7 @@ SYRIAC CROSS, WEST 2670 Syriac Letters 0710 Syriac Punctuation and Signs 0700 syriac sam 070F +Syriac Supplement 0860 T WITH CARON, LATIN SMALL LETTER 0165 T WITH CEDILLA, LATIN SMALL LETTER 0163 T WITH CIRCUMFLEX BELOW, LATIN SMALL LETTER 1E71 @@ -5267,6 +5282,7 @@ T, COMBINING LATIN SMALL LETTER 036D T, LATIN LETTER SMALL CAPITAL 1D1B T, LATIN SMALL LETTER TURNED 0287 T, LATIN SUBSCRIPT SMALL LETTER 209C +T-REX 1F996 tab 0009 TAB KEY, HORIZONTAL 2B7E TAB KEY, VERTICAL 2B7F @@ -5603,6 +5619,9 @@ TWO DOT LEADER 2025 TWO DOT PUNCTUATION 205A TWO, SUPERSCRIPT 00B2 TWO-EM DASH 2E3A +Typicon Punctuation 2E44 +Typicon Symbols 1F900 +tyrannosaurus rex 1F996 U BAR, LATIN CAPITAL LETTER 0244 U BAR, LATIN SMALL LETTER 0289 U WITH ACUTE, LATIN CAPITAL LETTER 00DA @@ -5718,6 +5737,7 @@ V, LATIN SUBSCRIPT SMALL LETTER 1D65 Vai A500 valentine 2665 valid 22A8 +VAMPIRE 1F9DB varavu, tamil 0BF7 varia, greek 0300 VARIATION INDICATOR, IDEOGRAPHIC 303E @@ -5984,6 +6004,7 @@ Z WITH SWASH TAIL, LATIN SMALL LETTER 0240 Z, BLACK-LETTER CAPITAL 2128 Z, DOUBLE-STRUCK CAPITAL 2124 Z, LATIN LETTER SMALL CAPITAL 1D22 +Zanabazar Square 11A00 Zapf Dingbats Series 100, ITC 2700 ZERO WIDTH JOINER 200D ZERO WIDTH NO-BREAK SPACE FEFF @@ -5995,6 +6016,7 @@ ZERO, SUPERSCRIPT 2070 ZIGZAG ABOVE, COMBINING 035B Zodiac, Signs of the Asian 1F400 Zodiacal Symbols 2648 +ZOMBIE 1F9DF zwj 200D zwnbsp FEFF zwnj 200C diff --git a/lib/unicore/IndicPositionalCategory.txt b/lib/unicore/IndicPositionalCategory.txt index 16a8268a25..40d8b3765f 100644 --- a/lib/unicore/IndicPositionalCategory.txt +++ b/lib/unicore/IndicPositionalCategory.txt @@ -1,6 +1,6 @@ -# IndicPositionalCategory-9.0.0.txt -# Date: 2016-06-09, 19:33:00 GMT [RP] -# © 2016 Unicode®, Inc. +# IndicPositionalCategory-10.0.0.txt +# Date: 2017-05-31, 01:07:00 GMT [RP] +# © 2017 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html # @@ -59,10 +59,11 @@ # Ahom, Balinese, Batak, Bengali, Bhaiksuki, Brahmi, Buginese, Buhid, # Chakma, Cham, Devanagari, Grantha, Gujarati, Gurmukhi, Hanunoo, # Javanese, Kaithi, Kannada, Kharoshthi, Khmer, Khojki, Khudawadi, -# Lao, Lepcha, Limbu, Malayalam, Marchen, Meetei Mayek, Modi, -# Myanmar, Newa, New Tai Lue, Oriya, Rejang, Saurashtra, Sharada, -# Siddham, Sinhala, Sundanese, Syloti Nagri, Tagalog, Tagbanwa, Tai -# Tham, Tai Viet, Takri, Tamil, Telugu, Thai, Tibetan, and Tirhuta. +# Lao, Lepcha, Limbu, Malayalam, Marchen, Masaram Gondi, Meetei +# Mayek, Modi, Myanmar, Newa, New Tai Lue, Oriya, Rejang, Saurashtra, +# Sharada, Siddham, Sinhala, Soyombo, Sundanese, Syloti Nagri, +# Tagalog, Tagbanwa, Tai Tham, Tai Viet, Takri, Tamil, Telugu, Thai, +# Tibetan, Tirhuta, and Zanabazar Square. # # All characters for all other scripts not in that list # take the default value for this property. @@ -179,6 +180,7 @@ 1C24..1C26 ; Right # Mc [3] LEPCHA SUBJOINED LETTER YA..LEPCHA VOWEL SIGN AA 1C2A..1C2B ; Right # Mc [2] LEPCHA VOWEL SIGN U..LEPCHA VOWEL SIGN UU 1CE1 ; Right # Mc VEDIC TONE ATHARVAVEDIC INDEPENDENT SVARITA +1CF7 ; Right # Mc VEDIC SIGN ATIKRAMA A823..A824 ; Right # Mc [2] SYLOTI NAGRI VOWEL SIGN A..SYLOTI NAGRI VOWEL SIGN I A827 ; Right # Mc SYLOTI NAGRI VOWEL SIGN OO A880..A881 ; Right # Mc [2] SAURASHTRA SIGN ANUSVARA..SAURASHTRA SIGN VISARGA @@ -186,7 +188,7 @@ A8B4..A8C3 ; Right # Mc [16] SAURASHTRA CONSONANT SIGN HAARU..SAURASHTRA VOW A952..A953 ; Right # Mc [2] REJANG CONSONANT SIGN H..REJANG VIRAMA A983 ; Right # Mc JAVANESE SIGN WIGNYAN A9B4..A9B5 ; Right # Mc [2] JAVANESE VOWEL SIGN TARUNG..JAVANESE VOWEL SIGN TOLONG -A9BD..A9BF ; Right # Mc [3] JAVANESE CONSONANT SIGN KERET..JAVANESE CONSONANT SIGN CAKRA +A9BD..A9BE ; Right # Mc [2] JAVANESE CONSONANT SIGN KERET..JAVANESE CONSONANT SIGN PENGKAL AA33 ; Right # Mc CHAM CONSONANT SIGN YA AA4D ; Right # Mc CHAM CONSONANT SIGN FINAL H AA7B ; Right # Mc MYANMAR SIGN PAO KAREN TONE @@ -238,6 +240,9 @@ ABEC ; Right # Mc MEETEI MAYEK LUM IYEK 116AF ; Right # Mc TAKRI VOWEL SIGN II 116B6 ; Right # Mc TAKRI SIGN VIRAMA 11720..11721 ; Right # Mc [2] AHOM VOWEL SIGN A..AHOM VOWEL SIGN AA +11A39 ; Right # Mc ZANABAZAR SQUARE SIGN VISARGA +11A57..11A58 ; Right # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU +11A97 ; Right # Mc SOYOMBO SIGN VISARGA 11C2F ; Right # Mc BHAIKSUKI VOWEL SIGN AA 11C3E ; Right # Mc BHAIKSUKI SIGN VISARGA 11CA9 ; Right # Mc MARCHEN SUBJOINED LETTER YA @@ -335,6 +340,7 @@ AABB..AABC ; Visual_Order_Left # Lo [2] TAI VIET VOWEL AUE..TAI VIET VOWEL 0A81..0A82 ; Top # Mn [2] GUJARATI SIGN CANDRABINDU..GUJARATI SIGN ANUSVARA 0AC5 ; Top # Mn GUJARATI VOWEL SIGN CANDRA E 0AC7..0AC8 ; Top # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI +0AFA..0AFF ; Top # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE 0B01 ; Top # Mn ORIYA SIGN CANDRABINDU 0B3F ; Top # Mn ORIYA VOWEL SIGN I 0B56 ; Top # Mn ORIYA AI LENGTH MARK @@ -350,7 +356,8 @@ AABB..AABC ; Visual_Order_Left # Lo [2] TAI VIET VOWEL AUE..TAI VIET VOWEL 0CBF ; Top # Mn KANNADA VOWEL SIGN I 0CC6 ; Top # Mn KANNADA VOWEL SIGN E 0CCC..0CCD ; Top # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA -0D01 ; Top # Mn MALAYALAM SIGN CANDRABINDU +0D00..0D01 ; Top # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU +0D3B..0D3C ; Top # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA 0D4D ; Top # Mn MALAYALAM SIGN VIRAMA 0DCA ; Top # Mn SINHALA SIGN AL-LAKUNA 0DD2..0DD3 ; Top # Mn [2] SINHALA VOWEL SIGN KETTI IS-PILLA..SINHALA VOWEL SIGN DIGA IS-PILLA @@ -478,10 +485,22 @@ ABE5 ; Top # Mn MEETEI MAYEK VOWEL SIGN ANAP 11722..11723 ; Top # Mn [2] AHOM VOWEL SIGN I..AHOM VOWEL SIGN II 11727 ; Top # Mn AHOM VOWEL SIGN AW 11729..1172B ; Top # Mn [3] AHOM VOWEL SIGN AI..AHOM SIGN KILLER +11A01 ; Top # Mn ZANABAZAR SQUARE VOWEL SIGN I +11A04..11A09 ; Top # Mn [6] ZANABAZAR SQUARE VOWEL SIGN E..ZANABAZAR SQUARE VOWEL SIGN REVERSED I +11A35..11A38 ; Top # Mn [4] ZANABAZAR SQUARE SIGN CANDRABINDU..ZANABAZAR SQUARE SIGN ANUSVARA +11A51 ; Top # Mn SOYOMBO VOWEL SIGN I +11A54..11A56 ; Top # Mn [3] SOYOMBO VOWEL SIGN E..SOYOMBO VOWEL SIGN OE +11A96 ; Top # Mn SOYOMBO SIGN ANUSVARA +11A98 ; Top # Mn SOYOMBO GEMINATION MARK 11C30..11C31 ; Top # Mn [2] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN II 11C38..11C3D ; Top # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA 11CB3 ; Top # Mn MARCHEN VOWEL SIGN E 11CB5..11CB6 ; Top # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D31..11D35 ; Top # Mn [5] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN UU +11D3A ; Top # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; Top # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D41 ; Top # Mn [3] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI SIGN VISARGA +11D43 ; Top # Mn MASARAM GONDI SIGN CANDRA # Indic_Positional_Category=Bottom @@ -601,11 +620,22 @@ ABED ; Bottom # Mn MEETEI MAYEK APUN IYEK 1171D ; Bottom # Mn AHOM CONSONANT SIGN MEDIAL LA 11724..11725 ; Bottom # Mn [2] AHOM VOWEL SIGN U..AHOM VOWEL SIGN UU 11728 ; Bottom # Mn AHOM VOWEL SIGN O +11A02..11A03 ; Bottom # Mn [2] ZANABAZAR SQUARE VOWEL SIGN UE..ZANABAZAR SQUARE VOWEL SIGN U +11A0A ; Bottom # Mn ZANABAZAR SQUARE VOWEL LENGTH MARK +11A33..11A34 ; Bottom # Mn [2] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN VIRAMA +11A3B..11A3E ; Bottom # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A52..11A53 ; Bottom # Mn [2] SOYOMBO VOWEL SIGN UE..SOYOMBO VOWEL SIGN U +11A59..11A5B ; Bottom # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A8A..11A95 ; Bottom # Mn [12] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO FINAL CONSONANT SIGN -A 11C32..11C36 ; Bottom # Mn [5] BHAIKSUKI VOWEL SIGN U..BHAIKSUKI VOWEL SIGN VOCALIC L 11C3F ; Bottom # Mn BHAIKSUKI SIGN VIRAMA 11C92..11CA7 ; Bottom # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA 11CAA..11CB0 ; Bottom # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA 11CB2 ; Bottom # Mn MARCHEN VOWEL SIGN U +11D36 ; Bottom # Mn MASARAM GONDI VOWEL SIGN VOCALIC R +11D42 ; Bottom # Mn MASARAM GONDI SIGN NUKTA +11D44 ; Bottom # Mn MASARAM GONDI SIGN HALANTA +11D47 ; Bottom # Mn MASARAM GONDI RA-KARA # Indic_Positional_Category=Top_And_Bottom @@ -649,6 +679,10 @@ ABED ; Bottom # Mn MEETEI MAYEK APUN IYEK 1B3B ; Bottom_And_Right # Mc BALINESE VOWEL SIGN RA REPA TEDUNG A9C0 ; Bottom_And_Right # Mc JAVANESE PANGKON +# Indic_Positional_Category=Bottom_And_Left + +A9BF ; Bottom_And_Left # Mc JAVANESE CONSONANT SIGN CAKRA + # Indic_Positional_Category=Top_And_Bottom_And_Right 1B3D ; Top_And_Bottom_And_Right # Mc BALINESE VOWEL SIGN LA LENGA TEDUNG diff --git a/lib/unicore/IndicSyllabicCategory.txt b/lib/unicore/IndicSyllabicCategory.txt index d6c6162826..fcd40af932 100644 --- a/lib/unicore/IndicSyllabicCategory.txt +++ b/lib/unicore/IndicSyllabicCategory.txt @@ -1,6 +1,6 @@ -# IndicSyllabicCategory-9.0.0.txt -# Date: 2016-05-21, 02:46:00 GMT [RP] -# © 2016 Unicode®, Inc. +# IndicSyllabicCategory-10.0.0.txt +# Date: 2017-05-31, 01:07:00 GMT [KW, RP] +# © 2017 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html # @@ -21,7 +21,7 @@ # of Indic script characters which are relevant to how Indic # syllables (or aksaras) are constructed. Note that rules for # syllabic structure in Indic scripts may differ significantly -# from how phonological syllables are defined. +# from how phonological syllables are defined. # # Format: # Field 0 Unicode code point value or range of code point values @@ -38,11 +38,12 @@ # Ahom, Balinese, Batak, Bengali, Bhaiksuki, Brahmi, Buginese, Buhid, # Chakma, Cham, Devanagari, Grantha, Gujarati, Gurmukhi, Hanunoo, # Javanese, Kaithi, Kannada, Kayah Li, Kharoshthi, Khmer, Khojki, -# Khudawadi, Lao, Lepcha, Limbu, Mahajani, Malayalam, Marchen, Meetei -# Mayek, Modi, Multani, Myanmar, Newa, New Tai Lue, Oriya, Phags-pa, -# Rejang, Saurashtra, Sharada, Siddham, Sinhala, Sundanese, Syloti -# Nagri, Tagalog, Tagbanwa, Tai Le, Tai Tham, Tai Viet, Takri, Tamil, -# Telugu, Thai, Tibetan, and Tirhuta. +# Khudawadi, Lao, Lepcha, Limbu, Mahajani, Malayalam, Marchen, +# Masaram Gondi, Meetei Mayek, Modi, Multani, Myanmar, Newa, New Tai +# Lue, Oriya, Phags-pa, Rejang, Saurashtra, Sharada, Siddham, +# Sinhala, Soyombo, Sundanese, Syloti Nagri, Tagalog, Tagbanwa, Tai +# Le, Tai Tham, Tai Viet, Takri, Tamil, Telugu, Thai, Tibetan, +# Tirhuta, and Zanabazar Square. # # All characters for all other scripts not in that list # take the default value for this property, unless they @@ -63,13 +64,13 @@ # Indic_Syllabic_Category=Bindu # Bindu/Anusvara (nasalization or -n) -# Excludes various Vedic nasalization signs. # [Not derivable] 0900..0902 ; Bindu # Mn [3] DEVANAGARI SIGN INVERTED CANDRABINDU..DEVANAGARI SIGN ANUSVARA 0981 ; Bindu # Mn BENGALI SIGN CANDRABINDU 0982 ; Bindu # Mc BENGALI SIGN ANUSVARA +09FC ; Bindu # Lo BENGALI LETTER VEDIC ANUSVARA 0A01..0A02 ; Bindu # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI 0A70 ; Bindu # Mn GURMUKHI TIPPI 0A81..0A82 ; Bindu # Mn [2] GUJARATI SIGN CANDRABINDU..GUJARATI SIGN ANUSVARA @@ -80,6 +81,7 @@ 0C01..0C02 ; Bindu # Mc [2] TELUGU SIGN CANDRABINDU..TELUGU SIGN ANUSVARA 0C81 ; Bindu # Mn KANNADA SIGN CANDRABINDU 0C82 ; Bindu # Mc KANNADA SIGN ANUSVARA +0D00 ; Bindu # Mn MALAYALAM SIGN COMBINING ANUSVARA ABOVE 0D01 ; Bindu # Mn MALAYALAM SIGN CANDRABINDU 0D02 ; Bindu # Mc MALAYALAM SIGN ANUSVARA 0D82 ; Bindu # Mc SINHALA SIGN ANUSVARAYA @@ -90,6 +92,7 @@ 1036 ; Bindu # Mn MYANMAR SIGN ANUSVARA 17C6 ; Bindu # Mn KHMER SIGN NIKAHIT 1932 ; Bindu # Mn LIMBU SMALL LETTER ANUSVARA +1A74 ; Bindu # Mn TAI THAM SIGN MAI KANG 1B00..1B02 ; Bindu # Mn [3] BALINESE SIGN ULU RICEM..BALINESE SIGN CECEK 1B80 ; Bindu # Mn SUNDANESE SIGN PANYECEK 1C34..1C35 ; Bindu # Mc [2] LEPCHA CONSONANT SIGN NYIN-DO..LEPCHA CONSONANT SIGN KANG @@ -97,6 +100,7 @@ A80B ; Bindu # Mn SYLOTI NAGRI SIGN ANUSVARA A873 ; Bindu # Lo PHAGS-PA LETTER CANDRABINDU A880 ; Bindu # Mc SAURASHTRA SIGN ANUSVARA A8C5 ; Bindu # Mn SAURASHTRA SIGN CANDRABINDU +A8F2..A8F3 ; Bindu # Lo [2] DEVANAGARI SIGN SPACING CANDRABINDU..DEVANAGARI SIGN CANDRABINDU VIRAMA A980..A981 ; Bindu # Mn [2] JAVANESE SIGN PANYANGGA..JAVANESE SIGN CECAK 10A0E ; Bindu # Mn KHAROSHTHI SIGN ANUSVARA 11000 ; Bindu # Mc BRAHMI SIGN CANDRABINDU @@ -108,13 +112,17 @@ A980..A981 ; Bindu # Mn [2] JAVANESE SIGN PANYANGGA..JAVANESE SIGN CECAK 112DF ; Bindu # Mn KHUDAWADI SIGN ANUSVARA 11300..11301 ; Bindu # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU 11302 ; Bindu # Mc GRANTHA SIGN ANUSVARA +1135E..1135F ; Bindu # Lo [2] GRANTHA LETTER VEDIC ANUSVARA..GRANTHA LETTER VEDIC DOUBLE ANUSVARA 11443..11444 ; Bindu # Mn [2] NEWA SIGN CANDRABINDU..NEWA SIGN ANUSVARA 114BF..114C0 ; Bindu # Mn [2] TIRHUTA SIGN CANDRABINDU..TIRHUTA SIGN ANUSVARA 115BC..115BD ; Bindu # Mn [2] SIDDHAM SIGN CANDRABINDU..SIDDHAM SIGN ANUSVARA 1163D ; Bindu # Mn MODI SIGN ANUSVARA 116AB ; Bindu # Mn TAKRI SIGN ANUSVARA +11A35..11A38 ; Bindu # Mn [4] ZANABAZAR SQUARE SIGN CANDRABINDU..ZANABAZAR SQUARE SIGN ANUSVARA +11A96 ; Bindu # Mn SOYOMBO SIGN ANUSVARA 11C3C..11C3D ; Bindu # Mn [2] BHAIKSUKI SIGN CANDRABINDU..BHAIKSUKI SIGN ANUSVARA 11CB5..11CB6 ; Bindu # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D40 ; Bindu # Mn MASARAM GONDI SIGN ANUSVARA # ================================================ @@ -123,7 +131,7 @@ A980..A981 ; Bindu # Mn [2] JAVANESE SIGN PANYANGGA..JAVANESE SIGN CECAK # Visarga (-h) # Includes specialized case for Sanskrit: ardhavisarga # Excludes letters for jihvamuliya and upadhmaniya, which are -# related, but structured somewhat differently. +# related, but structured somewhat differently. # [Not derivable] @@ -156,7 +164,10 @@ AAF5 ; Visarga # Mc MEETEI MAYEK VOWEL SIGN VISARGA 115BE ; Visarga # Mc SIDDHAM SIGN VISARGA 1163E ; Visarga # Mc MODI SIGN VISARGA 116AC ; Visarga # Mc TAKRI SIGN VISARGA +11A39 ; Visarga # Mc ZANABAZAR SQUARE SIGN VISARGA +11A97 ; Visarga # Mc SOYOMBO SIGN VISARGA 11C3E ; Visarga # Mc BHAIKSUKI SIGN VISARGA +11D41 ; Visarga # Mn MASARAM GONDI SIGN VISARGA # ================================================ @@ -187,14 +198,19 @@ AAF5 ; Visarga # Mc MEETEI MAYEK VOWEL SIGN VISARGA # Indic_Syllabic_Category=Nukta # Nukta (diacritic for borrowed consonants or other consonant -# modifications) +# modifications). Note that while the resulting sound is typically a +# consonant, the base letter a nukta follows may be an independent +# vowel. For example, <U+0A85 GUJARATI LETTER A, U+0AFD GUJARATI +# SIGN THREE-DOT NUKTA ABOVE> is used to transcribe ARABIC LETTER +# AIN. -# [Derivation: (ccc=7) + 0F39 + 10A38..10A3A - 1037 - 1E94A] +# [Not derivable] 093C ; Nukta # Mn DEVANAGARI SIGN NUKTA 09BC ; Nukta # Mn BENGALI SIGN NUKTA 0A3C ; Nukta # Mn GURMUKHI SIGN NUKTA 0ABC ; Nukta # Mn GUJARATI SIGN NUKTA +0AFD..0AFF ; Nukta # Mn [3] GUJARATI SIGN THREE-DOT NUKTA ABOVE..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE 0B3C ; Nukta # Mn ORIYA SIGN NUKTA 0CBC ; Nukta # Mn KANNADA SIGN NUKTA 0F39 ; Nukta # Mn TIBETAN MARK TSA -PHRU @@ -213,6 +229,7 @@ A9B3 ; Nukta # Mn JAVANESE SIGN CECAK TELU 114C3 ; Nukta # Mn TIRHUTA SIGN NUKTA 115C0 ; Nukta # Mn SIDDHAM SIGN NUKTA 116B7 ; Nukta # Mn TAKRI SIGN NUKTA +11D42 ; Nukta # Mn MASARAM GONDI SIGN NUKTA # ================================================ @@ -261,6 +278,8 @@ A9C0 ; Virama # Mc JAVANESE PANGKON # [Not derivable] +0D3B ; Pure_Killer # Mn MALAYALAM SIGN VERTICAL BAR VIRAMA +0D3C ; Pure_Killer # Mn MALAYALAM SIGN CIRCULAR VIRAMA 0E3A ; Pure_Killer # Mn THAI CHARACTER PHINTHU 0E4E ; Pure_Killer # Mn THAI CHARACTER YAMAKKAN 0F84 ; Pure_Killer # Mn TIBETAN MARK HALANTA @@ -268,6 +287,7 @@ A9C0 ; Virama # Mc JAVANESE PANGKON 1714 ; Pure_Killer # Mn TAGALOG SIGN VIRAMA 1734 ; Pure_Killer # Mn HANUNOO SIGN PAMUDPOD 17D1 ; Pure_Killer # Mn KHMER SIGN VIRIAM +1A7A ; Pure_Killer # Mn TAI THAM SIGN RA HAAM 1BAA ; Pure_Killer # Mc SUNDANESE SIGN PAMAAEH 1BF2..1BF3 ; Pure_Killer # Mc [2] BATAK PANGOLAT..BATAK PANONGONAN A806 ; Pure_Killer # Mn SYLOTI NAGRI SIGN HASANTA @@ -276,6 +296,8 @@ ABED ; Pure_Killer # Mn MEETEI MAYEK APUN IYEK 11134 ; Pure_Killer # Mn CHAKMA MAAYYAA 112EA ; Pure_Killer # Mn KHUDAWADI SIGN VIRAMA 1172B ; Pure_Killer # Mn AHOM SIGN KILLER +11A34 ; Pure_Killer # Mn ZANABAZAR SQUARE SIGN VIRAMA +11D44 ; Pure_Killer # Mn MASARAM GONDI SIGN HALANTA # ================================================ @@ -292,6 +314,9 @@ ABED ; Pure_Killer # Mn MEETEI MAYEK APUN IYEK AAF6 ; Invisible_Stacker # Mn MEETEI MAYEK VIRAMA 10A3F ; Invisible_Stacker # Mn KHAROSHTHI VIRAMA 11133 ; Invisible_Stacker # Mn CHAKMA VIRAMA +11A47 ; Invisible_Stacker # Mn ZANABAZAR SQUARE SUBJOINER +11A99 ; Invisible_Stacker # Mn SOYOMBO SUBJOINER +11D45 ; Invisible_Stacker # Mn MASARAM GONDI VIRAMA # ================================================ @@ -372,15 +397,22 @@ ABD1 ; Vowel_Independent # Lo MEETEI MAYEK LETTER ATIYA 115D8..115DB ; Vowel_Independent # Lo [4] SIDDHAM LETTER THREE-CIRCLE ALTERNATE I..SIDDHAM LETTER ALTERNATE U 11600..1160D ; Vowel_Independent # Lo [14] MODI LETTER A..MODI LETTER AU 11680..11689 ; Vowel_Independent # Lo [10] TAKRI LETTER A..TAKRI LETTER AU +11A00 ; Vowel_Independent # Lo ZANABAZAR SQUARE LETTER A +11A50 ; Vowel_Independent # Lo SOYOMBO LETTER A 11C00..11C08 ; Vowel_Independent # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C0D ; Vowel_Independent # Lo [4] BHAIKSUKI LETTER E..BHAIKSUKI LETTER AU +11D00..11D06 ; Vowel_Independent # Lo [6] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E +11D08..11D09 ; Vowel_Independent # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O +11D0B ; Vowel_Independent # Lo MASARAM GONDI LETTER AU # ================================================ # Indic_Syllabic_Category=Vowel_Dependent -# Dependent Vowels (contrasted with independent vowels and/or with complex placement) -# Matras (in Indic scripts) +# Dependent Vowels (contrasted with independent vowels and/or with +# complex placement). Known as matras in Indic scripts. Also +# includes vowel modifiers that follow dependent (and sometimes +# independent) vowels. # [Not derivable] @@ -497,7 +529,7 @@ ABD1 ; Vowel_Independent # Lo MEETEI MAYEK LETTER ATIYA 1A63..1A64 ; Vowel_Dependent # Mc [2] TAI THAM VOWEL SIGN AA..TAI THAM VOWEL SIGN TALL AA 1A65..1A6C ; Vowel_Dependent # Mn [8] TAI THAM VOWEL SIGN I..TAI THAM VOWEL SIGN OA BELOW 1A6D..1A72 ; Vowel_Dependent # Mc [6] TAI THAM VOWEL SIGN OY..TAI THAM VOWEL SIGN THAM AI -1A73..1A74 ; Vowel_Dependent # Mn [2] TAI THAM VOWEL SIGN OA ABOVE..TAI THAM SIGN MAI KANG +1A73 ; Vowel_Dependent # Mn TAI THAM VOWEL SIGN OA ABOVE 1B35 ; Vowel_Dependent # Mc BALINESE VOWEL SIGN TEDUNG 1B36..1B3A ; Vowel_Dependent # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA 1B3B ; Vowel_Dependent # Mc BALINESE VOWEL SIGN RA REPA TEDUNG @@ -593,6 +625,12 @@ ABE9..ABEA ; Vowel_Dependent # Mc [2] MEETEI MAYEK VOWEL SIGN CHEINAP..MEET 11722..11725 ; Vowel_Dependent # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU 11726 ; Vowel_Dependent # Mc AHOM VOWEL SIGN E 11727..1172A ; Vowel_Dependent # Mn [4] AHOM VOWEL SIGN AW..AHOM VOWEL SIGN AM +11A01..11A06 ; Vowel_Dependent # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O +11A07..11A08 ; Vowel_Dependent # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU +11A09..11A0A ; Vowel_Dependent # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A51..11A56 ; Vowel_Dependent # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A57..11A58 ; Vowel_Dependent # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU +11A59..11A5B ; Vowel_Dependent # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK 11C2F ; Vowel_Dependent # Mc BHAIKSUKI VOWEL SIGN AA 11C30..11C36 ; Vowel_Dependent # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L 11C38..11C3B ; Vowel_Dependent # Mn [4] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI VOWEL SIGN AU @@ -600,6 +638,11 @@ ABE9..ABEA ; Vowel_Dependent # Mc [2] MEETEI MAYEK VOWEL SIGN CHEINAP..MEET 11CB1 ; Vowel_Dependent # Mc MARCHEN VOWEL SIGN I 11CB2..11CB3 ; Vowel_Dependent # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E 11CB4 ; Vowel_Dependent # Mc MARCHEN VOWEL SIGN O +11D31..11D36 ; Vowel_Dependent # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; Vowel_Dependent # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; Vowel_Dependent # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F ; Vowel_Dependent # Mn MASARAM GONDI VOWEL SIGN AU +11D43 ; Vowel_Dependent # Mn MASARAM GONDI SIGN CANDRA # ================================================ @@ -637,6 +680,8 @@ A926..A92A ; Vowel # Mn [5] KAYAH LI VOWEL UE..KAYAH LI VOWEL O 2010..2014 ; Consonant_Placeholder # Pd [5] HYPHEN..EM DASH 25CC ; Consonant_Placeholder # So DOTTED CIRCLE AA74..AA76 ; Consonant_Placeholder # Lo [3] MYANMAR LOGOGRAM KHAMTI OAY..MYANMAR LOGOGRAM KHAMTI HM +11A3F ; Consonant_Placeholder # Po ZANABAZAR SQUARE INITIAL HEAD MARK +11A45 ; Consonant_Placeholder # Po ZANABAZAR SQUARE INITIAL DOUBLE-LINED HEAD MARK # ================================================ @@ -791,8 +836,11 @@ ABD2..ABDA ; Consonant # Lo [9] MEETEI MAYEK LETTER GOK..MEETEI MAYEK LETTE 1160E..1162F ; Consonant # Lo [34] MODI LETTER KA..MODI LETTER LLA 1168A..116AA ; Consonant # Lo [33] TAKRI LETTER KA..TAKRI LETTER RRA 11700..11719 ; Consonant # Lo [26] AHOM LETTER KA..AHOM LETTER JHA +11A0B..11A32 ; Consonant # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA +11A5C..11A83 ; Consonant # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA 11C0E..11C2E ; Consonant # Lo [33] BHAIKSUKI LETTER KA..BHAIKSUKI LETTER HA 11C72..11C8F ; Consonant # Lo [30] MARCHEN LETTER KA..MARCHEN LETTER A +11D0C..11D30 ; Consonant # Lo [37] MASARAM GONDI LETTER KA..MASARAM GONDI LETTER TRA # ================================================ @@ -822,11 +870,13 @@ ABD2..ABDA ; Consonant # Lo [9] MEETEI MAYEK LETTER GOK..MEETEI MAYEK LETTE # Indic_Syllabic_Category=Consonant_Prefixed -# Cluster-intial consonants +# Cluster-initial consonants # [Not derivable] 111C2..111C3 ; Consonant_Prefixed # Lo [2] SHARADA SIGN JIHVAMULIYA..SHARADA SIGN UPADHMANIYA +11A3A ; Consonant_Prefixed # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA +11A86..11A89 ; Consonant_Prefixed # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA # ================================================ @@ -837,16 +887,20 @@ ABD2..ABDA ; Consonant # Lo [9] MEETEI MAYEK LETTER GOK..MEETEI MAYEK LETTE # [Not derivable] 0D4E ; Consonant_Preceding_Repha # Lo MALAYALAM LETTER DOT REPH +11D46 ; Consonant_Preceding_Repha # Lo MASARAM GONDI REPHA # ================================================ # Indic_Syllabic_Category=Consonant_Succeeding_Repha -# Repha Form of RA (reanalyzed in some scripts), when succeeding the main consonant +# Repha Form of RA (reanalyzed in some scripts), when succeeding the main consonant. +# Additionally, U+1A5A TAI THAM CONSONANT SIGN LOW PA has been temporarily classified +# in this class due to its behavior, although it is not a RA. # [Not derivable] 17CC ; Consonant_Succeeding_Repha # Mn KHMER SIGN ROBAT +1A5A ; Consonant_Succeeding_Repha # Mn TAI THAM CONSONANT SIGN LOW PA 1B03 ; Consonant_Succeeding_Repha # Mn BALINESE SIGN SURANG 1B81 ; Consonant_Succeeding_Repha # Mn SUNDANESE SIGN PANGLAYAR A982 ; Consonant_Succeeding_Repha # Mn JAVANESE SIGN LAYAR @@ -862,6 +916,8 @@ A982 ; Consonant_Succeeding_Repha # Mn JAVANESE SIGN LAYAR 0F8D..0F97 ; Consonant_Subjoined # Mn [11] TIBETAN SUBJOINED SIGN LCE TSA CAN..TIBETAN SUBJOINED LETTER JA 0F99..0FBC ; Consonant_Subjoined # Mn [36] TIBETAN SUBJOINED LETTER NYA..TIBETAN SUBJOINED LETTER FIXED-FORM RA 1929..192B ; Consonant_Subjoined # Mc [3] LIMBU SUBJOINED LETTER YA..LIMBU SUBJOINED LETTER WA +1A57 ; Consonant_Subjoined # Mc TAI THAM CONSONANT SIGN LA TANG LAI +1A5B..1A5E ; Consonant_Subjoined # Mn [4] TAI THAM CONSONANT SIGN HIGH RATHA OR LOW PA..TAI THAM CONSONANT SIGN SA 1BA1 ; Consonant_Subjoined # Mc SUNDANESE CONSONANT SIGN PAMINGKAL 1BA2..1BA3 ; Consonant_Subjoined # Mn [2] SUNDANESE CONSONANT SIGN PANYAKRA..SUNDANESE CONSONANT SIGN PANYIKU 1BAC..1BAD ; Consonant_Subjoined # Mn [2] SUNDANESE CONSONANT SIGN PASANGAN MA..SUNDANESE CONSONANT SIGN PASANGAN WA @@ -894,6 +950,8 @@ A9BE..A9BF ; Consonant_Medial # Mc [2] JAVANESE CONSONANT SIGN PENGKAL..JAV AA33..AA34 ; Consonant_Medial # Mc [2] CHAM CONSONANT SIGN YA..CHAM CONSONANT SIGN RA AA35..AA36 ; Consonant_Medial # Mn [2] CHAM CONSONANT SIGN LA..CHAM CONSONANT SIGN WA 1171D..1171F ; Consonant_Medial # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA +11A3B..11A3E ; Consonant_Medial # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11D47 ; Consonant_Medial # Mn MASARAM GONDI RA-KARA # ================================================ @@ -907,8 +965,7 @@ AA35..AA36 ; Consonant_Medial # Mn [2] CHAM CONSONANT SIGN LA..CHAM CONSONA 1933..1938 ; Consonant_Final # Mc [6] LIMBU SMALL LETTER TA..LIMBU SMALL LETTER LA 1939 ; Consonant_Final # Mn LIMBU SIGN MUKPHRENG 19C1..19C7 ; Consonant_Final # Lo [7] NEW TAI LUE LETTER FINAL V..NEW TAI LUE LETTER FINAL B -1A57 ; Consonant_Final # Mc TAI THAM CONSONANT SIGN LA TANG LAI -1A58..1A5E ; Consonant_Final # Mn [7] TAI THAM SIGN MAI KANG LAI..TAI THAM CONSONANT SIGN SA +1A58..1A59 ; Consonant_Final # Mn [2] TAI THAM SIGN MAI KANG LAI..TAI THAM CONSONANT SIGN FINAL NGA 1BBE..1BBF ; Consonant_Final # Lo [2] SUNDANESE LETTER FINAL K..SUNDANESE LETTER FINAL M 1BF0..1BF1 ; Consonant_Final # Mn [2] BATAK CONSONANT SIGN NG..BATAK CONSONANT SIGN H 1C2D..1C33 ; Consonant_Final # Mn [7] LEPCHA CONSONANT SIGN K..LEPCHA CONSONANT SIGN T @@ -921,6 +978,7 @@ AA44..AA4B ; Consonant_Final # Lo [8] CHAM LETTER FINAL CH..CHAM LETTER FIN AA4C ; Consonant_Final # Mn CHAM CONSONANT SIGN FINAL M AA4D ; Consonant_Final # Mc CHAM CONSONANT SIGN FINAL H ABDB..ABE2 ; Consonant_Final # Lo [8] MEETEI MAYEK LETTER KOK LONSUM..MEETEI MAYEK LETTER I LONSUM +11A8A..11A95 ; Consonant_Final # Mn [12] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO FINAL CONSONANT SIGN -A # ================================================ @@ -993,6 +1051,7 @@ ABEC ; Tone_Mark # Mc MEETEI MAYEK LUM IYEK 0A71 ; Gemination_Mark # Mn GURMUKHI ADDAK 11237 ; Gemination_Mark # Mn KHOJKI SIGN SHADDA +11A98 ; Gemination_Mark # Mn SOYOMBO GEMINATION MARK # ================================================ @@ -1003,10 +1062,12 @@ ABEC ; Tone_Mark # Mc MEETEI MAYEK LUM IYEK # [Not derivable] 0951..0952 ; Cantillation_Mark # Mn [2] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI STRESS SIGN ANUDATTA +0AFA..0AFC ; Cantillation_Mark # Mn [3] GUJARATI SIGN SUKUN..GUJARATI SIGN MADDAH 1CD0..1CD2 ; Cantillation_Mark # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA 1CD4..1CE0 ; Cantillation_Mark # Mn [13] VEDIC SIGN YAJURVEDIC MIDLINE SVARITA..VEDIC TONE RIGVEDIC KASHMIRI INDEPENDENT SVARITA 1CE1 ; Cantillation_Mark # Mc VEDIC TONE ATHARVAVEDIC INDEPENDENT SVARITA 1CF4 ; Cantillation_Mark # Mn VEDIC TONE CANDRA ABOVE +1CF7 ; Cantillation_Mark # Mc VEDIC SIGN ATIKRAMA 1CF8..1CF9 ; Cantillation_Mark # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE A8E0..A8F1 ; Cantillation_Mark # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA 1123E ; Cantillation_Mark # Mn KHOJKI SIGN SUKUN @@ -1041,12 +1102,13 @@ A8E0..A8F1 ; Cantillation_Mark # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..CO 17D3 ; Syllable_Modifier # Mn KHMER SIGN BATHAMASAT 17DD ; Syllable_Modifier # Mn KHMER SIGN ATTHACAN 193B ; Syllable_Modifier # Mn LIMBU SIGN SA-I -1A7A..1A7C ; Syllable_Modifier # Mn [3] TAI THAM SIGN RA HAAM..TAI THAM SIGN KHUEN-LUE KARAN +1A7B..1A7C ; Syllable_Modifier # Mn [2] TAI THAM SIGN MAI SAM..TAI THAM SIGN KHUEN-LUE KARAN 1A7F ; Syllable_Modifier # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT 1C36 ; Syllable_Modifier # Mn LEPCHA SIGN RAN 1DFB ; Syllable_Modifier # Mn COMBINING DELETION MARK 2074 ; Syllable_Modifier # No SUPERSCRIPT FOUR 2082..2084 ; Syllable_Modifier # No [3] SUBSCRIPT TWO..SUBSCRIPT FOUR +11A33 ; Syllable_Modifier # Mn ZANABAZAR SQUARE FINAL CONSONANT MARK # ================================================ @@ -1095,6 +1157,10 @@ A8E0..A8F1 ; Cantillation_Mark # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..CO # Indic_Syllabic_Category=Number # Number (can be used as vowel-holders like consonant placeholders) +# Note: A number may even hold subjoined consonants which may in turn +# have been formed using a virama or a stacker, e.g. the sequence +# <U+1A93, U+1A60, U+1A34> where THAI THAM LETTER LOW TA is subjoined to +# TAI THAM THAM DIGIT THREE using an invisible stacker. # [Not derivable] @@ -1143,6 +1209,7 @@ ABF0..ABF9 ; Number # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NI 1173A..1173B ; Number # No [2] AHOM NUMBER TEN..AHOM NUMBER TWENTY 11C50..11C59 ; Number # Nd [10] BHAIKSUKI DIGIT ZERO..BHAIKSUKI DIGIT NINE 11C5A..11C6C ; Number # No [19] BHAIKSUKI NUMBER ONE..BHAIKSUKI HUNDREDS UNIT MARK +11D50..11D59 ; Number # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE # ================================================ diff --git a/lib/unicore/Jamo.txt b/lib/unicore/Jamo.txt index 13111e1001..f2b5ecb5ca 100644 --- a/lib/unicore/Jamo.txt +++ b/lib/unicore/Jamo.txt @@ -1,6 +1,6 @@ -# Jamo-9.0.0.txt -# Date: 2016-01-21, 22:00:00 GMT [KW, LI] -# © 2016 Unicode®, Inc. +# Jamo-10.0.0.txt +# Date: 2017-02-15, 00:00:00 GMT [KW, LI] +# © 2017 Unicode®, Inc. # For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database @@ -8,7 +8,7 @@ # # This file defines the Jamo_Short_Name property. # -# See Section 3.12 of The Unicode Standard, Version 9.0 +# See Section 3.12 of The Unicode Standard, Version 10.0 # for more information. # # Each line contains two fields, separated by a semicolon. diff --git a/lib/unicore/LineBreak.txt b/lib/unicore/LineBreak.txt index 5f09ad728b..d80210bde3 100644 --- a/lib/unicore/LineBreak.txt +++ b/lib/unicore/LineBreak.txt @@ -1,6 +1,6 @@ -# LineBreak-9.0.0.txt -# Date: 2016-05-26, 01:00:00 GMT [KW, LI] -# © 2016 Unicode®, Inc. +# LineBreak-10.0.0.txt +# Date: 2017-03-08, 02:00:00 GMT [KW, LI] +# © 2017 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html # @@ -273,6 +273,7 @@ 0840..0858;AL # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 0859..085B;CM # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK 085E;AL # Po MANDAIC PUNCTUATION +0860..086A;AL # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 08A0..08B4;AL # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW 08B6..08BD;AL # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON 08D4..08E1;CM # Mn [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA @@ -327,6 +328,8 @@ 09F9;PO # No BENGALI CURRENCY DENOMINATOR SIXTEEN 09FA;AL # So BENGALI ISSHAR 09FB;PR # Sc BENGALI GANDA MARK +09FC;AL # Lo BENGALI LETTER VEDIC ANUSVARA +09FD;AL # Po BENGALI ABBREVIATION SIGN 0A01..0A02;CM # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI 0A03;CM # Mc GURMUKHI SIGN VISARGA 0A05..0A0A;AL # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU @@ -371,6 +374,7 @@ 0AF0;AL # Po GUJARATI ABBREVIATION SIGN 0AF1;PR # Sc GUJARATI RUPEE SIGN 0AF9;AL # Lo GUJARATI LETTER ZHA +0AFA..0AFF;CM # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE 0B01;CM # Mn ORIYA SIGN CANDRABINDU 0B02..0B03;CM # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA 0B05..0B0C;AL # Lo [8] ORIYA LETTER A..ORIYA LETTER VOCALIC L @@ -462,11 +466,12 @@ 0CE2..0CE3;CM # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL 0CE6..0CEF;NU # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE 0CF1..0CF2;AL # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA -0D01;CM # Mn MALAYALAM SIGN CANDRABINDU +0D00..0D01;CM # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU 0D02..0D03;CM # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA 0D05..0D0C;AL # Lo [8] MALAYALAM LETTER A..MALAYALAM LETTER VOCALIC L 0D0E..0D10;AL # Lo [3] MALAYALAM LETTER E..MALAYALAM LETTER AI 0D12..0D3A;AL # Lo [41] MALAYALAM LETTER O..MALAYALAM LETTER TTTA +0D3B..0D3C;CM # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA 0D3D;AL # Lo MALAYALAM SIGN AVAGRAHA 0D3E..0D40;CM # Mc [3] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN II 0D41..0D44;CM # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR @@ -824,6 +829,7 @@ 1CF2..1CF3;CM # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA 1CF4;CM # Mn VEDIC TONE CANDRA ABOVE 1CF5..1CF6;AL # Lo [2] VEDIC SIGN JIHVAMULIYA..VEDIC SIGN UPADHMANIYA +1CF7;CM # Mc VEDIC SIGN ATIKRAMA 1CF8..1CF9;CM # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE 1D00..1D2B;AL # Ll [44] LATIN LETTER SMALL CAPITAL A..CYRILLIC LETTER SMALL CAPITAL EL 1D2C..1D6A;AL # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI @@ -832,7 +838,7 @@ 1D79..1D7F;AL # Ll [7] LATIN SMALL LETTER INSULAR G..LATIN SMALL LETTER UPSILON WITH STROKE 1D80..1D9A;AL # Ll [27] LATIN SMALL LETTER B WITH PALATAL HOOK..LATIN SMALL LETTER EZH WITH RETROFLEX HOOK 1D9B..1DBF;AL # Lm [37] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL THETA -1DC0..1DF5;CM # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE +1DC0..1DF9;CM # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW 1DFB..1DFF;CM # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 1E00..1EFF;AL # L& [256] LATIN CAPITAL LETTER A WITH RING BELOW..LATIN SMALL LETTER Y WITH LOOP 1F00..1F15;AL # L& [22] GREEK SMALL LETTER ALPHA WITH PSILI..GREEK SMALL LETTER EPSILON WITH DASIA AND OXIA @@ -940,7 +946,8 @@ 20BB;PO # Sc NORDIC MARK SIGN 20BC..20BD;PR # Sc [2] MANAT SIGN..RUBLE SIGN 20BE;PO # Sc LARI SIGN -20BF..20CF;PR # Cn [17] <reserved-20BF>..<reserved-20CF> +20BF;PR # Sc BITCOIN SIGN +20C0..20CF;PR # Cn [16] <reserved-20C0>..<reserved-20CF> 20D0..20DC;CM # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE 20DD..20E0;CM # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH 20E1;CM # Mn COMBINING LEFT RIGHT ARROW ABOVE @@ -1103,7 +1110,7 @@ 23DC..23E1;AL # Sm [6] TOP PARENTHESIS..BOTTOM TORTOISE SHELL BRACKET 23E2..23EF;AL # So [14] WHITE TRAPEZIUM..BLACK RIGHT-POINTING TRIANGLE WITH DOUBLE VERTICAL BAR 23F0..23F3;ID # So [4] ALARM CLOCK..HOURGLASS WITH FLOWING SAND -23F4..23FE;AL # So [11] BLACK MEDIUM LEFT-POINTING TRIANGLE..POWER SLEEP SYMBOL +23F4..23FF;AL # So [12] BLACK MEDIUM LEFT-POINTING TRIANGLE..OBSERVER EYE SYMBOL 2400..2426;AL # So [39] SYMBOL FOR NULL..SYMBOL FOR SUBSTITUTE FORM TWO 2440..244A;AL # So [11] OCR HOOK..OCR DOUBLE BACKSLASH 2460..249B;AI # No [60] CIRCLED DIGIT ONE..NUMBER TWENTY FULL STOP @@ -1295,7 +1302,7 @@ 2B76..2B95;AL # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW 2B98..2BB9;AL # So [34] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..UP ARROWHEAD IN A RECTANGLE BOX 2BBD..2BC8;AL # So [12] BALLOT BOX WITH LIGHT X..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED -2BCA..2BD1;AL # So [8] TOP HALF BLACK CIRCLE..UNCERTAINTY SIGN +2BCA..2BD2;AL # So [9] TOP HALF BLACK CIRCLE..GROUP MARK 2BEC..2BEF;AL # So [4] LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS..DOWNWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS 2C00..2C2E;AL # Lu [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE 2C30..2C5E;AL # Ll [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE @@ -1373,7 +1380,7 @@ 2E40;BA # Pd DOUBLE HYPHEN 2E41;BA # Po REVERSED COMMA 2E42;OP # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK -2E43..2E44;BA # Po [2] DASH WITH LEFT UPTURN..DOUBLE SUSPENSION MARK +2E43..2E49;BA # Po [7] DASH WITH LEFT UPTURN..DOUBLE STACKED COMMA 2E80..2E99;ID # So [26] CJK RADICAL REPEAT..CJK RADICAL RAP 2E9B..2EF3;ID # So [89] CJK RADICAL CHOKE..CJK RADICAL C-SIMPLIFIED TURTLE 2F00..2FD5;ID # So [214] KANGXI RADICAL ONE..KANGXI RADICAL FLUTE @@ -1472,7 +1479,7 @@ 30FC;CJ # Lm KATAKANA-HIRAGANA PROLONGED SOUND MARK 30FD..30FE;NS # Lm [2] KATAKANA ITERATION MARK..KATAKANA VOICED ITERATION MARK 30FF;ID # Lo KATAKANA DIGRAPH KOTO -3105..312D;ID # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH +3105..312E;ID # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE 3131..318E;ID # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE 3190..3191;ID # So [2] IDEOGRAPHIC ANNOTATION LINKING MARK..IDEOGRAPHIC ANNOTATION REVERSE MARK 3192..3195;ID # No [4] IDEOGRAPHIC ANNOTATION ONE MARK..IDEOGRAPHIC ANNOTATION FOUR MARK @@ -1495,8 +1502,8 @@ 3400..4DB5;ID # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 4DB6..4DBF;ID # Cn [10] <reserved-4DB6>..<reserved-4DBF> 4DC0..4DFF;AL # So [64] HEXAGRAM FOR THE CREATIVE HEAVEN..HEXAGRAM FOR BEFORE COMPLETION -4E00..9FD5;ID # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5 -9FD6..9FFF;ID # Cn [42] <reserved-9FD6>..<reserved-9FFF> +4E00..9FEA;ID # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA +9FEB..9FFF;ID # Cn [21] <reserved-9FEB>..<reserved-9FFF> A000..A014;ID # Lo [21] YI SYLLABLE IT..YI SYLLABLE E A015;NS # Lm YI SYLLABLE WU A016..A48C;ID # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR @@ -2640,6 +2647,7 @@ FFFD;AI # So REPLACEMENT CHARACTER 102E1..102FB;AL # No [27] COPTIC EPACT DIGIT ONE..COPTIC EPACT NUMBER NINE HUNDRED 10300..1031F;AL # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS 10320..10323;AL # No [4] OLD ITALIC NUMERAL ONE..OLD ITALIC NUMERAL FIFTY +1032D..1032F;AL # Lo [3] OLD ITALIC LETTER YE..OLD ITALIC LETTER SOUTHERN TSE 10330..10340;AL # Lo [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA 10341;AL # Nl GOTHIC LETTER NINETY 10342..10349;AL # Lo [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL @@ -2903,6 +2911,33 @@ FFFD;AI # So REPLACEMENT CHARACTER 118E0..118E9;NU # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE 118EA..118F2;AL # No [9] WARANG CITI NUMBER TEN..WARANG CITI NUMBER NINETY 118FF;AL # Lo WARANG CITI OM +11A00;AL # Lo ZANABAZAR SQUARE LETTER A +11A01..11A06;CM # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O +11A07..11A08;CM # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU +11A09..11A0A;CM # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A0B..11A32;AL # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA +11A33..11A38;CM # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A39;CM # Mc ZANABAZAR SQUARE SIGN VISARGA +11A3A;AL # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA +11A3B..11A3E;CM # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A3F;BB # Po ZANABAZAR SQUARE INITIAL HEAD MARK +11A40;AL # Po ZANABAZAR SQUARE CLOSING HEAD MARK +11A41..11A44;BA # Po [4] ZANABAZAR SQUARE MARK TSHEG..ZANABAZAR SQUARE MARK LONG TSHEG +11A45;BB # Po ZANABAZAR SQUARE INITIAL DOUBLE-LINED HEAD MARK +11A46;AL # Po ZANABAZAR SQUARE CLOSING DOUBLE-LINED HEAD MARK +11A47;CM # Mn ZANABAZAR SQUARE SUBJOINER +11A50;AL # Lo SOYOMBO LETTER A +11A51..11A56;CM # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A57..11A58;CM # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU +11A59..11A5B;CM # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A5C..11A83;AL # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA +11A86..11A89;AL # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA +11A8A..11A96;CM # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A97;CM # Mc SOYOMBO SIGN VISARGA +11A98..11A99;CM # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER +11A9A..11A9C;BA # Po [3] SOYOMBO MARK TSHEG..SOYOMBO MARK DOUBLE SHAD +11A9E..11AA0;BB # Po [3] SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME..SOYOMBO HEAD MARK WITH MOON AND SUN +11AA1..11AA2;BA # Po [2] SOYOMBO TERMINAL MARK-1..SOYOMBO TERMINAL MARK-2 11AC0..11AF8;AL # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL 11C00..11C08;AL # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E;AL # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA @@ -2925,6 +2960,16 @@ FFFD;AI # So REPLACEMENT CHARACTER 11CB2..11CB3;CM # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E 11CB4;CM # Mc MARCHEN VOWEL SIGN O 11CB5..11CB6;CM # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D00..11D06;AL # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E +11D08..11D09;AL # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O +11D0B..11D30;AL # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA +11D31..11D36;CM # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A;CM # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D;CM # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45;CM # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D46;AL # Lo MASARAM GONDI REPHA +11D47;CM # Mn MASARAM GONDI RA-KARA +11D50..11D59;NU # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE 12000..12399;AL # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E;AL # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12470..12474;BA # Po [5] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON @@ -2971,10 +3016,12 @@ FFFD;AI # So REPLACEMENT CHARACTER 16F51..16F7E;CM # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG 16F8F..16F92;CM # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW 16F93..16F9F;AL # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 -16FE0;NS # Lm TANGUT ITERATION MARK +16FE0..16FE1;NS # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK 17000..187EC;ID # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC 18800..18AF2;ID # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755 -1B000..1B001;ID # Lo [2] KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE +1B000..1B0FF;ID # Lo [256] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER RE-2 +1B100..1B11E;ID # Lo [31] HENTAIGANA LETTER RE-3..HENTAIGANA LETTER N-MU-MO-2 +1B170..1B2FB;ID # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 1BC00..1BC6A;AL # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M 1BC70..1BC7C;AL # Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK 1BC80..1BC88;AL # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL @@ -3132,7 +3179,9 @@ FFFD;AI # So REPLACEMENT CHARACTER 1F240..1F248;ID # So [9] TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C..TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557 1F249..1F24F;ID # Cn [7] <reserved-1F249>..<reserved-1F24F> 1F250..1F251;ID # So [2] CIRCLED IDEOGRAPH ADVANTAGE..CIRCLED IDEOGRAPH ACCEPT -1F252..1F2FF;ID # Cn [174] <reserved-1F252>..<reserved-1F2FF> +1F252..1F25F;ID # Cn [14] <reserved-1F252>..<reserved-1F25F> +1F260..1F265;ID # So [6] ROUNDED SYMBOL FOR FU..ROUNDED SYMBOL FOR CAI +1F266..1F2FF;ID # Cn [154] <reserved-1F266>..<reserved-1F2FF> 1F300..1F384;ID # So [133] CYCLONE..CHRISTMAS TREE 1F385;EB # So FATHER CHRISTMAS 1F386..1F39B;ID # So [22] FIREWORKS..CONTROL KNOBS @@ -3141,11 +3190,13 @@ FFFD;AI # So REPLACEMENT CHARACTER 1F3B5..1F3B6;AL # So [2] MUSICAL NOTE..MULTIPLE MUSICAL NOTES 1F3B7..1F3BB;ID # So [5] SAXOPHONE..VIOLIN 1F3BC;AL # So MUSICAL SCORE -1F3BD..1F3C2;ID # So [6] RUNNING SHIRT WITH SASH..SNOWBOARDER -1F3C3..1F3C4;EB # So [2] RUNNER..SURFER -1F3C5..1F3C9;ID # So [5] SPORTS MEDAL..RUGBY FOOTBALL -1F3CA..1F3CB;EB # So [2] SWIMMER..WEIGHT LIFTER -1F3CC..1F3FA;ID # So [47] GOLFER..AMPHORA +1F3BD..1F3C1;ID # So [5] RUNNING SHIRT WITH SASH..CHEQUERED FLAG +1F3C2..1F3C4;EB # So [3] SNOWBOARDER..SURFER +1F3C5..1F3C6;ID # So [2] SPORTS MEDAL..TROPHY +1F3C7;EB # So HORSE RACING +1F3C8..1F3C9;ID # So [2] AMERICAN FOOTBALL..RUGBY FOOTBALL +1F3CA..1F3CC;EB # So [3] SWIMMER..GOLFER +1F3CD..1F3FA;ID # So [46] RACING MOTORCYCLE..AMPHORA 1F3FB..1F3FF;EM # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6 1F400..1F441;ID # So [66] RAT..EYE 1F442..1F443;EB # So [2] EAR..NOSE @@ -3181,8 +3232,8 @@ FFFD;AI # So REPLACEMENT CHARACTER 1F517..1F524;AL # So [14] LINK SYMBOL..INPUT SYMBOL FOR LATIN LETTERS 1F525..1F531;ID # So [13] FIRE..TRIDENT EMBLEM 1F532..1F549;AL # So [24] BLACK SQUARE BUTTON..OM SYMBOL -1F54A..1F574;ID # So [43] DOVE OF PEACE..MAN IN BUSINESS SUIT LEVITATING -1F575;EB # So SLEUTH OR SPY +1F54A..1F573;ID # So [42] DOVE OF PEACE..HOLE +1F574..1F575;EB # So [2] MAN IN BUSINESS SUIT LEVITATING..SLEUTH OR SPY 1F576..1F579;ID # So [4] DARK SUNGLASSES..JOYSTICK 1F57A;EB # So MAN DANCING 1F57B..1F58F;ID # So [21] LEFT HAND TELEPHONE RECEIVER..TURNED OK HAND SIGN @@ -3208,12 +3259,14 @@ FFFD;AI # So REPLACEMENT CHARACTER 1F6B4..1F6B6;EB # So [3] BICYCLIST..PEDESTRIAN 1F6B7..1F6BF;ID # So [9] NO PEDESTRIANS..SHOWER 1F6C0;EB # So BATH -1F6C1..1F6D2;ID # So [18] BATHTUB..SHOPPING TROLLEY -1F6D3..1F6DF;ID # Cn [13] <reserved-1F6D3>..<reserved-1F6DF> +1F6C1..1F6CB;ID # So [11] BATHTUB..COUCH AND LAMP +1F6CC;EB # So SLEEPING ACCOMMODATION +1F6CD..1F6D4;ID # So [8] SHOPPING BAGS..PAGODA +1F6D5..1F6DF;ID # Cn [11] <reserved-1F6D5>..<reserved-1F6DF> 1F6E0..1F6EC;ID # So [13] HAMMER AND WRENCH..AIRPLANE ARRIVING 1F6ED..1F6EF;ID # Cn [3] <reserved-1F6ED>..<reserved-1F6EF> -1F6F0..1F6F6;ID # So [7] SATELLITE..CANOE -1F6F7..1F6FF;ID # Cn [9] <reserved-1F6F7>..<reserved-1F6FF> +1F6F0..1F6F8;ID # So [9] SATELLITE..FLYING SAUCER +1F6F9..1F6FF;ID # Cn [7] <reserved-1F6F9>..<reserved-1F6FF> 1F700..1F773;AL # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE 1F774..1F77F;ID # Cn [12] <reserved-1F774>..<reserved-1F77F> 1F780..1F7D4;AL # So [85] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..HEAVY TWELVE POINTED PINWHEEL STAR @@ -3227,28 +3280,32 @@ FFFD;AI # So REPLACEMENT CHARACTER 1F860..1F887;AL # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW 1F888..1F88F;ID # Cn [8] <reserved-1F888>..<reserved-1F88F> 1F890..1F8AD;AL # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS -1F8AE..1F90F;ID # Cn [98] <reserved-1F8AE>..<reserved-1F90F> +1F8AE..1F8FF;ID # Cn [82] <reserved-1F8AE>..<reserved-1F8FF> +1F900..1F90B;AL # So [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT +1F90C..1F90F;ID # Cn [4] <reserved-1F90C>..<reserved-1F90F> 1F910..1F917;ID # So [8] ZIPPER-MOUTH FACE..HUGGING FACE -1F918..1F91E;EB # So [7] SIGN OF THE HORNS..HAND WITH INDEX AND MIDDLE FINGERS CROSSED -1F91F;ID # Cn <reserved-1F91F> +1F918..1F91C;EB # So [5] SIGN OF THE HORNS..RIGHT-FACING FIST +1F91D;ID # So HANDSHAKE +1F91E..1F91F;EB # So [2] HAND WITH INDEX AND MIDDLE FINGERS CROSSED..I LOVE YOU HAND SIGN 1F920..1F925;ID # So [6] FACE WITH COWBOY HAT..LYING FACE 1F926;EB # So FACE PALM -1F927;ID # So SNEEZING FACE -1F928..1F92F;ID # Cn [8] <reserved-1F928>..<reserved-1F92F> -1F930;EB # So PREGNANT WOMAN -1F931..1F932;ID # Cn [2] <reserved-1F931>..<reserved-1F932> -1F933..1F939;EB # So [7] SELFIE..JUGGLING -1F93A..1F93B;ID # So [2] FENCER..MODERN PENTATHLON -1F93C..1F93E;EB # So [3] WRESTLERS..HANDBALL +1F927..1F92F;ID # So [9] SNEEZING FACE..SHOCKED FACE WITH EXPLODING HEAD +1F930..1F939;EB # So [10] PREGNANT WOMAN..JUGGLING +1F93A..1F93C;ID # So [3] FENCER..WRESTLERS +1F93D..1F93E;EB # So [2] WATER POLO..HANDBALL 1F93F;ID # Cn <reserved-1F93F> -1F940..1F94B;ID # So [12] WILTED FLOWER..MARTIAL ARTS UNIFORM -1F94C..1F94F;ID # Cn [4] <reserved-1F94C>..<reserved-1F94F> -1F950..1F95E;ID # So [15] CROISSANT..PANCAKES -1F95F..1F97F;ID # Cn [33] <reserved-1F95F>..<reserved-1F97F> -1F980..1F991;ID # So [18] CRAB..SQUID -1F992..1F9BF;ID # Cn [46] <reserved-1F992>..<reserved-1F9BF> +1F940..1F94C;ID # So [13] WILTED FLOWER..CURLING STONE +1F94D..1F94F;ID # Cn [3] <reserved-1F94D>..<reserved-1F94F> +1F950..1F96B;ID # So [28] CROISSANT..CANNED FOOD +1F96C..1F97F;ID # Cn [20] <reserved-1F96C>..<reserved-1F97F> +1F980..1F997;ID # So [24] CRAB..CRICKET +1F998..1F9BF;ID # Cn [40] <reserved-1F998>..<reserved-1F9BF> 1F9C0;ID # So CHEESE WEDGE -1F9C1..1FFFD;ID # Cn [1597] <reserved-1F9C1>..<reserved-1FFFD> +1F9C1..1F9CF;ID # Cn [15] <reserved-1F9C1>..<reserved-1F9CF> +1F9D0;ID # So FACE WITH MONOCLE +1F9D1..1F9DD;EB # So [13] ADULT..ELF +1F9DE..1F9E6;ID # So [9] GENIE..SOCKS +1F9E7..1FFFD;ID # Cn [1559] <reserved-1F9E7>..<reserved-1FFFD> 20000..2A6D6;ID # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6 2A6D7..2A6FF;ID # Cn [41] <reserved-2A6D7>..<reserved-2A6FF> 2A700..2B734;ID # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 @@ -3256,7 +3313,9 @@ FFFD;AI # So REPLACEMENT CHARACTER 2B740..2B81D;ID # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B81E..2B81F;ID # Cn [2] <reserved-2B81E>..<reserved-2B81F> 2B820..2CEA1;ID # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 -2CEA2..2F7FF;ID # Cn [10590] <reserved-2CEA2>..<reserved-2F7FF> +2CEA2..2CEAF;ID # Cn [14] <reserved-2CEA2>..<reserved-2CEAF> +2CEB0..2EBE0;ID # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 +2EBE1..2F7FF;ID # Cn [3103] <reserved-2EBE1>..<reserved-2F7FF> 2F800..2FA1D;ID # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D 2FA1E..2FFFD;ID # Cn [1504] <reserved-2FA1E>..<reserved-2FFFD> 30000..3FFFD;ID # Cn [65534] <reserved-30000>..<reserved-3FFFD> diff --git a/lib/unicore/NameAliases.txt b/lib/unicore/NameAliases.txt index 4a2a15070a..f4ba3caee5 100644 --- a/lib/unicore/NameAliases.txt +++ b/lib/unicore/NameAliases.txt @@ -1,6 +1,6 @@ -# NameAliases-9.0.0.txt -# Date: 2016-01-21, 22:00:00 GMT [KW, LI] -# © 2016 Unicode®, Inc. +# NameAliases-10.0.0.txt +# Date: 2017-05-06, 18:10:00 GMT [KW, LI] +# © 2017 Unicode®, Inc. # For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database @@ -262,6 +262,10 @@ 0EA3;LAO LETTER RO;correction 0EA5;LAO LETTER LO;correction 0FD0;TIBETAN MARK BKA- SHOG GI MGO RGYAN;correction +11EC;HANGUL JONGSEONG YESIEUNG-KIYEOK;correction +11ED;HANGUL JONGSEONG YESIEUNG-SSANGKIYEOK;correction +11EE;HANGUL JONGSEONG SSANGYESIEUNG;correction +11EF;HANGUL JONGSEONG YESIEUNG-KHIEUKH;correction 180B;FVS1;abbreviation 180C;FVS2;abbreviation 180D;FVS3;abbreviation @@ -289,7 +293,6 @@ 2B7A;LEFTWARDS TRIANGLE-HEADED ARROW WITH DOUBLE VERTICAL STROKE;correction 2B7C;RIGHTWARDS TRIANGLE-HEADED ARROW WITH DOUBLE VERTICAL STROKE;correction A015;YI SYLLABLE ITERATION MARK;correction -FE18;PRESENTATION FORM FOR VERTICAL RIGHT WHITE LENTICULAR BRACKET;correction FE00;VS1;abbreviation FE01;VS2;abbreviation FE02;VS3;abbreviation @@ -306,11 +309,13 @@ FE0C;VS13;abbreviation FE0D;VS14;abbreviation FE0E;VS15;abbreviation FE0F;VS16;abbreviation +FE18;PRESENTATION FORM FOR VERTICAL RIGHT WHITE LENTICULAR BRACKET;correction FEFF;BYTE ORDER MARK;alternate FEFF;BOM;abbreviation FEFF;ZWNBSP;abbreviation 122D4;CUNEIFORM SIGN NU11 TENU;correction 122D5;CUNEIFORM SIGN NU11 OVER NU11 BUR OVER BUR;correction +1B001;HENTAIGANA LETTER E-1;correction 1D0C5;BYZANTINE MUSICAL SYMBOL FTHORA SKLIRON CHROMA VASIS;correction E0100;VS17;abbreviation E0101;VS18;abbreviation diff --git a/lib/unicore/NamedSequences.txt b/lib/unicore/NamedSequences.txt index 6213419c4a..a315b42f5d 100644 --- a/lib/unicore/NamedSequences.txt +++ b/lib/unicore/NamedSequences.txt @@ -1,6 +1,6 @@ -# NamedSequences-9.0.0.txt -# Date: 2016-05-26, 00:00:00 GMT [KW, LI] -# © 2016 Unicode®, Inc. +# NamedSequences-10.0.0.txt +# Date: 2017-04-13, 01:00:00 GMT [KW, LI] +# © 2017 Unicode®, Inc. # For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database @@ -37,6 +37,24 @@ # ================================================ +# Named keycap sequences for telephone keypad (used for emoji) +# Provisional, 2015-05-05 +# FE0F added to the sequences, 2016-05-11 +# Approved 2017-05-12 + +KEYCAP NUMBER SIGN;0023 FE0F 20E3 +KEYCAP ASTERISK;002A FE0F 20E3 +KEYCAP DIGIT ZERO;0030 FE0F 20E3 +KEYCAP DIGIT ONE;0031 FE0F 20E3 +KEYCAP DIGIT TWO;0032 FE0F 20E3 +KEYCAP DIGIT THREE;0033 FE0F 20E3 +KEYCAP DIGIT FOUR;0034 FE0F 20E3 +KEYCAP DIGIT FIVE;0035 FE0F 20E3 +KEYCAP DIGIT SIX;0036 FE0F 20E3 +KEYCAP DIGIT SEVEN;0037 FE0F 20E3 +KEYCAP DIGIT EIGHT;0038 FE0F 20E3 +KEYCAP DIGIT NINE;0039 FE0F 20E3 + # Latin letter plus accent combinations. # These are part of the original set of approved named sequences # for Unicode 4.1. 2005. @@ -523,7 +541,7 @@ KHMER VOWEL SIGN AAM;17B6 17C6 # Entries for JIS X 0213 compatibility mapping. # Provisional 2008-11-07, Approved 2010-05-14 -# +# # Two of these were part of the original set of approved named sequences # for Unicode 4.1. 2005. diff --git a/lib/unicore/NamedSqProv.txt b/lib/unicore/NamedSqProv.txt index e3cea4f742..707341773b 100644 --- a/lib/unicore/NamedSqProv.txt +++ b/lib/unicore/NamedSqProv.txt @@ -1,6 +1,6 @@ -# NamedSequencesProv-9.0.0.txt -# Date: 2016-05-26, 00:00:00 GMT [KW, LI] -# © 2016 Unicode®, Inc. +# NamedSequencesProv-10.0.0.txt +# Date: 2017-04-13, 01:00:00 GMT [KW, LI] +# © 2017 Unicode®, Inc. # For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database @@ -26,7 +26,7 @@ # in this data file, would correspond to an ISO/IEC 10646 USI # as follows: # -# <1000, 1001, 1002> +# <1000, 1001, 1002> # # For more information, see UAX #34: Unicode Named Character # Sequences, at http://www.unicode.org/unicode/reports/tr34/ @@ -40,22 +40,7 @@ # Provisional entries for NamedSequences.txt. -# Named keycap sequences for telephone keypad (used for emoji) -# Added to provisional named sequences, 2015-05-05 -# FE0F added to the sequences, 2016-05-11 - -KEYCAP NUMBER SIGN;0023 FE0F 20E3 -KEYCAP ASTERISK;002A FE0F 20E3 -KEYCAP DIGIT ZERO;0030 FE0F 20E3 -KEYCAP DIGIT ONE;0031 FE0F 20E3 -KEYCAP DIGIT TWO;0032 FE0F 20E3 -KEYCAP DIGIT THREE;0033 FE0F 20E3 -KEYCAP DIGIT FOUR;0034 FE0F 20E3 -KEYCAP DIGIT FIVE;0035 FE0F 20E3 -KEYCAP DIGIT SIX;0036 FE0F 20E3 -KEYCAP DIGIT SEVEN;0037 FE0F 20E3 -KEYCAP DIGIT EIGHT;0038 FE0F 20E3 -KEYCAP DIGIT NINE;0039 FE0F 20E3 +# Currently there are no provisional entries. # ================================================ @@ -67,7 +52,7 @@ KEYCAP DIGIT NINE;0039 FE0F 20E3 # GURMUKHI PARI YA;0A4D 0A2F # Entry removed 2006-05-18: -# +# # LATIN SMALL LETTER A WITH ACUTE AND OGONEK;00E1 0328 # # This entry was removed because the sequence was not in NFC, diff --git a/lib/unicore/NamesList.txt b/lib/unicore/NamesList.txt index ef838ee49f..ebfd939190 100644 --- a/lib/unicore/NamesList.txt +++ b/lib/unicore/NamesList.txt @@ -1,14 +1,14 @@ ; charset=UTF-8 -@@@ The Unicode Standard 9.0.0 -@@@+ U90M160615.lst - Unicode 9.0.0 final names list. +@@@ The Unicode Standard 10.0.0 +@@@+ U10M170525.lst + Unicode 10.0.0 final names list. This file is semi-automatically derived from UnicodeData.txt and a set of manually created annotations using a script to select or suppress information from the data file. The rules used for this process are aimed at readability for the human reader, at the expense of some details; therefore, this file should not be parsed for machine-readable information. -@+ © 2016 Unicode®, Inc. +@+ © 2017 Unicode®, Inc. For terms of use, see http://www.unicode.org/terms_of_use.html @@ 0000 C0 Controls and Basic Latin (Basic Latin) 007F @@+ @@ -121,8 +121,6 @@ x (l b bar symbol - 2114) x (viewdata square - 2317) x (music sharp sign - 266F) - ~ 0023 FE0E text style - ~ 0023 FE0F emoji style 0024 DOLLAR SIGN = milréis, escudo * used for many peso currencies in Latin America and elsewhere @@ -166,8 +164,6 @@ x (asterisk operator - 2217) x (sextile - 26B9) x (heavy asterisk - 2731) - ~ 002A FE0E text style - ~ 002A FE0F emoji style 002B PLUS SIGN x (heavy plus sign - 2795) 002C COMMA @@ -201,35 +197,15 @@ @ ASCII digits 0030 DIGIT ZERO ~ 0030 FE00 short diagonal stroke form - ~ 0030 FE0E text style - ~ 0030 FE0F emoji style 0031 DIGIT ONE - ~ 0031 FE0E text style - ~ 0031 FE0F emoji style 0032 DIGIT TWO - ~ 0032 FE0E text style - ~ 0032 FE0F emoji style 0033 DIGIT THREE - ~ 0033 FE0E text style - ~ 0033 FE0F emoji style 0034 DIGIT FOUR - ~ 0034 FE0E text style - ~ 0034 FE0F emoji style 0035 DIGIT FIVE - ~ 0035 FE0E text style - ~ 0035 FE0F emoji style 0036 DIGIT SIX - ~ 0036 FE0E text style - ~ 0036 FE0F emoji style 0037 DIGIT SEVEN - ~ 0037 FE0E text style - ~ 0037 FE0F emoji style 0038 DIGIT EIGHT - ~ 0038 FE0E text style - ~ 0038 FE0F emoji style 0039 DIGIT NINE - ~ 0039 FE0E text style - ~ 0039 FE0F emoji style @ ASCII punctuation and symbols 003A COLON * also used to denote division or scale; for that mathematical use 2236 is preferred @@ -506,7 +482,7 @@ x (turkish lira sign - 20BA) x (roman semuncia sign - 10192) 00A4 CURRENCY SIGN - * other currency symbol characters: 20A0-20BA + * other currency symbol characters: 20A0-20BF x (dollar sign - 0024) 00A5 YEN SIGN = yuan sign @@ -523,8 +499,6 @@ 00A9 COPYRIGHT SIGN x (sound recording copyright - 2117) x (circled latin capital letter c - 24B8) - ~ 00A9 FE0E text style - ~ 00A9 FE0F emoji style 00AA FEMININE ORDINAL INDICATOR * Spanish # <super> 0061 @@ -543,8 +517,6 @@ 00AE REGISTERED SIGN = registered trade mark sign (1.0) x (circled latin capital letter r - 24C7) - ~ 00AE FE0E text style - ~ 00AE FE0F emoji style 00AF MACRON = overline, APL overbar * this is a spacing character @@ -800,7 +772,6 @@ * French, medieval Hungarian orthography * uppercase is 0178 : 0079 0308 -@~ ! @@ 0100 Latin Extended-A 017F @ European Latin 0100 LATIN CAPITAL LETTER A WITH MACRON @@ -1832,6 +1803,7 @@ * semi-high front unrounded vowel * preferred IPA alternate for 0269 * uppercase is A7AE + * glyph should have top and bottom serifs even in sans serif IPA font designs, to avoid confusion with lowercase l 026B LATIN SMALL LETTER L WITH MIDDLE TILDE * velarized voiced alveolar lateral approximant * uppercase is 2C62 @@ -2292,6 +2264,7 @@ 02F1 MODIFIER LETTER LOW LEFT ARROWHEAD 02F2 MODIFIER LETTER LOW RIGHT ARROWHEAD 02F3 MODIFIER LETTER LOW RING + x (combining ring below - 0325) 02F4 MODIFIER LETTER MIDDLE GRAVE ACCENT 02F5 MODIFIER LETTER MIDDLE DOUBLE GRAVE ACCENT 02F6 MODIFIER LETTER MIDDLE DOUBLE ACUTE ACCENT @@ -2441,6 +2414,7 @@ * IPA: voiceless * vocalic (in Latin transliteration of Indic sonorants) * Madurese + x (modifier letter low ring - 02F3) 0326 COMBINING COMMA BELOW * Romanian, Latvian, Livonian 0327 COMBINING CEDILLA @@ -2498,8 +2472,13 @@ @ Additions 0339 COMBINING RIGHT HALF RING BELOW 033A COMBINING INVERTED BRIDGE BELOW + * IPA: apical + x (combining wide inverted bridge below - 1DF9) 033B COMBINING SQUARE BELOW + * IPA: laminal + * preferred glyph shape is a horizontal rectangle for IPA usage 033C COMBINING SEAGULL BELOW + * IPA: linguolabial 033D COMBINING X ABOVE 033E COMBINING VERTICAL TILDE = yerik @@ -2570,12 +2549,13 @@ @ Miscellaneous additions 0358 COMBINING DOT ABOVE RIGHT * Latin transliterations of the Southern Min dialects of Chinese + x (combining dot above left - 1DF8) 0359 COMBINING ASTERISK BELOW x (low asterisk - 204E) 035A COMBINING DOUBLE RING BELOW * Kharoshthi transliteration 035B COMBINING ZIGZAG ABOVE - * Latin abbreviation, Lithuanian phonetics and mediaevalist transcriptions + * Latin abbreviation, Lithuanian phonetics and medievalist transcriptions @ Double diacritics 035C COMBINING DOUBLE BREVE BELOW = ligature tie below, papyrological hyphen @@ -4484,10 +4464,13 @@ 07EF NKO COMBINING LONG HIGH TONE 07F0 NKO COMBINING LONG LOW TONE 07F1 NKO COMBINING LONG RISING TONE +@ Other diacritics 07F2 NKO COMBINING NASALIZATION MARK x (combining dot below - 0323) 07F3 NKO COMBINING DOUBLE DOT ABOVE x (combining diaeresis - 0308) +@ Tonal apostrophes +@+ These apostrophes mark elision of a vowel while preserving the tonal information of the syllable. 07F4 NKO HIGH TONE APOSTROPHE x (modifier letter apostrophe - 02BC) 07F5 NKO LOW TONE APOSTROPHE @@ -4626,6 +4609,31 @@ 085B MANDAIC GEMINATION MARK @ Punctuation 085E MANDAIC PUNCTUATION +@@ 0860 Syriac Supplement 086F +@ Syriac letters +@+ Used for writing Suriyani Malayalam, which is also known as Garshuni (Karshoni) and Syriac Malayalam. +0860 SYRIAC LETTER MALAYALAM NGA + x (malayalam letter nga - 0D19) +0861 SYRIAC LETTER MALAYALAM JA + x (malayalam letter ja - 0D1C) +0862 SYRIAC LETTER MALAYALAM NYA + x (malayalam letter nya - 0D1E) +0863 SYRIAC LETTER MALAYALAM TTA + x (malayalam letter tta - 0D1F) +0864 SYRIAC LETTER MALAYALAM NNA + x (malayalam letter nna - 0D23) +0865 SYRIAC LETTER MALAYALAM NNNA + x (malayalam letter nnna - 0D29) +0866 SYRIAC LETTER MALAYALAM BHA + x (malayalam letter bha - 0D2D) +0867 SYRIAC LETTER MALAYALAM RA + x (malayalam letter ra - 0D30) +0868 SYRIAC LETTER MALAYALAM LLA + x (malayalam letter lla - 0D33) +0869 SYRIAC LETTER MALAYALAM LLLA + x (malayalam letter llla - 0D34) +086A SYRIAC LETTER MALAYALAM SSA + x (malayalam letter ssa - 0D37) @@ 08A0 Arabic Extended-A 08FF @ Arabic letters for African languages 08A0 ARABIC LETTER BEH WITH SMALL V BELOW @@ -5107,6 +5115,9 @@ * written before the name of a deceased person @ Historic currency sign 09FB BENGALI GANDA MARK +@ Signs +09FC BENGALI LETTER VEDIC ANUSVARA +09FD BENGALI ABBREVIATION SIGN @@ 0A00 Gurmukhi 0A7F @ Various signs 0A01 GURMUKHI SIGN ADAK BINDI @@ -5227,6 +5238,7 @@ 0A74 GURMUKHI EK ONKAR * God is One 0A75 GURMUKHI SIGN YAKASH + * some fonts use an alternate glyph shaped more like the lower part of 0A2F @@ 0A80 Gujarati 0AFF @ Various signs 0A81 GUJARATI SIGN CANDRABINDU @@ -5337,6 +5349,14 @@ 0AF9 GUJARATI LETTER ZHA * used in transliteration of Avestan x (devanagari letter zha - 0979) +@ Transliteration signs +@+ Used for the transliteration of the Arabic script into Gujarati by Ismaili Khoja communities. +0AFA GUJARATI SIGN SUKUN +0AFB GUJARATI SIGN SHADDA +0AFC GUJARATI SIGN MADDAH +0AFD GUJARATI SIGN THREE-DOT NUKTA ABOVE +0AFE GUJARATI SIGN CIRCLE NUKTA ABOVE +0AFF GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE @@ 0B00 Oriya 0B7F @+ As of 2012, the name "Oriya" for this script and language is officially spelled "Odia" in India. That change in spelling does not affect the Unicode block or character names, which are constrained by stability guarantees. @ Various signs @@ -5836,6 +5856,7 @@ x (vedic sign upadhmaniya - 1CF6) @@ 0D00 Malayalam 0D7F @ Various signs +0D00 MALAYALAM SIGN COMBINING ANUSVARA ABOVE 0D01 MALAYALAM SIGN CANDRABINDU 0D02 MALAYALAM SIGN ANUSVARA * used in Prakrit language texts to indicate gemination of the following consonant @@ -5913,6 +5934,9 @@ 0D39 MALAYALAM LETTER HA 0D3A MALAYALAM LETTER TTTA * historic use only +@ Variant shape viramas +0D3B MALAYALAM SIGN VERTICAL BAR VIRAMA +0D3C MALAYALAM SIGN CIRCULAR VIRAMA @ Addition for Sanskrit 0D3D MALAYALAM SIGN AVAGRAHA = praslesham @@ -5954,7 +5978,7 @@ 0D54 MALAYALAM LETTER CHILLU M 0D55 MALAYALAM LETTER CHILLU Y 0D56 MALAYALAM LETTER CHILLU LLL -@ Various signs +@ Dependent vowel sign 0D57 MALAYALAM AU LENGTH MARK * used alone to write the /au/ dependent vowel in modern texts x (malayalam vowel sign au - 0D4C) @@ -7479,13 +7503,13 @@ 11EA HANGUL JONGSEONG SIOS-PIEUP 11EB HANGUL JONGSEONG PANSIOS 11EC HANGUL JONGSEONG IEUNG-KIYEOK - = yesieung-kiyeok + % HANGUL JONGSEONG YESIEUNG-KIYEOK 11ED HANGUL JONGSEONG IEUNG-SSANGKIYEOK - = yesieung-ssangkiyeok + % HANGUL JONGSEONG YESIEUNG-SSANGKIYEOK 11EE HANGUL JONGSEONG SSANGIEUNG - = ssangyesieung + % HANGUL JONGSEONG SSANGYESIEUNG 11EF HANGUL JONGSEONG IEUNG-KHIEUKH - = yesieung-khieukh + % HANGUL JONGSEONG YESIEUNG-KHIEUKH 11F0 HANGUL JONGSEONG YESIEUNG 11F1 HANGUL JONGSEONG YESIEUNG-SIOS 11F2 HANGUL JONGSEONG YESIEUNG-PANSIOS @@ -9230,9 +9254,11 @@ * not a format control character, but simply a hyphen for Todo x (soft hyphen - 00AD) 1807 MONGOLIAN SIBE SYLLABLE BOUNDARY MARKER + ~ 1807 ALT1 first form (medial) 1808 MONGOLIAN MANCHU COMMA 1809 MONGOLIAN MANCHU FULL STOP 180A MONGOLIAN NIRUGU + ~ 180A ALT1 first form (medial) @ Format controls 180B MONGOLIAN FREE VARIATION SELECTOR ONE * abbreviated FVS1 @@ -9310,6 +9336,9 @@ ~ 1826 180B second form (final) ~ 1826 180C third form (medial) 1827 MONGOLIAN LETTER EE + ~ 1827 ALT1 first form (initial) + ~ 1827 ALT1 first form (medial) + ~ 1827 ALT1 first form (final) 1828 MONGOLIAN LETTER NA x (cyrillic small letter en - 043D) ~ 1828 ALT1 first form (initial) @@ -9318,24 +9347,30 @@ ~ 1828 180B second form (initial) ~ 1828 180B second form (medial) ~ 1828 180C third form (medial) - ~ 1828 180D separate form (medial) + ~ 1828 180D fourth form (medial) 1829 MONGOLIAN LETTER ANG + ~ 1829 ALT1 first form (initial) + ~ 1829 ALT1 first form (medial) + ~ 1829 ALT1 first form (final) 182A MONGOLIAN LETTER BA x (cyrillic small letter be - 0431) ~ 182A ALT1 first form (initial) ~ 182A ALT1 first form (medial) ~ 182A ALT1 first form (final) - ~ 182A 180B alternative form (final) + ~ 182A 180B second form (final) 182B MONGOLIAN LETTER PA x (cyrillic small letter pe - 043F) + ~ 182B ALT1 first form (initial) + ~ 182B ALT1 first form (medial) + ~ 182B ALT1 first form (final) 182C MONGOLIAN LETTER QA x (cyrillic small letter ha - 0445) ~ 182C ALT1 first form (initial) ~ 182C ALT1 first form (medial) ~ 182C ALT1 first form (final) + ~ 182C 180B second form (isolate) ~ 182C 180B second form (initial) ~ 182C 180B second form (medial) - ~ 182C 180B feminine second form (isolate) ~ 182C 180C third form (medial) ~ 182C 180D fourth form (medial) 182D MONGOLIAN LETTER GA @@ -9345,13 +9380,19 @@ ~ 182D ALT1 first form (final) ~ 182D 180B second form (initial) ~ 182D 180B second form (medial) - ~ 182D 180B feminine form (final) + ~ 182D 180B second form (final) ~ 182D 180C third form (medial) - ~ 182D 180D feminine form (medial) + ~ 182D 180D fourth form (medial) 182E MONGOLIAN LETTER MA x (cyrillic small letter em - 043C) + ~ 182E ALT1 first form (initial) + ~ 182E ALT1 first form (medial) + ~ 182E ALT1 first form (final) 182F MONGOLIAN LETTER LA x (cyrillic small letter el - 043B) + ~ 182F ALT1 first form (initial) + ~ 182F ALT1 first form (medial) + ~ 182F ALT1 first form (final) 1830 MONGOLIAN LETTER SA x (cyrillic small letter es - 0441) ~ 1830 ALT1 first form (initial) @@ -9361,6 +9402,9 @@ ~ 1830 180C third form (final) 1831 MONGOLIAN LETTER SHA x (cyrillic small letter sha - 0448) + ~ 1831 ALT1 first form (initial) + ~ 1831 ALT1 first form (medial) + ~ 1831 ALT1 first form (final) 1832 MONGOLIAN LETTER TA x (cyrillic small letter te - 0442) ~ 1832 ALT1 first form (initial) @@ -9377,6 +9421,9 @@ ~ 1833 180B second form (final) 1834 MONGOLIAN LETTER CHA x (cyrillic small letter che - 0447) + ~ 1834 ALT1 first form (initial) + ~ 1834 ALT1 first form (medial) + ~ 1834 ALT1 first form (final) 1835 MONGOLIAN LETTER JA x (cyrillic small letter zhe - 0436) ~ 1835 ALT1 first form (initial) @@ -9393,6 +9440,9 @@ ~ 1836 180C third form (medial) 1837 MONGOLIAN LETTER RA x (cyrillic small letter er - 0440) + ~ 1837 ALT1 first form (initial) + ~ 1837 ALT1 first form (medial) + ~ 1837 ALT1 first form (final) 1838 MONGOLIAN LETTER WA x (cyrillic small letter ve - 0432) ~ 1838 ALT1 first form (initial) @@ -9401,23 +9451,56 @@ ~ 1838 180B second form (final) 1839 MONGOLIAN LETTER FA x (cyrillic small letter ef - 0444) + ~ 1839 ALT1 first form (initial) + ~ 1839 ALT1 first form (medial) + ~ 1839 ALT1 first form (final) 183A MONGOLIAN LETTER KA x (cyrillic small letter ha - 0445) + ~ 183A ALT1 first form (initial) + ~ 183A ALT1 first form (medial) + ~ 183A ALT1 first form (final) 183B MONGOLIAN LETTER KHA x (cyrillic small letter ka - 043A) + ~ 183B ALT1 first form (initial) + ~ 183B ALT1 first form (medial) + ~ 183B ALT1 first form (final) 183C MONGOLIAN LETTER TSA x (cyrillic small letter tse - 0446) + ~ 183C ALT1 first form (initial) + ~ 183C ALT1 first form (medial) + ~ 183C ALT1 first form (final) 183D MONGOLIAN LETTER ZA x (cyrillic small letter ze - 0437) + ~ 183D ALT1 first form (initial) + ~ 183D ALT1 first form (medial) + ~ 183D ALT1 first form (final) 183E MONGOLIAN LETTER HAA x (cyrillic small letter ha - 0445) + ~ 183E ALT1 first form (initial) + ~ 183E ALT1 first form (medial) + ~ 183E ALT1 first form (final) 183F MONGOLIAN LETTER ZRA x (cyrillic small letter zhe - 0436) + ~ 183F ALT1 first form (initial) + ~ 183F ALT1 first form (medial) + ~ 183F ALT1 first form (final) 1840 MONGOLIAN LETTER LHA + ~ 1840 ALT1 first form (initial) + ~ 1840 ALT1 first form (medial) + ~ 1840 ALT1 first form (final) 1841 MONGOLIAN LETTER ZHI + ~ 1841 ALT1 first form (initial) + ~ 1841 ALT1 first form (medial) + ~ 1841 ALT1 first form (final) 1842 MONGOLIAN LETTER CHI + ~ 1842 ALT1 first form (initial) + ~ 1842 ALT1 first form (medial) + ~ 1842 ALT1 first form (final) @ Todo letters 1843 MONGOLIAN LETTER TODO LONG VOWEL SIGN + ~ 1843 ALT1 first form (initial) + ~ 1843 ALT1 first form (medial) + ~ 1843 ALT1 first form (final) 1844 MONGOLIAN LETTER TODO E ~ 1844 ALT1 first form (initial) ~ 1844 ALT1 first form (medial) @@ -9453,41 +9536,94 @@ ~ 1849 180B second form (isolate) ~ 1849 180B second form (medial) 184A MONGOLIAN LETTER TODO ANG + ~ 184A ALT1 first form (initial) + ~ 184A ALT1 first form (medial) + ~ 184A ALT1 first form (final) 184B MONGOLIAN LETTER TODO BA + ~ 184B ALT1 first form (initial) + ~ 184B ALT1 first form (medial) + ~ 184B ALT1 first form (final) 184C MONGOLIAN LETTER TODO PA + ~ 184C ALT1 first form (initial) + ~ 184C ALT1 first form (medial) + ~ 184C ALT1 first form (final) 184D MONGOLIAN LETTER TODO QA ~ 184D ALT1 first form (initial) ~ 184D ALT1 first form (medial) ~ 184D ALT1 first form (final) - ~ 184D 180B feminine form (initial) - ~ 184D 180B feminine form (medial) + ~ 184D 180B second form (initial) + ~ 184D 180B second form (medial) 184E MONGOLIAN LETTER TODO GA ~ 184E ALT1 first form (initial) ~ 184E ALT1 first form (medial) ~ 184E ALT1 first form (final) ~ 184E 180B second form (medial) 184F MONGOLIAN LETTER TODO MA + ~ 184F ALT1 first form (initial) + ~ 184F ALT1 first form (medial) + ~ 184F ALT1 first form (final) 1850 MONGOLIAN LETTER TODO TA + ~ 1850 ALT1 first form (initial) + ~ 1850 ALT1 first form (medial) + ~ 1850 ALT1 first form (final) 1851 MONGOLIAN LETTER TODO DA + ~ 1851 ALT1 first form (initial) + ~ 1851 ALT1 first form (medial) + ~ 1851 ALT1 first form (final) 1852 MONGOLIAN LETTER TODO CHA + ~ 1852 ALT1 first form (initial) + ~ 1852 ALT1 first form (medial) + ~ 1852 ALT1 first form (final) 1853 MONGOLIAN LETTER TODO JA + ~ 1853 ALT1 first form (initial) + ~ 1853 ALT1 first form (medial) + ~ 1853 ALT1 first form (final) 1854 MONGOLIAN LETTER TODO TSA + ~ 1854 ALT1 first form (initial) + ~ 1854 ALT1 first form (medial) + ~ 1854 ALT1 first form (final) 1855 MONGOLIAN LETTER TODO YA + ~ 1855 ALT1 first form (initial) + ~ 1855 ALT1 first form (medial) + ~ 1855 ALT1 first form (final) 1856 MONGOLIAN LETTER TODO WA + ~ 1856 ALT1 first form (initial) + ~ 1856 ALT1 first form (medial) + ~ 1856 ALT1 first form (final) 1857 MONGOLIAN LETTER TODO KA + ~ 1857 ALT1 first form (initial) + ~ 1857 ALT1 first form (medial) + ~ 1857 ALT1 first form (final) 1858 MONGOLIAN LETTER TODO GAA + ~ 1858 ALT1 first form (initial) + ~ 1858 ALT1 first form (medial) + ~ 1858 ALT1 first form (final) 1859 MONGOLIAN LETTER TODO HAA + ~ 1859 ALT1 first form (initial) + ~ 1859 ALT1 first form (medial) + ~ 1859 ALT1 first form (final) 185A MONGOLIAN LETTER TODO JIA + ~ 185A ALT1 first form (initial) + ~ 185A ALT1 first form (medial) + ~ 185A ALT1 first form (final) 185B MONGOLIAN LETTER TODO NIA + ~ 185B ALT1 first form (initial) + ~ 185B ALT1 first form (medial) + ~ 185B ALT1 first form (final) 185C MONGOLIAN LETTER TODO DZA + ~ 185C ALT1 first form (initial) + ~ 185C ALT1 first form (medial) + ~ 185C ALT1 first form (final) @ Sibe letters 185D MONGOLIAN LETTER SIBE E + ~ 185D ALT1 first form (isolate) ~ 185D ALT1 first form (initial) ~ 185D ALT1 first form (medial) ~ 185D ALT1 first form (final) ~ 185D 180B second form (medial) ~ 185D 180B second form (final) 185E MONGOLIAN LETTER SIBE I + ~ 185E ALT1 first form (isolate) ~ 185E ALT1 first form (initial) ~ 185E ALT1 first form (medial) ~ 185E ALT1 first form (final) @@ -9496,6 +9632,9 @@ ~ 185E 180C third form (medial) ~ 185E 180C third form (final) 185F MONGOLIAN LETTER SIBE IY + ~ 185F ALT1 first form (initial) + ~ 185F ALT1 first form (medial) + ~ 185F ALT1 first form (final) 1860 MONGOLIAN LETTER SIBE UE ~ 1860 ALT1 first form (initial) ~ 1860 ALT1 first form (medial) @@ -9503,16 +9642,35 @@ ~ 1860 180B second form (medial) ~ 1860 180B second form (final) 1861 MONGOLIAN LETTER SIBE U + ~ 1861 ALT1 first form (isolate) + ~ 1861 ALT1 first form (initial) + ~ 1861 ALT1 first form (medial) + ~ 1861 ALT1 first form (final) 1862 MONGOLIAN LETTER SIBE ANG + ~ 1862 ALT1 first form (initial) + ~ 1862 ALT1 first form (medial) + ~ 1862 ALT1 first form (final) 1863 MONGOLIAN LETTER SIBE KA ~ 1863 ALT1 first form (initial) ~ 1863 ALT1 first form (medial) ~ 1863 ALT1 first form (final) ~ 1863 180B second form (medial) 1864 MONGOLIAN LETTER SIBE GA + ~ 1864 ALT1 first form (initial) + ~ 1864 ALT1 first form (medial) + ~ 1864 ALT1 first form (final) 1865 MONGOLIAN LETTER SIBE HA + ~ 1865 ALT1 first form (initial) + ~ 1865 ALT1 first form (medial) + ~ 1865 ALT1 first form (final) 1866 MONGOLIAN LETTER SIBE PA + ~ 1866 ALT1 first form (initial) + ~ 1866 ALT1 first form (medial) + ~ 1866 ALT1 first form (final) 1867 MONGOLIAN LETTER SIBE SHA + ~ 1867 ALT1 first form (initial) + ~ 1867 ALT1 first form (medial) + ~ 1867 ALT1 first form (final) 1868 MONGOLIAN LETTER SIBE TA ~ 1868 ALT1 first form (initial) ~ 1868 ALT1 first form (medial) @@ -9527,10 +9685,25 @@ ~ 1869 180B second form (initial) ~ 1869 180B second form (medial) 186A MONGOLIAN LETTER SIBE JA + ~ 186A ALT1 first form (initial) + ~ 186A ALT1 first form (medial) + ~ 186A ALT1 first form (final) 186B MONGOLIAN LETTER SIBE FA + ~ 186B ALT1 first form (initial) + ~ 186B ALT1 first form (medial) + ~ 186B ALT1 first form (final) 186C MONGOLIAN LETTER SIBE GAA + ~ 186C ALT1 first form (initial) + ~ 186C ALT1 first form (medial) + ~ 186C ALT1 first form (final) 186D MONGOLIAN LETTER SIBE HAA + ~ 186D ALT1 first form (initial) + ~ 186D ALT1 first form (medial) + ~ 186D ALT1 first form (final) 186E MONGOLIAN LETTER SIBE TSA + ~ 186E ALT1 first form (initial) + ~ 186E ALT1 first form (medial) + ~ 186E ALT1 first form (final) 186F MONGOLIAN LETTER SIBE ZA ~ 186F ALT1 first form (initial) ~ 186F ALT1 first form (medial) @@ -9538,10 +9711,20 @@ ~ 186F 180B second form (initial) ~ 186F 180B second form (medial) 1870 MONGOLIAN LETTER SIBE RAA + ~ 1870 ALT1 first form (initial) + ~ 1870 ALT1 first form (medial) + ~ 1870 ALT1 first form (final) 1871 MONGOLIAN LETTER SIBE CHA + ~ 1871 ALT1 first form (initial) + ~ 1871 ALT1 first form (medial) + ~ 1871 ALT1 first form (final) 1872 MONGOLIAN LETTER SIBE ZHA + ~ 1872 ALT1 first form (initial) + ~ 1872 ALT1 first form (medial) + ~ 1872 ALT1 first form (final) @ Manchu letters 1873 MONGOLIAN LETTER MANCHU I + ~ 1873 ALT1 first form (isolate) ~ 1873 ALT1 first form (initial) ~ 1873 ALT1 first form (medial) ~ 1873 ALT1 first form (final) @@ -9555,11 +9738,14 @@ ~ 1874 ALT1 first form (medial) ~ 1874 ALT1 first form (final) ~ 1874 180B second form (medial) - ~ 1874 180B feminine first final form (final) - ~ 1874 180C feminine first medial form (medial) - ~ 1874 180C feminine second final form (final) - ~ 1874 180D feminine second medial form (medial) + ~ 1874 180B second form (final) + ~ 1874 180C third form (medial) + ~ 1874 180C third form (final) + ~ 1874 180D fourth form (medial) 1875 MONGOLIAN LETTER MANCHU RA + ~ 1875 ALT1 first form (initial) + ~ 1875 ALT1 first form (medial) + ~ 1875 ALT1 first form (final) 1876 MONGOLIAN LETTER MANCHU FA ~ 1876 ALT1 first form (initial) ~ 1876 ALT1 first form (medial) @@ -9567,6 +9753,9 @@ ~ 1876 180B second form (initial) ~ 1876 180B second form (medial) 1877 MONGOLIAN LETTER MANCHU ZHA + ~ 1877 ALT1 first form (initial) + ~ 1877 ALT1 first form (medial) + ~ 1877 ALT1 first form (final) @ Extensions for Sanskrit and Tibetan 1880 MONGOLIAN LETTER ALI GALI ANUSVARA ONE x (tibetan sign sna ldan - 0F83) @@ -9596,6 +9785,9 @@ ~ 1888 ALT1 first form (final) ~ 1888 180B second form (final) 1889 MONGOLIAN LETTER ALI GALI KA + ~ 1889 ALT1 first form (initial) + ~ 1889 ALT1 first form (medial) + ~ 1889 ALT1 first form (final) 188A MONGOLIAN LETTER ALI GALI NGA ~ 188A ALT1 first form (initial) ~ 188A ALT1 first form (medial) @@ -9603,37 +9795,130 @@ ~ 188A 180B second form (initial) ~ 188A 180B second form (medial) 188B MONGOLIAN LETTER ALI GALI CA + ~ 188B ALT1 first form (initial) + ~ 188B ALT1 first form (medial) + ~ 188B ALT1 first form (final) 188C MONGOLIAN LETTER ALI GALI TTA + ~ 188C ALT1 first form (initial) + ~ 188C ALT1 first form (medial) + ~ 188C ALT1 first form (final) 188D MONGOLIAN LETTER ALI GALI TTHA + ~ 188D ALT1 first form (initial) + ~ 188D ALT1 first form (medial) + ~ 188D ALT1 first form (final) 188E MONGOLIAN LETTER ALI GALI DDA + ~ 188E ALT1 first form (initial) + ~ 188E ALT1 first form (medial) + ~ 188E ALT1 first form (final) 188F MONGOLIAN LETTER ALI GALI NNA + ~ 188F ALT1 first form (initial) + ~ 188F ALT1 first form (medial) + ~ 188F ALT1 first form (final) 1890 MONGOLIAN LETTER ALI GALI TA + ~ 1890 ALT1 first form (initial) + ~ 1890 ALT1 first form (medial) + ~ 1890 ALT1 first form (final) 1891 MONGOLIAN LETTER ALI GALI DA + ~ 1891 ALT1 first form (initial) + ~ 1891 ALT1 first form (medial) + ~ 1891 ALT1 first form (final) 1892 MONGOLIAN LETTER ALI GALI PA + ~ 1892 ALT1 first form (initial) + ~ 1892 ALT1 first form (medial) + ~ 1892 ALT1 first form (final) 1893 MONGOLIAN LETTER ALI GALI PHA + ~ 1893 ALT1 first form (initial) + ~ 1893 ALT1 first form (medial) + ~ 1893 ALT1 first form (final) 1894 MONGOLIAN LETTER ALI GALI SSA + ~ 1894 ALT1 first form (initial) + ~ 1894 ALT1 first form (medial) + ~ 1894 ALT1 first form (final) 1895 MONGOLIAN LETTER ALI GALI ZHA + ~ 1895 ALT1 first form (initial) + ~ 1895 ALT1 first form (medial) + ~ 1895 ALT1 first form (final) 1896 MONGOLIAN LETTER ALI GALI ZA + ~ 1896 ALT1 first form (initial) + ~ 1896 ALT1 first form (medial) + ~ 1896 ALT1 first form (final) 1897 MONGOLIAN LETTER ALI GALI AH + ~ 1897 ALT1 first form (initial) + ~ 1897 ALT1 first form (medial) + ~ 1897 ALT1 first form (final) 1898 MONGOLIAN LETTER TODO ALI GALI TA + ~ 1898 ALT1 first form (initial) + ~ 1898 ALT1 first form (medial) + ~ 1898 ALT1 first form (final) 1899 MONGOLIAN LETTER TODO ALI GALI ZHA + ~ 1899 ALT1 first form (initial) + ~ 1899 ALT1 first form (medial) + ~ 1899 ALT1 first form (final) 189A MONGOLIAN LETTER MANCHU ALI GALI GHA + ~ 189A ALT1 first form (initial) + ~ 189A ALT1 first form (medial) + ~ 189A ALT1 first form (final) 189B MONGOLIAN LETTER MANCHU ALI GALI NGA + ~ 189B ALT1 first form (initial) + ~ 189B ALT1 first form (medial) + ~ 189B ALT1 first form (final) 189C MONGOLIAN LETTER MANCHU ALI GALI CA + ~ 189C ALT1 first form (initial) + ~ 189C ALT1 first form (medial) + ~ 189C ALT1 first form (final) 189D MONGOLIAN LETTER MANCHU ALI GALI JHA + ~ 189D ALT1 first form (initial) + ~ 189D ALT1 first form (medial) + ~ 189D ALT1 first form (final) 189E MONGOLIAN LETTER MANCHU ALI GALI TTA + ~ 189E ALT1 first form (initial) + ~ 189E ALT1 first form (medial) + ~ 189E ALT1 first form (final) 189F MONGOLIAN LETTER MANCHU ALI GALI DDHA + ~ 189F ALT1 first form (initial) + ~ 189F ALT1 first form (medial) + ~ 189F ALT1 first form (final) 18A0 MONGOLIAN LETTER MANCHU ALI GALI TA + ~ 18A0 ALT1 first form (initial) + ~ 18A0 ALT1 first form (medial) + ~ 18A0 ALT1 first form (final) 18A1 MONGOLIAN LETTER MANCHU ALI GALI DHA + ~ 18A1 ALT1 first form (initial) + ~ 18A1 ALT1 first form (medial) + ~ 18A1 ALT1 first form (final) 18A2 MONGOLIAN LETTER MANCHU ALI GALI SSA + ~ 18A2 ALT1 first form (initial) + ~ 18A2 ALT1 first form (medial) + ~ 18A2 ALT1 first form (final) 18A3 MONGOLIAN LETTER MANCHU ALI GALI CYA + ~ 18A3 ALT1 first form (initial) + ~ 18A3 ALT1 first form (medial) + ~ 18A3 ALT1 first form (final) 18A4 MONGOLIAN LETTER MANCHU ALI GALI ZHA + ~ 18A4 ALT1 first form (initial) + ~ 18A4 ALT1 first form (medial) + ~ 18A4 ALT1 first form (final) 18A5 MONGOLIAN LETTER MANCHU ALI GALI ZA + ~ 18A5 ALT1 first form (initial) + ~ 18A5 ALT1 first form (medial) + ~ 18A5 ALT1 first form (final) 18A6 MONGOLIAN LETTER ALI GALI HALF U + ~ 18A6 ALT1 first form (initial) + ~ 18A6 ALT1 first form (medial) + ~ 18A6 ALT1 first form (final) 18A7 MONGOLIAN LETTER ALI GALI HALF YA + ~ 18A7 ALT1 first form (initial) + ~ 18A7 ALT1 first form (medial) + ~ 18A7 ALT1 first form (final) 18A8 MONGOLIAN LETTER MANCHU ALI GALI BHA + ~ 18A8 ALT1 first form (initial) + ~ 18A8 ALT1 first form (medial) + ~ 18A8 ALT1 first form (final) 18A9 MONGOLIAN LETTER ALI GALI DAGALGA 18AA MONGOLIAN LETTER MANCHU ALI GALI LHA + ~ 18AA ALT1 first form (initial) + ~ 18AA ALT1 first form (medial) + ~ 18AA ALT1 first form (final) @@@~ Contextual Variants and Standardized Variation Sequences @+ Unlike other blocks, these variation sequences use the script-specific variation selectors for Mongolian. @@ 18B0 Unified Canadian Aboriginal Syllabics Extended 18FF @@ -9895,6 +10180,7 @@ 19A9 NEW TAI LUE LETTER LOW XVA 19AA NEW TAI LUE LETTER HIGH SUA 19AB NEW TAI LUE LETTER LOW SUA + * a labialized consonant cluster @ Vowel signs 19B0 NEW TAI LUE VOWEL SIGN VOWEL SHORTENER 19B1 NEW TAI LUE VOWEL SIGN AA @@ -10728,14 +11014,23 @@ @@ 1C80 Cyrillic Extended-C 1C8F @ Historic letter variants 1C80 CYRILLIC SMALL LETTER ROUNDED VE + x (cyrillic small letter ve - 0432) 1C81 CYRILLIC SMALL LETTER LONG-LEGGED DE + x (cyrillic small letter de - 0434) 1C82 CYRILLIC SMALL LETTER NARROW O + x (cyrillic small letter o - 043E) 1C83 CYRILLIC SMALL LETTER WIDE ES + x (cyrillic small letter es - 0441) 1C84 CYRILLIC SMALL LETTER TALL TE 1C85 CYRILLIC SMALL LETTER THREE-LEGGED TE + x (cyrillic small letter te - 0442) 1C86 CYRILLIC SMALL LETTER TALL HARD SIGN + x (cyrillic small letter hard sign - 044A) 1C87 CYRILLIC SMALL LETTER TALL YAT + x (cyrillic small letter yat - 0463) 1C88 CYRILLIC SMALL LETTER UNBLENDED UK + x (cyrillic small letter uk - 0479) + x (cyrillic small letter monograph uk - A64B) @@ 1CC0 Sundanese Supplement 1CCF @ Punctuation 1CC0 SUNDANESE PUNCTUATION BINDU SURYA @@ -10847,6 +11142,9 @@ * marks a bilabial fricative occurring only before unvoiced labial stops x (kannada sign upadhmaniya - 0CF2) x (tibetan sign mchu can - 0F89) +1CF7 VEDIC SIGN ATIKRAMA + = vaidika saamagaana atikrama + * indicates skipping of a svara @ Signs for Jaiminiya Sama Veda 1CF8 VEDIC TONE RING ABOVE 1CF9 VEDIC TONE DOUBLE RING ABOVE @@ -11286,6 +11584,14 @@ 1DF4 COMBINING LATIN SMALL LETTER U WITH DIAERESIS @ Diacritic for American lexicography 1DF5 COMBINING UP TACK ABOVE +@ Typicon marks +1DF6 COMBINING KAVYKA ABOVE RIGHT +1DF7 COMBINING KAVYKA ABOVE LEFT + x (combining cyrillic kavyka - A67C) +1DF8 COMBINING DOT ABOVE LEFT + x (combining dot above right - 0358) +1DF9 COMBINING WIDE INVERTED BRIDGE BELOW + x (combining inverted bridge below - 033A) @ Miscellaneous mark 1DFB COMBINING DELETION MARK * used for "mhusaa" in Newa scribal tradition @@ -12559,8 +12865,6 @@ @ Double punctuation for vertical text 203C DOUBLE EXCLAMATION MARK x (exclamation mark - 0021) - ~ 203C FE0E text style - ~ 203C FE0F emoji style # 0021 0021 @ General punctuation 203D INTERROBANG @@ -12596,8 +12900,6 @@ 2048 QUESTION EXCLAMATION MARK # 003F 0021 2049 EXCLAMATION QUESTION MARK - ~ 2049 FE0E text style - ~ 2049 FE0F emoji style # 0021 003F @ General punctuation 204A TIRONIAN SIGN ET @@ -12699,7 +13001,6 @@ 206D ACTIVATE ARABIC FORM SHAPING 206E NATIONAL DIGIT SHAPES 206F NOMINAL DIGIT SHAPES -@~ ! @@ 2070 Superscripts and Subscripts 209F @ Superscripts @+ See also superscript Latin letters in the Spacing Modifier Letters block starting at 02B0. @@ -12904,6 +13205,7 @@ * Russia 20BE LARI SIGN * Georgia +20BF BITCOIN SIGN @@ 20D0 Combining Diacritical Marks for Symbols 20FF @ Combining diacritical marks for symbols 20D0 COMBINING LEFT HARPOON ABOVE @@ -13077,8 +13379,6 @@ # 0054 0045 004C 2122 TRADE MARK SIGN x (circled wz - 1F12E) - ~ 2122 FE0E text style - ~ 2122 FE0F emoji style # <super> 0054 004D 2123 VERSICLE 2124 DOUBLE-STRUCK CAPITAL Z @@ -13160,8 +13460,6 @@ 2139 INFORMATION SOURCE * intended for use with 20DD x (circled information source - 1F6C8) - ~ 2139 FE0E text style - ~ 2139 FE0F emoji style # <font> 0069 latin small letter i 213A ROTATED CAPITAL Q * a binding signature mark @@ -13220,7 +13518,6 @@ x (greek small letter digamma - 03DD) @ Biblical editorial symbol 214F SYMBOL FOR SAMARITAN SOURCE -@~ ! @@ 2150 Number Forms 218F @ Fractions @+ Other fraction number forms are found in the Latin-1 Supplement block. @@ -13370,23 +13667,11 @@ * IPA: ingressive airflow 2194 LEFT RIGHT ARROW = z notation relation - ~ 2194 FE0E text style - ~ 2194 FE0F emoji style 2195 UP DOWN ARROW - ~ 2195 FE0E text style - ~ 2195 FE0F emoji style 2196 NORTH WEST ARROW - ~ 2196 FE0E text style - ~ 2196 FE0F emoji style 2197 NORTH EAST ARROW - ~ 2197 FE0E text style - ~ 2197 FE0F emoji style 2198 SOUTH EAST ARROW - ~ 2198 FE0E text style - ~ 2198 FE0F emoji style 2199 SOUTH WEST ARROW - ~ 2199 FE0E text style - ~ 2199 FE0F emoji style @ Arrows with modifications 219A LEFTWARDS ARROW WITH STROKE * negation of 2190 @@ -13419,11 +13704,7 @@ = depth symbol 21A8 UP DOWN ARROW WITH BASE 21A9 LEFTWARDS ARROW WITH HOOK - ~ 21A9 FE0E text style - ~ 21A9 FE0F emoji style 21AA RIGHTWARDS ARROW WITH HOOK - ~ 21AA FE0E text style - ~ 21AA FE0F emoji style 21AB LEFTWARDS ARROW WITH LOOP 21AC RIGHTWARDS ARROW WITH LOOP 21AD LEFT RIGHT WAVE ARROW @@ -13561,7 +13842,6 @@ 21FD LEFTWARDS OPEN-HEADED ARROW 21FE RIGHTWARDS OPEN-HEADED ARROW 21FF LEFT RIGHT OPEN-HEADED ARROW -@~ ! @@ 2200 Mathematical Operators 22FF @@+ @ Miscellaneous mathematical symbols @@ -14180,12 +14460,8 @@ 231A WATCH x (alarm clock - 23F0) x (clock face one oclock - 1F550) - ~ 231A FE0E text style - ~ 231A FE0F emoji style 231B HOURGLASS = alchemical symbol for hour - ~ 231B FE0E text style - ~ 231B FE0F emoji style @ Quine corners @+ These form a set of four quine corners, for quincuncial arrangement. They are also used in upper and lower pairs in mathematic, or more rarely in editorial usage as alternatives to half brackets. 231C TOP LEFT CORNER @@ -14214,8 +14490,6 @@ 2328 KEYBOARD x (keyboard and mouse - 1F5A6) x (wired keyboard - 1F5AE) - ~ 2328 FE0E text style - ~ 2328 FE0F emoji style @ Deprecated angle brackets @+ These characters are deprecated and are strongly discouraged for mathematical use because of their canonical equivalence to CJK punctuation. 2329 LEFT-POINTING ANGLE BRACKET @@ -14453,9 +14727,10 @@ 23B8 LEFT VERTICAL BOX LINE 23B9 RIGHT VERTICAL BOX LINE @ Scan lines for terminal graphics -@+ The scan line numbers here refer to old, low-resolution technology for terminals, with only 9 scan lines per fixed-size character glyph. Even-numbered scan lines are unified with box-drawing graphics. +@+ The scan line numbers here refer to old, low-resolution technology for terminals, with only 9 scan lines per fixed-size character glyph. 23BA HORIZONTAL SCAN LINE-1 23BB HORIZONTAL SCAN LINE-3 + * scan line-5 is unified with the box-drawing graphic character 2500 23BC HORIZONTAL SCAN LINE-7 23BD HORIZONTAL SCAN LINE-9 @ Dentistry notation symbols @@ -14491,8 +14766,6 @@ x (return left - 2B90) 23CF EJECT SYMBOL * UI symbol to eject media - ~ 23CF FE0E text style - ~ 23CF FE0F emoji style @ Special character extension 23D0 VERTICAL LINE EXTENSION * used for extension of arrows @@ -14546,57 +14819,45 @@ 23EB BLACK UP-POINTING DOUBLE TRIANGLE 23EC BLACK DOWN-POINTING DOUBLE TRIANGLE 23ED BLACK RIGHT-POINTING DOUBLE TRIANGLE WITH VERTICAL BAR - ~ 23ED FE0E text style - ~ 23ED FE0F emoji style 23EE BLACK LEFT-POINTING DOUBLE TRIANGLE WITH VERTICAL BAR - ~ 23EE FE0E text style - ~ 23EE FE0F emoji style 23EF BLACK RIGHT-POINTING TRIANGLE WITH DOUBLE VERTICAL BAR - ~ 23EF FE0E text style - ~ 23EF FE0F emoji style 23F0 ALARM CLOCK x (watch - 231A) x (clock face one oclock - 1F550) x (mantelpiece clock - 1F570) 23F1 STOPWATCH - ~ 23F1 FE0E text style - ~ 23F1 FE0F emoji style 23F2 TIMER CLOCK - ~ 23F2 FE0E text style - ~ 23F2 FE0F emoji style 23F3 HOURGLASS WITH FLOWING SAND x (hourglass - 231B) 23F4 BLACK MEDIUM LEFT-POINTING TRIANGLE = reverse, back * preferred to 25C0 black left-pointing triangle + x (black medium left-pointing triangle centred - 2BC7) x (black left-pointing isosceles right triangle - 1F780) 23F5 BLACK MEDIUM RIGHT-POINTING TRIANGLE = forward * preferred to 25B6 black right-pointing triangle + x (black medium right-pointing triangle centred - 2BC8) x (black right-pointing isosceles right triangle - 1F782) 23F6 BLACK MEDIUM UP-POINTING TRIANGLE = increase * preferred to 25B2 black up-pointing triangle + x (black medium up-pointing triangle centred - 2BC5) x (black up-pointing isosceles right triangle - 1F781) 23F7 BLACK MEDIUM DOWN-POINTING TRIANGLE = decrease * preferred to 25BC black down-pointing triangle + x (black medium down-pointing triangle centred - 2BC6) x (black down-pointing isosceles right triangle - 1F783) 23F8 DOUBLE VERTICAL BAR = pause x (double vertical line - 2016) - ~ 23F8 FE0E text style - ~ 23F8 FE0F emoji style 23F9 BLACK SQUARE FOR STOP = stop x (black medium square - 25FC) - ~ 23F9 FE0E text style - ~ 23F9 FE0F emoji style 23FA BLACK CIRCLE FOR RECORD = record x (medium black circle - 26AB) - ~ 23FA FE0E text style - ~ 23FA FE0F emoji style @ Power symbols from ISO 7000:2012 23FB POWER SYMBOL @+ * IEC 5009 standby symbol @@ -14609,7 +14870,8 @@ @ Power symbol from IEEE 1621-2004 23FE POWER SLEEP SYMBOL x (last quarter moon - 263E) -@~ ! +@ Miscellaneous symbol +23FF OBSERVER EYE SYMBOL @@ 2400 Control Pictures 243F @+ The diagonal lettering glyphs are only exemplary; alternate representations may be, and often are used in the visible display of control codes. @ Graphic pictures for control codes @@ -14894,8 +15156,6 @@ 24C1 CIRCLED LATIN CAPITAL LETTER L # <circle> 004C 24C2 CIRCLED LATIN CAPITAL LETTER M - ~ 24C2 FE0E text style - ~ 24C2 FE0F emoji style # <circle> 004D 24C3 CIRCLED LATIN CAPITAL LETTER N # <circle> 004E @@ -15005,7 +15265,6 @@ @ Additional white on black circled number 24FF NEGATIVE CIRCLED DIGIT ZERO x (dingbat negative circled digit one - 2776) -@~ ! @@ 2500 Box Drawing 257F @+ All of these characters are intended for compatibility with character cell graphic sets in use prior to 1990. @ Light and heavy solid lines @@ -15245,12 +15504,8 @@ 25AA BLACK SMALL SQUARE = square bullet x (black very small square - 2B1D) - ~ 25AA FE0E text style - ~ 25AA FE0F emoji style 25AB WHITE SMALL SQUARE x (white very small square - 2B1E) - ~ 25AB FE0E text style - ~ 25AB FE0F emoji style 25AC BLACK RECTANGLE 25AD WHITE RECTANGLE 25AE BLACK VERTICAL RECTANGLE @@ -15263,7 +15518,7 @@ 25B1 WHITE PARALLELOGRAM 25B2 BLACK UP-POINTING TRIANGLE x (black medium up-pointing triangle - 23F6) - x (mountain - 26F0) + x (black medium up-pointing triangle centred - 2BC5) x (up-pointing red triangle - 1F53A) 25B3 WHITE UP-POINTING TRIANGLE = trine @@ -15276,8 +15531,7 @@ 25B5 WHITE UP-POINTING SMALL TRIANGLE 25B6 BLACK RIGHT-POINTING TRIANGLE x (black medium right-pointing triangle - 23F5) - ~ 25B6 FE0E text style - ~ 25B6 FE0F emoji style + x (black medium right-pointing triangle centred - 2BC8) 25B7 WHITE RIGHT-POINTING TRIANGLE = z notation range restriction 25B8 BLACK RIGHT-POINTING SMALL TRIANGLE @@ -15289,6 +15543,7 @@ x (contains as normal subgroup - 22B3) 25BC BLACK DOWN-POINTING TRIANGLE x (black medium down-pointing triangle - 23F7) + x (black medium down-pointing triangle centred - 2BC6) x (down-pointing red triangle - 1F53B) 25BD WHITE DOWN-POINTING TRIANGLE = Hamilton operator @@ -15300,8 +15555,7 @@ 25BF WHITE DOWN-POINTING SMALL TRIANGLE 25C0 BLACK LEFT-POINTING TRIANGLE x (black medium left-pointing triangle - 23F4) - ~ 25C0 FE0E text style - ~ 25C0 FE0F emoji style + x (black medium left-pointing triangle centred - 2BC7) 25C1 WHITE LEFT-POINTING TRIANGLE = z notation domain restriction 25C2 BLACK LEFT-POINTING SMALL TRIANGLE @@ -15408,24 +15662,15 @@ = always (modal operator) x (white square - 25A1) x (white square with leftwards tick - 27E4) - ~ 25FB FE0E text style - ~ 25FB FE0F emoji style 25FC BLACK MEDIUM SQUARE x (black square for stop - 23F9) x (black square - 25A0) - ~ 25FC FE0E text style - ~ 25FC FE0F emoji style 25FD WHITE MEDIUM SMALL SQUARE x (white small square - 25AB) - ~ 25FD FE0E text style - ~ 25FD FE0F emoji style 25FE BLACK MEDIUM SMALL SQUARE x (black small square - 25AA) - ~ 25FE FE0E text style - ~ 25FE FE0F emoji style 25FF LOWER RIGHT TRIANGLE x (right triangle - 22BF) -@~ ! @@ 2600 Miscellaneous Symbols 26FF @@+ @ Weather and astrological symbols @@ -15433,28 +15678,21 @@ = clear weather x (sun - 2609) x (high brightness symbol - 1F506) - ~ 2600 FE0E text style - ~ 2600 FE0F emoji style 2601 CLOUD = cloudy weather - ~ 2601 FE0E text style - ~ 2601 FE0F emoji style 2602 UMBRELLA = rainy weather x (closed umbrella - 1F302) - ~ 2602 FE0E text style - ~ 2602 FE0F emoji style 2603 SNOWMAN = snowy weather - ~ 2603 FE0E text style - ~ 2603 FE0F emoji style 2604 COMET - ~ 2604 FE0E text style - ~ 2604 FE0F emoji style 2605 BLACK STAR x (star operator - 22C6) + x (black small star - 2B51) + x (light five pointed black star - 1F7C9) 2606 WHITE STAR x (stress outlined white star - 2729) + x (white medium star - 2B50) x (glowing star - 1F31F) 2607 LIGHTNING 2608 THUNDERSTORM @@ -15478,16 +15716,12 @@ x (telephone location sign - 2706) x (telephone receiver - 1F4DE) x (black touchtone telephone - 1F57F) - ~ 260E FE0E text style - ~ 260E FE0F emoji style 260F WHITE TELEPHONE x (white touchtone telephone - 1F57E) 2610 BALLOT BOX x (white square - 25A1) 2611 BALLOT BOX WITH CHECK x (ballot box with bold check - 1F5F9) - ~ 2611 FE0E text style - ~ 2611 FE0F emoji style 2612 BALLOT BOX WITH X x (squared times - 22A0) x (ballot box with light x - 2BBD) @@ -15500,8 +15734,6 @@ @ Weather symbol 2614 UMBRELLA WITH RAIN DROPS = showery weather - ~ 2614 FE0E text style - ~ 2614 FE0F emoji style @ Miscellaneous symbol 2615 HOT BEVERAGE = tea or coffee, depending on locale @@ -15509,16 +15741,12 @@ x (watch - 231A) x (hourglass - 231B) x (teacup without handle - 1F375) - ~ 2615 FE0E text style - ~ 2615 FE0F emoji style @ Japanese chess symbols 2616 WHITE SHOGI PIECE 2617 BLACK SHOGI PIECE @ Miscellaneous symbols 2618 SHAMROCK x (four leaf clover - 1F340) - ~ 2618 FE0E text style - ~ 2618 FE0F emoji style 2619 REVERSED ROTATED FLORAL HEART BULLET * a binding signature mark x (rotated floral heart bullet - 2767) @@ -15531,8 +15759,6 @@ x (sideways white left pointing index - 1F598) 261D WHITE UP POINTING INDEX x (sideways white up pointing index - 1F59E) - ~ 261D FE0E text style - ~ 261D FE0F emoji style 261E WHITE RIGHT POINTING INDEX = fist (typographic term) x (sideways white right pointing index - 1F599) @@ -15543,15 +15769,9 @@ 2620 SKULL AND CROSSBONES = poison x (black skull and crossbones - 1F571) - ~ 2620 FE0E text style - ~ 2620 FE0F emoji style 2621 CAUTION SIGN 2622 RADIOACTIVE SIGN - ~ 2622 FE0E text style - ~ 2622 FE0F emoji style 2623 BIOHAZARD SIGN - ~ 2623 FE0E text style - ~ 2623 FE0F emoji style @ Medical and healing symbols 2624 CADUCEUS x (staff of aesculapius - 2695) @@ -15559,29 +15779,23 @@ 2625 ANKH @ Religious and political symbols 2626 ORTHODOX CROSS - ~ 2626 FE0E text style - ~ 2626 FE0F emoji style 2627 CHI RHO = Constantine's cross, Christogram x (coptic symbol khi ro - 2CE9) 2628 CROSS OF LORRAINE 2629 CROSS OF JERUSALEM + = simple cross potent + * contrasts with the actual cross of Jerusalem, which adds a small crosslet at each corner x (alchemical symbol for vinegar - 1F70A) 262A STAR AND CRESCENT - ~ 262A FE0E text style - ~ 262A FE0F emoji style 262B FARSI SYMBOL = symbol of iran (1.0) 262C ADI SHAKTI = Gurmukhi khanda 262D HAMMER AND SICKLE 262E PEACE SYMBOL - ~ 262E FE0E text style - ~ 262E FE0F emoji style 262F YIN YANG x (tibetan symbol nor bu nyis -khyil - 0FCA) - ~ 262F FE0E text style - ~ 262F FE0F emoji style @ Yijing trigram symbols 2630 TRIGRAM FOR HEAVEN = qian2 @@ -15602,19 +15816,13 @@ @ Miscellaneous symbol 2638 WHEEL OF DHARMA x (helm symbol - 2388) - ~ 2638 FE0E text style - ~ 2638 FE0F emoji style @ Emoticons @+ Many other emoticons are encoded in the Emoticons block starting at 1F600. 2639 WHITE FROWNING FACE x (slightly frowning face - 1F641) - ~ 2639 FE0E text style - ~ 2639 FE0F emoji style 263A WHITE SMILING FACE x (slightly smiling face - 1F642) = have a nice day! - ~ 263A FE0E text style - ~ 263A FE0F emoji style 263B BLACK SMILING FACE @ Miscellaneous symbol 263C WHITE SUN WITH RAYS @@ -15657,51 +15865,27 @@ @+ See also Asian zodiacal symbols among the animal symbols in the range 1F400-1F418. 2648 ARIES x (ram - 1F40F) - ~ 2648 FE0E text style - ~ 2648 FE0F emoji style 2649 TAURUS - ~ 2649 FE0E text style - ~ 2649 FE0F emoji style 264A GEMINI - ~ 264A FE0E text style - ~ 264A FE0F emoji style 264B CANCER x (crab - 1F980) - ~ 264B FE0E text style - ~ 264B FE0F emoji style 264C LEO x (lion face - 1F981) - ~ 264C FE0E text style - ~ 264C FE0F emoji style 264D VIRGO = minim (alternate glyph) - ~ 264D FE0E text style - ~ 264D FE0F emoji style 264E LIBRA x (scales - 2696) x (alchemical symbol for sublimation - 1F75E) - ~ 264E FE0E text style - ~ 264E FE0F emoji style 264F SCORPIUS = scorpio = minim, drop x (scorpion - 1F982) - ~ 264F FE0E text style - ~ 264F FE0F emoji style 2650 SAGITTARIUS x (bow and arrow - 1F3F9) - ~ 2650 FE0E text style - ~ 2650 FE0F emoji style 2651 CAPRICORN - ~ 2651 FE0E text style - ~ 2651 FE0F emoji style 2652 AQUARIUS x (amphora - 1F3FA) - ~ 2652 FE0E text style - ~ 2652 FE0F emoji style 2653 PISCES - ~ 2653 FE0E text style - ~ 2653 FE0F emoji style @ Chess symbols 2654 WHITE CHESS KING 2655 WHITE CHESS QUEEN @@ -15717,16 +15901,12 @@ 265F BLACK CHESS PAWN @ Playing card symbols 2660 BLACK SPADE SUIT - ~ 2660 FE0E text style - ~ 2660 FE0F emoji style 2661 WHITE HEART SUIT 2662 WHITE DIAMOND SUIT x (white diamond - 25C7) x (lozenge - 25CA) 2663 BLACK CLUB SUIT x (shamrock - 2618) - ~ 2663 FE0E text style - ~ 2663 FE0F emoji style 2664 WHITE SPADE SUIT 2665 BLACK HEART SUIT = valentine @@ -15734,17 +15914,11 @@ x (heart with tip on the left - 1F394) x (blue heart - 1F499) x (black heart - 1F5A4) - ~ 2665 FE0E text style - ~ 2665 FE0F emoji style 2666 BLACK DIAMOND SUIT x (black diamond - 25C6) - ~ 2666 FE0E text style - ~ 2666 FE0F emoji style 2667 WHITE CLUB SUIT @ Miscellaneous symbol 2668 HOT SPRINGS - ~ 2668 FE0E text style - ~ 2668 FE0F emoji style @ Musical symbols 2669 QUARTER NOTE = crotchet @@ -15789,8 +15963,6 @@ * used together with other text and labels to indicate the type of material to be recycled 267B BLACK UNIVERSAL RECYCLING SYMBOL x (clockwise rightwards and leftwards open circle arrows - 1F501) - ~ 267B FE0E text style - ~ 267B FE0F emoji style 267C RECYCLED PAPER SYMBOL * used to indicate 100% recycled paper content 267D PARTIALLY-RECYCLED PAPER SYMBOL @@ -15798,8 +15970,6 @@ @ Miscellaneous symbols 267E PERMANENT PAPER SIGN 267F WHEELCHAIR SYMBOL - ~ 267F FE0E text style - ~ 267F FE0F emoji style @ Dice 2680 DIE FACE-1 x (game die - 1F3B2) @@ -15830,17 +16000,11 @@ = mining, working day (in timetables) x (pick - 26CF) x (hammer and wrench - 1F6E0) - ~ 2692 FE0E text style - ~ 2692 FE0F emoji style 2693 ANCHOR = nautical term, harbor (on maps) - ~ 2693 FE0E text style - ~ 2693 FE0F emoji style 2694 CROSSED SWORDS = military term, battleground (on maps), killed in action x (fencer - 1F93A) - ~ 2694 FE0E text style - ~ 2694 FE0F emoji style 2695 STAFF OF AESCULAPIUS = medical term * both inclined or upright renderings of this symbol are common @@ -15849,13 +16013,9 @@ 2696 SCALES = legal term, jurisprudence x (libra - 264E) - ~ 2696 FE0E text style - ~ 2696 FE0F emoji style 2697 ALEMBIC = chemical term, chemistry x (alchemical symbol for retort - 1F76D) - ~ 2697 FE0E text style - ~ 2697 FE0F emoji style 2698 FLOWER = botanical term x (flower punctuation mark - 2055) @@ -15863,19 +16023,13 @@ x (tulip - 1F337) 2699 GEAR = technology, tools - ~ 2699 FE0E text style - ~ 2699 FE0F emoji style 269A STAFF OF HERMES * signifies a commercial term or commerce * glyph shows a heraldic staff with a winged wheel 269B ATOM SYMBOL = nuclear installation (on maps) - ~ 269B FE0E text style - ~ 269B FE0F emoji style @ Miscellaneous symbols 269C FLEUR-DE-LIS - ~ 269C FE0E text style - ~ 269C FE0F emoji style 269D OUTLINED WHITE STAR * alternative form of the interlaced pentagram (a symbol of Morocco) x (right-handed interlaced pentagram - 26E5) @@ -15889,14 +16043,10 @@ @ Miscellaneous symbols 26A0 WARNING SIGN x (octagonal sign - 1F6D1) - ~ 26A0 FE0E text style - ~ 26A0 FE0F emoji style 26A1 HIGH VOLTAGE SIGN = thunder = lightning symbol x (lightning mood - 1F5F2) - ~ 26A1 FE0E text style - ~ 26A1 FE0F emoji style @ Gender symbols 26A2 DOUBLED FEMALE SIGN = lesbianism @@ -15926,13 +16076,9 @@ = engaged, betrothed * base for male or female sign x (medium bold white circle - 1F785) - ~ 26AA FE0E text style - ~ 26AA FE0F emoji style 26AB MEDIUM BLACK CIRCLE * UI symbol for record function x (black circle for record - 23FA) - ~ 26AB FE0E text style - ~ 26AB FE0F emoji style 26AC MEDIUM SMALL WHITE CIRCLE = engaged, betrothed (genealogy) * can represent wedding ring @@ -15947,12 +16093,8 @@ 26B0 COFFIN = buried (genealogy) x (white rectangle - 25AD) - ~ 26B0 FE0E text style - ~ 26B0 FE0F emoji style 26B1 FUNERAL URN = cremated (genealogy) - ~ 26B1 FE0E text style - ~ 26B1 FE0F emoji style @ Gender symbol 26B2 NEUTER @ Astrological signs @@ -15974,11 +16116,7 @@ @ Sport symbols @+ See other sport symbols in the Miscellaneous Symbols and Pictographs block. 26BD SOCCER BALL - ~ 26BD FE0E text style - ~ 26BD FE0F emoji style 26BE BASEBALL - ~ 26BE FE0E text style - ~ 26BE FE0F emoji style @ Miscellaneous symbol from ARIB STD B24 26BF SQUARED KEY = parental lock @@ -15991,13 +16129,9 @@ @ Weather symbols from ARIB STD B24 26C4 SNOWMAN WITHOUT SNOW = light snow - ~ 26C4 FE0E text style - ~ 26C4 FE0F emoji style 26C5 SUN BEHIND CLOUD = partly cloudy x (white sun with small cloud - 1F324) - ~ 26C5 FE0E text style - ~ 26C5 FE0F emoji style 26C6 RAIN = rainy weather 26C7 BLACK SNOWMAN @@ -16005,8 +16139,6 @@ 26C8 THUNDER CLOUD AND RAIN = thunderstorm x (cloud with lightning - 1F329) - ~ 26C8 FE0E text style - ~ 26C8 FE0F emoji style @ Game symbols from ARIB STD B24 26C9 TURNED WHITE SHOGI PIECE 26CA TURNED BLACK SHOGI PIECE @@ -16024,26 +16156,18 @@ = under construction x (hammer and pick - 2692) x (construction sign - 1F6A7) - ~ 26CF FE0E text style - ~ 26CF FE0F emoji style 26D0 CAR SLIDING = icy road 26D1 HELMET WITH WHITE CROSS = maintenance x (construction worker - 1F477) - ~ 26D1 FE0E text style - ~ 26D1 FE0F emoji style 26D2 CIRCLED CROSSING LANES = road closed x (circled times - 2297) 26D3 CHAINS = tyre chains required - ~ 26D3 FE0E text style - ~ 26D3 FE0F emoji style 26D4 NO ENTRY x (no entry sign - 1F6AB) - ~ 26D4 FE0E text style - ~ 26D4 FE0F emoji style 26D5 ALTERNATE ONE-WAY LEFT WAY TRAFFIC * left side traffic 26D6 BLACK TWO-WAY LEFT WAY TRAFFIC @@ -16094,11 +16218,7 @@ x (hospital - 1F3E5) 26E9 SHINTO SHRINE = torii - ~ 26E9 FE0E text style - ~ 26E9 FE0F emoji style 26EA CHURCH - ~ 26EA FE0E text style - ~ 26EA FE0F emoji style 26EB CASTLE x (european castle - 1F3F0) 26EC HISTORIC SITE @@ -16111,70 +16231,46 @@ = power plant, power substation 26EF MAP SYMBOL FOR LIGHTHOUSE 26F0 MOUNTAIN - x (black up-pointing triangle - 25B2) x (snow capped mountain - 1F3D4) - ~ 26F0 FE0E text style - ~ 26F0 FE0F emoji style 26F1 UMBRELLA ON GROUND = bathing beach x (umbrella - 2602) x (beach with umbrella - 1F3D6) - ~ 26F1 FE0E text style - ~ 26F1 FE0F emoji style 26F2 FOUNTAIN = park - ~ 26F2 FE0E text style - ~ 26F2 FE0F emoji style 26F3 FLAG IN HOLE = golf course x (triangular flag on post - 1F6A9) - ~ 26F3 FE0E text style - ~ 26F3 FE0F emoji style 26F4 FERRY = ferry boat terminal x (ship - 1F6A2) - ~ 26F4 FE0E text style - ~ 26F4 FE0F emoji style 26F5 SAILBOAT = marina or yacht harbour x (rowboat - 1F6A3) - ~ 26F5 FE0E text style - ~ 26F5 FE0F emoji style 26F6 SQUARE FOUR CORNERS = intersection 26F7 SKIER = ski resort x (ski and ski boot - 1F3BF) - ~ 26F7 FE0E text style - ~ 26F7 FE0F emoji style 26F8 ICE SKATE = ice skating rink - ~ 26F8 FE0E text style - ~ 26F8 FE0F emoji style 26F9 PERSON WITH BALL = track and field, gymnasium - ~ 26F9 FE0E text style - ~ 26F9 FE0F emoji style 26FA TENT = camping site x (camping - 1F3D5) - ~ 26FA FE0E text style - ~ 26FA FE0F emoji style 26FB JAPANESE BANK SYMBOL x (bank - 1F3E6) 26FC HEADSTONE GRAVEYARD SYMBOL = graveyard, memorial park, cemetery 26FD FUEL PUMP = petrol station, gas station - ~ 26FD FE0E text style - ~ 26FD FE0F emoji style 26FE CUP ON BLACK SQUARE = drive-in restaurant x (hot beverage - 2615) x (teacup without handle - 1F375) 26FF WHITE FLAG WITH HORIZONTAL MIDDLE BLACK STRIPE = Japanese self-defence force site -@~ ! @@ 2700 Dingbats 27BF @+ ITC Zapf dingbats series 100. Some of the ITC Zapf dingbats have been unified with geometric shape characters. Gaps in the chart have subsequently been filled with other dingbat-like symbols. x (black telephone - 260E) @@ -16194,8 +16290,6 @@ * forms a pair with 2704 white scissors 2701 UPPER BLADE SCISSORS 2702 BLACK SCISSORS - ~ 2702 FE0E text style - ~ 2702 FE0F emoji style 2703 LOWER BLADE SCISSORS 2704 WHITE SCISSORS 2705 WHITE HEAVY CHECK MARK @@ -16206,13 +16300,9 @@ 2707 TAPE DRIVE 2708 AIRPLANE x (up-pointing airplane - 1F6E7) - ~ 2708 FE0E text style - ~ 2708 FE0F emoji style 2709 ENVELOPE x (incoming envelope - 1F4E8) x (back of envelope - 1F582) - ~ 2709 FE0E text style - ~ 2709 FE0F emoji style 270A RAISED FIST = rock in Rock, Paper, Scissors game x (fisted hand sign - 1F44A) @@ -16223,35 +16313,23 @@ 270C VICTORY HAND = scissors in Rock, Paper, Scissors game x (reversed victory hand - 1F594) - ~ 270C FE0E text style - ~ 270C FE0F emoji style 270D WRITING HAND x (left writing hand - 1F58E) - ~ 270D FE0E text style - ~ 270D FE0F emoji style 270E LOWER RIGHT PENCIL x (lower left pencil - 1F589) 270F PENCIL - ~ 270F FE0E text style - ~ 270F FE0F emoji style 2710 UPPER RIGHT PENCIL 2711 WHITE NIB x (lower left fountain pen - 1F58B) 2712 BLACK NIB - ~ 2712 FE0E text style - ~ 2712 FE0F emoji style 2713 CHECK MARK x (square root - 221A) x (light check mark - 1F5F8) 2714 HEAVY CHECK MARK - ~ 2714 FE0E text style - ~ 2714 FE0F emoji style 2715 MULTIPLICATION X x (multiplication sign - 00D7) x (box drawings light diagonal cross - 2573) 2716 HEAVY MULTIPLICATION X - ~ 2716 FE0E text style - ~ 2716 FE0F emoji style 2717 BALLOT X x (saltire - 2613) x (ballot script x - 1F5F4) @@ -16264,18 +16342,15 @@ 271B OPEN CENTRE CROSS 271C HEAVY OPEN CENTRE CROSS 271D LATIN CROSS - ~ 271D FE0E text style - ~ 271D FE0F emoji style 271E SHADOWED WHITE LATIN CROSS x (white latin cross - 1F546) 271F OUTLINED LATIN CROSS 2720 MALTESE CROSS * Historically, the Maltese cross took many forms; the shape shown in the Zapf Dingbats is similar to one known as the Cross Formée. + x (circled cross formee - 1F902) @ Stars and asterisks 2721 STAR OF DAVID x (six pointed star with middle dot - 1F52F) - ~ 2721 FE0E text style - ~ 2721 FE0F emoji style 2722 FOUR TEARDROP-SPOKED ASTERISK 2723 FOUR BALLOON-SPOKED ASTERISK 2724 HEAVY FOUR BALLOON-SPOKED ASTERISK @@ -16301,11 +16376,7 @@ 2732 OPEN CENTRE ASTERISK 2733 EIGHT SPOKED ASTERISK x (light eight spoked asterisk - 1F7BB) - ~ 2733 FE0E text style - ~ 2733 FE0F emoji style 2734 EIGHT POINTED BLACK STAR - ~ 2734 FE0E text style - ~ 2734 FE0F emoji style 2735 EIGHT POINTED PINWHEEL STAR x (heavy eight pointed pinwheel star - 1F7D1) 2736 SIX POINTED BLACK STAR @@ -16332,13 +16403,9 @@ 2742 CIRCLED OPEN CENTRE EIGHT POINTED STAR 2743 HEAVY TEARDROP-SPOKED PINWHEEL ASTERISK 2744 SNOWFLAKE - ~ 2744 FE0E text style - ~ 2744 FE0F emoji style 2745 TIGHT TRIFOLIATE SNOWFLAKE 2746 HEAVY CHEVRON SNOWFLAKE 2747 SPARKLE - ~ 2747 FE0E text style - ~ 2747 FE0F emoji style 2748 HEAVY SPARKLE 2749 BALLOON-SPOKED ASTERISK = jack @@ -16363,8 +16430,6 @@ 2756 BLACK DIAMOND MINUS WHITE X 2757 HEAVY EXCLAMATION MARK SYMBOL = obstacles on the road, ARIB STD B24 - ~ 2757 FE0E text style - ~ 2757 FE0F emoji style 2758 LIGHT VERTICAL BAR x (vertical line - 007C) 2759 MEDIUM VERTICAL BAR @@ -16390,12 +16455,8 @@ 2762 HEAVY EXCLAMATION MARK ORNAMENT x (exclamation mark - 0021) 2763 HEAVY HEART EXCLAMATION MARK ORNAMENT - ~ 2763 FE0E text style - ~ 2763 FE0F emoji style 2764 HEAVY BLACK HEART x (black heart suit - 2665) - ~ 2764 FE0E text style - ~ 2764 FE0F emoji style 2765 ROTATED HEAVY BLACK HEART BULLET @ Fleurons 2766 FLORAL HEART @@ -16484,8 +16545,6 @@ * fonts may harmonize this glyph with the style for other black arrows x (leftwards black arrow - 2B05) x (rightwards black arrow - 2B95) - ~ 27A1 FE0E text style - ~ 27A1 FE0F emoji style 27A2 THREE-D TOP-LIGHTED RIGHTWARDS ARROWHEAD x (three-d top-lighted rightwards equilateral arrowhead - 2B9A) 27A3 THREE-D BOTTOM-LIGHTED RIGHTWARDS ARROWHEAD @@ -16530,7 +16589,6 @@ 27BE OPEN-OUTLINED RIGHTWARDS ARROW @ Miscellaneous 27BF DOUBLE CURLY LOOP -@~ ! @@ 27C0 Miscellaneous Mathematical Symbols-A 27EF @ Miscellaneous symbols 27C0 THREE DIMENSIONAL ANGLE @@ -17059,11 +17117,7 @@ x (rightwards wave arrow - 219D) x (wave arrow pointing directly left - 2B3F) 2934 ARROW POINTING RIGHTWARDS THEN CURVING UPWARDS - ~ 2934 FE0E text style - ~ 2934 FE0F emoji style 2935 ARROW POINTING RIGHTWARDS THEN CURVING DOWNWARDS - ~ 2935 FE0E text style - ~ 2935 FE0F emoji style 2936 ARROW POINTING DOWNWARDS THEN CURVING LEFTWARDS 2937 ARROW POINTING DOWNWARDS THEN CURVING RIGHTWARDS 2938 RIGHT-SIDE ARC CLOCKWISE ARROW @@ -17156,7 +17210,6 @@ 297D RIGHT FISH TAIL 297E UP FISH TAIL 297F DOWN FISH TAIL -@~ ! @@ 2980 Miscellaneous Mathematical Symbols-B 29FF @ Miscellaneous mathematical symbols 2980 TRIPLE VERTICAL BAR DELIMITER @@ -17338,6 +17391,7 @@ 29E7 THERMODYNAMIC * vertical bar crossed by two horizontals x (not equal to - 2260) + x (group mark - 2BD2) 29E8 DOWN-POINTING TRIANGLE WITH LEFT HALF BLACK x (up-pointing triangle with left half black - 25ED) 29E9 DOWN-POINTING TRIANGLE WITH RIGHT HALF BLACK @@ -17811,14 +17865,8 @@ 2B05 LEFTWARDS BLACK ARROW x (black rightwards arrow - 27A1) x (rightwards black arrow - 2B95) - ~ 2B05 FE0E text style - ~ 2B05 FE0F emoji style 2B06 UPWARDS BLACK ARROW - ~ 2B06 FE0E text style - ~ 2B06 FE0F emoji style 2B07 DOWNWARDS BLACK ARROW - ~ 2B07 FE0E text style - ~ 2B07 FE0F emoji style 2B08 NORTH EAST BLACK ARROW 2B09 NORTH WEST BLACK ARROW 2B0A SOUTH EAST BLACK ARROW @@ -17846,12 +17894,8 @@ 2B1A DOTTED SQUARE 2B1B BLACK LARGE SQUARE x (black square - 25A0) - ~ 2B1B FE0E text style - ~ 2B1B FE0F emoji style 2B1C WHITE LARGE SQUARE x (white square - 25A1) - ~ 2B1C FE0E text style - ~ 2B1C FE0F emoji style 2B1D BLACK VERY SMALL SQUARE x (black small square - 25AA) 2B1E WHITE VERY SMALL SQUARE @@ -17960,11 +18004,11 @@ * slight fall or overall fall in tone when at the end of a word or at the beginning of a phrase, respectively @ Stars 2B50 WHITE MEDIUM STAR - x (star operator - 22C6) - ~ 2B50 FE0E text style - ~ 2B50 FE0F emoji style + x (white star - 2606) 2B51 BLACK SMALL STAR x (arabic five pointed star - 066D) + x (star operator - 22C6) + x (black star - 2605) 2B52 WHITE SMALL STAR @ Pentagons 2B53 BLACK RIGHT-POINTING PENTAGON @@ -17974,8 +18018,6 @@ = basic symbol for speed limit * forms a game tally pair with 274C x (large circle - 25EF) - ~ 2B55 FE0E text style - ~ 2B55 FE0F emoji style @ Dictionary and map symbols from ARIB STD B24 2B56 HEAVY OVAL WITH OVAL INSIDE = prefectural office @@ -18056,9 +18098,11 @@ = end 2B79 SOUTH WEST TRIANGLE-HEADED ARROW TO BAR 2B7A LEFTWARDS TRIANGLE-HEADED ARROW WITH DOUBLE HORIZONTAL STROKE + % LEFTWARDS TRIANGLE-HEADED ARROW WITH DOUBLE VERTICAL STROKE 2B7B UPWARDS TRIANGLE-HEADED ARROW WITH DOUBLE HORIZONTAL STROKE = page up 2B7C RIGHTWARDS TRIANGLE-HEADED ARROW WITH DOUBLE HORIZONTAL STROKE + % RIGHTWARDS TRIANGLE-HEADED ARROW WITH DOUBLE VERTICAL STROKE 2B7D DOWNWARDS TRIANGLE-HEADED ARROW WITH DOUBLE HORIZONTAL STROKE = page down @ Keyboard symbols @@ -18172,11 +18216,16 @@ 2BC1 BLACK DIAMOND CENTRED 2BC2 TURNED BLACK PENTAGON 2BC3 HORIZONTAL BLACK OCTAGON + x (octagonal sign - 1F6D1) 2BC4 BLACK OCTAGON 2BC5 BLACK MEDIUM UP-POINTING TRIANGLE CENTRED + x (black up-pointing triangle - 25B2) 2BC6 BLACK MEDIUM DOWN-POINTING TRIANGLE CENTRED + x (black down-pointing triangle - 25BC) 2BC7 BLACK MEDIUM LEFT-POINTING TRIANGLE CENTRED + x (black left-pointing triangle - 25C0) 2BC8 BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED + x (black right-pointing triangle - 25B6) @ Half circles 2BCA TOP HALF BLACK CIRCLE 2BCB BOTTOM HALF BLACK CIRCLE @@ -18195,6 +18244,10 @@ = query x (apl functional symbol quad question - 2370) x (replacement character - FFFD) +2BD2 GROUP MARK + * formerly used as a separator character for I/O operations + x (double dagger - 2021) + x (thermodynamic - 29E7) @ Two-headed arrow symbols @+ The following four arrow symbols are the preferred representation for fast cursor direction for ISO 9995-7. 2BEC LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS @@ -18206,7 +18259,6 @@ = fast cursor right 2BEF DOWNWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS = fast cursor down -@~ ! @@ 2C00 Glagolitic 2C5F @ Capital letters 2C00 GLAGOLITIC CAPITAL LETTER AZU @@ -18924,6 +18976,14 @@ 2E43 DASH WITH LEFT UPTURN @ Miscellaneous punctuation 2E44 DOUBLE SUSPENSION MARK +@ Typicon punctuation +2E45 INVERTED LOW KAVYKA +2E46 INVERTED LOW KAVYKA WITH KAVYKA ABOVE + x (modifier breve with inverted breve - AB5B) +2E47 LOW KAVYKA + x (cyrillic kavyka - A67E) +2E48 LOW KAVYKA WITH DOT +2E49 DOUBLE STACKED COMMA @@ 2E80 CJK Radicals Supplement 2EFF @ CJK radicals supplement 2E80 CJK RADICAL REPEAT @@ -19749,19 +19809,20 @@ = single dot Bangjeom 302F HANGUL DOUBLE DOT TONE MARK = double dot Bangjeom -@ Other CJK symbols +@ Other CJK punctuation 3030 WAVY DASH x (wavy line - 2307) x (wave dash - 301C) - ~ 3030 FE0E text style - ~ 3030 FE0F emoji style +@ Kana repeat marks +@+ These characters are only used in vertical writing of Japanese. 3031 VERTICAL KANA REPEAT MARK 3032 VERTICAL KANA REPEAT WITH VOICED SOUND MARK - * the preceding two semantic characters are preferred to the following three glyphic forms + * implemented as glyphs that are two-em tall 3033 VERTICAL KANA REPEAT MARK UPPER HALF 3034 VERTICAL KANA REPEAT WITH VOICED SOUND MARK UPPER HALF - * the preceding two are glyphs used in conjunction with the following glyph + * implemented as glyphs that are one-em tall and that combine with the following character to form ligated two-em glyphs for the complete repeat marks 3035 VERTICAL KANA REPEAT MARK LOWER HALF +@ Other CJK symbols 3036 CIRCLED POSTAL MARK # 3012 postal mark 3037 IDEOGRAPHIC TELEGRAPH LINE FEED SEPARATOR SYMBOL @@ -19779,15 +19840,12 @@ x (squared rising diagonal slash - 29C4) 303D PART ALTERNATION MARK * marks the start of a song part in Japanese - ~ 303D FE0E text style - ~ 303D FE0F emoji style @ Special CJK indicators @+ These are visibly displayed graphic characters, not invisible format control characters. 303E IDEOGRAPHIC VARIATION INDICATOR * visual indicator that the following ideograph is to be taken as a variant of the intended character 303F IDEOGRAPHIC HALF FILL SPACE * visual indicator of a screen space for half of an ideograph -@~ ! @@ 3040 Hiragana 309F @ Hiragana letters 3041 HIRAGANA LETTER SMALL A @@ -20118,9 +20176,11 @@ 312A BOPOMOFO LETTER V 312B BOPOMOFO LETTER NG 312C BOPOMOFO LETTER GN -@ Miscellaneous addition +@ Miscellaneous additions 312D BOPOMOFO LETTER IH * for analytic representation of apical vowel +312E BOPOMOFO LETTER O WITH DOT ABOVE + * early form of letter e @@ 3130 Hangul Compatibility Jamo 318F @ Consonant letters 3131 HANGUL LETTER KIYEOK @@ -20837,14 +20897,10 @@ 3296 CIRCLED IDEOGRAPH FINANCIAL # <circle> 8CA1 3297 CIRCLED IDEOGRAPH CONGRATULATION - ~ 3297 FE0E text style - ~ 3297 FE0F emoji style # <circle> 795D 3298 CIRCLED IDEOGRAPH LABOR # <circle> 52B4 3299 CIRCLED IDEOGRAPH SECRET - ~ 3299 FE0E text style - ~ 3299 FE0F emoji style # <circle> 79D8 329A CIRCLED IDEOGRAPH MALE # <circle> 7537 @@ -21054,7 +21110,6 @@ # <circle> 30F1 32FE CIRCLED KATAKANA WO # <circle> 30F2 -@~ ! @@ 3300 CJK Compatibility 33FF @ Squared Katakana words 3300 SQUARE APAATO @@ -21190,7 +21245,8 @@ * percent # <square> 30D1 30FC 30BB 30F3 30C8 332C SQUARE PAATU - * parts + * a mistaken, unused representation originally intended for the Thai baht currency sign + x (thai currency symbol baht - 0E3F) # <square> 30D1 30FC 30C4 332D SQUARE BAARERU * barrel @@ -21737,7 +21793,7 @@ 4DFD HEXAGRAM FOR SMALL PREPONDERANCE 4DFE HEXAGRAM FOR AFTER COMPLETION 4DFF HEXAGRAM FOR BEFORE COMPLETION -@@ 4E00 CJK Unified Ideographs 9FD5 +@@ 4E00 CJK Unified Ideographs 9FEA @@ A000 Yi Syllables A48F @@+ @ Syllables @@ -23461,12 +23517,15 @@ A67B COMBINING CYRILLIC LETTER OMEGA A67C COMBINING CYRILLIC KAVYKA * indicates an alternative reading to part of a word x (combining breve - 0306) + x (combining kavyka above right - 1DF6) + x (combining kavyka above left - 1DF7) A67D COMBINING CYRILLIC PAYEROK * may indicate an omitted yer x (combining vertical tilde - 033E) @ Punctuation mark A67E CYRILLIC KAVYKA * used to mark off word that has alternative reading + x (low kavyka - 2E47) @ Modifier letter A67F CYRILLIC PAYEROK * may indicate an omitted yer @@ -24301,6 +24360,8 @@ A8FB DEVANAGARI HEADSTROKE A8FC DEVANAGARI SIGN SIDDHAM = siddhirastu * used at the beginning of texts as an invocation + x (tibetan mark initial yig mgo mdun ma - 0F04) + x (mongolian birga - 1800) x (sharada sign siddham - 111DB) A8FD DEVANAGARI JAIN OM @@ A900 Kayah Li A92F @@ -24985,6 +25046,7 @@ AB5B MODIFIER BREVE WITH INVERTED BREVE x (breve - 02D8) x (close up - 2050) x (metrical breve - 23D1) + x (inverted low kavyka with kavyka above - 2E46) AB5C MODIFIER LETTER SMALL HENG # <super> A727 AB5D MODIFIER LETTER SMALL L WITH INVERTED LAZY S @@ -25383,6 +25445,9 @@ F92A CJK COMPATIBILITY IDEOGRAPH-F92A F92B CJK COMPATIBILITY IDEOGRAPH-F92B : 72FC F92C CJK COMPATIBILITY IDEOGRAPH-F92C + * a mapping change removed the original K0 source + x (cjk unified ideograph-90DE - 90DE) + x (cjk compatibility ideograph-FA2E - FA2E) : 90CE F92D CJK COMPATIBILITY IDEOGRAPH-F92D : 4F86 @@ -25663,7 +25728,9 @@ F9B6 CJK COMPATIBILITY IDEOGRAPH-F9B6 F9B7 CJK COMPATIBILITY IDEOGRAPH-F9B7 : 91B4 F9B8 CJK COMPATIBILITY IDEOGRAPH-F9B8 + * a mapping change removed the original K0 source x (cjk unified ideograph-96B7 - 96B7) + x (cjk compatibility ideograph-FA2F - FA2F) : 96B8 F9B9 CJK COMPATIBILITY IDEOGRAPH-F9B9 : 60E1 @@ -27637,7 +27704,7 @@ FDFC RIAL SIGN FDFD ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM @@ FE00 Variation Selectors FE0F @ Variation selectors -@+ Combining characters; in conjunction with the preceding character these indicate a predetermined choice of variant glyph +@+ These are combining characters; in conjunction with the preceding character they indicate a predetermined choice of variant glyph. FE00 VARIATION SELECTOR-1 * these are abbreviated VS1, and so on FE01 VARIATION SELECTOR-2 @@ -27653,8 +27720,12 @@ FE0A VARIATION SELECTOR-11 FE0B VARIATION SELECTOR-12 FE0C VARIATION SELECTOR-13 FE0D VARIATION SELECTOR-14 +@ Emoji-specific variation selectors +@+ For documentation about use of these with emoji, see UTS #51, Unicode Emoji. FE0E VARIATION SELECTOR-15 + = text variation selector FE0F VARIATION SELECTOR-16 + = emoji variation selector @@ FE10 Vertical Forms FE1F @+ These characters are compatibility characters needed to map to GB 18030. @ Glyphs for vertical variants @@ -29280,6 +29351,10 @@ FFFF <not a character> 10321 OLD ITALIC NUMERAL FIVE 10322 OLD ITALIC NUMERAL TEN 10323 OLD ITALIC NUMERAL FIFTY +@ North Italic letters +1032D OLD ITALIC LETTER YE +1032E OLD ITALIC LETTER NORTHERN TSE +1032F OLD ITALIC LETTER SOUTHERN TSE @@ 10330 Gothic 1034F @ Letters 10330 GOTHIC LETTER AHSA @@ -29529,7 +29604,8 @@ FFFF <not a character> 1044E DESERET SMALL LETTER OI 1044F DESERET SMALL LETTER EW @@ 10450 Shavian 1047F -@ Consonants +@ Tall and deep letters (consonants) +@+ Shavian tall letters mostly represent voiceless obstruents, whereas the deep letters represent the voiced counterparts. 10450 SHAVIAN LETTER PEEP 10451 SHAVIAN LETTER TOT 10452 SHAVIAN LETTER KICK @@ -29539,7 +29615,9 @@ FFFF <not a character> 10456 SHAVIAN LETTER SURE 10457 SHAVIAN LETTER CHURCH 10458 SHAVIAN LETTER YEA + * voiced palatal approximant 10459 SHAVIAN LETTER HUNG + * voiced velar nasal 1045A SHAVIAN LETTER BIB 1045B SHAVIAN LETTER DEAD 1045C SHAVIAN LETTER GAG @@ -29549,10 +29627,13 @@ FFFF <not a character> 10460 SHAVIAN LETTER MEASURE 10461 SHAVIAN LETTER JUDGE 10462 SHAVIAN LETTER WOE + * voiced labiovelar approximant 10463 SHAVIAN LETTER HA-HA + * voiceless glottal fricative +@ Short letters +@+ Shavian short letters mostly represent vowels, but also include some nasals and liquids. 10464 SHAVIAN LETTER LOLL 10465 SHAVIAN LETTER MIME -@ Vowels 10466 SHAVIAN LETTER IF 10467 SHAVIAN LETTER EGG 10468 SHAVIAN LETTER ASH @@ -29571,6 +29652,8 @@ FFFF <not a character> 10475 SHAVIAN LETTER OOZE 10476 SHAVIAN LETTER OIL 10477 SHAVIAN LETTER AWE +@ Ligatures +@+ Shavian ligatures represent r-colored vowels or diphthongs. 10478 SHAVIAN LETTER ARE 10479 SHAVIAN LETTER OR 1047A SHAVIAN LETTER AIR @@ -30602,10 +30685,10 @@ FFFF <not a character> 1091B PHOENICIAN NUMBER THREE @ Punctuation 1091F PHOENICIAN WORD SEPARATOR + * sometimes shown with a glyph for a short vertical bar x (full stop - 002E) x (middle dot - 00B7) x (word separator middle dot - 2E31) - * sometimes shown with a glyph for a short vertical bar @@ 10920 Lydian 1093F @ Letters 10920 LYDIAN LETTER A @@ -32000,6 +32083,7 @@ FFFF <not a character> x (myanmar sign virama - 1039) 11134 CHAKMA MAAYYAA * killer + * also used distinctly as a gemination mark which can occur with vowels x (myanmar sign asat - 103A) @ Digits 11136 CHAKMA DIGIT ZERO @@ -33193,6 +33277,232 @@ FFFF <not a character> 118F2 WARANG CITI NUMBER NINETY @ Sign 118FF WARANG CITI OM +@@ 11A00 Zanabazar Square 11A4F +@+ The common Mongolian name for the script is Zanabazarin Dörböljin Useg. It is also known as Xewtee Dörböljin Bicig or in English as the Horizontal Square Script. +@ Vowel letter +11A00 ZANABAZAR SQUARE LETTER A + * used for representing independent vowels in combination with vowel signs +@ Vowel signs +11A01 ZANABAZAR SQUARE VOWEL SIGN I +11A02 ZANABAZAR SQUARE VOWEL SIGN UE +11A03 ZANABAZAR SQUARE VOWEL SIGN U +11A04 ZANABAZAR SQUARE VOWEL SIGN E +11A05 ZANABAZAR SQUARE VOWEL SIGN OE +11A06 ZANABAZAR SQUARE VOWEL SIGN O +11A07 ZANABAZAR SQUARE VOWEL SIGN AI + * also represents secondary vowel i +11A08 ZANABAZAR SQUARE VOWEL SIGN AU + * also represents secondary vowel u +11A09 ZANABAZAR SQUARE VOWEL SIGN REVERSED I + * used for Sanskrit vocalic sounds +@ Vowel length mark +11A0A ZANABAZAR SQUARE VOWEL LENGTH MARK +@ Consonants +11A0B ZANABAZAR SQUARE LETTER KA +11A0C ZANABAZAR SQUARE LETTER KHA +11A0D ZANABAZAR SQUARE LETTER GA +11A0E ZANABAZAR SQUARE LETTER GHA +11A0F ZANABAZAR SQUARE LETTER NGA +11A10 ZANABAZAR SQUARE LETTER CA +11A11 ZANABAZAR SQUARE LETTER CHA +11A12 ZANABAZAR SQUARE LETTER JA +11A13 ZANABAZAR SQUARE LETTER NYA +11A14 ZANABAZAR SQUARE LETTER TTA +11A15 ZANABAZAR SQUARE LETTER TTHA +11A16 ZANABAZAR SQUARE LETTER DDA +11A17 ZANABAZAR SQUARE LETTER DDHA +11A18 ZANABAZAR SQUARE LETTER NNA +11A19 ZANABAZAR SQUARE LETTER TA +11A1A ZANABAZAR SQUARE LETTER THA +11A1B ZANABAZAR SQUARE LETTER DA +11A1C ZANABAZAR SQUARE LETTER DHA +11A1D ZANABAZAR SQUARE LETTER NA +11A1E ZANABAZAR SQUARE LETTER PA +11A1F ZANABAZAR SQUARE LETTER PHA +11A20 ZANABAZAR SQUARE LETTER BA + * also used instead of non-initial 11A2D in conjuncts +11A21 ZANABAZAR SQUARE LETTER BHA +11A22 ZANABAZAR SQUARE LETTER MA +11A23 ZANABAZAR SQUARE LETTER TSA +11A24 ZANABAZAR SQUARE LETTER TSHA +11A25 ZANABAZAR SQUARE LETTER DZA +11A26 ZANABAZAR SQUARE LETTER DZHA +11A27 ZANABAZAR SQUARE LETTER ZHA +11A28 ZANABAZAR SQUARE LETTER ZA +11A29 ZANABAZAR SQUARE LETTER -A + * Mongolian aang + * Tibetan a-chung + x (tibetan letter -a - 0F60) +11A2A ZANABAZAR SQUARE LETTER YA +11A2B ZANABAZAR SQUARE LETTER RA +11A2C ZANABAZAR SQUARE LETTER LA +11A2D ZANABAZAR SQUARE LETTER VA +11A2E ZANABAZAR SQUARE LETTER SHA +11A2F ZANABAZAR SQUARE LETTER SSA +11A30 ZANABAZAR SQUARE LETTER SA +11A31 ZANABAZAR SQUARE LETTER HA +11A32 ZANABAZAR SQUARE LETTER KSSA +@ Final consonant mark +11A33 ZANABAZAR SQUARE FINAL CONSONANT MARK + * used for marking a syllable-final consonant in Mongolian + * indicates a syllabic boundary in Mongolian +@ Virama +11A34 ZANABAZAR SQUARE SIGN VIRAMA + * indicates a bare consonant in Sanskrit and Tibetan + * not used for conjunct formation + x (tibetan mark halanta - 0F84) +@ Candrabindu and candra ornaments +11A35 ZANABAZAR SQUARE SIGN CANDRABINDU + * indicates nasalization + x (tibetan sign sna ldan - 0F83) + x (mongolian letter ali gali anusvara one - 1880) +11A36 ZANABAZAR SQUARE SIGN CANDRABINDU WITH ORNAMENT + * used primarily with 11A3F +11A37 ZANABAZAR SQUARE SIGN CANDRA WITH ORNAMENT + * used primarily with 11A3F + x (tibetan sign nyi zla naa da - 0F82) +@ Signs for Sanskrit +11A38 ZANABAZAR SQUARE SIGN ANUSVARA + * indicates nasalization + x (tibetan sign rjes su nga ro - 0F7E) +11A39 ZANABAZAR SQUARE SIGN VISARGA + * indicates post-vocalic aspiration + x (tibetan sign rnam bcad - 0F7F) +@ Cluster-initial consonant +11A3A ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA + * initial form of 11A2B in Tibetan conjuncts +@ Cluster-final consonants +11A3B ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA + * final form of 11A2A in Tibetan conjuncts +11A3C ZANABAZAR SQUARE CLUSTER-FINAL LETTER RA + * final form of 11A2B in Tibetan conjuncts +11A3D ZANABAZAR SQUARE CLUSTER-FINAL LETTER LA + * final form of 11A2C in Tibetan conjuncts +11A3E ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA + * final form of 11A2D in Tibetan conjuncts +@ Head marks +11A3F ZANABAZAR SQUARE INITIAL HEAD MARK + x (tibetan mark initial brda rnying yig mgo mdun ma - 0FD3) + x (mongolian birga - 1800) +11A40 ZANABAZAR SQUARE CLOSING HEAD MARK + x (tibetan mark closing brda rnying yig mgo sgab ma - 0FD4) +@ Punctuation +11A41 ZANABAZAR SQUARE MARK TSHEG + x (tibetan mark intersyllabic tsheg - 0F0B) +11A42 ZANABAZAR SQUARE MARK SHAD + x (tibetan mark shad - 0F0D) +11A43 ZANABAZAR SQUARE MARK DOUBLE SHAD + x (tibetan mark nyis shad - 0F0E) +11A44 ZANABAZAR SQUARE MARK LONG TSHEG + x (tibetan mark gter tsheg - 0F14) +@ Head marks +11A45 ZANABAZAR SQUARE INITIAL DOUBLE-LINED HEAD MARK + x (tibetan mark initial yig mgo mdun ma - 0F04) +11A46 ZANABAZAR SQUARE CLOSING DOUBLE-LINED HEAD MARK + x (tibetan mark closing yig mgo sgab ma - 0F05) +@ Subjoiner +11A47 ZANABAZAR SQUARE SUBJOINER + * used for producing consonant conjuncts +@@ 11A50 Soyombo 11AAF +@ Vowel letter +11A50 SOYOMBO LETTER A + * used for representing independent vowels in combination with vowel signs +@ Vowel signs +11A51 SOYOMBO VOWEL SIGN I +11A52 SOYOMBO VOWEL SIGN UE +11A53 SOYOMBO VOWEL SIGN U +11A54 SOYOMBO VOWEL SIGN E +11A55 SOYOMBO VOWEL SIGN O +11A56 SOYOMBO VOWEL SIGN OE +11A57 SOYOMBO VOWEL SIGN AI +11A58 SOYOMBO VOWEL SIGN AU +11A59 SOYOMBO VOWEL SIGN VOCALIC R +11A5A SOYOMBO VOWEL SIGN VOCALIC L +@ Vowel length mark +11A5B SOYOMBO VOWEL LENGTH MARK +@ Consonants +11A5C SOYOMBO LETTER KA +11A5D SOYOMBO LETTER KHA +11A5E SOYOMBO LETTER GA +11A5F SOYOMBO LETTER GHA +11A60 SOYOMBO LETTER NGA +11A61 SOYOMBO LETTER CA +11A62 SOYOMBO LETTER CHA +11A63 SOYOMBO LETTER JA +11A64 SOYOMBO LETTER JHA +11A65 SOYOMBO LETTER NYA +11A66 SOYOMBO LETTER TTA +11A67 SOYOMBO LETTER TTHA +11A68 SOYOMBO LETTER DDA +11A69 SOYOMBO LETTER DDHA +11A6A SOYOMBO LETTER NNA +11A6B SOYOMBO LETTER TA +11A6C SOYOMBO LETTER THA +11A6D SOYOMBO LETTER DA +11A6E SOYOMBO LETTER DHA +11A6F SOYOMBO LETTER NA +11A70 SOYOMBO LETTER PA +11A71 SOYOMBO LETTER PHA +11A72 SOYOMBO LETTER BA +11A73 SOYOMBO LETTER BHA +11A74 SOYOMBO LETTER MA +11A75 SOYOMBO LETTER TSA +11A76 SOYOMBO LETTER TSHA +11A77 SOYOMBO LETTER DZA +11A78 SOYOMBO LETTER ZHA +11A79 SOYOMBO LETTER ZA +11A7A SOYOMBO LETTER -A +11A7B SOYOMBO LETTER YA +11A7C SOYOMBO LETTER RA +11A7D SOYOMBO LETTER LA +11A7E SOYOMBO LETTER VA +11A7F SOYOMBO LETTER SHA +11A80 SOYOMBO LETTER SSA +11A81 SOYOMBO LETTER SA +11A82 SOYOMBO LETTER HA +11A83 SOYOMBO LETTER KSSA +@ Cluster-initial letters +11A86 SOYOMBO CLUSTER-INITIAL LETTER RA +11A87 SOYOMBO CLUSTER-INITIAL LETTER LA +11A88 SOYOMBO CLUSTER-INITIAL LETTER SHA +11A89 SOYOMBO CLUSTER-INITIAL LETTER SA +@ Final consonant signs +11A8A SOYOMBO FINAL CONSONANT SIGN G +11A8B SOYOMBO FINAL CONSONANT SIGN K +11A8C SOYOMBO FINAL CONSONANT SIGN NG +11A8D SOYOMBO FINAL CONSONANT SIGN D +11A8E SOYOMBO FINAL CONSONANT SIGN N +11A8F SOYOMBO FINAL CONSONANT SIGN B +11A90 SOYOMBO FINAL CONSONANT SIGN M +11A91 SOYOMBO FINAL CONSONANT SIGN R +11A92 SOYOMBO FINAL CONSONANT SIGN L +11A93 SOYOMBO FINAL CONSONANT SIGN SH +11A94 SOYOMBO FINAL CONSONANT SIGN S +11A95 SOYOMBO FINAL CONSONANT SIGN -A + * Mongolian aang + * Tibetan a-chung + x (tibetan letter -a - 0F60) +@ Various signs +11A96 SOYOMBO SIGN ANUSVARA +11A97 SOYOMBO SIGN VISARGA +@ Gemination mark +11A98 SOYOMBO GEMINATION MARK +@ Subjoiner +11A99 SOYOMBO SUBJOINER + * used for producing consonant conjuncts +@ Punctuation +11A9A SOYOMBO MARK TSHEG +11A9B SOYOMBO MARK SHAD +11A9C SOYOMBO MARK DOUBLE SHAD +@ Head marks +11A9E SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME + * national symbol of Mongolia +11A9F SOYOMBO HEAD MARK WITH MOON AND SUN AND FLAME +11AA0 SOYOMBO HEAD MARK WITH MOON AND SUN +@ Terminal marks +11AA1 SOYOMBO TERMINAL MARK-1 +11AA2 SOYOMBO TERMINAL MARK-2 + = cintamani, candamani @@ 11AC0 Pau Cin Hau 11AFF @ Consonants 11AC0 PAU CIN HAU LETTER PA @@ -33436,6 +33746,95 @@ FFFF <not a character> @ Various signs 11CB5 MARCHEN SIGN ANUSVARA 11CB6 MARCHEN SIGN CANDRABINDU +@@ 11D00 Masaram Gondi 11D5F +@ Vowels +11D00 MASARAM GONDI LETTER A +11D01 MASARAM GONDI LETTER AA +11D02 MASARAM GONDI LETTER I +11D03 MASARAM GONDI LETTER II +11D04 MASARAM GONDI LETTER U +11D05 MASARAM GONDI LETTER UU +11D06 MASARAM GONDI LETTER E +11D08 MASARAM GONDI LETTER AI +11D09 MASARAM GONDI LETTER O +11D0B MASARAM GONDI LETTER AU +@ Consonants +11D0C MASARAM GONDI LETTER KA +11D0D MASARAM GONDI LETTER KHA +11D0E MASARAM GONDI LETTER GA +11D0F MASARAM GONDI LETTER GHA +11D10 MASARAM GONDI LETTER NGA +11D11 MASARAM GONDI LETTER CA +11D12 MASARAM GONDI LETTER CHA +11D13 MASARAM GONDI LETTER JA +11D14 MASARAM GONDI LETTER JHA +11D15 MASARAM GONDI LETTER NYA +11D16 MASARAM GONDI LETTER TTA +11D17 MASARAM GONDI LETTER TTHA +11D18 MASARAM GONDI LETTER DDA +11D19 MASARAM GONDI LETTER DDHA +11D1A MASARAM GONDI LETTER NNA +11D1B MASARAM GONDI LETTER TA +11D1C MASARAM GONDI LETTER THA +11D1D MASARAM GONDI LETTER DA +11D1E MASARAM GONDI LETTER DHA +11D1F MASARAM GONDI LETTER NA +11D20 MASARAM GONDI LETTER PA +11D21 MASARAM GONDI LETTER PHA +11D22 MASARAM GONDI LETTER BA +11D23 MASARAM GONDI LETTER BHA +11D24 MASARAM GONDI LETTER MA +11D25 MASARAM GONDI LETTER YA +11D26 MASARAM GONDI LETTER RA +11D27 MASARAM GONDI LETTER LA +11D28 MASARAM GONDI LETTER VA +11D29 MASARAM GONDI LETTER SHA +11D2A MASARAM GONDI LETTER SSA +11D2B MASARAM GONDI LETTER SA +11D2C MASARAM GONDI LETTER HA +11D2D MASARAM GONDI LETTER LLA +@ Conjunct letters +11D2E MASARAM GONDI LETTER KSSA +11D2F MASARAM GONDI LETTER JNYA +11D30 MASARAM GONDI LETTER TRA +@ Dependent vowel signs +11D31 MASARAM GONDI VOWEL SIGN AA +11D32 MASARAM GONDI VOWEL SIGN I +11D33 MASARAM GONDI VOWEL SIGN II +11D34 MASARAM GONDI VOWEL SIGN U +11D35 MASARAM GONDI VOWEL SIGN UU +11D36 MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A MASARAM GONDI VOWEL SIGN E +11D3C MASARAM GONDI VOWEL SIGN AI +11D3D MASARAM GONDI VOWEL SIGN O +11D3F MASARAM GONDI VOWEL SIGN AU +@ Various signs +11D40 MASARAM GONDI SIGN ANUSVARA +11D41 MASARAM GONDI SIGN VISARGA +11D42 MASARAM GONDI SIGN NUKTA +11D43 MASARAM GONDI SIGN CANDRA + * used for transcribing foreign vowels +11D44 MASARAM GONDI SIGN HALANTA + * used for silencing the inherent vowel +@ Virama +11D45 MASARAM GONDI VIRAMA + * used for producing conjuncts +@ Cluster-specific consonant forms +11D46 MASARAM GONDI REPHA + * cluster-initial form of 11D26 +11D47 MASARAM GONDI RA-KARA + * cluster-final form of 11D26 +@ Digits +11D50 MASARAM GONDI DIGIT ZERO +11D51 MASARAM GONDI DIGIT ONE +11D52 MASARAM GONDI DIGIT TWO +11D53 MASARAM GONDI DIGIT THREE +11D54 MASARAM GONDI DIGIT FOUR +11D55 MASARAM GONDI DIGIT FIVE +11D56 MASARAM GONDI DIGIT SIX +11D57 MASARAM GONDI DIGIT SEVEN +11D58 MASARAM GONDI DIGIT EIGHT +11D59 MASARAM GONDI DIGIT NINE @@ 12000 Cuneiform 123FF @ Signs 12000 CUNEIFORM SIGN A @@ -38079,6 +38478,8 @@ FFFF <not a character> @ Tangut mark 16FE0 TANGUT ITERATION MARK x (ideographic iteration mark - 3005) +@ Nushu mark +16FE1 NUSHU ITERATION MARK @@ 17000 Tangut 187EC @@ 18800 Tangut Components 18AFF @+ This is a superset of components used in various Tangut sources. Indexes of components (001..755) used for Tangut ideographs are shown in the Tangut block. @@ -38849,13 +39250,1030 @@ FFFF <not a character> 18AEF TANGUT COMPONENT-752 18AF0 TANGUT COMPONENT-753 18AF1 TANGUT COMPONENT-754 -@ Sixteen-stroke components +@ Sixteen-stroke component 18AF2 TANGUT COMPONENT-755 @@ 1B000 Kana Supplement 1B0FF @ Historic Katakana 1B000 KATAKANA LETTER ARCHAIC E -@ Historic Hiragana +@ Historic Hiragana and Hentaigana 1B001 HIRAGANA LETTER ARCHAIC YE + % HENTAIGANA LETTER E-1 + * derived from 6C5F +@ Hentaigana +1B002 HENTAIGANA LETTER A-1 + * derived from 5B89 +1B003 HENTAIGANA LETTER A-2 + * derived from 611B +1B004 HENTAIGANA LETTER A-3 + * derived from 963F +1B005 HENTAIGANA LETTER A-WO + * derived from 60E1 +1B006 HENTAIGANA LETTER I-1 + * derived from 4EE5 +1B007 HENTAIGANA LETTER I-2 + * derived from 4F0A +1B008 HENTAIGANA LETTER I-3 + * derived from 610F +1B009 HENTAIGANA LETTER I-4 + * derived from 79FB +1B00A HENTAIGANA LETTER U-1 + * derived from 5B87 +1B00B HENTAIGANA LETTER U-2 + * derived from 5B87 +1B00C HENTAIGANA LETTER U-3 + * derived from 6182 +1B00D HENTAIGANA LETTER U-4 + * derived from 6709 +1B00E HENTAIGANA LETTER U-5 + * derived from 96F2 +1B00F HENTAIGANA LETTER E-2 + * derived from 76C8 +1B010 HENTAIGANA LETTER E-3 + * derived from 7E01 +1B011 HENTAIGANA LETTER E-4 + * derived from 8863 +1B012 HENTAIGANA LETTER E-5 + * derived from 8863 +1B013 HENTAIGANA LETTER E-6 + * derived from 8981 +1B014 HENTAIGANA LETTER O-1 + * derived from 65BC +1B015 HENTAIGANA LETTER O-2 + * derived from 65BC +1B016 HENTAIGANA LETTER O-3 + * derived from 96B1 +1B017 HENTAIGANA LETTER KA-1 + * derived from 4F73 +1B018 HENTAIGANA LETTER KA-2 + * derived from 52A0 +1B019 HENTAIGANA LETTER KA-3 + * derived from 53EF +1B01A HENTAIGANA LETTER KA-4 + * derived from 53EF +1B01B HENTAIGANA LETTER KA-5 + * derived from 5609 +1B01C HENTAIGANA LETTER KA-6 + * derived from 6211 +1B01D HENTAIGANA LETTER KA-7 + * derived from 6B5F +1B01E HENTAIGANA LETTER KA-8 + * derived from 8CC0 +1B01F HENTAIGANA LETTER KA-9 + * derived from 9591 +1B020 HENTAIGANA LETTER KA-10 + * derived from 9999 +1B021 HENTAIGANA LETTER KA-11 + * derived from 99D5 +1B022 HENTAIGANA LETTER KA-KE + * derived from 5BB6 +1B023 HENTAIGANA LETTER KI-1 + * derived from 559C +1B024 HENTAIGANA LETTER KI-2 + * derived from 5E7E +1B025 HENTAIGANA LETTER KI-3 + * derived from 5E7E +1B026 HENTAIGANA LETTER KI-4 + * derived from 652F +1B027 HENTAIGANA LETTER KI-5 + * derived from 6728 +1B028 HENTAIGANA LETTER KI-6 + * derived from 7948 +1B029 HENTAIGANA LETTER KI-7 + * derived from 8CB4 +1B02A HENTAIGANA LETTER KI-8 + * derived from 8D77 +1B02B HENTAIGANA LETTER KU-1 + * derived from 4E45 +1B02C HENTAIGANA LETTER KU-2 + * derived from 4E45 +1B02D HENTAIGANA LETTER KU-3 + * derived from 4E5D +1B02E HENTAIGANA LETTER KU-4 + * derived from 4F9B +1B02F HENTAIGANA LETTER KU-5 + * derived from 5036 +1B030 HENTAIGANA LETTER KU-6 + * derived from 5177 +1B031 HENTAIGANA LETTER KU-7 + * derived from 6C42 +1B032 HENTAIGANA LETTER KE-1 + * derived from 4ECB +1B033 HENTAIGANA LETTER KE-2 + * derived from 4ECB +1B034 HENTAIGANA LETTER KE-3 + * derived from 5E0C +1B035 HENTAIGANA LETTER KE-4 + * derived from 6C23 +1B036 HENTAIGANA LETTER KE-5 + * derived from 8A08 +1B037 HENTAIGANA LETTER KE-6 + * derived from 9063 +1B038 HENTAIGANA LETTER KO-1 + * derived from 53E4 +1B039 HENTAIGANA LETTER KO-2 + * derived from 6545 +1B03A HENTAIGANA LETTER KO-3 + * derived from 8A31 +1B03B HENTAIGANA LETTER KO-KI + * derived from 671F +1B03C HENTAIGANA LETTER SA-1 + * derived from 4E4D +1B03D HENTAIGANA LETTER SA-2 + * derived from 4F50 +1B03E HENTAIGANA LETTER SA-3 + * derived from 4F50 +1B03F HENTAIGANA LETTER SA-4 + * derived from 5DE6 +1B040 HENTAIGANA LETTER SA-5 + * derived from 5DEE +1B041 HENTAIGANA LETTER SA-6 + * derived from 6563 +1B042 HENTAIGANA LETTER SA-7 + * derived from 659C +1B043 HENTAIGANA LETTER SA-8 + * derived from 6C99 +1B044 HENTAIGANA LETTER SI-1 + * derived from 4E4B +1B045 HENTAIGANA LETTER SI-2 + * derived from 4E4B +1B046 HENTAIGANA LETTER SI-3 + * derived from 4E8B +1B047 HENTAIGANA LETTER SI-4 + * derived from 56DB +1B048 HENTAIGANA LETTER SI-5 + * derived from 5FD7 +1B049 HENTAIGANA LETTER SI-6 + * derived from 65B0 +1B04A HENTAIGANA LETTER SU-1 + * derived from 53D7 +1B04B HENTAIGANA LETTER SU-2 + * derived from 58FD +1B04C HENTAIGANA LETTER SU-3 + * derived from 6578 +1B04D HENTAIGANA LETTER SU-4 + * derived from 6578 +1B04E HENTAIGANA LETTER SU-5 + * derived from 6625 +1B04F HENTAIGANA LETTER SU-6 + * derived from 6625 +1B050 HENTAIGANA LETTER SU-7 + * derived from 9808 +1B051 HENTAIGANA LETTER SU-8 + * derived from 9808 +1B052 HENTAIGANA LETTER SE-1 + * derived from 4E16 +1B053 HENTAIGANA LETTER SE-2 + * derived from 4E16 +1B054 HENTAIGANA LETTER SE-3 + * derived from 4E16 +1B055 HENTAIGANA LETTER SE-4 + * derived from 52E2 +1B056 HENTAIGANA LETTER SE-5 + * derived from 8072 +1B057 HENTAIGANA LETTER SO-1 + * derived from 6240 +1B058 HENTAIGANA LETTER SO-2 + * derived from 6240 +1B059 HENTAIGANA LETTER SO-3 + * derived from 66FE +1B05A HENTAIGANA LETTER SO-4 + * derived from 66FE +1B05B HENTAIGANA LETTER SO-5 + * derived from 695A +1B05C HENTAIGANA LETTER SO-6 + * derived from 8607 +1B05D HENTAIGANA LETTER SO-7 + * derived from 8655 +1B05E HENTAIGANA LETTER TA-1 + * derived from 5802 +1B05F HENTAIGANA LETTER TA-2 + * derived from 591A +1B060 HENTAIGANA LETTER TA-3 + * derived from 591A +1B061 HENTAIGANA LETTER TA-4 + * derived from 7576 +1B062 HENTAIGANA LETTER TI-1 + * derived from 5343 +1B063 HENTAIGANA LETTER TI-2 + * derived from 5730 +1B064 HENTAIGANA LETTER TI-3 + * derived from 667A +1B065 HENTAIGANA LETTER TI-4 + * derived from 77E5 +1B066 HENTAIGANA LETTER TI-5 + * derived from 77E5 +1B067 HENTAIGANA LETTER TI-6 + * derived from 81F4 +1B068 HENTAIGANA LETTER TI-7 + * derived from 9072 +1B069 HENTAIGANA LETTER TU-1 + * derived from 5DDD +1B06A HENTAIGANA LETTER TU-2 + * derived from 5DDD +1B06B HENTAIGANA LETTER TU-3 + * derived from 6D25 +1B06C HENTAIGANA LETTER TU-4 + * derived from 90FD +1B06D HENTAIGANA LETTER TU-TO + * derived from 5F92 +1B06E HENTAIGANA LETTER TE-1 + * derived from 4EAD +1B06F HENTAIGANA LETTER TE-2 + * derived from 4F4E +1B070 HENTAIGANA LETTER TE-3 + * derived from 50B3 +1B071 HENTAIGANA LETTER TE-4 + * derived from 5929 +1B072 HENTAIGANA LETTER TE-5 + * derived from 5929 +1B073 HENTAIGANA LETTER TE-6 + * derived from 5929 +1B074 HENTAIGANA LETTER TE-7 + * derived from 5E1D +1B075 HENTAIGANA LETTER TE-8 + * derived from 5F16 +1B076 HENTAIGANA LETTER TE-9 + * derived from 8F49 +1B077 HENTAIGANA LETTER TO-1 + * derived from 571F +1B078 HENTAIGANA LETTER TO-2 + * derived from 5EA6 +1B079 HENTAIGANA LETTER TO-3 + * derived from 6771 +1B07A HENTAIGANA LETTER TO-4 + * derived from 767B +1B07B HENTAIGANA LETTER TO-5 + * derived from 767B +1B07C HENTAIGANA LETTER TO-6 + * derived from 7825 +1B07D HENTAIGANA LETTER TO-RA + * derived from 7B49 +1B07E HENTAIGANA LETTER NA-1 + * derived from 5357 +1B07F HENTAIGANA LETTER NA-2 + * derived from 540D +1B080 HENTAIGANA LETTER NA-3 + * derived from 5948 +1B081 HENTAIGANA LETTER NA-4 + * derived from 5948 +1B082 HENTAIGANA LETTER NA-5 + * derived from 5948 +1B083 HENTAIGANA LETTER NA-6 + * derived from 83DC +1B084 HENTAIGANA LETTER NA-7 + * derived from 90A3 +1B085 HENTAIGANA LETTER NA-8 + * derived from 90A3 +1B086 HENTAIGANA LETTER NA-9 + * derived from 96E3 +1B087 HENTAIGANA LETTER NI-1 + * derived from 4E39 +1B088 HENTAIGANA LETTER NI-2 + * derived from 4E8C +1B089 HENTAIGANA LETTER NI-3 + * derived from 4EC1 +1B08A HENTAIGANA LETTER NI-4 + * derived from 5152 +1B08B HENTAIGANA LETTER NI-5 + * derived from 723E +1B08C HENTAIGANA LETTER NI-6 + * derived from 723E +1B08D HENTAIGANA LETTER NI-7 + * derived from 8033 +1B08E HENTAIGANA LETTER NI-TE + * derived from 800C +1B08F HENTAIGANA LETTER NU-1 + * derived from 52AA +1B090 HENTAIGANA LETTER NU-2 + * derived from 5974 +1B091 HENTAIGANA LETTER NU-3 + * derived from 6012 +1B092 HENTAIGANA LETTER NE-1 + * derived from 5E74 +1B093 HENTAIGANA LETTER NE-2 + * derived from 5E74 +1B094 HENTAIGANA LETTER NE-3 + * derived from 5E74 +1B095 HENTAIGANA LETTER NE-4 + * derived from 6839 +1B096 HENTAIGANA LETTER NE-5 + * derived from 71B1 +1B097 HENTAIGANA LETTER NE-6 + * derived from 79B0 +1B098 HENTAIGANA LETTER NE-KO + * derived from 5B50 +1B099 HENTAIGANA LETTER NO-1 + * derived from 4E43 +1B09A HENTAIGANA LETTER NO-2 + * derived from 6FC3 +1B09B HENTAIGANA LETTER NO-3 + * derived from 80FD +1B09C HENTAIGANA LETTER NO-4 + * derived from 80FD +1B09D HENTAIGANA LETTER NO-5 + * derived from 8FB2 +1B09E HENTAIGANA LETTER HA-1 + * derived from 516B +1B09F HENTAIGANA LETTER HA-2 + * derived from 534A +1B0A0 HENTAIGANA LETTER HA-3 + * derived from 5A46 +1B0A1 HENTAIGANA LETTER HA-4 + * derived from 6CE2 +1B0A2 HENTAIGANA LETTER HA-5 + * derived from 76E4 +1B0A3 HENTAIGANA LETTER HA-6 + * derived from 76E4 +1B0A4 HENTAIGANA LETTER HA-7 + * derived from 7834 +1B0A5 HENTAIGANA LETTER HA-8 + * derived from 8005 +1B0A6 HENTAIGANA LETTER HA-9 + * derived from 8005 +1B0A7 HENTAIGANA LETTER HA-10 + * derived from 8449 +1B0A8 HENTAIGANA LETTER HA-11 + * derived from 9817 +1B0A9 HENTAIGANA LETTER HI-1 + * derived from 60B2 +1B0AA HENTAIGANA LETTER HI-2 + * derived from 65E5 +1B0AB HENTAIGANA LETTER HI-3 + * derived from 6BD4 +1B0AC HENTAIGANA LETTER HI-4 + * derived from 907F +1B0AD HENTAIGANA LETTER HI-5 + * derived from 975E +1B0AE HENTAIGANA LETTER HI-6 + * derived from 98DB +1B0AF HENTAIGANA LETTER HI-7 + * derived from 98DB +1B0B0 HENTAIGANA LETTER HU-1 + * derived from 4E0D +1B0B1 HENTAIGANA LETTER HU-2 + * derived from 5A66 +1B0B2 HENTAIGANA LETTER HU-3 + * derived from 5E03 +1B0B3 HENTAIGANA LETTER HE-1 + * derived from 500D +1B0B4 HENTAIGANA LETTER HE-2 + * derived from 5F0A +1B0B5 HENTAIGANA LETTER HE-3 + * derived from 5F0A +1B0B6 HENTAIGANA LETTER HE-4 + * derived from 904D +1B0B7 HENTAIGANA LETTER HE-5 + * derived from 908A +1B0B8 HENTAIGANA LETTER HE-6 + * derived from 908A +1B0B9 HENTAIGANA LETTER HE-7 + * derived from 90E8 +1B0BA HENTAIGANA LETTER HO-1 + * derived from 4FDD +1B0BB HENTAIGANA LETTER HO-2 + * derived from 4FDD +1B0BC HENTAIGANA LETTER HO-3 + * derived from 5831 +1B0BD HENTAIGANA LETTER HO-4 + * derived from 5949 +1B0BE HENTAIGANA LETTER HO-5 + * derived from 5BF6 +1B0BF HENTAIGANA LETTER HO-6 + * derived from 672C +1B0C0 HENTAIGANA LETTER HO-7 + * derived from 672C +1B0C1 HENTAIGANA LETTER HO-8 + * derived from 8C50 +1B0C2 HENTAIGANA LETTER MA-1 + * derived from 4E07 +1B0C3 HENTAIGANA LETTER MA-2 + * derived from 672B +1B0C4 HENTAIGANA LETTER MA-3 + * derived from 672B +1B0C5 HENTAIGANA LETTER MA-4 + * derived from 6EFF +1B0C6 HENTAIGANA LETTER MA-5 + * derived from 6EFF +1B0C7 HENTAIGANA LETTER MA-6 + * derived from 842C +1B0C8 HENTAIGANA LETTER MA-7 + * derived from 9EBB +1B0C9 HENTAIGANA LETTER MI-1 + * derived from 4E09 +1B0CA HENTAIGANA LETTER MI-2 + * derived from 5FAE +1B0CB HENTAIGANA LETTER MI-3 + * derived from 7F8E +1B0CC HENTAIGANA LETTER MI-4 + * derived from 7F8E +1B0CD HENTAIGANA LETTER MI-5 + * derived from 7F8E +1B0CE HENTAIGANA LETTER MI-6 + * derived from 898B +1B0CF HENTAIGANA LETTER MI-7 + * derived from 8EAB +1B0D0 HENTAIGANA LETTER MU-1 + * derived from 6B66 +1B0D1 HENTAIGANA LETTER MU-2 + * derived from 7121 +1B0D2 HENTAIGANA LETTER MU-3 + * derived from 725F +1B0D3 HENTAIGANA LETTER MU-4 + * derived from 821E +1B0D4 HENTAIGANA LETTER ME-1 + * derived from 514D +1B0D5 HENTAIGANA LETTER ME-2 + * derived from 9762 +1B0D6 HENTAIGANA LETTER ME-MA + * derived from 99AC +1B0D7 HENTAIGANA LETTER MO-1 + * derived from 6BCD +1B0D8 HENTAIGANA LETTER MO-2 + * derived from 6BDB +1B0D9 HENTAIGANA LETTER MO-3 + * derived from 6BDB +1B0DA HENTAIGANA LETTER MO-4 + * derived from 6BDB +1B0DB HENTAIGANA LETTER MO-5 + * derived from 8302 +1B0DC HENTAIGANA LETTER MO-6 + * derived from 88F3 +1B0DD HENTAIGANA LETTER YA-1 + * derived from 4E5F +1B0DE HENTAIGANA LETTER YA-2 + * derived from 4E5F +1B0DF HENTAIGANA LETTER YA-3 + * derived from 5C4B +1B0E0 HENTAIGANA LETTER YA-4 + * derived from 8036 +1B0E1 HENTAIGANA LETTER YA-5 + * derived from 8036 +1B0E2 HENTAIGANA LETTER YA-YO + * derived from 591C +1B0E3 HENTAIGANA LETTER YU-1 + * derived from 6E38 +1B0E4 HENTAIGANA LETTER YU-2 + * derived from 7531 +1B0E5 HENTAIGANA LETTER YU-3 + * derived from 7531 +1B0E6 HENTAIGANA LETTER YU-4 + * derived from 904A +1B0E7 HENTAIGANA LETTER YO-1 + * derived from 4EE3 +1B0E8 HENTAIGANA LETTER YO-2 + * derived from 4F59 +1B0E9 HENTAIGANA LETTER YO-3 + * derived from 8207 +1B0EA HENTAIGANA LETTER YO-4 + * derived from 8207 +1B0EB HENTAIGANA LETTER YO-5 + * derived from 8207 +1B0EC HENTAIGANA LETTER YO-6 + * derived from 9918 +1B0ED HENTAIGANA LETTER RA-1 + * derived from 7F85 +1B0EE HENTAIGANA LETTER RA-2 + * derived from 826F +1B0EF HENTAIGANA LETTER RA-3 + * derived from 826F +1B0F0 HENTAIGANA LETTER RA-4 + * derived from 826F +1B0F1 HENTAIGANA LETTER RI-1 + * derived from 5229 +1B0F2 HENTAIGANA LETTER RI-2 + * derived from 5229 +1B0F3 HENTAIGANA LETTER RI-3 + * derived from 674E +1B0F4 HENTAIGANA LETTER RI-4 + * derived from 68A8 +1B0F5 HENTAIGANA LETTER RI-5 + * derived from 7406 +1B0F6 HENTAIGANA LETTER RI-6 + * derived from 91CC +1B0F7 HENTAIGANA LETTER RI-7 + * derived from 96E2 +1B0F8 HENTAIGANA LETTER RU-1 + * derived from 6D41 +1B0F9 HENTAIGANA LETTER RU-2 + * derived from 7559 +1B0FA HENTAIGANA LETTER RU-3 + * derived from 7559 +1B0FB HENTAIGANA LETTER RU-4 + * derived from 7559 +1B0FC HENTAIGANA LETTER RU-5 + * derived from 7D2F +1B0FD HENTAIGANA LETTER RU-6 + * derived from 985E +1B0FE HENTAIGANA LETTER RE-1 + * derived from 79AE +1B0FF HENTAIGANA LETTER RE-2 + * derived from 79AE +@@ 1B100 Kana Extended-A 1B12F +@ Hentaigana +1B100 HENTAIGANA LETTER RE-3 + * derived from 9023 +1B101 HENTAIGANA LETTER RE-4 + * derived from 9E97 +1B102 HENTAIGANA LETTER RO-1 + * derived from 5442 +1B103 HENTAIGANA LETTER RO-2 + * derived from 5442 +1B104 HENTAIGANA LETTER RO-3 + * derived from 5A41 +1B105 HENTAIGANA LETTER RO-4 + * derived from 6A13 +1B106 HENTAIGANA LETTER RO-5 + * derived from 8DEF +1B107 HENTAIGANA LETTER RO-6 + * derived from 9732 +1B108 HENTAIGANA LETTER WA-1 + * derived from 502D +1B109 HENTAIGANA LETTER WA-2 + * derived from 548C +1B10A HENTAIGANA LETTER WA-3 + * derived from 548C +1B10B HENTAIGANA LETTER WA-4 + * derived from 738B +1B10C HENTAIGANA LETTER WA-5 + * derived from 738B +1B10D HENTAIGANA LETTER WI-1 + * derived from 4E95 +1B10E HENTAIGANA LETTER WI-2 + * derived from 4E95 +1B10F HENTAIGANA LETTER WI-3 + * derived from 5C45 +1B110 HENTAIGANA LETTER WI-4 + * derived from 7232 +1B111 HENTAIGANA LETTER WI-5 + * derived from 907A +1B112 HENTAIGANA LETTER WE-1 + * derived from 60E0 +1B113 HENTAIGANA LETTER WE-2 + * derived from 885E +1B114 HENTAIGANA LETTER WE-3 + * derived from 885E +1B115 HENTAIGANA LETTER WE-4 + * derived from 885E +1B116 HENTAIGANA LETTER WO-1 + * derived from 4E4E +1B117 HENTAIGANA LETTER WO-2 + * derived from 4E4E +1B118 HENTAIGANA LETTER WO-3 + * derived from 5C3E +1B119 HENTAIGANA LETTER WO-4 + * derived from 7DD2 +1B11A HENTAIGANA LETTER WO-5 + * derived from 8D8A +1B11B HENTAIGANA LETTER WO-6 + * derived from 9060 +1B11C HENTAIGANA LETTER WO-7 + * derived from 9060 +1B11D HENTAIGANA LETTER N-MU-MO-1 + * derived from 65E0 +1B11E HENTAIGANA LETTER N-MU-MO-2 + * derived from 65E0 +@@ 1B170 Nushu 1B2FF +@+ A more accurate spelling of the name of this script is Nüshu. +@ One-stroke character +1B170 NUSHU CHARACTER-1B170 + x 4E00 +@ Two-stroke characters +1B171 NUSHU CHARACTER-1B171 + x 4E8C +1B172 NUSHU CHARACTER-1B172 +1B173 NUSHU CHARACTER-1B173 +1B174 NUSHU CHARACTER-1B174 +1B175 NUSHU CHARACTER-1B175 +1B176 NUSHU CHARACTER-1B176 +1B177 NUSHU CHARACTER-1B177 +@ Three-stroke characters +1B178 NUSHU CHARACTER-1B178 + x 6C34 +1B179 NUSHU CHARACTER-1B179 +1B17A NUSHU CHARACTER-1B17A +1B17B NUSHU CHARACTER-1B17B +1B17C NUSHU CHARACTER-1B17C +1B17D NUSHU CHARACTER-1B17D +1B17E NUSHU CHARACTER-1B17E +1B17F NUSHU CHARACTER-1B17F +1B180 NUSHU CHARACTER-1B180 + x 571F +1B181 NUSHU CHARACTER-1B181 +1B182 NUSHU CHARACTER-1B182 +1B183 NUSHU CHARACTER-1B183 + x 5DE5 +1B184 NUSHU CHARACTER-1B184 +1B185 NUSHU CHARACTER-1B185 + x 4E2A +1B186 NUSHU CHARACTER-1B186 +1B187 NUSHU CHARACTER-1B187 +1B188 NUSHU CHARACTER-1B188 +1B189 NUSHU CHARACTER-1B189 +1B18A NUSHU CHARACTER-1B18A + x 4E09 +@ Four-stroke characters +1B18B NUSHU CHARACTER-1B18B +1B18C NUSHU CHARACTER-1B18C +1B18D NUSHU CHARACTER-1B18D +1B18E NUSHU CHARACTER-1B18E +1B18F NUSHU CHARACTER-1B18F +1B190 NUSHU CHARACTER-1B190 +1B191 NUSHU CHARACTER-1B191 +1B192 NUSHU CHARACTER-1B192 +1B193 NUSHU CHARACTER-1B193 +1B194 NUSHU CHARACTER-1B194 + x 592B +1B195 NUSHU CHARACTER-1B195 + x 706B +1B196 NUSHU CHARACTER-1B196 +1B197 NUSHU CHARACTER-1B197 +1B198 NUSHU CHARACTER-1B198 +1B199 NUSHU CHARACTER-1B199 +1B19A NUSHU CHARACTER-1B19A +1B19B NUSHU CHARACTER-1B19B +1B19C NUSHU CHARACTER-1B19C +1B19D NUSHU CHARACTER-1B19D +1B19E NUSHU CHARACTER-1B19E +1B19F NUSHU CHARACTER-1B19F +1B1A0 NUSHU CHARACTER-1B1A0 +1B1A1 NUSHU CHARACTER-1B1A1 + x 4EA1 +1B1A2 NUSHU CHARACTER-1B1A2 +1B1A3 NUSHU CHARACTER-1B1A3 +1B1A4 NUSHU CHARACTER-1B1A4 +1B1A5 NUSHU CHARACTER-1B1A5 +1B1A6 NUSHU CHARACTER-1B1A6 +1B1A7 NUSHU CHARACTER-1B1A7 + x 738B +@ Five-stroke characters +1B1A8 NUSHU CHARACTER-1B1A8 + x 672A +1B1A9 NUSHU CHARACTER-1B1A9 +1B1AA NUSHU CHARACTER-1B1AA +1B1AB NUSHU CHARACTER-1B1AB + x 5185 +1B1AC NUSHU CHARACTER-1B1AC +1B1AD NUSHU CHARACTER-1B1AD +1B1AE NUSHU CHARACTER-1B1AE +1B1AF NUSHU CHARACTER-1B1AF +1B1B0 NUSHU CHARACTER-1B1B0 +1B1B1 NUSHU CHARACTER-1B1B1 +1B1B2 NUSHU CHARACTER-1B1B2 +1B1B3 NUSHU CHARACTER-1B1B3 +1B1B4 NUSHU CHARACTER-1B1B4 +1B1B5 NUSHU CHARACTER-1B1B5 +1B1B6 NUSHU CHARACTER-1B1B6 +1B1B7 NUSHU CHARACTER-1B1B7 +1B1B8 NUSHU CHARACTER-1B1B8 +1B1B9 NUSHU CHARACTER-1B1B9 +1B1BA NUSHU CHARACTER-1B1BA +1B1BB NUSHU CHARACTER-1B1BB +1B1BC NUSHU CHARACTER-1B1BC +1B1BD NUSHU CHARACTER-1B1BD +1B1BE NUSHU CHARACTER-1B1BE +1B1BF NUSHU CHARACTER-1B1BF +1B1C0 NUSHU CHARACTER-1B1C0 +1B1C1 NUSHU CHARACTER-1B1C1 +1B1C2 NUSHU CHARACTER-1B1C2 +1B1C3 NUSHU CHARACTER-1B1C3 +1B1C4 NUSHU CHARACTER-1B1C4 +1B1C5 NUSHU CHARACTER-1B1C5 +1B1C6 NUSHU CHARACTER-1B1C6 +1B1C7 NUSHU CHARACTER-1B1C7 +1B1C8 NUSHU CHARACTER-1B1C8 +1B1C9 NUSHU CHARACTER-1B1C9 +1B1CA NUSHU CHARACTER-1B1CA +1B1CB NUSHU CHARACTER-1B1CB +1B1CC NUSHU CHARACTER-1B1CC + x 540E +1B1CD NUSHU CHARACTER-1B1CD +1B1CE NUSHU CHARACTER-1B1CE +1B1CF NUSHU CHARACTER-1B1CF +1B1D0 NUSHU CHARACTER-1B1D0 +1B1D1 NUSHU CHARACTER-1B1D1 +1B1D2 NUSHU CHARACTER-1B1D2 +1B1D3 NUSHU CHARACTER-1B1D3 +1B1D4 NUSHU CHARACTER-1B1D4 +1B1D5 NUSHU CHARACTER-1B1D5 +1B1D6 NUSHU CHARACTER-1B1D6 +1B1D7 NUSHU CHARACTER-1B1D7 +1B1D8 NUSHU CHARACTER-1B1D8 +1B1D9 NUSHU CHARACTER-1B1D9 +1B1DA NUSHU CHARACTER-1B1DA +1B1DB NUSHU CHARACTER-1B1DB +1B1DC NUSHU CHARACTER-1B1DC +1B1DD NUSHU CHARACTER-1B1DD +@ Six-stroke characters +1B1DE NUSHU CHARACTER-1B1DE +1B1DF NUSHU CHARACTER-1B1DF +1B1E0 NUSHU CHARACTER-1B1E0 +1B1E1 NUSHU CHARACTER-1B1E1 +1B1E2 NUSHU CHARACTER-1B1E2 +1B1E3 NUSHU CHARACTER-1B1E3 +1B1E4 NUSHU CHARACTER-1B1E4 +1B1E5 NUSHU CHARACTER-1B1E5 +1B1E6 NUSHU CHARACTER-1B1E6 +1B1E7 NUSHU CHARACTER-1B1E7 +1B1E8 NUSHU CHARACTER-1B1E8 +1B1E9 NUSHU CHARACTER-1B1E9 +1B1EA NUSHU CHARACTER-1B1EA +1B1EB NUSHU CHARACTER-1B1EB +1B1EC NUSHU CHARACTER-1B1EC +1B1ED NUSHU CHARACTER-1B1ED +1B1EE NUSHU CHARACTER-1B1EE +1B1EF NUSHU CHARACTER-1B1EF +1B1F0 NUSHU CHARACTER-1B1F0 + x 53E4 +1B1F1 NUSHU CHARACTER-1B1F1 +1B1F2 NUSHU CHARACTER-1B1F2 +1B1F3 NUSHU CHARACTER-1B1F3 +1B1F4 NUSHU CHARACTER-1B1F4 +1B1F5 NUSHU CHARACTER-1B1F5 +1B1F6 NUSHU CHARACTER-1B1F6 +1B1F7 NUSHU CHARACTER-1B1F7 +1B1F8 NUSHU CHARACTER-1B1F8 +1B1F9 NUSHU CHARACTER-1B1F9 +1B1FA NUSHU CHARACTER-1B1FA +1B1FB NUSHU CHARACTER-1B1FB +1B1FC NUSHU CHARACTER-1B1FC +1B1FD NUSHU CHARACTER-1B1FD +1B1FE NUSHU CHARACTER-1B1FE +1B1FF NUSHU CHARACTER-1B1FF +1B200 NUSHU CHARACTER-1B200 +1B201 NUSHU CHARACTER-1B201 + x 591A +1B202 NUSHU CHARACTER-1B202 +1B203 NUSHU CHARACTER-1B203 +1B204 NUSHU CHARACTER-1B204 +1B205 NUSHU CHARACTER-1B205 + x 7532 +1B206 NUSHU CHARACTER-1B206 +1B207 NUSHU CHARACTER-1B207 +1B208 NUSHU CHARACTER-1B208 +1B209 NUSHU CHARACTER-1B209 +1B20A NUSHU CHARACTER-1B20A + x 53CC +1B20B NUSHU CHARACTER-1B20B +1B20C NUSHU CHARACTER-1B20C +1B20D NUSHU CHARACTER-1B20D +1B20E NUSHU CHARACTER-1B20E + x 7530 +1B20F NUSHU CHARACTER-1B20F +1B210 NUSHU CHARACTER-1B210 +1B211 NUSHU CHARACTER-1B211 +1B212 NUSHU CHARACTER-1B212 +1B213 NUSHU CHARACTER-1B213 + x 5723 +1B214 NUSHU CHARACTER-1B214 +1B215 NUSHU CHARACTER-1B215 +@ Seven-stroke characters +1B216 NUSHU CHARACTER-1B216 + x 65E9 +1B217 NUSHU CHARACTER-1B217 +1B218 NUSHU CHARACTER-1B218 +1B219 NUSHU CHARACTER-1B219 +1B21A NUSHU CHARACTER-1B21A +1B21B NUSHU CHARACTER-1B21B +1B21C NUSHU CHARACTER-1B21C +1B21D NUSHU CHARACTER-1B21D +1B21E NUSHU CHARACTER-1B21E +1B21F NUSHU CHARACTER-1B21F +1B220 NUSHU CHARACTER-1B220 +1B221 NUSHU CHARACTER-1B221 +1B222 NUSHU CHARACTER-1B222 +1B223 NUSHU CHARACTER-1B223 +1B224 NUSHU CHARACTER-1B224 +1B225 NUSHU CHARACTER-1B225 +1B226 NUSHU CHARACTER-1B226 +1B227 NUSHU CHARACTER-1B227 +1B228 NUSHU CHARACTER-1B228 +1B229 NUSHU CHARACTER-1B229 +1B22A NUSHU CHARACTER-1B22A +1B22B NUSHU CHARACTER-1B22B +1B22C NUSHU CHARACTER-1B22C +1B22D NUSHU CHARACTER-1B22D +1B22E NUSHU CHARACTER-1B22E + x 6286 +1B22F NUSHU CHARACTER-1B22F +1B230 NUSHU CHARACTER-1B230 +1B231 NUSHU CHARACTER-1B231 +1B232 NUSHU CHARACTER-1B232 +1B233 NUSHU CHARACTER-1B233 +1B234 NUSHU CHARACTER-1B234 +1B235 NUSHU CHARACTER-1B235 +1B236 NUSHU CHARACTER-1B236 +1B237 NUSHU CHARACTER-1B237 +1B238 NUSHU CHARACTER-1B238 +1B239 NUSHU CHARACTER-1B239 +1B23A NUSHU CHARACTER-1B23A +1B23B NUSHU CHARACTER-1B23B +1B23C NUSHU CHARACTER-1B23C +1B23D NUSHU CHARACTER-1B23D +1B23E NUSHU CHARACTER-1B23E +1B23F NUSHU CHARACTER-1B23F +1B240 NUSHU CHARACTER-1B240 +1B241 NUSHU CHARACTER-1B241 +1B242 NUSHU CHARACTER-1B242 +1B243 NUSHU CHARACTER-1B243 +@ Eight-stroke characters +1B244 NUSHU CHARACTER-1B244 + x 91CC +1B245 NUSHU CHARACTER-1B245 +1B246 NUSHU CHARACTER-1B246 +1B247 NUSHU CHARACTER-1B247 +1B248 NUSHU CHARACTER-1B248 +1B249 NUSHU CHARACTER-1B249 +1B24A NUSHU CHARACTER-1B24A +1B24B NUSHU CHARACTER-1B24B +1B24C NUSHU CHARACTER-1B24C +1B24D NUSHU CHARACTER-1B24D +1B24E NUSHU CHARACTER-1B24E +1B24F NUSHU CHARACTER-1B24F +1B250 NUSHU CHARACTER-1B250 +1B251 NUSHU CHARACTER-1B251 +1B252 NUSHU CHARACTER-1B252 +1B253 NUSHU CHARACTER-1B253 +1B254 NUSHU CHARACTER-1B254 +1B255 NUSHU CHARACTER-1B255 +1B256 NUSHU CHARACTER-1B256 +1B257 NUSHU CHARACTER-1B257 +1B258 NUSHU CHARACTER-1B258 +1B259 NUSHU CHARACTER-1B259 +1B25A NUSHU CHARACTER-1B25A +1B25B NUSHU CHARACTER-1B25B +1B25C NUSHU CHARACTER-1B25C +1B25D NUSHU CHARACTER-1B25D +1B25E NUSHU CHARACTER-1B25E +1B25F NUSHU CHARACTER-1B25F +1B260 NUSHU CHARACTER-1B260 +1B261 NUSHU CHARACTER-1B261 +1B262 NUSHU CHARACTER-1B262 +1B263 NUSHU CHARACTER-1B263 +1B264 NUSHU CHARACTER-1B264 +1B265 NUSHU CHARACTER-1B265 + x 53F7 +1B266 NUSHU CHARACTER-1B266 +1B267 NUSHU CHARACTER-1B267 +1B268 NUSHU CHARACTER-1B268 +1B269 NUSHU CHARACTER-1B269 +1B26A NUSHU CHARACTER-1B26A +1B26B NUSHU CHARACTER-1B26B +1B26C NUSHU CHARACTER-1B26C +1B26D NUSHU CHARACTER-1B26D +1B26E NUSHU CHARACTER-1B26E +1B26F NUSHU CHARACTER-1B26F +1B270 NUSHU CHARACTER-1B270 +1B271 NUSHU CHARACTER-1B271 +1B272 NUSHU CHARACTER-1B272 +1B273 NUSHU CHARACTER-1B273 +1B274 NUSHU CHARACTER-1B274 +1B275 NUSHU CHARACTER-1B275 +1B276 NUSHU CHARACTER-1B276 +1B277 NUSHU CHARACTER-1B277 +1B278 NUSHU CHARACTER-1B278 +1B279 NUSHU CHARACTER-1B279 +1B27A NUSHU CHARACTER-1B27A +1B27B NUSHU CHARACTER-1B27B +1B27C NUSHU CHARACTER-1B27C +1B27D NUSHU CHARACTER-1B27D +1B27E NUSHU CHARACTER-1B27E +1B27F NUSHU CHARACTER-1B27F +1B280 NUSHU CHARACTER-1B280 +1B281 NUSHU CHARACTER-1B281 +1B282 NUSHU CHARACTER-1B282 +1B283 NUSHU CHARACTER-1B283 +@ Nine-stroke characters +1B284 NUSHU CHARACTER-1B284 +1B285 NUSHU CHARACTER-1B285 +1B286 NUSHU CHARACTER-1B286 +1B287 NUSHU CHARACTER-1B287 +1B288 NUSHU CHARACTER-1B288 +1B289 NUSHU CHARACTER-1B289 +1B28A NUSHU CHARACTER-1B28A +1B28B NUSHU CHARACTER-1B28B +1B28C NUSHU CHARACTER-1B28C +1B28D NUSHU CHARACTER-1B28D +1B28E NUSHU CHARACTER-1B28E +1B28F NUSHU CHARACTER-1B28F +1B290 NUSHU CHARACTER-1B290 +1B291 NUSHU CHARACTER-1B291 +1B292 NUSHU CHARACTER-1B292 +1B293 NUSHU CHARACTER-1B293 +1B294 NUSHU CHARACTER-1B294 +1B295 NUSHU CHARACTER-1B295 +1B296 NUSHU CHARACTER-1B296 +1B297 NUSHU CHARACTER-1B297 +1B298 NUSHU CHARACTER-1B298 +1B299 NUSHU CHARACTER-1B299 +1B29A NUSHU CHARACTER-1B29A +1B29B NUSHU CHARACTER-1B29B +1B29C NUSHU CHARACTER-1B29C +1B29D NUSHU CHARACTER-1B29D +1B29E NUSHU CHARACTER-1B29E +1B29F NUSHU CHARACTER-1B29F +1B2A0 NUSHU CHARACTER-1B2A0 +1B2A1 NUSHU CHARACTER-1B2A1 +1B2A2 NUSHU CHARACTER-1B2A2 +1B2A3 NUSHU CHARACTER-1B2A3 + x 82F1 +1B2A4 NUSHU CHARACTER-1B2A4 +1B2A5 NUSHU CHARACTER-1B2A5 +1B2A6 NUSHU CHARACTER-1B2A6 +1B2A7 NUSHU CHARACTER-1B2A7 +1B2A8 NUSHU CHARACTER-1B2A8 +1B2A9 NUSHU CHARACTER-1B2A9 +1B2AA NUSHU CHARACTER-1B2AA +1B2AB NUSHU CHARACTER-1B2AB +1B2AC NUSHU CHARACTER-1B2AC +1B2AD NUSHU CHARACTER-1B2AD +1B2AE NUSHU CHARACTER-1B2AE +1B2AF NUSHU CHARACTER-1B2AF +@ Ten-stroke characters +1B2B0 NUSHU CHARACTER-1B2B0 +1B2B1 NUSHU CHARACTER-1B2B1 +1B2B2 NUSHU CHARACTER-1B2B2 +1B2B3 NUSHU CHARACTER-1B2B3 +1B2B4 NUSHU CHARACTER-1B2B4 +1B2B5 NUSHU CHARACTER-1B2B5 +1B2B6 NUSHU CHARACTER-1B2B6 +1B2B7 NUSHU CHARACTER-1B2B7 +1B2B8 NUSHU CHARACTER-1B2B8 +1B2B9 NUSHU CHARACTER-1B2B9 +1B2BA NUSHU CHARACTER-1B2BA +1B2BB NUSHU CHARACTER-1B2BB +1B2BC NUSHU CHARACTER-1B2BC +1B2BD NUSHU CHARACTER-1B2BD +1B2BE NUSHU CHARACTER-1B2BE +1B2BF NUSHU CHARACTER-1B2BF +1B2C0 NUSHU CHARACTER-1B2C0 +1B2C1 NUSHU CHARACTER-1B2C1 + x 9580 +1B2C2 NUSHU CHARACTER-1B2C2 +1B2C3 NUSHU CHARACTER-1B2C3 +1B2C4 NUSHU CHARACTER-1B2C4 +1B2C5 NUSHU CHARACTER-1B2C5 +1B2C6 NUSHU CHARACTER-1B2C6 +1B2C7 NUSHU CHARACTER-1B2C7 +1B2C8 NUSHU CHARACTER-1B2C8 +1B2C9 NUSHU CHARACTER-1B2C9 +1B2CA NUSHU CHARACTER-1B2CA +1B2CB NUSHU CHARACTER-1B2CB +1B2CC NUSHU CHARACTER-1B2CC +1B2CD NUSHU CHARACTER-1B2CD +@ Eleven-stroke characters +1B2CE NUSHU CHARACTER-1B2CE +1B2CF NUSHU CHARACTER-1B2CF +1B2D0 NUSHU CHARACTER-1B2D0 +1B2D1 NUSHU CHARACTER-1B2D1 + x 57CB +1B2D2 NUSHU CHARACTER-1B2D2 +1B2D3 NUSHU CHARACTER-1B2D3 +1B2D4 NUSHU CHARACTER-1B2D4 +1B2D5 NUSHU CHARACTER-1B2D5 +1B2D6 NUSHU CHARACTER-1B2D6 + x 83AB +1B2D7 NUSHU CHARACTER-1B2D7 +1B2D8 NUSHU CHARACTER-1B2D8 +1B2D9 NUSHU CHARACTER-1B2D9 +1B2DA NUSHU CHARACTER-1B2DA +1B2DB NUSHU CHARACTER-1B2DB +1B2DC NUSHU CHARACTER-1B2DC +1B2DD NUSHU CHARACTER-1B2DD +1B2DE NUSHU CHARACTER-1B2DE +1B2DF NUSHU CHARACTER-1B2DF +1B2E0 NUSHU CHARACTER-1B2E0 +@ Twelve-stroke characters +1B2E1 NUSHU CHARACTER-1B2E1 +1B2E2 NUSHU CHARACTER-1B2E2 +1B2E3 NUSHU CHARACTER-1B2E3 +1B2E4 NUSHU CHARACTER-1B2E4 +1B2E5 NUSHU CHARACTER-1B2E5 +1B2E6 NUSHU CHARACTER-1B2E6 +1B2E7 NUSHU CHARACTER-1B2E7 +1B2E8 NUSHU CHARACTER-1B2E8 +1B2E9 NUSHU CHARACTER-1B2E9 +1B2EA NUSHU CHARACTER-1B2EA +1B2EB NUSHU CHARACTER-1B2EB +1B2EC NUSHU CHARACTER-1B2EC +1B2ED NUSHU CHARACTER-1B2ED +@ Thirteen-stroke characters +1B2EE NUSHU CHARACTER-1B2EE +1B2EF NUSHU CHARACTER-1B2EF +1B2F0 NUSHU CHARACTER-1B2F0 +1B2F1 NUSHU CHARACTER-1B2F1 +1B2F2 NUSHU CHARACTER-1B2F2 +1B2F3 NUSHU CHARACTER-1B2F3 +@ Fourteen-stroke characters +1B2F4 NUSHU CHARACTER-1B2F4 +1B2F5 NUSHU CHARACTER-1B2F5 +1B2F6 NUSHU CHARACTER-1B2F6 +@ Fifteen-stroke characters +1B2F7 NUSHU CHARACTER-1B2F7 +1B2F8 NUSHU CHARACTER-1B2F8 +1B2F9 NUSHU CHARACTER-1B2F9 +@ Sixteen-stroke characters +1B2FA NUSHU CHARACTER-1B2FA +1B2FB NUSHU CHARACTER-1B2FB @@ 1BC00 Duployan 1BC9F @ Non-joining consonants 1BC00 DUPLOYAN LETTER H @@ -39199,7 +40617,7 @@ FFFF <not a character> * Romanian str-/-str 1BC79 DUPLOYAN AFFIX ATTACHED TAIL * orientating character - * French suffix -sionaire + * French suffix -sionnaire 1BC7A DUPLOYAN AFFIX ATTACHED E HOOK * glyph is retrograde and opens up or down, depending on preceding letter * French suffix -te @@ -39271,12 +40689,12 @@ FFFF <not a character> 1BC93 DUPLOYAN AFFIX LOW LONG GRAVE * Pernin extra- 1BC94 DUPLOYAN AFFIX LOW DOT - * French suffix -ie + * French suffix -ié * French iterative number * Romanian affix inter- * not Romanian millions - see 0323 combining dot below and 0324 combining diaeresis below 1BC95 DUPLOYAN AFFIX LOW CIRCLE - * French suffix -iere + * French suffix -ière * French percent x (modifier letter low ring - 02F3) 1BC96 DUPLOYAN AFFIX LOW LINE @@ -40090,7 +41508,7 @@ FFFF <not a character> @ Monogram 1D300 MONOGRAM FOR EARTH = ren - * usually associated with human (Chinese ren), rather than earth + * usually associated with human (Chinese rén), rather than earth (Chinese dì) x (monogram for yang - 268A) x (monogram for yin - 268B) @ Digrams @@ -40848,9 +42266,9 @@ FFFF <not a character> 1D537 MATHEMATICAL FRAKTUR SMALL Z # <font> 007A latin small letter z @ Double-struck symbols -@+ This style is sometimes known as open-face or blackboard-bold. Double-struck symbols already encoded in the Letterlike Symbols block and omitted here to avoid duplicate encoding. Considerable variation in font style is acceptable, as long as the glyphs retain the visual element of doubled strokes. +@+ This style is sometimes known as open-face or blackboard-bold. Double-struck symbols already encoded in the Letterlike Symbols block are omitted here to avoid duplicate encoding. Considerable variation in font style is acceptable, as long as the glyphs retain the visual element of doubled strokes. 1D538 MATHEMATICAL DOUBLE-STRUCK CAPITAL A - * a glyph variant with doubled stroke on the right exists + * a glyph variant with doubled stroke on the left exists # <font> 0041 latin capital letter a 1D539 MATHEMATICAL DOUBLE-STRUCK CAPITAL B # <font> 0042 latin capital letter b @@ -43751,8 +45169,6 @@ FFFF <not a character> @ Dragon tiles 1F004 MAHJONG TILE RED DRAGON = hongzhong - ~ 1F004 FE0E text style - ~ 1F004 FE0F emoji style 1F005 MAHJONG TILE GREEN DRAGON = qingfa 1F006 MAHJONG TILE WHITE DRAGON @@ -43808,7 +45224,6 @@ FFFF <not a character> 1F02A MAHJONG TILE JOKER = baida 1F02B MAHJONG TILE BACK -@~ ! @@ 1F030 Domino Tiles 1F09F @ Horizontal tiles 1F030 DOMINO TILE HORIZONTAL BACK @@ -44292,12 +45707,8 @@ FFFF <not a character> @+ The square edges may be slightly rounded. 1F170 NEGATIVE SQUARED LATIN CAPITAL LETTER A = blood type A - ~ 1F170 FE0E text style - ~ 1F170 FE0F emoji style 1F171 NEGATIVE SQUARED LATIN CAPITAL LETTER B = blood type B - ~ 1F171 FE0E text style - ~ 1F171 FE0F emoji style 1F172 NEGATIVE SQUARED LATIN CAPITAL LETTER C = centre, city centre 1F173 NEGATIVE SQUARED LATIN CAPITAL LETTER D @@ -44319,12 +45730,8 @@ FFFF <not a character> 1F17D NEGATIVE SQUARED LATIN CAPITAL LETTER N 1F17E NEGATIVE SQUARED LATIN CAPITAL LETTER O = blood type O - ~ 1F17E FE0E text style - ~ 1F17E FE0F emoji style 1F17F NEGATIVE SQUARED LATIN CAPITAL LETTER P = parking space empty-full (ARIB STD B24) - ~ 1F17F FE0E text style - ~ 1F17F FE0F emoji style 1F180 NEGATIVE SQUARED LATIN CAPITAL LETTER Q 1F181 NEGATIVE SQUARED LATIN CAPITAL LETTER R 1F182 NEGATIVE SQUARED LATIN CAPITAL LETTER S @@ -44375,10 +45782,15 @@ FFFF <not a character> 1F19E SQUARED FOUR K 1F19F SQUARED EIGHT K 1F1A0 SQUARED FIVE POINT ONE + * denotes 5.1-channel surround sound 1F1A1 SQUARED SEVEN POINT ONE + * denotes 7.1-channel surround sound 1F1A2 SQUARED TWENTY-TWO POINT TWO + * denotes 22.2-channel surround sound 1F1A3 SQUARED SIXTY P + * denotes 60Hz frame rate with progressive scanning 1F1A4 SQUARED ONE HUNDRED TWENTY P + * denotes 120Hz frame rate with progressive scanning 1F1A5 SQUARED LATIN SMALL LETTER D = data 1F1A6 SQUARED HC @@ -44422,7 +45834,6 @@ FFFF <not a character> 1F1FD REGIONAL INDICATOR SYMBOL LETTER X 1F1FE REGIONAL INDICATOR SYMBOL LETTER Y 1F1FF REGIONAL INDICATOR SYMBOL LETTER Z -@~ ! @@ 1F200 Enclosed Ideographic Supplement 1F2FF @ Squared hiragana from ARIB STD B24 1F200 SQUARE HIRAGANA HOKA @@ -44435,8 +45846,6 @@ FFFF <not a character> 1F202 SQUARED KATAKANA SA = service sign x (circled katakana sa - 32DA) - ~ 1F202 FE0E text style - ~ 1F202 FE0F emoji style # <square> 30B5 @ Squared ideographs and kana from ARIB STD B24 1F210 SQUARED CJK UNIFIED IDEOGRAPH-624B @@ -44473,8 +45882,6 @@ FFFF <not a character> 1F21A SQUARED CJK UNIFIED IDEOGRAPH-7121 = free broadcasting service = non-existence sign - ~ 1F21A FE0E text style - ~ 1F21A FE0F emoji style # <square> 7121 1F21B SQUARED CJK UNIFIED IDEOGRAPH-6599 = pay broadcasting service @@ -44539,8 +45946,6 @@ FFFF <not a character> 1F22F SQUARED CJK UNIFIED IDEOGRAPH-6307 = designated hitter = reserved sign - ~ 1F22F FE0E text style - ~ 1F22F FE0F emoji style # <square> 6307 1F230 SQUARED CJK UNIFIED IDEOGRAPH-8D70 = runner @@ -44568,8 +45973,6 @@ FFFF <not a character> 1F237 SQUARED CJK UNIFIED IDEOGRAPH-6708 = monthly sign x (circled ideograph moon - 328A) - ~ 1F237 FE0E text style - ~ 1F237 FE0F emoji style # <square> 6708 1F238 SQUARED CJK UNIFIED IDEOGRAPH-7533 = application sign @@ -44618,7 +46021,28 @@ FFFF <not a character> 1F251 CIRCLED IDEOGRAPH ACCEPT = accept sign # <circle> 53EF -@~ ! +@ Symbols for Chinese folk religion +1F260 ROUNDED SYMBOL FOR FU + * luck + x 798F +1F261 ROUNDED SYMBOL FOR LU + * prosperity + x 797F + x 7984 +1F262 ROUNDED SYMBOL FOR SHOU + * longevity + x 58FD + x 5BFF +1F263 ROUNDED SYMBOL FOR XI + * happiness + x 559C +1F264 ROUNDED SYMBOL FOR SHUANGXI + * double happiness, love and marriage + x 56CD +1F265 ROUNDED SYMBOL FOR CAI + * wealth + x 8CA1 + x 8D22 @@ 1F300 Miscellaneous Symbols and Pictographs 1F5FF @ Weather, landscape, and sky symbols 1F300 CYCLONE @@ -44635,6 +46059,7 @@ FFFF <not a character> 1F308 RAINBOW 1F309 BRIDGE AT NIGHT 1F30A WATER WAVE + = tsunami, tidal wave 1F30B VOLCANO 1F30C MILKY WAY @ Globe symbols @@ -44672,8 +46097,6 @@ FFFF <not a character> @ Weather symbols 1F321 THERMOMETER = temperature, warm - ~ 1F321 FE0E text style - ~ 1F321 FE0F emoji style 1F322 BLACK DROPLET = droplet x (droplet - 1F4A7) @@ -44683,41 +46106,23 @@ FFFF <not a character> 1F324 WHITE SUN WITH SMALL CLOUD = mostly sunny x (sun behind cloud - 26C5) - ~ 1F324 FE0E text style - ~ 1F324 FE0F emoji style 1F325 WHITE SUN BEHIND CLOUD = mostly cloudy - ~ 1F325 FE0E text style - ~ 1F325 FE0F emoji style 1F326 WHITE SUN BEHIND CLOUD WITH RAIN = showers - ~ 1F326 FE0E text style - ~ 1F326 FE0F emoji style 1F327 CLOUD WITH RAIN = rain - ~ 1F327 FE0E text style - ~ 1F327 FE0F emoji style 1F328 CLOUD WITH SNOW = snow, snow showers - ~ 1F328 FE0E text style - ~ 1F328 FE0F emoji style 1F329 CLOUD WITH LIGHTNING = lightning, thunderstorm x (thunder cloud and rain - 26C8) - ~ 1F329 FE0E text style - ~ 1F329 FE0F emoji style 1F32A CLOUD WITH TORNADO = tornado, twister - ~ 1F32A FE0E text style - ~ 1F32A FE0F emoji style 1F32B FOG x (foggy - 1F301) - ~ 1F32B FE0E text style - ~ 1F32B FE0F emoji style 1F32C WIND BLOWING FACE = wind - ~ 1F32C FE0E text style - ~ 1F32C FE0F emoji style @ Food symbols 1F32D HOT DOG 1F32E TACO @@ -44734,8 +46139,6 @@ FFFF <not a character> x (desert - 1F3DC) 1F336 HOT PEPPER = hot, spicy - ~ 1F336 FE0E text style - ~ 1F336 FE0F emoji style 1F337 TULIP x (flower - 2698) 1F338 CHERRY BLOSSOM @@ -44838,8 +46241,6 @@ FFFF <not a character> 1F37D FORK AND KNIFE WITH PLATE = dining x (fork and knife - 1F374) - ~ 1F37D FE0E text style - ~ 1F37D FE0F emoji style @ Beverage and food symbols 1F37E BOTTLE WITH POPPING CORK 1F37F POPCORN @@ -44885,28 +46286,18 @@ FFFF <not a character> = occasion x (bouquet - 1F490) 1F396 MILITARY MEDAL - ~ 1F396 FE0E text style - ~ 1F396 FE0F emoji style 1F397 REMINDER RIBBON - ~ 1F397 FE0E text style - ~ 1F397 FE0F emoji style @ Musical symbols 1F398 MUSICAL KEYBOARD WITH JACKS - = midi, midi keyboard + = midi, midi keyboard, master keyboard with plugs x (musical keyboard - 1F3B9) 1F399 STUDIO MICROPHONE = microphone x (microphone - 1F3A4) - ~ 1F399 FE0E text style - ~ 1F399 FE0F emoji style 1F39A LEVEL SLIDER = level control - ~ 1F39A FE0E text style - ~ 1F39A FE0F emoji style 1F39B CONTROL KNOBS = audio control - ~ 1F39B FE0E text style - ~ 1F39B FE0F emoji style 1F39C BEAMED ASCENDING MUSICAL NOTES = musical performance = music, musical background @@ -44919,13 +46310,9 @@ FFFF <not a character> 1F39E FILM FRAMES = film clip x (movie camera - 1F3A5) - ~ 1F39E FE0E text style - ~ 1F39E FE0F emoji style 1F39F ADMISSION TICKETS = ticket x (ticket - 1F3AB) - ~ 1F39F FE0E text style - ~ 1F39F FE0F emoji style 1F3A0 CAROUSEL HORSE = amusement park 1F3A1 FERRIS WHEEL @@ -44965,7 +46352,6 @@ FFFF <not a character> x (bullseye - 25CE) 1F3B0 SLOT MACHINE 1F3B1 BILLIARDS - * sometimes depicted as just an 8-ball 1F3B2 GAME DIE 1F3B3 BOWLING 1F3B4 FLOWER PLAYING CARDS @@ -44986,7 +46372,7 @@ FFFF <not a character> 1F3BC MUSICAL SCORE x (musical symbol g clef - 1D11E) @ Sport symbols -@+ See other sport symbols in the Miscelleaneous Symbols block. +@+ See other sport symbols in the Miscellaneous Symbols block. 1F3BD RUNNING SHIRT WITH SASH = ekiden (Japanese) * running shirt with separate sash signifies long-distance relay running @@ -45015,20 +46401,12 @@ FFFF <not a character> 1F3CA SWIMMER 1F3CB WEIGHT LIFTER = health - ~ 1F3CB FE0E text style - ~ 1F3CB FE0F emoji style 1F3CC GOLFER - ~ 1F3CC FE0E text style - ~ 1F3CC FE0F emoji style 1F3CD RACING MOTORCYCLE = motorcycle * may be depicted as an ordinary motorcycle, especially in emoji presentation - ~ 1F3CD FE0E text style - ~ 1F3CD FE0F emoji style 1F3CE RACING CAR = race car - ~ 1F3CE FE0E text style - ~ 1F3CE FE0F emoji style 1F3CF CRICKET BAT AND BALL 1F3D0 VOLLEYBALL 1F3D1 FIELD HOCKEY STICK AND BALL @@ -45037,58 +46415,33 @@ FFFF <not a character> @ Building and map symbols 1F3D4 SNOW CAPPED MOUNTAIN x (mountain - 26F0) - ~ 1F3D4 FE0E text style - ~ 1F3D4 FE0F emoji style 1F3D5 CAMPING = camping site x (tent - 26FA) - ~ 1F3D5 FE0E text style - ~ 1F3D5 FE0F emoji style 1F3D6 BEACH WITH UMBRELLA x (umbrella on ground - 26F1) - ~ 1F3D6 FE0E text style - ~ 1F3D6 FE0F emoji style 1F3D7 BUILDING CONSTRUCTION = under construction x (construction sign - 1F6A7) - ~ 1F3D7 FE0E text style - ~ 1F3D7 FE0F emoji style 1F3D8 HOUSE BUILDINGS = town x (house with garden - 1F3E1) - ~ 1F3D8 FE0E text style - ~ 1F3D8 FE0F emoji style 1F3D9 CITYSCAPE = skyline, city x (cityscape at dusk - 1F306) - ~ 1F3D9 FE0E text style - ~ 1F3D9 FE0F emoji style 1F3DA DERELICT HOUSE BUILDING = derelict site - ~ 1F3DA FE0E text style - ~ 1F3DA FE0F emoji style 1F3DB CLASSICAL BUILDING = public building - ~ 1F3DB FE0E text style - ~ 1F3DB FE0F emoji style 1F3DC DESERT - = desert x (cactus - 1F335) - ~ 1F3DC FE0E text style - ~ 1F3DC FE0F emoji style 1F3DD DESERT ISLAND = island x (palm tree - 1F334) - ~ 1F3DD FE0E text style - ~ 1F3DD FE0F emoji style 1F3DE NATIONAL PARK * by semantic extension has come to connote saving trees, and hence is also used as a symbol meaning "do not print this (email, document)" x (evergreen tree - 1F332) - ~ 1F3DE FE0E text style - ~ 1F3DE FE0F emoji style 1F3DF STADIUM - ~ 1F3DF FE0E text style - ~ 1F3DF FE0F emoji style 1F3E0 HOUSE BUILDING 1F3E1 HOUSE WITH GARDEN = home, house with yard @@ -45126,22 +46479,16 @@ FFFF <not a character> 1F3F3 WAVING WHITE FLAG = flag x (white flag - 2690) - ~ 1F3F3 FE0E text style - ~ 1F3F3 FE0F emoji style 1F3F4 WAVING BLACK FLAG @ Rosettes 1F3F5 ROSETTE x (white florette - 2740) - ~ 1F3F5 FE0E text style - ~ 1F3F5 FE0F emoji style 1F3F6 BLACK ROSETTE x (eight petalled outlined black florette - 2741) @ Miscellaneous symbol 1F3F7 LABEL = price, price tag x (bookmark - 1F516) - ~ 1F3F7 FE0E text style - ~ 1F3F7 FE0F emoji style @ Sport symbols 1F3F8 BADMINTON RACQUET AND SHUTTLECOCK 1F3F9 BOW AND ARROW @@ -45265,14 +46612,10 @@ FFFF <not a character> x (footprints - 1F463) 1F43F CHIPMUNK = animal, critter - ~ 1F43F FE0E text style - ~ 1F43F FE0F emoji style @ Facial parts symbols 1F440 EYES 1F441 EYE = sight - ~ 1F441 FE0E text style - ~ 1F441 FE0F emoji style 1F442 EAR 1F443 NOSE 1F444 MOUTH @@ -45333,8 +46676,10 @@ FFFF <not a character> = accounts 1F466 BOY 1F467 GIRL + x (child - 1F9D2) 1F468 MAN 1F469 WOMAN + x (adult - 1F9D1) 1F46A FAMILY = rated for family 1F46B MAN AND WOMAN HOLDING HANDS @@ -45352,6 +46697,7 @@ FFFF <not a character> * may be shown with or without a beard 1F474 OLDER MAN 1F475 OLDER WOMAN + x (older adult - 1F9D3) 1F476 BABY 1F477 CONSTRUCTION WORKER * the helmet may show a green cross, used as a safety reminder in Japan @@ -45364,6 +46710,7 @@ FFFF <not a character> 1F47B GHOST 1F47C BABY ANGEL 1F47D EXTRATERRESTRIAL ALIEN + x (flying saucer - 1F6F8) 1F47E ALIEN MONSTER x (robot face - 1F916) 1F47F IMP @@ -45375,7 +46722,6 @@ FFFF <not a character> 1F482 GUARDSMAN 1F483 DANCER * also used for "let's party" - * may be depicted as gender neutral x (man dancing - 1F57A) @ Personal care symbols 1F484 LIPSTICK @@ -45415,6 +46761,7 @@ FFFF <not a character> x (white heart suit - 2661) x (black heart suit - 2665) x (heavy black heart - 2764) + x (orange heart - 1F9E1) 1F49A GREEN HEART 1F49B YELLOW HEART 1F49C PURPLE HEART @@ -45442,7 +46789,7 @@ FFFF <not a character> = running dash, briffits 1F4A9 PILE OF POO = dog dirt - * may be depicted with a friendly face + * may be depicted with or without a friendly face 1F4AA FLEXED BICEPS = strong, muscled 1F4AB DIZZY SYMBOL @@ -45586,8 +46933,6 @@ FFFF <not a character> 1F4FD FILM PROJECTOR = movies x (cinema - 1F3A6) - ~ 1F4FD FE0E text style - ~ 1F4FD FE0F emoji style 1F4FE PORTABLE STEREO = stereo @ Religious symbol @@ -45740,12 +47085,8 @@ FFFF <not a character> 1F549 OM SYMBOL * generic symbol independent of Devanagari font x (devanagari om - 0950) - ~ 1F549 FE0E text style - ~ 1F549 FE0F emoji style 1F54A DOVE OF PEACE = peace - ~ 1F54A FE0E text style - ~ 1F54A FE0F emoji style 1F54B KAABA 1F54C MOSQUE 1F54D SYNAGOGUE @@ -45799,43 +47140,25 @@ FFFF <not a character> 1F56E BOOK x (open book - 1F4D6) 1F56F CANDLE - ~ 1F56F FE0E text style - ~ 1F56F FE0F emoji style 1F570 MANTELPIECE CLOCK = clock x (alarm clock - 23F0) - ~ 1F570 FE0E text style - ~ 1F570 FE0F emoji style 1F571 BLACK SKULL AND CROSSBONES x (skull and crossbones - 2620) 1F572 NO PIRACY 1F573 HOLE = portable hole - ~ 1F573 FE0E text style - ~ 1F573 FE0F emoji style 1F574 MAN IN BUSINESS SUIT LEVITATING = jump - ~ 1F574 FE0E text style - ~ 1F574 FE0F emoji style 1F575 SLEUTH OR SPY = investigate - ~ 1F575 FE0E text style - ~ 1F575 FE0F emoji style 1F576 DARK SUNGLASSES = cool - ~ 1F576 FE0E text style - ~ 1F576 FE0F emoji style @ Animal symbols 1F577 SPIDER - ~ 1F577 FE0E text style - ~ 1F577 FE0F emoji style 1F578 SPIDER WEB - ~ 1F578 FE0E text style - ~ 1F578 FE0F emoji style @ Game symbol 1F579 JOYSTICK - ~ 1F579 FE0E text style - ~ 1F579 FE0F emoji style @ Role symbol 1F57A MAN DANCING * forms a gender pair with 1F483 @@ -45872,8 +47195,6 @@ FFFF <not a character> 1F587 LINKED PAPERCLIPS = links x (paperclip - 1F4CE) - ~ 1F587 FE0E text style - ~ 1F587 FE0F emoji style 1F588 BLACK PUSHPIN = marker x (pushpin - 1F4CC) @@ -45882,21 +47203,13 @@ FFFF <not a character> x (lower right pencil - 270E) 1F58A LOWER LEFT BALLPOINT PEN = ballpoint pen - ~ 1F58A FE0E text style - ~ 1F58A FE0F emoji style 1F58B LOWER LEFT FOUNTAIN PEN = fountain pen x (white nib - 2711) - ~ 1F58B FE0E text style - ~ 1F58B FE0F emoji style 1F58C LOWER LEFT PAINTBRUSH = brush - ~ 1F58C FE0E text style - ~ 1F58C FE0F emoji style 1F58D LOWER LEFT CRAYON = crayon - ~ 1F58D FE0E text style - ~ 1F58D FE0F emoji style @ Hand symbols 1F58E LEFT WRITING HAND x (writing hand - 270D) @@ -45905,8 +47218,6 @@ FFFF <not a character> 1F590 RAISED HAND WITH FINGERS SPLAYED = halt x (raised hand - 270B) - ~ 1F590 FE0E text style - ~ 1F590 FE0F emoji style 1F591 REVERSED RAISED HAND WITH FINGERS SPLAYED 1F592 REVERSED THUMBS UP SIGN x (thumbs up sign - 1F44D) @@ -45947,16 +47258,12 @@ FFFF <not a character> @ Computer symbols 1F5A5 DESKTOP COMPUTER = tower computer - ~ 1F5A5 FE0E text style - ~ 1F5A5 FE0F emoji style 1F5A6 KEYBOARD AND MOUSE x (keyboard - 2328) 1F5A7 THREE NETWORKED COMPUTERS = computer network 1F5A8 PRINTER x (fax machine - 1F4E0) - ~ 1F5A8 FE0E text style - ~ 1F5A8 FE0F emoji style 1F5A9 POCKET CALCULATOR = calculator 1F5AA BLACK HARD SHELL FLOPPY DISK @@ -45971,12 +47278,8 @@ FFFF <not a character> 1F5AF ONE BUTTON MOUSE 1F5B0 TWO BUTTON MOUSE 1F5B1 THREE BUTTON MOUSE - ~ 1F5B1 FE0E text style - ~ 1F5B1 FE0F emoji style 1F5B2 TRACKBALL = ballpoint - ~ 1F5B2 FE0E text style - ~ 1F5B2 FE0F emoji style 1F5B3 OLD PERSONAL COMPUTER = personal computer x (personal computer - 1F4BB) @@ -45998,8 +47301,6 @@ FFFF <not a character> = graphic document 1F5BC FRAME WITH PICTURE = art - ~ 1F5BC FE0E text style - ~ 1F5BC FE0F emoji style 1F5BD FRAME WITH TILES = frames 1F5BE FRAME WITH AN X @@ -46014,15 +47315,9 @@ FFFF <not a character> 1F5C2 CARD INDEX DIVIDERS = index x (card index - 1F4C7) - ~ 1F5C2 FE0E text style - ~ 1F5C2 FE0F emoji style 1F5C3 CARD FILE BOX = archive - ~ 1F5C3 FE0E text style - ~ 1F5C3 FE0F emoji style 1F5C4 FILE CABINET - ~ 1F5C4 FE0E text style - ~ 1F5C4 FE0F emoji style 1F5C5 EMPTY NOTE 1F5C6 EMPTY NOTE PAGE 1F5C7 EMPTY NOTE PAD @@ -46039,18 +47334,12 @@ FFFF <not a character> 1F5D0 PAGES 1F5D1 WASTEBASKET = trashcan - ~ 1F5D1 FE0E text style - ~ 1F5D1 FE0F emoji style 1F5D2 SPIRAL NOTE PAD = note, empty calendar x (calendar - 1F4C5) - ~ 1F5D2 FE0E text style - ~ 1F5D2 FE0F emoji style 1F5D3 SPIRAL CALENDAR PAD = calendar, day 1 x (tear-off calendar - 1F4C6) - ~ 1F5D3 FE0E text style - ~ 1F5D3 FE0F emoji style 1F5D4 DESKTOP WINDOW 1F5D5 MINIMIZE 1F5D6 MAXIMIZE @@ -46066,19 +47355,13 @@ FFFF <not a character> 1F5DB DECREASE FONT SIZE SYMBOL 1F5DC COMPRESSION * symbol depicts a hand press with a box inside - ~ 1F5DC FE0E text style - ~ 1F5DC FE0F emoji style 1F5DD OLD KEY = encryption x (key - 1F511) - ~ 1F5DD FE0E text style - ~ 1F5DD FE0F emoji style @ Miscellaneous symbols 1F5DE ROLLED-UP NEWSPAPER = news x (newspaper - 1F4F0) - ~ 1F5DE FE0E text style - ~ 1F5DE FE0F emoji style 1F5DF PAGE WITH CIRCLED TEXT = classified 1F5E0 STOCK CHART @@ -46090,16 +47373,12 @@ FFFF <not a character> = rated for violence = hate x (hocho - 1F52A) - ~ 1F5E1 FE0E text style - ~ 1F5E1 FE0F emoji style 1F5E2 LIPS = rated for sex = kiss x (kiss mark - 1F48B) 1F5E3 SPEAKING HEAD IN SILHOUETTE = rated for strong language - ~ 1F5E3 FE0E text style - ~ 1F5E3 FE0F emoji style @ Sound symbols 1F5E4 THREE RAYS ABOVE 1F5E5 THREE RAYS BELOW @@ -46109,8 +47388,6 @@ FFFF <not a character> x (three lines converging left - 269F) @ Bubble symbols 1F5E8 LEFT SPEECH BUBBLE - ~ 1F5E8 FE0E text style - ~ 1F5E8 FE0F emoji style 1F5E9 RIGHT SPEECH BUBBLE 1F5EA TWO SPEECH BUBBLES = chat @@ -46123,8 +47400,6 @@ FFFF <not a character> = shout left 1F5EF RIGHT ANGER BUBBLE = shout right - ~ 1F5EF FE0E text style - ~ 1F5EF FE0F emoji style 1F5F0 MOOD BUBBLE = new x (collision symbol - 1F4A5) @@ -46137,8 +47412,6 @@ FFFF <not a character> 1F5F3 BALLOT BOX WITH BALLOT = vote x (ballot box with x - 2612) - ~ 1F5F3 FE0E text style - ~ 1F5F3 FE0F emoji style 1F5F4 BALLOT SCRIPT X = x mark x (ballot x - 2717) @@ -46154,8 +47427,6 @@ FFFF <not a character> x (ballot box with check - 2611) @ Map symbol 1F5FA WORLD MAP - ~ 1F5FA FE0E text style - ~ 1F5FA FE0F emoji style @ Cultural symbols 1F5FB MOUNT FUJI 1F5FC TOKYO TOWER @@ -46163,7 +47434,6 @@ FFFF <not a character> 1F5FE SILHOUETTE OF JAPAN 1F5FF MOYAI * Japanese stone statue like Moai on Easter Island -@~ ! @@ 1F600 Emoticons 1F64F @+ The emoticons have been organized by mouth shape to make it easier to locate the different characters in the code chart. @ Faces @@ -46466,22 +47736,14 @@ FFFF <not a character> @+ These symbols constitute a set along with 1F378 for lounge. 1F6CB COUCH AND LAMP = furniture, lifestyles - ~ 1F6CB FE0E text style - ~ 1F6CB FE0F emoji style 1F6CC SLEEPING ACCOMMODATION = hotel, guestrooms x (hotel - 1F3E8) 1F6CD SHOPPING BAGS = shopping - ~ 1F6CD FE0E text style - ~ 1F6CD FE0F emoji style 1F6CE BELLHOP BELL = reception, services - ~ 1F6CE FE0E text style - ~ 1F6CE FE0F emoji style 1F6CF BED - ~ 1F6CF FE0E text style - ~ 1F6CF FE0F emoji style @ Signage and other symbols 1F6D0 PLACE OF WORSHIP 1F6D1 OCTAGONAL SIGN @@ -46489,35 +47751,27 @@ FFFF <not a character> * may contain text indicating stop x (warning sign - 26A0) x (heavy white down-pointing triangle - 26DB) + x (horizontal black octagon - 2BC3) 1F6D2 SHOPPING TROLLEY = shopping cart +@ Map symbols +1F6D3 STUPA +1F6D4 PAGODA @ Miscellaneous symbols 1F6E0 HAMMER AND WRENCH = tools, repair facility x (hammer and pick - 2692) - ~ 1F6E0 FE0E text style - ~ 1F6E0 FE0F emoji style 1F6E1 SHIELD = US road interstate highway - ~ 1F6E1 FE0E text style - ~ 1F6E1 FE0F emoji style 1F6E2 OIL DRUM = commodities - ~ 1F6E2 FE0E text style - ~ 1F6E2 FE0F emoji style 1F6E3 MOTORWAY - ~ 1F6E3 FE0E text style - ~ 1F6E3 FE0F emoji style 1F6E4 RAILWAY TRACK = railroad - ~ 1F6E4 FE0E text style - ~ 1F6E4 FE0F emoji style @ Vehicles 1F6E5 MOTOR BOAT = boat x (speedboat - 1F6A4) - ~ 1F6E5 FE0E text style - ~ 1F6E5 FE0F emoji style 1F6E6 UP-POINTING MILITARY AIRPLANE = military airport 1F6E7 UP-POINTING AIRPLANE @@ -46526,16 +47780,12 @@ FFFF <not a character> 1F6E8 UP-POINTING SMALL AIRPLANE = airfield 1F6E9 SMALL AIRPLANE - ~ 1F6E9 FE0E text style - ~ 1F6E9 FE0F emoji style 1F6EA NORTHEAST-POINTING AIRPLANE 1F6EB AIRPLANE DEPARTURE = departures 1F6EC AIRPLANE ARRIVING = arrivals 1F6F0 SATELLITE - ~ 1F6F0 FE0E text style - ~ 1F6F0 FE0F emoji style 1F6F1 ONCOMING FIRE ENGINE = fire x (fire engine - 1F692) @@ -46546,12 +47796,14 @@ FFFF <not a character> 1F6F3 PASSENGER SHIP = cruise line vacation x (ship - 1F6A2) - ~ 1F6F3 FE0E text style - ~ 1F6F3 FE0F emoji style 1F6F4 SCOOTER 1F6F5 MOTOR SCOOTER 1F6F6 CANOE -@~ ! +1F6F7 SLED + = sledge, toboggan +1F6F8 FLYING SAUCER + = UFO + x (extraterrestrial alien - 1F47D) @@ 1F700 Alchemical Symbols 1F77F @ Symbols for Aristotelian elements 1F700 ALCHEMICAL SYMBOL FOR QUINTESSENCE @@ -46796,7 +48048,6 @@ FFFF <not a character> 1F785 MEDIUM BOLD WHITE CIRCLE x (medium white circle - 26AA) 1F786 BOLD WHITE CIRCLE - = very heavy circle 1F787 HEAVY WHITE CIRCLE 1F788 VERY HEAVY WHITE CIRCLE 1F789 EXTREMELY HEAVY WHITE CIRCLE @@ -47105,6 +48356,20 @@ FFFF <not a character> 1F8AC WHITE ARROW SHAFT WIDTH ONE 1F8AD WHITE ARROW SHAFT WIDTH TWO THIRDS @@ 1F900 Supplemental Symbols and Pictographs 1F9FF +@ Typicon symbols +1F900 CIRCLED CROSS FORMEE WITH FOUR DOTS +1F901 CIRCLED CROSS FORMEE WITH TWO DOTS +1F902 CIRCLED CROSS FORMEE + x (maltese cross - 2720) +1F903 LEFT HALF CIRCLE WITH FOUR DOTS +1F904 LEFT HALF CIRCLE WITH THREE DOTS +1F905 LEFT HALF CIRCLE WITH TWO DOTS +1F906 LEFT HALF CIRCLE WITH DOT +1F907 LEFT HALF CIRCLE +1F908 DOWNWARD FACING HOOK +1F909 DOWNWARD FACING NOTCHED HOOK +1F90A DOWNWARD FACING HOOK WITH DOT +1F90B DOWNWARD FACING NOTCHED HOOK WITH DOT @ Emoticon faces 1F910 ZIPPER-MOUTH FACE 1F911 MONEY-MOUTH FACE @@ -47123,6 +48388,8 @@ FFFF <not a character> 1F91C RIGHT-FACING FIST 1F91D HANDSHAKE 1F91E HAND WITH INDEX AND MIDDLE FINGERS CROSSED +1F91F I LOVE YOU HAND SIGN + * can be abbreviated ILY @ Emoticon faces 1F920 FACE WITH COWBOY HAT 1F921 CLOWN FACE @@ -47134,9 +48401,19 @@ FFFF <not a character> 1F926 FACE PALM = frustration, disbelief 1F927 SNEEZING FACE - = gesundheit + = Gesundheit +1F928 FACE WITH ONE EYEBROW RAISED +1F929 GRINNING FACE WITH STAR EYES +1F92A GRINNING FACE WITH ONE LARGE AND ONE SMALL EYE +1F92B FACE WITH FINGER COVERING CLOSED LIPS +1F92C SERIOUS FACE WITH SYMBOLS COVERING MOUTH +1F92D SMILING FACE WITH SMILING EYES AND HAND COVERING MOUTH +1F92E FACE WITH OPEN MOUTH VOMITING +1F92F SHOCKED FACE WITH EXPLODING HEAD @ Portrait and role symbols 1F930 PREGNANT WOMAN +1F931 BREAST-FEEDING +1F932 PALMS UP TOGETHER 1F933 SELFIE * typically used with face or human figure on the left 1F934 PRINCE @@ -47186,6 +48463,7 @@ FFFF <not a character> = boxing 1F94B MARTIAL ARTS UNIFORM = judo, karate, taekwondo +1F94C CURLING STONE @ Food symbols 1F950 CROISSANT 1F951 AVOCADO @@ -47210,6 +48488,27 @@ FFFF <not a character> 1F95E PANCAKES = hotcakes, crêpes, blini * sweet or savory +1F95F DUMPLING + = potsticker, gyooza, jiaozi, pierogi, empanada +1F960 FORTUNE COOKIE +1F961 TAKEOUT BOX + = take-away box, oyster pail +1F962 CHOPSTICKS + = kuaizi, hashi, jeotgarak +1F963 BOWL WITH SPOON + * can indicate breakfast, cereal, congee, etc. +1F964 CUP WITH STRAW + * can indicate soda, juice, etc. +1F965 COCONUT +1F966 BROCCOLI +1F967 PIE + * may be sweet or savory +1F968 PRETZEL + * can indicate twistiness, intricacy +1F969 CUT OF MEAT + = porkchop, chop, steak +1F96A SANDWICH +1F96B CANNED FOOD @ Animal symbols 1F980 CRAB * used for Cancer @@ -47235,8 +48534,61 @@ FFFF <not a character> 1F98F RHINOCEROS 1F990 SHRIMP 1F991 SQUID +1F992 GIRAFFE FACE +1F993 ZEBRA FACE +1F994 HEDGEHOG +1F995 SAUROPOD + * includes Brontosaurus, Diplodocus, Brachiosaurus +1F996 T-REX + = Tyrannosaurus rex +1F997 CRICKET @ Food symbol 1F9C0 CHEESE WEDGE +@ Portrait and role symbols +1F9D0 FACE WITH MONOCLE +1F9D1 ADULT + * no specified gender + x (man - 1F468) + x (woman - 1F469) +1F9D2 CHILD + * no specified gender + x (boy - 1F466) + x (girl - 1F467) +1F9D3 OLDER ADULT + * no specified gender + x (older man - 1F474) + x (older woman - 1F475) +1F9D4 BEARDED PERSON +1F9D5 PERSON WITH HEADSCARF + = woman's headscarf, hijab +1F9D6 PERSON IN STEAMY ROOM + = sauna, steam room +1F9D7 PERSON CLIMBING +1F9D8 PERSON IN LOTUS POSITION + = yoga, meditation +@ Fantasy beings +1F9D9 MAGE + = wizard, witch, sorcerer, sorceress +1F9DA FAIRY +1F9DB VAMPIRE +1F9DC MERPERSON + = mermaid, merman +1F9DD ELF +1F9DE GENIE +1F9DF ZOMBIE +@ Miscellaneous symbols +1F9E0 BRAIN +1F9E1 ORANGE HEART + x (blue heart - 1F499) + x (green heart - 1F49A) + x (yellow heart - 1F49B) + x (purple heart - 1F49C) +1F9E2 BILLED CAP + = baseball cap +1F9E3 SCARF +1F9E4 GLOVES +1F9E5 COAT +1F9E6 SOCKS @@ 1FF80 Unassigned 1FFFF @ Noncharacters @+ These codes are intended for process-internal uses. @@ -47246,6 +48598,7 @@ FFFF <not a character> @@ 2A700 CJK Unified Ideographs Extension C 2B734 @@ 2B740 CJK Unified Ideographs Extension D 2B81D @@ 2B820 CJK Unified Ideographs Extension E 2CEA1 +@@ 2CEB0 CJK Unified Ideographs Extension F 2EBE0 @@ 2F800 CJK Compatibility Ideographs Supplement 2FA1F @ Duplicate characters from CNS 11643-1992 2F800 CJK COMPATIBILITY IDEOGRAPH-2F800 @@ -48508,8 +49861,9 @@ E007E TAG TILDE @ Stateful tag terminator E007F CANCEL TAG @@ E0100 Variation Selectors Supplement E01EF -@+ These complete the set started at FE00 to FE0F -@ Variation selectors +@+ These complete the set started at FE00 to FE0F. +@ Ideographic-specific variation selectors +@+ For documentation about use of these with ideographs, see UTS #37, Unicode Ideographic Variation Database. E0100 VARIATION SELECTOR-17 * these are abbreviated VS17, and so on E0101 VARIATION SELECTOR-18 diff --git a/lib/unicore/NormalizationCorrections.txt b/lib/unicore/NormalizationCorrections.txt index 836d29c100..f7fc35e52c 100644 --- a/lib/unicore/NormalizationCorrections.txt +++ b/lib/unicore/NormalizationCorrections.txt @@ -1,6 +1,6 @@ -# NormalizationCorrections-9.0.0.txt -# Date: 2016-01-21, 22:00:00 GMT [KW, LI] -# © 2016 Unicode®, Inc. +# NormalizationCorrections-10.0.0.txt +# Date: 2017-04-13, 01:00:00 GMT [KW, LI] +# © 2017 Unicode®, Inc. # For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database @@ -27,7 +27,7 @@ # # Currently this list has exactly six entries in it, one for the # typo found and corrected in Corrigendum #3, and five for -# the typos and misidentifications found and corrected in +# the typos and misidentifications found and corrected in # Corrigendum #4. All efforts # will be made to keep the entries limited to just those fixes. # @@ -37,7 +37,7 @@ # Field 2: Corrected decomposition # Field 3: Version of Unicode for which the correction was # entered into UnicodeData.txt, in n.n.n format. -# Comment: Indicates the Unicode Corrigendum which documents +# Comment: Indicates the Unicode Corrigendum which documents # the correction # # For more information, see UAX #15, Unicode Normalization Forms. diff --git a/lib/unicore/PropList.txt b/lib/unicore/PropList.txt index a8c0da7135..9a2d0e4b1c 100644 --- a/lib/unicore/PropList.txt +++ b/lib/unicore/PropList.txt @@ -1,6 +1,6 @@ -# PropList-9.0.0.txt -# Date: 2016-06-01, 10:34:30 GMT -# © 2016 Unicode®, Inc. +# PropList-10.0.0.txt +# Date: 2017-03-10, 08:25:30 GMT +# © 2017 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html # @@ -199,6 +199,9 @@ FF64 ; Terminal_Punctuation # Po HALFWIDTH IDEOGRAPHIC COMMA 115C9..115D7 ; Terminal_Punctuation # Po [15] SIDDHAM END OF TEXT MARK..SIDDHAM SECTION MARK WITH CIRCLES AND FOUR ENCLOSURES 11641..11642 ; Terminal_Punctuation # Po [2] MODI DANDA..MODI DOUBLE DANDA 1173C..1173E ; Terminal_Punctuation # Po [3] AHOM SIGN SMALL SECTION..AHOM SIGN RULAI +11A42..11A43 ; Terminal_Punctuation # Po [2] ZANABAZAR SQUARE MARK SHAD..ZANABAZAR SQUARE MARK DOUBLE SHAD +11A9B..11A9C ; Terminal_Punctuation # Po [2] SOYOMBO MARK SHAD..SOYOMBO MARK DOUBLE SHAD +11AA1..11AA2 ; Terminal_Punctuation # Po [2] SOYOMBO TERMINAL MARK-1..SOYOMBO TERMINAL MARK-2 11C41..11C43 ; Terminal_Punctuation # Po [3] BHAIKSUKI DANDA..BHAIKSUKI WORD SEPARATOR 11C71 ; Terminal_Punctuation # Po MARCHEN MARK SHAD 12470..12474 ; Terminal_Punctuation # Po [5] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON @@ -209,7 +212,7 @@ FF64 ; Terminal_Punctuation # Po HALFWIDTH IDEOGRAPHIC COMMA 1BC9F ; Terminal_Punctuation # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1DA87..1DA8A ; Terminal_Punctuation # Po [4] SIGNWRITING COMMA..SIGNWRITING COLON -# Total code points: 246 +# Total code points: 252 # ================================================ @@ -471,6 +474,7 @@ FF41..FF46 ; Hex_Digit # L& [6] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L 0AC9 ; Other_Alphabetic # Mc GUJARATI VOWEL SIGN CANDRA O 0ACB..0ACC ; Other_Alphabetic # Mc [2] GUJARATI VOWEL SIGN O..GUJARATI VOWEL SIGN AU 0AE2..0AE3 ; Other_Alphabetic # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0AFA..0AFC ; Other_Alphabetic # Mn [3] GUJARATI SIGN SUKUN..GUJARATI SIGN MADDAH 0B01 ; Other_Alphabetic # Mn ORIYA SIGN CANDRABINDU 0B02..0B03 ; Other_Alphabetic # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA 0B3E ; Other_Alphabetic # Mc ORIYA VOWEL SIGN AA @@ -508,7 +512,7 @@ FF41..FF46 ; Hex_Digit # L& [6] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L 0CCC ; Other_Alphabetic # Mn KANNADA VOWEL SIGN AU 0CD5..0CD6 ; Other_Alphabetic # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK 0CE2..0CE3 ; Other_Alphabetic # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL -0D01 ; Other_Alphabetic # Mn MALAYALAM SIGN CANDRABINDU +0D00..0D01 ; Other_Alphabetic # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU 0D02..0D03 ; Other_Alphabetic # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA 0D3E..0D40 ; Other_Alphabetic # Mc [3] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN II 0D41..0D44 ; Other_Alphabetic # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR @@ -726,6 +730,17 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA 11722..11725 ; Other_Alphabetic # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU 11726 ; Other_Alphabetic # Mc AHOM VOWEL SIGN E 11727..1172A ; Other_Alphabetic # Mn [4] AHOM VOWEL SIGN AW..AHOM VOWEL SIGN AM +11A01..11A06 ; Other_Alphabetic # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O +11A07..11A08 ; Other_Alphabetic # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU +11A09..11A0A ; Other_Alphabetic # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A35..11A38 ; Other_Alphabetic # Mn [4] ZANABAZAR SQUARE SIGN CANDRABINDU..ZANABAZAR SQUARE SIGN ANUSVARA +11A39 ; Other_Alphabetic # Mc ZANABAZAR SQUARE SIGN VISARGA +11A3B..11A3E ; Other_Alphabetic # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A51..11A56 ; Other_Alphabetic # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A57..11A58 ; Other_Alphabetic # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU +11A59..11A5B ; Other_Alphabetic # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A8A..11A96 ; Other_Alphabetic # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A97 ; Other_Alphabetic # Mc SOYOMBO SIGN VISARGA 11C2F ; Other_Alphabetic # Mc BHAIKSUKI VOWEL SIGN AA 11C30..11C36 ; Other_Alphabetic # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L 11C38..11C3D ; Other_Alphabetic # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA @@ -737,6 +752,12 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA 11CB2..11CB3 ; Other_Alphabetic # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E 11CB4 ; Other_Alphabetic # Mc MARCHEN VOWEL SIGN O 11CB5..11CB6 ; Other_Alphabetic # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D31..11D36 ; Other_Alphabetic # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; Other_Alphabetic # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; Other_Alphabetic # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D41 ; Other_Alphabetic # Mn [3] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI SIGN VISARGA +11D43 ; Other_Alphabetic # Mn MASARAM GONDI SIGN CANDRA +11D47 ; Other_Alphabetic # Mn MASARAM GONDI RA-KARA 16B30..16B36 ; Other_Alphabetic # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM 16F51..16F7E ; Other_Alphabetic # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG 1BC9E ; Other_Alphabetic # Mn DUPLOYAN DOUBLE MARK @@ -750,7 +771,7 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA 1F150..1F169 ; Other_Alphabetic # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; Other_Alphabetic # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 1238 +# Total code points: 1300 # ================================================ @@ -759,18 +780,20 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA 3021..3029 ; Ideographic # Nl [9] HANGZHOU NUMERAL ONE..HANGZHOU NUMERAL NINE 3038..303A ; Ideographic # Nl [3] HANGZHOU NUMERAL TEN..HANGZHOU NUMERAL THIRTY 3400..4DB5 ; Ideographic # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 -4E00..9FD5 ; Ideographic # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5 +4E00..9FEA ; Ideographic # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA F900..FA6D ; Ideographic # Lo [366] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA6D FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COMPATIBILITY IDEOGRAPH-FAD9 17000..187EC ; Ideographic # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC 18800..18AF2 ; Ideographic # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755 +1B170..1B2FB ; Ideographic # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 20000..2A6D6 ; Ideographic # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6 2A700..2B734 ; Ideographic # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 2B740..2B81D ; Ideographic # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; Ideographic # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 +2CEB0..2EBE0 ; Ideographic # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; Ideographic # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D -# Total code points: 88284 +# Total code points: 96174 # ================================================ @@ -826,12 +849,14 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM 0A4D ; Diacritic # Mn GURMUKHI SIGN VIRAMA 0ABC ; Diacritic # Mn GUJARATI SIGN NUKTA 0ACD ; Diacritic # Mn GUJARATI SIGN VIRAMA +0AFD..0AFF ; Diacritic # Mn [3] GUJARATI SIGN THREE-DOT NUKTA ABOVE..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE 0B3C ; Diacritic # Mn ORIYA SIGN NUKTA 0B4D ; Diacritic # Mn ORIYA SIGN VIRAMA 0BCD ; Diacritic # Mn TAMIL SIGN VIRAMA 0C4D ; Diacritic # Mn TELUGU SIGN VIRAMA 0CBC ; Diacritic # Mn KANNADA SIGN NUKTA 0CCD ; Diacritic # Mn KANNADA SIGN VIRAMA +0D3B..0D3C ; Diacritic # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA 0D4D ; Diacritic # Mn MALAYALAM SIGN VIRAMA 0DCA ; Diacritic # Mn SINHALA SIGN AL-LAKUNA 0E47..0E4C ; Diacritic # Mn [6] THAI CHARACTER MAITAIKHU..THAI CHARACTER THANTHAKHAT @@ -871,10 +896,11 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM 1CE2..1CE8 ; Diacritic # Mn [7] VEDIC SIGN VISARGA SVARITA..VEDIC SIGN VISARGA ANUDATTA WITH TAIL 1CED ; Diacritic # Mn VEDIC SIGN TIRYAK 1CF4 ; Diacritic # Mn VEDIC TONE CANDRA ABOVE +1CF7 ; Diacritic # Mc VEDIC SIGN ATIKRAMA 1CF8..1CF9 ; Diacritic # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE 1D2C..1D6A ; Diacritic # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI 1DC4..1DCF ; Diacritic # Mn [12] COMBINING MACRON-ACUTE..COMBINING ZIGZAG BELOW -1DF5 ; Diacritic # Mn COMBINING UP TACK ABOVE +1DF5..1DF9 ; Diacritic # Mn [5] COMBINING UP TACK ABOVE..COMBINING WIDE INVERTED BRIDGE BELOW 1DFD..1DFF ; Diacritic # Mn [3] COMBINING ALMOST EQUAL TO BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 1FBD ; Diacritic # Sk GREEK KORONIS 1FBF..1FC1 ; Diacritic # Sk [3] GREEK PSILI..GREEK DIALYTIKA AND PERISPOMENI @@ -947,7 +973,12 @@ FFE3 ; Diacritic # Sk FULLWIDTH MACRON 116B6 ; Diacritic # Mc TAKRI SIGN VIRAMA 116B7 ; Diacritic # Mn TAKRI SIGN NUKTA 1172B ; Diacritic # Mn AHOM SIGN KILLER +11A34 ; Diacritic # Mn ZANABAZAR SQUARE SIGN VIRAMA +11A47 ; Diacritic # Mn ZANABAZAR SQUARE SUBJOINER +11A99 ; Diacritic # Mn SOYOMBO SUBJOINER 11C3F ; Diacritic # Mn BHAIKSUKI SIGN VIRAMA +11D42 ; Diacritic # Mn MASARAM GONDI SIGN NUKTA +11D44..11D45 ; Diacritic # Mn [2] MASARAM GONDI SIGN HALANTA..MASARAM GONDI VIRAMA 16AF0..16AF4 ; Diacritic # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16F8F..16F92 ; Diacritic # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW 16F93..16F9F ; Diacritic # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 @@ -960,7 +991,7 @@ FFE3 ; Diacritic # Sk FULLWIDTH MACRON 1E944..1E946 ; Diacritic # Mn [3] ADLAM ALIF LENGTHENER..ADLAM GEMINATION MARK 1E948..1E94A ; Diacritic # Mn [3] ADLAM CONSONANT MODIFIER..ADLAM NUKTA -# Total code points: 782 +# Total code points: 798 # ================================================ @@ -989,11 +1020,12 @@ AAF3..AAF4 ; Extender # Lm [2] MEETEI MAYEK SYLLABLE REPETITION MARK..MEETE FF70 ; Extender # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK 1135D ; Extender # Lo GRANTHA SIGN PLUTA 115C6..115C8 ; Extender # Po [3] SIDDHAM REPETITION MARK-1..SIDDHAM REPETITION MARK-3 +11A98 ; Extender # Mn SOYOMBO GEMINATION MARK 16B42..16B43 ; Extender # Lm [2] PAHAWH HMONG SIGN VOS NRUA..PAHAWH HMONG SIGN IB YAM -16FE0 ; Extender # Lm TANGUT ITERATION MARK +16FE0..16FE1 ; Extender # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK 1E944..1E946 ; Extender # Mn [3] ADLAM ALIF LENGTHENER..ADLAM GEMINATION MARK -# Total code points: 42 +# Total code points: 44 # ================================================ @@ -1105,7 +1137,7 @@ E0020..E007F ; Other_Grapheme_Extend # Cf [96] TAG SPACE..CANCEL TAG # ================================================ 3400..4DB5 ; Unified_Ideograph # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 -4E00..9FD5 ; Unified_Ideograph # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5 +4E00..9FEA ; Unified_Ideograph # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA FA0E..FA0F ; Unified_Ideograph # Lo [2] CJK COMPATIBILITY IDEOGRAPH-FA0E..CJK COMPATIBILITY IDEOGRAPH-FA0F FA11 ; Unified_Ideograph # Lo CJK COMPATIBILITY IDEOGRAPH-FA11 FA13..FA14 ; Unified_Ideograph # Lo [2] CJK COMPATIBILITY IDEOGRAPH-FA13..CJK COMPATIBILITY IDEOGRAPH-FA14 @@ -1117,8 +1149,9 @@ FA27..FA29 ; Unified_Ideograph # Lo [3] CJK COMPATIBILITY IDEOGRAPH-FA27..C 2A700..2B734 ; Unified_Ideograph # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 2B740..2B81D ; Unified_Ideograph # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; Unified_Ideograph # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 +2CEB0..2EBE0 ; Unified_Ideograph # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 -# Total code points: 80388 +# Total code points: 87882 # ================================================ @@ -1277,6 +1310,8 @@ FF61 ; Sentence_Terminal # Po HALFWIDTH IDEOGRAPHIC FULL STOP 115C9..115D7 ; Sentence_Terminal # Po [15] SIDDHAM END OF TEXT MARK..SIDDHAM SECTION MARK WITH CIRCLES AND FOUR ENCLOSURES 11641..11642 ; Sentence_Terminal # Po [2] MODI DANDA..MODI DOUBLE DANDA 1173C..1173E ; Sentence_Terminal # Po [3] AHOM SIGN SMALL SECTION..AHOM SIGN RULAI +11A42..11A43 ; Sentence_Terminal # Po [2] ZANABAZAR SQUARE MARK SHAD..ZANABAZAR SQUARE MARK DOUBLE SHAD +11A9B..11A9C ; Sentence_Terminal # Po [2] SOYOMBO MARK SHAD..SOYOMBO MARK DOUBLE SHAD 11C41..11C42 ; Sentence_Terminal # Po [2] BHAIKSUKI DANDA..BHAIKSUKI DOUBLE DANDA 16A6E..16A6F ; Sentence_Terminal # Po [2] MRO DANDA..MRO DOUBLE DANDA 16AF5 ; Sentence_Terminal # Po BASSA VAH FULL STOP @@ -1285,7 +1320,7 @@ FF61 ; Sentence_Terminal # Po HALFWIDTH IDEOGRAPHIC FULL STOP 1BC9F ; Sentence_Terminal # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1DA88 ; Sentence_Terminal # Po SIGNWRITING FULL STOP -# Total code points: 124 +# Total code points: 128 # ================================================ @@ -1402,9 +1437,7 @@ E0100..E01EF ; Variation_Selector # Mn [240] VARIATION SELECTOR-17..VARIATION S 239B..23B3 ; Pattern_Syntax # Sm [25] LEFT PARENTHESIS UPPER HOOK..SUMMATION BOTTOM 23B4..23DB ; Pattern_Syntax # So [40] TOP SQUARE BRACKET..FUSE 23DC..23E1 ; Pattern_Syntax # Sm [6] TOP PARENTHESIS..BOTTOM TORTOISE SHELL BRACKET -23E2..23FE ; Pattern_Syntax # So [29] WHITE TRAPEZIUM..POWER SLEEP SYMBOL -23FF ; Pattern_Syntax # Cn <reserved-23FF> -2400..2426 ; Pattern_Syntax # So [39] SYMBOL FOR NULL..SYMBOL FOR SUBSTITUTE FORM TWO +23E2..2426 ; Pattern_Syntax # So [69] WHITE TRAPEZIUM..SYMBOL FOR SUBSTITUTE FORM TWO 2427..243F ; Pattern_Syntax # Cn [25] <reserved-2427>..<reserved-243F> 2440..244A ; Pattern_Syntax # So [11] OCR HOOK..OCR DOUBLE BACKSLASH 244B..245F ; Pattern_Syntax # Cn [21] <reserved-244B>..<reserved-245F> @@ -1492,8 +1525,8 @@ E0100..E01EF ; Variation_Selector # Mn [240] VARIATION SELECTOR-17..VARIATION S 2BBA..2BBC ; Pattern_Syntax # Cn [3] <reserved-2BBA>..<reserved-2BBC> 2BBD..2BC8 ; Pattern_Syntax # So [12] BALLOT BOX WITH LIGHT X..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED 2BC9 ; Pattern_Syntax # Cn <reserved-2BC9> -2BCA..2BD1 ; Pattern_Syntax # So [8] TOP HALF BLACK CIRCLE..UNCERTAINTY SIGN -2BD2..2BEB ; Pattern_Syntax # Cn [26] <reserved-2BD2>..<reserved-2BEB> +2BCA..2BD2 ; Pattern_Syntax # So [9] TOP HALF BLACK CIRCLE..GROUP MARK +2BD3..2BEB ; Pattern_Syntax # Cn [25] <reserved-2BD3>..<reserved-2BEB> 2BEC..2BEF ; Pattern_Syntax # So [4] LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS..DOWNWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS 2BF0..2BFF ; Pattern_Syntax # Cn [16] <reserved-2BF0>..<reserved-2BFF> 2E00..2E01 ; Pattern_Syntax # Po [2] RIGHT ANGLE SUBSTITUTION MARKER..RIGHT ANGLE DOTTED SUBSTITUTION MARKER @@ -1533,8 +1566,8 @@ E0100..E01EF ; Variation_Selector # Mn [240] VARIATION SELECTOR-17..VARIATION S 2E40 ; Pattern_Syntax # Pd DOUBLE HYPHEN 2E41 ; Pattern_Syntax # Po REVERSED COMMA 2E42 ; Pattern_Syntax # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK -2E43..2E44 ; Pattern_Syntax # Po [2] DASH WITH LEFT UPTURN..DOUBLE SUSPENSION MARK -2E45..2E7F ; Pattern_Syntax # Cn [59] <reserved-2E45>..<reserved-2E7F> +2E43..2E49 ; Pattern_Syntax # Po [7] DASH WITH LEFT UPTURN..DOUBLE STACKED COMMA +2E4A..2E7F ; Pattern_Syntax # Cn [54] <reserved-2E4A>..<reserved-2E7F> 3001..3003 ; Pattern_Syntax # Po [3] IDEOGRAPHIC COMMA..DITTO MARK 3008 ; Pattern_Syntax # Ps LEFT ANGLE BRACKET 3009 ; Pattern_Syntax # Pe RIGHT ANGLE BRACKET @@ -1576,4 +1609,10 @@ FE45..FE46 ; Pattern_Syntax # Po [2] SESAME DOT..WHITE SESAME DOT # Total code points: 10 +# ================================================ + +1F1E6..1F1FF ; Regional_Indicator # So [26] REGIONAL INDICATOR SYMBOL LETTER A..REGIONAL INDICATOR SYMBOL LETTER Z + +# Total code points: 26 + # EOF diff --git a/lib/unicore/PropValueAliases.txt b/lib/unicore/PropValueAliases.txt index f56ab59a1a..e9b3548cac 100644 --- a/lib/unicore/PropValueAliases.txt +++ b/lib/unicore/PropValueAliases.txt @@ -1,6 +1,6 @@ -# PropertyValueAliases-9.0.0.txt -# Date: 2016-03-02, 18:55:05 GMT -# © 2016 Unicode®, Inc. +# PropertyValueAliases-10.0.0.txt +# Date: 2017-05-17, 08:45:34 GMT +# © 2017 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html # @@ -80,6 +80,7 @@ age; 6.3 ; V6_3 age; 7.0 ; V7_0 age; 8.0 ; V8_0 age; 9.0 ; V9_0 +age; 10.0 ; V10_0 age; NA ; Unassigned # Alphabetic (Alpha) @@ -191,6 +192,7 @@ blk; CJK_Ext_B ; CJK_Unified_Ideographs_Extension_B blk; CJK_Ext_C ; CJK_Unified_Ideographs_Extension_C blk; CJK_Ext_D ; CJK_Unified_Ideographs_Extension_D blk; CJK_Ext_E ; CJK_Unified_Ideographs_Extension_E +blk; CJK_Ext_F ; CJK_Unified_Ideographs_Extension_F blk; CJK_Radicals_Sup ; CJK_Radicals_Supplement blk; CJK_Strokes ; CJK_Strokes blk; CJK_Symbols ; CJK_Symbols_And_Punctuation @@ -263,6 +265,7 @@ blk; Jamo_Ext_A ; Hangul_Jamo_Extended_A blk; Jamo_Ext_B ; Hangul_Jamo_Extended_B blk; Javanese ; Javanese blk; Kaithi ; Kaithi +blk; Kana_Ext_A ; Kana_Extended_A blk; Kana_Sup ; Kana_Supplement blk; Kanbun ; Kanbun blk; Kangxi ; Kangxi_Radicals @@ -299,6 +302,7 @@ blk; Malayalam ; Malayalam blk; Mandaic ; Mandaic blk; Manichaean ; Manichaean blk; Marchen ; Marchen +blk; Masaram_Gondi ; Masaram_Gondi blk; Math_Alphanum ; Mathematical_Alphanumeric_Symbols blk; Math_Operators ; Mathematical_Operators blk; Meetei_Mayek ; Meetei_Mayek @@ -330,6 +334,7 @@ blk; New_Tai_Lue ; New_Tai_Lue blk; Newa ; Newa blk; NKo ; NKo blk; Number_Forms ; Number_Forms +blk; Nushu ; Nushu blk; OCR ; Optical_Character_Recognition blk; Ogham ; Ogham blk; Ol_Chiki ; Ol_Chiki @@ -369,6 +374,7 @@ blk; Sinhala ; Sinhala blk; Sinhala_Archaic_Numbers ; Sinhala_Archaic_Numbers blk; Small_Forms ; Small_Form_Variants blk; Sora_Sompeng ; Sora_Sompeng +blk; Soyombo ; Soyombo blk; Specials ; Specials blk; Sundanese ; Sundanese blk; Sundanese_Sup ; Sundanese_Supplement @@ -384,6 +390,7 @@ blk; Super_And_Sub ; Superscripts_And_Subscripts blk; Sutton_SignWriting ; Sutton_SignWriting blk; Syloti_Nagri ; Syloti_Nagri blk; Syriac ; Syriac +blk; Syriac_Sup ; Syriac_Supplement blk; Tagalog ; Tagalog blk; Tagbanwa ; Tagbanwa blk; Tags ; Tags @@ -414,6 +421,7 @@ blk; Warang_Citi ; Warang_Citi blk; Yi_Radicals ; Yi_Radicals blk; Yi_Syllables ; Yi_Syllables blk; Yijing ; Yijing_Hexagram_Symbols +blk; Zanabazar_Square ; Zanabazar_Square # Canonical_Combining_Class (ccc) @@ -741,6 +749,7 @@ Ideo; Y ; Yes ; T # Indic_Positional_Category (InPC) InPC; Bottom ; Bottom +InPC; Bottom_And_Left ; Bottom_And_Left InPC; Bottom_And_Right ; Bottom_And_Right InPC; Left ; Left InPC; Left_And_Right ; Left_And_Right @@ -885,6 +894,17 @@ jg ; Khaph ; Khaph jg ; Knotted_Heh ; Knotted_Heh jg ; Lam ; Lam jg ; Lamadh ; Lamadh +jg ; Malayalam_Bha ; Malayalam_Bha +jg ; Malayalam_Ja ; Malayalam_Ja +jg ; Malayalam_Lla ; Malayalam_Lla +jg ; Malayalam_Llla ; Malayalam_Llla +jg ; Malayalam_Nga ; Malayalam_Nga +jg ; Malayalam_Nna ; Malayalam_Nna +jg ; Malayalam_Nnna ; Malayalam_Nnna +jg ; Malayalam_Nya ; Malayalam_Nya +jg ; Malayalam_Ra ; Malayalam_Ra +jg ; Malayalam_Ssa ; Malayalam_Ssa +jg ; Malayalam_Tta ; Malayalam_Tta jg ; Manichaean_Aleph ; Manichaean_Aleph jg ; Manichaean_Ayin ; Manichaean_Ayin jg ; Manichaean_Beth ; Manichaean_Beth @@ -1135,6 +1155,11 @@ QMark; Y ; Yes ; T Radical; N ; No ; F ; False Radical; Y ; Yes ; T ; True +# Regional_Indicator (RI) + +RI ; N ; No ; F ; False +RI ; Y ; Yes ; T ; True + # Script (sc) sc ; Adlm ; Adlam @@ -1171,6 +1196,7 @@ sc ; Elba ; Elbasan sc ; Ethi ; Ethiopic sc ; Geor ; Georgian sc ; Glag ; Glagolitic +sc ; Gonm ; Masaram_Gondi sc ; Goth ; Gothic sc ; Gran ; Grantha sc ; Grek ; Greek @@ -1223,6 +1249,7 @@ sc ; Narb ; Old_North_Arabian sc ; Nbat ; Nabataean sc ; Newa ; Newa sc ; Nkoo ; Nko +sc ; Nshu ; Nushu sc ; Ogam ; Ogham sc ; Olck ; Ol_Chiki sc ; Orkh ; Old_Turkic @@ -1250,6 +1277,7 @@ sc ; Sidd ; Siddham sc ; Sind ; Khudawadi sc ; Sinh ; Sinhala sc ; Sora ; Sora_Sompeng +sc ; Soyo ; Soyombo sc ; Sund ; Sundanese sc ; Sylo ; Syloti_Nagri sc ; Syrc ; Syriac @@ -1273,6 +1301,7 @@ sc ; Wara ; Warang_Citi sc ; Xpeo ; Old_Persian sc ; Xsux ; Cuneiform sc ; Yiii ; Yi +sc ; Zanb ; Zanabazar_Square sc ; Zinh ; Inherited ; Qaai sc ; Zyyy ; Common sc ; Zzzz ; Unknown @@ -1357,6 +1386,13 @@ Upper; Y ; Yes ; T VS ; N ; No ; F ; False VS ; Y ; Yes ; T ; True +# Vertical_Orientation (vo) + +vo ; R ; Rotated +vo ; Tr ; Transformed_Rotated +vo ; Tu ; Transformed_Upright +vo ; U ; Upright + # White_Space (WSpace) WSpace; N ; No ; F ; False diff --git a/lib/unicore/PropertyAliases.txt b/lib/unicore/PropertyAliases.txt index 5284682a16..f2e26ba05e 100644 --- a/lib/unicore/PropertyAliases.txt +++ b/lib/unicore/PropertyAliases.txt @@ -1,6 +1,6 @@ -# PropertyAliases-9.0.0.txt -# Date: 2016-03-02, 18:55:05 GMT -# © 2016 Unicode®, Inc. +# PropertyAliases-10.0.0.txt +# Date: 2017-02-14, 04:26:16 GMT +# © 2017 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html # @@ -123,6 +123,7 @@ NFKC_QC ; NFKC_Quick_Check NFKD_QC ; NFKD_Quick_Check nt ; Numeric_Type SB ; Sentence_Break +vo ; Vertical_Orientation WB ; Word_Break # ================================================ @@ -175,6 +176,7 @@ Pat_WS ; Pattern_White_Space PCM ; Prepended_Concatenation_Mark QMark ; Quotation_Mark Radical ; Radical +RI ; Regional_Indicator SD ; Soft_Dotted STerm ; Sentence_Terminal Term ; Terminal_Punctuation @@ -190,6 +192,6 @@ XO_NFKC ; Expands_On_NFKC XO_NFKD ; Expands_On_NFKD # ================================================ -# Total: 118 +# Total: 120 # EOF diff --git a/lib/unicore/README.perl b/lib/unicore/README.perl index f892334d45..74caf48e02 100644 --- a/lib/unicore/README.perl +++ b/lib/unicore/README.perl @@ -61,6 +61,7 @@ mv extracted/DerivedJoiningType.txt extracted/DJoinType.txt mv extracted/DerivedLineBreak.txt extracted/DLineBreak.txt mv extracted/DerivedNumericType.txt extracted/DNumType.txt mv extracted/DerivedNumericValues.txt extracted/DNumValues.txt +mv extracted/DerivedName.txt extracted/DName.txt rmdir extracted 2>/dev/null # Will fail if non-empty, but if it is empty # was an early release that didn't have it. diff --git a/lib/unicore/ReadMe.txt b/lib/unicore/ReadMe.txt index 5da3522deb..1ba7a9d9da 100644 --- a/lib/unicore/ReadMe.txt +++ b/lib/unicore/ReadMe.txt @@ -1,7 +1,6 @@ # Unicode Character Database -# Date: 2016-06-20, 14:59:00 GMT [KW] -# © 2016 Unicode®, Inc. -# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# Date: 2017-06-18, 23:32:00 GMT [KW] +# © 2017 Unicode®, Inc. # For terms of use, see http://www.unicode.org/terms_of_use.html # # For documentation, see the following: @@ -9,7 +8,7 @@ # UAX #38, "Unicode Han Database (Unihan)" # UAX #44, "Unicode Character Database." # -# The UAXes can be accessed at http://www.unicode.org/versions/Unicode9.0.0/ +# The UAXes can be accessed at http://www.unicode.org/versions/Unicode10.0.0/ This directory contains the final data files -for the Unicode Character Database, for Version 9.0.0 of the Unicode Standard. +for the Unicode Character Database, for Version 10.0.0 of the Unicode Standard. diff --git a/lib/unicore/ScriptExtensions.txt b/lib/unicore/ScriptExtensions.txt index 4bf9a23c31..4dd151313a 100644 --- a/lib/unicore/ScriptExtensions.txt +++ b/lib/unicore/ScriptExtensions.txt @@ -1,6 +1,6 @@ -# ScriptExtensions-9.0.0.txt -# Date: 2016-06-01, 10:34:37 GMT -# © 2016 Unicode®, Inc. +# ScriptExtensions-10.0.0.txt +# Date: 2017-05-31, 01:07:00 GMT [RP] +# © 2017 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html # @@ -39,6 +39,14 @@ # ================================================ +# Script_Extensions=Beng + +1CF7 ; Beng # Mc VEDIC SIGN ATIKRAMA + +# Total code points: 1 + +# ================================================ + # Script_Extensions=Deva 1CD1 ; Deva # Mn VEDIC TONE SHARA @@ -256,10 +264,12 @@ A8F3 ; Deva Taml # Lo DEVANAGARI SIGN CANDRABINDU VIRAMA 0BB5 ; Gran Taml # Lo TAMIL LETTER VA 0BE6..0BEF ; Gran Taml # Nd [10] TAMIL DIGIT ZERO..TAMIL DIGIT NINE 0BF0..0BF2 ; Gran Taml # No [3] TAMIL NUMBER TEN..TAMIL NUMBER ONE THOUSAND +11301 ; Gran Taml # Mn GRANTHA SIGN CANDRABINDU 11303 ; Gran Taml # Mc GRANTHA SIGN VISARGA 1133C ; Gran Taml # Mn GRANTHA SIGN NUKTA -# Total code points: 17 + +# Total code points: 18 # ================================================ @@ -306,9 +316,10 @@ FF9E..FF9F ; Hira Kana # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFW 060C ; Arab Syrc Thaa # Po ARABIC COMMA 061B ; Arab Syrc Thaa # Po ARABIC SEMICOLON +061C ; Arab Syrc Thaa # Cf ARABIC LETTER MARK 061F ; Arab Syrc Thaa # Po ARABIC QUESTION MARK -# Total code points: 3 +# Total code points: 4 # ================================================ diff --git a/lib/unicore/Scripts.txt b/lib/unicore/Scripts.txt index 687994b58e..72319448e9 100644 --- a/lib/unicore/Scripts.txt +++ b/lib/unicore/Scripts.txt @@ -1,6 +1,6 @@ -# Scripts-9.0.0.txt -# Date: 2016-06-01, 10:34:37 GMT -# © 2016 Unicode®, Inc. +# Scripts-10.0.0.txt +# Date: 2017-03-11, 06:40:37 GMT +# © 2017 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html # @@ -93,7 +93,6 @@ 0605 ; Common # Cf ARABIC NUMBER MARK ABOVE 060C ; Common # Po ARABIC COMMA 061B ; Common # Po ARABIC SEMICOLON -061C ; Common # Cf ARABIC LETTER MARK 061F ; Common # Po ARABIC QUESTION MARK 0640 ; Common # Lm ARABIC TATWEEL 06DD ; Common # Cf ARABIC END OF AYAH @@ -112,6 +111,7 @@ 1CEE..1CF1 ; Common # Lo [4] VEDIC SIGN HEXIFORM LONG ANUSVARA..VEDIC SIGN ANUSVARA UBHAYATO MUKHA 1CF2..1CF3 ; Common # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA 1CF5..1CF6 ; Common # Lo [2] VEDIC SIGN JIHVAMULIYA..VEDIC SIGN UPADHMANIYA +1CF7 ; Common # Mc VEDIC SIGN ATIKRAMA 2000..200A ; Common # Zs [11] EN QUAD..HAIR SPACE 200B ; Common # Cf ZERO WIDTH SPACE 200E..200F ; Common # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK @@ -155,7 +155,7 @@ 208A..208C ; Common # Sm [3] SUBSCRIPT PLUS SIGN..SUBSCRIPT EQUALS SIGN 208D ; Common # Ps SUBSCRIPT LEFT PARENTHESIS 208E ; Common # Pe SUBSCRIPT RIGHT PARENTHESIS -20A0..20BE ; Common # Sc [31] EURO-CURRENCY SIGN..LARI SIGN +20A0..20BF ; Common # Sc [32] EURO-CURRENCY SIGN..BITCOIN SIGN 2100..2101 ; Common # So [2] ACCOUNT OF..ADDRESSED TO THE SUBJECT 2102 ; Common # L& DOUBLE-STRUCK CAPITAL C 2103..2106 ; Common # So [4] DEGREE CELSIUS..CADA UNA @@ -225,8 +225,7 @@ 239B..23B3 ; Common # Sm [25] LEFT PARENTHESIS UPPER HOOK..SUMMATION BOTTOM 23B4..23DB ; Common # So [40] TOP SQUARE BRACKET..FUSE 23DC..23E1 ; Common # Sm [6] TOP PARENTHESIS..BOTTOM TORTOISE SHELL BRACKET -23E2..23FE ; Common # So [29] WHITE TRAPEZIUM..POWER SLEEP SYMBOL -2400..2426 ; Common # So [39] SYMBOL FOR NULL..SYMBOL FOR SUBSTITUTE FORM TWO +23E2..2426 ; Common # So [69] WHITE TRAPEZIUM..SYMBOL FOR SUBSTITUTE FORM TWO 2440..244A ; Common # So [11] OCR HOOK..OCR DOUBLE BACKSLASH 2460..249B ; Common # No [60] CIRCLED DIGIT ONE..NUMBER TWENTY FULL STOP 249C..24E9 ; Common # So [78] PARENTHESIZED LATIN SMALL LETTER A..CIRCLED LATIN SMALL LETTER Z @@ -311,7 +310,7 @@ 2B76..2B95 ; Common # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW 2B98..2BB9 ; Common # So [34] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..UP ARROWHEAD IN A RECTANGLE BOX 2BBD..2BC8 ; Common # So [12] BALLOT BOX WITH LIGHT X..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED -2BCA..2BD1 ; Common # So [8] TOP HALF BLACK CIRCLE..UNCERTAINTY SIGN +2BCA..2BD2 ; Common # So [9] TOP HALF BLACK CIRCLE..GROUP MARK 2BEC..2BEF ; Common # So [4] LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS..DOWNWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS 2E00..2E01 ; Common # Po [2] RIGHT ANGLE SUBSTITUTION MARKER..RIGHT ANGLE DOTTED SUBSTITUTION MARKER 2E02 ; Common # Pi LEFT SUBSTITUTION BRACKET @@ -350,7 +349,7 @@ 2E40 ; Common # Pd DOUBLE HYPHEN 2E41 ; Common # Po REVERSED COMMA 2E42 ; Common # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK -2E43..2E44 ; Common # Po [2] DASH WITH LEFT UPTURN..DOUBLE SUSPENSION MARK +2E43..2E49 ; Common # Po [7] DASH WITH LEFT UPTURN..DOUBLE STACKED COMMA 2FF0..2FFB ; Common # So [12] IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT..IDEOGRAPHIC DESCRIPTION CHARACTER OVERLAID 3000 ; Common # Zs IDEOGRAPHIC SPACE 3001..3003 ; Common # Po [3] IDEOGRAPHIC COMMA..DITTO MARK @@ -581,11 +580,12 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR 1F210..1F23B ; Common # So [44] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-914D 1F240..1F248 ; Common # So [9] TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C..TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557 1F250..1F251 ; Common # So [2] CIRCLED IDEOGRAPH ADVANTAGE..CIRCLED IDEOGRAPH ACCEPT +1F260..1F265 ; Common # So [6] ROUNDED SYMBOL FOR FU..ROUNDED SYMBOL FOR CAI 1F300..1F3FA ; Common # So [251] CYCLONE..AMPHORA 1F3FB..1F3FF ; Common # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6 -1F400..1F6D2 ; Common # So [723] RAT..SHOPPING TROLLEY +1F400..1F6D4 ; Common # So [725] RAT..PAGODA 1F6E0..1F6EC ; Common # So [13] HAMMER AND WRENCH..AIRPLANE ARRIVING -1F6F0..1F6F6 ; Common # So [7] SATELLITE..CANOE +1F6F0..1F6F8 ; Common # So [9] SATELLITE..FLYING SAUCER 1F700..1F773 ; Common # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE 1F780..1F7D4 ; Common # So [85] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..HEAVY TWELVE POINTED PINWHEEL STAR 1F800..1F80B ; Common # So [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD @@ -593,18 +593,17 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR 1F850..1F859 ; Common # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW 1F860..1F887 ; Common # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW 1F890..1F8AD ; Common # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS -1F910..1F91E ; Common # So [15] ZIPPER-MOUTH FACE..HAND WITH INDEX AND MIDDLE FINGERS CROSSED -1F920..1F927 ; Common # So [8] FACE WITH COWBOY HAT..SNEEZING FACE -1F930 ; Common # So PREGNANT WOMAN -1F933..1F93E ; Common # So [12] SELFIE..HANDBALL -1F940..1F94B ; Common # So [12] WILTED FLOWER..MARTIAL ARTS UNIFORM -1F950..1F95E ; Common # So [15] CROISSANT..PANCAKES -1F980..1F991 ; Common # So [18] CRAB..SQUID +1F900..1F90B ; Common # So [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT +1F910..1F93E ; Common # So [47] ZIPPER-MOUTH FACE..HANDBALL +1F940..1F94C ; Common # So [13] WILTED FLOWER..CURLING STONE +1F950..1F96B ; Common # So [28] CROISSANT..CANNED FOOD +1F980..1F997 ; Common # So [24] CRAB..CRICKET 1F9C0 ; Common # So CHEESE WEDGE +1F9D0..1F9E6 ; Common # So [23] FACE WITH MONOCLE..SOCKS E0001 ; Common # Cf LANGUAGE TAG E0020..E007F ; Common # Cf [96] TAG SPACE..CANCEL TAG -# Total code points: 7279 +# Total code points: 7363 # ================================================ @@ -798,6 +797,7 @@ FB46..FB4F ; Hebrew # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATU 060D ; Arabic # Po ARABIC DATE SEPARATOR 060E..060F ; Arabic # So [2] ARABIC POETIC VERSE SIGN..ARABIC SIGN MISRA 0610..061A ; Arabic # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA +061C ; Arabic # Cf ARABIC LETTER MARK 061E ; Arabic # Po ARABIC TRIPLE DOT PUNCTUATION MARK 0620..063F ; Arabic # Lo [32] ARABIC LETTER KASHMIRI YEH..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE 0641..064A ; Arabic # Lo [10] ARABIC LETTER FEH..ARABIC LETTER YEH @@ -871,7 +871,7 @@ FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LA 1EEAB..1EEBB ; Arabic # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN 1EEF0..1EEF1 ; Arabic # Sm [2] ARABIC MATHEMATICAL OPERATOR MEEM WITH HAH WITH TATWEEL..ARABIC MATHEMATICAL OPERATOR HAH WITH DAL -# Total code points: 1279 +# Total code points: 1280 # ================================================ @@ -882,8 +882,9 @@ FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LA 0712..072F ; Syriac # Lo [30] SYRIAC LETTER BETH..SYRIAC LETTER PERSIAN DHALATH 0730..074A ; Syriac # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH 074D..074F ; Syriac # Lo [3] SYRIAC LETTER SOGDIAN ZHAIN..SYRIAC LETTER SOGDIAN FE +0860..086A ; Syriac # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA -# Total code points: 77 +# Total code points: 88 # ================================================ @@ -953,8 +954,10 @@ A8FD ; Devanagari # Lo DEVANAGARI JAIN OM 09F4..09F9 ; Bengali # No [6] BENGALI CURRENCY NUMERATOR ONE..BENGALI CURRENCY DENOMINATOR SIXTEEN 09FA ; Bengali # So BENGALI ISSHAR 09FB ; Bengali # Sc BENGALI GANDA MARK +09FC ; Bengali # Lo BENGALI LETTER VEDIC ANUSVARA +09FD ; Bengali # Po BENGALI ABBREVIATION SIGN -# Total code points: 93 +# Total code points: 95 # ================================================ @@ -1007,8 +1010,9 @@ A8FD ; Devanagari # Lo DEVANAGARI JAIN OM 0AF0 ; Gujarati # Po GUJARATI ABBREVIATION SIGN 0AF1 ; Gujarati # Sc GUJARATI RUPEE SIGN 0AF9 ; Gujarati # Lo GUJARATI LETTER ZHA +0AFA..0AFF ; Gujarati # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE -# Total code points: 85 +# Total code points: 91 # ================================================ @@ -1123,11 +1127,12 @@ A8FD ; Devanagari # Lo DEVANAGARI JAIN OM # ================================================ -0D01 ; Malayalam # Mn MALAYALAM SIGN CANDRABINDU +0D00..0D01 ; Malayalam # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU 0D02..0D03 ; Malayalam # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA 0D05..0D0C ; Malayalam # Lo [8] MALAYALAM LETTER A..MALAYALAM LETTER VOCALIC L 0D0E..0D10 ; Malayalam # Lo [3] MALAYALAM LETTER E..MALAYALAM LETTER AI 0D12..0D3A ; Malayalam # Lo [41] MALAYALAM LETTER O..MALAYALAM LETTER TTTA +0D3B..0D3C ; Malayalam # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA 0D3D ; Malayalam # Lo MALAYALAM SIGN AVAGRAHA 0D3E..0D40 ; Malayalam # Mc [3] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN II 0D41..0D44 ; Malayalam # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR @@ -1146,7 +1151,7 @@ A8FD ; Devanagari # Lo DEVANAGARI JAIN OM 0D79 ; Malayalam # So MALAYALAM DATE MARK 0D7A..0D7F ; Malayalam # Lo [6] MALAYALAM LETTER CHILLU NN..MALAYALAM LETTER CHILLU K -# Total code points: 114 +# Total code points: 117 # ================================================ @@ -1463,10 +1468,10 @@ AB70..ABBF ; Cherokee # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETT 3041..3096 ; Hiragana # Lo [86] HIRAGANA LETTER SMALL A..HIRAGANA LETTER SMALL KE 309D..309E ; Hiragana # Lm [2] HIRAGANA ITERATION MARK..HIRAGANA VOICED ITERATION MARK 309F ; Hiragana # Lo HIRAGANA DIGRAPH YORI -1B001 ; Hiragana # Lo HIRAGANA LETTER ARCHAIC YE +1B001..1B11E ; Hiragana # Lo [286] HIRAGANA LETTER ARCHAIC YE..HENTAIGANA LETTER N-MU-MO-2 1F200 ; Hiragana # So SQUARE HIRAGANA HOKA -# Total code points: 91 +# Total code points: 376 # ================================================ @@ -1485,10 +1490,10 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK # ================================================ 02EA..02EB ; Bopomofo # Sk [2] MODIFIER LETTER YIN DEPARTING TONE MARK..MODIFIER LETTER YANG DEPARTING TONE MARK -3105..312D ; Bopomofo # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH +3105..312E ; Bopomofo # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE 31A0..31BA ; Bopomofo # Lo [27] BOPOMOFO LETTER BU..BOPOMOFO LETTER ZY -# Total code points: 70 +# Total code points: 71 # ================================================ @@ -1501,16 +1506,17 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK 3038..303A ; Han # Nl [3] HANGZHOU NUMERAL TEN..HANGZHOU NUMERAL THIRTY 303B ; Han # Lm VERTICAL IDEOGRAPHIC ITERATION MARK 3400..4DB5 ; Han # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 -4E00..9FD5 ; Han # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5 +4E00..9FEA ; Han # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA F900..FA6D ; Han # Lo [366] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA6D FA70..FAD9 ; Han # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COMPATIBILITY IDEOGRAPH-FAD9 20000..2A6D6 ; Han # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6 2A700..2B734 ; Han # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 2B740..2B81D ; Han # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; Han # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 +2CEB0..2EBE0 ; Han # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; Han # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D -# Total code points: 81734 +# Total code points: 89228 # ================================================ @@ -1525,8 +1531,9 @@ A490..A4C6 ; Yi # So [55] YI RADICAL QOT..YI RADICAL KE 10300..1031F ; Old_Italic # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS 10320..10323 ; Old_Italic # No [4] OLD ITALIC NUMERAL ONE..OLD ITALIC NUMERAL FIFTY +1032D..1032F ; Old_Italic # Lo [3] OLD ITALIC LETTER YE..OLD ITALIC LETTER SOUTHERN TSE -# Total code points: 36 +# Total code points: 39 # ================================================ @@ -1558,7 +1565,7 @@ A490..A4C6 ; Yi # So [55] YI RADICAL QOT..YI RADICAL KE 1CED ; Inherited # Mn VEDIC SIGN TIRYAK 1CF4 ; Inherited # Mn VEDIC TONE CANDRA ABOVE 1CF8..1CF9 ; Inherited # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE -1DC0..1DF5 ; Inherited # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE +1DC0..1DF9 ; Inherited # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW 1DFB..1DFF ; Inherited # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 200C..200D ; Inherited # Cf [2] ZERO WIDTH NON-JOINER..ZERO WIDTH JOINER 20D0..20DC ; Inherited # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE @@ -1578,7 +1585,7 @@ FE20..FE2D ; Inherited # Mn [14] COMBINING LIGATURE LEFT HALF..COMBINING CON 1D1AA..1D1AD ; Inherited # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO E0100..E01EF ; Inherited # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 564 +# Total code points: 568 # ================================================ @@ -2629,4 +2636,58 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI # Total code points: 6881 +# ================================================ + +11D00..11D06 ; Masaram_Gondi # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E +11D08..11D09 ; Masaram_Gondi # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O +11D0B..11D30 ; Masaram_Gondi # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA +11D31..11D36 ; Masaram_Gondi # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; Masaram_Gondi # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; Masaram_Gondi # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45 ; Masaram_Gondi # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D46 ; Masaram_Gondi # Lo MASARAM GONDI REPHA +11D47 ; Masaram_Gondi # Mn MASARAM GONDI RA-KARA +11D50..11D59 ; Masaram_Gondi # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE + +# Total code points: 75 + +# ================================================ + +16FE1 ; Nushu # Lm NUSHU ITERATION MARK +1B170..1B2FB ; Nushu # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB + +# Total code points: 397 + +# ================================================ + +11A50 ; Soyombo # Lo SOYOMBO LETTER A +11A51..11A56 ; Soyombo # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A57..11A58 ; Soyombo # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU +11A59..11A5B ; Soyombo # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A5C..11A83 ; Soyombo # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA +11A86..11A89 ; Soyombo # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA +11A8A..11A96 ; Soyombo # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A97 ; Soyombo # Mc SOYOMBO SIGN VISARGA +11A98..11A99 ; Soyombo # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER +11A9A..11A9C ; Soyombo # Po [3] SOYOMBO MARK TSHEG..SOYOMBO MARK DOUBLE SHAD +11A9E..11AA2 ; Soyombo # Po [5] SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME..SOYOMBO TERMINAL MARK-2 + +# Total code points: 80 + +# ================================================ + +11A00 ; Zanabazar_Square # Lo ZANABAZAR SQUARE LETTER A +11A01..11A06 ; Zanabazar_Square # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O +11A07..11A08 ; Zanabazar_Square # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU +11A09..11A0A ; Zanabazar_Square # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A0B..11A32 ; Zanabazar_Square # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA +11A33..11A38 ; Zanabazar_Square # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A39 ; Zanabazar_Square # Mc ZANABAZAR SQUARE SIGN VISARGA +11A3A ; Zanabazar_Square # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA +11A3B..11A3E ; Zanabazar_Square # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A3F..11A46 ; Zanabazar_Square # Po [8] ZANABAZAR SQUARE INITIAL HEAD MARK..ZANABAZAR SQUARE CLOSING DOUBLE-LINED HEAD MARK +11A47 ; Zanabazar_Square # Mn ZANABAZAR SQUARE SUBJOINER + +# Total code points: 72 + # EOF diff --git a/lib/unicore/SpecialCasing.txt b/lib/unicore/SpecialCasing.txt index b23fa7f768..b9ba0d81c1 100644 --- a/lib/unicore/SpecialCasing.txt +++ b/lib/unicore/SpecialCasing.txt @@ -1,6 +1,6 @@ -# SpecialCasing-9.0.0.txt -# Date: 2016-03-02, 18:55:13 GMT -# © 2016 Unicode®, Inc. +# SpecialCasing-10.0.0.txt +# Date: 2017-04-14, 05:40:43 GMT +# © 2017 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html # @@ -197,7 +197,7 @@ FB17; FB17; 0544 056D; 0544 053D; # ARMENIAN SMALL LIGATURE MEN XEH # ================================================================================ # Conditional Mappings -# The remainder of this file provides conditional casing data used to produce +# The remainder of this file provides conditional casing data used to produce # full case mappings. # ================================================================================ # Language-Insensitive Mappings diff --git a/lib/unicore/StandardizedVariants.txt b/lib/unicore/StandardizedVariants.txt index b749b1e4c3..769c998dc5 100644 --- a/lib/unicore/StandardizedVariants.txt +++ b/lib/unicore/StandardizedVariants.txt @@ -1,6 +1,6 @@ -# StandardizedVariants-9.0.0.txt -# Date: 2015-11-20, 22:54:00 GMT [KW, LI, RP] -# © 1991-2015 Unicode®, Inc. +# StandardizedVariants-10.0.0.txt +# Date: 2017-05-02, 01:00:00 GMT [KW, LI, RP] +# © 2017 Unicode®, Inc. # For terms of use, see http://www.unicode.org/terms_of_use.html # # Specification of the variation sequences that are defined in the @@ -10,21 +10,30 @@ # Unicode Character Database. # # Standardized variation sequences are defined in this file. +# # Ideographic variation sequences are defined according to the registration # process specified in UTS #37, and are listed in the Ideographic -# Variation Database. Only those two types of variation sequences +# Variation Database. +# +# Emoji variation sequences are defined in the file +# emoji-variation-sequences.txt, documented in UTS #51, Unicode Emoji. +# +# Only those three types of variation sequences # are sanctioned for use by conformant implementations. # In all other cases, use of a variation selector character does # not change the visual appearance of the preceding base character # from what it would have had in the absence of the variation selector. # -# For more information on standardized variation sequences, -# see Section 23.4, Variation Selectors, -# in The Unicode Standard, Version 9.0. +# For more information on standardized variation sequences, +# see Section 23.4, Variation Selectors, +# in The Unicode Standard, Version 10.0. # # For more information on the Ideographic Variation Database, # see http://www.unicode.org/ivd/ # +# For more information on emoji variation sequences, +# see http://www.unicode.org/reports/tr51/ +# # Format: # Field 0: the variation sequence # Field 1: the description of the desired appearance @@ -37,7 +46,7 @@ 0030 FE00; short diagonal stroke form; # DIGIT ZERO 2205 FE00; zero with long diagonal stroke overlay form; # EMPTY SET -2229 FE00; with serifs; # INTERSECTION +2229 FE00; with serifs; # INTERSECTION 222A FE00; with serifs; # UNION 2268 FE00; with vertical stroke; # LESS-THAN BUT NOT EQUAL TO 2269 FE00; with vertical stroke; # GREATER-THAN BUT NOT EQUAL TO @@ -117,43 +126,41 @@ A868 FE00; phags-pa letter reversed shaping subjoined ya; # PHAGS-PA SUBJOINED L # Mongolian 1820 180B; second form; isolate medial final # MONGOLIAN LETTER A -1820 180C; third form; medial # MONGOLIAN LETTER A +1820 180C; third form; medial # MONGOLIAN LETTER A 1821 180B; second form; initial final # MONGOLIAN LETTER E 1822 180B; second form; medial # MONGOLIAN LETTER I -1823 180B; second form; medial final # MONGOLIAN LETTER O -1824 180B; second form; medial # MONGOLIAN LETTER U -1825 180B; second form; medial final # MONGOLIAN LETTER OE -1825 180C; third form; medial # MONGOLIAN LETTER OE -1826 180B; second form; isolate medial final # MONGOLIAN LETTER UE -1826 180C; third form; medial # MONGOLIAN LETTER UE +1823 180B; second form; medial final # MONGOLIAN LETTER O +1824 180B; second form; medial # MONGOLIAN LETTER U +1825 180B; second form; medial final # MONGOLIAN LETTER OE +1825 180C; third form; medial # MONGOLIAN LETTER OE +1826 180B; second form; isolate medial final # MONGOLIAN LETTER UE +1826 180C; third form; medial # MONGOLIAN LETTER UE 1828 180B; second form; initial medial # MONGOLIAN LETTER NA 1828 180C; third form; medial # MONGOLIAN LETTER NA -1828 180D; separate form; medial # MONGOLIAN LETTER NA -182A 180B; alternative form; final # MONGOLIAN LETTER BA -182C 180B; second form; initial medial # MONGOLIAN LETTER QA -182C 180B; feminine second form; isolate # MONGOLIAN LETTER QA +1828 180D; fourth form; medial # MONGOLIAN LETTER NA +182A 180B; second form; final # MONGOLIAN LETTER BA +182C 180B; second form; isolate initial medial # MONGOLIAN LETTER QA 182C 180C; third form; medial # MONGOLIAN LETTER QA 182C 180D; fourth form; medial # MONGOLIAN LETTER QA -182D 180B; second form; initial medial # MONGOLIAN LETTER GA -182D 180B; feminine form; final # MONGOLIAN LETTER GA +182D 180B; second form; initial medial final # MONGOLIAN LETTER GA 182D 180C; third form; medial # MONGOLIAN LETTER GA -182D 180D; feminine form; medial # MONGOLIAN LETTER GA +182D 180D; fourth form; medial # MONGOLIAN LETTER GA 1830 180B; second form; final # MONGOLIAN LETTER SA 1830 180C; third form; final # MONGOLIAN LETTER SA -1832 180B; second form; medial # MONGOLIAN LETTER TA +1832 180B; second form; medial # MONGOLIAN LETTER TA 1833 180B; second form; initial medial final # MONGOLIAN LETTER DA 1835 180B; second form; medial # MONGOLIAN LETTER JA -1836 180B; second form; initial medial # # MONGOLIAN LETTER YA +1836 180B; second form; initial medial # MONGOLIAN LETTER YA 1836 180C; third form; medial # MONGOLIAN LETTER YA 1838 180B; second form; final # MONGOLIAN LETTER WA 1844 180B; second form; medial # MONGOLIAN LETTER TODO E -1845 180B; second form; medial # MONGOLIAN LETTER TODO I +1845 180B; second form; medial # MONGOLIAN LETTER TODO I 1846 180B; second form; medial # MONGOLIAN LETTER TODO O 1847 180B; second form; isolate medial final # MONGOLIAN LETTER TODO U 1847 180C; third form; medial # MONGOLIAN LETTER TODO U 1848 180B; second form; medial # MONGOLIAN LETTER TODO OE 1849 180B; second form; isolate medial # MONGOLIAN LETTER TODO UE -184D 180B; feminine form; initial medial # MONGOLIAN LETTER TODO QA +184D 180B; second form; initial medial # MONGOLIAN LETTER TODO QA 184E 180B; second form; medial # MONGOLIAN LETTER TODO GA 185D 180B; second form; medial final # MONGOLIAN LETTER SIBE E 185E 180B; second form; medial final # MONGOLIAN LETTER SIBE I @@ -167,536 +174,18 @@ A868 FE00; phags-pa letter reversed shaping subjoined ya; # PHAGS-PA SUBJOINED L 1873 180B; second form; medial final # MONGOLIAN LETTER MANCHU I 1873 180C; third form; medial final # MONGOLIAN LETTER MANCHU I 1873 180D; fourth form; medial # MONGOLIAN LETTER MANCHU I -1874 180B; second form; medial # MONGOLIAN LETTER MANCHU KA -1874 180B; feminine first final form; final # MONGOLIAN LETTER MANCHU KA -1874 180C; feminine first medial form; medial # MONGOLIAN LETTER MANCHU KA -1874 180C; feminine second final form; final # MONGOLIAN LETTER MANCHU KA -1874 180D; feminine second medial form; medial # MONGOLIAN LETTER MANCHU KA +1874 180B; second form; medial final # MONGOLIAN LETTER MANCHU KA +1874 180C; third form; medial final # MONGOLIAN LETTER MANCHU KA +1874 180D; fourth form; medial # MONGOLIAN LETTER MANCHU KA 1876 180B; second form; initial medial # MONGOLIAN LETTER MANCHU FA 1880 180B; second form; # MONGOLIAN LETTER ALI GALI ANUSVARA ONE 1881 180B; second form; # MONGOLIAN LETTER ALI GALI VISARGA ONE 1887 180B; second form; isolate final # MONGOLIAN LETTER ALI GALI A 1887 180C; third form; final # MONGOLIAN LETTER ALI GALI A 1887 180D; fourth form; final # MONGOLIAN LETTER ALI GALI A -1888 180B; second form; final # MONGOLIAN LETTER ALI GALI I +1888 180B; second form; final # MONGOLIAN LETTER ALI GALI I 188A 180B; second form; initial medial # MONGOLIAN LETTER ALI GALI NGA -# Emoji variation sequences for use as part of keycap symbols - -0023 FE0E; text style; # NUMBER SIGN -0023 FE0F; emoji style; # NUMBER SIGN -002A FE0E; text style; # ASTERISK -002A FE0F; emoji style; # ASTERISK -0030 FE0E; text style; # DIGIT ZERO -0030 FE0F; emoji style; # DIGIT ZERO -0031 FE0E; text style; # DIGIT ONE -0031 FE0F; emoji style; # DIGIT ONE -0032 FE0E; text style; # DIGIT TWO -0032 FE0F; emoji style; # DIGIT TWO -0033 FE0E; text style; # DIGIT THREE -0033 FE0F; emoji style; # DIGIT THREE -0034 FE0E; text style; # DIGIT FOUR -0034 FE0F; emoji style; # DIGIT FOUR -0035 FE0E; text style; # DIGIT FIVE -0035 FE0F; emoji style; # DIGIT FIVE -0036 FE0E; text style; # DIGIT SIX -0036 FE0F; emoji style; # DIGIT SIX -0037 FE0E; text style; # DIGIT SEVEN -0037 FE0F; emoji style; # DIGIT SEVEN -0038 FE0E; text style; # DIGIT EIGHT -0038 FE0F; emoji style; # DIGIT EIGHT -0039 FE0E; text style; # DIGIT NINE -0039 FE0F; emoji style; # DIGIT NINE - -# Emoji variation sequences - -00A9 FE0E; text style; # COPYRIGHT SIGN -00A9 FE0F; emoji style; # COPYRIGHT SIGN -00AE FE0E; text style; # REGISTERED SIGN -00AE FE0F; emoji style; # REGISTERED SIGN -203C FE0E; text style; # DOUBLE EXCLAMATION MARK -203C FE0F; emoji style; # DOUBLE EXCLAMATION MARK -2049 FE0E; text style; # EXCLAMATION QUESTION MARK -2049 FE0F; emoji style; # EXCLAMATION QUESTION MARK -2122 FE0E; text style; # TRADE MARK SIGN -2122 FE0F; emoji style; # TRADE MARK SIGN -2139 FE0E; text style; # INFORMATION SOURCE -2139 FE0F; emoji style; # INFORMATION SOURCE -2194 FE0E; text style; # LEFT RIGHT ARROW -2194 FE0F; emoji style; # LEFT RIGHT ARROW -2195 FE0E; text style; # UP DOWN ARROW -2195 FE0F; emoji style; # UP DOWN ARROW -2196 FE0E; text style; # NORTH WEST ARROW -2196 FE0F; emoji style; # NORTH WEST ARROW -2197 FE0E; text style; # NORTH EAST ARROW -2197 FE0F; emoji style; # NORTH EAST ARROW -2198 FE0E; text style; # SOUTH EAST ARROW -2198 FE0F; emoji style; # SOUTH EAST ARROW -2199 FE0E; text style; # SOUTH WEST ARROW -2199 FE0F; emoji style; # SOUTH WEST ARROW -21A9 FE0E; text style; # LEFTWARDS ARROW WITH HOOK -21A9 FE0F; emoji style; # LEFTWARDS ARROW WITH HOOK -21AA FE0E; text style; # RIGHTWARDS ARROW WITH HOOK -21AA FE0F; emoji style; # RIGHTWARDS ARROW WITH HOOK -231A FE0E; text style; # WATCH -231A FE0F; emoji style; # WATCH -231B FE0E; text style; # HOURGLASS -231B FE0F; emoji style; # HOURGLASS -2328 FE0E; text style; # KEYBOARD -2328 FE0F; emoji style; # KEYBOARD -23CF FE0E; text style; # EJECT SYMBOL -23CF FE0F; emoji style; # EJECT SYMBOL -23ED FE0E; text style; # BLACK RIGHT-POINTING DOUBLE TRIANGLE WITH VERTICAL BAR -23ED FE0F; emoji style; # BLACK RIGHT-POINTING DOUBLE TRIANGLE WITH VERTICAL BAR -23EE FE0E; text style; # BLACK LEFT-POINTING DOUBLE TRIANGLE WITH VERTICAL BAR -23EE FE0F; emoji style; # BLACK LEFT-POINTING DOUBLE TRIANGLE WITH VERTICAL BAR -23EF FE0E; text style; # BLACK RIGHT-POINTING TRIANGLE WITH DOUBLE VERTICAL BAR -23EF FE0F; emoji style; # BLACK RIGHT-POINTING TRIANGLE WITH DOUBLE VERTICAL BAR -23F1 FE0E; text style; # STOPWATCH -23F1 FE0F; emoji style; # STOPWATCH -23F2 FE0E; text style; # TIMER CLOCK -23F2 FE0F; emoji style; # TIMER CLOCK -23F8 FE0E; text style; # DOUBLE VERTICAL BAR -23F8 FE0F; emoji style; # DOUBLE VERTICAL BAR -23F9 FE0E; text style; # BLACK SQUARE FOR STOP -23F9 FE0F; emoji style; # BLACK SQUARE FOR STOP -23FA FE0E; text style; # BLACK CIRCLE FOR RECORD -23FA FE0F; emoji style; # BLACK CIRCLE FOR RECORD -24C2 FE0E; text style; # CIRCLED LATIN CAPITAL LETTER M -24C2 FE0F; emoji style; # CIRCLED LATIN CAPITAL LETTER M -25AA FE0E; text style; # BLACK SMALL SQUARE -25AA FE0F; emoji style; # BLACK SMALL SQUARE -25AB FE0E; text style; # WHITE SMALL SQUARE -25AB FE0F; emoji style; # WHITE SMALL SQUARE -25B6 FE0E; text style; # BLACK RIGHT-POINTING TRIANGLE -25B6 FE0F; emoji style; # BLACK RIGHT-POINTING TRIANGLE -25C0 FE0E; text style; # BLACK LEFT-POINTING TRIANGLE -25C0 FE0F; emoji style; # BLACK LEFT-POINTING TRIANGLE -25FB FE0E; text style; # WHITE MEDIUM SQUARE -25FB FE0F; emoji style; # WHITE MEDIUM SQUARE -25FC FE0E; text style; # BLACK MEDIUM SQUARE -25FC FE0F; emoji style; # BLACK MEDIUM SQUARE -25FD FE0E; text style; # WHITE MEDIUM SMALL SQUARE -25FD FE0F; emoji style; # WHITE MEDIUM SMALL SQUARE -25FE FE0E; text style; # BLACK MEDIUM SMALL SQUARE -25FE FE0F; emoji style; # BLACK MEDIUM SMALL SQUARE -2600 FE0E; text style; # BLACK SUN WITH RAYS -2600 FE0F; emoji style; # BLACK SUN WITH RAYS -2601 FE0E; text style; # CLOUD -2601 FE0F; emoji style; # CLOUD -2602 FE0E; text style; # UMBRELLA -2602 FE0F; emoji style; # UMBRELLA -2603 FE0E; text style; # SNOWMAN -2603 FE0F; emoji style; # SNOWMAN -2604 FE0E; text style; # COMET -2604 FE0F; emoji style; # COMET -260E FE0E; text style; # BLACK TELEPHONE -260E FE0F; emoji style; # BLACK TELEPHONE -2611 FE0E; text style; # BALLOT BOX WITH CHECK -2611 FE0F; emoji style; # BALLOT BOX WITH CHECK -2614 FE0E; text style; # UMBRELLA WITH RAIN DROPS -2614 FE0F; emoji style; # UMBRELLA WITH RAIN DROPS -2615 FE0E; text style; # HOT BEVERAGE -2615 FE0F; emoji style; # HOT BEVERAGE -2618 FE0E; text style; # SHAMROCK -2618 FE0F; emoji style; # SHAMROCK -261D FE0E; text style; # WHITE UP POINTING INDEX -261D FE0F; emoji style; # WHITE UP POINTING INDEX -2620 FE0E; text style; # SKULL AND CROSSBONES -2620 FE0F; emoji style; # SKULL AND CROSSBONES -2622 FE0E; text style; # RADIOACTIVE SIGN -2622 FE0F; emoji style; # RADIOACTIVE SIGN -2623 FE0E; text style; # BIOHAZARD SIGN -2623 FE0F; emoji style; # BIOHAZARD SIGN -2626 FE0E; text style; # ORTHODOX CROSS -2626 FE0F; emoji style; # ORTHODOX CROSS -262A FE0E; text style; # STAR AND CRESCENT -262A FE0F; emoji style; # STAR AND CRESCENT -262E FE0E; text style; # PEACE SYMBOL -262E FE0F; emoji style; # PEACE SYMBOL -262F FE0E; text style; # YIN YANG -262F FE0F; emoji style; # YIN YANG -2638 FE0E; text style; # WHEEL OF DHARMA -2638 FE0F; emoji style; # WHEEL OF DHARMA -2639 FE0E; text style; # WHITE FROWNING FACE -2639 FE0F; emoji style; # WHITE FROWNING FACE -263A FE0E; text style; # WHITE SMILING FACE -263A FE0F; emoji style; # WHITE SMILING FACE -2648 FE0E; text style; # ARIES -2648 FE0F; emoji style; # ARIES -2649 FE0E; text style; # TAURUS -2649 FE0F; emoji style; # TAURUS -264A FE0E; text style; # GEMINI -264A FE0F; emoji style; # GEMINI -264B FE0E; text style; # CANCER -264B FE0F; emoji style; # CANCER -264C FE0E; text style; # LEO -264C FE0F; emoji style; # LEO -264D FE0E; text style; # VIRGO -264D FE0F; emoji style; # VIRGO -264E FE0E; text style; # LIBRA -264E FE0F; emoji style; # LIBRA -264F FE0E; text style; # SCORPIUS -264F FE0F; emoji style; # SCORPIUS -2650 FE0E; text style; # SAGITTARIUS -2650 FE0F; emoji style; # SAGITTARIUS -2651 FE0E; text style; # CAPRICORN -2651 FE0F; emoji style; # CAPRICORN -2652 FE0E; text style; # AQUARIUS -2652 FE0F; emoji style; # AQUARIUS -2653 FE0E; text style; # PISCES -2653 FE0F; emoji style; # PISCES -2660 FE0E; text style; # BLACK SPADE SUIT -2660 FE0F; emoji style; # BLACK SPADE SUIT -2663 FE0E; text style; # BLACK CLUB SUIT -2663 FE0F; emoji style; # BLACK CLUB SUIT -2665 FE0E; text style; # BLACK HEART SUIT -2665 FE0F; emoji style; # BLACK HEART SUIT -2666 FE0E; text style; # BLACK DIAMOND SUIT -2666 FE0F; emoji style; # BLACK DIAMOND SUIT -2668 FE0E; text style; # HOT SPRINGS -2668 FE0F; emoji style; # HOT SPRINGS -267B FE0E; text style; # BLACK UNIVERSAL RECYCLING SYMBOL -267B FE0F; emoji style; # BLACK UNIVERSAL RECYCLING SYMBOL -267F FE0E; text style; # WHEELCHAIR SYMBOL -267F FE0F; emoji style; # WHEELCHAIR SYMBOL -2692 FE0E; text style; # HAMMER AND PICK -2692 FE0F; emoji style; # HAMMER AND PICK -2693 FE0E; text style; # ANCHOR -2693 FE0F; emoji style; # ANCHOR -2694 FE0E; text style; # CROSSED SWORDS -2694 FE0F; emoji style; # CROSSED SWORDS -2696 FE0E; text style; # SCALES -2696 FE0F; emoji style; # SCALES -2697 FE0E; text style; # ALEMBIC -2697 FE0F; emoji style; # ALEMBIC -2699 FE0E; text style; # GEAR -2699 FE0F; emoji style; # GEAR -269B FE0E; text style; # ATOM SYMBOL -269B FE0F; emoji style; # ATOM SYMBOL -269C FE0E; text style; # FLEUR-DE-LIS -269C FE0F; emoji style; # FLEUR-DE-LIS -26A0 FE0E; text style; # WARNING SIGN -26A0 FE0F; emoji style; # WARNING SIGN -26A1 FE0E; text style; # HIGH VOLTAGE SIGN -26A1 FE0F; emoji style; # HIGH VOLTAGE SIGN -26AA FE0E; text style; # MEDIUM WHITE CIRCLE -26AA FE0F; emoji style; # MEDIUM WHITE CIRCLE -26AB FE0E; text style; # MEDIUM BLACK CIRCLE -26AB FE0F; emoji style; # MEDIUM BLACK CIRCLE -26B0 FE0E; text style; # COFFIN -26B0 FE0F; emoji style; # COFFIN -26B1 FE0E; text style; # FUNERAL URN -26B1 FE0F; emoji style; # FUNERAL URN -26BD FE0E; text style; # SOCCER BALL -26BD FE0F; emoji style; # SOCCER BALL -26BE FE0E; text style; # BASEBALL -26BE FE0F; emoji style; # BASEBALL -26C4 FE0E; text style; # SNOWMAN WITHOUT SNOW -26C4 FE0F; emoji style; # SNOWMAN WITHOUT SNOW -26C5 FE0E; text style; # SUN BEHIND CLOUD -26C5 FE0F; emoji style; # SUN BEHIND CLOUD -26C8 FE0E; text style; # THUNDER CLOUD AND RAIN -26C8 FE0F; emoji style; # THUNDER CLOUD AND RAIN -26CF FE0E; text style; # PICK -26CF FE0F; emoji style; # PICK -26D1 FE0E; text style; # HELMET WITH WHITE CROSS -26D1 FE0F; emoji style; # HELMET WITH WHITE CROSS -26D3 FE0E; text style; # CHAINS -26D3 FE0F; emoji style; # CHAINS -26D4 FE0E; text style; # NO ENTRY -26D4 FE0F; emoji style; # NO ENTRY -26E9 FE0E; text style; # SHINTO SHRINE -26E9 FE0F; emoji style; # SHINTO SHRINE -26EA FE0E; text style; # CHURCH -26EA FE0F; emoji style; # CHURCH -26F0 FE0E; text style; # MOUNTAIN -26F0 FE0F; emoji style; # MOUNTAIN -26F1 FE0E; text style; # UMBRELLA ON GROUND -26F1 FE0F; emoji style; # UMBRELLA ON GROUND -26F2 FE0E; text style; # FOUNTAIN -26F2 FE0F; emoji style; # FOUNTAIN -26F3 FE0E; text style; # FLAG IN HOLE -26F3 FE0F; emoji style; # FLAG IN HOLE -26F4 FE0E; text style; # FERRY -26F4 FE0F; emoji style; # FERRY -26F5 FE0E; text style; # SAILBOAT -26F5 FE0F; emoji style; # SAILBOAT -26F7 FE0E; text style; # SKIER -26F7 FE0F; emoji style; # SKIER -26F8 FE0E; text style; # ICE SKATE -26F8 FE0F; emoji style; # ICE SKATE -26F9 FE0E; text style; # PERSON WITH BALL -26F9 FE0F; emoji style; # PERSON WITH BALL -26FA FE0E; text style; # TENT -26FA FE0F; emoji style; # TENT -26FD FE0E; text style; # FUEL PUMP -26FD FE0F; emoji style; # FUEL PUMP -2702 FE0E; text style; # BLACK SCISSORS -2702 FE0F; emoji style; # BLACK SCISSORS -2708 FE0E; text style; # AIRPLANE -2708 FE0F; emoji style; # AIRPLANE -2709 FE0E; text style; # ENVELOPE -2709 FE0F; emoji style; # ENVELOPE -270C FE0E; text style; # VICTORY HAND -270C FE0F; emoji style; # VICTORY HAND -270D FE0E; text style; # WRITING HAND -270D FE0F; emoji style; # WRITING HAND -270F FE0E; text style; # PENCIL -270F FE0F; emoji style; # PENCIL -2712 FE0E; text style; # BLACK NIB -2712 FE0F; emoji style; # BLACK NIB -2714 FE0E; text style; # HEAVY CHECK MARK -2714 FE0F; emoji style; # HEAVY CHECK MARK -2716 FE0E; text style; # HEAVY MULTIPLICATION X -2716 FE0F; emoji style; # HEAVY MULTIPLICATION X -271D FE0E; text style; # LATIN CROSS -271D FE0F; emoji style; # LATIN CROSS -2721 FE0E; text style; # STAR OF DAVID -2721 FE0F; emoji style; # STAR OF DAVID -2733 FE0E; text style; # EIGHT SPOKED ASTERISK -2733 FE0F; emoji style; # EIGHT SPOKED ASTERISK -2734 FE0E; text style; # EIGHT POINTED BLACK STAR -2734 FE0F; emoji style; # EIGHT POINTED BLACK STAR -2744 FE0E; text style; # SNOWFLAKE -2744 FE0F; emoji style; # SNOWFLAKE -2747 FE0E; text style; # SPARKLE -2747 FE0F; emoji style; # SPARKLE -2757 FE0E; text style; # HEAVY EXCLAMATION MARK SYMBOL -2757 FE0F; emoji style; # HEAVY EXCLAMATION MARK SYMBOL -2763 FE0E; text style; # HEAVY HEART EXCLAMATION MARK ORNAMENT -2763 FE0F; emoji style; # HEAVY HEART EXCLAMATION MARK ORNAMENT -2764 FE0E; text style; # HEAVY BLACK HEART -2764 FE0F; emoji style; # HEAVY BLACK HEART -27A1 FE0E; text style; # BLACK RIGHTWARDS ARROW -27A1 FE0F; emoji style; # BLACK RIGHTWARDS ARROW -2934 FE0E; text style; # ARROW POINTING RIGHTWARDS THEN CURVING UPWARDS -2934 FE0F; emoji style; # ARROW POINTING RIGHTWARDS THEN CURVING UPWARDS -2935 FE0E; text style; # ARROW POINTING RIGHTWARDS THEN CURVING DOWNWARDS -2935 FE0F; emoji style; # ARROW POINTING RIGHTWARDS THEN CURVING DOWNWARDS -2B05 FE0E; text style; # LEFTWARDS BLACK ARROW -2B05 FE0F; emoji style; # LEFTWARDS BLACK ARROW -2B06 FE0E; text style; # UPWARDS BLACK ARROW -2B06 FE0F; emoji style; # UPWARDS BLACK ARROW -2B07 FE0E; text style; # DOWNWARDS BLACK ARROW -2B07 FE0F; emoji style; # DOWNWARDS BLACK ARROW -2B1B FE0E; text style; # BLACK LARGE SQUARE -2B1B FE0F; emoji style; # BLACK LARGE SQUARE -2B1C FE0E; text style; # WHITE LARGE SQUARE -2B1C FE0F; emoji style; # WHITE LARGE SQUARE -2B50 FE0E; text style; # WHITE MEDIUM STAR -2B50 FE0F; emoji style; # WHITE MEDIUM STAR -2B55 FE0E; text style; # HEAVY LARGE CIRCLE -2B55 FE0F; emoji style; # HEAVY LARGE CIRCLE -3030 FE0E; text style; # WAVY DASH -3030 FE0F; emoji style; # WAVY DASH -303D FE0E; text style; # PART ALTERNATION MARK -303D FE0F; emoji style; # PART ALTERNATION MARK -3297 FE0E; text style; # CIRCLED IDEOGRAPH CONGRATULATION -3297 FE0F; emoji style; # CIRCLED IDEOGRAPH CONGRATULATION -3299 FE0E; text style; # CIRCLED IDEOGRAPH SECRET -3299 FE0F; emoji style; # CIRCLED IDEOGRAPH SECRET -1F004 FE0E; text style; # MAHJONG TILE RED DRAGON -1F004 FE0F; emoji style; # MAHJONG TILE RED DRAGON -1F170 FE0E; text style; # NEGATIVE SQUARED LATIN CAPITAL LETTER A -1F170 FE0F; emoji style; # NEGATIVE SQUARED LATIN CAPITAL LETTER A -1F171 FE0E; text style; # NEGATIVE SQUARED LATIN CAPITAL LETTER B -1F171 FE0F; emoji style; # NEGATIVE SQUARED LATIN CAPITAL LETTER B -1F17E FE0E; text style; # NEGATIVE SQUARED LATIN CAPITAL LETTER O -1F17E FE0F; emoji style; # NEGATIVE SQUARED LATIN CAPITAL LETTER O -1F17F FE0E; text style; # NEGATIVE SQUARED LATIN CAPITAL LETTER P -1F17F FE0F; emoji style; # NEGATIVE SQUARED LATIN CAPITAL LETTER P -1F202 FE0E; text style; # SQUARED KATAKANA SA -1F202 FE0F; emoji style; # SQUARED KATAKANA SA -1F21A FE0E; text style; # SQUARED CJK UNIFIED IDEOGRAPH-7121 -1F21A FE0F; emoji style; # SQUARED CJK UNIFIED IDEOGRAPH-7121 -1F22F FE0E; text style; # SQUARED CJK UNIFIED IDEOGRAPH-6307 -1F22F FE0F; emoji style; # SQUARED CJK UNIFIED IDEOGRAPH-6307 -1F237 FE0E; text style; # SQUARED CJK UNIFIED IDEOGRAPH-6708 -1F237 FE0F; emoji style; # SQUARED CJK UNIFIED IDEOGRAPH-6708 -1F321 FE0E; text style; # THERMOMETER -1F321 FE0F; emoji style; # THERMOMETER -1F324 FE0E; text style; # WHITE SUN WITH SMALL CLOUD -1F324 FE0F; emoji style; # WHITE SUN WITH SMALL CLOUD -1F325 FE0E; text style; # WHITE SUN BEHIND CLOUD -1F325 FE0F; emoji style; # WHITE SUN BEHIND CLOUD -1F326 FE0E; text style; # WHITE SUN BEHIND CLOUD WITH RAIN -1F326 FE0F; emoji style; # WHITE SUN BEHIND CLOUD WITH RAIN -1F327 FE0E; text style; # CLOUD WITH RAIN -1F327 FE0F; emoji style; # CLOUD WITH RAIN -1F328 FE0E; text style; # CLOUD WITH SNOW -1F328 FE0F; emoji style; # CLOUD WITH SNOW -1F329 FE0E; text style; # CLOUD WITH LIGHTNING -1F329 FE0F; emoji style; # CLOUD WITH LIGHTNING -1F32A FE0E; text style; # CLOUD WITH TORNADO -1F32A FE0F; emoji style; # CLOUD WITH TORNADO -1F32B FE0E; text style; # FOG -1F32B FE0F; emoji style; # FOG -1F32C FE0E; text style; # WIND BLOWING FACE -1F32C FE0F; emoji style; # WIND BLOWING FACE -1F336 FE0E; text style; # HOT PEPPER -1F336 FE0F; emoji style; # HOT PEPPER -1F37D FE0E; text style; # FORK AND KNIFE WITH PLATE -1F37D FE0F; emoji style; # FORK AND KNIFE WITH PLATE -1F396 FE0E; text style; # MILITARY MEDAL -1F396 FE0F; emoji style; # MILITARY MEDAL -1F397 FE0E; text style; # REMINDER RIBBON -1F397 FE0F; emoji style; # REMINDER RIBBON -1F399 FE0E; text style; # STUDIO MICROPHONE -1F399 FE0F; emoji style; # STUDIO MICROPHONE -1F39A FE0E; text style; # LEVEL SLIDER -1F39A FE0F; emoji style; # LEVEL SLIDER -1F39B FE0E; text style; # CONTROL KNOBS -1F39B FE0F; emoji style; # CONTROL KNOBS -1F39E FE0E; text style; # FILM FRAMES -1F39E FE0F; emoji style; # FILM FRAMES -1F39F FE0E; text style; # ADMISSION TICKETS -1F39F FE0F; emoji style; # ADMISSION TICKETS -1F3CB FE0E; text style; # WEIGHT LIFTER -1F3CB FE0F; emoji style; # WEIGHT LIFTER -1F3CC FE0E; text style; # GOLFER -1F3CC FE0F; emoji style; # GOLFER -1F3CD FE0E; text style; # RACING MOTORCYCLE -1F3CD FE0F; emoji style; # RACING MOTORCYCLE -1F3CE FE0E; text style; # RACING CAR -1F3CE FE0F; emoji style; # RACING CAR -1F3D4 FE0E; text style; # SNOW CAPPED MOUNTAIN -1F3D4 FE0F; emoji style; # SNOW CAPPED MOUNTAIN -1F3D5 FE0E; text style; # CAMPING -1F3D5 FE0F; emoji style; # CAMPING -1F3D6 FE0E; text style; # BEACH WITH UMBRELLA -1F3D6 FE0F; emoji style; # BEACH WITH UMBRELLA -1F3D7 FE0E; text style; # BUILDING CONSTRUCTION -1F3D7 FE0F; emoji style; # BUILDING CONSTRUCTION -1F3D8 FE0E; text style; # HOUSE BUILDINGS -1F3D8 FE0F; emoji style; # HOUSE BUILDINGS -1F3D9 FE0E; text style; # CITYSCAPE -1F3D9 FE0F; emoji style; # CITYSCAPE -1F3DA FE0E; text style; # DERELICT HOUSE BUILDING -1F3DA FE0F; emoji style; # DERELICT HOUSE BUILDING -1F3DB FE0E; text style; # CLASSICAL BUILDING -1F3DB FE0F; emoji style; # CLASSICAL BUILDING -1F3DC FE0E; text style; # DESERT -1F3DC FE0F; emoji style; # DESERT -1F3DD FE0E; text style; # DESERT ISLAND -1F3DD FE0F; emoji style; # DESERT ISLAND -1F3DE FE0E; text style; # NATIONAL PARK -1F3DE FE0F; emoji style; # NATIONAL PARK -1F3DF FE0E; text style; # STADIUM -1F3DF FE0F; emoji style; # STADIUM -1F3F3 FE0E; text style; # WAVING WHITE FLAG -1F3F3 FE0F; emoji style; # WAVING WHITE FLAG -1F3F5 FE0E; text style; # ROSETTE -1F3F5 FE0F; emoji style; # ROSETTE -1F3F7 FE0E; text style; # LABEL -1F3F7 FE0F; emoji style; # LABEL -1F43F FE0E; text style; # CHIPMUNK -1F43F FE0F; emoji style; # CHIPMUNK -1F441 FE0E; text style; # EYE -1F441 FE0F; emoji style; # EYE -1F4FD FE0E; text style; # FILM PROJECTOR -1F4FD FE0F; emoji style; # FILM PROJECTOR -1F549 FE0E; text style; # OM SYMBOL -1F549 FE0F; emoji style; # OM SYMBOL -1F54A FE0E; text style; # DOVE OF PEACE -1F54A FE0F; emoji style; # DOVE OF PEACE -1F56F FE0E; text style; # CANDLE -1F56F FE0F; emoji style; # CANDLE -1F570 FE0E; text style; # MANTELPIECE CLOCK -1F570 FE0F; emoji style; # MANTELPIECE CLOCK -1F573 FE0E; text style; # HOLE -1F573 FE0F; emoji style; # HOLE -1F574 FE0E; text style; # MAN IN BUSINESS SUIT LEVITATING -1F574 FE0F; emoji style; # MAN IN BUSINESS SUIT LEVITATING -1F575 FE0E; text style; # SLEUTH OR SPY -1F575 FE0F; emoji style; # SLEUTH OR SPY -1F576 FE0E; text style; # DARK SUNGLASSES -1F576 FE0F; emoji style; # DARK SUNGLASSES -1F577 FE0E; text style; # SPIDER -1F577 FE0F; emoji style; # SPIDER -1F578 FE0E; text style; # SPIDER WEB -1F578 FE0F; emoji style; # SPIDER WEB -1F579 FE0E; text style; # JOYSTICK -1F579 FE0F; emoji style; # JOYSTICK -1F587 FE0E; text style; # LINKED PAPERCLIPS -1F587 FE0F; emoji style; # LINKED PAPERCLIPS -1F58A FE0E; text style; # LOWER LEFT BALLPOINT PEN -1F58A FE0F; emoji style; # LOWER LEFT BALLPOINT PEN -1F58B FE0E; text style; # LOWER LEFT FOUNTAIN PEN -1F58B FE0F; emoji style; # LOWER LEFT FOUNTAIN PEN -1F58C FE0E; text style; # LOWER LEFT PAINTBRUSH -1F58C FE0F; emoji style; # LOWER LEFT PAINTBRUSH -1F58D FE0E; text style; # LOWER LEFT CRAYON -1F58D FE0F; emoji style; # LOWER LEFT CRAYON -1F590 FE0E; text style; # RAISED HAND WITH FINGERS SPLAYED -1F590 FE0F; emoji style; # RAISED HAND WITH FINGERS SPLAYED -1F5A5 FE0E; text style; # DESKTOP COMPUTER -1F5A5 FE0F; emoji style; # DESKTOP COMPUTER -1F5A8 FE0E; text style; # PRINTER -1F5A8 FE0F; emoji style; # PRINTER -1F5B1 FE0E; text style; # THREE BUTTON MOUSE -1F5B1 FE0F; emoji style; # THREE BUTTON MOUSE -1F5B2 FE0E; text style; # TRACKBALL -1F5B2 FE0F; emoji style; # TRACKBALL -1F5BC FE0E; text style; # FRAME WITH PICTURE -1F5BC FE0F; emoji style; # FRAME WITH PICTURE -1F5C2 FE0E; text style; # CARD INDEX DIVIDERS -1F5C2 FE0F; emoji style; # CARD INDEX DIVIDERS -1F5C3 FE0E; text style; # CARD FILE BOX -1F5C3 FE0F; emoji style; # CARD FILE BOX -1F5C4 FE0E; text style; # FILE CABINET -1F5C4 FE0F; emoji style; # FILE CABINET -1F5D1 FE0E; text style; # WASTEBASKET -1F5D1 FE0F; emoji style; # WASTEBASKET -1F5D2 FE0E; text style; # SPIRAL NOTE PAD -1F5D2 FE0F; emoji style; # SPIRAL NOTE PAD -1F5D3 FE0E; text style; # SPIRAL CALENDAR PAD -1F5D3 FE0F; emoji style; # SPIRAL CALENDAR PAD -1F5DC FE0E; text style; # COMPRESSION -1F5DC FE0F; emoji style; # COMPRESSION -1F5DD FE0E; text style; # OLD KEY -1F5DD FE0F; emoji style; # OLD KEY -1F5DE FE0E; text style; # ROLLED-UP NEWSPAPER -1F5DE FE0F; emoji style; # ROLLED-UP NEWSPAPER -1F5E1 FE0E; text style; # DAGGER KNIFE -1F5E1 FE0F; emoji style; # DAGGER KNIFE -1F5E3 FE0E; text style; # SPEAKING HEAD IN SILHOUETTE -1F5E3 FE0F; emoji style; # SPEAKING HEAD IN SILHOUETTE -1F5E8 FE0E; text style; # LEFT SPEECH BUBBLE -1F5E8 FE0F; emoji style; # LEFT SPEECH BUBBLE -1F5EF FE0E; text style; # RIGHT ANGER BUBBLE -1F5EF FE0F; emoji style; # RIGHT ANGER BUBBLE -1F5F3 FE0E; text style; # BALLOT BOX WITH BALLOT -1F5F3 FE0F; emoji style; # BALLOT BOX WITH BALLOT -1F5FA FE0E; text style; # WORLD MAP -1F5FA FE0F; emoji style; # WORLD MAP -1F6CB FE0E; text style; # COUCH AND LAMP -1F6CB FE0F; emoji style; # COUCH AND LAMP -1F6CD FE0E; text style; # SHOPPING BAGS -1F6CD FE0F; emoji style; # SHOPPING BAGS -1F6CE FE0E; text style; # BELLHOP BELL -1F6CE FE0F; emoji style; # BELLHOP BELL -1F6CF FE0E; text style; # BED -1F6CF FE0F; emoji style; # BED -1F6E0 FE0E; text style; # HAMMER AND WRENCH -1F6E0 FE0F; emoji style; # HAMMER AND WRENCH -1F6E1 FE0E; text style; # SHIELD -1F6E1 FE0F; emoji style; # SHIELD -1F6E2 FE0E; text style; # OIL DRUM -1F6E2 FE0F; emoji style; # OIL DRUM -1F6E3 FE0E; text style; # MOTORWAY -1F6E3 FE0F; emoji style; # MOTORWAY -1F6E4 FE0E; text style; # RAILWAY TRACK -1F6E4 FE0F; emoji style; # RAILWAY TRACK -1F6E5 FE0E; text style; # MOTOR BOAT -1F6E5 FE0F; emoji style; # MOTOR BOAT -1F6E9 FE0E; text style; # SMALL AIRPLANE -1F6E9 FE0F; emoji style; # SMALL AIRPLANE -1F6F0 FE0E; text style; # SATELLITE -1F6F0 FE0F; emoji style; # SATELLITE -1F6F3 FE0E; text style; # PASSENGER SHIP -1F6F3 FE0F; emoji style; # PASSENGER SHIP - # CJK compatibility ideographs # Note: In the entries for CJK compatibility ideographs, field 1 diff --git a/lib/unicore/UnicodeData.txt b/lib/unicore/UnicodeData.txt index a756976461..d89c64f526 100644 --- a/lib/unicore/UnicodeData.txt +++ b/lib/unicore/UnicodeData.txt @@ -2072,6 +2072,17 @@ 085A;MANDAIC VOCALIZATION MARK;Mn;220;NSM;;;;;N;;;;; 085B;MANDAIC GEMINATION MARK;Mn;220;NSM;;;;;N;;;;; 085E;MANDAIC PUNCTUATION;Po;0;R;;;;;N;;;;; +0860;SYRIAC LETTER MALAYALAM NGA;Lo;0;AL;;;;;N;;;;; +0861;SYRIAC LETTER MALAYALAM JA;Lo;0;AL;;;;;N;;;;; +0862;SYRIAC LETTER MALAYALAM NYA;Lo;0;AL;;;;;N;;;;; +0863;SYRIAC LETTER MALAYALAM TTA;Lo;0;AL;;;;;N;;;;; +0864;SYRIAC LETTER MALAYALAM NNA;Lo;0;AL;;;;;N;;;;; +0865;SYRIAC LETTER MALAYALAM NNNA;Lo;0;AL;;;;;N;;;;; +0866;SYRIAC LETTER MALAYALAM BHA;Lo;0;AL;;;;;N;;;;; +0867;SYRIAC LETTER MALAYALAM RA;Lo;0;AL;;;;;N;;;;; +0868;SYRIAC LETTER MALAYALAM LLA;Lo;0;AL;;;;;N;;;;; +0869;SYRIAC LETTER MALAYALAM LLLA;Lo;0;AL;;;;;N;;;;; +086A;SYRIAC LETTER MALAYALAM SSA;Lo;0;AL;;;;;N;;;;; 08A0;ARABIC LETTER BEH WITH SMALL V BELOW;Lo;0;AL;;;;;N;;;;; 08A1;ARABIC LETTER BEH WITH HAMZA ABOVE;Lo;0;AL;;;;;N;;;;; 08A2;ARABIC LETTER JEEM WITH TWO DOTS ABOVE;Lo;0;AL;;;;;N;;;;; @@ -2366,6 +2377,8 @@ 09F9;BENGALI CURRENCY DENOMINATOR SIXTEEN;No;0;L;;;;16;N;;;;; 09FA;BENGALI ISSHAR;So;0;L;;;;;N;;;;; 09FB;BENGALI GANDA MARK;Sc;0;ET;;;;;N;;;;; +09FC;BENGALI LETTER VEDIC ANUSVARA;Lo;0;L;;;;;N;;;;; +09FD;BENGALI ABBREVIATION SIGN;Po;0;L;;;;;N;;;;; 0A01;GURMUKHI SIGN ADAK BINDI;Mn;0;NSM;;;;;N;;;;; 0A02;GURMUKHI SIGN BINDI;Mn;0;NSM;;;;;N;;;;; 0A03;GURMUKHI SIGN VISARGA;Mc;0;L;;;;;N;;;;; @@ -2530,6 +2543,12 @@ 0AF0;GUJARATI ABBREVIATION SIGN;Po;0;L;;;;;N;;;;; 0AF1;GUJARATI RUPEE SIGN;Sc;0;ET;;;;;N;;;;; 0AF9;GUJARATI LETTER ZHA;Lo;0;L;;;;;N;;;;; +0AFA;GUJARATI SIGN SUKUN;Mn;0;NSM;;;;;N;;;;; +0AFB;GUJARATI SIGN SHADDA;Mn;0;NSM;;;;;N;;;;; +0AFC;GUJARATI SIGN MADDAH;Mn;0;NSM;;;;;N;;;;; +0AFD;GUJARATI SIGN THREE-DOT NUKTA ABOVE;Mn;0;NSM;;;;;N;;;;; +0AFE;GUJARATI SIGN CIRCLE NUKTA ABOVE;Mn;0;NSM;;;;;N;;;;; +0AFF;GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE;Mn;0;NSM;;;;;N;;;;; 0B01;ORIYA SIGN CANDRABINDU;Mn;0;NSM;;;;;N;;;;; 0B02;ORIYA SIGN ANUSVARA;Mc;0;L;;;;;N;;;;; 0B03;ORIYA SIGN VISARGA;Mc;0;L;;;;;N;;;;; @@ -2876,6 +2895,7 @@ 0CEF;KANNADA DIGIT NINE;Nd;0;L;;9;9;9;N;;;;; 0CF1;KANNADA SIGN JIHVAMULIYA;Lo;0;L;;;;;N;;;;; 0CF2;KANNADA SIGN UPADHMANIYA;Lo;0;L;;;;;N;;;;; +0D00;MALAYALAM SIGN COMBINING ANUSVARA ABOVE;Mn;0;NSM;;;;;N;;;;; 0D01;MALAYALAM SIGN CANDRABINDU;Mn;0;NSM;;;;;N;;;;; 0D02;MALAYALAM SIGN ANUSVARA;Mc;0;L;;;;;N;;;;; 0D03;MALAYALAM SIGN VISARGA;Mc;0;L;;;;;N;;;;; @@ -2931,6 +2951,8 @@ 0D38;MALAYALAM LETTER SA;Lo;0;L;;;;;N;;;;; 0D39;MALAYALAM LETTER HA;Lo;0;L;;;;;N;;;;; 0D3A;MALAYALAM LETTER TTTA;Lo;0;L;;;;;N;;;;; +0D3B;MALAYALAM SIGN VERTICAL BAR VIRAMA;Mn;9;NSM;;;;;N;;;;; +0D3C;MALAYALAM SIGN CIRCULAR VIRAMA;Mn;9;NSM;;;;;N;;;;; 0D3D;MALAYALAM SIGN AVAGRAHA;Lo;0;L;;;;;N;;;;; 0D3E;MALAYALAM VOWEL SIGN AA;Mc;0;L;;;;;N;;;;; 0D3F;MALAYALAM VOWEL SIGN I;Mc;0;L;;;;;N;;;;; @@ -6413,6 +6435,7 @@ 1CF4;VEDIC TONE CANDRA ABOVE;Mn;230;NSM;;;;;N;;;;; 1CF5;VEDIC SIGN JIHVAMULIYA;Lo;0;L;;;;;N;;;;; 1CF6;VEDIC SIGN UPADHMANIYA;Lo;0;L;;;;;N;;;;; +1CF7;VEDIC SIGN ATIKRAMA;Mc;0;L;;;;;N;;;;; 1CF8;VEDIC TONE RING ABOVE;Mn;230;NSM;;;;;N;;;;; 1CF9;VEDIC TONE DOUBLE RING ABOVE;Mn;230;NSM;;;;;N;;;;; 1D00;LATIN LETTER SMALL CAPITAL A;Ll;0;L;;;;;N;;;;; @@ -6661,6 +6684,10 @@ 1DF3;COMBINING LATIN SMALL LETTER O WITH DIAERESIS;Mn;230;NSM;;;;;N;;;;; 1DF4;COMBINING LATIN SMALL LETTER U WITH DIAERESIS;Mn;230;NSM;;;;;N;;;;; 1DF5;COMBINING UP TACK ABOVE;Mn;230;NSM;;;;;N;;;;; +1DF6;COMBINING KAVYKA ABOVE RIGHT;Mn;232;NSM;;;;;N;;;;; +1DF7;COMBINING KAVYKA ABOVE LEFT;Mn;228;NSM;;;;;N;;;;; +1DF8;COMBINING DOT ABOVE LEFT;Mn;228;NSM;;;;;N;;;;; +1DF9;COMBINING WIDE INVERTED BRIDGE BELOW;Mn;220;NSM;;;;;N;;;;; 1DFB;COMBINING DELETION MARK;Mn;230;NSM;;;;;N;;;;; 1DFC;COMBINING DOUBLE INVERTED BREVE BELOW;Mn;233;NSM;;;;;N;;;;; 1DFD;COMBINING ALMOST EQUAL TO BELOW;Mn;220;NSM;;;;;N;;;;; @@ -7339,6 +7366,7 @@ 20BC;MANAT SIGN;Sc;0;ET;;;;;N;;;;; 20BD;RUBLE SIGN;Sc;0;ET;;;;;N;;;;; 20BE;LARI SIGN;Sc;0;ET;;;;;N;;;;; +20BF;BITCOIN SIGN;Sc;0;ET;;;;;N;;;;; 20D0;COMBINING LEFT HARPOON ABOVE;Mn;230;NSM;;;;;N;NON-SPACING LEFT HARPOON ABOVE;;;; 20D1;COMBINING RIGHT HARPOON ABOVE;Mn;230;NSM;;;;;N;NON-SPACING RIGHT HARPOON ABOVE;;;; 20D2;COMBINING LONG VERTICAL LINE OVERLAY;Mn;1;NSM;;;;;N;NON-SPACING LONG VERTICAL BAR OVERLAY;;;; @@ -8135,6 +8163,7 @@ 23FC;POWER ON-OFF SYMBOL;So;0;ON;;;;;N;;;;; 23FD;POWER ON SYMBOL;So;0;ON;;;;;N;;;;; 23FE;POWER SLEEP SYMBOL;So;0;ON;;;;;N;;;;; +23FF;OBSERVER EYE SYMBOL;So;0;ON;;;;;N;;;;; 2400;SYMBOL FOR NULL;So;0;ON;;;;;N;GRAPHIC FOR NULL;;;; 2401;SYMBOL FOR START OF HEADING;So;0;ON;;;;;N;GRAPHIC FOR START OF HEADING;;;; 2402;SYMBOL FOR START OF TEXT;So;0;ON;;;;;N;GRAPHIC FOR START OF TEXT;;;; @@ -10083,6 +10112,7 @@ 2BCF;ROTATED WHITE FOUR POINTED CUSP;So;0;ON;;;;;N;;;;; 2BD0;SQUARE POSITION INDICATOR;So;0;ON;;;;;N;;;;; 2BD1;UNCERTAINTY SIGN;So;0;ON;;;;;N;;;;; +2BD2;GROUP MARK;So;0;ON;;;;;N;;;;; 2BEC;LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS;So;0;ON;;;;;N;;;;; 2BED;UPWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS;So;0;ON;;;;;N;;;;; 2BEE;RIGHTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS;So;0;ON;;;;;N;;;;; @@ -10615,6 +10645,11 @@ 2E42;DOUBLE LOW-REVERSED-9 QUOTATION MARK;Ps;0;ON;;;;;N;;;;; 2E43;DASH WITH LEFT UPTURN;Po;0;ON;;;;;N;;;;; 2E44;DOUBLE SUSPENSION MARK;Po;0;ON;;;;;N;;;;; +2E45;INVERTED LOW KAVYKA;Po;0;ON;;;;;N;;;;; +2E46;INVERTED LOW KAVYKA WITH KAVYKA ABOVE;Po;0;ON;;;;;N;;;;; +2E47;LOW KAVYKA;Po;0;ON;;;;;N;;;;; +2E48;LOW KAVYKA WITH DOT;Po;0;ON;;;;;N;;;;; +2E49;DOUBLE STACKED COMMA;Po;0;ON;;;;;N;;;;; 2E80;CJK RADICAL REPEAT;So;0;ON;;;;;N;;;;; 2E81;CJK RADICAL CLIFF;So;0;ON;;;;;N;;;;; 2E82;CJK RADICAL SECOND ONE;So;0;ON;;;;;N;;;;; @@ -11250,6 +11285,7 @@ 312B;BOPOMOFO LETTER NG;Lo;0;L;;;;;N;;;;; 312C;BOPOMOFO LETTER GN;Lo;0;L;;;;;N;;;;; 312D;BOPOMOFO LETTER IH;Lo;0;L;;;;;N;;;;; +312E;BOPOMOFO LETTER O WITH DOT ABOVE;Lo;0;L;;;;;N;;;;; 3131;HANGUL LETTER KIYEOK;Lo;0;L;<compat> 1100;;;;N;HANGUL LETTER GIYEOG;;;; 3132;HANGUL LETTER SSANGKIYEOK;Lo;0;L;<compat> 1101;;;;N;HANGUL LETTER SSANG GIYEOG;;;; 3133;HANGUL LETTER KIYEOK-SIOS;Lo;0;L;<compat> 11AA;;;;N;HANGUL LETTER GIYEOG SIOS;;;; @@ -12016,7 +12052,7 @@ 4DFE;HEXAGRAM FOR AFTER COMPLETION;So;0;ON;;;;;N;;;;; 4DFF;HEXAGRAM FOR BEFORE COMPLETION;So;0;ON;;;;;N;;;;; 4E00;<CJK Ideograph, First>;Lo;0;L;;;;;N;;;;; -9FD5;<CJK Ideograph, Last>;Lo;0;L;;;;;N;;;;; +9FEA;<CJK Ideograph, Last>;Lo;0;L;;;;;N;;;;; A000;YI SYLLABLE IT;Lo;0;L;;;;;N;;;;; A001;YI SYLLABLE IX;Lo;0;L;;;;;N;;;;; A002;YI SYLLABLE I;Lo;0;L;;;;;N;;;;; @@ -17093,6 +17129,9 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 10321;OLD ITALIC NUMERAL FIVE;No;0;L;;;;5;N;;;;; 10322;OLD ITALIC NUMERAL TEN;No;0;L;;;;10;N;;;;; 10323;OLD ITALIC NUMERAL FIFTY;No;0;L;;;;50;N;;;;; +1032D;OLD ITALIC LETTER YE;Lo;0;L;;;;;N;;;;; +1032E;OLD ITALIC LETTER NORTHERN TSE;Lo;0;L;;;;;N;;;;; +1032F;OLD ITALIC LETTER SOUTHERN TSE;Lo;0;L;;;;;N;;;;; 10330;GOTHIC LETTER AHSA;Lo;0;L;;;;;N;;;;; 10331;GOTHIC LETTER BAIRKAN;Lo;0;L;;;;;N;;;;; 10332;GOTHIC LETTER GIBA;Lo;0;L;;;;;N;;;;; @@ -20068,6 +20107,158 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 118F1;WARANG CITI NUMBER EIGHTY;No;0;L;;;;80;N;;;;; 118F2;WARANG CITI NUMBER NINETY;No;0;L;;;;90;N;;;;; 118FF;WARANG CITI OM;Lo;0;L;;;;;N;;;;; +11A00;ZANABAZAR SQUARE LETTER A;Lo;0;L;;;;;N;;;;; +11A01;ZANABAZAR SQUARE VOWEL SIGN I;Mn;0;NSM;;;;;N;;;;; +11A02;ZANABAZAR SQUARE VOWEL SIGN UE;Mn;0;NSM;;;;;N;;;;; +11A03;ZANABAZAR SQUARE VOWEL SIGN U;Mn;0;NSM;;;;;N;;;;; +11A04;ZANABAZAR SQUARE VOWEL SIGN E;Mn;0;NSM;;;;;N;;;;; +11A05;ZANABAZAR SQUARE VOWEL SIGN OE;Mn;0;NSM;;;;;N;;;;; +11A06;ZANABAZAR SQUARE VOWEL SIGN O;Mn;0;NSM;;;;;N;;;;; +11A07;ZANABAZAR SQUARE VOWEL SIGN AI;Mc;0;L;;;;;N;;;;; +11A08;ZANABAZAR SQUARE VOWEL SIGN AU;Mc;0;L;;;;;N;;;;; +11A09;ZANABAZAR SQUARE VOWEL SIGN REVERSED I;Mn;0;NSM;;;;;N;;;;; +11A0A;ZANABAZAR SQUARE VOWEL LENGTH MARK;Mn;0;NSM;;;;;N;;;;; +11A0B;ZANABAZAR SQUARE LETTER KA;Lo;0;L;;;;;N;;;;; +11A0C;ZANABAZAR SQUARE LETTER KHA;Lo;0;L;;;;;N;;;;; +11A0D;ZANABAZAR SQUARE LETTER GA;Lo;0;L;;;;;N;;;;; +11A0E;ZANABAZAR SQUARE LETTER GHA;Lo;0;L;;;;;N;;;;; +11A0F;ZANABAZAR SQUARE LETTER NGA;Lo;0;L;;;;;N;;;;; +11A10;ZANABAZAR SQUARE LETTER CA;Lo;0;L;;;;;N;;;;; +11A11;ZANABAZAR SQUARE LETTER CHA;Lo;0;L;;;;;N;;;;; +11A12;ZANABAZAR SQUARE LETTER JA;Lo;0;L;;;;;N;;;;; +11A13;ZANABAZAR SQUARE LETTER NYA;Lo;0;L;;;;;N;;;;; +11A14;ZANABAZAR SQUARE LETTER TTA;Lo;0;L;;;;;N;;;;; +11A15;ZANABAZAR SQUARE LETTER TTHA;Lo;0;L;;;;;N;;;;; +11A16;ZANABAZAR SQUARE LETTER DDA;Lo;0;L;;;;;N;;;;; +11A17;ZANABAZAR SQUARE LETTER DDHA;Lo;0;L;;;;;N;;;;; +11A18;ZANABAZAR SQUARE LETTER NNA;Lo;0;L;;;;;N;;;;; +11A19;ZANABAZAR SQUARE LETTER TA;Lo;0;L;;;;;N;;;;; +11A1A;ZANABAZAR SQUARE LETTER THA;Lo;0;L;;;;;N;;;;; +11A1B;ZANABAZAR SQUARE LETTER DA;Lo;0;L;;;;;N;;;;; +11A1C;ZANABAZAR SQUARE LETTER DHA;Lo;0;L;;;;;N;;;;; +11A1D;ZANABAZAR SQUARE LETTER NA;Lo;0;L;;;;;N;;;;; +11A1E;ZANABAZAR SQUARE LETTER PA;Lo;0;L;;;;;N;;;;; +11A1F;ZANABAZAR SQUARE LETTER PHA;Lo;0;L;;;;;N;;;;; +11A20;ZANABAZAR SQUARE LETTER BA;Lo;0;L;;;;;N;;;;; +11A21;ZANABAZAR SQUARE LETTER BHA;Lo;0;L;;;;;N;;;;; +11A22;ZANABAZAR SQUARE LETTER MA;Lo;0;L;;;;;N;;;;; +11A23;ZANABAZAR SQUARE LETTER TSA;Lo;0;L;;;;;N;;;;; +11A24;ZANABAZAR SQUARE LETTER TSHA;Lo;0;L;;;;;N;;;;; +11A25;ZANABAZAR SQUARE LETTER DZA;Lo;0;L;;;;;N;;;;; +11A26;ZANABAZAR SQUARE LETTER DZHA;Lo;0;L;;;;;N;;;;; +11A27;ZANABAZAR SQUARE LETTER ZHA;Lo;0;L;;;;;N;;;;; +11A28;ZANABAZAR SQUARE LETTER ZA;Lo;0;L;;;;;N;;;;; +11A29;ZANABAZAR SQUARE LETTER -A;Lo;0;L;;;;;N;;;;; +11A2A;ZANABAZAR SQUARE LETTER YA;Lo;0;L;;;;;N;;;;; +11A2B;ZANABAZAR SQUARE LETTER RA;Lo;0;L;;;;;N;;;;; +11A2C;ZANABAZAR SQUARE LETTER LA;Lo;0;L;;;;;N;;;;; +11A2D;ZANABAZAR SQUARE LETTER VA;Lo;0;L;;;;;N;;;;; +11A2E;ZANABAZAR SQUARE LETTER SHA;Lo;0;L;;;;;N;;;;; +11A2F;ZANABAZAR SQUARE LETTER SSA;Lo;0;L;;;;;N;;;;; +11A30;ZANABAZAR SQUARE LETTER SA;Lo;0;L;;;;;N;;;;; +11A31;ZANABAZAR SQUARE LETTER HA;Lo;0;L;;;;;N;;;;; +11A32;ZANABAZAR SQUARE LETTER KSSA;Lo;0;L;;;;;N;;;;; +11A33;ZANABAZAR SQUARE FINAL CONSONANT MARK;Mn;0;NSM;;;;;N;;;;; +11A34;ZANABAZAR SQUARE SIGN VIRAMA;Mn;9;NSM;;;;;N;;;;; +11A35;ZANABAZAR SQUARE SIGN CANDRABINDU;Mn;0;NSM;;;;;N;;;;; +11A36;ZANABAZAR SQUARE SIGN CANDRABINDU WITH ORNAMENT;Mn;0;NSM;;;;;N;;;;; +11A37;ZANABAZAR SQUARE SIGN CANDRA WITH ORNAMENT;Mn;0;NSM;;;;;N;;;;; +11A38;ZANABAZAR SQUARE SIGN ANUSVARA;Mn;0;NSM;;;;;N;;;;; +11A39;ZANABAZAR SQUARE SIGN VISARGA;Mc;0;L;;;;;N;;;;; +11A3A;ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA;Lo;0;L;;;;;N;;;;; +11A3B;ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA;Mn;0;NSM;;;;;N;;;;; +11A3C;ZANABAZAR SQUARE CLUSTER-FINAL LETTER RA;Mn;0;NSM;;;;;N;;;;; +11A3D;ZANABAZAR SQUARE CLUSTER-FINAL LETTER LA;Mn;0;NSM;;;;;N;;;;; +11A3E;ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA;Mn;0;NSM;;;;;N;;;;; +11A3F;ZANABAZAR SQUARE INITIAL HEAD MARK;Po;0;L;;;;;N;;;;; +11A40;ZANABAZAR SQUARE CLOSING HEAD MARK;Po;0;L;;;;;N;;;;; +11A41;ZANABAZAR SQUARE MARK TSHEG;Po;0;L;;;;;N;;;;; +11A42;ZANABAZAR SQUARE MARK SHAD;Po;0;L;;;;;N;;;;; +11A43;ZANABAZAR SQUARE MARK DOUBLE SHAD;Po;0;L;;;;;N;;;;; +11A44;ZANABAZAR SQUARE MARK LONG TSHEG;Po;0;L;;;;;N;;;;; +11A45;ZANABAZAR SQUARE INITIAL DOUBLE-LINED HEAD MARK;Po;0;L;;;;;N;;;;; +11A46;ZANABAZAR SQUARE CLOSING DOUBLE-LINED HEAD MARK;Po;0;L;;;;;N;;;;; +11A47;ZANABAZAR SQUARE SUBJOINER;Mn;9;NSM;;;;;N;;;;; +11A50;SOYOMBO LETTER A;Lo;0;L;;;;;N;;;;; +11A51;SOYOMBO VOWEL SIGN I;Mn;0;NSM;;;;;N;;;;; +11A52;SOYOMBO VOWEL SIGN UE;Mn;0;NSM;;;;;N;;;;; +11A53;SOYOMBO VOWEL SIGN U;Mn;0;NSM;;;;;N;;;;; +11A54;SOYOMBO VOWEL SIGN E;Mn;0;NSM;;;;;N;;;;; +11A55;SOYOMBO VOWEL SIGN O;Mn;0;NSM;;;;;N;;;;; +11A56;SOYOMBO VOWEL SIGN OE;Mn;0;NSM;;;;;N;;;;; +11A57;SOYOMBO VOWEL SIGN AI;Mc;0;L;;;;;N;;;;; +11A58;SOYOMBO VOWEL SIGN AU;Mc;0;L;;;;;N;;;;; +11A59;SOYOMBO VOWEL SIGN VOCALIC R;Mn;0;NSM;;;;;N;;;;; +11A5A;SOYOMBO VOWEL SIGN VOCALIC L;Mn;0;NSM;;;;;N;;;;; +11A5B;SOYOMBO VOWEL LENGTH MARK;Mn;0;NSM;;;;;N;;;;; +11A5C;SOYOMBO LETTER KA;Lo;0;L;;;;;N;;;;; +11A5D;SOYOMBO LETTER KHA;Lo;0;L;;;;;N;;;;; +11A5E;SOYOMBO LETTER GA;Lo;0;L;;;;;N;;;;; +11A5F;SOYOMBO LETTER GHA;Lo;0;L;;;;;N;;;;; +11A60;SOYOMBO LETTER NGA;Lo;0;L;;;;;N;;;;; +11A61;SOYOMBO LETTER CA;Lo;0;L;;;;;N;;;;; +11A62;SOYOMBO LETTER CHA;Lo;0;L;;;;;N;;;;; +11A63;SOYOMBO LETTER JA;Lo;0;L;;;;;N;;;;; +11A64;SOYOMBO LETTER JHA;Lo;0;L;;;;;N;;;;; +11A65;SOYOMBO LETTER NYA;Lo;0;L;;;;;N;;;;; +11A66;SOYOMBO LETTER TTA;Lo;0;L;;;;;N;;;;; +11A67;SOYOMBO LETTER TTHA;Lo;0;L;;;;;N;;;;; +11A68;SOYOMBO LETTER DDA;Lo;0;L;;;;;N;;;;; +11A69;SOYOMBO LETTER DDHA;Lo;0;L;;;;;N;;;;; +11A6A;SOYOMBO LETTER NNA;Lo;0;L;;;;;N;;;;; +11A6B;SOYOMBO LETTER TA;Lo;0;L;;;;;N;;;;; +11A6C;SOYOMBO LETTER THA;Lo;0;L;;;;;N;;;;; +11A6D;SOYOMBO LETTER DA;Lo;0;L;;;;;N;;;;; +11A6E;SOYOMBO LETTER DHA;Lo;0;L;;;;;N;;;;; +11A6F;SOYOMBO LETTER NA;Lo;0;L;;;;;N;;;;; +11A70;SOYOMBO LETTER PA;Lo;0;L;;;;;N;;;;; +11A71;SOYOMBO LETTER PHA;Lo;0;L;;;;;N;;;;; +11A72;SOYOMBO LETTER BA;Lo;0;L;;;;;N;;;;; +11A73;SOYOMBO LETTER BHA;Lo;0;L;;;;;N;;;;; +11A74;SOYOMBO LETTER MA;Lo;0;L;;;;;N;;;;; +11A75;SOYOMBO LETTER TSA;Lo;0;L;;;;;N;;;;; +11A76;SOYOMBO LETTER TSHA;Lo;0;L;;;;;N;;;;; +11A77;SOYOMBO LETTER DZA;Lo;0;L;;;;;N;;;;; +11A78;SOYOMBO LETTER ZHA;Lo;0;L;;;;;N;;;;; +11A79;SOYOMBO LETTER ZA;Lo;0;L;;;;;N;;;;; +11A7A;SOYOMBO LETTER -A;Lo;0;L;;;;;N;;;;; +11A7B;SOYOMBO LETTER YA;Lo;0;L;;;;;N;;;;; +11A7C;SOYOMBO LETTER RA;Lo;0;L;;;;;N;;;;; +11A7D;SOYOMBO LETTER LA;Lo;0;L;;;;;N;;;;; +11A7E;SOYOMBO LETTER VA;Lo;0;L;;;;;N;;;;; +11A7F;SOYOMBO LETTER SHA;Lo;0;L;;;;;N;;;;; +11A80;SOYOMBO LETTER SSA;Lo;0;L;;;;;N;;;;; +11A81;SOYOMBO LETTER SA;Lo;0;L;;;;;N;;;;; +11A82;SOYOMBO LETTER HA;Lo;0;L;;;;;N;;;;; +11A83;SOYOMBO LETTER KSSA;Lo;0;L;;;;;N;;;;; +11A86;SOYOMBO CLUSTER-INITIAL LETTER RA;Lo;0;L;;;;;N;;;;; +11A87;SOYOMBO CLUSTER-INITIAL LETTER LA;Lo;0;L;;;;;N;;;;; +11A88;SOYOMBO CLUSTER-INITIAL LETTER SHA;Lo;0;L;;;;;N;;;;; +11A89;SOYOMBO CLUSTER-INITIAL LETTER SA;Lo;0;L;;;;;N;;;;; +11A8A;SOYOMBO FINAL CONSONANT SIGN G;Mn;0;NSM;;;;;N;;;;; +11A8B;SOYOMBO FINAL CONSONANT SIGN K;Mn;0;NSM;;;;;N;;;;; +11A8C;SOYOMBO FINAL CONSONANT SIGN NG;Mn;0;NSM;;;;;N;;;;; +11A8D;SOYOMBO FINAL CONSONANT SIGN D;Mn;0;NSM;;;;;N;;;;; +11A8E;SOYOMBO FINAL CONSONANT SIGN N;Mn;0;NSM;;;;;N;;;;; +11A8F;SOYOMBO FINAL CONSONANT SIGN B;Mn;0;NSM;;;;;N;;;;; +11A90;SOYOMBO FINAL CONSONANT SIGN M;Mn;0;NSM;;;;;N;;;;; +11A91;SOYOMBO FINAL CONSONANT SIGN R;Mn;0;NSM;;;;;N;;;;; +11A92;SOYOMBO FINAL CONSONANT SIGN L;Mn;0;NSM;;;;;N;;;;; +11A93;SOYOMBO FINAL CONSONANT SIGN SH;Mn;0;NSM;;;;;N;;;;; +11A94;SOYOMBO FINAL CONSONANT SIGN S;Mn;0;NSM;;;;;N;;;;; +11A95;SOYOMBO FINAL CONSONANT SIGN -A;Mn;0;NSM;;;;;N;;;;; +11A96;SOYOMBO SIGN ANUSVARA;Mn;0;NSM;;;;;N;;;;; +11A97;SOYOMBO SIGN VISARGA;Mc;0;L;;;;;N;;;;; +11A98;SOYOMBO GEMINATION MARK;Mn;0;NSM;;;;;N;;;;; +11A99;SOYOMBO SUBJOINER;Mn;9;NSM;;;;;N;;;;; +11A9A;SOYOMBO MARK TSHEG;Po;0;L;;;;;N;;;;; +11A9B;SOYOMBO MARK SHAD;Po;0;L;;;;;N;;;;; +11A9C;SOYOMBO MARK DOUBLE SHAD;Po;0;L;;;;;N;;;;; +11A9E;SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME;Po;0;L;;;;;N;;;;; +11A9F;SOYOMBO HEAD MARK WITH MOON AND SUN AND FLAME;Po;0;L;;;;;N;;;;; +11AA0;SOYOMBO HEAD MARK WITH MOON AND SUN;Po;0;L;;;;;N;;;;; +11AA1;SOYOMBO TERMINAL MARK-1;Po;0;L;;;;;N;;;;; +11AA2;SOYOMBO TERMINAL MARK-2;Po;0;L;;;;;N;;;;; 11AC0;PAU CIN HAU LETTER PA;Lo;0;L;;;;;N;;;;; 11AC1;PAU CIN HAU LETTER KA;Lo;0;L;;;;;N;;;;; 11AC2;PAU CIN HAU LETTER LA;Lo;0;L;;;;;N;;;;; @@ -20290,6 +20481,81 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 11CB4;MARCHEN VOWEL SIGN O;Mc;0;L;;;;;N;;;;; 11CB5;MARCHEN SIGN ANUSVARA;Mn;0;NSM;;;;;N;;;;; 11CB6;MARCHEN SIGN CANDRABINDU;Mn;0;NSM;;;;;N;;;;; +11D00;MASARAM GONDI LETTER A;Lo;0;L;;;;;N;;;;; +11D01;MASARAM GONDI LETTER AA;Lo;0;L;;;;;N;;;;; +11D02;MASARAM GONDI LETTER I;Lo;0;L;;;;;N;;;;; +11D03;MASARAM GONDI LETTER II;Lo;0;L;;;;;N;;;;; +11D04;MASARAM GONDI LETTER U;Lo;0;L;;;;;N;;;;; +11D05;MASARAM GONDI LETTER UU;Lo;0;L;;;;;N;;;;; +11D06;MASARAM GONDI LETTER E;Lo;0;L;;;;;N;;;;; +11D08;MASARAM GONDI LETTER AI;Lo;0;L;;;;;N;;;;; +11D09;MASARAM GONDI LETTER O;Lo;0;L;;;;;N;;;;; +11D0B;MASARAM GONDI LETTER AU;Lo;0;L;;;;;N;;;;; +11D0C;MASARAM GONDI LETTER KA;Lo;0;L;;;;;N;;;;; +11D0D;MASARAM GONDI LETTER KHA;Lo;0;L;;;;;N;;;;; +11D0E;MASARAM GONDI LETTER GA;Lo;0;L;;;;;N;;;;; +11D0F;MASARAM GONDI LETTER GHA;Lo;0;L;;;;;N;;;;; +11D10;MASARAM GONDI LETTER NGA;Lo;0;L;;;;;N;;;;; +11D11;MASARAM GONDI LETTER CA;Lo;0;L;;;;;N;;;;; +11D12;MASARAM GONDI LETTER CHA;Lo;0;L;;;;;N;;;;; +11D13;MASARAM GONDI LETTER JA;Lo;0;L;;;;;N;;;;; +11D14;MASARAM GONDI LETTER JHA;Lo;0;L;;;;;N;;;;; +11D15;MASARAM GONDI LETTER NYA;Lo;0;L;;;;;N;;;;; +11D16;MASARAM GONDI LETTER TTA;Lo;0;L;;;;;N;;;;; +11D17;MASARAM GONDI LETTER TTHA;Lo;0;L;;;;;N;;;;; +11D18;MASARAM GONDI LETTER DDA;Lo;0;L;;;;;N;;;;; +11D19;MASARAM GONDI LETTER DDHA;Lo;0;L;;;;;N;;;;; +11D1A;MASARAM GONDI LETTER NNA;Lo;0;L;;;;;N;;;;; +11D1B;MASARAM GONDI LETTER TA;Lo;0;L;;;;;N;;;;; +11D1C;MASARAM GONDI LETTER THA;Lo;0;L;;;;;N;;;;; +11D1D;MASARAM GONDI LETTER DA;Lo;0;L;;;;;N;;;;; +11D1E;MASARAM GONDI LETTER DHA;Lo;0;L;;;;;N;;;;; +11D1F;MASARAM GONDI LETTER NA;Lo;0;L;;;;;N;;;;; +11D20;MASARAM GONDI LETTER PA;Lo;0;L;;;;;N;;;;; +11D21;MASARAM GONDI LETTER PHA;Lo;0;L;;;;;N;;;;; +11D22;MASARAM GONDI LETTER BA;Lo;0;L;;;;;N;;;;; +11D23;MASARAM GONDI LETTER BHA;Lo;0;L;;;;;N;;;;; +11D24;MASARAM GONDI LETTER MA;Lo;0;L;;;;;N;;;;; +11D25;MASARAM GONDI LETTER YA;Lo;0;L;;;;;N;;;;; +11D26;MASARAM GONDI LETTER RA;Lo;0;L;;;;;N;;;;; +11D27;MASARAM GONDI LETTER LA;Lo;0;L;;;;;N;;;;; +11D28;MASARAM GONDI LETTER VA;Lo;0;L;;;;;N;;;;; +11D29;MASARAM GONDI LETTER SHA;Lo;0;L;;;;;N;;;;; +11D2A;MASARAM GONDI LETTER SSA;Lo;0;L;;;;;N;;;;; +11D2B;MASARAM GONDI LETTER SA;Lo;0;L;;;;;N;;;;; +11D2C;MASARAM GONDI LETTER HA;Lo;0;L;;;;;N;;;;; +11D2D;MASARAM GONDI LETTER LLA;Lo;0;L;;;;;N;;;;; +11D2E;MASARAM GONDI LETTER KSSA;Lo;0;L;;;;;N;;;;; +11D2F;MASARAM GONDI LETTER JNYA;Lo;0;L;;;;;N;;;;; +11D30;MASARAM GONDI LETTER TRA;Lo;0;L;;;;;N;;;;; +11D31;MASARAM GONDI VOWEL SIGN AA;Mn;0;NSM;;;;;N;;;;; +11D32;MASARAM GONDI VOWEL SIGN I;Mn;0;NSM;;;;;N;;;;; +11D33;MASARAM GONDI VOWEL SIGN II;Mn;0;NSM;;;;;N;;;;; +11D34;MASARAM GONDI VOWEL SIGN U;Mn;0;NSM;;;;;N;;;;; +11D35;MASARAM GONDI VOWEL SIGN UU;Mn;0;NSM;;;;;N;;;;; +11D36;MASARAM GONDI VOWEL SIGN VOCALIC R;Mn;0;NSM;;;;;N;;;;; +11D3A;MASARAM GONDI VOWEL SIGN E;Mn;0;NSM;;;;;N;;;;; +11D3C;MASARAM GONDI VOWEL SIGN AI;Mn;0;NSM;;;;;N;;;;; +11D3D;MASARAM GONDI VOWEL SIGN O;Mn;0;NSM;;;;;N;;;;; +11D3F;MASARAM GONDI VOWEL SIGN AU;Mn;0;NSM;;;;;N;;;;; +11D40;MASARAM GONDI SIGN ANUSVARA;Mn;0;NSM;;;;;N;;;;; +11D41;MASARAM GONDI SIGN VISARGA;Mn;0;NSM;;;;;N;;;;; +11D42;MASARAM GONDI SIGN NUKTA;Mn;7;NSM;;;;;N;;;;; +11D43;MASARAM GONDI SIGN CANDRA;Mn;0;NSM;;;;;N;;;;; +11D44;MASARAM GONDI SIGN HALANTA;Mn;9;NSM;;;;;N;;;;; +11D45;MASARAM GONDI VIRAMA;Mn;9;NSM;;;;;N;;;;; +11D46;MASARAM GONDI REPHA;Lo;0;L;;;;;N;;;;; +11D47;MASARAM GONDI RA-KARA;Mn;0;NSM;;;;;N;;;;; +11D50;MASARAM GONDI DIGIT ZERO;Nd;0;L;;0;0;0;N;;;;; +11D51;MASARAM GONDI DIGIT ONE;Nd;0;L;;1;1;1;N;;;;; +11D52;MASARAM GONDI DIGIT TWO;Nd;0;L;;2;2;2;N;;;;; +11D53;MASARAM GONDI DIGIT THREE;Nd;0;L;;3;3;3;N;;;;; +11D54;MASARAM GONDI DIGIT FOUR;Nd;0;L;;4;4;4;N;;;;; +11D55;MASARAM GONDI DIGIT FIVE;Nd;0;L;;5;5;5;N;;;;; +11D56;MASARAM GONDI DIGIT SIX;Nd;0;L;;6;6;6;N;;;;; +11D57;MASARAM GONDI DIGIT SEVEN;Nd;0;L;;7;7;7;N;;;;; +11D58;MASARAM GONDI DIGIT EIGHT;Nd;0;L;;8;8;8;N;;;;; +11D59;MASARAM GONDI DIGIT NINE;Nd;0;L;;9;9;9;N;;;;; 12000;CUNEIFORM SIGN A;Lo;0;L;;;;;N;;;;; 12001;CUNEIFORM SIGN A TIMES A;Lo;0;L;;;;;N;;;;; 12002;CUNEIFORM SIGN A TIMES BAD;Lo;0;L;;;;;N;;;;; @@ -24087,6 +24353,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 16F9E;MIAO LETTER REFORMED TONE-6;Lm;0;L;;;;;N;;;;; 16F9F;MIAO LETTER REFORMED TONE-8;Lm;0;L;;;;;N;;;;; 16FE0;TANGUT ITERATION MARK;Lm;0;L;;;;;N;;;;; +16FE1;NUSHU ITERATION MARK;Lm;0;L;;;;;N;;;;; 17000;<Tangut Ideograph, First>;Lo;0;L;;;;;N;;;;; 187EC;<Tangut Ideograph, Last>;Lo;0;L;;;;;N;;;;; 18800;TANGUT COMPONENT-001;Lo;0;L;;;;;N;;;;; @@ -24846,6 +25113,687 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 18AF2;TANGUT COMPONENT-755;Lo;0;L;;;;;N;;;;; 1B000;KATAKANA LETTER ARCHAIC E;Lo;0;L;;;;;N;;;;; 1B001;HIRAGANA LETTER ARCHAIC YE;Lo;0;L;;;;;N;;;;; +1B002;HENTAIGANA LETTER A-1;Lo;0;L;;;;;N;;;;; +1B003;HENTAIGANA LETTER A-2;Lo;0;L;;;;;N;;;;; +1B004;HENTAIGANA LETTER A-3;Lo;0;L;;;;;N;;;;; +1B005;HENTAIGANA LETTER A-WO;Lo;0;L;;;;;N;;;;; +1B006;HENTAIGANA LETTER I-1;Lo;0;L;;;;;N;;;;; +1B007;HENTAIGANA LETTER I-2;Lo;0;L;;;;;N;;;;; +1B008;HENTAIGANA LETTER I-3;Lo;0;L;;;;;N;;;;; +1B009;HENTAIGANA LETTER I-4;Lo;0;L;;;;;N;;;;; +1B00A;HENTAIGANA LETTER U-1;Lo;0;L;;;;;N;;;;; +1B00B;HENTAIGANA LETTER U-2;Lo;0;L;;;;;N;;;;; +1B00C;HENTAIGANA LETTER U-3;Lo;0;L;;;;;N;;;;; +1B00D;HENTAIGANA LETTER U-4;Lo;0;L;;;;;N;;;;; +1B00E;HENTAIGANA LETTER U-5;Lo;0;L;;;;;N;;;;; +1B00F;HENTAIGANA LETTER E-2;Lo;0;L;;;;;N;;;;; +1B010;HENTAIGANA LETTER E-3;Lo;0;L;;;;;N;;;;; +1B011;HENTAIGANA LETTER E-4;Lo;0;L;;;;;N;;;;; +1B012;HENTAIGANA LETTER E-5;Lo;0;L;;;;;N;;;;; +1B013;HENTAIGANA LETTER E-6;Lo;0;L;;;;;N;;;;; +1B014;HENTAIGANA LETTER O-1;Lo;0;L;;;;;N;;;;; +1B015;HENTAIGANA LETTER O-2;Lo;0;L;;;;;N;;;;; +1B016;HENTAIGANA LETTER O-3;Lo;0;L;;;;;N;;;;; +1B017;HENTAIGANA LETTER KA-1;Lo;0;L;;;;;N;;;;; +1B018;HENTAIGANA LETTER KA-2;Lo;0;L;;;;;N;;;;; +1B019;HENTAIGANA LETTER KA-3;Lo;0;L;;;;;N;;;;; +1B01A;HENTAIGANA LETTER KA-4;Lo;0;L;;;;;N;;;;; +1B01B;HENTAIGANA LETTER KA-5;Lo;0;L;;;;;N;;;;; +1B01C;HENTAIGANA LETTER KA-6;Lo;0;L;;;;;N;;;;; +1B01D;HENTAIGANA LETTER KA-7;Lo;0;L;;;;;N;;;;; +1B01E;HENTAIGANA LETTER KA-8;Lo;0;L;;;;;N;;;;; +1B01F;HENTAIGANA LETTER KA-9;Lo;0;L;;;;;N;;;;; +1B020;HENTAIGANA LETTER KA-10;Lo;0;L;;;;;N;;;;; +1B021;HENTAIGANA LETTER KA-11;Lo;0;L;;;;;N;;;;; +1B022;HENTAIGANA LETTER KA-KE;Lo;0;L;;;;;N;;;;; +1B023;HENTAIGANA LETTER KI-1;Lo;0;L;;;;;N;;;;; +1B024;HENTAIGANA LETTER KI-2;Lo;0;L;;;;;N;;;;; +1B025;HENTAIGANA LETTER KI-3;Lo;0;L;;;;;N;;;;; +1B026;HENTAIGANA LETTER KI-4;Lo;0;L;;;;;N;;;;; +1B027;HENTAIGANA LETTER KI-5;Lo;0;L;;;;;N;;;;; +1B028;HENTAIGANA LETTER KI-6;Lo;0;L;;;;;N;;;;; +1B029;HENTAIGANA LETTER KI-7;Lo;0;L;;;;;N;;;;; +1B02A;HENTAIGANA LETTER KI-8;Lo;0;L;;;;;N;;;;; +1B02B;HENTAIGANA LETTER KU-1;Lo;0;L;;;;;N;;;;; +1B02C;HENTAIGANA LETTER KU-2;Lo;0;L;;;;;N;;;;; +1B02D;HENTAIGANA LETTER KU-3;Lo;0;L;;;;;N;;;;; +1B02E;HENTAIGANA LETTER KU-4;Lo;0;L;;;;;N;;;;; +1B02F;HENTAIGANA LETTER KU-5;Lo;0;L;;;;;N;;;;; +1B030;HENTAIGANA LETTER KU-6;Lo;0;L;;;;;N;;;;; +1B031;HENTAIGANA LETTER KU-7;Lo;0;L;;;;;N;;;;; +1B032;HENTAIGANA LETTER KE-1;Lo;0;L;;;;;N;;;;; +1B033;HENTAIGANA LETTER KE-2;Lo;0;L;;;;;N;;;;; +1B034;HENTAIGANA LETTER KE-3;Lo;0;L;;;;;N;;;;; +1B035;HENTAIGANA LETTER KE-4;Lo;0;L;;;;;N;;;;; +1B036;HENTAIGANA LETTER KE-5;Lo;0;L;;;;;N;;;;; +1B037;HENTAIGANA LETTER KE-6;Lo;0;L;;;;;N;;;;; +1B038;HENTAIGANA LETTER KO-1;Lo;0;L;;;;;N;;;;; +1B039;HENTAIGANA LETTER KO-2;Lo;0;L;;;;;N;;;;; +1B03A;HENTAIGANA LETTER KO-3;Lo;0;L;;;;;N;;;;; +1B03B;HENTAIGANA LETTER KO-KI;Lo;0;L;;;;;N;;;;; +1B03C;HENTAIGANA LETTER SA-1;Lo;0;L;;;;;N;;;;; +1B03D;HENTAIGANA LETTER SA-2;Lo;0;L;;;;;N;;;;; +1B03E;HENTAIGANA LETTER SA-3;Lo;0;L;;;;;N;;;;; +1B03F;HENTAIGANA LETTER SA-4;Lo;0;L;;;;;N;;;;; +1B040;HENTAIGANA LETTER SA-5;Lo;0;L;;;;;N;;;;; +1B041;HENTAIGANA LETTER SA-6;Lo;0;L;;;;;N;;;;; +1B042;HENTAIGANA LETTER SA-7;Lo;0;L;;;;;N;;;;; +1B043;HENTAIGANA LETTER SA-8;Lo;0;L;;;;;N;;;;; +1B044;HENTAIGANA LETTER SI-1;Lo;0;L;;;;;N;;;;; +1B045;HENTAIGANA LETTER SI-2;Lo;0;L;;;;;N;;;;; +1B046;HENTAIGANA LETTER SI-3;Lo;0;L;;;;;N;;;;; +1B047;HENTAIGANA LETTER SI-4;Lo;0;L;;;;;N;;;;; +1B048;HENTAIGANA LETTER SI-5;Lo;0;L;;;;;N;;;;; +1B049;HENTAIGANA LETTER SI-6;Lo;0;L;;;;;N;;;;; +1B04A;HENTAIGANA LETTER SU-1;Lo;0;L;;;;;N;;;;; +1B04B;HENTAIGANA LETTER SU-2;Lo;0;L;;;;;N;;;;; +1B04C;HENTAIGANA LETTER SU-3;Lo;0;L;;;;;N;;;;; +1B04D;HENTAIGANA LETTER SU-4;Lo;0;L;;;;;N;;;;; +1B04E;HENTAIGANA LETTER SU-5;Lo;0;L;;;;;N;;;;; +1B04F;HENTAIGANA LETTER SU-6;Lo;0;L;;;;;N;;;;; +1B050;HENTAIGANA LETTER SU-7;Lo;0;L;;;;;N;;;;; +1B051;HENTAIGANA LETTER SU-8;Lo;0;L;;;;;N;;;;; +1B052;HENTAIGANA LETTER SE-1;Lo;0;L;;;;;N;;;;; +1B053;HENTAIGANA LETTER SE-2;Lo;0;L;;;;;N;;;;; +1B054;HENTAIGANA LETTER SE-3;Lo;0;L;;;;;N;;;;; +1B055;HENTAIGANA LETTER SE-4;Lo;0;L;;;;;N;;;;; +1B056;HENTAIGANA LETTER SE-5;Lo;0;L;;;;;N;;;;; +1B057;HENTAIGANA LETTER SO-1;Lo;0;L;;;;;N;;;;; +1B058;HENTAIGANA LETTER SO-2;Lo;0;L;;;;;N;;;;; +1B059;HENTAIGANA LETTER SO-3;Lo;0;L;;;;;N;;;;; +1B05A;HENTAIGANA LETTER SO-4;Lo;0;L;;;;;N;;;;; +1B05B;HENTAIGANA LETTER SO-5;Lo;0;L;;;;;N;;;;; +1B05C;HENTAIGANA LETTER SO-6;Lo;0;L;;;;;N;;;;; +1B05D;HENTAIGANA LETTER SO-7;Lo;0;L;;;;;N;;;;; +1B05E;HENTAIGANA LETTER TA-1;Lo;0;L;;;;;N;;;;; +1B05F;HENTAIGANA LETTER TA-2;Lo;0;L;;;;;N;;;;; +1B060;HENTAIGANA LETTER TA-3;Lo;0;L;;;;;N;;;;; +1B061;HENTAIGANA LETTER TA-4;Lo;0;L;;;;;N;;;;; +1B062;HENTAIGANA LETTER TI-1;Lo;0;L;;;;;N;;;;; +1B063;HENTAIGANA LETTER TI-2;Lo;0;L;;;;;N;;;;; +1B064;HENTAIGANA LETTER TI-3;Lo;0;L;;;;;N;;;;; +1B065;HENTAIGANA LETTER TI-4;Lo;0;L;;;;;N;;;;; +1B066;HENTAIGANA LETTER TI-5;Lo;0;L;;;;;N;;;;; +1B067;HENTAIGANA LETTER TI-6;Lo;0;L;;;;;N;;;;; +1B068;HENTAIGANA LETTER TI-7;Lo;0;L;;;;;N;;;;; +1B069;HENTAIGANA LETTER TU-1;Lo;0;L;;;;;N;;;;; +1B06A;HENTAIGANA LETTER TU-2;Lo;0;L;;;;;N;;;;; +1B06B;HENTAIGANA LETTER TU-3;Lo;0;L;;;;;N;;;;; +1B06C;HENTAIGANA LETTER TU-4;Lo;0;L;;;;;N;;;;; +1B06D;HENTAIGANA LETTER TU-TO;Lo;0;L;;;;;N;;;;; +1B06E;HENTAIGANA LETTER TE-1;Lo;0;L;;;;;N;;;;; +1B06F;HENTAIGANA LETTER TE-2;Lo;0;L;;;;;N;;;;; +1B070;HENTAIGANA LETTER TE-3;Lo;0;L;;;;;N;;;;; +1B071;HENTAIGANA LETTER TE-4;Lo;0;L;;;;;N;;;;; +1B072;HENTAIGANA LETTER TE-5;Lo;0;L;;;;;N;;;;; +1B073;HENTAIGANA LETTER TE-6;Lo;0;L;;;;;N;;;;; +1B074;HENTAIGANA LETTER TE-7;Lo;0;L;;;;;N;;;;; +1B075;HENTAIGANA LETTER TE-8;Lo;0;L;;;;;N;;;;; +1B076;HENTAIGANA LETTER TE-9;Lo;0;L;;;;;N;;;;; +1B077;HENTAIGANA LETTER TO-1;Lo;0;L;;;;;N;;;;; +1B078;HENTAIGANA LETTER TO-2;Lo;0;L;;;;;N;;;;; +1B079;HENTAIGANA LETTER TO-3;Lo;0;L;;;;;N;;;;; +1B07A;HENTAIGANA LETTER TO-4;Lo;0;L;;;;;N;;;;; +1B07B;HENTAIGANA LETTER TO-5;Lo;0;L;;;;;N;;;;; +1B07C;HENTAIGANA LETTER TO-6;Lo;0;L;;;;;N;;;;; +1B07D;HENTAIGANA LETTER TO-RA;Lo;0;L;;;;;N;;;;; +1B07E;HENTAIGANA LETTER NA-1;Lo;0;L;;;;;N;;;;; +1B07F;HENTAIGANA LETTER NA-2;Lo;0;L;;;;;N;;;;; +1B080;HENTAIGANA LETTER NA-3;Lo;0;L;;;;;N;;;;; +1B081;HENTAIGANA LETTER NA-4;Lo;0;L;;;;;N;;;;; +1B082;HENTAIGANA LETTER NA-5;Lo;0;L;;;;;N;;;;; +1B083;HENTAIGANA LETTER NA-6;Lo;0;L;;;;;N;;;;; +1B084;HENTAIGANA LETTER NA-7;Lo;0;L;;;;;N;;;;; +1B085;HENTAIGANA LETTER NA-8;Lo;0;L;;;;;N;;;;; +1B086;HENTAIGANA LETTER NA-9;Lo;0;L;;;;;N;;;;; +1B087;HENTAIGANA LETTER NI-1;Lo;0;L;;;;;N;;;;; +1B088;HENTAIGANA LETTER NI-2;Lo;0;L;;;;;N;;;;; +1B089;HENTAIGANA LETTER NI-3;Lo;0;L;;;;;N;;;;; +1B08A;HENTAIGANA LETTER NI-4;Lo;0;L;;;;;N;;;;; +1B08B;HENTAIGANA LETTER NI-5;Lo;0;L;;;;;N;;;;; +1B08C;HENTAIGANA LETTER NI-6;Lo;0;L;;;;;N;;;;; +1B08D;HENTAIGANA LETTER NI-7;Lo;0;L;;;;;N;;;;; +1B08E;HENTAIGANA LETTER NI-TE;Lo;0;L;;;;;N;;;;; +1B08F;HENTAIGANA LETTER NU-1;Lo;0;L;;;;;N;;;;; +1B090;HENTAIGANA LETTER NU-2;Lo;0;L;;;;;N;;;;; +1B091;HENTAIGANA LETTER NU-3;Lo;0;L;;;;;N;;;;; +1B092;HENTAIGANA LETTER NE-1;Lo;0;L;;;;;N;;;;; +1B093;HENTAIGANA LETTER NE-2;Lo;0;L;;;;;N;;;;; +1B094;HENTAIGANA LETTER NE-3;Lo;0;L;;;;;N;;;;; +1B095;HENTAIGANA LETTER NE-4;Lo;0;L;;;;;N;;;;; +1B096;HENTAIGANA LETTER NE-5;Lo;0;L;;;;;N;;;;; +1B097;HENTAIGANA LETTER NE-6;Lo;0;L;;;;;N;;;;; +1B098;HENTAIGANA LETTER NE-KO;Lo;0;L;;;;;N;;;;; +1B099;HENTAIGANA LETTER NO-1;Lo;0;L;;;;;N;;;;; +1B09A;HENTAIGANA LETTER NO-2;Lo;0;L;;;;;N;;;;; +1B09B;HENTAIGANA LETTER NO-3;Lo;0;L;;;;;N;;;;; +1B09C;HENTAIGANA LETTER NO-4;Lo;0;L;;;;;N;;;;; +1B09D;HENTAIGANA LETTER NO-5;Lo;0;L;;;;;N;;;;; +1B09E;HENTAIGANA LETTER HA-1;Lo;0;L;;;;;N;;;;; +1B09F;HENTAIGANA LETTER HA-2;Lo;0;L;;;;;N;;;;; +1B0A0;HENTAIGANA LETTER HA-3;Lo;0;L;;;;;N;;;;; +1B0A1;HENTAIGANA LETTER HA-4;Lo;0;L;;;;;N;;;;; +1B0A2;HENTAIGANA LETTER HA-5;Lo;0;L;;;;;N;;;;; +1B0A3;HENTAIGANA LETTER HA-6;Lo;0;L;;;;;N;;;;; +1B0A4;HENTAIGANA LETTER HA-7;Lo;0;L;;;;;N;;;;; +1B0A5;HENTAIGANA LETTER HA-8;Lo;0;L;;;;;N;;;;; +1B0A6;HENTAIGANA LETTER HA-9;Lo;0;L;;;;;N;;;;; +1B0A7;HENTAIGANA LETTER HA-10;Lo;0;L;;;;;N;;;;; +1B0A8;HENTAIGANA LETTER HA-11;Lo;0;L;;;;;N;;;;; +1B0A9;HENTAIGANA LETTER HI-1;Lo;0;L;;;;;N;;;;; +1B0AA;HENTAIGANA LETTER HI-2;Lo;0;L;;;;;N;;;;; +1B0AB;HENTAIGANA LETTER HI-3;Lo;0;L;;;;;N;;;;; +1B0AC;HENTAIGANA LETTER HI-4;Lo;0;L;;;;;N;;;;; +1B0AD;HENTAIGANA LETTER HI-5;Lo;0;L;;;;;N;;;;; +1B0AE;HENTAIGANA LETTER HI-6;Lo;0;L;;;;;N;;;;; +1B0AF;HENTAIGANA LETTER HI-7;Lo;0;L;;;;;N;;;;; +1B0B0;HENTAIGANA LETTER HU-1;Lo;0;L;;;;;N;;;;; +1B0B1;HENTAIGANA LETTER HU-2;Lo;0;L;;;;;N;;;;; +1B0B2;HENTAIGANA LETTER HU-3;Lo;0;L;;;;;N;;;;; +1B0B3;HENTAIGANA LETTER HE-1;Lo;0;L;;;;;N;;;;; +1B0B4;HENTAIGANA LETTER HE-2;Lo;0;L;;;;;N;;;;; +1B0B5;HENTAIGANA LETTER HE-3;Lo;0;L;;;;;N;;;;; +1B0B6;HENTAIGANA LETTER HE-4;Lo;0;L;;;;;N;;;;; +1B0B7;HENTAIGANA LETTER HE-5;Lo;0;L;;;;;N;;;;; +1B0B8;HENTAIGANA LETTER HE-6;Lo;0;L;;;;;N;;;;; +1B0B9;HENTAIGANA LETTER HE-7;Lo;0;L;;;;;N;;;;; +1B0BA;HENTAIGANA LETTER HO-1;Lo;0;L;;;;;N;;;;; +1B0BB;HENTAIGANA LETTER HO-2;Lo;0;L;;;;;N;;;;; +1B0BC;HENTAIGANA LETTER HO-3;Lo;0;L;;;;;N;;;;; +1B0BD;HENTAIGANA LETTER HO-4;Lo;0;L;;;;;N;;;;; +1B0BE;HENTAIGANA LETTER HO-5;Lo;0;L;;;;;N;;;;; +1B0BF;HENTAIGANA LETTER HO-6;Lo;0;L;;;;;N;;;;; +1B0C0;HENTAIGANA LETTER HO-7;Lo;0;L;;;;;N;;;;; +1B0C1;HENTAIGANA LETTER HO-8;Lo;0;L;;;;;N;;;;; +1B0C2;HENTAIGANA LETTER MA-1;Lo;0;L;;;;;N;;;;; +1B0C3;HENTAIGANA LETTER MA-2;Lo;0;L;;;;;N;;;;; +1B0C4;HENTAIGANA LETTER MA-3;Lo;0;L;;;;;N;;;;; +1B0C5;HENTAIGANA LETTER MA-4;Lo;0;L;;;;;N;;;;; +1B0C6;HENTAIGANA LETTER MA-5;Lo;0;L;;;;;N;;;;; +1B0C7;HENTAIGANA LETTER MA-6;Lo;0;L;;;;;N;;;;; +1B0C8;HENTAIGANA LETTER MA-7;Lo;0;L;;;;;N;;;;; +1B0C9;HENTAIGANA LETTER MI-1;Lo;0;L;;;;;N;;;;; +1B0CA;HENTAIGANA LETTER MI-2;Lo;0;L;;;;;N;;;;; +1B0CB;HENTAIGANA LETTER MI-3;Lo;0;L;;;;;N;;;;; +1B0CC;HENTAIGANA LETTER MI-4;Lo;0;L;;;;;N;;;;; +1B0CD;HENTAIGANA LETTER MI-5;Lo;0;L;;;;;N;;;;; +1B0CE;HENTAIGANA LETTER MI-6;Lo;0;L;;;;;N;;;;; +1B0CF;HENTAIGANA LETTER MI-7;Lo;0;L;;;;;N;;;;; +1B0D0;HENTAIGANA LETTER MU-1;Lo;0;L;;;;;N;;;;; +1B0D1;HENTAIGANA LETTER MU-2;Lo;0;L;;;;;N;;;;; +1B0D2;HENTAIGANA LETTER MU-3;Lo;0;L;;;;;N;;;;; +1B0D3;HENTAIGANA LETTER MU-4;Lo;0;L;;;;;N;;;;; +1B0D4;HENTAIGANA LETTER ME-1;Lo;0;L;;;;;N;;;;; +1B0D5;HENTAIGANA LETTER ME-2;Lo;0;L;;;;;N;;;;; +1B0D6;HENTAIGANA LETTER ME-MA;Lo;0;L;;;;;N;;;;; +1B0D7;HENTAIGANA LETTER MO-1;Lo;0;L;;;;;N;;;;; +1B0D8;HENTAIGANA LETTER MO-2;Lo;0;L;;;;;N;;;;; +1B0D9;HENTAIGANA LETTER MO-3;Lo;0;L;;;;;N;;;;; +1B0DA;HENTAIGANA LETTER MO-4;Lo;0;L;;;;;N;;;;; +1B0DB;HENTAIGANA LETTER MO-5;Lo;0;L;;;;;N;;;;; +1B0DC;HENTAIGANA LETTER MO-6;Lo;0;L;;;;;N;;;;; +1B0DD;HENTAIGANA LETTER YA-1;Lo;0;L;;;;;N;;;;; +1B0DE;HENTAIGANA LETTER YA-2;Lo;0;L;;;;;N;;;;; +1B0DF;HENTAIGANA LETTER YA-3;Lo;0;L;;;;;N;;;;; +1B0E0;HENTAIGANA LETTER YA-4;Lo;0;L;;;;;N;;;;; +1B0E1;HENTAIGANA LETTER YA-5;Lo;0;L;;;;;N;;;;; +1B0E2;HENTAIGANA LETTER YA-YO;Lo;0;L;;;;;N;;;;; +1B0E3;HENTAIGANA LETTER YU-1;Lo;0;L;;;;;N;;;;; +1B0E4;HENTAIGANA LETTER YU-2;Lo;0;L;;;;;N;;;;; +1B0E5;HENTAIGANA LETTER YU-3;Lo;0;L;;;;;N;;;;; +1B0E6;HENTAIGANA LETTER YU-4;Lo;0;L;;;;;N;;;;; +1B0E7;HENTAIGANA LETTER YO-1;Lo;0;L;;;;;N;;;;; +1B0E8;HENTAIGANA LETTER YO-2;Lo;0;L;;;;;N;;;;; +1B0E9;HENTAIGANA LETTER YO-3;Lo;0;L;;;;;N;;;;; +1B0EA;HENTAIGANA LETTER YO-4;Lo;0;L;;;;;N;;;;; +1B0EB;HENTAIGANA LETTER YO-5;Lo;0;L;;;;;N;;;;; +1B0EC;HENTAIGANA LETTER YO-6;Lo;0;L;;;;;N;;;;; +1B0ED;HENTAIGANA LETTER RA-1;Lo;0;L;;;;;N;;;;; +1B0EE;HENTAIGANA LETTER RA-2;Lo;0;L;;;;;N;;;;; +1B0EF;HENTAIGANA LETTER RA-3;Lo;0;L;;;;;N;;;;; +1B0F0;HENTAIGANA LETTER RA-4;Lo;0;L;;;;;N;;;;; +1B0F1;HENTAIGANA LETTER RI-1;Lo;0;L;;;;;N;;;;; +1B0F2;HENTAIGANA LETTER RI-2;Lo;0;L;;;;;N;;;;; +1B0F3;HENTAIGANA LETTER RI-3;Lo;0;L;;;;;N;;;;; +1B0F4;HENTAIGANA LETTER RI-4;Lo;0;L;;;;;N;;;;; +1B0F5;HENTAIGANA LETTER RI-5;Lo;0;L;;;;;N;;;;; +1B0F6;HENTAIGANA LETTER RI-6;Lo;0;L;;;;;N;;;;; +1B0F7;HENTAIGANA LETTER RI-7;Lo;0;L;;;;;N;;;;; +1B0F8;HENTAIGANA LETTER RU-1;Lo;0;L;;;;;N;;;;; +1B0F9;HENTAIGANA LETTER RU-2;Lo;0;L;;;;;N;;;;; +1B0FA;HENTAIGANA LETTER RU-3;Lo;0;L;;;;;N;;;;; +1B0FB;HENTAIGANA LETTER RU-4;Lo;0;L;;;;;N;;;;; +1B0FC;HENTAIGANA LETTER RU-5;Lo;0;L;;;;;N;;;;; +1B0FD;HENTAIGANA LETTER RU-6;Lo;0;L;;;;;N;;;;; +1B0FE;HENTAIGANA LETTER RE-1;Lo;0;L;;;;;N;;;;; +1B0FF;HENTAIGANA LETTER RE-2;Lo;0;L;;;;;N;;;;; +1B100;HENTAIGANA LETTER RE-3;Lo;0;L;;;;;N;;;;; +1B101;HENTAIGANA LETTER RE-4;Lo;0;L;;;;;N;;;;; +1B102;HENTAIGANA LETTER RO-1;Lo;0;L;;;;;N;;;;; +1B103;HENTAIGANA LETTER RO-2;Lo;0;L;;;;;N;;;;; +1B104;HENTAIGANA LETTER RO-3;Lo;0;L;;;;;N;;;;; +1B105;HENTAIGANA LETTER RO-4;Lo;0;L;;;;;N;;;;; +1B106;HENTAIGANA LETTER RO-5;Lo;0;L;;;;;N;;;;; +1B107;HENTAIGANA LETTER RO-6;Lo;0;L;;;;;N;;;;; +1B108;HENTAIGANA LETTER WA-1;Lo;0;L;;;;;N;;;;; +1B109;HENTAIGANA LETTER WA-2;Lo;0;L;;;;;N;;;;; +1B10A;HENTAIGANA LETTER WA-3;Lo;0;L;;;;;N;;;;; +1B10B;HENTAIGANA LETTER WA-4;Lo;0;L;;;;;N;;;;; +1B10C;HENTAIGANA LETTER WA-5;Lo;0;L;;;;;N;;;;; +1B10D;HENTAIGANA LETTER WI-1;Lo;0;L;;;;;N;;;;; +1B10E;HENTAIGANA LETTER WI-2;Lo;0;L;;;;;N;;;;; +1B10F;HENTAIGANA LETTER WI-3;Lo;0;L;;;;;N;;;;; +1B110;HENTAIGANA LETTER WI-4;Lo;0;L;;;;;N;;;;; +1B111;HENTAIGANA LETTER WI-5;Lo;0;L;;;;;N;;;;; +1B112;HENTAIGANA LETTER WE-1;Lo;0;L;;;;;N;;;;; +1B113;HENTAIGANA LETTER WE-2;Lo;0;L;;;;;N;;;;; +1B114;HENTAIGANA LETTER WE-3;Lo;0;L;;;;;N;;;;; +1B115;HENTAIGANA LETTER WE-4;Lo;0;L;;;;;N;;;;; +1B116;HENTAIGANA LETTER WO-1;Lo;0;L;;;;;N;;;;; +1B117;HENTAIGANA LETTER WO-2;Lo;0;L;;;;;N;;;;; +1B118;HENTAIGANA LETTER WO-3;Lo;0;L;;;;;N;;;;; +1B119;HENTAIGANA LETTER WO-4;Lo;0;L;;;;;N;;;;; +1B11A;HENTAIGANA LETTER WO-5;Lo;0;L;;;;;N;;;;; +1B11B;HENTAIGANA LETTER WO-6;Lo;0;L;;;;;N;;;;; +1B11C;HENTAIGANA LETTER WO-7;Lo;0;L;;;;;N;;;;; +1B11D;HENTAIGANA LETTER N-MU-MO-1;Lo;0;L;;;;;N;;;;; +1B11E;HENTAIGANA LETTER N-MU-MO-2;Lo;0;L;;;;;N;;;;; +1B170;NUSHU CHARACTER-1B170;Lo;0;L;;;;;N;;;;; +1B171;NUSHU CHARACTER-1B171;Lo;0;L;;;;;N;;;;; +1B172;NUSHU CHARACTER-1B172;Lo;0;L;;;;;N;;;;; +1B173;NUSHU CHARACTER-1B173;Lo;0;L;;;;;N;;;;; +1B174;NUSHU CHARACTER-1B174;Lo;0;L;;;;;N;;;;; +1B175;NUSHU CHARACTER-1B175;Lo;0;L;;;;;N;;;;; +1B176;NUSHU CHARACTER-1B176;Lo;0;L;;;;;N;;;;; +1B177;NUSHU CHARACTER-1B177;Lo;0;L;;;;;N;;;;; +1B178;NUSHU CHARACTER-1B178;Lo;0;L;;;;;N;;;;; +1B179;NUSHU CHARACTER-1B179;Lo;0;L;;;;;N;;;;; +1B17A;NUSHU CHARACTER-1B17A;Lo;0;L;;;;;N;;;;; +1B17B;NUSHU CHARACTER-1B17B;Lo;0;L;;;;;N;;;;; +1B17C;NUSHU CHARACTER-1B17C;Lo;0;L;;;;;N;;;;; +1B17D;NUSHU CHARACTER-1B17D;Lo;0;L;;;;;N;;;;; +1B17E;NUSHU CHARACTER-1B17E;Lo;0;L;;;;;N;;;;; +1B17F;NUSHU CHARACTER-1B17F;Lo;0;L;;;;;N;;;;; +1B180;NUSHU CHARACTER-1B180;Lo;0;L;;;;;N;;;;; +1B181;NUSHU CHARACTER-1B181;Lo;0;L;;;;;N;;;;; +1B182;NUSHU CHARACTER-1B182;Lo;0;L;;;;;N;;;;; +1B183;NUSHU CHARACTER-1B183;Lo;0;L;;;;;N;;;;; +1B184;NUSHU CHARACTER-1B184;Lo;0;L;;;;;N;;;;; +1B185;NUSHU CHARACTER-1B185;Lo;0;L;;;;;N;;;;; +1B186;NUSHU CHARACTER-1B186;Lo;0;L;;;;;N;;;;; +1B187;NUSHU CHARACTER-1B187;Lo;0;L;;;;;N;;;;; +1B188;NUSHU CHARACTER-1B188;Lo;0;L;;;;;N;;;;; +1B189;NUSHU CHARACTER-1B189;Lo;0;L;;;;;N;;;;; +1B18A;NUSHU CHARACTER-1B18A;Lo;0;L;;;;;N;;;;; +1B18B;NUSHU CHARACTER-1B18B;Lo;0;L;;;;;N;;;;; +1B18C;NUSHU CHARACTER-1B18C;Lo;0;L;;;;;N;;;;; +1B18D;NUSHU CHARACTER-1B18D;Lo;0;L;;;;;N;;;;; +1B18E;NUSHU CHARACTER-1B18E;Lo;0;L;;;;;N;;;;; +1B18F;NUSHU CHARACTER-1B18F;Lo;0;L;;;;;N;;;;; +1B190;NUSHU CHARACTER-1B190;Lo;0;L;;;;;N;;;;; +1B191;NUSHU CHARACTER-1B191;Lo;0;L;;;;;N;;;;; +1B192;NUSHU CHARACTER-1B192;Lo;0;L;;;;;N;;;;; +1B193;NUSHU CHARACTER-1B193;Lo;0;L;;;;;N;;;;; +1B194;NUSHU CHARACTER-1B194;Lo;0;L;;;;;N;;;;; +1B195;NUSHU CHARACTER-1B195;Lo;0;L;;;;;N;;;;; +1B196;NUSHU CHARACTER-1B196;Lo;0;L;;;;;N;;;;; +1B197;NUSHU CHARACTER-1B197;Lo;0;L;;;;;N;;;;; +1B198;NUSHU CHARACTER-1B198;Lo;0;L;;;;;N;;;;; +1B199;NUSHU CHARACTER-1B199;Lo;0;L;;;;;N;;;;; +1B19A;NUSHU CHARACTER-1B19A;Lo;0;L;;;;;N;;;;; +1B19B;NUSHU CHARACTER-1B19B;Lo;0;L;;;;;N;;;;; +1B19C;NUSHU CHARACTER-1B19C;Lo;0;L;;;;;N;;;;; +1B19D;NUSHU CHARACTER-1B19D;Lo;0;L;;;;;N;;;;; +1B19E;NUSHU CHARACTER-1B19E;Lo;0;L;;;;;N;;;;; +1B19F;NUSHU CHARACTER-1B19F;Lo;0;L;;;;;N;;;;; +1B1A0;NUSHU CHARACTER-1B1A0;Lo;0;L;;;;;N;;;;; +1B1A1;NUSHU CHARACTER-1B1A1;Lo;0;L;;;;;N;;;;; +1B1A2;NUSHU CHARACTER-1B1A2;Lo;0;L;;;;;N;;;;; +1B1A3;NUSHU CHARACTER-1B1A3;Lo;0;L;;;;;N;;;;; +1B1A4;NUSHU CHARACTER-1B1A4;Lo;0;L;;;;;N;;;;; +1B1A5;NUSHU CHARACTER-1B1A5;Lo;0;L;;;;;N;;;;; +1B1A6;NUSHU CHARACTER-1B1A6;Lo;0;L;;;;;N;;;;; +1B1A7;NUSHU CHARACTER-1B1A7;Lo;0;L;;;;;N;;;;; +1B1A8;NUSHU CHARACTER-1B1A8;Lo;0;L;;;;;N;;;;; +1B1A9;NUSHU CHARACTER-1B1A9;Lo;0;L;;;;;N;;;;; +1B1AA;NUSHU CHARACTER-1B1AA;Lo;0;L;;;;;N;;;;; +1B1AB;NUSHU CHARACTER-1B1AB;Lo;0;L;;;;;N;;;;; +1B1AC;NUSHU CHARACTER-1B1AC;Lo;0;L;;;;;N;;;;; +1B1AD;NUSHU CHARACTER-1B1AD;Lo;0;L;;;;;N;;;;; +1B1AE;NUSHU CHARACTER-1B1AE;Lo;0;L;;;;;N;;;;; +1B1AF;NUSHU CHARACTER-1B1AF;Lo;0;L;;;;;N;;;;; +1B1B0;NUSHU CHARACTER-1B1B0;Lo;0;L;;;;;N;;;;; +1B1B1;NUSHU CHARACTER-1B1B1;Lo;0;L;;;;;N;;;;; +1B1B2;NUSHU CHARACTER-1B1B2;Lo;0;L;;;;;N;;;;; +1B1B3;NUSHU CHARACTER-1B1B3;Lo;0;L;;;;;N;;;;; +1B1B4;NUSHU CHARACTER-1B1B4;Lo;0;L;;;;;N;;;;; +1B1B5;NUSHU CHARACTER-1B1B5;Lo;0;L;;;;;N;;;;; +1B1B6;NUSHU CHARACTER-1B1B6;Lo;0;L;;;;;N;;;;; +1B1B7;NUSHU CHARACTER-1B1B7;Lo;0;L;;;;;N;;;;; +1B1B8;NUSHU CHARACTER-1B1B8;Lo;0;L;;;;;N;;;;; +1B1B9;NUSHU CHARACTER-1B1B9;Lo;0;L;;;;;N;;;;; +1B1BA;NUSHU CHARACTER-1B1BA;Lo;0;L;;;;;N;;;;; +1B1BB;NUSHU CHARACTER-1B1BB;Lo;0;L;;;;;N;;;;; +1B1BC;NUSHU CHARACTER-1B1BC;Lo;0;L;;;;;N;;;;; +1B1BD;NUSHU CHARACTER-1B1BD;Lo;0;L;;;;;N;;;;; +1B1BE;NUSHU CHARACTER-1B1BE;Lo;0;L;;;;;N;;;;; +1B1BF;NUSHU CHARACTER-1B1BF;Lo;0;L;;;;;N;;;;; +1B1C0;NUSHU CHARACTER-1B1C0;Lo;0;L;;;;;N;;;;; +1B1C1;NUSHU CHARACTER-1B1C1;Lo;0;L;;;;;N;;;;; +1B1C2;NUSHU CHARACTER-1B1C2;Lo;0;L;;;;;N;;;;; +1B1C3;NUSHU CHARACTER-1B1C3;Lo;0;L;;;;;N;;;;; +1B1C4;NUSHU CHARACTER-1B1C4;Lo;0;L;;;;;N;;;;; +1B1C5;NUSHU CHARACTER-1B1C5;Lo;0;L;;;;;N;;;;; +1B1C6;NUSHU CHARACTER-1B1C6;Lo;0;L;;;;;N;;;;; +1B1C7;NUSHU CHARACTER-1B1C7;Lo;0;L;;;;;N;;;;; +1B1C8;NUSHU CHARACTER-1B1C8;Lo;0;L;;;;;N;;;;; +1B1C9;NUSHU CHARACTER-1B1C9;Lo;0;L;;;;;N;;;;; +1B1CA;NUSHU CHARACTER-1B1CA;Lo;0;L;;;;;N;;;;; +1B1CB;NUSHU CHARACTER-1B1CB;Lo;0;L;;;;;N;;;;; +1B1CC;NUSHU CHARACTER-1B1CC;Lo;0;L;;;;;N;;;;; +1B1CD;NUSHU CHARACTER-1B1CD;Lo;0;L;;;;;N;;;;; +1B1CE;NUSHU CHARACTER-1B1CE;Lo;0;L;;;;;N;;;;; +1B1CF;NUSHU CHARACTER-1B1CF;Lo;0;L;;;;;N;;;;; +1B1D0;NUSHU CHARACTER-1B1D0;Lo;0;L;;;;;N;;;;; +1B1D1;NUSHU CHARACTER-1B1D1;Lo;0;L;;;;;N;;;;; +1B1D2;NUSHU CHARACTER-1B1D2;Lo;0;L;;;;;N;;;;; +1B1D3;NUSHU CHARACTER-1B1D3;Lo;0;L;;;;;N;;;;; +1B1D4;NUSHU CHARACTER-1B1D4;Lo;0;L;;;;;N;;;;; +1B1D5;NUSHU CHARACTER-1B1D5;Lo;0;L;;;;;N;;;;; +1B1D6;NUSHU CHARACTER-1B1D6;Lo;0;L;;;;;N;;;;; +1B1D7;NUSHU CHARACTER-1B1D7;Lo;0;L;;;;;N;;;;; +1B1D8;NUSHU CHARACTER-1B1D8;Lo;0;L;;;;;N;;;;; +1B1D9;NUSHU CHARACTER-1B1D9;Lo;0;L;;;;;N;;;;; +1B1DA;NUSHU CHARACTER-1B1DA;Lo;0;L;;;;;N;;;;; +1B1DB;NUSHU CHARACTER-1B1DB;Lo;0;L;;;;;N;;;;; +1B1DC;NUSHU CHARACTER-1B1DC;Lo;0;L;;;;;N;;;;; +1B1DD;NUSHU CHARACTER-1B1DD;Lo;0;L;;;;;N;;;;; +1B1DE;NUSHU CHARACTER-1B1DE;Lo;0;L;;;;;N;;;;; +1B1DF;NUSHU CHARACTER-1B1DF;Lo;0;L;;;;;N;;;;; +1B1E0;NUSHU CHARACTER-1B1E0;Lo;0;L;;;;;N;;;;; +1B1E1;NUSHU CHARACTER-1B1E1;Lo;0;L;;;;;N;;;;; +1B1E2;NUSHU CHARACTER-1B1E2;Lo;0;L;;;;;N;;;;; +1B1E3;NUSHU CHARACTER-1B1E3;Lo;0;L;;;;;N;;;;; +1B1E4;NUSHU CHARACTER-1B1E4;Lo;0;L;;;;;N;;;;; +1B1E5;NUSHU CHARACTER-1B1E5;Lo;0;L;;;;;N;;;;; +1B1E6;NUSHU CHARACTER-1B1E6;Lo;0;L;;;;;N;;;;; +1B1E7;NUSHU CHARACTER-1B1E7;Lo;0;L;;;;;N;;;;; +1B1E8;NUSHU CHARACTER-1B1E8;Lo;0;L;;;;;N;;;;; +1B1E9;NUSHU CHARACTER-1B1E9;Lo;0;L;;;;;N;;;;; +1B1EA;NUSHU CHARACTER-1B1EA;Lo;0;L;;;;;N;;;;; +1B1EB;NUSHU CHARACTER-1B1EB;Lo;0;L;;;;;N;;;;; +1B1EC;NUSHU CHARACTER-1B1EC;Lo;0;L;;;;;N;;;;; +1B1ED;NUSHU CHARACTER-1B1ED;Lo;0;L;;;;;N;;;;; +1B1EE;NUSHU CHARACTER-1B1EE;Lo;0;L;;;;;N;;;;; +1B1EF;NUSHU CHARACTER-1B1EF;Lo;0;L;;;;;N;;;;; +1B1F0;NUSHU CHARACTER-1B1F0;Lo;0;L;;;;;N;;;;; +1B1F1;NUSHU CHARACTER-1B1F1;Lo;0;L;;;;;N;;;;; +1B1F2;NUSHU CHARACTER-1B1F2;Lo;0;L;;;;;N;;;;; +1B1F3;NUSHU CHARACTER-1B1F3;Lo;0;L;;;;;N;;;;; +1B1F4;NUSHU CHARACTER-1B1F4;Lo;0;L;;;;;N;;;;; +1B1F5;NUSHU CHARACTER-1B1F5;Lo;0;L;;;;;N;;;;; +1B1F6;NUSHU CHARACTER-1B1F6;Lo;0;L;;;;;N;;;;; +1B1F7;NUSHU CHARACTER-1B1F7;Lo;0;L;;;;;N;;;;; +1B1F8;NUSHU CHARACTER-1B1F8;Lo;0;L;;;;;N;;;;; +1B1F9;NUSHU CHARACTER-1B1F9;Lo;0;L;;;;;N;;;;; +1B1FA;NUSHU CHARACTER-1B1FA;Lo;0;L;;;;;N;;;;; +1B1FB;NUSHU CHARACTER-1B1FB;Lo;0;L;;;;;N;;;;; +1B1FC;NUSHU CHARACTER-1B1FC;Lo;0;L;;;;;N;;;;; +1B1FD;NUSHU CHARACTER-1B1FD;Lo;0;L;;;;;N;;;;; +1B1FE;NUSHU CHARACTER-1B1FE;Lo;0;L;;;;;N;;;;; +1B1FF;NUSHU CHARACTER-1B1FF;Lo;0;L;;;;;N;;;;; +1B200;NUSHU CHARACTER-1B200;Lo;0;L;;;;;N;;;;; +1B201;NUSHU CHARACTER-1B201;Lo;0;L;;;;;N;;;;; +1B202;NUSHU CHARACTER-1B202;Lo;0;L;;;;;N;;;;; +1B203;NUSHU CHARACTER-1B203;Lo;0;L;;;;;N;;;;; +1B204;NUSHU CHARACTER-1B204;Lo;0;L;;;;;N;;;;; +1B205;NUSHU CHARACTER-1B205;Lo;0;L;;;;;N;;;;; +1B206;NUSHU CHARACTER-1B206;Lo;0;L;;;;;N;;;;; +1B207;NUSHU CHARACTER-1B207;Lo;0;L;;;;;N;;;;; +1B208;NUSHU CHARACTER-1B208;Lo;0;L;;;;;N;;;;; +1B209;NUSHU CHARACTER-1B209;Lo;0;L;;;;;N;;;;; +1B20A;NUSHU CHARACTER-1B20A;Lo;0;L;;;;;N;;;;; +1B20B;NUSHU CHARACTER-1B20B;Lo;0;L;;;;;N;;;;; +1B20C;NUSHU CHARACTER-1B20C;Lo;0;L;;;;;N;;;;; +1B20D;NUSHU CHARACTER-1B20D;Lo;0;L;;;;;N;;;;; +1B20E;NUSHU CHARACTER-1B20E;Lo;0;L;;;;;N;;;;; +1B20F;NUSHU CHARACTER-1B20F;Lo;0;L;;;;;N;;;;; +1B210;NUSHU CHARACTER-1B210;Lo;0;L;;;;;N;;;;; +1B211;NUSHU CHARACTER-1B211;Lo;0;L;;;;;N;;;;; +1B212;NUSHU CHARACTER-1B212;Lo;0;L;;;;;N;;;;; +1B213;NUSHU CHARACTER-1B213;Lo;0;L;;;;;N;;;;; +1B214;NUSHU CHARACTER-1B214;Lo;0;L;;;;;N;;;;; +1B215;NUSHU CHARACTER-1B215;Lo;0;L;;;;;N;;;;; +1B216;NUSHU CHARACTER-1B216;Lo;0;L;;;;;N;;;;; +1B217;NUSHU CHARACTER-1B217;Lo;0;L;;;;;N;;;;; +1B218;NUSHU CHARACTER-1B218;Lo;0;L;;;;;N;;;;; +1B219;NUSHU CHARACTER-1B219;Lo;0;L;;;;;N;;;;; +1B21A;NUSHU CHARACTER-1B21A;Lo;0;L;;;;;N;;;;; +1B21B;NUSHU CHARACTER-1B21B;Lo;0;L;;;;;N;;;;; +1B21C;NUSHU CHARACTER-1B21C;Lo;0;L;;;;;N;;;;; +1B21D;NUSHU CHARACTER-1B21D;Lo;0;L;;;;;N;;;;; +1B21E;NUSHU CHARACTER-1B21E;Lo;0;L;;;;;N;;;;; +1B21F;NUSHU CHARACTER-1B21F;Lo;0;L;;;;;N;;;;; +1B220;NUSHU CHARACTER-1B220;Lo;0;L;;;;;N;;;;; +1B221;NUSHU CHARACTER-1B221;Lo;0;L;;;;;N;;;;; +1B222;NUSHU CHARACTER-1B222;Lo;0;L;;;;;N;;;;; +1B223;NUSHU CHARACTER-1B223;Lo;0;L;;;;;N;;;;; +1B224;NUSHU CHARACTER-1B224;Lo;0;L;;;;;N;;;;; +1B225;NUSHU CHARACTER-1B225;Lo;0;L;;;;;N;;;;; +1B226;NUSHU CHARACTER-1B226;Lo;0;L;;;;;N;;;;; +1B227;NUSHU CHARACTER-1B227;Lo;0;L;;;;;N;;;;; +1B228;NUSHU CHARACTER-1B228;Lo;0;L;;;;;N;;;;; +1B229;NUSHU CHARACTER-1B229;Lo;0;L;;;;;N;;;;; +1B22A;NUSHU CHARACTER-1B22A;Lo;0;L;;;;;N;;;;; +1B22B;NUSHU CHARACTER-1B22B;Lo;0;L;;;;;N;;;;; +1B22C;NUSHU CHARACTER-1B22C;Lo;0;L;;;;;N;;;;; +1B22D;NUSHU CHARACTER-1B22D;Lo;0;L;;;;;N;;;;; +1B22E;NUSHU CHARACTER-1B22E;Lo;0;L;;;;;N;;;;; +1B22F;NUSHU CHARACTER-1B22F;Lo;0;L;;;;;N;;;;; +1B230;NUSHU CHARACTER-1B230;Lo;0;L;;;;;N;;;;; +1B231;NUSHU CHARACTER-1B231;Lo;0;L;;;;;N;;;;; +1B232;NUSHU CHARACTER-1B232;Lo;0;L;;;;;N;;;;; +1B233;NUSHU CHARACTER-1B233;Lo;0;L;;;;;N;;;;; +1B234;NUSHU CHARACTER-1B234;Lo;0;L;;;;;N;;;;; +1B235;NUSHU CHARACTER-1B235;Lo;0;L;;;;;N;;;;; +1B236;NUSHU CHARACTER-1B236;Lo;0;L;;;;;N;;;;; +1B237;NUSHU CHARACTER-1B237;Lo;0;L;;;;;N;;;;; +1B238;NUSHU CHARACTER-1B238;Lo;0;L;;;;;N;;;;; +1B239;NUSHU CHARACTER-1B239;Lo;0;L;;;;;N;;;;; +1B23A;NUSHU CHARACTER-1B23A;Lo;0;L;;;;;N;;;;; +1B23B;NUSHU CHARACTER-1B23B;Lo;0;L;;;;;N;;;;; +1B23C;NUSHU CHARACTER-1B23C;Lo;0;L;;;;;N;;;;; +1B23D;NUSHU CHARACTER-1B23D;Lo;0;L;;;;;N;;;;; +1B23E;NUSHU CHARACTER-1B23E;Lo;0;L;;;;;N;;;;; +1B23F;NUSHU CHARACTER-1B23F;Lo;0;L;;;;;N;;;;; +1B240;NUSHU CHARACTER-1B240;Lo;0;L;;;;;N;;;;; +1B241;NUSHU CHARACTER-1B241;Lo;0;L;;;;;N;;;;; +1B242;NUSHU CHARACTER-1B242;Lo;0;L;;;;;N;;;;; +1B243;NUSHU CHARACTER-1B243;Lo;0;L;;;;;N;;;;; +1B244;NUSHU CHARACTER-1B244;Lo;0;L;;;;;N;;;;; +1B245;NUSHU CHARACTER-1B245;Lo;0;L;;;;;N;;;;; +1B246;NUSHU CHARACTER-1B246;Lo;0;L;;;;;N;;;;; +1B247;NUSHU CHARACTER-1B247;Lo;0;L;;;;;N;;;;; +1B248;NUSHU CHARACTER-1B248;Lo;0;L;;;;;N;;;;; +1B249;NUSHU CHARACTER-1B249;Lo;0;L;;;;;N;;;;; +1B24A;NUSHU CHARACTER-1B24A;Lo;0;L;;;;;N;;;;; +1B24B;NUSHU CHARACTER-1B24B;Lo;0;L;;;;;N;;;;; +1B24C;NUSHU CHARACTER-1B24C;Lo;0;L;;;;;N;;;;; +1B24D;NUSHU CHARACTER-1B24D;Lo;0;L;;;;;N;;;;; +1B24E;NUSHU CHARACTER-1B24E;Lo;0;L;;;;;N;;;;; +1B24F;NUSHU CHARACTER-1B24F;Lo;0;L;;;;;N;;;;; +1B250;NUSHU CHARACTER-1B250;Lo;0;L;;;;;N;;;;; +1B251;NUSHU CHARACTER-1B251;Lo;0;L;;;;;N;;;;; +1B252;NUSHU CHARACTER-1B252;Lo;0;L;;;;;N;;;;; +1B253;NUSHU CHARACTER-1B253;Lo;0;L;;;;;N;;;;; +1B254;NUSHU CHARACTER-1B254;Lo;0;L;;;;;N;;;;; +1B255;NUSHU CHARACTER-1B255;Lo;0;L;;;;;N;;;;; +1B256;NUSHU CHARACTER-1B256;Lo;0;L;;;;;N;;;;; +1B257;NUSHU CHARACTER-1B257;Lo;0;L;;;;;N;;;;; +1B258;NUSHU CHARACTER-1B258;Lo;0;L;;;;;N;;;;; +1B259;NUSHU CHARACTER-1B259;Lo;0;L;;;;;N;;;;; +1B25A;NUSHU CHARACTER-1B25A;Lo;0;L;;;;;N;;;;; +1B25B;NUSHU CHARACTER-1B25B;Lo;0;L;;;;;N;;;;; +1B25C;NUSHU CHARACTER-1B25C;Lo;0;L;;;;;N;;;;; +1B25D;NUSHU CHARACTER-1B25D;Lo;0;L;;;;;N;;;;; +1B25E;NUSHU CHARACTER-1B25E;Lo;0;L;;;;;N;;;;; +1B25F;NUSHU CHARACTER-1B25F;Lo;0;L;;;;;N;;;;; +1B260;NUSHU CHARACTER-1B260;Lo;0;L;;;;;N;;;;; +1B261;NUSHU CHARACTER-1B261;Lo;0;L;;;;;N;;;;; +1B262;NUSHU CHARACTER-1B262;Lo;0;L;;;;;N;;;;; +1B263;NUSHU CHARACTER-1B263;Lo;0;L;;;;;N;;;;; +1B264;NUSHU CHARACTER-1B264;Lo;0;L;;;;;N;;;;; +1B265;NUSHU CHARACTER-1B265;Lo;0;L;;;;;N;;;;; +1B266;NUSHU CHARACTER-1B266;Lo;0;L;;;;;N;;;;; +1B267;NUSHU CHARACTER-1B267;Lo;0;L;;;;;N;;;;; +1B268;NUSHU CHARACTER-1B268;Lo;0;L;;;;;N;;;;; +1B269;NUSHU CHARACTER-1B269;Lo;0;L;;;;;N;;;;; +1B26A;NUSHU CHARACTER-1B26A;Lo;0;L;;;;;N;;;;; +1B26B;NUSHU CHARACTER-1B26B;Lo;0;L;;;;;N;;;;; +1B26C;NUSHU CHARACTER-1B26C;Lo;0;L;;;;;N;;;;; +1B26D;NUSHU CHARACTER-1B26D;Lo;0;L;;;;;N;;;;; +1B26E;NUSHU CHARACTER-1B26E;Lo;0;L;;;;;N;;;;; +1B26F;NUSHU CHARACTER-1B26F;Lo;0;L;;;;;N;;;;; +1B270;NUSHU CHARACTER-1B270;Lo;0;L;;;;;N;;;;; +1B271;NUSHU CHARACTER-1B271;Lo;0;L;;;;;N;;;;; +1B272;NUSHU CHARACTER-1B272;Lo;0;L;;;;;N;;;;; +1B273;NUSHU CHARACTER-1B273;Lo;0;L;;;;;N;;;;; +1B274;NUSHU CHARACTER-1B274;Lo;0;L;;;;;N;;;;; +1B275;NUSHU CHARACTER-1B275;Lo;0;L;;;;;N;;;;; +1B276;NUSHU CHARACTER-1B276;Lo;0;L;;;;;N;;;;; +1B277;NUSHU CHARACTER-1B277;Lo;0;L;;;;;N;;;;; +1B278;NUSHU CHARACTER-1B278;Lo;0;L;;;;;N;;;;; +1B279;NUSHU CHARACTER-1B279;Lo;0;L;;;;;N;;;;; +1B27A;NUSHU CHARACTER-1B27A;Lo;0;L;;;;;N;;;;; +1B27B;NUSHU CHARACTER-1B27B;Lo;0;L;;;;;N;;;;; +1B27C;NUSHU CHARACTER-1B27C;Lo;0;L;;;;;N;;;;; +1B27D;NUSHU CHARACTER-1B27D;Lo;0;L;;;;;N;;;;; +1B27E;NUSHU CHARACTER-1B27E;Lo;0;L;;;;;N;;;;; +1B27F;NUSHU CHARACTER-1B27F;Lo;0;L;;;;;N;;;;; +1B280;NUSHU CHARACTER-1B280;Lo;0;L;;;;;N;;;;; +1B281;NUSHU CHARACTER-1B281;Lo;0;L;;;;;N;;;;; +1B282;NUSHU CHARACTER-1B282;Lo;0;L;;;;;N;;;;; +1B283;NUSHU CHARACTER-1B283;Lo;0;L;;;;;N;;;;; +1B284;NUSHU CHARACTER-1B284;Lo;0;L;;;;;N;;;;; +1B285;NUSHU CHARACTER-1B285;Lo;0;L;;;;;N;;;;; +1B286;NUSHU CHARACTER-1B286;Lo;0;L;;;;;N;;;;; +1B287;NUSHU CHARACTER-1B287;Lo;0;L;;;;;N;;;;; +1B288;NUSHU CHARACTER-1B288;Lo;0;L;;;;;N;;;;; +1B289;NUSHU CHARACTER-1B289;Lo;0;L;;;;;N;;;;; +1B28A;NUSHU CHARACTER-1B28A;Lo;0;L;;;;;N;;;;; +1B28B;NUSHU CHARACTER-1B28B;Lo;0;L;;;;;N;;;;; +1B28C;NUSHU CHARACTER-1B28C;Lo;0;L;;;;;N;;;;; +1B28D;NUSHU CHARACTER-1B28D;Lo;0;L;;;;;N;;;;; +1B28E;NUSHU CHARACTER-1B28E;Lo;0;L;;;;;N;;;;; +1B28F;NUSHU CHARACTER-1B28F;Lo;0;L;;;;;N;;;;; +1B290;NUSHU CHARACTER-1B290;Lo;0;L;;;;;N;;;;; +1B291;NUSHU CHARACTER-1B291;Lo;0;L;;;;;N;;;;; +1B292;NUSHU CHARACTER-1B292;Lo;0;L;;;;;N;;;;; +1B293;NUSHU CHARACTER-1B293;Lo;0;L;;;;;N;;;;; +1B294;NUSHU CHARACTER-1B294;Lo;0;L;;;;;N;;;;; +1B295;NUSHU CHARACTER-1B295;Lo;0;L;;;;;N;;;;; +1B296;NUSHU CHARACTER-1B296;Lo;0;L;;;;;N;;;;; +1B297;NUSHU CHARACTER-1B297;Lo;0;L;;;;;N;;;;; +1B298;NUSHU CHARACTER-1B298;Lo;0;L;;;;;N;;;;; +1B299;NUSHU CHARACTER-1B299;Lo;0;L;;;;;N;;;;; +1B29A;NUSHU CHARACTER-1B29A;Lo;0;L;;;;;N;;;;; +1B29B;NUSHU CHARACTER-1B29B;Lo;0;L;;;;;N;;;;; +1B29C;NUSHU CHARACTER-1B29C;Lo;0;L;;;;;N;;;;; +1B29D;NUSHU CHARACTER-1B29D;Lo;0;L;;;;;N;;;;; +1B29E;NUSHU CHARACTER-1B29E;Lo;0;L;;;;;N;;;;; +1B29F;NUSHU CHARACTER-1B29F;Lo;0;L;;;;;N;;;;; +1B2A0;NUSHU CHARACTER-1B2A0;Lo;0;L;;;;;N;;;;; +1B2A1;NUSHU CHARACTER-1B2A1;Lo;0;L;;;;;N;;;;; +1B2A2;NUSHU CHARACTER-1B2A2;Lo;0;L;;;;;N;;;;; +1B2A3;NUSHU CHARACTER-1B2A3;Lo;0;L;;;;;N;;;;; +1B2A4;NUSHU CHARACTER-1B2A4;Lo;0;L;;;;;N;;;;; +1B2A5;NUSHU CHARACTER-1B2A5;Lo;0;L;;;;;N;;;;; +1B2A6;NUSHU CHARACTER-1B2A6;Lo;0;L;;;;;N;;;;; +1B2A7;NUSHU CHARACTER-1B2A7;Lo;0;L;;;;;N;;;;; +1B2A8;NUSHU CHARACTER-1B2A8;Lo;0;L;;;;;N;;;;; +1B2A9;NUSHU CHARACTER-1B2A9;Lo;0;L;;;;;N;;;;; +1B2AA;NUSHU CHARACTER-1B2AA;Lo;0;L;;;;;N;;;;; +1B2AB;NUSHU CHARACTER-1B2AB;Lo;0;L;;;;;N;;;;; +1B2AC;NUSHU CHARACTER-1B2AC;Lo;0;L;;;;;N;;;;; +1B2AD;NUSHU CHARACTER-1B2AD;Lo;0;L;;;;;N;;;;; +1B2AE;NUSHU CHARACTER-1B2AE;Lo;0;L;;;;;N;;;;; +1B2AF;NUSHU CHARACTER-1B2AF;Lo;0;L;;;;;N;;;;; +1B2B0;NUSHU CHARACTER-1B2B0;Lo;0;L;;;;;N;;;;; +1B2B1;NUSHU CHARACTER-1B2B1;Lo;0;L;;;;;N;;;;; +1B2B2;NUSHU CHARACTER-1B2B2;Lo;0;L;;;;;N;;;;; +1B2B3;NUSHU CHARACTER-1B2B3;Lo;0;L;;;;;N;;;;; +1B2B4;NUSHU CHARACTER-1B2B4;Lo;0;L;;;;;N;;;;; +1B2B5;NUSHU CHARACTER-1B2B5;Lo;0;L;;;;;N;;;;; +1B2B6;NUSHU CHARACTER-1B2B6;Lo;0;L;;;;;N;;;;; +1B2B7;NUSHU CHARACTER-1B2B7;Lo;0;L;;;;;N;;;;; +1B2B8;NUSHU CHARACTER-1B2B8;Lo;0;L;;;;;N;;;;; +1B2B9;NUSHU CHARACTER-1B2B9;Lo;0;L;;;;;N;;;;; +1B2BA;NUSHU CHARACTER-1B2BA;Lo;0;L;;;;;N;;;;; +1B2BB;NUSHU CHARACTER-1B2BB;Lo;0;L;;;;;N;;;;; +1B2BC;NUSHU CHARACTER-1B2BC;Lo;0;L;;;;;N;;;;; +1B2BD;NUSHU CHARACTER-1B2BD;Lo;0;L;;;;;N;;;;; +1B2BE;NUSHU CHARACTER-1B2BE;Lo;0;L;;;;;N;;;;; +1B2BF;NUSHU CHARACTER-1B2BF;Lo;0;L;;;;;N;;;;; +1B2C0;NUSHU CHARACTER-1B2C0;Lo;0;L;;;;;N;;;;; +1B2C1;NUSHU CHARACTER-1B2C1;Lo;0;L;;;;;N;;;;; +1B2C2;NUSHU CHARACTER-1B2C2;Lo;0;L;;;;;N;;;;; +1B2C3;NUSHU CHARACTER-1B2C3;Lo;0;L;;;;;N;;;;; +1B2C4;NUSHU CHARACTER-1B2C4;Lo;0;L;;;;;N;;;;; +1B2C5;NUSHU CHARACTER-1B2C5;Lo;0;L;;;;;N;;;;; +1B2C6;NUSHU CHARACTER-1B2C6;Lo;0;L;;;;;N;;;;; +1B2C7;NUSHU CHARACTER-1B2C7;Lo;0;L;;;;;N;;;;; +1B2C8;NUSHU CHARACTER-1B2C8;Lo;0;L;;;;;N;;;;; +1B2C9;NUSHU CHARACTER-1B2C9;Lo;0;L;;;;;N;;;;; +1B2CA;NUSHU CHARACTER-1B2CA;Lo;0;L;;;;;N;;;;; +1B2CB;NUSHU CHARACTER-1B2CB;Lo;0;L;;;;;N;;;;; +1B2CC;NUSHU CHARACTER-1B2CC;Lo;0;L;;;;;N;;;;; +1B2CD;NUSHU CHARACTER-1B2CD;Lo;0;L;;;;;N;;;;; +1B2CE;NUSHU CHARACTER-1B2CE;Lo;0;L;;;;;N;;;;; +1B2CF;NUSHU CHARACTER-1B2CF;Lo;0;L;;;;;N;;;;; +1B2D0;NUSHU CHARACTER-1B2D0;Lo;0;L;;;;;N;;;;; +1B2D1;NUSHU CHARACTER-1B2D1;Lo;0;L;;;;;N;;;;; +1B2D2;NUSHU CHARACTER-1B2D2;Lo;0;L;;;;;N;;;;; +1B2D3;NUSHU CHARACTER-1B2D3;Lo;0;L;;;;;N;;;;; +1B2D4;NUSHU CHARACTER-1B2D4;Lo;0;L;;;;;N;;;;; +1B2D5;NUSHU CHARACTER-1B2D5;Lo;0;L;;;;;N;;;;; +1B2D6;NUSHU CHARACTER-1B2D6;Lo;0;L;;;;;N;;;;; +1B2D7;NUSHU CHARACTER-1B2D7;Lo;0;L;;;;;N;;;;; +1B2D8;NUSHU CHARACTER-1B2D8;Lo;0;L;;;;;N;;;;; +1B2D9;NUSHU CHARACTER-1B2D9;Lo;0;L;;;;;N;;;;; +1B2DA;NUSHU CHARACTER-1B2DA;Lo;0;L;;;;;N;;;;; +1B2DB;NUSHU CHARACTER-1B2DB;Lo;0;L;;;;;N;;;;; +1B2DC;NUSHU CHARACTER-1B2DC;Lo;0;L;;;;;N;;;;; +1B2DD;NUSHU CHARACTER-1B2DD;Lo;0;L;;;;;N;;;;; +1B2DE;NUSHU CHARACTER-1B2DE;Lo;0;L;;;;;N;;;;; +1B2DF;NUSHU CHARACTER-1B2DF;Lo;0;L;;;;;N;;;;; +1B2E0;NUSHU CHARACTER-1B2E0;Lo;0;L;;;;;N;;;;; +1B2E1;NUSHU CHARACTER-1B2E1;Lo;0;L;;;;;N;;;;; +1B2E2;NUSHU CHARACTER-1B2E2;Lo;0;L;;;;;N;;;;; +1B2E3;NUSHU CHARACTER-1B2E3;Lo;0;L;;;;;N;;;;; +1B2E4;NUSHU CHARACTER-1B2E4;Lo;0;L;;;;;N;;;;; +1B2E5;NUSHU CHARACTER-1B2E5;Lo;0;L;;;;;N;;;;; +1B2E6;NUSHU CHARACTER-1B2E6;Lo;0;L;;;;;N;;;;; +1B2E7;NUSHU CHARACTER-1B2E7;Lo;0;L;;;;;N;;;;; +1B2E8;NUSHU CHARACTER-1B2E8;Lo;0;L;;;;;N;;;;; +1B2E9;NUSHU CHARACTER-1B2E9;Lo;0;L;;;;;N;;;;; +1B2EA;NUSHU CHARACTER-1B2EA;Lo;0;L;;;;;N;;;;; +1B2EB;NUSHU CHARACTER-1B2EB;Lo;0;L;;;;;N;;;;; +1B2EC;NUSHU CHARACTER-1B2EC;Lo;0;L;;;;;N;;;;; +1B2ED;NUSHU CHARACTER-1B2ED;Lo;0;L;;;;;N;;;;; +1B2EE;NUSHU CHARACTER-1B2EE;Lo;0;L;;;;;N;;;;; +1B2EF;NUSHU CHARACTER-1B2EF;Lo;0;L;;;;;N;;;;; +1B2F0;NUSHU CHARACTER-1B2F0;Lo;0;L;;;;;N;;;;; +1B2F1;NUSHU CHARACTER-1B2F1;Lo;0;L;;;;;N;;;;; +1B2F2;NUSHU CHARACTER-1B2F2;Lo;0;L;;;;;N;;;;; +1B2F3;NUSHU CHARACTER-1B2F3;Lo;0;L;;;;;N;;;;; +1B2F4;NUSHU CHARACTER-1B2F4;Lo;0;L;;;;;N;;;;; +1B2F5;NUSHU CHARACTER-1B2F5;Lo;0;L;;;;;N;;;;; +1B2F6;NUSHU CHARACTER-1B2F6;Lo;0;L;;;;;N;;;;; +1B2F7;NUSHU CHARACTER-1B2F7;Lo;0;L;;;;;N;;;;; +1B2F8;NUSHU CHARACTER-1B2F8;Lo;0;L;;;;;N;;;;; +1B2F9;NUSHU CHARACTER-1B2F9;Lo;0;L;;;;;N;;;;; +1B2FA;NUSHU CHARACTER-1B2FA;Lo;0;L;;;;;N;;;;; +1B2FB;NUSHU CHARACTER-1B2FB;Lo;0;L;;;;;N;;;;; 1BC00;DUPLOYAN LETTER H;Lo;0;L;;;;;N;;;;; 1BC01;DUPLOYAN LETTER X;Lo;0;L;;;;;N;;;;; 1BC02;DUPLOYAN LETTER P;Lo;0;L;;;;;N;;;;; @@ -28269,6 +29217,12 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1F248;TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557;So;0;L;<compat> 3014 6557 3015;;;;N;;;;; 1F250;CIRCLED IDEOGRAPH ADVANTAGE;So;0;L;<circle> 5F97;;;;N;;;;; 1F251;CIRCLED IDEOGRAPH ACCEPT;So;0;L;<circle> 53EF;;;;N;;;;; +1F260;ROUNDED SYMBOL FOR FU;So;0;ON;;;;;N;;;;; +1F261;ROUNDED SYMBOL FOR LU;So;0;ON;;;;;N;;;;; +1F262;ROUNDED SYMBOL FOR SHOU;So;0;ON;;;;;N;;;;; +1F263;ROUNDED SYMBOL FOR XI;So;0;ON;;;;;N;;;;; +1F264;ROUNDED SYMBOL FOR SHUANGXI;So;0;ON;;;;;N;;;;; +1F265;ROUNDED SYMBOL FOR CAI;So;0;ON;;;;;N;;;;; 1F300;CYCLONE;So;0;ON;;;;;N;;;;; 1F301;FOGGY;So;0;ON;;;;;N;;;;; 1F302;CLOSED UMBRELLA;So;0;ON;;;;;N;;;;; @@ -29248,6 +30202,8 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1F6D0;PLACE OF WORSHIP;So;0;ON;;;;;N;;;;; 1F6D1;OCTAGONAL SIGN;So;0;ON;;;;;N;;;;; 1F6D2;SHOPPING TROLLEY;So;0;ON;;;;;N;;;;; +1F6D3;STUPA;So;0;ON;;;;;N;;;;; +1F6D4;PAGODA;So;0;ON;;;;;N;;;;; 1F6E0;HAMMER AND WRENCH;So;0;ON;;;;;N;;;;; 1F6E1;SHIELD;So;0;ON;;;;;N;;;;; 1F6E2;OIL DRUM;So;0;ON;;;;;N;;;;; @@ -29268,6 +30224,8 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1F6F4;SCOOTER;So;0;ON;;;;;N;;;;; 1F6F5;MOTOR SCOOTER;So;0;ON;;;;;N;;;;; 1F6F6;CANOE;So;0;ON;;;;;N;;;;; +1F6F7;SLED;So;0;ON;;;;;N;;;;; +1F6F8;FLYING SAUCER;So;0;ON;;;;;N;;;;; 1F700;ALCHEMICAL SYMBOL FOR QUINTESSENCE;So;0;ON;;;;;N;;;;; 1F701;ALCHEMICAL SYMBOL FOR AIR;So;0;ON;;;;;N;;;;; 1F702;ALCHEMICAL SYMBOL FOR FIRE;So;0;ON;;;;;N;;;;; @@ -29617,6 +30575,18 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1F8AB;RIGHTWARDS FRONT-TILTED SHADOWED WHITE ARROW;So;0;ON;;;;;N;;;;; 1F8AC;WHITE ARROW SHAFT WIDTH ONE;So;0;ON;;;;;N;;;;; 1F8AD;WHITE ARROW SHAFT WIDTH TWO THIRDS;So;0;ON;;;;;N;;;;; +1F900;CIRCLED CROSS FORMEE WITH FOUR DOTS;So;0;ON;;;;;N;;;;; +1F901;CIRCLED CROSS FORMEE WITH TWO DOTS;So;0;ON;;;;;N;;;;; +1F902;CIRCLED CROSS FORMEE;So;0;ON;;;;;N;;;;; +1F903;LEFT HALF CIRCLE WITH FOUR DOTS;So;0;ON;;;;;N;;;;; +1F904;LEFT HALF CIRCLE WITH THREE DOTS;So;0;ON;;;;;N;;;;; +1F905;LEFT HALF CIRCLE WITH TWO DOTS;So;0;ON;;;;;N;;;;; +1F906;LEFT HALF CIRCLE WITH DOT;So;0;ON;;;;;N;;;;; +1F907;LEFT HALF CIRCLE;So;0;ON;;;;;N;;;;; +1F908;DOWNWARD FACING HOOK;So;0;ON;;;;;N;;;;; +1F909;DOWNWARD FACING NOTCHED HOOK;So;0;ON;;;;;N;;;;; +1F90A;DOWNWARD FACING HOOK WITH DOT;So;0;ON;;;;;N;;;;; +1F90B;DOWNWARD FACING NOTCHED HOOK WITH DOT;So;0;ON;;;;;N;;;;; 1F910;ZIPPER-MOUTH FACE;So;0;ON;;;;;N;;;;; 1F911;MONEY-MOUTH FACE;So;0;ON;;;;;N;;;;; 1F912;FACE WITH THERMOMETER;So;0;ON;;;;;N;;;;; @@ -29632,6 +30602,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1F91C;RIGHT-FACING FIST;So;0;ON;;;;;N;;;;; 1F91D;HANDSHAKE;So;0;ON;;;;;N;;;;; 1F91E;HAND WITH INDEX AND MIDDLE FINGERS CROSSED;So;0;ON;;;;;N;;;;; +1F91F;I LOVE YOU HAND SIGN;So;0;ON;;;;;N;;;;; 1F920;FACE WITH COWBOY HAT;So;0;ON;;;;;N;;;;; 1F921;CLOWN FACE;So;0;ON;;;;;N;;;;; 1F922;NAUSEATED FACE;So;0;ON;;;;;N;;;;; @@ -29640,7 +30611,17 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1F925;LYING FACE;So;0;ON;;;;;N;;;;; 1F926;FACE PALM;So;0;ON;;;;;N;;;;; 1F927;SNEEZING FACE;So;0;ON;;;;;N;;;;; +1F928;FACE WITH ONE EYEBROW RAISED;So;0;ON;;;;;N;;;;; +1F929;GRINNING FACE WITH STAR EYES;So;0;ON;;;;;N;;;;; +1F92A;GRINNING FACE WITH ONE LARGE AND ONE SMALL EYE;So;0;ON;;;;;N;;;;; +1F92B;FACE WITH FINGER COVERING CLOSED LIPS;So;0;ON;;;;;N;;;;; +1F92C;SERIOUS FACE WITH SYMBOLS COVERING MOUTH;So;0;ON;;;;;N;;;;; +1F92D;SMILING FACE WITH SMILING EYES AND HAND COVERING MOUTH;So;0;ON;;;;;N;;;;; +1F92E;FACE WITH OPEN MOUTH VOMITING;So;0;ON;;;;;N;;;;; +1F92F;SHOCKED FACE WITH EXPLODING HEAD;So;0;ON;;;;;N;;;;; 1F930;PREGNANT WOMAN;So;0;ON;;;;;N;;;;; +1F931;BREAST-FEEDING;So;0;ON;;;;;N;;;;; +1F932;PALMS UP TOGETHER;So;0;ON;;;;;N;;;;; 1F933;SELFIE;So;0;ON;;;;;N;;;;; 1F934;PRINCE;So;0;ON;;;;;N;;;;; 1F935;MAN IN TUXEDO;So;0;ON;;;;;N;;;;; @@ -29665,6 +30646,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1F949;THIRD PLACE MEDAL;So;0;ON;;;;;N;;;;; 1F94A;BOXING GLOVE;So;0;ON;;;;;N;;;;; 1F94B;MARTIAL ARTS UNIFORM;So;0;ON;;;;;N;;;;; +1F94C;CURLING STONE;So;0;ON;;;;;N;;;;; 1F950;CROISSANT;So;0;ON;;;;;N;;;;; 1F951;AVOCADO;So;0;ON;;;;;N;;;;; 1F952;CUCUMBER;So;0;ON;;;;;N;;;;; @@ -29680,6 +30662,19 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1F95C;PEANUTS;So;0;ON;;;;;N;;;;; 1F95D;KIWIFRUIT;So;0;ON;;;;;N;;;;; 1F95E;PANCAKES;So;0;ON;;;;;N;;;;; +1F95F;DUMPLING;So;0;ON;;;;;N;;;;; +1F960;FORTUNE COOKIE;So;0;ON;;;;;N;;;;; +1F961;TAKEOUT BOX;So;0;ON;;;;;N;;;;; +1F962;CHOPSTICKS;So;0;ON;;;;;N;;;;; +1F963;BOWL WITH SPOON;So;0;ON;;;;;N;;;;; +1F964;CUP WITH STRAW;So;0;ON;;;;;N;;;;; +1F965;COCONUT;So;0;ON;;;;;N;;;;; +1F966;BROCCOLI;So;0;ON;;;;;N;;;;; +1F967;PIE;So;0;ON;;;;;N;;;;; +1F968;PRETZEL;So;0;ON;;;;;N;;;;; +1F969;CUT OF MEAT;So;0;ON;;;;;N;;;;; +1F96A;SANDWICH;So;0;ON;;;;;N;;;;; +1F96B;CANNED FOOD;So;0;ON;;;;;N;;;;; 1F980;CRAB;So;0;ON;;;;;N;;;;; 1F981;LION FACE;So;0;ON;;;;;N;;;;; 1F982;SCORPION;So;0;ON;;;;;N;;;;; @@ -29698,7 +30693,36 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1F98F;RHINOCEROS;So;0;ON;;;;;N;;;;; 1F990;SHRIMP;So;0;ON;;;;;N;;;;; 1F991;SQUID;So;0;ON;;;;;N;;;;; +1F992;GIRAFFE FACE;So;0;ON;;;;;N;;;;; +1F993;ZEBRA FACE;So;0;ON;;;;;N;;;;; +1F994;HEDGEHOG;So;0;ON;;;;;N;;;;; +1F995;SAUROPOD;So;0;ON;;;;;N;;;;; +1F996;T-REX;So;0;ON;;;;;N;;;;; +1F997;CRICKET;So;0;ON;;;;;N;;;;; 1F9C0;CHEESE WEDGE;So;0;ON;;;;;N;;;;; +1F9D0;FACE WITH MONOCLE;So;0;ON;;;;;N;;;;; +1F9D1;ADULT;So;0;ON;;;;;N;;;;; +1F9D2;CHILD;So;0;ON;;;;;N;;;;; +1F9D3;OLDER ADULT;So;0;ON;;;;;N;;;;; +1F9D4;BEARDED PERSON;So;0;ON;;;;;N;;;;; +1F9D5;PERSON WITH HEADSCARF;So;0;ON;;;;;N;;;;; +1F9D6;PERSON IN STEAMY ROOM;So;0;ON;;;;;N;;;;; +1F9D7;PERSON CLIMBING;So;0;ON;;;;;N;;;;; +1F9D8;PERSON IN LOTUS POSITION;So;0;ON;;;;;N;;;;; +1F9D9;MAGE;So;0;ON;;;;;N;;;;; +1F9DA;FAIRY;So;0;ON;;;;;N;;;;; +1F9DB;VAMPIRE;So;0;ON;;;;;N;;;;; +1F9DC;MERPERSON;So;0;ON;;;;;N;;;;; +1F9DD;ELF;So;0;ON;;;;;N;;;;; +1F9DE;GENIE;So;0;ON;;;;;N;;;;; +1F9DF;ZOMBIE;So;0;ON;;;;;N;;;;; +1F9E0;BRAIN;So;0;ON;;;;;N;;;;; +1F9E1;ORANGE HEART;So;0;ON;;;;;N;;;;; +1F9E2;BILLED CAP;So;0;ON;;;;;N;;;;; +1F9E3;SCARF;So;0;ON;;;;;N;;;;; +1F9E4;GLOVES;So;0;ON;;;;;N;;;;; +1F9E5;COAT;So;0;ON;;;;;N;;;;; +1F9E6;SOCKS;So;0;ON;;;;;N;;;;; 20000;<CJK Ideograph Extension B, First>;Lo;0;L;;;;;N;;;;; 2A6D6;<CJK Ideograph Extension B, Last>;Lo;0;L;;;;;N;;;;; 2A700;<CJK Ideograph Extension C, First>;Lo;0;L;;;;;N;;;;; @@ -29707,6 +30731,8 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 2B81D;<CJK Ideograph Extension D, Last>;Lo;0;L;;;;;N;;;;; 2B820;<CJK Ideograph Extension E, First>;Lo;0;L;;;;;N;;;;; 2CEA1;<CJK Ideograph Extension E, Last>;Lo;0;L;;;;;N;;;;; +2CEB0;<CJK Ideograph Extension F, First>;Lo;0;L;;;;;N;;;;; +2EBE0;<CJK Ideograph Extension F, Last>;Lo;0;L;;;;;N;;;;; 2F800;CJK COMPATIBILITY IDEOGRAPH-2F800;Lo;0;L;4E3D;;;;N;;;;; 2F801;CJK COMPATIBILITY IDEOGRAPH-2F801;Lo;0;L;4E38;;;;N;;;;; 2F802;CJK COMPATIBILITY IDEOGRAPH-2F802;Lo;0;L;4E41;;;;N;;;;; diff --git a/lib/unicore/VerticalOrientation.txt b/lib/unicore/VerticalOrientation.txt new file mode 100644 index 0000000000..567df2f2cb --- /dev/null +++ b/lib/unicore/VerticalOrientation.txt @@ -0,0 +1,2199 @@ +# VerticalOrientation-10.0.0.txt +# Date: 2017-03-08, 02:05:46 GMT [EM, KI, LI] +# © 2017 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see http://www.unicode.org/terms_of_use.html +# +# Unicode Character Database +# For documentation, see http://www.unicode.org/reports/tr44/ +# +# Vertical_Orientation (vo) Property +# +# This file defines the Vertical_Orientation property. See UAX #50: +# Unicode Vertical Text Layout, at http://www.unicode.org/reports/tr50/ +# +# The format of the file is two fields separated by a semicolon. +# Field 0: Unicode code point value or range of code point values in +# hexadecimal form +# Field 1: Vertical_Orientation property value, one of the following: +# U - Upright, the same orientation as in the code charts +# R - Rotated 90 degrees clockwise compared to the code charts +# Tu - Transformed typographically, with fallback to Upright +# Tr - Transformed typographically, with fallback to Rotated +# +# - Certain ranges of unassigned code points default to U. These ranges +# are mostly associated with CJK scripts and punctuation, or with +# a small number of other scripts which are predominantly Upright. +# The private use areas also default to U, because of their most +# common use for CJK. In the following list of explicit code points +# and ranges, all unassigned code points default to U: +# Canadian Syllabics Extended: U+18B0..U+18FF +# Reserved Default_Ignorable_Code_Point: U+2065 +# Number Forms: U+2150..U+218F +# Control Pictures & OCR U+2400..U+245F +# Symbols: U+2BB8..U+2BFF +# CJK-Related & Yi: U+2E80..U+A4CF +# Hangul Jamo Extended-A: U+A960..U+A97F +# Hangul Syllables & Jamo Extended-B: U+AC00..U+D7FF +# PUA & CJK Compatibility Ideographs: U+E000..U+FAFF +# Vertical Forms: U+FE10..U+FE1F +# Small Form Variants: U+FE50..U+FE6F +# Fullwidth Forms: U+FFE7 +# Specials: U+FFF0..U+FFF8 +# Siddham: U+11580..U+115FF +# Zanabazar Square & Soyombo: U+11A00..U+11AAF +# Egyptian Hieroglyphs: U+13000..U+1342F +# Anatolian Hieroglyphs: U+14400..U+1467F +# Ideographic Symbols & Tangut: U+16FE0..U+18AFF +# Kana Extended-A: U+1B100..U+1B12F +# Nushu: U+1B170..U+1B2FF +# Musical Symbols: U+1D000..U+1D1FF +# Symbols & Rods: U+1D300..U+1D37F +# Sutton SignWriting: U+1D800..U+1DAAF +# Game Symbols: U+1F000..U+1F0FF +# Enclosed Symbols: U+1F100..U+1F2FF +# Symbols: U+1F680..U+1F7FF +# Symbols and Pictographs: U+1F900..U+1F9FF +# Plane 2: U+20000..U+2FFFD +# Plane 3: U+30000..U+3FFFD +# Plane 15 PUA: U+F0000..U+FFFFD +# Plane 16 PUA: U+100000..U+10FFFD +# +# - All other code points, assigned and unassigned, that are not listed +# explicitly in the data section of this file are given the value R. +# +# The comments following the number sign "#" list the General_Category +# property value or the L& alias of the derived value LC, the Unicode +# character name or names, and, in lines with ranges of code points, +# the code point count in square brackets. +# +# @missing: 0000..10FFFF; R + +0000..001F ; R # Cc [32] <control-0000>..<control-001F> +0020 ; R # Zs SPACE +0021..0023 ; R # Po [3] EXCLAMATION MARK..NUMBER SIGN +0024 ; R # Sc DOLLAR SIGN +0025..0027 ; R # Po [3] PERCENT SIGN..APOSTROPHE +0028 ; R # Ps LEFT PARENTHESIS +0029 ; R # Pe RIGHT PARENTHESIS +002A ; R # Po ASTERISK +002B ; R # Sm PLUS SIGN +002C ; R # Po COMMA +002D ; R # Pd HYPHEN-MINUS +002E..002F ; R # Po [2] FULL STOP..SOLIDUS +0030..0039 ; R # Nd [10] DIGIT ZERO..DIGIT NINE +003A..003B ; R # Po [2] COLON..SEMICOLON +003C..003E ; R # Sm [3] LESS-THAN SIGN..GREATER-THAN SIGN +003F..0040 ; R # Po [2] QUESTION MARK..COMMERCIAL AT +0041..005A ; R # Lu [26] LATIN CAPITAL LETTER A..LATIN CAPITAL LETTER Z +005B ; R # Ps LEFT SQUARE BRACKET +005C ; R # Po REVERSE SOLIDUS +005D ; R # Pe RIGHT SQUARE BRACKET +005E ; R # Sk CIRCUMFLEX ACCENT +005F ; R # Pc LOW LINE +0060 ; R # Sk GRAVE ACCENT +0061..007A ; R # Ll [26] LATIN SMALL LETTER A..LATIN SMALL LETTER Z +007B ; R # Ps LEFT CURLY BRACKET +007C ; R # Sm VERTICAL LINE +007D ; R # Pe RIGHT CURLY BRACKET +007E ; R # Sm TILDE +007F ; R # Cc <control-007F> +0080..009F ; R # Cc [32] <control-0080>..<control-009F> +00A0 ; R # Zs NO-BREAK SPACE +00A1 ; R # Po INVERTED EXCLAMATION MARK +00A2..00A5 ; R # Sc [4] CENT SIGN..YEN SIGN +00A6 ; R # So BROKEN BAR +00A7 ; U # Po SECTION SIGN +00A8 ; R # Sk DIAERESIS +00A9 ; U # So COPYRIGHT SIGN +00AA ; R # Lo FEMININE ORDINAL INDICATOR +00AB ; R # Pi LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +00AC ; R # Sm NOT SIGN +00AD ; R # Cf SOFT HYPHEN +00AE ; U # So REGISTERED SIGN +00AF ; R # Sk MACRON +00B0 ; R # So DEGREE SIGN +00B1 ; U # Sm PLUS-MINUS SIGN +00B2..00B3 ; R # No [2] SUPERSCRIPT TWO..SUPERSCRIPT THREE +00B4 ; R # Sk ACUTE ACCENT +00B5 ; R # Ll MICRO SIGN +00B6..00B7 ; R # Po [2] PILCROW SIGN..MIDDLE DOT +00B8 ; R # Sk CEDILLA +00B9 ; R # No SUPERSCRIPT ONE +00BA ; R # Lo MASCULINE ORDINAL INDICATOR +00BB ; R # Pf RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +00BC..00BE ; U # No [3] VULGAR FRACTION ONE QUARTER..VULGAR FRACTION THREE QUARTERS +00BF ; R # Po INVERTED QUESTION MARK +00C0..00D6 ; R # Lu [23] LATIN CAPITAL LETTER A WITH GRAVE..LATIN CAPITAL LETTER O WITH DIAERESIS +00D7 ; U # Sm MULTIPLICATION SIGN +00D8..00F6 ; R # L& [31] LATIN CAPITAL LETTER O WITH STROKE..LATIN SMALL LETTER O WITH DIAERESIS +00F7 ; U # Sm DIVISION SIGN +00F8..00FF ; R # L& [8] LATIN SMALL LETTER O WITH STROKE..LATIN SMALL LETTER Y WITH DIAERESIS +0100..017F ; R # L& [128] LATIN CAPITAL LETTER A WITH MACRON..LATIN SMALL LETTER LONG S +0180..01BA ; R # L& [59] LATIN SMALL LETTER B WITH STROKE..LATIN SMALL LETTER EZH WITH TAIL +01BB ; R # Lo LATIN LETTER TWO WITH STROKE +01BC..01BF ; R # L& [4] LATIN CAPITAL LETTER TONE FIVE..LATIN LETTER WYNN +01C0..01C3 ; R # Lo [4] LATIN LETTER DENTAL CLICK..LATIN LETTER RETROFLEX CLICK +01C4..024F ; R # L& [140] LATIN CAPITAL LETTER DZ WITH CARON..LATIN SMALL LETTER Y WITH STROKE +0250..0293 ; R # Ll [68] LATIN SMALL LETTER TURNED A..LATIN SMALL LETTER EZH WITH CURL +0294 ; R # Lo LATIN LETTER GLOTTAL STOP +0295..02AF ; R # Ll [27] LATIN LETTER PHARYNGEAL VOICED FRICATIVE..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL +02B0..02C1 ; R # Lm [18] MODIFIER LETTER SMALL H..MODIFIER LETTER REVERSED GLOTTAL STOP +02C2..02C5 ; R # Sk [4] MODIFIER LETTER LEFT ARROWHEAD..MODIFIER LETTER DOWN ARROWHEAD +02C6..02D1 ; R # Lm [12] MODIFIER LETTER CIRCUMFLEX ACCENT..MODIFIER LETTER HALF TRIANGULAR COLON +02D2..02DF ; R # Sk [14] MODIFIER LETTER CENTRED RIGHT HALF RING..MODIFIER LETTER CROSS ACCENT +02E0..02E4 ; R # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP +02E5..02E9 ; R # Sk [5] MODIFIER LETTER EXTRA-HIGH TONE BAR..MODIFIER LETTER EXTRA-LOW TONE BAR +02EA..02EB ; U # Sk [2] MODIFIER LETTER YIN DEPARTING TONE MARK..MODIFIER LETTER YANG DEPARTING TONE MARK +02EC ; R # Lm MODIFIER LETTER VOICING +02ED ; R # Sk MODIFIER LETTER UNASPIRATED +02EE ; R # Lm MODIFIER LETTER DOUBLE APOSTROPHE +02EF..02FF ; R # Sk [17] MODIFIER LETTER LOW DOWN ARROWHEAD..MODIFIER LETTER LOW LEFT ARROW +0300..036F ; R # Mn [112] COMBINING GRAVE ACCENT..COMBINING LATIN SMALL LETTER X +0370..0373 ; R # L& [4] GREEK CAPITAL LETTER HETA..GREEK SMALL LETTER ARCHAIC SAMPI +0374 ; R # Lm GREEK NUMERAL SIGN +0375 ; R # Sk GREEK LOWER NUMERAL SIGN +0376..0377 ; R # L& [2] GREEK CAPITAL LETTER PAMPHYLIAN DIGAMMA..GREEK SMALL LETTER PAMPHYLIAN DIGAMMA +037A ; R # Lm GREEK YPOGEGRAMMENI +037B..037D ; R # Ll [3] GREEK SMALL REVERSED LUNATE SIGMA SYMBOL..GREEK SMALL REVERSED DOTTED LUNATE SIGMA SYMBOL +037E ; R # Po GREEK QUESTION MARK +037F ; R # Lu GREEK CAPITAL LETTER YOT +0384..0385 ; R # Sk [2] GREEK TONOS..GREEK DIALYTIKA TONOS +0386 ; R # Lu GREEK CAPITAL LETTER ALPHA WITH TONOS +0387 ; R # Po GREEK ANO TELEIA +0388..038A ; R # Lu [3] GREEK CAPITAL LETTER EPSILON WITH TONOS..GREEK CAPITAL LETTER IOTA WITH TONOS +038C ; R # Lu GREEK CAPITAL LETTER OMICRON WITH TONOS +038E..03A1 ; R # L& [20] GREEK CAPITAL LETTER UPSILON WITH TONOS..GREEK CAPITAL LETTER RHO +03A3..03F5 ; R # L& [83] GREEK CAPITAL LETTER SIGMA..GREEK LUNATE EPSILON SYMBOL +03F6 ; R # Sm GREEK REVERSED LUNATE EPSILON SYMBOL +03F7..03FF ; R # L& [9] GREEK CAPITAL LETTER SHO..GREEK CAPITAL REVERSED DOTTED LUNATE SIGMA SYMBOL +0400..0481 ; R # L& [130] CYRILLIC CAPITAL LETTER IE WITH GRAVE..CYRILLIC SMALL LETTER KOPPA +0482 ; R # So CYRILLIC THOUSANDS SIGN +0483..0487 ; R # Mn [5] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC POKRYTIE +0488..0489 ; R # Me [2] COMBINING CYRILLIC HUNDRED THOUSANDS SIGN..COMBINING CYRILLIC MILLIONS SIGN +048A..04FF ; R # L& [118] CYRILLIC CAPITAL LETTER SHORT I WITH TAIL..CYRILLIC SMALL LETTER HA WITH STROKE +0500..052F ; R # L& [48] CYRILLIC CAPITAL LETTER KOMI DE..CYRILLIC SMALL LETTER EL WITH DESCENDER +0531..0556 ; R # Lu [38] ARMENIAN CAPITAL LETTER AYB..ARMENIAN CAPITAL LETTER FEH +0559 ; R # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING +055A..055F ; R # Po [6] ARMENIAN APOSTROPHE..ARMENIAN ABBREVIATION MARK +0561..0587 ; R # Ll [39] ARMENIAN SMALL LETTER AYB..ARMENIAN SMALL LIGATURE ECH YIWN +0589 ; R # Po ARMENIAN FULL STOP +058A ; R # Pd ARMENIAN HYPHEN +058D..058E ; R # So [2] RIGHT-FACING ARMENIAN ETERNITY SIGN..LEFT-FACING ARMENIAN ETERNITY SIGN +058F ; R # Sc ARMENIAN DRAM SIGN +0591..05BD ; R # Mn [45] HEBREW ACCENT ETNAHTA..HEBREW POINT METEG +05BE ; R # Pd HEBREW PUNCTUATION MAQAF +05BF ; R # Mn HEBREW POINT RAFE +05C0 ; R # Po HEBREW PUNCTUATION PASEQ +05C1..05C2 ; R # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT +05C3 ; R # Po HEBREW PUNCTUATION SOF PASUQ +05C4..05C5 ; R # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT +05C6 ; R # Po HEBREW PUNCTUATION NUN HAFUKHA +05C7 ; R # Mn HEBREW POINT QAMATS QATAN +05D0..05EA ; R # Lo [27] HEBREW LETTER ALEF..HEBREW LETTER TAV +05F0..05F2 ; R # Lo [3] HEBREW LIGATURE YIDDISH DOUBLE VAV..HEBREW LIGATURE YIDDISH DOUBLE YOD +05F3..05F4 ; R # Po [2] HEBREW PUNCTUATION GERESH..HEBREW PUNCTUATION GERSHAYIM +0600..0605 ; R # Cf [6] ARABIC NUMBER SIGN..ARABIC NUMBER MARK ABOVE +0606..0608 ; R # Sm [3] ARABIC-INDIC CUBE ROOT..ARABIC RAY +0609..060A ; R # Po [2] ARABIC-INDIC PER MILLE SIGN..ARABIC-INDIC PER TEN THOUSAND SIGN +060B ; R # Sc AFGHANI SIGN +060C..060D ; R # Po [2] ARABIC COMMA..ARABIC DATE SEPARATOR +060E..060F ; R # So [2] ARABIC POETIC VERSE SIGN..ARABIC SIGN MISRA +0610..061A ; R # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA +061B ; R # Po ARABIC SEMICOLON +061C ; R # Cf ARABIC LETTER MARK +061E..061F ; R # Po [2] ARABIC TRIPLE DOT PUNCTUATION MARK..ARABIC QUESTION MARK +0620..063F ; R # Lo [32] ARABIC LETTER KASHMIRI YEH..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE +0640 ; R # Lm ARABIC TATWEEL +0641..064A ; R # Lo [10] ARABIC LETTER FEH..ARABIC LETTER YEH +064B..065F ; R # Mn [21] ARABIC FATHATAN..ARABIC WAVY HAMZA BELOW +0660..0669 ; R # Nd [10] ARABIC-INDIC DIGIT ZERO..ARABIC-INDIC DIGIT NINE +066A..066D ; R # Po [4] ARABIC PERCENT SIGN..ARABIC FIVE POINTED STAR +066E..066F ; R # Lo [2] ARABIC LETTER DOTLESS BEH..ARABIC LETTER DOTLESS QAF +0670 ; R # Mn ARABIC LETTER SUPERSCRIPT ALEF +0671..06D3 ; R # Lo [99] ARABIC LETTER ALEF WASLA..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE +06D4 ; R # Po ARABIC FULL STOP +06D5 ; R # Lo ARABIC LETTER AE +06D6..06DC ; R # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN +06DD ; R # Cf ARABIC END OF AYAH +06DE ; R # So ARABIC START OF RUB EL HIZB +06DF..06E4 ; R # Mn [6] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH MADDA +06E5..06E6 ; R # Lm [2] ARABIC SMALL WAW..ARABIC SMALL YEH +06E7..06E8 ; R # Mn [2] ARABIC SMALL HIGH YEH..ARABIC SMALL HIGH NOON +06E9 ; R # So ARABIC PLACE OF SAJDAH +06EA..06ED ; R # Mn [4] ARABIC EMPTY CENTRE LOW STOP..ARABIC SMALL LOW MEEM +06EE..06EF ; R # Lo [2] ARABIC LETTER DAL WITH INVERTED V..ARABIC LETTER REH WITH INVERTED V +06F0..06F9 ; R # Nd [10] EXTENDED ARABIC-INDIC DIGIT ZERO..EXTENDED ARABIC-INDIC DIGIT NINE +06FA..06FC ; R # Lo [3] ARABIC LETTER SHEEN WITH DOT BELOW..ARABIC LETTER GHAIN WITH DOT BELOW +06FD..06FE ; R # So [2] ARABIC SIGN SINDHI AMPERSAND..ARABIC SIGN SINDHI POSTPOSITION MEN +06FF ; R # Lo ARABIC LETTER HEH WITH INVERTED V +0700..070D ; R # Po [14] SYRIAC END OF PARAGRAPH..SYRIAC HARKLEAN ASTERISCUS +070F ; R # Cf SYRIAC ABBREVIATION MARK +0710 ; R # Lo SYRIAC LETTER ALAPH +0711 ; R # Mn SYRIAC LETTER SUPERSCRIPT ALAPH +0712..072F ; R # Lo [30] SYRIAC LETTER BETH..SYRIAC LETTER PERSIAN DHALATH +0730..074A ; R # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH +074D..074F ; R # Lo [3] SYRIAC LETTER SOGDIAN ZHAIN..SYRIAC LETTER SOGDIAN FE +0750..077F ; R # Lo [48] ARABIC LETTER BEH WITH THREE DOTS HORIZONTALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS ABOVE +0780..07A5 ; R # Lo [38] THAANA LETTER HAA..THAANA LETTER WAAVU +07A6..07B0 ; R # Mn [11] THAANA ABAFILI..THAANA SUKUN +07B1 ; R # Lo THAANA LETTER NAA +07C0..07C9 ; R # Nd [10] NKO DIGIT ZERO..NKO DIGIT NINE +07CA..07EA ; R # Lo [33] NKO LETTER A..NKO LETTER JONA RA +07EB..07F3 ; R # Mn [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE +07F4..07F5 ; R # Lm [2] NKO HIGH TONE APOSTROPHE..NKO LOW TONE APOSTROPHE +07F6 ; R # So NKO SYMBOL OO DENNEN +07F7..07F9 ; R # Po [3] NKO SYMBOL GBAKURUNEN..NKO EXCLAMATION MARK +07FA ; R # Lm NKO LAJANYALAN +0800..0815 ; R # Lo [22] SAMARITAN LETTER ALAF..SAMARITAN LETTER TAAF +0816..0819 ; R # Mn [4] SAMARITAN MARK IN..SAMARITAN MARK DAGESH +081A ; R # Lm SAMARITAN MODIFIER LETTER EPENTHETIC YUT +081B..0823 ; R # Mn [9] SAMARITAN MARK EPENTHETIC YUT..SAMARITAN VOWEL SIGN A +0824 ; R # Lm SAMARITAN MODIFIER LETTER SHORT A +0825..0827 ; R # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U +0828 ; R # Lm SAMARITAN MODIFIER LETTER I +0829..082D ; R # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA +0830..083E ; R # Po [15] SAMARITAN PUNCTUATION NEQUDAA..SAMARITAN PUNCTUATION ANNAAU +0840..0858 ; R # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN +0859..085B ; R # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK +085E ; R # Po MANDAIC PUNCTUATION +0860..086A ; R # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA +08A0..08B4 ; R # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW +08B6..08BD ; R # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON +08D4..08E1 ; R # Mn [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA +08E2 ; R # Cf ARABIC DISPUTED END OF AYAH +08E3..08FF ; R # Mn [29] ARABIC TURNED DAMMA BELOW..ARABIC MARK SIDEWAYS NOON GHUNNA +0900..0902 ; R # Mn [3] DEVANAGARI SIGN INVERTED CANDRABINDU..DEVANAGARI SIGN ANUSVARA +0903 ; R # Mc DEVANAGARI SIGN VISARGA +0904..0939 ; R # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA +093A ; R # Mn DEVANAGARI VOWEL SIGN OE +093B ; R # Mc DEVANAGARI VOWEL SIGN OOE +093C ; R # Mn DEVANAGARI SIGN NUKTA +093D ; R # Lo DEVANAGARI SIGN AVAGRAHA +093E..0940 ; R # Mc [3] DEVANAGARI VOWEL SIGN AA..DEVANAGARI VOWEL SIGN II +0941..0948 ; R # Mn [8] DEVANAGARI VOWEL SIGN U..DEVANAGARI VOWEL SIGN AI +0949..094C ; R # Mc [4] DEVANAGARI VOWEL SIGN CANDRA O..DEVANAGARI VOWEL SIGN AU +094D ; R # Mn DEVANAGARI SIGN VIRAMA +094E..094F ; R # Mc [2] DEVANAGARI VOWEL SIGN PRISHTHAMATRA E..DEVANAGARI VOWEL SIGN AW +0950 ; R # Lo DEVANAGARI OM +0951..0957 ; R # Mn [7] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI VOWEL SIGN UUE +0958..0961 ; R # Lo [10] DEVANAGARI LETTER QA..DEVANAGARI LETTER VOCALIC LL +0962..0963 ; R # Mn [2] DEVANAGARI VOWEL SIGN VOCALIC L..DEVANAGARI VOWEL SIGN VOCALIC LL +0964..0965 ; R # Po [2] DEVANAGARI DANDA..DEVANAGARI DOUBLE DANDA +0966..096F ; R # Nd [10] DEVANAGARI DIGIT ZERO..DEVANAGARI DIGIT NINE +0970 ; R # Po DEVANAGARI ABBREVIATION SIGN +0971 ; R # Lm DEVANAGARI SIGN HIGH SPACING DOT +0972..097F ; R # Lo [14] DEVANAGARI LETTER CANDRA A..DEVANAGARI LETTER BBA +0980 ; R # Lo BENGALI ANJI +0981 ; R # Mn BENGALI SIGN CANDRABINDU +0982..0983 ; R # Mc [2] BENGALI SIGN ANUSVARA..BENGALI SIGN VISARGA +0985..098C ; R # Lo [8] BENGALI LETTER A..BENGALI LETTER VOCALIC L +098F..0990 ; R # Lo [2] BENGALI LETTER E..BENGALI LETTER AI +0993..09A8 ; R # Lo [22] BENGALI LETTER O..BENGALI LETTER NA +09AA..09B0 ; R # Lo [7] BENGALI LETTER PA..BENGALI LETTER RA +09B2 ; R # Lo BENGALI LETTER LA +09B6..09B9 ; R # Lo [4] BENGALI LETTER SHA..BENGALI LETTER HA +09BC ; R # Mn BENGALI SIGN NUKTA +09BD ; R # Lo BENGALI SIGN AVAGRAHA +09BE..09C0 ; R # Mc [3] BENGALI VOWEL SIGN AA..BENGALI VOWEL SIGN II +09C1..09C4 ; R # Mn [4] BENGALI VOWEL SIGN U..BENGALI VOWEL SIGN VOCALIC RR +09C7..09C8 ; R # Mc [2] BENGALI VOWEL SIGN E..BENGALI VOWEL SIGN AI +09CB..09CC ; R # Mc [2] BENGALI VOWEL SIGN O..BENGALI VOWEL SIGN AU +09CD ; R # Mn BENGALI SIGN VIRAMA +09CE ; R # Lo BENGALI LETTER KHANDA TA +09D7 ; R # Mc BENGALI AU LENGTH MARK +09DC..09DD ; R # Lo [2] BENGALI LETTER RRA..BENGALI LETTER RHA +09DF..09E1 ; R # Lo [3] BENGALI LETTER YYA..BENGALI LETTER VOCALIC LL +09E2..09E3 ; R # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL +09E6..09EF ; R # Nd [10] BENGALI DIGIT ZERO..BENGALI DIGIT NINE +09F0..09F1 ; R # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL +09F2..09F3 ; R # Sc [2] BENGALI RUPEE MARK..BENGALI RUPEE SIGN +09F4..09F9 ; R # No [6] BENGALI CURRENCY NUMERATOR ONE..BENGALI CURRENCY DENOMINATOR SIXTEEN +09FA ; R # So BENGALI ISSHAR +09FB ; R # Sc BENGALI GANDA MARK +09FC ; R # Lo BENGALI LETTER VEDIC ANUSVARA +09FD ; R # Po BENGALI ABBREVIATION SIGN +0A01..0A02 ; R # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI +0A03 ; R # Mc GURMUKHI SIGN VISARGA +0A05..0A0A ; R # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU +0A0F..0A10 ; R # Lo [2] GURMUKHI LETTER EE..GURMUKHI LETTER AI +0A13..0A28 ; R # Lo [22] GURMUKHI LETTER OO..GURMUKHI LETTER NA +0A2A..0A30 ; R # Lo [7] GURMUKHI LETTER PA..GURMUKHI LETTER RA +0A32..0A33 ; R # Lo [2] GURMUKHI LETTER LA..GURMUKHI LETTER LLA +0A35..0A36 ; R # Lo [2] GURMUKHI LETTER VA..GURMUKHI LETTER SHA +0A38..0A39 ; R # Lo [2] GURMUKHI LETTER SA..GURMUKHI LETTER HA +0A3C ; R # Mn GURMUKHI SIGN NUKTA +0A3E..0A40 ; R # Mc [3] GURMUKHI VOWEL SIGN AA..GURMUKHI VOWEL SIGN II +0A41..0A42 ; R # Mn [2] GURMUKHI VOWEL SIGN U..GURMUKHI VOWEL SIGN UU +0A47..0A48 ; R # Mn [2] GURMUKHI VOWEL SIGN EE..GURMUKHI VOWEL SIGN AI +0A4B..0A4D ; R # Mn [3] GURMUKHI VOWEL SIGN OO..GURMUKHI SIGN VIRAMA +0A51 ; R # Mn GURMUKHI SIGN UDAAT +0A59..0A5C ; R # Lo [4] GURMUKHI LETTER KHHA..GURMUKHI LETTER RRA +0A5E ; R # Lo GURMUKHI LETTER FA +0A66..0A6F ; R # Nd [10] GURMUKHI DIGIT ZERO..GURMUKHI DIGIT NINE +0A70..0A71 ; R # Mn [2] GURMUKHI TIPPI..GURMUKHI ADDAK +0A72..0A74 ; R # Lo [3] GURMUKHI IRI..GURMUKHI EK ONKAR +0A75 ; R # Mn GURMUKHI SIGN YAKASH +0A81..0A82 ; R # Mn [2] GUJARATI SIGN CANDRABINDU..GUJARATI SIGN ANUSVARA +0A83 ; R # Mc GUJARATI SIGN VISARGA +0A85..0A8D ; R # Lo [9] GUJARATI LETTER A..GUJARATI VOWEL CANDRA E +0A8F..0A91 ; R # Lo [3] GUJARATI LETTER E..GUJARATI VOWEL CANDRA O +0A93..0AA8 ; R # Lo [22] GUJARATI LETTER O..GUJARATI LETTER NA +0AAA..0AB0 ; R # Lo [7] GUJARATI LETTER PA..GUJARATI LETTER RA +0AB2..0AB3 ; R # Lo [2] GUJARATI LETTER LA..GUJARATI LETTER LLA +0AB5..0AB9 ; R # Lo [5] GUJARATI LETTER VA..GUJARATI LETTER HA +0ABC ; R # Mn GUJARATI SIGN NUKTA +0ABD ; R # Lo GUJARATI SIGN AVAGRAHA +0ABE..0AC0 ; R # Mc [3] GUJARATI VOWEL SIGN AA..GUJARATI VOWEL SIGN II +0AC1..0AC5 ; R # Mn [5] GUJARATI VOWEL SIGN U..GUJARATI VOWEL SIGN CANDRA E +0AC7..0AC8 ; R # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI +0AC9 ; R # Mc GUJARATI VOWEL SIGN CANDRA O +0ACB..0ACC ; R # Mc [2] GUJARATI VOWEL SIGN O..GUJARATI VOWEL SIGN AU +0ACD ; R # Mn GUJARATI SIGN VIRAMA +0AD0 ; R # Lo GUJARATI OM +0AE0..0AE1 ; R # Lo [2] GUJARATI LETTER VOCALIC RR..GUJARATI LETTER VOCALIC LL +0AE2..0AE3 ; R # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0AE6..0AEF ; R # Nd [10] GUJARATI DIGIT ZERO..GUJARATI DIGIT NINE +0AF0 ; R # Po GUJARATI ABBREVIATION SIGN +0AF1 ; R # Sc GUJARATI RUPEE SIGN +0AF9 ; R # Lo GUJARATI LETTER ZHA +0AFA..0AFF ; R # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE +0B01 ; R # Mn ORIYA SIGN CANDRABINDU +0B02..0B03 ; R # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA +0B05..0B0C ; R # Lo [8] ORIYA LETTER A..ORIYA LETTER VOCALIC L +0B0F..0B10 ; R # Lo [2] ORIYA LETTER E..ORIYA LETTER AI +0B13..0B28 ; R # Lo [22] ORIYA LETTER O..ORIYA LETTER NA +0B2A..0B30 ; R # Lo [7] ORIYA LETTER PA..ORIYA LETTER RA +0B32..0B33 ; R # Lo [2] ORIYA LETTER LA..ORIYA LETTER LLA +0B35..0B39 ; R # Lo [5] ORIYA LETTER VA..ORIYA LETTER HA +0B3C ; R # Mn ORIYA SIGN NUKTA +0B3D ; R # Lo ORIYA SIGN AVAGRAHA +0B3E ; R # Mc ORIYA VOWEL SIGN AA +0B3F ; R # Mn ORIYA VOWEL SIGN I +0B40 ; R # Mc ORIYA VOWEL SIGN II +0B41..0B44 ; R # Mn [4] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC RR +0B47..0B48 ; R # Mc [2] ORIYA VOWEL SIGN E..ORIYA VOWEL SIGN AI +0B4B..0B4C ; R # Mc [2] ORIYA VOWEL SIGN O..ORIYA VOWEL SIGN AU +0B4D ; R # Mn ORIYA SIGN VIRAMA +0B56 ; R # Mn ORIYA AI LENGTH MARK +0B57 ; R # Mc ORIYA AU LENGTH MARK +0B5C..0B5D ; R # Lo [2] ORIYA LETTER RRA..ORIYA LETTER RHA +0B5F..0B61 ; R # Lo [3] ORIYA LETTER YYA..ORIYA LETTER VOCALIC LL +0B62..0B63 ; R # Mn [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL +0B66..0B6F ; R # Nd [10] ORIYA DIGIT ZERO..ORIYA DIGIT NINE +0B70 ; R # So ORIYA ISSHAR +0B71 ; R # Lo ORIYA LETTER WA +0B72..0B77 ; R # No [6] ORIYA FRACTION ONE QUARTER..ORIYA FRACTION THREE SIXTEENTHS +0B82 ; R # Mn TAMIL SIGN ANUSVARA +0B83 ; R # Lo TAMIL SIGN VISARGA +0B85..0B8A ; R # Lo [6] TAMIL LETTER A..TAMIL LETTER UU +0B8E..0B90 ; R # Lo [3] TAMIL LETTER E..TAMIL LETTER AI +0B92..0B95 ; R # Lo [4] TAMIL LETTER O..TAMIL LETTER KA +0B99..0B9A ; R # Lo [2] TAMIL LETTER NGA..TAMIL LETTER CA +0B9C ; R # Lo TAMIL LETTER JA +0B9E..0B9F ; R # Lo [2] TAMIL LETTER NYA..TAMIL LETTER TTA +0BA3..0BA4 ; R # Lo [2] TAMIL LETTER NNA..TAMIL LETTER TA +0BA8..0BAA ; R # Lo [3] TAMIL LETTER NA..TAMIL LETTER PA +0BAE..0BB9 ; R # Lo [12] TAMIL LETTER MA..TAMIL LETTER HA +0BBE..0BBF ; R # Mc [2] TAMIL VOWEL SIGN AA..TAMIL VOWEL SIGN I +0BC0 ; R # Mn TAMIL VOWEL SIGN II +0BC1..0BC2 ; R # Mc [2] TAMIL VOWEL SIGN U..TAMIL VOWEL SIGN UU +0BC6..0BC8 ; R # Mc [3] TAMIL VOWEL SIGN E..TAMIL VOWEL SIGN AI +0BCA..0BCC ; R # Mc [3] TAMIL VOWEL SIGN O..TAMIL VOWEL SIGN AU +0BCD ; R # Mn TAMIL SIGN VIRAMA +0BD0 ; R # Lo TAMIL OM +0BD7 ; R # Mc TAMIL AU LENGTH MARK +0BE6..0BEF ; R # Nd [10] TAMIL DIGIT ZERO..TAMIL DIGIT NINE +0BF0..0BF2 ; R # No [3] TAMIL NUMBER TEN..TAMIL NUMBER ONE THOUSAND +0BF3..0BF8 ; R # So [6] TAMIL DAY SIGN..TAMIL AS ABOVE SIGN +0BF9 ; R # Sc TAMIL RUPEE SIGN +0BFA ; R # So TAMIL NUMBER SIGN +0C00 ; R # Mn TELUGU SIGN COMBINING CANDRABINDU ABOVE +0C01..0C03 ; R # Mc [3] TELUGU SIGN CANDRABINDU..TELUGU SIGN VISARGA +0C05..0C0C ; R # Lo [8] TELUGU LETTER A..TELUGU LETTER VOCALIC L +0C0E..0C10 ; R # Lo [3] TELUGU LETTER E..TELUGU LETTER AI +0C12..0C28 ; R # Lo [23] TELUGU LETTER O..TELUGU LETTER NA +0C2A..0C39 ; R # Lo [16] TELUGU LETTER PA..TELUGU LETTER HA +0C3D ; R # Lo TELUGU SIGN AVAGRAHA +0C3E..0C40 ; R # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II +0C41..0C44 ; R # Mc [4] TELUGU VOWEL SIGN U..TELUGU VOWEL SIGN VOCALIC RR +0C46..0C48 ; R # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI +0C4A..0C4D ; R # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA +0C55..0C56 ; R # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK +0C58..0C5A ; R # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA +0C60..0C61 ; R # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL +0C62..0C63 ; R # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL +0C66..0C6F ; R # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE +0C78..0C7E ; R # No [7] TELUGU FRACTION DIGIT ZERO FOR ODD POWERS OF FOUR..TELUGU FRACTION DIGIT THREE FOR EVEN POWERS OF FOUR +0C7F ; R # So TELUGU SIGN TUUMU +0C80 ; R # Lo KANNADA SIGN SPACING CANDRABINDU +0C81 ; R # Mn KANNADA SIGN CANDRABINDU +0C82..0C83 ; R # Mc [2] KANNADA SIGN ANUSVARA..KANNADA SIGN VISARGA +0C85..0C8C ; R # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L +0C8E..0C90 ; R # Lo [3] KANNADA LETTER E..KANNADA LETTER AI +0C92..0CA8 ; R # Lo [23] KANNADA LETTER O..KANNADA LETTER NA +0CAA..0CB3 ; R # Lo [10] KANNADA LETTER PA..KANNADA LETTER LLA +0CB5..0CB9 ; R # Lo [5] KANNADA LETTER VA..KANNADA LETTER HA +0CBC ; R # Mn KANNADA SIGN NUKTA +0CBD ; R # Lo KANNADA SIGN AVAGRAHA +0CBE ; R # Mc KANNADA VOWEL SIGN AA +0CBF ; R # Mn KANNADA VOWEL SIGN I +0CC0..0CC4 ; R # Mc [5] KANNADA VOWEL SIGN II..KANNADA VOWEL SIGN VOCALIC RR +0CC6 ; R # Mn KANNADA VOWEL SIGN E +0CC7..0CC8 ; R # Mc [2] KANNADA VOWEL SIGN EE..KANNADA VOWEL SIGN AI +0CCA..0CCB ; R # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO +0CCC..0CCD ; R # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA +0CD5..0CD6 ; R # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK +0CDE ; R # Lo KANNADA LETTER FA +0CE0..0CE1 ; R # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL +0CE2..0CE3 ; R # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL +0CE6..0CEF ; R # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE +0CF1..0CF2 ; R # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA +0D00..0D01 ; R # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU +0D02..0D03 ; R # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA +0D05..0D0C ; R # Lo [8] MALAYALAM LETTER A..MALAYALAM LETTER VOCALIC L +0D0E..0D10 ; R # Lo [3] MALAYALAM LETTER E..MALAYALAM LETTER AI +0D12..0D3A ; R # Lo [41] MALAYALAM LETTER O..MALAYALAM LETTER TTTA +0D3B..0D3C ; R # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA +0D3D ; R # Lo MALAYALAM SIGN AVAGRAHA +0D3E..0D40 ; R # Mc [3] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN II +0D41..0D44 ; R # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR +0D46..0D48 ; R # Mc [3] MALAYALAM VOWEL SIGN E..MALAYALAM VOWEL SIGN AI +0D4A..0D4C ; R # Mc [3] MALAYALAM VOWEL SIGN O..MALAYALAM VOWEL SIGN AU +0D4D ; R # Mn MALAYALAM SIGN VIRAMA +0D4E ; R # Lo MALAYALAM LETTER DOT REPH +0D4F ; R # So MALAYALAM SIGN PARA +0D54..0D56 ; R # Lo [3] MALAYALAM LETTER CHILLU M..MALAYALAM LETTER CHILLU LLL +0D57 ; R # Mc MALAYALAM AU LENGTH MARK +0D58..0D5E ; R # No [7] MALAYALAM FRACTION ONE ONE-HUNDRED-AND-SIXTIETH..MALAYALAM FRACTION ONE FIFTH +0D5F..0D61 ; R # Lo [3] MALAYALAM LETTER ARCHAIC II..MALAYALAM LETTER VOCALIC LL +0D62..0D63 ; R # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL +0D66..0D6F ; R # Nd [10] MALAYALAM DIGIT ZERO..MALAYALAM DIGIT NINE +0D70..0D78 ; R # No [9] MALAYALAM NUMBER TEN..MALAYALAM FRACTION THREE SIXTEENTHS +0D79 ; R # So MALAYALAM DATE MARK +0D7A..0D7F ; R # Lo [6] MALAYALAM LETTER CHILLU NN..MALAYALAM LETTER CHILLU K +0D82..0D83 ; R # Mc [2] SINHALA SIGN ANUSVARAYA..SINHALA SIGN VISARGAYA +0D85..0D96 ; R # Lo [18] SINHALA LETTER AYANNA..SINHALA LETTER AUYANNA +0D9A..0DB1 ; R # Lo [24] SINHALA LETTER ALPAPRAANA KAYANNA..SINHALA LETTER DANTAJA NAYANNA +0DB3..0DBB ; R # Lo [9] SINHALA LETTER SANYAKA DAYANNA..SINHALA LETTER RAYANNA +0DBD ; R # Lo SINHALA LETTER DANTAJA LAYANNA +0DC0..0DC6 ; R # Lo [7] SINHALA LETTER VAYANNA..SINHALA LETTER FAYANNA +0DCA ; R # Mn SINHALA SIGN AL-LAKUNA +0DCF..0DD1 ; R # Mc [3] SINHALA VOWEL SIGN AELA-PILLA..SINHALA VOWEL SIGN DIGA AEDA-PILLA +0DD2..0DD4 ; R # Mn [3] SINHALA VOWEL SIGN KETTI IS-PILLA..SINHALA VOWEL SIGN KETTI PAA-PILLA +0DD6 ; R # Mn SINHALA VOWEL SIGN DIGA PAA-PILLA +0DD8..0DDF ; R # Mc [8] SINHALA VOWEL SIGN GAETTA-PILLA..SINHALA VOWEL SIGN GAYANUKITTA +0DE6..0DEF ; R # Nd [10] SINHALA LITH DIGIT ZERO..SINHALA LITH DIGIT NINE +0DF2..0DF3 ; R # Mc [2] SINHALA VOWEL SIGN DIGA GAETTA-PILLA..SINHALA VOWEL SIGN DIGA GAYANUKITTA +0DF4 ; R # Po SINHALA PUNCTUATION KUNDDALIYA +0E01..0E30 ; R # Lo [48] THAI CHARACTER KO KAI..THAI CHARACTER SARA A +0E31 ; R # Mn THAI CHARACTER MAI HAN-AKAT +0E32..0E33 ; R # Lo [2] THAI CHARACTER SARA AA..THAI CHARACTER SARA AM +0E34..0E3A ; R # Mn [7] THAI CHARACTER SARA I..THAI CHARACTER PHINTHU +0E3F ; R # Sc THAI CURRENCY SYMBOL BAHT +0E40..0E45 ; R # Lo [6] THAI CHARACTER SARA E..THAI CHARACTER LAKKHANGYAO +0E46 ; R # Lm THAI CHARACTER MAIYAMOK +0E47..0E4E ; R # Mn [8] THAI CHARACTER MAITAIKHU..THAI CHARACTER YAMAKKAN +0E4F ; R # Po THAI CHARACTER FONGMAN +0E50..0E59 ; R # Nd [10] THAI DIGIT ZERO..THAI DIGIT NINE +0E5A..0E5B ; R # Po [2] THAI CHARACTER ANGKHANKHU..THAI CHARACTER KHOMUT +0E81..0E82 ; R # Lo [2] LAO LETTER KO..LAO LETTER KHO SUNG +0E84 ; R # Lo LAO LETTER KHO TAM +0E87..0E88 ; R # Lo [2] LAO LETTER NGO..LAO LETTER CO +0E8A ; R # Lo LAO LETTER SO TAM +0E8D ; R # Lo LAO LETTER NYO +0E94..0E97 ; R # Lo [4] LAO LETTER DO..LAO LETTER THO TAM +0E99..0E9F ; R # Lo [7] LAO LETTER NO..LAO LETTER FO SUNG +0EA1..0EA3 ; R # Lo [3] LAO LETTER MO..LAO LETTER LO LING +0EA5 ; R # Lo LAO LETTER LO LOOT +0EA7 ; R # Lo LAO LETTER WO +0EAA..0EAB ; R # Lo [2] LAO LETTER SO SUNG..LAO LETTER HO SUNG +0EAD..0EB0 ; R # Lo [4] LAO LETTER O..LAO VOWEL SIGN A +0EB1 ; R # Mn LAO VOWEL SIGN MAI KAN +0EB2..0EB3 ; R # Lo [2] LAO VOWEL SIGN AA..LAO VOWEL SIGN AM +0EB4..0EB9 ; R # Mn [6] LAO VOWEL SIGN I..LAO VOWEL SIGN UU +0EBB..0EBC ; R # Mn [2] LAO VOWEL SIGN MAI KON..LAO SEMIVOWEL SIGN LO +0EBD ; R # Lo LAO SEMIVOWEL SIGN NYO +0EC0..0EC4 ; R # Lo [5] LAO VOWEL SIGN E..LAO VOWEL SIGN AI +0EC6 ; R # Lm LAO KO LA +0EC8..0ECD ; R # Mn [6] LAO TONE MAI EK..LAO NIGGAHITA +0ED0..0ED9 ; R # Nd [10] LAO DIGIT ZERO..LAO DIGIT NINE +0EDC..0EDF ; R # Lo [4] LAO HO NO..LAO LETTER KHMU NYO +0F00 ; R # Lo TIBETAN SYLLABLE OM +0F01..0F03 ; R # So [3] TIBETAN MARK GTER YIG MGO TRUNCATED A..TIBETAN MARK GTER YIG MGO -UM GTER TSHEG MA +0F04..0F12 ; R # Po [15] TIBETAN MARK INITIAL YIG MGO MDUN MA..TIBETAN MARK RGYA GRAM SHAD +0F13 ; R # So TIBETAN MARK CARET -DZUD RTAGS ME LONG CAN +0F14 ; R # Po TIBETAN MARK GTER TSHEG +0F15..0F17 ; R # So [3] TIBETAN LOGOTYPE SIGN CHAD RTAGS..TIBETAN ASTROLOGICAL SIGN SGRA GCAN -CHAR RTAGS +0F18..0F19 ; R # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS +0F1A..0F1F ; R # So [6] TIBETAN SIGN RDEL DKAR GCIG..TIBETAN SIGN RDEL DKAR RDEL NAG +0F20..0F29 ; R # Nd [10] TIBETAN DIGIT ZERO..TIBETAN DIGIT NINE +0F2A..0F33 ; R # No [10] TIBETAN DIGIT HALF ONE..TIBETAN DIGIT HALF ZERO +0F34 ; R # So TIBETAN MARK BSDUS RTAGS +0F35 ; R # Mn TIBETAN MARK NGAS BZUNG NYI ZLA +0F36 ; R # So TIBETAN MARK CARET -DZUD RTAGS BZHI MIG CAN +0F37 ; R # Mn TIBETAN MARK NGAS BZUNG SGOR RTAGS +0F38 ; R # So TIBETAN MARK CHE MGO +0F39 ; R # Mn TIBETAN MARK TSA -PHRU +0F3A ; R # Ps TIBETAN MARK GUG RTAGS GYON +0F3B ; R # Pe TIBETAN MARK GUG RTAGS GYAS +0F3C ; R # Ps TIBETAN MARK ANG KHANG GYON +0F3D ; R # Pe TIBETAN MARK ANG KHANG GYAS +0F3E..0F3F ; R # Mc [2] TIBETAN SIGN YAR TSHES..TIBETAN SIGN MAR TSHES +0F40..0F47 ; R # Lo [8] TIBETAN LETTER KA..TIBETAN LETTER JA +0F49..0F6C ; R # Lo [36] TIBETAN LETTER NYA..TIBETAN LETTER RRA +0F71..0F7E ; R # Mn [14] TIBETAN VOWEL SIGN AA..TIBETAN SIGN RJES SU NGA RO +0F7F ; R # Mc TIBETAN SIGN RNAM BCAD +0F80..0F84 ; R # Mn [5] TIBETAN VOWEL SIGN REVERSED I..TIBETAN MARK HALANTA +0F85 ; R # Po TIBETAN MARK PALUTA +0F86..0F87 ; R # Mn [2] TIBETAN SIGN LCI RTAGS..TIBETAN SIGN YANG RTAGS +0F88..0F8C ; R # Lo [5] TIBETAN SIGN LCE TSA CAN..TIBETAN SIGN INVERTED MCHU CAN +0F8D..0F97 ; R # Mn [11] TIBETAN SUBJOINED SIGN LCE TSA CAN..TIBETAN SUBJOINED LETTER JA +0F99..0FBC ; R # Mn [36] TIBETAN SUBJOINED LETTER NYA..TIBETAN SUBJOINED LETTER FIXED-FORM RA +0FBE..0FC5 ; R # So [8] TIBETAN KU RU KHA..TIBETAN SYMBOL RDO RJE +0FC6 ; R # Mn TIBETAN SYMBOL PADMA GDAN +0FC7..0FCC ; R # So [6] TIBETAN SYMBOL RDO RJE RGYA GRAM..TIBETAN SYMBOL NOR BU BZHI -KHYIL +0FCE..0FCF ; R # So [2] TIBETAN SIGN RDEL NAG RDEL DKAR..TIBETAN SIGN RDEL NAG GSUM +0FD0..0FD4 ; R # Po [5] TIBETAN MARK BSKA- SHOG GI MGO RGYAN..TIBETAN MARK CLOSING BRDA RNYING YIG MGO SGAB MA +0FD5..0FD8 ; R # So [4] RIGHT-FACING SVASTI SIGN..LEFT-FACING SVASTI SIGN WITH DOTS +0FD9..0FDA ; R # Po [2] TIBETAN MARK LEADING MCHAN RTAGS..TIBETAN MARK TRAILING MCHAN RTAGS +1000..102A ; R # Lo [43] MYANMAR LETTER KA..MYANMAR LETTER AU +102B..102C ; R # Mc [2] MYANMAR VOWEL SIGN TALL AA..MYANMAR VOWEL SIGN AA +102D..1030 ; R # Mn [4] MYANMAR VOWEL SIGN I..MYANMAR VOWEL SIGN UU +1031 ; R # Mc MYANMAR VOWEL SIGN E +1032..1037 ; R # Mn [6] MYANMAR VOWEL SIGN AI..MYANMAR SIGN DOT BELOW +1038 ; R # Mc MYANMAR SIGN VISARGA +1039..103A ; R # Mn [2] MYANMAR SIGN VIRAMA..MYANMAR SIGN ASAT +103B..103C ; R # Mc [2] MYANMAR CONSONANT SIGN MEDIAL YA..MYANMAR CONSONANT SIGN MEDIAL RA +103D..103E ; R # Mn [2] MYANMAR CONSONANT SIGN MEDIAL WA..MYANMAR CONSONANT SIGN MEDIAL HA +103F ; R # Lo MYANMAR LETTER GREAT SA +1040..1049 ; R # Nd [10] MYANMAR DIGIT ZERO..MYANMAR DIGIT NINE +104A..104F ; R # Po [6] MYANMAR SIGN LITTLE SECTION..MYANMAR SYMBOL GENITIVE +1050..1055 ; R # Lo [6] MYANMAR LETTER SHA..MYANMAR LETTER VOCALIC LL +1056..1057 ; R # Mc [2] MYANMAR VOWEL SIGN VOCALIC R..MYANMAR VOWEL SIGN VOCALIC RR +1058..1059 ; R # Mn [2] MYANMAR VOWEL SIGN VOCALIC L..MYANMAR VOWEL SIGN VOCALIC LL +105A..105D ; R # Lo [4] MYANMAR LETTER MON NGA..MYANMAR LETTER MON BBE +105E..1060 ; R # Mn [3] MYANMAR CONSONANT SIGN MON MEDIAL NA..MYANMAR CONSONANT SIGN MON MEDIAL LA +1061 ; R # Lo MYANMAR LETTER SGAW KAREN SHA +1062..1064 ; R # Mc [3] MYANMAR VOWEL SIGN SGAW KAREN EU..MYANMAR TONE MARK SGAW KAREN KE PHO +1065..1066 ; R # Lo [2] MYANMAR LETTER WESTERN PWO KAREN THA..MYANMAR LETTER WESTERN PWO KAREN PWA +1067..106D ; R # Mc [7] MYANMAR VOWEL SIGN WESTERN PWO KAREN EU..MYANMAR SIGN WESTERN PWO KAREN TONE-5 +106E..1070 ; R # Lo [3] MYANMAR LETTER EASTERN PWO KAREN NNA..MYANMAR LETTER EASTERN PWO KAREN GHWA +1071..1074 ; R # Mn [4] MYANMAR VOWEL SIGN GEBA KAREN I..MYANMAR VOWEL SIGN KAYAH EE +1075..1081 ; R # Lo [13] MYANMAR LETTER SHAN KA..MYANMAR LETTER SHAN HA +1082 ; R # Mn MYANMAR CONSONANT SIGN SHAN MEDIAL WA +1083..1084 ; R # Mc [2] MYANMAR VOWEL SIGN SHAN AA..MYANMAR VOWEL SIGN SHAN E +1085..1086 ; R # Mn [2] MYANMAR VOWEL SIGN SHAN E ABOVE..MYANMAR VOWEL SIGN SHAN FINAL Y +1087..108C ; R # Mc [6] MYANMAR SIGN SHAN TONE-2..MYANMAR SIGN SHAN COUNCIL TONE-3 +108D ; R # Mn MYANMAR SIGN SHAN COUNCIL EMPHATIC TONE +108E ; R # Lo MYANMAR LETTER RUMAI PALAUNG FA +108F ; R # Mc MYANMAR SIGN RUMAI PALAUNG TONE-5 +1090..1099 ; R # Nd [10] MYANMAR SHAN DIGIT ZERO..MYANMAR SHAN DIGIT NINE +109A..109C ; R # Mc [3] MYANMAR SIGN KHAMTI TONE-1..MYANMAR VOWEL SIGN AITON A +109D ; R # Mn MYANMAR VOWEL SIGN AITON AI +109E..109F ; R # So [2] MYANMAR SYMBOL SHAN ONE..MYANMAR SYMBOL SHAN EXCLAMATION +10A0..10C5 ; R # Lu [38] GEORGIAN CAPITAL LETTER AN..GEORGIAN CAPITAL LETTER HOE +10C7 ; R # Lu GEORGIAN CAPITAL LETTER YN +10CD ; R # Lu GEORGIAN CAPITAL LETTER AEN +10D0..10FA ; R # Lo [43] GEORGIAN LETTER AN..GEORGIAN LETTER AIN +10FB ; R # Po GEORGIAN PARAGRAPH SEPARATOR +10FC ; R # Lm MODIFIER LETTER GEORGIAN NAR +10FD..10FF ; R # Lo [3] GEORGIAN LETTER AEN..GEORGIAN LETTER LABIAL SIGN +1100..11FF ; U # Lo [256] HANGUL CHOSEONG KIYEOK..HANGUL JONGSEONG SSANGNIEUN +1200..1248 ; R # Lo [73] ETHIOPIC SYLLABLE HA..ETHIOPIC SYLLABLE QWA +124A..124D ; R # Lo [4] ETHIOPIC SYLLABLE QWI..ETHIOPIC SYLLABLE QWE +1250..1256 ; R # Lo [7] ETHIOPIC SYLLABLE QHA..ETHIOPIC SYLLABLE QHO +1258 ; R # Lo ETHIOPIC SYLLABLE QHWA +125A..125D ; R # Lo [4] ETHIOPIC SYLLABLE QHWI..ETHIOPIC SYLLABLE QHWE +1260..1288 ; R # Lo [41] ETHIOPIC SYLLABLE BA..ETHIOPIC SYLLABLE XWA +128A..128D ; R # Lo [4] ETHIOPIC SYLLABLE XWI..ETHIOPIC SYLLABLE XWE +1290..12B0 ; R # Lo [33] ETHIOPIC SYLLABLE NA..ETHIOPIC SYLLABLE KWA +12B2..12B5 ; R # Lo [4] ETHIOPIC SYLLABLE KWI..ETHIOPIC SYLLABLE KWE +12B8..12BE ; R # Lo [7] ETHIOPIC SYLLABLE KXA..ETHIOPIC SYLLABLE KXO +12C0 ; R # Lo ETHIOPIC SYLLABLE KXWA +12C2..12C5 ; R # Lo [4] ETHIOPIC SYLLABLE KXWI..ETHIOPIC SYLLABLE KXWE +12C8..12D6 ; R # Lo [15] ETHIOPIC SYLLABLE WA..ETHIOPIC SYLLABLE PHARYNGEAL O +12D8..1310 ; R # Lo [57] ETHIOPIC SYLLABLE ZA..ETHIOPIC SYLLABLE GWA +1312..1315 ; R # Lo [4] ETHIOPIC SYLLABLE GWI..ETHIOPIC SYLLABLE GWE +1318..135A ; R # Lo [67] ETHIOPIC SYLLABLE GGA..ETHIOPIC SYLLABLE FYA +135D..135F ; R # Mn [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK +1360..1368 ; R # Po [9] ETHIOPIC SECTION MARK..ETHIOPIC PARAGRAPH SEPARATOR +1369..137C ; R # No [20] ETHIOPIC DIGIT ONE..ETHIOPIC NUMBER TEN THOUSAND +1380..138F ; R # Lo [16] ETHIOPIC SYLLABLE SEBATBEIT MWA..ETHIOPIC SYLLABLE PWE +1390..1399 ; R # So [10] ETHIOPIC TONAL MARK YIZET..ETHIOPIC TONAL MARK KURT +13A0..13F5 ; R # Lu [86] CHEROKEE LETTER A..CHEROKEE LETTER MV +13F8..13FD ; R # Ll [6] CHEROKEE SMALL LETTER YE..CHEROKEE SMALL LETTER MV +1400 ; R # Pd CANADIAN SYLLABICS HYPHEN +1401..166C ; U # Lo [620] CANADIAN SYLLABICS E..CANADIAN SYLLABICS CARRIER TTSA +166D..166E ; U # Po [2] CANADIAN SYLLABICS CHI SIGN..CANADIAN SYLLABICS FULL STOP +166F..167F ; U # Lo [17] CANADIAN SYLLABICS QAI..CANADIAN SYLLABICS BLACKFOOT W +1680 ; R # Zs OGHAM SPACE MARK +1681..169A ; R # Lo [26] OGHAM LETTER BEITH..OGHAM LETTER PEITH +169B ; R # Ps OGHAM FEATHER MARK +169C ; R # Pe OGHAM REVERSED FEATHER MARK +16A0..16EA ; R # Lo [75] RUNIC LETTER FEHU FEOH FE F..RUNIC LETTER X +16EB..16ED ; R # Po [3] RUNIC SINGLE PUNCTUATION..RUNIC CROSS PUNCTUATION +16EE..16F0 ; R # Nl [3] RUNIC ARLAUG SYMBOL..RUNIC BELGTHOR SYMBOL +16F1..16F8 ; R # Lo [8] RUNIC LETTER K..RUNIC LETTER FRANKS CASKET AESC +1700..170C ; R # Lo [13] TAGALOG LETTER A..TAGALOG LETTER YA +170E..1711 ; R # Lo [4] TAGALOG LETTER LA..TAGALOG LETTER HA +1712..1714 ; R # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA +1720..1731 ; R # Lo [18] HANUNOO LETTER A..HANUNOO LETTER HA +1732..1734 ; R # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1735..1736 ; R # Po [2] PHILIPPINE SINGLE PUNCTUATION..PHILIPPINE DOUBLE PUNCTUATION +1740..1751 ; R # Lo [18] BUHID LETTER A..BUHID LETTER HA +1752..1753 ; R # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U +1760..176C ; R # Lo [13] TAGBANWA LETTER A..TAGBANWA LETTER YA +176E..1770 ; R # Lo [3] TAGBANWA LETTER LA..TAGBANWA LETTER SA +1772..1773 ; R # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U +1780..17B3 ; R # Lo [52] KHMER LETTER KA..KHMER INDEPENDENT VOWEL QAU +17B4..17B5 ; R # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA +17B6 ; R # Mc KHMER VOWEL SIGN AA +17B7..17BD ; R # Mn [7] KHMER VOWEL SIGN I..KHMER VOWEL SIGN UA +17BE..17C5 ; R # Mc [8] KHMER VOWEL SIGN OE..KHMER VOWEL SIGN AU +17C6 ; R # Mn KHMER SIGN NIKAHIT +17C7..17C8 ; R # Mc [2] KHMER SIGN REAHMUK..KHMER SIGN YUUKALEAPINTU +17C9..17D3 ; R # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT +17D4..17D6 ; R # Po [3] KHMER SIGN KHAN..KHMER SIGN CAMNUC PII KUUH +17D7 ; R # Lm KHMER SIGN LEK TOO +17D8..17DA ; R # Po [3] KHMER SIGN BEYYAL..KHMER SIGN KOOMUUT +17DB ; R # Sc KHMER CURRENCY SYMBOL RIEL +17DC ; R # Lo KHMER SIGN AVAKRAHASANYA +17DD ; R # Mn KHMER SIGN ATTHACAN +17E0..17E9 ; R # Nd [10] KHMER DIGIT ZERO..KHMER DIGIT NINE +17F0..17F9 ; R # No [10] KHMER SYMBOL LEK ATTAK SON..KHMER SYMBOL LEK ATTAK PRAM-BUON +1800..1805 ; R # Po [6] MONGOLIAN BIRGA..MONGOLIAN FOUR DOTS +1806 ; R # Pd MONGOLIAN TODO SOFT HYPHEN +1807..180A ; R # Po [4] MONGOLIAN SIBE SYLLABLE BOUNDARY MARKER..MONGOLIAN NIRUGU +180B..180D ; R # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +180E ; R # Cf MONGOLIAN VOWEL SEPARATOR +1810..1819 ; R # Nd [10] MONGOLIAN DIGIT ZERO..MONGOLIAN DIGIT NINE +1820..1842 ; R # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI +1843 ; R # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN +1844..1877 ; R # Lo [52] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER MANCHU ZHA +1880..1884 ; R # Lo [5] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER ALI GALI INVERTED UBADAMA +1885..1886 ; R # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA +1887..18A8 ; R # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA +18A9 ; R # Mn MONGOLIAN LETTER ALI GALI DAGALGA +18AA ; R # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA +18B0..18F5 ; U # Lo [70] CANADIAN SYLLABICS OY..CANADIAN SYLLABICS CARRIER DENTAL S +18F6..18FF ; U # Cn [10] <reserved-18F6>..<reserved-18FF> +1900..191E ; R # Lo [31] LIMBU VOWEL-CARRIER LETTER..LIMBU LETTER TRA +1920..1922 ; R # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U +1923..1926 ; R # Mc [4] LIMBU VOWEL SIGN EE..LIMBU VOWEL SIGN AU +1927..1928 ; R # Mn [2] LIMBU VOWEL SIGN E..LIMBU VOWEL SIGN O +1929..192B ; R # Mc [3] LIMBU SUBJOINED LETTER YA..LIMBU SUBJOINED LETTER WA +1930..1931 ; R # Mc [2] LIMBU SMALL LETTER KA..LIMBU SMALL LETTER NGA +1932 ; R # Mn LIMBU SMALL LETTER ANUSVARA +1933..1938 ; R # Mc [6] LIMBU SMALL LETTER TA..LIMBU SMALL LETTER LA +1939..193B ; R # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I +1940 ; R # So LIMBU SIGN LOO +1944..1945 ; R # Po [2] LIMBU EXCLAMATION MARK..LIMBU QUESTION MARK +1946..194F ; R # Nd [10] LIMBU DIGIT ZERO..LIMBU DIGIT NINE +1950..196D ; R # Lo [30] TAI LE LETTER KA..TAI LE LETTER AI +1970..1974 ; R # Lo [5] TAI LE LETTER TONE-2..TAI LE LETTER TONE-6 +1980..19AB ; R # Lo [44] NEW TAI LUE LETTER HIGH QA..NEW TAI LUE LETTER LOW SUA +19B0..19C9 ; R # Lo [26] NEW TAI LUE VOWEL SIGN VOWEL SHORTENER..NEW TAI LUE TONE MARK-2 +19D0..19D9 ; R # Nd [10] NEW TAI LUE DIGIT ZERO..NEW TAI LUE DIGIT NINE +19DA ; R # No NEW TAI LUE THAM DIGIT ONE +19DE..19DF ; R # So [2] NEW TAI LUE SIGN LAE..NEW TAI LUE SIGN LAEV +19E0..19FF ; R # So [32] KHMER SYMBOL PATHAMASAT..KHMER SYMBOL DAP-PRAM ROC +1A00..1A16 ; R # Lo [23] BUGINESE LETTER KA..BUGINESE LETTER HA +1A17..1A18 ; R # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U +1A19..1A1A ; R # Mc [2] BUGINESE VOWEL SIGN E..BUGINESE VOWEL SIGN O +1A1B ; R # Mn BUGINESE VOWEL SIGN AE +1A1E..1A1F ; R # Po [2] BUGINESE PALLAWA..BUGINESE END OF SECTION +1A20..1A54 ; R # Lo [53] TAI THAM LETTER HIGH KA..TAI THAM LETTER GREAT SA +1A55 ; R # Mc TAI THAM CONSONANT SIGN MEDIAL RA +1A56 ; R # Mn TAI THAM CONSONANT SIGN MEDIAL LA +1A57 ; R # Mc TAI THAM CONSONANT SIGN LA TANG LAI +1A58..1A5E ; R # Mn [7] TAI THAM SIGN MAI KANG LAI..TAI THAM CONSONANT SIGN SA +1A60 ; R # Mn TAI THAM SIGN SAKOT +1A61 ; R # Mc TAI THAM VOWEL SIGN A +1A62 ; R # Mn TAI THAM VOWEL SIGN MAI SAT +1A63..1A64 ; R # Mc [2] TAI THAM VOWEL SIGN AA..TAI THAM VOWEL SIGN TALL AA +1A65..1A6C ; R # Mn [8] TAI THAM VOWEL SIGN I..TAI THAM VOWEL SIGN OA BELOW +1A6D..1A72 ; R # Mc [6] TAI THAM VOWEL SIGN OY..TAI THAM VOWEL SIGN THAM AI +1A73..1A7C ; R # Mn [10] TAI THAM VOWEL SIGN OA ABOVE..TAI THAM SIGN KHUEN-LUE KARAN +1A7F ; R # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT +1A80..1A89 ; R # Nd [10] TAI THAM HORA DIGIT ZERO..TAI THAM HORA DIGIT NINE +1A90..1A99 ; R # Nd [10] TAI THAM THAM DIGIT ZERO..TAI THAM THAM DIGIT NINE +1AA0..1AA6 ; R # Po [7] TAI THAM SIGN WIANG..TAI THAM SIGN REVERSED ROTATED RANA +1AA7 ; R # Lm TAI THAM SIGN MAI YAMOK +1AA8..1AAD ; R # Po [6] TAI THAM SIGN KAAN..TAI THAM SIGN CAANG +1AB0..1ABD ; R # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW +1ABE ; R # Me COMBINING PARENTHESES OVERLAY +1B00..1B03 ; R # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG +1B04 ; R # Mc BALINESE SIGN BISAH +1B05..1B33 ; R # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA +1B34 ; R # Mn BALINESE SIGN REREKAN +1B35 ; R # Mc BALINESE VOWEL SIGN TEDUNG +1B36..1B3A ; R # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA +1B3B ; R # Mc BALINESE VOWEL SIGN RA REPA TEDUNG +1B3C ; R # Mn BALINESE VOWEL SIGN LA LENGA +1B3D..1B41 ; R # Mc [5] BALINESE VOWEL SIGN LA LENGA TEDUNG..BALINESE VOWEL SIGN TALING REPA TEDUNG +1B42 ; R # Mn BALINESE VOWEL SIGN PEPET +1B43..1B44 ; R # Mc [2] BALINESE VOWEL SIGN PEPET TEDUNG..BALINESE ADEG ADEG +1B45..1B4B ; R # Lo [7] BALINESE LETTER KAF SASAK..BALINESE LETTER ASYURA SASAK +1B50..1B59 ; R # Nd [10] BALINESE DIGIT ZERO..BALINESE DIGIT NINE +1B5A..1B60 ; R # Po [7] BALINESE PANTI..BALINESE PAMENENG +1B61..1B6A ; R # So [10] BALINESE MUSICAL SYMBOL DONG..BALINESE MUSICAL SYMBOL DANG GEDE +1B6B..1B73 ; R # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG +1B74..1B7C ; R # So [9] BALINESE MUSICAL SYMBOL RIGHT-HAND OPEN DUG..BALINESE MUSICAL SYMBOL LEFT-HAND OPEN PING +1B80..1B81 ; R # Mn [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR +1B82 ; R # Mc SUNDANESE SIGN PANGWISAD +1B83..1BA0 ; R # Lo [30] SUNDANESE LETTER A..SUNDANESE LETTER HA +1BA1 ; R # Mc SUNDANESE CONSONANT SIGN PAMINGKAL +1BA2..1BA5 ; R # Mn [4] SUNDANESE CONSONANT SIGN PANYAKRA..SUNDANESE VOWEL SIGN PANYUKU +1BA6..1BA7 ; R # Mc [2] SUNDANESE VOWEL SIGN PANAELAENG..SUNDANESE VOWEL SIGN PANOLONG +1BA8..1BA9 ; R # Mn [2] SUNDANESE VOWEL SIGN PAMEPET..SUNDANESE VOWEL SIGN PANEULEUNG +1BAA ; R # Mc SUNDANESE SIGN PAMAAEH +1BAB..1BAD ; R # Mn [3] SUNDANESE SIGN VIRAMA..SUNDANESE CONSONANT SIGN PASANGAN WA +1BAE..1BAF ; R # Lo [2] SUNDANESE LETTER KHA..SUNDANESE LETTER SYA +1BB0..1BB9 ; R # Nd [10] SUNDANESE DIGIT ZERO..SUNDANESE DIGIT NINE +1BBA..1BBF ; R # Lo [6] SUNDANESE AVAGRAHA..SUNDANESE LETTER FINAL M +1BC0..1BE5 ; R # Lo [38] BATAK LETTER A..BATAK LETTER U +1BE6 ; R # Mn BATAK SIGN TOMPI +1BE7 ; R # Mc BATAK VOWEL SIGN E +1BE8..1BE9 ; R # Mn [2] BATAK VOWEL SIGN PAKPAK E..BATAK VOWEL SIGN EE +1BEA..1BEC ; R # Mc [3] BATAK VOWEL SIGN I..BATAK VOWEL SIGN O +1BED ; R # Mn BATAK VOWEL SIGN KARO O +1BEE ; R # Mc BATAK VOWEL SIGN U +1BEF..1BF1 ; R # Mn [3] BATAK VOWEL SIGN U FOR SIMALUNGUN SA..BATAK CONSONANT SIGN H +1BF2..1BF3 ; R # Mc [2] BATAK PANGOLAT..BATAK PANONGONAN +1BFC..1BFF ; R # Po [4] BATAK SYMBOL BINDU NA METEK..BATAK SYMBOL BINDU PANGOLAT +1C00..1C23 ; R # Lo [36] LEPCHA LETTER KA..LEPCHA LETTER A +1C24..1C2B ; R # Mc [8] LEPCHA SUBJOINED LETTER YA..LEPCHA VOWEL SIGN UU +1C2C..1C33 ; R # Mn [8] LEPCHA VOWEL SIGN E..LEPCHA CONSONANT SIGN T +1C34..1C35 ; R # Mc [2] LEPCHA CONSONANT SIGN NYIN-DO..LEPCHA CONSONANT SIGN KANG +1C36..1C37 ; R # Mn [2] LEPCHA SIGN RAN..LEPCHA SIGN NUKTA +1C3B..1C3F ; R # Po [5] LEPCHA PUNCTUATION TA-ROL..LEPCHA PUNCTUATION TSHOOK +1C40..1C49 ; R # Nd [10] LEPCHA DIGIT ZERO..LEPCHA DIGIT NINE +1C4D..1C4F ; R # Lo [3] LEPCHA LETTER TTA..LEPCHA LETTER DDA +1C50..1C59 ; R # Nd [10] OL CHIKI DIGIT ZERO..OL CHIKI DIGIT NINE +1C5A..1C77 ; R # Lo [30] OL CHIKI LETTER LA..OL CHIKI LETTER OH +1C78..1C7D ; R # Lm [6] OL CHIKI MU TTUDDAG..OL CHIKI AHAD +1C7E..1C7F ; R # Po [2] OL CHIKI PUNCTUATION MUCAAD..OL CHIKI PUNCTUATION DOUBLE MUCAAD +1C80..1C88 ; R # Ll [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK +1CC0..1CC7 ; R # Po [8] SUNDANESE PUNCTUATION BINDU SURYA..SUNDANESE PUNCTUATION BINDU BA SATANGA +1CD0..1CD2 ; R # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA +1CD3 ; R # Po VEDIC SIGN NIHSHVASA +1CD4..1CE0 ; R # Mn [13] VEDIC SIGN YAJURVEDIC MIDLINE SVARITA..VEDIC TONE RIGVEDIC KASHMIRI INDEPENDENT SVARITA +1CE1 ; R # Mc VEDIC TONE ATHARVAVEDIC INDEPENDENT SVARITA +1CE2..1CE8 ; R # Mn [7] VEDIC SIGN VISARGA SVARITA..VEDIC SIGN VISARGA ANUDATTA WITH TAIL +1CE9..1CEC ; R # Lo [4] VEDIC SIGN ANUSVARA ANTARGOMUKHA..VEDIC SIGN ANUSVARA VAMAGOMUKHA WITH TAIL +1CED ; R # Mn VEDIC SIGN TIRYAK +1CEE..1CF1 ; R # Lo [4] VEDIC SIGN HEXIFORM LONG ANUSVARA..VEDIC SIGN ANUSVARA UBHAYATO MUKHA +1CF2..1CF3 ; R # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA +1CF4 ; R # Mn VEDIC TONE CANDRA ABOVE +1CF5..1CF6 ; R # Lo [2] VEDIC SIGN JIHVAMULIYA..VEDIC SIGN UPADHMANIYA +1CF7 ; R # Mc VEDIC SIGN ATIKRAMA +1CF8..1CF9 ; R # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE +1D00..1D2B ; R # Ll [44] LATIN LETTER SMALL CAPITAL A..CYRILLIC LETTER SMALL CAPITAL EL +1D2C..1D6A ; R # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI +1D6B..1D77 ; R # Ll [13] LATIN SMALL LETTER UE..LATIN SMALL LETTER TURNED G +1D78 ; R # Lm MODIFIER LETTER CYRILLIC EN +1D79..1D7F ; R # Ll [7] LATIN SMALL LETTER INSULAR G..LATIN SMALL LETTER UPSILON WITH STROKE +1D80..1D9A ; R # Ll [27] LATIN SMALL LETTER B WITH PALATAL HOOK..LATIN SMALL LETTER EZH WITH RETROFLEX HOOK +1D9B..1DBF ; R # Lm [37] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL THETA +1DC0..1DF9 ; R # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW +1DFB..1DFF ; R # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +1E00..1EFF ; R # L& [256] LATIN CAPITAL LETTER A WITH RING BELOW..LATIN SMALL LETTER Y WITH LOOP +1F00..1F15 ; R # L& [22] GREEK SMALL LETTER ALPHA WITH PSILI..GREEK SMALL LETTER EPSILON WITH DASIA AND OXIA +1F18..1F1D ; R # Lu [6] GREEK CAPITAL LETTER EPSILON WITH PSILI..GREEK CAPITAL LETTER EPSILON WITH DASIA AND OXIA +1F20..1F45 ; R # L& [38] GREEK SMALL LETTER ETA WITH PSILI..GREEK SMALL LETTER OMICRON WITH DASIA AND OXIA +1F48..1F4D ; R # Lu [6] GREEK CAPITAL LETTER OMICRON WITH PSILI..GREEK CAPITAL LETTER OMICRON WITH DASIA AND OXIA +1F50..1F57 ; R # Ll [8] GREEK SMALL LETTER UPSILON WITH PSILI..GREEK SMALL LETTER UPSILON WITH DASIA AND PERISPOMENI +1F59 ; R # Lu GREEK CAPITAL LETTER UPSILON WITH DASIA +1F5B ; R # Lu GREEK CAPITAL LETTER UPSILON WITH DASIA AND VARIA +1F5D ; R # Lu GREEK CAPITAL LETTER UPSILON WITH DASIA AND OXIA +1F5F..1F7D ; R # L& [31] GREEK CAPITAL LETTER UPSILON WITH DASIA AND PERISPOMENI..GREEK SMALL LETTER OMEGA WITH OXIA +1F80..1FB4 ; R # L& [53] GREEK SMALL LETTER ALPHA WITH PSILI AND YPOGEGRAMMENI..GREEK SMALL LETTER ALPHA WITH OXIA AND YPOGEGRAMMENI +1FB6..1FBC ; R # L& [7] GREEK SMALL LETTER ALPHA WITH PERISPOMENI..GREEK CAPITAL LETTER ALPHA WITH PROSGEGRAMMENI +1FBD ; R # Sk GREEK KORONIS +1FBE ; R # Ll GREEK PROSGEGRAMMENI +1FBF..1FC1 ; R # Sk [3] GREEK PSILI..GREEK DIALYTIKA AND PERISPOMENI +1FC2..1FC4 ; R # Ll [3] GREEK SMALL LETTER ETA WITH VARIA AND YPOGEGRAMMENI..GREEK SMALL LETTER ETA WITH OXIA AND YPOGEGRAMMENI +1FC6..1FCC ; R # L& [7] GREEK SMALL LETTER ETA WITH PERISPOMENI..GREEK CAPITAL LETTER ETA WITH PROSGEGRAMMENI +1FCD..1FCF ; R # Sk [3] GREEK PSILI AND VARIA..GREEK PSILI AND PERISPOMENI +1FD0..1FD3 ; R # Ll [4] GREEK SMALL LETTER IOTA WITH VRACHY..GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA +1FD6..1FDB ; R # L& [6] GREEK SMALL LETTER IOTA WITH PERISPOMENI..GREEK CAPITAL LETTER IOTA WITH OXIA +1FDD..1FDF ; R # Sk [3] GREEK DASIA AND VARIA..GREEK DASIA AND PERISPOMENI +1FE0..1FEC ; R # L& [13] GREEK SMALL LETTER UPSILON WITH VRACHY..GREEK CAPITAL LETTER RHO WITH DASIA +1FED..1FEF ; R # Sk [3] GREEK DIALYTIKA AND VARIA..GREEK VARIA +1FF2..1FF4 ; R # Ll [3] GREEK SMALL LETTER OMEGA WITH VARIA AND YPOGEGRAMMENI..GREEK SMALL LETTER OMEGA WITH OXIA AND YPOGEGRAMMENI +1FF6..1FFC ; R # L& [7] GREEK SMALL LETTER OMEGA WITH PERISPOMENI..GREEK CAPITAL LETTER OMEGA WITH PROSGEGRAMMENI +1FFD..1FFE ; R # Sk [2] GREEK OXIA..GREEK DASIA +2000..200A ; R # Zs [11] EN QUAD..HAIR SPACE +200B..200F ; R # Cf [5] ZERO WIDTH SPACE..RIGHT-TO-LEFT MARK +2010..2015 ; R # Pd [6] HYPHEN..HORIZONTAL BAR +2016 ; U # Po DOUBLE VERTICAL LINE +2017 ; R # Po DOUBLE LOW LINE +2018 ; R # Pi LEFT SINGLE QUOTATION MARK +2019 ; R # Pf RIGHT SINGLE QUOTATION MARK +201A ; R # Ps SINGLE LOW-9 QUOTATION MARK +201B..201C ; R # Pi [2] SINGLE HIGH-REVERSED-9 QUOTATION MARK..LEFT DOUBLE QUOTATION MARK +201D ; R # Pf RIGHT DOUBLE QUOTATION MARK +201E ; R # Ps DOUBLE LOW-9 QUOTATION MARK +201F ; R # Pi DOUBLE HIGH-REVERSED-9 QUOTATION MARK +2020..2021 ; U # Po [2] DAGGER..DOUBLE DAGGER +2022..2027 ; R # Po [6] BULLET..HYPHENATION POINT +2028 ; R # Zl LINE SEPARATOR +2029 ; R # Zp PARAGRAPH SEPARATOR +202A..202E ; R # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE +202F ; R # Zs NARROW NO-BREAK SPACE +2030..2031 ; U # Po [2] PER MILLE SIGN..PER TEN THOUSAND SIGN +2032..2038 ; R # Po [7] PRIME..CARET +2039 ; R # Pi SINGLE LEFT-POINTING ANGLE QUOTATION MARK +203A ; R # Pf SINGLE RIGHT-POINTING ANGLE QUOTATION MARK +203B..203C ; U # Po [2] REFERENCE MARK..DOUBLE EXCLAMATION MARK +203D..203E ; R # Po [2] INTERROBANG..OVERLINE +203F..2040 ; R # Pc [2] UNDERTIE..CHARACTER TIE +2041 ; R # Po CARET INSERTION POINT +2042 ; U # Po ASTERISM +2043 ; R # Po HYPHEN BULLET +2044 ; R # Sm FRACTION SLASH +2045 ; R # Ps LEFT SQUARE BRACKET WITH QUILL +2046 ; R # Pe RIGHT SQUARE BRACKET WITH QUILL +2047..2049 ; U # Po [3] DOUBLE QUESTION MARK..EXCLAMATION QUESTION MARK +204A..2050 ; R # Po [7] TIRONIAN SIGN ET..CLOSE UP +2051 ; U # Po TWO ASTERISKS ALIGNED VERTICALLY +2052 ; R # Sm COMMERCIAL MINUS SIGN +2053 ; R # Po SWUNG DASH +2054 ; R # Pc INVERTED UNDERTIE +2055..205E ; R # Po [10] FLOWER PUNCTUATION MARK..VERTICAL FOUR DOTS +205F ; R # Zs MEDIUM MATHEMATICAL SPACE +2060..2064 ; R # Cf [5] WORD JOINER..INVISIBLE PLUS +2065 ; U # Cn <reserved-2065> +2066..206F ; R # Cf [10] LEFT-TO-RIGHT ISOLATE..NOMINAL DIGIT SHAPES +2070 ; R # No SUPERSCRIPT ZERO +2071 ; R # Lm SUPERSCRIPT LATIN SMALL LETTER I +2074..2079 ; R # No [6] SUPERSCRIPT FOUR..SUPERSCRIPT NINE +207A..207C ; R # Sm [3] SUPERSCRIPT PLUS SIGN..SUPERSCRIPT EQUALS SIGN +207D ; R # Ps SUPERSCRIPT LEFT PARENTHESIS +207E ; R # Pe SUPERSCRIPT RIGHT PARENTHESIS +207F ; R # Lm SUPERSCRIPT LATIN SMALL LETTER N +2080..2089 ; R # No [10] SUBSCRIPT ZERO..SUBSCRIPT NINE +208A..208C ; R # Sm [3] SUBSCRIPT PLUS SIGN..SUBSCRIPT EQUALS SIGN +208D ; R # Ps SUBSCRIPT LEFT PARENTHESIS +208E ; R # Pe SUBSCRIPT RIGHT PARENTHESIS +2090..209C ; R # Lm [13] LATIN SUBSCRIPT SMALL LETTER A..LATIN SUBSCRIPT SMALL LETTER T +20A0..20BF ; R # Sc [32] EURO-CURRENCY SIGN..BITCOIN SIGN +20D0..20DC ; R # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE +20DD..20E0 ; U # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH +20E1 ; R # Mn COMBINING LEFT RIGHT ARROW ABOVE +20E2..20E4 ; U # Me [3] COMBINING ENCLOSING SCREEN..COMBINING ENCLOSING UPWARD POINTING TRIANGLE +20E5..20F0 ; R # Mn [12] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING ASTERISK ABOVE +2100..2101 ; U # So [2] ACCOUNT OF..ADDRESSED TO THE SUBJECT +2102 ; R # Lu DOUBLE-STRUCK CAPITAL C +2103..2106 ; U # So [4] DEGREE CELSIUS..CADA UNA +2107 ; U # Lu EULER CONSTANT +2108..2109 ; U # So [2] SCRUPLE..DEGREE FAHRENHEIT +210A..210E ; R # L& [5] SCRIPT SMALL G..PLANCK CONSTANT +210F ; U # Ll PLANCK CONSTANT OVER TWO PI +2110..2112 ; R # Lu [3] SCRIPT CAPITAL I..SCRIPT CAPITAL L +2113 ; U # Ll SCRIPT SMALL L +2114 ; U # So L B BAR SYMBOL +2115 ; R # Lu DOUBLE-STRUCK CAPITAL N +2116..2117 ; U # So [2] NUMERO SIGN..SOUND RECORDING COPYRIGHT +2118 ; R # Sm SCRIPT CAPITAL P +2119..211D ; R # Lu [5] DOUBLE-STRUCK CAPITAL P..DOUBLE-STRUCK CAPITAL R +211E..2123 ; U # So [6] PRESCRIPTION TAKE..VERSICLE +2124 ; R # Lu DOUBLE-STRUCK CAPITAL Z +2125 ; U # So OUNCE SIGN +2126 ; R # Lu OHM SIGN +2127 ; U # So INVERTED OHM SIGN +2128 ; R # Lu BLACK-LETTER CAPITAL Z +2129 ; U # So TURNED GREEK SMALL LETTER IOTA +212A..212D ; R # Lu [4] KELVIN SIGN..BLACK-LETTER CAPITAL C +212E ; U # So ESTIMATED SYMBOL +212F..2134 ; R # L& [6] SCRIPT SMALL E..SCRIPT SMALL O +2135..2138 ; U # Lo [4] ALEF SYMBOL..DALET SYMBOL +2139 ; U # Ll INFORMATION SOURCE +213A..213B ; U # So [2] ROTATED CAPITAL Q..FACSIMILE SIGN +213C..213F ; U # L& [4] DOUBLE-STRUCK SMALL PI..DOUBLE-STRUCK CAPITAL PI +2140..2144 ; R # Sm [5] DOUBLE-STRUCK N-ARY SUMMATION..TURNED SANS-SERIF CAPITAL Y +2145..2149 ; U # L& [5] DOUBLE-STRUCK ITALIC CAPITAL D..DOUBLE-STRUCK ITALIC SMALL J +214A ; U # So PROPERTY LINE +214B ; R # Sm TURNED AMPERSAND +214C..214D ; U # So [2] PER SIGN..AKTIESELSKAB +214E ; R # Ll TURNED SMALL F +214F ; U # So SYMBOL FOR SAMARITAN SOURCE +2150..215F ; U # No [16] VULGAR FRACTION ONE SEVENTH..FRACTION NUMERATOR ONE +2160..2182 ; U # Nl [35] ROMAN NUMERAL ONE..ROMAN NUMERAL TEN THOUSAND +2183..2184 ; U # L& [2] ROMAN NUMERAL REVERSED ONE HUNDRED..LATIN SMALL LETTER REVERSED C +2185..2188 ; U # Nl [4] ROMAN NUMERAL SIX LATE FORM..ROMAN NUMERAL ONE HUNDRED THOUSAND +2189 ; U # No VULGAR FRACTION ZERO THIRDS +218A..218B ; R # So [2] TURNED DIGIT TWO..TURNED DIGIT THREE +218C..218F ; U # Cn [4] <reserved-218C>..<reserved-218F> +2190..2194 ; R # Sm [5] LEFTWARDS ARROW..LEFT RIGHT ARROW +2195..2199 ; R # So [5] UP DOWN ARROW..SOUTH WEST ARROW +219A..219B ; R # Sm [2] LEFTWARDS ARROW WITH STROKE..RIGHTWARDS ARROW WITH STROKE +219C..219F ; R # So [4] LEFTWARDS WAVE ARROW..UPWARDS TWO HEADED ARROW +21A0 ; R # Sm RIGHTWARDS TWO HEADED ARROW +21A1..21A2 ; R # So [2] DOWNWARDS TWO HEADED ARROW..LEFTWARDS ARROW WITH TAIL +21A3 ; R # Sm RIGHTWARDS ARROW WITH TAIL +21A4..21A5 ; R # So [2] LEFTWARDS ARROW FROM BAR..UPWARDS ARROW FROM BAR +21A6 ; R # Sm RIGHTWARDS ARROW FROM BAR +21A7..21AD ; R # So [7] DOWNWARDS ARROW FROM BAR..LEFT RIGHT WAVE ARROW +21AE ; R # Sm LEFT RIGHT ARROW WITH STROKE +21AF..21CD ; R # So [31] DOWNWARDS ZIGZAG ARROW..LEFTWARDS DOUBLE ARROW WITH STROKE +21CE..21CF ; R # Sm [2] LEFT RIGHT DOUBLE ARROW WITH STROKE..RIGHTWARDS DOUBLE ARROW WITH STROKE +21D0..21D1 ; R # So [2] LEFTWARDS DOUBLE ARROW..UPWARDS DOUBLE ARROW +21D2 ; R # Sm RIGHTWARDS DOUBLE ARROW +21D3 ; R # So DOWNWARDS DOUBLE ARROW +21D4 ; R # Sm LEFT RIGHT DOUBLE ARROW +21D5..21F3 ; R # So [31] UP DOWN DOUBLE ARROW..UP DOWN WHITE ARROW +21F4..21FF ; R # Sm [12] RIGHT ARROW WITH SMALL CIRCLE..LEFT RIGHT OPEN-HEADED ARROW +2200..221D ; R # Sm [30] FOR ALL..PROPORTIONAL TO +221E ; U # Sm INFINITY +221F..2233 ; R # Sm [21] RIGHT ANGLE..ANTICLOCKWISE CONTOUR INTEGRAL +2234..2235 ; U # Sm [2] THEREFORE..BECAUSE +2236..22FF ; R # Sm [202] RATIO..Z NOTATION BAG MEMBERSHIP +2300..2307 ; U # So [8] DIAMETER SIGN..WAVY LINE +2308 ; R # Ps LEFT CEILING +2309 ; R # Pe RIGHT CEILING +230A ; R # Ps LEFT FLOOR +230B ; R # Pe RIGHT FLOOR +230C..231F ; U # So [20] BOTTOM RIGHT CROP..BOTTOM RIGHT CORNER +2320..2321 ; R # Sm [2] TOP HALF INTEGRAL..BOTTOM HALF INTEGRAL +2322..2323 ; R # So [2] FROWN..SMILE +2324..2328 ; U # So [5] UP ARROWHEAD BETWEEN TWO HORIZONTAL BARS..KEYBOARD +2329 ; Tr # Ps LEFT-POINTING ANGLE BRACKET +232A ; Tr # Pe RIGHT-POINTING ANGLE BRACKET +232B ; U # So ERASE TO THE LEFT +232C..237B ; R # So [80] BENZENE RING..NOT CHECK MARK +237C ; R # Sm RIGHT ANGLE WITH DOWNWARDS ZIGZAG ARROW +237D..239A ; U # So [30] SHOULDERED OPEN BOX..CLEAR SCREEN SYMBOL +239B..23B3 ; R # Sm [25] LEFT PARENTHESIS UPPER HOOK..SUMMATION BOTTOM +23B4..23BD ; R # So [10] TOP SQUARE BRACKET..HORIZONTAL SCAN LINE-9 +23BE..23CD ; U # So [16] DENTISTRY SYMBOL LIGHT VERTICAL AND TOP RIGHT..SQUARE FOOT +23CE ; R # So RETURN SYMBOL +23CF ; U # So EJECT SYMBOL +23D0 ; R # So VERTICAL LINE EXTENSION +23D1..23DB ; U # So [11] METRICAL BREVE..FUSE +23DC..23E1 ; R # Sm [6] TOP PARENTHESIS..BOTTOM TORTOISE SHELL BRACKET +23E2..23FF ; U # So [30] WHITE TRAPEZIUM..OBSERVER EYE SYMBOL +2400..2422 ; U # So [35] SYMBOL FOR NULL..BLANK SYMBOL +2423 ; R # So OPEN BOX +2424..2426 ; U # So [3] SYMBOL FOR NEWLINE..SYMBOL FOR SUBSTITUTE FORM TWO +2427..243F ; U # Cn [25] <reserved-2427>..<reserved-243F> +2440..244A ; U # So [11] OCR HOOK..OCR DOUBLE BACKSLASH +244B..245F ; U # Cn [21] <reserved-244B>..<reserved-245F> +2460..249B ; U # No [60] CIRCLED DIGIT ONE..NUMBER TWENTY FULL STOP +249C..24E9 ; U # So [78] PARENTHESIZED LATIN SMALL LETTER A..CIRCLED LATIN SMALL LETTER Z +24EA..24FF ; U # No [22] CIRCLED DIGIT ZERO..NEGATIVE CIRCLED DIGIT ZERO +2500..257F ; R # So [128] BOX DRAWINGS LIGHT HORIZONTAL..BOX DRAWINGS HEAVY UP AND LIGHT DOWN +2580..259F ; R # So [32] UPPER HALF BLOCK..QUADRANT UPPER RIGHT AND LOWER LEFT AND LOWER RIGHT +25A0..25B6 ; U # So [23] BLACK SQUARE..BLACK RIGHT-POINTING TRIANGLE +25B7 ; U # Sm WHITE RIGHT-POINTING TRIANGLE +25B8..25C0 ; U # So [9] BLACK RIGHT-POINTING SMALL TRIANGLE..BLACK LEFT-POINTING TRIANGLE +25C1 ; U # Sm WHITE LEFT-POINTING TRIANGLE +25C2..25F7 ; U # So [54] BLACK LEFT-POINTING SMALL TRIANGLE..WHITE CIRCLE WITH UPPER RIGHT QUADRANT +25F8..25FF ; U # Sm [8] UPPER LEFT TRIANGLE..LOWER RIGHT TRIANGLE +2600..2619 ; U # So [26] BLACK SUN WITH RAYS..REVERSED ROTATED FLORAL HEART BULLET +261A..261F ; R # So [6] BLACK LEFT POINTING INDEX..WHITE DOWN POINTING INDEX +2620..266E ; U # So [79] SKULL AND CROSSBONES..MUSIC NATURAL SIGN +266F ; U # Sm MUSIC SHARP SIGN +2670..26FF ; U # So [144] WEST SYRIAC CROSS..WHITE FLAG WITH HORIZONTAL MIDDLE BLACK STRIPE +2700..2767 ; U # So [104] BLACK SAFETY SCISSORS..ROTATED FLORAL HEART BULLET +2768 ; R # Ps MEDIUM LEFT PARENTHESIS ORNAMENT +2769 ; R # Pe MEDIUM RIGHT PARENTHESIS ORNAMENT +276A ; R # Ps MEDIUM FLATTENED LEFT PARENTHESIS ORNAMENT +276B ; R # Pe MEDIUM FLATTENED RIGHT PARENTHESIS ORNAMENT +276C ; R # Ps MEDIUM LEFT-POINTING ANGLE BRACKET ORNAMENT +276D ; R # Pe MEDIUM RIGHT-POINTING ANGLE BRACKET ORNAMENT +276E ; R # Ps HEAVY LEFT-POINTING ANGLE QUOTATION MARK ORNAMENT +276F ; R # Pe HEAVY RIGHT-POINTING ANGLE QUOTATION MARK ORNAMENT +2770 ; R # Ps HEAVY LEFT-POINTING ANGLE BRACKET ORNAMENT +2771 ; R # Pe HEAVY RIGHT-POINTING ANGLE BRACKET ORNAMENT +2772 ; R # Ps LIGHT LEFT TORTOISE SHELL BRACKET ORNAMENT +2773 ; R # Pe LIGHT RIGHT TORTOISE SHELL BRACKET ORNAMENT +2774 ; R # Ps MEDIUM LEFT CURLY BRACKET ORNAMENT +2775 ; R # Pe MEDIUM RIGHT CURLY BRACKET ORNAMENT +2776..2793 ; U # No [30] DINGBAT NEGATIVE CIRCLED DIGIT ONE..DINGBAT NEGATIVE CIRCLED SANS-SERIF NUMBER TEN +2794..27BF ; R # So [44] HEAVY WIDE-HEADED RIGHTWARDS ARROW..DOUBLE CURLY LOOP +27C0..27C4 ; R # Sm [5] THREE DIMENSIONAL ANGLE..OPEN SUPERSET +27C5 ; R # Ps LEFT S-SHAPED BAG DELIMITER +27C6 ; R # Pe RIGHT S-SHAPED BAG DELIMITER +27C7..27E5 ; R # Sm [31] OR WITH DOT INSIDE..WHITE SQUARE WITH RIGHTWARDS TICK +27E6 ; R # Ps MATHEMATICAL LEFT WHITE SQUARE BRACKET +27E7 ; R # Pe MATHEMATICAL RIGHT WHITE SQUARE BRACKET +27E8 ; R # Ps MATHEMATICAL LEFT ANGLE BRACKET +27E9 ; R # Pe MATHEMATICAL RIGHT ANGLE BRACKET +27EA ; R # Ps MATHEMATICAL LEFT DOUBLE ANGLE BRACKET +27EB ; R # Pe MATHEMATICAL RIGHT DOUBLE ANGLE BRACKET +27EC ; R # Ps MATHEMATICAL LEFT WHITE TORTOISE SHELL BRACKET +27ED ; R # Pe MATHEMATICAL RIGHT WHITE TORTOISE SHELL BRACKET +27EE ; R # Ps MATHEMATICAL LEFT FLATTENED PARENTHESIS +27EF ; R # Pe MATHEMATICAL RIGHT FLATTENED PARENTHESIS +27F0..27FF ; R # Sm [16] UPWARDS QUADRUPLE ARROW..LONG RIGHTWARDS SQUIGGLE ARROW +2800..28FF ; R # So [256] BRAILLE PATTERN BLANK..BRAILLE PATTERN DOTS-12345678 +2900..297F ; R # Sm [128] RIGHTWARDS TWO-HEADED ARROW WITH VERTICAL STROKE..DOWN FISH TAIL +2980..2982 ; R # Sm [3] TRIPLE VERTICAL BAR DELIMITER..Z NOTATION TYPE COLON +2983 ; R # Ps LEFT WHITE CURLY BRACKET +2984 ; R # Pe RIGHT WHITE CURLY BRACKET +2985 ; R # Ps LEFT WHITE PARENTHESIS +2986 ; R # Pe RIGHT WHITE PARENTHESIS +2987 ; R # Ps Z NOTATION LEFT IMAGE BRACKET +2988 ; R # Pe Z NOTATION RIGHT IMAGE BRACKET +2989 ; R # Ps Z NOTATION LEFT BINDING BRACKET +298A ; R # Pe Z NOTATION RIGHT BINDING BRACKET +298B ; R # Ps LEFT SQUARE BRACKET WITH UNDERBAR +298C ; R # Pe RIGHT SQUARE BRACKET WITH UNDERBAR +298D ; R # Ps LEFT SQUARE BRACKET WITH TICK IN TOP CORNER +298E ; R # Pe RIGHT SQUARE BRACKET WITH TICK IN BOTTOM CORNER +298F ; R # Ps LEFT SQUARE BRACKET WITH TICK IN BOTTOM CORNER +2990 ; R # Pe RIGHT SQUARE BRACKET WITH TICK IN TOP CORNER +2991 ; R # Ps LEFT ANGLE BRACKET WITH DOT +2992 ; R # Pe RIGHT ANGLE BRACKET WITH DOT +2993 ; R # Ps LEFT ARC LESS-THAN BRACKET +2994 ; R # Pe RIGHT ARC GREATER-THAN BRACKET +2995 ; R # Ps DOUBLE LEFT ARC GREATER-THAN BRACKET +2996 ; R # Pe DOUBLE RIGHT ARC LESS-THAN BRACKET +2997 ; R # Ps LEFT BLACK TORTOISE SHELL BRACKET +2998 ; R # Pe RIGHT BLACK TORTOISE SHELL BRACKET +2999..29D7 ; R # Sm [63] DOTTED FENCE..BLACK HOURGLASS +29D8 ; R # Ps LEFT WIGGLY FENCE +29D9 ; R # Pe RIGHT WIGGLY FENCE +29DA ; R # Ps LEFT DOUBLE WIGGLY FENCE +29DB ; R # Pe RIGHT DOUBLE WIGGLY FENCE +29DC..29FB ; R # Sm [32] INCOMPLETE INFINITY..TRIPLE PLUS +29FC ; R # Ps LEFT-POINTING CURVED ANGLE BRACKET +29FD ; R # Pe RIGHT-POINTING CURVED ANGLE BRACKET +29FE..29FF ; R # Sm [2] TINY..MINY +2A00..2AFF ; R # Sm [256] N-ARY CIRCLED DOT OPERATOR..N-ARY WHITE VERTICAL BAR +2B00..2B11 ; R # So [18] NORTH EAST WHITE ARROW..LEFTWARDS ARROW WITH TIP UPWARDS +2B12..2B2F ; U # So [30] SQUARE WITH TOP HALF BLACK..WHITE VERTICAL ELLIPSE +2B30..2B44 ; R # Sm [21] LEFT ARROW WITH SMALL CIRCLE..RIGHTWARDS ARROW THROUGH SUPERSET +2B45..2B46 ; R # So [2] LEFTWARDS QUADRUPLE ARROW..RIGHTWARDS QUADRUPLE ARROW +2B47..2B4C ; R # Sm [6] REVERSE TILDE OPERATOR ABOVE RIGHTWARDS ARROW..RIGHTWARDS ARROW ABOVE REVERSE TILDE OPERATOR +2B4D..2B4F ; R # So [3] DOWNWARDS TRIANGLE-HEADED ZIGZAG ARROW..SHORT BACKSLANTED SOUTH ARROW +2B50..2B59 ; U # So [10] WHITE MEDIUM STAR..HEAVY CIRCLED SALTIRE +2B5A..2B73 ; R # So [26] SLANTED NORTH ARROW WITH HOOKED HEAD..DOWNWARDS TRIANGLE-HEADED ARROW TO BAR +2B76..2B95 ; R # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW +2B98..2BB7 ; R # So [32] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..RIBBON ARROW RIGHT DOWN +2BB8..2BB9 ; U # So [2] UPWARDS WHITE ARROW FROM BAR WITH HORIZONTAL BAR..UP ARROWHEAD IN A RECTANGLE BOX +2BBA..2BBC ; U # Cn [3] <reserved-2BBA>..<reserved-2BBC> +2BBD..2BC8 ; U # So [12] BALLOT BOX WITH LIGHT X..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED +2BC9 ; U # Cn <reserved-2BC9> +2BCA..2BD1 ; U # So [8] TOP HALF BLACK CIRCLE..UNCERTAINTY SIGN +2BD2 ; R # So GROUP MARK +2BD3..2BEB ; U # Cn [25] <reserved-2BD3>..<reserved-2BEB> +2BEC..2BEF ; R # So [4] LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS..DOWNWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS +2BF0..2BFF ; U # Cn [16] <reserved-2BF0>..<reserved-2BFF> +2C00..2C2E ; R # Lu [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE +2C30..2C5E ; R # Ll [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE +2C60..2C7B ; R # L& [28] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN LETTER SMALL CAPITAL TURNED E +2C7C..2C7D ; R # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V +2C7E..2C7F ; R # Lu [2] LATIN CAPITAL LETTER S WITH SWASH TAIL..LATIN CAPITAL LETTER Z WITH SWASH TAIL +2C80..2CE4 ; R # L& [101] COPTIC CAPITAL LETTER ALFA..COPTIC SYMBOL KAI +2CE5..2CEA ; R # So [6] COPTIC SYMBOL MI RO..COPTIC SYMBOL SHIMA SIMA +2CEB..2CEE ; R # L& [4] COPTIC CAPITAL LETTER CRYPTOGRAMMIC SHEI..COPTIC SMALL LETTER CRYPTOGRAMMIC GANGIA +2CEF..2CF1 ; R # Mn [3] COPTIC COMBINING NI ABOVE..COPTIC COMBINING SPIRITUS LENIS +2CF2..2CF3 ; R # L& [2] COPTIC CAPITAL LETTER BOHAIRIC KHEI..COPTIC SMALL LETTER BOHAIRIC KHEI +2CF9..2CFC ; R # Po [4] COPTIC OLD NUBIAN FULL STOP..COPTIC OLD NUBIAN VERSE DIVIDER +2CFD ; R # No COPTIC FRACTION ONE HALF +2CFE..2CFF ; R # Po [2] COPTIC FULL STOP..COPTIC MORPHOLOGICAL DIVIDER +2D00..2D25 ; R # Ll [38] GEORGIAN SMALL LETTER AN..GEORGIAN SMALL LETTER HOE +2D27 ; R # Ll GEORGIAN SMALL LETTER YN +2D2D ; R # Ll GEORGIAN SMALL LETTER AEN +2D30..2D67 ; R # Lo [56] TIFINAGH LETTER YA..TIFINAGH LETTER YO +2D6F ; R # Lm TIFINAGH MODIFIER LETTER LABIALIZATION MARK +2D70 ; R # Po TIFINAGH SEPARATOR MARK +2D7F ; R # Mn TIFINAGH CONSONANT JOINER +2D80..2D96 ; R # Lo [23] ETHIOPIC SYLLABLE LOA..ETHIOPIC SYLLABLE GGWE +2DA0..2DA6 ; R # Lo [7] ETHIOPIC SYLLABLE SSA..ETHIOPIC SYLLABLE SSO +2DA8..2DAE ; R # Lo [7] ETHIOPIC SYLLABLE CCA..ETHIOPIC SYLLABLE CCO +2DB0..2DB6 ; R # Lo [7] ETHIOPIC SYLLABLE ZZA..ETHIOPIC SYLLABLE ZZO +2DB8..2DBE ; R # Lo [7] ETHIOPIC SYLLABLE CCHA..ETHIOPIC SYLLABLE CCHO +2DC0..2DC6 ; R # Lo [7] ETHIOPIC SYLLABLE QYA..ETHIOPIC SYLLABLE QYO +2DC8..2DCE ; R # Lo [7] ETHIOPIC SYLLABLE KYA..ETHIOPIC SYLLABLE KYO +2DD0..2DD6 ; R # Lo [7] ETHIOPIC SYLLABLE XYA..ETHIOPIC SYLLABLE XYO +2DD8..2DDE ; R # Lo [7] ETHIOPIC SYLLABLE GYA..ETHIOPIC SYLLABLE GYO +2DE0..2DFF ; R # Mn [32] COMBINING CYRILLIC LETTER BE..COMBINING CYRILLIC LETTER IOTIFIED BIG YUS +2E00..2E01 ; R # Po [2] RIGHT ANGLE SUBSTITUTION MARKER..RIGHT ANGLE DOTTED SUBSTITUTION MARKER +2E02 ; R # Pi LEFT SUBSTITUTION BRACKET +2E03 ; R # Pf RIGHT SUBSTITUTION BRACKET +2E04 ; R # Pi LEFT DOTTED SUBSTITUTION BRACKET +2E05 ; R # Pf RIGHT DOTTED SUBSTITUTION BRACKET +2E06..2E08 ; R # Po [3] RAISED INTERPOLATION MARKER..DOTTED TRANSPOSITION MARKER +2E09 ; R # Pi LEFT TRANSPOSITION BRACKET +2E0A ; R # Pf RIGHT TRANSPOSITION BRACKET +2E0B ; R # Po RAISED SQUARE +2E0C ; R # Pi LEFT RAISED OMISSION BRACKET +2E0D ; R # Pf RIGHT RAISED OMISSION BRACKET +2E0E..2E16 ; R # Po [9] EDITORIAL CORONIS..DOTTED RIGHT-POINTING ANGLE +2E17 ; R # Pd DOUBLE OBLIQUE HYPHEN +2E18..2E19 ; R # Po [2] INVERTED INTERROBANG..PALM BRANCH +2E1A ; R # Pd HYPHEN WITH DIAERESIS +2E1B ; R # Po TILDE WITH RING ABOVE +2E1C ; R # Pi LEFT LOW PARAPHRASE BRACKET +2E1D ; R # Pf RIGHT LOW PARAPHRASE BRACKET +2E1E..2E1F ; R # Po [2] TILDE WITH DOT ABOVE..TILDE WITH DOT BELOW +2E20 ; R # Pi LEFT VERTICAL BAR WITH QUILL +2E21 ; R # Pf RIGHT VERTICAL BAR WITH QUILL +2E22 ; R # Ps TOP LEFT HALF BRACKET +2E23 ; R # Pe TOP RIGHT HALF BRACKET +2E24 ; R # Ps BOTTOM LEFT HALF BRACKET +2E25 ; R # Pe BOTTOM RIGHT HALF BRACKET +2E26 ; R # Ps LEFT SIDEWAYS U BRACKET +2E27 ; R # Pe RIGHT SIDEWAYS U BRACKET +2E28 ; R # Ps LEFT DOUBLE PARENTHESIS +2E29 ; R # Pe RIGHT DOUBLE PARENTHESIS +2E2A..2E2E ; R # Po [5] TWO DOTS OVER ONE DOT PUNCTUATION..REVERSED QUESTION MARK +2E2F ; R # Lm VERTICAL TILDE +2E30..2E39 ; R # Po [10] RING POINT..TOP HALF SECTION SIGN +2E3A..2E3B ; R # Pd [2] TWO-EM DASH..THREE-EM DASH +2E3C..2E3F ; R # Po [4] STENOGRAPHIC FULL STOP..CAPITULUM +2E40 ; R # Pd DOUBLE HYPHEN +2E41 ; R # Po REVERSED COMMA +2E42 ; R # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK +2E43..2E49 ; R # Po [7] DASH WITH LEFT UPTURN..DOUBLE STACKED COMMA +2E80..2E99 ; U # So [26] CJK RADICAL REPEAT..CJK RADICAL RAP +2E9A ; U # Cn <reserved-2E9A> +2E9B..2EF3 ; U # So [89] CJK RADICAL CHOKE..CJK RADICAL C-SIMPLIFIED TURTLE +2EF4..2EFF ; U # Cn [12] <reserved-2EF4>..<reserved-2EFF> +2F00..2FD5 ; U # So [214] KANGXI RADICAL ONE..KANGXI RADICAL FLUTE +2FD6..2FDF ; U # Cn [10] <reserved-2FD6>..<reserved-2FDF> +2FE0..2FEF ; U # Cn [16] <reserved-2FE0>..<reserved-2FEF> +2FF0..2FFB ; U # So [12] IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT..IDEOGRAPHIC DESCRIPTION CHARACTER OVERLAID +2FFC..2FFF ; U # Cn [4] <reserved-2FFC>..<reserved-2FFF> +3000 ; U # Zs IDEOGRAPHIC SPACE +3001..3002 ; Tu # Po [2] IDEOGRAPHIC COMMA..IDEOGRAPHIC FULL STOP +3003 ; U # Po DITTO MARK +3004 ; U # So JAPANESE INDUSTRIAL STANDARD SYMBOL +3005 ; U # Lm IDEOGRAPHIC ITERATION MARK +3006 ; U # Lo IDEOGRAPHIC CLOSING MARK +3007 ; U # Nl IDEOGRAPHIC NUMBER ZERO +3008 ; Tr # Ps LEFT ANGLE BRACKET +3009 ; Tr # Pe RIGHT ANGLE BRACKET +300A ; Tr # Ps LEFT DOUBLE ANGLE BRACKET +300B ; Tr # Pe RIGHT DOUBLE ANGLE BRACKET +300C ; Tr # Ps LEFT CORNER BRACKET +300D ; Tr # Pe RIGHT CORNER BRACKET +300E ; Tr # Ps LEFT WHITE CORNER BRACKET +300F ; Tr # Pe RIGHT WHITE CORNER BRACKET +3010 ; Tr # Ps LEFT BLACK LENTICULAR BRACKET +3011 ; Tr # Pe RIGHT BLACK LENTICULAR BRACKET +3012..3013 ; U # So [2] POSTAL MARK..GETA MARK +3014 ; Tr # Ps LEFT TORTOISE SHELL BRACKET +3015 ; Tr # Pe RIGHT TORTOISE SHELL BRACKET +3016 ; Tr # Ps LEFT WHITE LENTICULAR BRACKET +3017 ; Tr # Pe RIGHT WHITE LENTICULAR BRACKET +3018 ; Tr # Ps LEFT WHITE TORTOISE SHELL BRACKET +3019 ; Tr # Pe RIGHT WHITE TORTOISE SHELL BRACKET +301A ; Tr # Ps LEFT WHITE SQUARE BRACKET +301B ; Tr # Pe RIGHT WHITE SQUARE BRACKET +301C ; Tr # Pd WAVE DASH +301D ; Tr # Ps REVERSED DOUBLE PRIME QUOTATION MARK +301E..301F ; Tr # Pe [2] DOUBLE PRIME QUOTATION MARK..LOW DOUBLE PRIME QUOTATION MARK +3020 ; U # So POSTAL MARK FACE +3021..3029 ; U # Nl [9] HANGZHOU NUMERAL ONE..HANGZHOU NUMERAL NINE +302A..302D ; U # Mn [4] IDEOGRAPHIC LEVEL TONE MARK..IDEOGRAPHIC ENTERING TONE MARK +302E..302F ; U # Mc [2] HANGUL SINGLE DOT TONE MARK..HANGUL DOUBLE DOT TONE MARK +3030 ; Tr # Pd WAVY DASH +3031..3035 ; U # Lm [5] VERTICAL KANA REPEAT MARK..VERTICAL KANA REPEAT MARK LOWER HALF +3036..3037 ; U # So [2] CIRCLED POSTAL MARK..IDEOGRAPHIC TELEGRAPH LINE FEED SEPARATOR SYMBOL +3038..303A ; U # Nl [3] HANGZHOU NUMERAL TEN..HANGZHOU NUMERAL THIRTY +303B ; U # Lm VERTICAL IDEOGRAPHIC ITERATION MARK +303C ; U # Lo MASU MARK +303D ; U # Po PART ALTERNATION MARK +303E..303F ; U # So [2] IDEOGRAPHIC VARIATION INDICATOR..IDEOGRAPHIC HALF FILL SPACE +3040 ; U # Cn <reserved-3040> +3041 ; Tu # Lo HIRAGANA LETTER SMALL A +3042 ; U # Lo HIRAGANA LETTER A +3043 ; Tu # Lo HIRAGANA LETTER SMALL I +3044 ; U # Lo HIRAGANA LETTER I +3045 ; Tu # Lo HIRAGANA LETTER SMALL U +3046 ; U # Lo HIRAGANA LETTER U +3047 ; Tu # Lo HIRAGANA LETTER SMALL E +3048 ; U # Lo HIRAGANA LETTER E +3049 ; Tu # Lo HIRAGANA LETTER SMALL O +304A..3062 ; U # Lo [25] HIRAGANA LETTER O..HIRAGANA LETTER DI +3063 ; Tu # Lo HIRAGANA LETTER SMALL TU +3064..3082 ; U # Lo [31] HIRAGANA LETTER TU..HIRAGANA LETTER MO +3083 ; Tu # Lo HIRAGANA LETTER SMALL YA +3084 ; U # Lo HIRAGANA LETTER YA +3085 ; Tu # Lo HIRAGANA LETTER SMALL YU +3086 ; U # Lo HIRAGANA LETTER YU +3087 ; Tu # Lo HIRAGANA LETTER SMALL YO +3088..308D ; U # Lo [6] HIRAGANA LETTER YO..HIRAGANA LETTER RO +308E ; Tu # Lo HIRAGANA LETTER SMALL WA +308F..3094 ; U # Lo [6] HIRAGANA LETTER WA..HIRAGANA LETTER VU +3095..3096 ; Tu # Lo [2] HIRAGANA LETTER SMALL KA..HIRAGANA LETTER SMALL KE +3097..3098 ; U # Cn [2] <reserved-3097>..<reserved-3098> +3099..309A ; U # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK +309B..309C ; Tu # Sk [2] KATAKANA-HIRAGANA VOICED SOUND MARK..KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK +309D..309E ; U # Lm [2] HIRAGANA ITERATION MARK..HIRAGANA VOICED ITERATION MARK +309F ; U # Lo HIRAGANA DIGRAPH YORI +30A0 ; Tr # Pd KATAKANA-HIRAGANA DOUBLE HYPHEN +30A1 ; Tu # Lo KATAKANA LETTER SMALL A +30A2 ; U # Lo KATAKANA LETTER A +30A3 ; Tu # Lo KATAKANA LETTER SMALL I +30A4 ; U # Lo KATAKANA LETTER I +30A5 ; Tu # Lo KATAKANA LETTER SMALL U +30A6 ; U # Lo KATAKANA LETTER U +30A7 ; Tu # Lo KATAKANA LETTER SMALL E +30A8 ; U # Lo KATAKANA LETTER E +30A9 ; Tu # Lo KATAKANA LETTER SMALL O +30AA..30C2 ; U # Lo [25] KATAKANA LETTER O..KATAKANA LETTER DI +30C3 ; Tu # Lo KATAKANA LETTER SMALL TU +30C4..30E2 ; U # Lo [31] KATAKANA LETTER TU..KATAKANA LETTER MO +30E3 ; Tu # Lo KATAKANA LETTER SMALL YA +30E4 ; U # Lo KATAKANA LETTER YA +30E5 ; Tu # Lo KATAKANA LETTER SMALL YU +30E6 ; U # Lo KATAKANA LETTER YU +30E7 ; Tu # Lo KATAKANA LETTER SMALL YO +30E8..30ED ; U # Lo [6] KATAKANA LETTER YO..KATAKANA LETTER RO +30EE ; Tu # Lo KATAKANA LETTER SMALL WA +30EF..30F4 ; U # Lo [6] KATAKANA LETTER WA..KATAKANA LETTER VU +30F5..30F6 ; Tu # Lo [2] KATAKANA LETTER SMALL KA..KATAKANA LETTER SMALL KE +30F7..30FA ; U # Lo [4] KATAKANA LETTER VA..KATAKANA LETTER VO +30FB ; U # Po KATAKANA MIDDLE DOT +30FC ; Tr # Lm KATAKANA-HIRAGANA PROLONGED SOUND MARK +30FD..30FE ; U # Lm [2] KATAKANA ITERATION MARK..KATAKANA VOICED ITERATION MARK +30FF ; U # Lo KATAKANA DIGRAPH KOTO +3100..3104 ; U # Cn [5] <reserved-3100>..<reserved-3104> +3105..3126 ; U # Lo [34] BOPOMOFO LETTER B..BOPOMOFO LETTER ER +3127 ; Tu # Lo BOPOMOFO LETTER I +3128..312E ; U # Lo [7] BOPOMOFO LETTER U..BOPOMOFO LETTER O WITH DOT ABOVE +312F ; U # Cn <reserved-312F> +3130 ; U # Cn <reserved-3130> +3131..318E ; U # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE +318F ; U # Cn <reserved-318F> +3190..3191 ; U # So [2] IDEOGRAPHIC ANNOTATION LINKING MARK..IDEOGRAPHIC ANNOTATION REVERSE MARK +3192..3195 ; U # No [4] IDEOGRAPHIC ANNOTATION ONE MARK..IDEOGRAPHIC ANNOTATION FOUR MARK +3196..319F ; U # So [10] IDEOGRAPHIC ANNOTATION TOP MARK..IDEOGRAPHIC ANNOTATION MAN MARK +31A0..31BA ; U # Lo [27] BOPOMOFO LETTER BU..BOPOMOFO LETTER ZY +31BB..31BF ; U # Cn [5] <reserved-31BB>..<reserved-31BF> +31C0..31E3 ; U # So [36] CJK STROKE T..CJK STROKE Q +31E4..31EF ; U # Cn [12] <reserved-31E4>..<reserved-31EF> +31F0..31FF ; Tu # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO +3200..321E ; U # So [31] PARENTHESIZED HANGUL KIYEOK..PARENTHESIZED KOREAN CHARACTER O HU +321F ; U # Cn <reserved-321F> +3220..3229 ; U # No [10] PARENTHESIZED IDEOGRAPH ONE..PARENTHESIZED IDEOGRAPH TEN +322A..3247 ; U # So [30] PARENTHESIZED IDEOGRAPH MOON..CIRCLED IDEOGRAPH KOTO +3248..324F ; U # No [8] CIRCLED NUMBER TEN ON BLACK SQUARE..CIRCLED NUMBER EIGHTY ON BLACK SQUARE +3250 ; U # So PARTNERSHIP SIGN +3251..325F ; U # No [15] CIRCLED NUMBER TWENTY ONE..CIRCLED NUMBER THIRTY FIVE +3260..327F ; U # So [32] CIRCLED HANGUL KIYEOK..KOREAN STANDARD SYMBOL +3280..3289 ; U # No [10] CIRCLED IDEOGRAPH ONE..CIRCLED IDEOGRAPH TEN +328A..32B0 ; U # So [39] CIRCLED IDEOGRAPH MOON..CIRCLED IDEOGRAPH NIGHT +32B1..32BF ; U # No [15] CIRCLED NUMBER THIRTY SIX..CIRCLED NUMBER FIFTY +32C0..32FE ; U # So [63] IDEOGRAPHIC TELEGRAPH SYMBOL FOR JANUARY..CIRCLED KATAKANA WO +32FF ; U # Cn <reserved-32FF> +3300..3357 ; Tu # So [88] SQUARE APAATO..SQUARE WATTO +3358..337A ; U # So [35] IDEOGRAPHIC TELEGRAPH SYMBOL FOR HOUR ZERO..SQUARE IU +337B..337F ; Tu # So [5] SQUARE ERA NAME HEISEI..SQUARE CORPORATION +3380..33FF ; U # So [128] SQUARE PA AMPS..SQUARE GAL +3400..4DB5 ; U # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 +4DB6..4DBF ; U # Cn [10] <reserved-4DB6>..<reserved-4DBF> +4DC0..4DFF ; U # So [64] HEXAGRAM FOR THE CREATIVE HEAVEN..HEXAGRAM FOR BEFORE COMPLETION +4E00..9FEA ; U # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA +9FEB..9FFF ; U # Cn [21] <reserved-9FEB>..<reserved-9FFF> +A000..A014 ; U # Lo [21] YI SYLLABLE IT..YI SYLLABLE E +A015 ; U # Lm YI SYLLABLE WU +A016..A48C ; U # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR +A48D..A48F ; U # Cn [3] <reserved-A48D>..<reserved-A48F> +A490..A4C6 ; U # So [55] YI RADICAL QOT..YI RADICAL KE +A4C7..A4CF ; U # Cn [9] <reserved-A4C7>..<reserved-A4CF> +A4D0..A4F7 ; R # Lo [40] LISU LETTER BA..LISU LETTER OE +A4F8..A4FD ; R # Lm [6] LISU LETTER TONE MYA TI..LISU LETTER TONE MYA JEU +A4FE..A4FF ; R # Po [2] LISU PUNCTUATION COMMA..LISU PUNCTUATION FULL STOP +A500..A60B ; R # Lo [268] VAI SYLLABLE EE..VAI SYLLABLE NG +A60C ; R # Lm VAI SYLLABLE LENGTHENER +A60D..A60F ; R # Po [3] VAI COMMA..VAI QUESTION MARK +A610..A61F ; R # Lo [16] VAI SYLLABLE NDOLE FA..VAI SYMBOL JONG +A620..A629 ; R # Nd [10] VAI DIGIT ZERO..VAI DIGIT NINE +A62A..A62B ; R # Lo [2] VAI SYLLABLE NDOLE MA..VAI SYLLABLE NDOLE DO +A640..A66D ; R # L& [46] CYRILLIC CAPITAL LETTER ZEMLYA..CYRILLIC SMALL LETTER DOUBLE MONOCULAR O +A66E ; R # Lo CYRILLIC LETTER MULTIOCULAR O +A66F ; R # Mn COMBINING CYRILLIC VZMET +A670..A672 ; R # Me [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRILLIC THOUSAND MILLIONS SIGN +A673 ; R # Po SLAVONIC ASTERISK +A674..A67D ; R # Mn [10] COMBINING CYRILLIC LETTER UKRAINIAN IE..COMBINING CYRILLIC PAYEROK +A67E ; R # Po CYRILLIC KAVYKA +A67F ; R # Lm CYRILLIC PAYEROK +A680..A69B ; R # L& [28] CYRILLIC CAPITAL LETTER DWE..CYRILLIC SMALL LETTER CROSSED O +A69C..A69D ; R # Lm [2] MODIFIER LETTER CYRILLIC HARD SIGN..MODIFIER LETTER CYRILLIC SOFT SIGN +A69E..A69F ; R # Mn [2] COMBINING CYRILLIC LETTER EF..COMBINING CYRILLIC LETTER IOTIFIED E +A6A0..A6E5 ; R # Lo [70] BAMUM LETTER A..BAMUM LETTER KI +A6E6..A6EF ; R # Nl [10] BAMUM LETTER MO..BAMUM LETTER KOGHOM +A6F0..A6F1 ; R # Mn [2] BAMUM COMBINING MARK KOQNDON..BAMUM COMBINING MARK TUKWENTIS +A6F2..A6F7 ; R # Po [6] BAMUM NJAEMLI..BAMUM QUESTION MARK +A700..A716 ; R # Sk [23] MODIFIER LETTER CHINESE TONE YIN PING..MODIFIER LETTER EXTRA-LOW LEFT-STEM TONE BAR +A717..A71F ; R # Lm [9] MODIFIER LETTER DOT VERTICAL BAR..MODIFIER LETTER LOW INVERTED EXCLAMATION MARK +A720..A721 ; R # Sk [2] MODIFIER LETTER STRESS AND HIGH TONE..MODIFIER LETTER STRESS AND LOW TONE +A722..A76F ; R # L& [78] LATIN CAPITAL LETTER EGYPTOLOGICAL ALEF..LATIN SMALL LETTER CON +A770 ; R # Lm MODIFIER LETTER US +A771..A787 ; R # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER INSULAR T +A788 ; R # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT +A789..A78A ; R # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN +A78B..A78E ; R # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT +A78F ; R # Lo LATIN LETTER SINOLOGICAL DOT +A790..A7AE ; R # L& [31] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER SMALL CAPITAL I +A7B0..A7B7 ; R # L& [8] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER OMEGA +A7F7 ; R # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I +A7F8..A7F9 ; R # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE +A7FA ; R # Ll LATIN LETTER SMALL CAPITAL TURNED M +A7FB..A7FF ; R # Lo [5] LATIN EPIGRAPHIC LETTER REVERSED F..LATIN EPIGRAPHIC LETTER ARCHAIC M +A800..A801 ; R # Lo [2] SYLOTI NAGRI LETTER A..SYLOTI NAGRI LETTER I +A802 ; R # Mn SYLOTI NAGRI SIGN DVISVARA +A803..A805 ; R # Lo [3] SYLOTI NAGRI LETTER U..SYLOTI NAGRI LETTER O +A806 ; R # Mn SYLOTI NAGRI SIGN HASANTA +A807..A80A ; R # Lo [4] SYLOTI NAGRI LETTER KO..SYLOTI NAGRI LETTER GHO +A80B ; R # Mn SYLOTI NAGRI SIGN ANUSVARA +A80C..A822 ; R # Lo [23] SYLOTI NAGRI LETTER CO..SYLOTI NAGRI LETTER HO +A823..A824 ; R # Mc [2] SYLOTI NAGRI VOWEL SIGN A..SYLOTI NAGRI VOWEL SIGN I +A825..A826 ; R # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E +A827 ; R # Mc SYLOTI NAGRI VOWEL SIGN OO +A828..A82B ; R # So [4] SYLOTI NAGRI POETRY MARK-1..SYLOTI NAGRI POETRY MARK-4 +A830..A835 ; R # No [6] NORTH INDIC FRACTION ONE QUARTER..NORTH INDIC FRACTION THREE SIXTEENTHS +A836..A837 ; R # So [2] NORTH INDIC QUARTER MARK..NORTH INDIC PLACEHOLDER MARK +A838 ; R # Sc NORTH INDIC RUPEE MARK +A839 ; R # So NORTH INDIC QUANTITY MARK +A840..A873 ; R # Lo [52] PHAGS-PA LETTER KA..PHAGS-PA LETTER CANDRABINDU +A874..A877 ; R # Po [4] PHAGS-PA SINGLE HEAD MARK..PHAGS-PA MARK DOUBLE SHAD +A880..A881 ; R # Mc [2] SAURASHTRA SIGN ANUSVARA..SAURASHTRA SIGN VISARGA +A882..A8B3 ; R # Lo [50] SAURASHTRA LETTER A..SAURASHTRA LETTER LLA +A8B4..A8C3 ; R # Mc [16] SAURASHTRA CONSONANT SIGN HAARU..SAURASHTRA VOWEL SIGN AU +A8C4..A8C5 ; R # Mn [2] SAURASHTRA SIGN VIRAMA..SAURASHTRA SIGN CANDRABINDU +A8CE..A8CF ; R # Po [2] SAURASHTRA DANDA..SAURASHTRA DOUBLE DANDA +A8D0..A8D9 ; R # Nd [10] SAURASHTRA DIGIT ZERO..SAURASHTRA DIGIT NINE +A8E0..A8F1 ; R # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA +A8F2..A8F7 ; R # Lo [6] DEVANAGARI SIGN SPACING CANDRABINDU..DEVANAGARI SIGN CANDRABINDU AVAGRAHA +A8F8..A8FA ; R # Po [3] DEVANAGARI SIGN PUSHPIKA..DEVANAGARI CARET +A8FB ; R # Lo DEVANAGARI HEADSTROKE +A8FC ; R # Po DEVANAGARI SIGN SIDDHAM +A8FD ; R # Lo DEVANAGARI JAIN OM +A900..A909 ; R # Nd [10] KAYAH LI DIGIT ZERO..KAYAH LI DIGIT NINE +A90A..A925 ; R # Lo [28] KAYAH LI LETTER KA..KAYAH LI LETTER OO +A926..A92D ; R # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU +A92E..A92F ; R # Po [2] KAYAH LI SIGN CWI..KAYAH LI SIGN SHYA +A930..A946 ; R # Lo [23] REJANG LETTER KA..REJANG LETTER A +A947..A951 ; R # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R +A952..A953 ; R # Mc [2] REJANG CONSONANT SIGN H..REJANG VIRAMA +A95F ; R # Po REJANG SECTION MARK +A960..A97C ; U # Lo [29] HANGUL CHOSEONG TIKEUT-MIEUM..HANGUL CHOSEONG SSANGYEORINHIEUH +A97D..A97F ; U # Cn [3] <reserved-A97D>..<reserved-A97F> +A980..A982 ; R # Mn [3] JAVANESE SIGN PANYANGGA..JAVANESE SIGN LAYAR +A983 ; R # Mc JAVANESE SIGN WIGNYAN +A984..A9B2 ; R # Lo [47] JAVANESE LETTER A..JAVANESE LETTER HA +A9B3 ; R # Mn JAVANESE SIGN CECAK TELU +A9B4..A9B5 ; R # Mc [2] JAVANESE VOWEL SIGN TARUNG..JAVANESE VOWEL SIGN TOLONG +A9B6..A9B9 ; R # Mn [4] JAVANESE VOWEL SIGN WULU..JAVANESE VOWEL SIGN SUKU MENDUT +A9BA..A9BB ; R # Mc [2] JAVANESE VOWEL SIGN TALING..JAVANESE VOWEL SIGN DIRGA MURE +A9BC ; R # Mn JAVANESE VOWEL SIGN PEPET +A9BD..A9C0 ; R # Mc [4] JAVANESE CONSONANT SIGN KERET..JAVANESE PANGKON +A9C1..A9CD ; R # Po [13] JAVANESE LEFT RERENGGAN..JAVANESE TURNED PADA PISELEH +A9CF ; R # Lm JAVANESE PANGRANGKEP +A9D0..A9D9 ; R # Nd [10] JAVANESE DIGIT ZERO..JAVANESE DIGIT NINE +A9DE..A9DF ; R # Po [2] JAVANESE PADA TIRTA TUMETES..JAVANESE PADA ISEN-ISEN +A9E0..A9E4 ; R # Lo [5] MYANMAR LETTER SHAN GHA..MYANMAR LETTER SHAN BHA +A9E5 ; R # Mn MYANMAR SIGN SHAN SAW +A9E6 ; R # Lm MYANMAR MODIFIER LETTER SHAN REDUPLICATION +A9E7..A9EF ; R # Lo [9] MYANMAR LETTER TAI LAING NYA..MYANMAR LETTER TAI LAING NNA +A9F0..A9F9 ; R # Nd [10] MYANMAR TAI LAING DIGIT ZERO..MYANMAR TAI LAING DIGIT NINE +A9FA..A9FE ; R # Lo [5] MYANMAR LETTER TAI LAING LLA..MYANMAR LETTER TAI LAING BHA +AA00..AA28 ; R # Lo [41] CHAM LETTER A..CHAM LETTER HA +AA29..AA2E ; R # Mn [6] CHAM VOWEL SIGN AA..CHAM VOWEL SIGN OE +AA2F..AA30 ; R # Mc [2] CHAM VOWEL SIGN O..CHAM VOWEL SIGN AI +AA31..AA32 ; R # Mn [2] CHAM VOWEL SIGN AU..CHAM VOWEL SIGN UE +AA33..AA34 ; R # Mc [2] CHAM CONSONANT SIGN YA..CHAM CONSONANT SIGN RA +AA35..AA36 ; R # Mn [2] CHAM CONSONANT SIGN LA..CHAM CONSONANT SIGN WA +AA40..AA42 ; R # Lo [3] CHAM LETTER FINAL K..CHAM LETTER FINAL NG +AA43 ; R # Mn CHAM CONSONANT SIGN FINAL NG +AA44..AA4B ; R # Lo [8] CHAM LETTER FINAL CH..CHAM LETTER FINAL SS +AA4C ; R # Mn CHAM CONSONANT SIGN FINAL M +AA4D ; R # Mc CHAM CONSONANT SIGN FINAL H +AA50..AA59 ; R # Nd [10] CHAM DIGIT ZERO..CHAM DIGIT NINE +AA5C..AA5F ; R # Po [4] CHAM PUNCTUATION SPIRAL..CHAM PUNCTUATION TRIPLE DANDA +AA60..AA6F ; R # Lo [16] MYANMAR LETTER KHAMTI GA..MYANMAR LETTER KHAMTI FA +AA70 ; R # Lm MYANMAR MODIFIER LETTER KHAMTI REDUPLICATION +AA71..AA76 ; R # Lo [6] MYANMAR LETTER KHAMTI XA..MYANMAR LOGOGRAM KHAMTI HM +AA77..AA79 ; R # So [3] MYANMAR SYMBOL AITON EXCLAMATION..MYANMAR SYMBOL AITON TWO +AA7A ; R # Lo MYANMAR LETTER AITON RA +AA7B ; R # Mc MYANMAR SIGN PAO KAREN TONE +AA7C ; R # Mn MYANMAR SIGN TAI LAING TONE-2 +AA7D ; R # Mc MYANMAR SIGN TAI LAING TONE-5 +AA7E..AA7F ; R # Lo [2] MYANMAR LETTER SHWE PALAUNG CHA..MYANMAR LETTER SHWE PALAUNG SHA +AA80..AAAF ; R # Lo [48] TAI VIET LETTER LOW KO..TAI VIET LETTER HIGH O +AAB0 ; R # Mn TAI VIET MAI KANG +AAB1 ; R # Lo TAI VIET VOWEL AA +AAB2..AAB4 ; R # Mn [3] TAI VIET VOWEL I..TAI VIET VOWEL U +AAB5..AAB6 ; R # Lo [2] TAI VIET VOWEL E..TAI VIET VOWEL O +AAB7..AAB8 ; R # Mn [2] TAI VIET MAI KHIT..TAI VIET VOWEL IA +AAB9..AABD ; R # Lo [5] TAI VIET VOWEL UEA..TAI VIET VOWEL AN +AABE..AABF ; R # Mn [2] TAI VIET VOWEL AM..TAI VIET TONE MAI EK +AAC0 ; R # Lo TAI VIET TONE MAI NUENG +AAC1 ; R # Mn TAI VIET TONE MAI THO +AAC2 ; R # Lo TAI VIET TONE MAI SONG +AADB..AADC ; R # Lo [2] TAI VIET SYMBOL KON..TAI VIET SYMBOL NUENG +AADD ; R # Lm TAI VIET SYMBOL SAM +AADE..AADF ; R # Po [2] TAI VIET SYMBOL HO HOI..TAI VIET SYMBOL KOI KOI +AAE0..AAEA ; R # Lo [11] MEETEI MAYEK LETTER E..MEETEI MAYEK LETTER SSA +AAEB ; R # Mc MEETEI MAYEK VOWEL SIGN II +AAEC..AAED ; R # Mn [2] MEETEI MAYEK VOWEL SIGN UU..MEETEI MAYEK VOWEL SIGN AAI +AAEE..AAEF ; R # Mc [2] MEETEI MAYEK VOWEL SIGN AU..MEETEI MAYEK VOWEL SIGN AAU +AAF0..AAF1 ; R # Po [2] MEETEI MAYEK CHEIKHAN..MEETEI MAYEK AHANG KHUDAM +AAF2 ; R # Lo MEETEI MAYEK ANJI +AAF3..AAF4 ; R # Lm [2] MEETEI MAYEK SYLLABLE REPETITION MARK..MEETEI MAYEK WORD REPETITION MARK +AAF5 ; R # Mc MEETEI MAYEK VOWEL SIGN VISARGA +AAF6 ; R # Mn MEETEI MAYEK VIRAMA +AB01..AB06 ; R # Lo [6] ETHIOPIC SYLLABLE TTHU..ETHIOPIC SYLLABLE TTHO +AB09..AB0E ; R # Lo [6] ETHIOPIC SYLLABLE DDHU..ETHIOPIC SYLLABLE DDHO +AB11..AB16 ; R # Lo [6] ETHIOPIC SYLLABLE DZU..ETHIOPIC SYLLABLE DZO +AB20..AB26 ; R # Lo [7] ETHIOPIC SYLLABLE CCHHA..ETHIOPIC SYLLABLE CCHHO +AB28..AB2E ; R # Lo [7] ETHIOPIC SYLLABLE BBA..ETHIOPIC SYLLABLE BBO +AB30..AB5A ; R # Ll [43] LATIN SMALL LETTER BARRED ALPHA..LATIN SMALL LETTER Y WITH SHORT RIGHT LEG +AB5B ; R # Sk MODIFIER BREVE WITH INVERTED BREVE +AB5C..AB5F ; R # Lm [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U WITH LEFT HOOK +AB60..AB65 ; R # Ll [6] LATIN SMALL LETTER SAKHA YAT..GREEK LETTER SMALL CAPITAL OMEGA +AB70..ABBF ; R # Ll [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA +ABC0..ABE2 ; R # Lo [35] MEETEI MAYEK LETTER KOK..MEETEI MAYEK LETTER I LONSUM +ABE3..ABE4 ; R # Mc [2] MEETEI MAYEK VOWEL SIGN ONAP..MEETEI MAYEK VOWEL SIGN INAP +ABE5 ; R # Mn MEETEI MAYEK VOWEL SIGN ANAP +ABE6..ABE7 ; R # Mc [2] MEETEI MAYEK VOWEL SIGN YENAP..MEETEI MAYEK VOWEL SIGN SOUNAP +ABE8 ; R # Mn MEETEI MAYEK VOWEL SIGN UNAP +ABE9..ABEA ; R # Mc [2] MEETEI MAYEK VOWEL SIGN CHEINAP..MEETEI MAYEK VOWEL SIGN NUNG +ABEB ; R # Po MEETEI MAYEK CHEIKHEI +ABEC ; R # Mc MEETEI MAYEK LUM IYEK +ABED ; R # Mn MEETEI MAYEK APUN IYEK +ABF0..ABF9 ; R # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE +AC00..D7A3 ; U # Lo [11172] HANGUL SYLLABLE GA..HANGUL SYLLABLE HIH +D7A4..D7AF ; U # Cn [12] <reserved-D7A4>..<reserved-D7AF> +D7B0..D7C6 ; U # Lo [23] HANGUL JUNGSEONG O-YEO..HANGUL JUNGSEONG ARAEA-E +D7C7..D7CA ; U # Cn [4] <reserved-D7C7>..<reserved-D7CA> +D7CB..D7FB ; U # Lo [49] HANGUL JONGSEONG NIEUN-RIEUL..HANGUL JONGSEONG PHIEUPH-THIEUTH +D7FC..D7FF ; U # Cn [4] <reserved-D7FC>..<reserved-D7FF> +D800..DFFF ; R # Cs [2048] <surrogate-D800>..<surrogate-DFFF> +E000..F8FF ; U # Co [6400] <private-use-E000>..<private-use-F8FF> +F900..FA6D ; U # Lo [366] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA6D +FA6E..FA6F ; U # Cn [2] <reserved-FA6E>..<reserved-FA6F> +FA70..FAD9 ; U # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COMPATIBILITY IDEOGRAPH-FAD9 +FADA..FAFF ; U # Cn [38] <reserved-FADA>..<reserved-FAFF> +FB00..FB06 ; R # Ll [7] LATIN SMALL LIGATURE FF..LATIN SMALL LIGATURE ST +FB13..FB17 ; R # Ll [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SMALL LIGATURE MEN XEH +FB1D ; R # Lo HEBREW LETTER YOD WITH HIRIQ +FB1E ; R # Mn HEBREW POINT JUDEO-SPANISH VARIKA +FB1F..FB28 ; R # Lo [10] HEBREW LIGATURE YIDDISH YOD YOD PATAH..HEBREW LETTER WIDE TAV +FB29 ; R # Sm HEBREW LETTER ALTERNATIVE PLUS SIGN +FB2A..FB36 ; R # Lo [13] HEBREW LETTER SHIN WITH SHIN DOT..HEBREW LETTER ZAYIN WITH DAGESH +FB38..FB3C ; R # Lo [5] HEBREW LETTER TET WITH DAGESH..HEBREW LETTER LAMED WITH DAGESH +FB3E ; R # Lo HEBREW LETTER MEM WITH DAGESH +FB40..FB41 ; R # Lo [2] HEBREW LETTER NUN WITH DAGESH..HEBREW LETTER SAMEKH WITH DAGESH +FB43..FB44 ; R # Lo [2] HEBREW LETTER FINAL PE WITH DAGESH..HEBREW LETTER PE WITH DAGESH +FB46..FB4F ; R # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATURE ALEF LAMED +FB50..FBB1 ; R # Lo [98] ARABIC LETTER ALEF WASLA ISOLATED FORM..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE FINAL FORM +FBB2..FBC1 ; R # Sk [16] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL SMALL TAH BELOW +FBD3..FD3D ; R # Lo [363] ARABIC LETTER NG ISOLATED FORM..ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM +FD3E ; R # Pe ORNATE LEFT PARENTHESIS +FD3F ; R # Ps ORNATE RIGHT PARENTHESIS +FD50..FD8F ; R # Lo [64] ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM..ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM +FD92..FDC7 ; R # Lo [54] ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM..ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM +FDF0..FDFB ; R # Lo [12] ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM..ARABIC LIGATURE JALLAJALALOUHOU +FDFC ; R # Sc RIAL SIGN +FDFD ; R # So ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM +FE00..FE0F ; R # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 +FE10..FE16 ; U # Po [7] PRESENTATION FORM FOR VERTICAL COMMA..PRESENTATION FORM FOR VERTICAL QUESTION MARK +FE17 ; U # Ps PRESENTATION FORM FOR VERTICAL LEFT WHITE LENTICULAR BRACKET +FE18 ; U # Pe PRESENTATION FORM FOR VERTICAL RIGHT WHITE LENTICULAR BRAKCET +FE19 ; U # Po PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS +FE1A..FE1F ; U # Cn [6] <reserved-FE1A>..<reserved-FE1F> +FE20..FE2F ; R # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF +FE30 ; U # Po PRESENTATION FORM FOR VERTICAL TWO DOT LEADER +FE31..FE32 ; U # Pd [2] PRESENTATION FORM FOR VERTICAL EM DASH..PRESENTATION FORM FOR VERTICAL EN DASH +FE33..FE34 ; U # Pc [2] PRESENTATION FORM FOR VERTICAL LOW LINE..PRESENTATION FORM FOR VERTICAL WAVY LOW LINE +FE35 ; U # Ps PRESENTATION FORM FOR VERTICAL LEFT PARENTHESIS +FE36 ; U # Pe PRESENTATION FORM FOR VERTICAL RIGHT PARENTHESIS +FE37 ; U # Ps PRESENTATION FORM FOR VERTICAL LEFT CURLY BRACKET +FE38 ; U # Pe PRESENTATION FORM FOR VERTICAL RIGHT CURLY BRACKET +FE39 ; U # Ps PRESENTATION FORM FOR VERTICAL LEFT TORTOISE SHELL BRACKET +FE3A ; U # Pe PRESENTATION FORM FOR VERTICAL RIGHT TORTOISE SHELL BRACKET +FE3B ; U # Ps PRESENTATION FORM FOR VERTICAL LEFT BLACK LENTICULAR BRACKET +FE3C ; U # Pe PRESENTATION FORM FOR VERTICAL RIGHT BLACK LENTICULAR BRACKET +FE3D ; U # Ps PRESENTATION FORM FOR VERTICAL LEFT DOUBLE ANGLE BRACKET +FE3E ; U # Pe PRESENTATION FORM FOR VERTICAL RIGHT DOUBLE ANGLE BRACKET +FE3F ; U # Ps PRESENTATION FORM FOR VERTICAL LEFT ANGLE BRACKET +FE40 ; U # Pe PRESENTATION FORM FOR VERTICAL RIGHT ANGLE BRACKET +FE41 ; U # Ps PRESENTATION FORM FOR VERTICAL LEFT CORNER BRACKET +FE42 ; U # Pe PRESENTATION FORM FOR VERTICAL RIGHT CORNER BRACKET +FE43 ; U # Ps PRESENTATION FORM FOR VERTICAL LEFT WHITE CORNER BRACKET +FE44 ; U # Pe PRESENTATION FORM FOR VERTICAL RIGHT WHITE CORNER BRACKET +FE45..FE46 ; U # Po [2] SESAME DOT..WHITE SESAME DOT +FE47 ; U # Ps PRESENTATION FORM FOR VERTICAL LEFT SQUARE BRACKET +FE48 ; U # Pe PRESENTATION FORM FOR VERTICAL RIGHT SQUARE BRACKET +FE49..FE4C ; R # Po [4] DASHED OVERLINE..DOUBLE WAVY OVERLINE +FE4D..FE4F ; R # Pc [3] DASHED LOW LINE..WAVY LOW LINE +FE50..FE52 ; Tu # Po [3] SMALL COMMA..SMALL FULL STOP +FE53 ; U # Cn <reserved-FE53> +FE54..FE57 ; U # Po [4] SMALL SEMICOLON..SMALL EXCLAMATION MARK +FE58 ; R # Pd SMALL EM DASH +FE59 ; Tr # Ps SMALL LEFT PARENTHESIS +FE5A ; Tr # Pe SMALL RIGHT PARENTHESIS +FE5B ; Tr # Ps SMALL LEFT CURLY BRACKET +FE5C ; Tr # Pe SMALL RIGHT CURLY BRACKET +FE5D ; Tr # Ps SMALL LEFT TORTOISE SHELL BRACKET +FE5E ; Tr # Pe SMALL RIGHT TORTOISE SHELL BRACKET +FE5F..FE61 ; U # Po [3] SMALL NUMBER SIGN..SMALL ASTERISK +FE62 ; U # Sm SMALL PLUS SIGN +FE63 ; R # Pd SMALL HYPHEN-MINUS +FE64..FE66 ; R # Sm [3] SMALL LESS-THAN SIGN..SMALL EQUALS SIGN +FE67 ; U # Cn <reserved-FE67> +FE68 ; U # Po SMALL REVERSE SOLIDUS +FE69 ; U # Sc SMALL DOLLAR SIGN +FE6A..FE6B ; U # Po [2] SMALL PERCENT SIGN..SMALL COMMERCIAL AT +FE6C..FE6F ; U # Cn [4] <reserved-FE6C>..<reserved-FE6F> +FE70..FE74 ; R # Lo [5] ARABIC FATHATAN ISOLATED FORM..ARABIC KASRATAN ISOLATED FORM +FE76..FEFC ; R # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LAM WITH ALEF FINAL FORM +FEFF ; R # Cf ZERO WIDTH NO-BREAK SPACE +FF01 ; Tu # Po FULLWIDTH EXCLAMATION MARK +FF02..FF03 ; U # Po [2] FULLWIDTH QUOTATION MARK..FULLWIDTH NUMBER SIGN +FF04 ; U # Sc FULLWIDTH DOLLAR SIGN +FF05..FF07 ; U # Po [3] FULLWIDTH PERCENT SIGN..FULLWIDTH APOSTROPHE +FF08 ; Tr # Ps FULLWIDTH LEFT PARENTHESIS +FF09 ; Tr # Pe FULLWIDTH RIGHT PARENTHESIS +FF0A ; U # Po FULLWIDTH ASTERISK +FF0B ; U # Sm FULLWIDTH PLUS SIGN +FF0C ; Tu # Po FULLWIDTH COMMA +FF0D ; R # Pd FULLWIDTH HYPHEN-MINUS +FF0E ; Tu # Po FULLWIDTH FULL STOP +FF0F ; U # Po FULLWIDTH SOLIDUS +FF10..FF19 ; U # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE +FF1A..FF1B ; Tr # Po [2] FULLWIDTH COLON..FULLWIDTH SEMICOLON +FF1C..FF1E ; R # Sm [3] FULLWIDTH LESS-THAN SIGN..FULLWIDTH GREATER-THAN SIGN +FF1F ; Tu # Po FULLWIDTH QUESTION MARK +FF20 ; U # Po FULLWIDTH COMMERCIAL AT +FF21..FF3A ; U # Lu [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER Z +FF3B ; Tr # Ps FULLWIDTH LEFT SQUARE BRACKET +FF3C ; U # Po FULLWIDTH REVERSE SOLIDUS +FF3D ; Tr # Pe FULLWIDTH RIGHT SQUARE BRACKET +FF3E ; U # Sk FULLWIDTH CIRCUMFLEX ACCENT +FF3F ; Tr # Pc FULLWIDTH LOW LINE +FF40 ; U # Sk FULLWIDTH GRAVE ACCENT +FF41..FF5A ; U # Ll [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER Z +FF5B ; Tr # Ps FULLWIDTH LEFT CURLY BRACKET +FF5C ; Tr # Sm FULLWIDTH VERTICAL LINE +FF5D ; Tr # Pe FULLWIDTH RIGHT CURLY BRACKET +FF5E ; Tr # Sm FULLWIDTH TILDE +FF5F ; Tr # Ps FULLWIDTH LEFT WHITE PARENTHESIS +FF60 ; Tr # Pe FULLWIDTH RIGHT WHITE PARENTHESIS +FF61 ; R # Po HALFWIDTH IDEOGRAPHIC FULL STOP +FF62 ; R # Ps HALFWIDTH LEFT CORNER BRACKET +FF63 ; R # Pe HALFWIDTH RIGHT CORNER BRACKET +FF64..FF65 ; R # Po [2] HALFWIDTH IDEOGRAPHIC COMMA..HALFWIDTH KATAKANA MIDDLE DOT +FF66..FF6F ; R # Lo [10] HALFWIDTH KATAKANA LETTER WO..HALFWIDTH KATAKANA LETTER SMALL TU +FF70 ; R # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK +FF71..FF9D ; R # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAKANA LETTER N +FF9E..FF9F ; R # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK +FFA0..FFBE ; R # Lo [31] HALFWIDTH HANGUL FILLER..HALFWIDTH HANGUL LETTER HIEUH +FFC2..FFC7 ; R # Lo [6] HALFWIDTH HANGUL LETTER A..HALFWIDTH HANGUL LETTER E +FFCA..FFCF ; R # Lo [6] HALFWIDTH HANGUL LETTER YEO..HALFWIDTH HANGUL LETTER OE +FFD2..FFD7 ; R # Lo [6] HALFWIDTH HANGUL LETTER YO..HALFWIDTH HANGUL LETTER YU +FFDA..FFDC ; R # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I +FFE0..FFE1 ; U # Sc [2] FULLWIDTH CENT SIGN..FULLWIDTH POUND SIGN +FFE2 ; U # Sm FULLWIDTH NOT SIGN +FFE3 ; Tr # Sk FULLWIDTH MACRON +FFE4 ; U # So FULLWIDTH BROKEN BAR +FFE5..FFE6 ; U # Sc [2] FULLWIDTH YEN SIGN..FULLWIDTH WON SIGN +FFE7 ; U # Cn <reserved-FFE7> +FFE8 ; R # So HALFWIDTH FORMS LIGHT VERTICAL +FFE9..FFEC ; R # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS ARROW +FFED..FFEE ; R # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE +FFF0..FFF8 ; U # Cn [9] <reserved-FFF0>..<reserved-FFF8> +FFF9..FFFB ; R # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR +FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER +10000..1000B ; R # Lo [12] LINEAR B SYLLABLE B008 A..LINEAR B SYLLABLE B046 JE +1000D..10026 ; R # Lo [26] LINEAR B SYLLABLE B036 JO..LINEAR B SYLLABLE B032 QO +10028..1003A ; R # Lo [19] LINEAR B SYLLABLE B060 RA..LINEAR B SYLLABLE B042 WO +1003C..1003D ; R # Lo [2] LINEAR B SYLLABLE B017 ZA..LINEAR B SYLLABLE B074 ZE +1003F..1004D ; R # Lo [15] LINEAR B SYLLABLE B020 ZO..LINEAR B SYLLABLE B091 TWO +10050..1005D ; R # Lo [14] LINEAR B SYMBOL B018..LINEAR B SYMBOL B089 +10080..100FA ; R # Lo [123] LINEAR B IDEOGRAM B100 MAN..LINEAR B IDEOGRAM VESSEL B305 +10100..10102 ; R # Po [3] AEGEAN WORD SEPARATOR LINE..AEGEAN CHECK MARK +10107..10133 ; R # No [45] AEGEAN NUMBER ONE..AEGEAN NUMBER NINETY THOUSAND +10137..1013F ; R # So [9] AEGEAN WEIGHT BASE UNIT..AEGEAN MEASURE THIRD SUBUNIT +10140..10174 ; R # Nl [53] GREEK ACROPHONIC ATTIC ONE QUARTER..GREEK ACROPHONIC STRATIAN FIFTY MNAS +10175..10178 ; R # No [4] GREEK ONE HALF SIGN..GREEK THREE QUARTERS SIGN +10179..10189 ; R # So [17] GREEK YEAR SIGN..GREEK TRYBLION BASE SIGN +1018A..1018B ; R # No [2] GREEK ZERO SIGN..GREEK ONE QUARTER SIGN +1018C..1018E ; R # So [3] GREEK SINUSOID SIGN..NOMISMA SIGN +10190..1019B ; R # So [12] ROMAN SEXTANS SIGN..ROMAN CENTURIAL SIGN +101A0 ; R # So GREEK SYMBOL TAU RHO +101D0..101FC ; R # So [45] PHAISTOS DISC SIGN PEDESTRIAN..PHAISTOS DISC SIGN WAVY BAND +101FD ; R # Mn PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE +10280..1029C ; R # Lo [29] LYCIAN LETTER A..LYCIAN LETTER X +102A0..102D0 ; R # Lo [49] CARIAN LETTER A..CARIAN LETTER UUU3 +102E0 ; R # Mn COPTIC EPACT THOUSANDS MARK +102E1..102FB ; R # No [27] COPTIC EPACT DIGIT ONE..COPTIC EPACT NUMBER NINE HUNDRED +10300..1031F ; R # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS +10320..10323 ; R # No [4] OLD ITALIC NUMERAL ONE..OLD ITALIC NUMERAL FIFTY +1032D..1032F ; R # Lo [3] OLD ITALIC LETTER YE..OLD ITALIC LETTER SOUTHERN TSE +10330..10340 ; R # Lo [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA +10341 ; R # Nl GOTHIC LETTER NINETY +10342..10349 ; R # Lo [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL +1034A ; R # Nl GOTHIC LETTER NINE HUNDRED +10350..10375 ; R # Lo [38] OLD PERMIC LETTER AN..OLD PERMIC LETTER IA +10376..1037A ; R # Mn [5] COMBINING OLD PERMIC LETTER AN..COMBINING OLD PERMIC LETTER SII +10380..1039D ; R # Lo [30] UGARITIC LETTER ALPA..UGARITIC LETTER SSU +1039F ; R # Po UGARITIC WORD DIVIDER +103A0..103C3 ; R # Lo [36] OLD PERSIAN SIGN A..OLD PERSIAN SIGN HA +103C8..103CF ; R # Lo [8] OLD PERSIAN SIGN AURAMAZDAA..OLD PERSIAN SIGN BUUMISH +103D0 ; R # Po OLD PERSIAN WORD DIVIDER +103D1..103D5 ; R # Nl [5] OLD PERSIAN NUMBER ONE..OLD PERSIAN NUMBER HUNDRED +10400..1044F ; R # L& [80] DESERET CAPITAL LETTER LONG I..DESERET SMALL LETTER EW +10450..1047F ; R # Lo [48] SHAVIAN LETTER PEEP..SHAVIAN LETTER YEW +10480..1049D ; R # Lo [30] OSMANYA LETTER ALEF..OSMANYA LETTER OO +104A0..104A9 ; R # Nd [10] OSMANYA DIGIT ZERO..OSMANYA DIGIT NINE +104B0..104D3 ; R # Lu [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA +104D8..104FB ; R # Ll [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA +10500..10527 ; R # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE +10530..10563 ; R # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW +1056F ; R # Po CAUCASIAN ALBANIAN CITATION MARK +10600..10736 ; R # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 +10740..10755 ; R # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE +10760..10767 ; R # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 +10800..10805 ; R # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA +10808 ; R # Lo CYPRIOT SYLLABLE JO +1080A..10835 ; R # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO +10837..10838 ; R # Lo [2] CYPRIOT SYLLABLE XA..CYPRIOT SYLLABLE XE +1083C ; R # Lo CYPRIOT SYLLABLE ZA +1083F ; R # Lo CYPRIOT SYLLABLE ZO +10840..10855 ; R # Lo [22] IMPERIAL ARAMAIC LETTER ALEPH..IMPERIAL ARAMAIC LETTER TAW +10857 ; R # Po IMPERIAL ARAMAIC SECTION SIGN +10858..1085F ; R # No [8] IMPERIAL ARAMAIC NUMBER ONE..IMPERIAL ARAMAIC NUMBER TEN THOUSAND +10860..10876 ; R # Lo [23] PALMYRENE LETTER ALEPH..PALMYRENE LETTER TAW +10877..10878 ; R # So [2] PALMYRENE LEFT-POINTING FLEURON..PALMYRENE RIGHT-POINTING FLEURON +10879..1087F ; R # No [7] PALMYRENE NUMBER ONE..PALMYRENE NUMBER TWENTY +10880..1089E ; R # Lo [31] NABATAEAN LETTER FINAL ALEPH..NABATAEAN LETTER TAW +108A7..108AF ; R # No [9] NABATAEAN NUMBER ONE..NABATAEAN NUMBER ONE HUNDRED +108E0..108F2 ; R # Lo [19] HATRAN LETTER ALEPH..HATRAN LETTER QOPH +108F4..108F5 ; R # Lo [2] HATRAN LETTER SHIN..HATRAN LETTER TAW +108FB..108FF ; R # No [5] HATRAN NUMBER ONE..HATRAN NUMBER ONE HUNDRED +10900..10915 ; R # Lo [22] PHOENICIAN LETTER ALF..PHOENICIAN LETTER TAU +10916..1091B ; R # No [6] PHOENICIAN NUMBER ONE..PHOENICIAN NUMBER THREE +1091F ; R # Po PHOENICIAN WORD SEPARATOR +10920..10939 ; R # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C +1093F ; R # Po LYDIAN TRIANGULAR MARK +10980..1099F ; U # Lo [32] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC HIEROGLYPHIC SYMBOL VIDJ-2 +109A0..109B7 ; R # Lo [24] MEROITIC CURSIVE LETTER A..MEROITIC CURSIVE LETTER DA +109BC..109BD ; R # No [2] MEROITIC CURSIVE FRACTION ELEVEN TWELFTHS..MEROITIC CURSIVE FRACTION ONE HALF +109BE..109BF ; R # Lo [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN +109C0..109CF ; R # No [16] MEROITIC CURSIVE NUMBER ONE..MEROITIC CURSIVE NUMBER SEVENTY +109D2..109FF ; R # No [46] MEROITIC CURSIVE NUMBER ONE HUNDRED..MEROITIC CURSIVE FRACTION TEN TWELFTHS +10A00 ; R # Lo KHAROSHTHI LETTER A +10A01..10A03 ; R # Mn [3] KHAROSHTHI VOWEL SIGN I..KHAROSHTHI VOWEL SIGN VOCALIC R +10A05..10A06 ; R # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O +10A0C..10A0F ; R # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA +10A10..10A13 ; R # Lo [4] KHAROSHTHI LETTER KA..KHAROSHTHI LETTER GHA +10A15..10A17 ; R # Lo [3] KHAROSHTHI LETTER CA..KHAROSHTHI LETTER JA +10A19..10A33 ; R # Lo [27] KHAROSHTHI LETTER NYA..KHAROSHTHI LETTER TTTHA +10A38..10A3A ; R # Mn [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW +10A3F ; R # Mn KHAROSHTHI VIRAMA +10A40..10A47 ; R # No [8] KHAROSHTHI DIGIT ONE..KHAROSHTHI NUMBER ONE THOUSAND +10A50..10A58 ; R # Po [9] KHAROSHTHI PUNCTUATION DOT..KHAROSHTHI PUNCTUATION LINES +10A60..10A7C ; R # Lo [29] OLD SOUTH ARABIAN LETTER HE..OLD SOUTH ARABIAN LETTER THETH +10A7D..10A7E ; R # No [2] OLD SOUTH ARABIAN NUMBER ONE..OLD SOUTH ARABIAN NUMBER FIFTY +10A7F ; R # Po OLD SOUTH ARABIAN NUMERIC INDICATOR +10A80..10A9C ; R # Lo [29] OLD NORTH ARABIAN LETTER HEH..OLD NORTH ARABIAN LETTER ZAH +10A9D..10A9F ; R # No [3] OLD NORTH ARABIAN NUMBER ONE..OLD NORTH ARABIAN NUMBER TWENTY +10AC0..10AC7 ; R # Lo [8] MANICHAEAN LETTER ALEPH..MANICHAEAN LETTER WAW +10AC8 ; R # So MANICHAEAN SIGN UD +10AC9..10AE4 ; R # Lo [28] MANICHAEAN LETTER ZAYIN..MANICHAEAN LETTER TAW +10AE5..10AE6 ; R # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW +10AEB..10AEF ; R # No [5] MANICHAEAN NUMBER ONE..MANICHAEAN NUMBER ONE HUNDRED +10AF0..10AF6 ; R # Po [7] MANICHAEAN PUNCTUATION STAR..MANICHAEAN PUNCTUATION LINE FILLER +10B00..10B35 ; R # Lo [54] AVESTAN LETTER A..AVESTAN LETTER HE +10B39..10B3F ; R # Po [7] AVESTAN ABBREVIATION MARK..LARGE ONE RING OVER TWO RINGS PUNCTUATION +10B40..10B55 ; R # Lo [22] INSCRIPTIONAL PARTHIAN LETTER ALEPH..INSCRIPTIONAL PARTHIAN LETTER TAW +10B58..10B5F ; R # No [8] INSCRIPTIONAL PARTHIAN NUMBER ONE..INSCRIPTIONAL PARTHIAN NUMBER ONE THOUSAND +10B60..10B72 ; R # Lo [19] INSCRIPTIONAL PAHLAVI LETTER ALEPH..INSCRIPTIONAL PAHLAVI LETTER TAW +10B78..10B7F ; R # No [8] INSCRIPTIONAL PAHLAVI NUMBER ONE..INSCRIPTIONAL PAHLAVI NUMBER ONE THOUSAND +10B80..10B91 ; R # Lo [18] PSALTER PAHLAVI LETTER ALEPH..PSALTER PAHLAVI LETTER TAW +10B99..10B9C ; R # Po [4] PSALTER PAHLAVI SECTION MARK..PSALTER PAHLAVI FOUR DOTS WITH DOT +10BA9..10BAF ; R # No [7] PSALTER PAHLAVI NUMBER ONE..PSALTER PAHLAVI NUMBER ONE HUNDRED +10C00..10C48 ; R # Lo [73] OLD TURKIC LETTER ORKHON A..OLD TURKIC LETTER ORKHON BASH +10C80..10CB2 ; R # Lu [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US +10CC0..10CF2 ; R # Ll [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US +10CFA..10CFF ; R # No [6] OLD HUNGARIAN NUMBER ONE..OLD HUNGARIAN NUMBER ONE THOUSAND +10E60..10E7E ; R # No [31] RUMI DIGIT ONE..RUMI FRACTION TWO THIRDS +11000 ; R # Mc BRAHMI SIGN CANDRABINDU +11001 ; R # Mn BRAHMI SIGN ANUSVARA +11002 ; R # Mc BRAHMI SIGN VISARGA +11003..11037 ; R # Lo [53] BRAHMI SIGN JIHVAMULIYA..BRAHMI LETTER OLD TAMIL NNNA +11038..11046 ; R # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA +11047..1104D ; R # Po [7] BRAHMI DANDA..BRAHMI PUNCTUATION LOTUS +11052..11065 ; R # No [20] BRAHMI NUMBER ONE..BRAHMI NUMBER ONE THOUSAND +11066..1106F ; R # Nd [10] BRAHMI DIGIT ZERO..BRAHMI DIGIT NINE +1107F ; R # Mn BRAHMI NUMBER JOINER +11080..11081 ; R # Mn [2] KAITHI SIGN CANDRABINDU..KAITHI SIGN ANUSVARA +11082 ; R # Mc KAITHI SIGN VISARGA +11083..110AF ; R # Lo [45] KAITHI LETTER A..KAITHI LETTER HA +110B0..110B2 ; R # Mc [3] KAITHI VOWEL SIGN AA..KAITHI VOWEL SIGN II +110B3..110B6 ; R # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI +110B7..110B8 ; R # Mc [2] KAITHI VOWEL SIGN O..KAITHI VOWEL SIGN AU +110B9..110BA ; R # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA +110BB..110BC ; R # Po [2] KAITHI ABBREVIATION SIGN..KAITHI ENUMERATION SIGN +110BD ; R # Cf KAITHI NUMBER SIGN +110BE..110C1 ; R # Po [4] KAITHI SECTION MARK..KAITHI DOUBLE DANDA +110D0..110E8 ; R # Lo [25] SORA SOMPENG LETTER SAH..SORA SOMPENG LETTER MAE +110F0..110F9 ; R # Nd [10] SORA SOMPENG DIGIT ZERO..SORA SOMPENG DIGIT NINE +11100..11102 ; R # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA +11103..11126 ; R # Lo [36] CHAKMA LETTER AA..CHAKMA LETTER HAA +11127..1112B ; R # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU +1112C ; R # Mc CHAKMA VOWEL SIGN E +1112D..11134 ; R # Mn [8] CHAKMA VOWEL SIGN AI..CHAKMA MAAYYAA +11136..1113F ; R # Nd [10] CHAKMA DIGIT ZERO..CHAKMA DIGIT NINE +11140..11143 ; R # Po [4] CHAKMA SECTION MARK..CHAKMA QUESTION MARK +11150..11172 ; R # Lo [35] MAHAJANI LETTER A..MAHAJANI LETTER RRA +11173 ; R # Mn MAHAJANI SIGN NUKTA +11174..11175 ; R # Po [2] MAHAJANI ABBREVIATION SIGN..MAHAJANI SECTION MARK +11176 ; R # Lo MAHAJANI LIGATURE SHRI +11180..11181 ; R # Mn [2] SHARADA SIGN CANDRABINDU..SHARADA SIGN ANUSVARA +11182 ; R # Mc SHARADA SIGN VISARGA +11183..111B2 ; R # Lo [48] SHARADA LETTER A..SHARADA LETTER HA +111B3..111B5 ; R # Mc [3] SHARADA VOWEL SIGN AA..SHARADA VOWEL SIGN II +111B6..111BE ; R # Mn [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O +111BF..111C0 ; R # Mc [2] SHARADA VOWEL SIGN AU..SHARADA SIGN VIRAMA +111C1..111C4 ; R # Lo [4] SHARADA SIGN AVAGRAHA..SHARADA OM +111C5..111C9 ; R # Po [5] SHARADA DANDA..SHARADA SANDHI MARK +111CA..111CC ; R # Mn [3] SHARADA SIGN NUKTA..SHARADA EXTRA SHORT VOWEL MARK +111CD ; R # Po SHARADA SUTRA MARK +111D0..111D9 ; R # Nd [10] SHARADA DIGIT ZERO..SHARADA DIGIT NINE +111DA ; R # Lo SHARADA EKAM +111DB ; R # Po SHARADA SIGN SIDDHAM +111DC ; R # Lo SHARADA HEADSTROKE +111DD..111DF ; R # Po [3] SHARADA CONTINUATION SIGN..SHARADA SECTION MARK-2 +111E1..111F4 ; R # No [20] SINHALA ARCHAIC DIGIT ONE..SINHALA ARCHAIC NUMBER ONE THOUSAND +11200..11211 ; R # Lo [18] KHOJKI LETTER A..KHOJKI LETTER JJA +11213..1122B ; R # Lo [25] KHOJKI LETTER NYA..KHOJKI LETTER LLA +1122C..1122E ; R # Mc [3] KHOJKI VOWEL SIGN AA..KHOJKI VOWEL SIGN II +1122F..11231 ; R # Mn [3] KHOJKI VOWEL SIGN U..KHOJKI VOWEL SIGN AI +11232..11233 ; R # Mc [2] KHOJKI VOWEL SIGN O..KHOJKI VOWEL SIGN AU +11234 ; R # Mn KHOJKI SIGN ANUSVARA +11235 ; R # Mc KHOJKI SIGN VIRAMA +11236..11237 ; R # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA +11238..1123D ; R # Po [6] KHOJKI DANDA..KHOJKI ABBREVIATION SIGN +1123E ; R # Mn KHOJKI SIGN SUKUN +11280..11286 ; R # Lo [7] MULTANI LETTER A..MULTANI LETTER GA +11288 ; R # Lo MULTANI LETTER GHA +1128A..1128D ; R # Lo [4] MULTANI LETTER CA..MULTANI LETTER JJA +1128F..1129D ; R # Lo [15] MULTANI LETTER NYA..MULTANI LETTER BA +1129F..112A8 ; R # Lo [10] MULTANI LETTER BHA..MULTANI LETTER RHA +112A9 ; R # Po MULTANI SECTION MARK +112B0..112DE ; R # Lo [47] KHUDAWADI LETTER A..KHUDAWADI LETTER HA +112DF ; R # Mn KHUDAWADI SIGN ANUSVARA +112E0..112E2 ; R # Mc [3] KHUDAWADI VOWEL SIGN AA..KHUDAWADI VOWEL SIGN II +112E3..112EA ; R # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA +112F0..112F9 ; R # Nd [10] KHUDAWADI DIGIT ZERO..KHUDAWADI DIGIT NINE +11300..11301 ; R # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU +11302..11303 ; R # Mc [2] GRANTHA SIGN ANUSVARA..GRANTHA SIGN VISARGA +11305..1130C ; R # Lo [8] GRANTHA LETTER A..GRANTHA LETTER VOCALIC L +1130F..11310 ; R # Lo [2] GRANTHA LETTER EE..GRANTHA LETTER AI +11313..11328 ; R # Lo [22] GRANTHA LETTER OO..GRANTHA LETTER NA +1132A..11330 ; R # Lo [7] GRANTHA LETTER PA..GRANTHA LETTER RA +11332..11333 ; R # Lo [2] GRANTHA LETTER LA..GRANTHA LETTER LLA +11335..11339 ; R # Lo [5] GRANTHA LETTER VA..GRANTHA LETTER HA +1133C ; R # Mn GRANTHA SIGN NUKTA +1133D ; R # Lo GRANTHA SIGN AVAGRAHA +1133E..1133F ; R # Mc [2] GRANTHA VOWEL SIGN AA..GRANTHA VOWEL SIGN I +11340 ; R # Mn GRANTHA VOWEL SIGN II +11341..11344 ; R # Mc [4] GRANTHA VOWEL SIGN U..GRANTHA VOWEL SIGN VOCALIC RR +11347..11348 ; R # Mc [2] GRANTHA VOWEL SIGN EE..GRANTHA VOWEL SIGN AI +1134B..1134D ; R # Mc [3] GRANTHA VOWEL SIGN OO..GRANTHA SIGN VIRAMA +11350 ; R # Lo GRANTHA OM +11357 ; R # Mc GRANTHA AU LENGTH MARK +1135D..11361 ; R # Lo [5] GRANTHA SIGN PLUTA..GRANTHA LETTER VOCALIC LL +11362..11363 ; R # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL +11366..1136C ; R # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX +11370..11374 ; R # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +11400..11434 ; R # Lo [53] NEWA LETTER A..NEWA LETTER HA +11435..11437 ; R # Mc [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II +11438..1143F ; R # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI +11440..11441 ; R # Mc [2] NEWA VOWEL SIGN O..NEWA VOWEL SIGN AU +11442..11444 ; R # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA +11445 ; R # Mc NEWA SIGN VISARGA +11446 ; R # Mn NEWA SIGN NUKTA +11447..1144A ; R # Lo [4] NEWA SIGN AVAGRAHA..NEWA SIDDHI +1144B..1144F ; R # Po [5] NEWA DANDA..NEWA ABBREVIATION SIGN +11450..11459 ; R # Nd [10] NEWA DIGIT ZERO..NEWA DIGIT NINE +1145B ; R # Po NEWA PLACEHOLDER MARK +1145D ; R # Po NEWA INSERTION SIGN +11480..114AF ; R # Lo [48] TIRHUTA ANJI..TIRHUTA LETTER HA +114B0..114B2 ; R # Mc [3] TIRHUTA VOWEL SIGN AA..TIRHUTA VOWEL SIGN II +114B3..114B8 ; R # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL +114B9 ; R # Mc TIRHUTA VOWEL SIGN E +114BA ; R # Mn TIRHUTA VOWEL SIGN SHORT E +114BB..114BE ; R # Mc [4] TIRHUTA VOWEL SIGN AI..TIRHUTA VOWEL SIGN AU +114BF..114C0 ; R # Mn [2] TIRHUTA SIGN CANDRABINDU..TIRHUTA SIGN ANUSVARA +114C1 ; R # Mc TIRHUTA SIGN VISARGA +114C2..114C3 ; R # Mn [2] TIRHUTA SIGN VIRAMA..TIRHUTA SIGN NUKTA +114C4..114C5 ; R # Lo [2] TIRHUTA SIGN AVAGRAHA..TIRHUTA GVANG +114C6 ; R # Po TIRHUTA ABBREVIATION SIGN +114C7 ; R # Lo TIRHUTA OM +114D0..114D9 ; R # Nd [10] TIRHUTA DIGIT ZERO..TIRHUTA DIGIT NINE +11580..115AE ; U # Lo [47] SIDDHAM LETTER A..SIDDHAM LETTER HA +115AF..115B1 ; U # Mc [3] SIDDHAM VOWEL SIGN AA..SIDDHAM VOWEL SIGN II +115B2..115B5 ; U # Mn [4] SIDDHAM VOWEL SIGN U..SIDDHAM VOWEL SIGN VOCALIC RR +115B6..115B7 ; U # Cn [2] <reserved-115B6>..<reserved-115B7> +115B8..115BB ; U # Mc [4] SIDDHAM VOWEL SIGN E..SIDDHAM VOWEL SIGN AU +115BC..115BD ; U # Mn [2] SIDDHAM SIGN CANDRABINDU..SIDDHAM SIGN ANUSVARA +115BE ; U # Mc SIDDHAM SIGN VISARGA +115BF..115C0 ; U # Mn [2] SIDDHAM SIGN VIRAMA..SIDDHAM SIGN NUKTA +115C1..115D7 ; U # Po [23] SIDDHAM SIGN SIDDHAM..SIDDHAM SECTION MARK WITH CIRCLES AND FOUR ENCLOSURES +115D8..115DB ; U # Lo [4] SIDDHAM LETTER THREE-CIRCLE ALTERNATE I..SIDDHAM LETTER ALTERNATE U +115DC..115DD ; U # Mn [2] SIDDHAM VOWEL SIGN ALTERNATE U..SIDDHAM VOWEL SIGN ALTERNATE UU +115DE..115FF ; U # Cn [34] <reserved-115DE>..<reserved-115FF> +11600..1162F ; R # Lo [48] MODI LETTER A..MODI LETTER LLA +11630..11632 ; R # Mc [3] MODI VOWEL SIGN AA..MODI VOWEL SIGN II +11633..1163A ; R # Mn [8] MODI VOWEL SIGN U..MODI VOWEL SIGN AI +1163B..1163C ; R # Mc [2] MODI VOWEL SIGN O..MODI VOWEL SIGN AU +1163D ; R # Mn MODI SIGN ANUSVARA +1163E ; R # Mc MODI SIGN VISARGA +1163F..11640 ; R # Mn [2] MODI SIGN VIRAMA..MODI SIGN ARDHACANDRA +11641..11643 ; R # Po [3] MODI DANDA..MODI ABBREVIATION SIGN +11644 ; R # Lo MODI SIGN HUVA +11650..11659 ; R # Nd [10] MODI DIGIT ZERO..MODI DIGIT NINE +11660..1166C ; R # Po [13] MONGOLIAN BIRGA WITH ORNAMENT..MONGOLIAN TURNED SWIRL BIRGA WITH DOUBLE ORNAMENT +11680..116AA ; R # Lo [43] TAKRI LETTER A..TAKRI LETTER RRA +116AB ; R # Mn TAKRI SIGN ANUSVARA +116AC ; R # Mc TAKRI SIGN VISARGA +116AD ; R # Mn TAKRI VOWEL SIGN AA +116AE..116AF ; R # Mc [2] TAKRI VOWEL SIGN I..TAKRI VOWEL SIGN II +116B0..116B5 ; R # Mn [6] TAKRI VOWEL SIGN U..TAKRI VOWEL SIGN AU +116B6 ; R # Mc TAKRI SIGN VIRAMA +116B7 ; R # Mn TAKRI SIGN NUKTA +116C0..116C9 ; R # Nd [10] TAKRI DIGIT ZERO..TAKRI DIGIT NINE +11700..11719 ; R # Lo [26] AHOM LETTER KA..AHOM LETTER JHA +1171D..1171F ; R # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA +11720..11721 ; R # Mc [2] AHOM VOWEL SIGN A..AHOM VOWEL SIGN AA +11722..11725 ; R # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU +11726 ; R # Mc AHOM VOWEL SIGN E +11727..1172B ; R # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER +11730..11739 ; R # Nd [10] AHOM DIGIT ZERO..AHOM DIGIT NINE +1173A..1173B ; R # No [2] AHOM NUMBER TEN..AHOM NUMBER TWENTY +1173C..1173E ; R # Po [3] AHOM SIGN SMALL SECTION..AHOM SIGN RULAI +1173F ; R # So AHOM SYMBOL VI +118A0..118DF ; R # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO +118E0..118E9 ; R # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE +118EA..118F2 ; R # No [9] WARANG CITI NUMBER TEN..WARANG CITI NUMBER NINETY +118FF ; R # Lo WARANG CITI OM +11A00 ; U # Lo ZANABAZAR SQUARE LETTER A +11A01..11A06 ; U # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O +11A07..11A08 ; U # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU +11A09..11A0A ; U # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A0B..11A32 ; U # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA +11A33..11A38 ; U # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A39 ; U # Mc ZANABAZAR SQUARE SIGN VISARGA +11A3A ; U # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA +11A3B..11A3E ; U # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A3F..11A46 ; U # Po [8] ZANABAZAR SQUARE INITIAL HEAD MARK..ZANABAZAR SQUARE CLOSING DOUBLE-LINED HEAD MARK +11A47 ; U # Mn ZANABAZAR SQUARE SUBJOINER +11A48..11A4F ; U # Cn [8] <reserved-11A48>..<reserved-11A4F> +11A50 ; U # Lo SOYOMBO LETTER A +11A51..11A56 ; U # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A57..11A58 ; U # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU +11A59..11A5B ; U # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A5C..11A83 ; U # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA +11A84..11A85 ; U # Cn [2] <reserved-11A84>..<reserved-11A85> +11A86..11A89 ; U # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA +11A8A..11A96 ; U # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A97 ; U # Mc SOYOMBO SIGN VISARGA +11A98..11A99 ; U # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER +11A9A..11A9C ; U # Po [3] SOYOMBO MARK TSHEG..SOYOMBO MARK DOUBLE SHAD +11A9D ; U # Cn <reserved-11A9D> +11A9E..11AA2 ; U # Po [5] SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME..SOYOMBO TERMINAL MARK-2 +11AA3..11AAF ; U # Cn [13] <reserved-11AA3>..<reserved-11AAF> +11AC0..11AF8 ; R # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL +11C00..11C08 ; R # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L +11C0A..11C2E ; R # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA +11C2F ; R # Mc BHAIKSUKI VOWEL SIGN AA +11C30..11C36 ; R # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L +11C38..11C3D ; R # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA +11C3E ; R # Mc BHAIKSUKI SIGN VISARGA +11C3F ; R # Mn BHAIKSUKI SIGN VIRAMA +11C40 ; R # Lo BHAIKSUKI SIGN AVAGRAHA +11C41..11C45 ; R # Po [5] BHAIKSUKI DANDA..BHAIKSUKI GAP FILLER-2 +11C50..11C59 ; R # Nd [10] BHAIKSUKI DIGIT ZERO..BHAIKSUKI DIGIT NINE +11C5A..11C6C ; R # No [19] BHAIKSUKI NUMBER ONE..BHAIKSUKI HUNDREDS UNIT MARK +11C70..11C71 ; R # Po [2] MARCHEN HEAD MARK..MARCHEN MARK SHAD +11C72..11C8F ; R # Lo [30] MARCHEN LETTER KA..MARCHEN LETTER A +11C92..11CA7 ; R # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA +11CA9 ; R # Mc MARCHEN SUBJOINED LETTER YA +11CAA..11CB0 ; R # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA +11CB1 ; R # Mc MARCHEN VOWEL SIGN I +11CB2..11CB3 ; R # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E +11CB4 ; R # Mc MARCHEN VOWEL SIGN O +11CB5..11CB6 ; R # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D00..11D06 ; R # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E +11D08..11D09 ; R # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O +11D0B..11D30 ; R # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA +11D31..11D36 ; R # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; R # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; R # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45 ; R # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D46 ; R # Lo MASARAM GONDI REPHA +11D47 ; R # Mn MASARAM GONDI RA-KARA +11D50..11D59 ; R # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE +12000..12399 ; R # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U +12400..1246E ; R # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM +12470..12474 ; R # Po [5] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON +12480..12543 ; R # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU +13000..1342E ; U # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032 +1342F ; U # Cn <reserved-1342F> +14400..14646 ; U # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530 +14647..1467F ; U # Cn [57] <reserved-14647>..<reserved-1467F> +16800..16A38 ; R # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ +16A40..16A5E ; R # Lo [31] MRO LETTER TA..MRO LETTER TEK +16A60..16A69 ; R # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE +16A6E..16A6F ; R # Po [2] MRO DANDA..MRO DOUBLE DANDA +16AD0..16AED ; R # Lo [30] BASSA VAH LETTER ENNI..BASSA VAH LETTER I +16AF0..16AF4 ; R # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE +16AF5 ; R # Po BASSA VAH FULL STOP +16B00..16B2F ; R # Lo [48] PAHAWH HMONG VOWEL KEEB..PAHAWH HMONG CONSONANT CAU +16B30..16B36 ; R # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM +16B37..16B3B ; R # Po [5] PAHAWH HMONG SIGN VOS THOM..PAHAWH HMONG SIGN VOS FEEM +16B3C..16B3F ; R # So [4] PAHAWH HMONG SIGN XYEEM NTXIV..PAHAWH HMONG SIGN XYEEM FAIB +16B40..16B43 ; R # Lm [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM +16B44 ; R # Po PAHAWH HMONG SIGN XAUS +16B45 ; R # So PAHAWH HMONG SIGN CIM TSOV ROG +16B50..16B59 ; R # Nd [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE +16B5B..16B61 ; R # No [7] PAHAWH HMONG NUMBER TENS..PAHAWH HMONG NUMBER TRILLIONS +16B63..16B77 ; R # Lo [21] PAHAWH HMONG SIGN VOS LUB..PAHAWH HMONG SIGN CIM NRES TOS +16B7D..16B8F ; R # Lo [19] PAHAWH HMONG CLAN SIGN TSHEEJ..PAHAWH HMONG CLAN SIGN VWJ +16F00..16F44 ; R # Lo [69] MIAO LETTER PA..MIAO LETTER HHA +16F50 ; R # Lo MIAO LETTER NASALIZATION +16F51..16F7E ; R # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG +16F8F..16F92 ; R # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW +16F93..16F9F ; R # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 +16FE0..16FE1 ; U # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK +16FE2..16FFF ; U # Cn [30] <reserved-16FE2>..<reserved-16FFF> +17000..187EC ; U # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC +187ED..187FF ; U # Cn [19] <reserved-187ED>..<reserved-187FF> +18800..18AF2 ; U # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755 +18AF3..18AFF ; U # Cn [13] <reserved-18AF3>..<reserved-18AFF> +1B000..1B0FF ; U # Lo [256] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER RE-2 +1B100..1B11E ; U # Lo [31] HENTAIGANA LETTER RE-3..HENTAIGANA LETTER N-MU-MO-2 +1B11F..1B12F ; U # Cn [17] <reserved-1B11F>..<reserved-1B12F> +1B170..1B2FB ; U # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB +1B2FC..1B2FF ; U # Cn [4] <reserved-1B2FC>..<reserved-1B2FF> +1BC00..1BC6A ; R # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M +1BC70..1BC7C ; R # Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK +1BC80..1BC88 ; R # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL +1BC90..1BC99 ; R # Lo [10] DUPLOYAN AFFIX LOW ACUTE..DUPLOYAN AFFIX LOW ARROW +1BC9C ; R # So DUPLOYAN SIGN O WITH CROSS +1BC9D..1BC9E ; R # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK +1BC9F ; R # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP +1BCA0..1BCA3 ; R # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1D000..1D0F5 ; U # So [246] BYZANTINE MUSICAL SYMBOL PSILI..BYZANTINE MUSICAL SYMBOL GORGON NEO KATO +1D0F6..1D0FF ; U # Cn [10] <reserved-1D0F6>..<reserved-1D0FF> +1D100..1D126 ; U # So [39] MUSICAL SYMBOL SINGLE BARLINE..MUSICAL SYMBOL DRUM CLEF-2 +1D127..1D128 ; U # Cn [2] <reserved-1D127>..<reserved-1D128> +1D129..1D164 ; U # So [60] MUSICAL SYMBOL MULTIPLE MEASURE REST..MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE +1D165..1D166 ; U # Mc [2] MUSICAL SYMBOL COMBINING STEM..MUSICAL SYMBOL COMBINING SPRECHGESANG STEM +1D167..1D169 ; U # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 +1D16A..1D16C ; U # So [3] MUSICAL SYMBOL FINGERED TREMOLO-1..MUSICAL SYMBOL FINGERED TREMOLO-3 +1D16D..1D172 ; U # Mc [6] MUSICAL SYMBOL COMBINING AUGMENTATION DOT..MUSICAL SYMBOL COMBINING FLAG-5 +1D173..1D17A ; U # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE +1D17B..1D182 ; U # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE +1D183..1D184 ; U # So [2] MUSICAL SYMBOL ARPEGGIATO UP..MUSICAL SYMBOL ARPEGGIATO DOWN +1D185..1D18B ; U # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE +1D18C..1D1A9 ; U # So [30] MUSICAL SYMBOL RINFORZANDO..MUSICAL SYMBOL DEGREE SLASH +1D1AA..1D1AD ; U # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO +1D1AE..1D1E8 ; U # So [59] MUSICAL SYMBOL PEDAL MARK..MUSICAL SYMBOL KIEVAN FLAT SIGN +1D1E9..1D1FF ; U # Cn [23] <reserved-1D1E9>..<reserved-1D1FF> +1D200..1D241 ; R # So [66] GREEK VOCAL NOTATION SYMBOL-1..GREEK INSTRUMENTAL NOTATION SYMBOL-54 +1D242..1D244 ; R # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME +1D245 ; R # So GREEK MUSICAL LEIMMA +1D300..1D356 ; U # So [87] MONOGRAM FOR EARTH..TETRAGRAM FOR FOSTERING +1D357..1D35F ; U # Cn [9] <reserved-1D357>..<reserved-1D35F> +1D360..1D371 ; U # No [18] COUNTING ROD UNIT DIGIT ONE..COUNTING ROD TENS DIGIT NINE +1D372..1D37F ; U # Cn [14] <reserved-1D372>..<reserved-1D37F> +1D400..1D454 ; R # L& [85] MATHEMATICAL BOLD CAPITAL A..MATHEMATICAL ITALIC SMALL G +1D456..1D49C ; R # L& [71] MATHEMATICAL ITALIC SMALL I..MATHEMATICAL SCRIPT CAPITAL A +1D49E..1D49F ; R # Lu [2] MATHEMATICAL SCRIPT CAPITAL C..MATHEMATICAL SCRIPT CAPITAL D +1D4A2 ; R # Lu MATHEMATICAL SCRIPT CAPITAL G +1D4A5..1D4A6 ; R # Lu [2] MATHEMATICAL SCRIPT CAPITAL J..MATHEMATICAL SCRIPT CAPITAL K +1D4A9..1D4AC ; R # Lu [4] MATHEMATICAL SCRIPT CAPITAL N..MATHEMATICAL SCRIPT CAPITAL Q +1D4AE..1D4B9 ; R # L& [12] MATHEMATICAL SCRIPT CAPITAL S..MATHEMATICAL SCRIPT SMALL D +1D4BB ; R # Ll MATHEMATICAL SCRIPT SMALL F +1D4BD..1D4C3 ; R # Ll [7] MATHEMATICAL SCRIPT SMALL H..MATHEMATICAL SCRIPT SMALL N +1D4C5..1D505 ; R # L& [65] MATHEMATICAL SCRIPT SMALL P..MATHEMATICAL FRAKTUR CAPITAL B +1D507..1D50A ; R # Lu [4] MATHEMATICAL FRAKTUR CAPITAL D..MATHEMATICAL FRAKTUR CAPITAL G +1D50D..1D514 ; R # Lu [8] MATHEMATICAL FRAKTUR CAPITAL J..MATHEMATICAL FRAKTUR CAPITAL Q +1D516..1D51C ; R # Lu [7] MATHEMATICAL FRAKTUR CAPITAL S..MATHEMATICAL FRAKTUR CAPITAL Y +1D51E..1D539 ; R # L& [28] MATHEMATICAL FRAKTUR SMALL A..MATHEMATICAL DOUBLE-STRUCK CAPITAL B +1D53B..1D53E ; R # Lu [4] MATHEMATICAL DOUBLE-STRUCK CAPITAL D..MATHEMATICAL DOUBLE-STRUCK CAPITAL G +1D540..1D544 ; R # Lu [5] MATHEMATICAL DOUBLE-STRUCK CAPITAL I..MATHEMATICAL DOUBLE-STRUCK CAPITAL M +1D546 ; R # Lu MATHEMATICAL DOUBLE-STRUCK CAPITAL O +1D54A..1D550 ; R # Lu [7] MATHEMATICAL DOUBLE-STRUCK CAPITAL S..MATHEMATICAL DOUBLE-STRUCK CAPITAL Y +1D552..1D6A5 ; R # L& [340] MATHEMATICAL DOUBLE-STRUCK SMALL A..MATHEMATICAL ITALIC SMALL DOTLESS J +1D6A8..1D6C0 ; R # Lu [25] MATHEMATICAL BOLD CAPITAL ALPHA..MATHEMATICAL BOLD CAPITAL OMEGA +1D6C1 ; R # Sm MATHEMATICAL BOLD NABLA +1D6C2..1D6DA ; R # Ll [25] MATHEMATICAL BOLD SMALL ALPHA..MATHEMATICAL BOLD SMALL OMEGA +1D6DB ; R # Sm MATHEMATICAL BOLD PARTIAL DIFFERENTIAL +1D6DC..1D6FA ; R # L& [31] MATHEMATICAL BOLD EPSILON SYMBOL..MATHEMATICAL ITALIC CAPITAL OMEGA +1D6FB ; R # Sm MATHEMATICAL ITALIC NABLA +1D6FC..1D714 ; R # Ll [25] MATHEMATICAL ITALIC SMALL ALPHA..MATHEMATICAL ITALIC SMALL OMEGA +1D715 ; R # Sm MATHEMATICAL ITALIC PARTIAL DIFFERENTIAL +1D716..1D734 ; R # L& [31] MATHEMATICAL ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD ITALIC CAPITAL OMEGA +1D735 ; R # Sm MATHEMATICAL BOLD ITALIC NABLA +1D736..1D74E ; R # Ll [25] MATHEMATICAL BOLD ITALIC SMALL ALPHA..MATHEMATICAL BOLD ITALIC SMALL OMEGA +1D74F ; R # Sm MATHEMATICAL BOLD ITALIC PARTIAL DIFFERENTIAL +1D750..1D76E ; R # L& [31] MATHEMATICAL BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD CAPITAL OMEGA +1D76F ; R # Sm MATHEMATICAL SANS-SERIF BOLD NABLA +1D770..1D788 ; R # Ll [25] MATHEMATICAL SANS-SERIF BOLD SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD SMALL OMEGA +1D789 ; R # Sm MATHEMATICAL SANS-SERIF BOLD PARTIAL DIFFERENTIAL +1D78A..1D7A8 ; R # L& [31] MATHEMATICAL SANS-SERIF BOLD EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL OMEGA +1D7A9 ; R # Sm MATHEMATICAL SANS-SERIF BOLD ITALIC NABLA +1D7AA..1D7C2 ; R # Ll [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA +1D7C3 ; R # Sm MATHEMATICAL SANS-SERIF BOLD ITALIC PARTIAL DIFFERENTIAL +1D7C4..1D7CB ; R # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA +1D7CE..1D7FF ; R # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE +1D800..1D9FF ; U # So [512] SIGNWRITING HAND-FIST INDEX..SIGNWRITING HEAD +1DA00..1DA36 ; U # Mn [55] SIGNWRITING HEAD RIM..SIGNWRITING AIR SUCKING IN +1DA37..1DA3A ; U # So [4] SIGNWRITING AIR BLOW SMALL ROTATIONS..SIGNWRITING BREATH EXHALE +1DA3B..1DA6C ; U # Mn [50] SIGNWRITING MOUTH CLOSED NEUTRAL..SIGNWRITING EXCITEMENT +1DA6D..1DA74 ; U # So [8] SIGNWRITING SHOULDER HIP SPINE..SIGNWRITING TORSO-FLOORPLANE TWISTING +1DA75 ; U # Mn SIGNWRITING UPPER BODY TILTING FROM HIP JOINTS +1DA76..1DA83 ; U # So [14] SIGNWRITING LIMB COMBINATION..SIGNWRITING LOCATION DEPTH +1DA84 ; U # Mn SIGNWRITING LOCATION HEAD NECK +1DA85..1DA86 ; U # So [2] SIGNWRITING LOCATION TORSO..SIGNWRITING LOCATION LIMBS DIGITS +1DA87..1DA8B ; U # Po [5] SIGNWRITING COMMA..SIGNWRITING PARENTHESIS +1DA8C..1DA9A ; U # Cn [15] <reserved-1DA8C>..<reserved-1DA9A> +1DA9B..1DA9F ; U # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6 +1DAA0 ; U # Cn <reserved-1DAA0> +1DAA1..1DAAF ; U # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 +1E000..1E006 ; R # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE +1E008..1E018 ; R # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU +1E01B..1E021 ; R # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI +1E023..1E024 ; R # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS +1E026..1E02A ; R # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA +1E800..1E8C4 ; R # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON +1E8C7..1E8CF ; R # No [9] MENDE KIKAKUI DIGIT ONE..MENDE KIKAKUI DIGIT NINE +1E8D0..1E8D6 ; R # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS +1E900..1E943 ; R # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA +1E944..1E94A ; R # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA +1E950..1E959 ; R # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE +1E95E..1E95F ; R # Po [2] ADLAM INITIAL EXCLAMATION MARK..ADLAM INITIAL QUESTION MARK +1EE00..1EE03 ; R # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL +1EE05..1EE1F ; R # Lo [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF +1EE21..1EE22 ; R # Lo [2] ARABIC MATHEMATICAL INITIAL BEH..ARABIC MATHEMATICAL INITIAL JEEM +1EE24 ; R # Lo ARABIC MATHEMATICAL INITIAL HEH +1EE27 ; R # Lo ARABIC MATHEMATICAL INITIAL HAH +1EE29..1EE32 ; R # Lo [10] ARABIC MATHEMATICAL INITIAL YEH..ARABIC MATHEMATICAL INITIAL QAF +1EE34..1EE37 ; R # Lo [4] ARABIC MATHEMATICAL INITIAL SHEEN..ARABIC MATHEMATICAL INITIAL KHAH +1EE39 ; R # Lo ARABIC MATHEMATICAL INITIAL DAD +1EE3B ; R # Lo ARABIC MATHEMATICAL INITIAL GHAIN +1EE42 ; R # Lo ARABIC MATHEMATICAL TAILED JEEM +1EE47 ; R # Lo ARABIC MATHEMATICAL TAILED HAH +1EE49 ; R # Lo ARABIC MATHEMATICAL TAILED YEH +1EE4B ; R # Lo ARABIC MATHEMATICAL TAILED LAM +1EE4D..1EE4F ; R # Lo [3] ARABIC MATHEMATICAL TAILED NOON..ARABIC MATHEMATICAL TAILED AIN +1EE51..1EE52 ; R # Lo [2] ARABIC MATHEMATICAL TAILED SAD..ARABIC MATHEMATICAL TAILED QAF +1EE54 ; R # Lo ARABIC MATHEMATICAL TAILED SHEEN +1EE57 ; R # Lo ARABIC MATHEMATICAL TAILED KHAH +1EE59 ; R # Lo ARABIC MATHEMATICAL TAILED DAD +1EE5B ; R # Lo ARABIC MATHEMATICAL TAILED GHAIN +1EE5D ; R # Lo ARABIC MATHEMATICAL TAILED DOTLESS NOON +1EE5F ; R # Lo ARABIC MATHEMATICAL TAILED DOTLESS QAF +1EE61..1EE62 ; R # Lo [2] ARABIC MATHEMATICAL STRETCHED BEH..ARABIC MATHEMATICAL STRETCHED JEEM +1EE64 ; R # Lo ARABIC MATHEMATICAL STRETCHED HEH +1EE67..1EE6A ; R # Lo [4] ARABIC MATHEMATICAL STRETCHED HAH..ARABIC MATHEMATICAL STRETCHED KAF +1EE6C..1EE72 ; R # Lo [7] ARABIC MATHEMATICAL STRETCHED MEEM..ARABIC MATHEMATICAL STRETCHED QAF +1EE74..1EE77 ; R # Lo [4] ARABIC MATHEMATICAL STRETCHED SHEEN..ARABIC MATHEMATICAL STRETCHED KHAH +1EE79..1EE7C ; R # Lo [4] ARABIC MATHEMATICAL STRETCHED DAD..ARABIC MATHEMATICAL STRETCHED DOTLESS BEH +1EE7E ; R # Lo ARABIC MATHEMATICAL STRETCHED DOTLESS FEH +1EE80..1EE89 ; R # Lo [10] ARABIC MATHEMATICAL LOOPED ALEF..ARABIC MATHEMATICAL LOOPED YEH +1EE8B..1EE9B ; R # Lo [17] ARABIC MATHEMATICAL LOOPED LAM..ARABIC MATHEMATICAL LOOPED GHAIN +1EEA1..1EEA3 ; R # Lo [3] ARABIC MATHEMATICAL DOUBLE-STRUCK BEH..ARABIC MATHEMATICAL DOUBLE-STRUCK DAL +1EEA5..1EEA9 ; R # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH +1EEAB..1EEBB ; R # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN +1EEF0..1EEF1 ; R # Sm [2] ARABIC MATHEMATICAL OPERATOR MEEM WITH HAH WITH TATWEEL..ARABIC MATHEMATICAL OPERATOR HAH WITH DAL +1F000..1F02B ; U # So [44] MAHJONG TILE EAST WIND..MAHJONG TILE BACK +1F02C..1F02F ; U # Cn [4] <reserved-1F02C>..<reserved-1F02F> +1F030..1F093 ; U # So [100] DOMINO TILE HORIZONTAL BACK..DOMINO TILE VERTICAL-06-06 +1F094..1F09F ; U # Cn [12] <reserved-1F094>..<reserved-1F09F> +1F0A0..1F0AE ; U # So [15] PLAYING CARD BACK..PLAYING CARD KING OF SPADES +1F0AF..1F0B0 ; U # Cn [2] <reserved-1F0AF>..<reserved-1F0B0> +1F0B1..1F0BF ; U # So [15] PLAYING CARD ACE OF HEARTS..PLAYING CARD RED JOKER +1F0C0 ; U # Cn <reserved-1F0C0> +1F0C1..1F0CF ; U # So [15] PLAYING CARD ACE OF DIAMONDS..PLAYING CARD BLACK JOKER +1F0D0 ; U # Cn <reserved-1F0D0> +1F0D1..1F0F5 ; U # So [37] PLAYING CARD ACE OF CLUBS..PLAYING CARD TRUMP-21 +1F0F6..1F0FF ; U # Cn [10] <reserved-1F0F6>..<reserved-1F0FF> +1F100..1F10C ; U # No [13] DIGIT ZERO FULL STOP..DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ZERO +1F10D..1F10F ; U # Cn [3] <reserved-1F10D>..<reserved-1F10F> +1F110..1F12E ; U # So [31] PARENTHESIZED LATIN CAPITAL LETTER A..CIRCLED WZ +1F12F ; U # Cn <reserved-1F12F> +1F130..1F16B ; U # So [60] SQUARED LATIN CAPITAL LETTER A..RAISED MD SIGN +1F16C..1F16F ; U # Cn [4] <reserved-1F16C>..<reserved-1F16F> +1F170..1F1AC ; U # So [61] NEGATIVE SQUARED LATIN CAPITAL LETTER A..SQUARED VOD +1F1AD..1F1E5 ; U # Cn [57] <reserved-1F1AD>..<reserved-1F1E5> +1F1E6..1F1FF ; U # So [26] REGIONAL INDICATOR SYMBOL LETTER A..REGIONAL INDICATOR SYMBOL LETTER Z +1F200..1F201 ; Tu # So [2] SQUARE HIRAGANA HOKA..SQUARED KATAKANA KOKO +1F202 ; U # So SQUARED KATAKANA SA +1F203..1F20F ; U # Cn [13] <reserved-1F203>..<reserved-1F20F> +1F210..1F23B ; U # So [44] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-914D +1F23C..1F23F ; U # Cn [4] <reserved-1F23C>..<reserved-1F23F> +1F240..1F248 ; U # So [9] TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C..TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557 +1F249..1F24F ; U # Cn [7] <reserved-1F249>..<reserved-1F24F> +1F250..1F251 ; U # So [2] CIRCLED IDEOGRAPH ADVANTAGE..CIRCLED IDEOGRAPH ACCEPT +1F252..1F25F ; U # Cn [14] <reserved-1F252>..<reserved-1F25F> +1F260..1F265 ; U # So [6] ROUNDED SYMBOL FOR FU..ROUNDED SYMBOL FOR CAI +1F266..1F2FF ; U # Cn [154] <reserved-1F266>..<reserved-1F2FF> +1F300..1F3FA ; U # So [251] CYCLONE..AMPHORA +1F3FB..1F3FF ; U # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6 +1F400..1F5FF ; U # So [512] RAT..MOYAI +1F600..1F64F ; U # So [80] GRINNING FACE..PERSON WITH FOLDED HANDS +1F650..1F67F ; U # So [48] NORTH WEST POINTING LEAF..REVERSE CHECKER BOARD +1F680..1F6D4 ; U # So [85] ROCKET..PAGODA +1F6D5..1F6DF ; U # Cn [11] <reserved-1F6D5>..<reserved-1F6DF> +1F6E0..1F6EC ; U # So [13] HAMMER AND WRENCH..AIRPLANE ARRIVING +1F6ED..1F6EF ; U # Cn [3] <reserved-1F6ED>..<reserved-1F6EF> +1F6F0..1F6F8 ; U # So [9] SATELLITE..FLYING SAUCER +1F6F9..1F6FF ; U # Cn [7] <reserved-1F6F9>..<reserved-1F6FF> +1F700..1F773 ; U # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE +1F774..1F77F ; U # Cn [12] <reserved-1F774>..<reserved-1F77F> +1F780..1F7D4 ; U # So [85] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..HEAVY TWELVE POINTED PINWHEEL STAR +1F7D5..1F7FF ; U # Cn [43] <reserved-1F7D5>..<reserved-1F7FF> +1F800..1F80B ; R # So [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD +1F810..1F847 ; R # So [56] LEFTWARDS ARROW WITH SMALL EQUILATERAL ARROWHEAD..DOWNWARDS HEAVY ARROW +1F850..1F859 ; R # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW +1F860..1F887 ; R # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW +1F890..1F8AD ; R # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS +1F900..1F90B ; U # So [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT +1F90C..1F90F ; U # Cn [4] <reserved-1F90C>..<reserved-1F90F> +1F910..1F93E ; U # So [47] ZIPPER-MOUTH FACE..HANDBALL +1F93F ; U # Cn <reserved-1F93F> +1F940..1F94C ; U # So [13] WILTED FLOWER..CURLING STONE +1F94D..1F94F ; U # Cn [3] <reserved-1F94D>..<reserved-1F94F> +1F950..1F96B ; U # So [28] CROISSANT..CANNED FOOD +1F96C..1F97F ; U # Cn [20] <reserved-1F96C>..<reserved-1F97F> +1F980..1F997 ; U # So [24] CRAB..CRICKET +1F998..1F9BF ; U # Cn [40] <reserved-1F998>..<reserved-1F9BF> +1F9C0 ; U # So CHEESE WEDGE +1F9C1..1F9CF ; U # Cn [15] <reserved-1F9C1>..<reserved-1F9CF> +1F9D0..1F9E6 ; U # So [23] FACE WITH MONOCLE..SOCKS +1F9E7..1F9FF ; U # Cn [25] <reserved-1F9E7>..<reserved-1F9FF> +20000..2A6D6 ; U # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6 +2A6D7..2A6FF ; U # Cn [41] <reserved-2A6D7>..<reserved-2A6FF> +2A700..2B734 ; U # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 +2B735..2B73F ; U # Cn [11] <reserved-2B735>..<reserved-2B73F> +2B740..2B81D ; U # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D +2B81E..2B81F ; U # Cn [2] <reserved-2B81E>..<reserved-2B81F> +2B820..2CEA1 ; U # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 +2CEA2..2CEAF ; U # Cn [14] <reserved-2CEA2>..<reserved-2CEAF> +2CEB0..2EBE0 ; U # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 +2EBE1..2F7FF ; U # Cn [3103] <reserved-2EBE1>..<reserved-2F7FF> +2F800..2FA1D ; U # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D +2FA1E..2FFFD ; U # Cn [1504] <reserved-2FA1E>..<reserved-2FFFD> +30000..3FFFD ; U # Cn [65534] <reserved-30000>..<reserved-3FFFD> +E0001 ; R # Cf LANGUAGE TAG +E0020..E007F ; R # Cf [96] TAG SPACE..CANCEL TAG +E0100..E01EF ; R # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 +F0000..FFFFD ; U # Co [65534] <private-use-F0000>..<private-use-FFFFD> +100000..10FFFD ; U # Co [65534] <private-use-100000>..<private-use-10FFFD> + +# EOF diff --git a/lib/unicore/auxiliary/GCBTest.txt b/lib/unicore/auxiliary/GCBTest.txt index 4bb4b1369b..d7d8f90de0 100644 --- a/lib/unicore/auxiliary/GCBTest.txt +++ b/lib/unicore/auxiliary/GCBTest.txt @@ -1,23 +1,24 @@ -# GraphemeBreakTest-9.0.0.txt -# Date: 2016-06-02, 18:28:17 GMT -# © 2016 Unicode®, Inc. +# GraphemeBreakTest-10.0.0.txt +# Date: 2017-04-14, 05:40:29 GMT +# © 2017 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database # For documentation, see http://www.unicode.org/reports/tr44/ # -# Default Grapheme Break Test +# Default Grapheme_Cluster_Break Test # # Format: -# <string> (# <comment>)? -# <string> contains hex Unicode code points, with -# ÷ wherever there is a break opportunity, and +# <string> (# <comment>)? +# <string> contains hex Unicode code points, with +# ÷ wherever there is a break opportunity, and # × wherever there is not. # <comment> the format can change, but currently it shows: # - the sample character name # - (x) the Grapheme_Cluster_Break property value for the sample character -# - [x] the rule that determines whether there is a break or not +# - [x] the rule that determines whether there is a break or not, +# as listed in the Rules section of GraphemeBreakTest.html # # These samples may be extended or changed in the future. # @@ -53,8 +54,8 @@ ÷ 0020 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 0020 × 200D ÷ # ÷ [0.2] SPACE (Other) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] ÷ 0020 × 0308 × 200D ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] -÷ 0020 ÷ 2764 ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 0020 × 0308 ÷ 2764 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 0020 ÷ 2640 ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 0020 × 0308 ÷ 2640 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 0020 ÷ 1F466 ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0020 × 0308 ÷ 1F466 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0020 ÷ 0378 ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] @@ -93,8 +94,8 @@ ÷ 000D ÷ 0308 ÷ 1F3FB ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 000D ÷ 200D ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] ÷ 000D ÷ 0308 × 200D ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] -÷ 000D ÷ 2764 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 000D ÷ 0308 ÷ 2764 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 000D ÷ 2640 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 000D ÷ 0308 ÷ 2640 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 000D ÷ 1F466 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] BOY (EBG) ÷ [0.3] ÷ 000D ÷ 0308 ÷ 1F466 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 000D ÷ 0378 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] <reserved-0378> (Other) ÷ [0.3] @@ -133,8 +134,8 @@ ÷ 000A ÷ 0308 ÷ 1F3FB ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 000A ÷ 200D ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] ÷ 000A ÷ 0308 × 200D ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] -÷ 000A ÷ 2764 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 000A ÷ 0308 ÷ 2764 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 000A ÷ 2640 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 000A ÷ 0308 ÷ 2640 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 000A ÷ 1F466 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] BOY (EBG) ÷ [0.3] ÷ 000A ÷ 0308 ÷ 1F466 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 000A ÷ 0378 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] <reserved-0378> (Other) ÷ [0.3] @@ -173,8 +174,8 @@ ÷ 0001 ÷ 0308 ÷ 1F3FB ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 0001 ÷ 200D ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] ÷ 0001 ÷ 0308 × 200D ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] -÷ 0001 ÷ 2764 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 0001 ÷ 0308 ÷ 2764 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 0001 ÷ 2640 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 0001 ÷ 0308 ÷ 2640 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 0001 ÷ 1F466 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] BOY (EBG) ÷ [0.3] ÷ 0001 ÷ 0308 ÷ 1F466 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0001 ÷ 0378 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] <reserved-0378> (Other) ÷ [0.3] @@ -213,8 +214,8 @@ ÷ 0300 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 0300 × 200D ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] ÷ 0300 × 0308 × 200D ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] -÷ 0300 ÷ 2764 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 0300 × 0308 ÷ 2764 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 0300 ÷ 2640 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 0300 × 0308 ÷ 2640 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 0300 ÷ 1F466 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0300 × 0308 ÷ 1F466 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0300 ÷ 0378 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] @@ -253,8 +254,8 @@ ÷ 0600 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 0600 × 200D ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] ÷ 0600 × 0308 × 200D ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] -÷ 0600 × 2764 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 0600 × 0308 ÷ 2764 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 0600 × 2640 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 0600 × 0308 ÷ 2640 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 0600 × 1F466 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] BOY (EBG) ÷ [0.3] ÷ 0600 × 0308 ÷ 1F466 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0600 × 0378 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] <reserved-0378> (Other) ÷ [0.3] @@ -293,8 +294,8 @@ ÷ 0903 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 0903 × 200D ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] ÷ 0903 × 0308 × 200D ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] -÷ 0903 ÷ 2764 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 0903 × 0308 ÷ 2764 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 0903 ÷ 2640 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 0903 × 0308 ÷ 2640 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 0903 ÷ 1F466 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0903 × 0308 ÷ 1F466 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0903 ÷ 0378 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] @@ -333,8 +334,8 @@ ÷ 1100 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 1100 × 200D ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] ÷ 1100 × 0308 × 200D ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] -÷ 1100 ÷ 2764 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 1100 × 0308 ÷ 2764 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 1100 ÷ 2640 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 1100 × 0308 ÷ 2640 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 1100 ÷ 1F466 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 1100 × 0308 ÷ 1F466 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 1100 ÷ 0378 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] @@ -373,8 +374,8 @@ ÷ 1160 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 1160 × 200D ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] ÷ 1160 × 0308 × 200D ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] -÷ 1160 ÷ 2764 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 1160 × 0308 ÷ 2764 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 1160 ÷ 2640 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 1160 × 0308 ÷ 2640 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 1160 ÷ 1F466 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 1160 × 0308 ÷ 1F466 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 1160 ÷ 0378 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] @@ -413,8 +414,8 @@ ÷ 11A8 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 11A8 × 200D ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] ÷ 11A8 × 0308 × 200D ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] -÷ 11A8 ÷ 2764 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 11A8 × 0308 ÷ 2764 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 11A8 ÷ 2640 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 11A8 × 0308 ÷ 2640 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 11A8 ÷ 1F466 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 11A8 × 0308 ÷ 1F466 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 11A8 ÷ 0378 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] @@ -453,8 +454,8 @@ ÷ AC00 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ AC00 × 200D ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] ÷ AC00 × 0308 × 200D ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] -÷ AC00 ÷ 2764 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ AC00 × 0308 ÷ 2764 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ AC00 ÷ 2640 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ AC00 × 0308 ÷ 2640 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ AC00 ÷ 1F466 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ AC00 × 0308 ÷ 1F466 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ AC00 ÷ 0378 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] @@ -493,8 +494,8 @@ ÷ AC01 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ AC01 × 200D ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] ÷ AC01 × 0308 × 200D ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] -÷ AC01 ÷ 2764 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ AC01 × 0308 ÷ 2764 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ AC01 ÷ 2640 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ AC01 × 0308 ÷ 2640 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ AC01 ÷ 1F466 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ AC01 × 0308 ÷ 1F466 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ AC01 ÷ 0378 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] @@ -533,8 +534,8 @@ ÷ 1F1E6 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 1F1E6 × 200D ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] ÷ 1F1E6 × 0308 × 200D ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] -÷ 1F1E6 ÷ 2764 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 1F1E6 × 0308 ÷ 2764 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 1F1E6 ÷ 2640 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 1F1E6 × 0308 ÷ 2640 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 1F1E6 ÷ 1F466 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 1F1E6 × 0308 ÷ 1F466 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 1F1E6 ÷ 0378 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] @@ -573,8 +574,8 @@ ÷ 261D × 0308 × 1F3FB ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) × [10.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 261D × 200D ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] ÷ 261D × 0308 × 200D ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] -÷ 261D ÷ 2764 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 261D × 0308 ÷ 2764 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 261D ÷ 2640 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 261D × 0308 ÷ 2640 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 261D ÷ 1F466 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 261D × 0308 ÷ 1F466 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 261D ÷ 0378 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] @@ -613,8 +614,8 @@ ÷ 1F3FB × 0308 ÷ 1F3FB ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 1F3FB × 200D ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] ÷ 1F3FB × 0308 × 200D ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] -÷ 1F3FB ÷ 2764 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 1F3FB × 0308 ÷ 2764 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 1F3FB ÷ 2640 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 1F3FB × 0308 ÷ 2640 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 1F3FB ÷ 1F466 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 1F3FB × 0308 ÷ 1F466 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 1F3FB ÷ 0378 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] @@ -653,54 +654,54 @@ ÷ 200D × 0308 ÷ 1F3FB ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 200D × 200D ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] ÷ 200D × 0308 × 200D ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] -÷ 200D × 2764 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [11.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 200D × 0308 ÷ 2764 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 200D × 2640 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [11.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 200D × 0308 ÷ 2640 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 200D × 1F466 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [11.0] BOY (EBG) ÷ [0.3] ÷ 200D × 0308 ÷ 1F466 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 200D ÷ 0378 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] ÷ 200D × 0308 ÷ 0378 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] ÷ 200D ÷ D800 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3] ÷ 200D × 0308 ÷ D800 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3] -÷ 2764 ÷ 0020 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] SPACE (Other) ÷ [0.3] -÷ 2764 × 0308 ÷ 0020 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3] -÷ 2764 ÷ 000D ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] -÷ 2764 × 0308 ÷ 000D ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] -÷ 2764 ÷ 000A ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3] -÷ 2764 × 0308 ÷ 000A ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3] -÷ 2764 ÷ 0001 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3] -÷ 2764 × 0308 ÷ 0001 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3] -÷ 2764 × 0300 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] -÷ 2764 × 0308 × 0300 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] -÷ 2764 ÷ 0600 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] -÷ 2764 × 0308 ÷ 0600 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] -÷ 2764 × 0903 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] -÷ 2764 × 0308 × 0903 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] -÷ 2764 ÷ 1100 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3] -÷ 2764 × 0308 ÷ 1100 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3] -÷ 2764 ÷ 1160 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3] -÷ 2764 × 0308 ÷ 1160 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3] -÷ 2764 ÷ 11A8 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3] -÷ 2764 × 0308 ÷ 11A8 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3] -÷ 2764 ÷ AC00 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3] -÷ 2764 × 0308 ÷ AC00 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3] -÷ 2764 ÷ AC01 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] -÷ 2764 × 0308 ÷ AC01 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] -÷ 2764 ÷ 1F1E6 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] -÷ 2764 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] -÷ 2764 ÷ 261D ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] -÷ 2764 × 0308 ÷ 261D ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] -÷ 2764 ÷ 1F3FB ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] -÷ 2764 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] -÷ 2764 × 200D ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] -÷ 2764 × 0308 × 200D ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] -÷ 2764 ÷ 2764 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 2764 × 0308 ÷ 2764 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 2764 ÷ 1F466 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] BOY (EBG) ÷ [0.3] -÷ 2764 × 0308 ÷ 1F466 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] -÷ 2764 ÷ 0378 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] -÷ 2764 × 0308 ÷ 0378 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] -÷ 2764 ÷ D800 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3] -÷ 2764 × 0308 ÷ D800 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3] +÷ 2640 ÷ 0020 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] SPACE (Other) ÷ [0.3] +÷ 2640 × 0308 ÷ 0020 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3] +÷ 2640 ÷ 000D ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 2640 × 0308 ÷ 000D ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 2640 ÷ 000A ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 2640 × 0308 ÷ 000A ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 2640 ÷ 0001 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3] +÷ 2640 × 0308 ÷ 0001 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3] +÷ 2640 × 0300 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] +÷ 2640 × 0308 × 0300 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] +÷ 2640 ÷ 0600 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] +÷ 2640 × 0308 ÷ 0600 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] +÷ 2640 × 0903 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] +÷ 2640 × 0308 × 0903 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] +÷ 2640 ÷ 1100 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3] +÷ 2640 × 0308 ÷ 1100 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3] +÷ 2640 ÷ 1160 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3] +÷ 2640 × 0308 ÷ 1160 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3] +÷ 2640 ÷ 11A8 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3] +÷ 2640 × 0308 ÷ 11A8 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3] +÷ 2640 ÷ AC00 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3] +÷ 2640 × 0308 ÷ AC00 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3] +÷ 2640 ÷ AC01 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] +÷ 2640 × 0308 ÷ AC01 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] +÷ 2640 ÷ 1F1E6 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ 2640 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ 2640 ÷ 261D ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ 2640 × 0308 ÷ 261D ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ 2640 ÷ 1F3FB ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ 2640 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ 2640 × 200D ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ 2640 × 0308 × 200D ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ 2640 ÷ 2640 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 2640 × 0308 ÷ 2640 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 2640 ÷ 1F466 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] BOY (EBG) ÷ [0.3] +÷ 2640 × 0308 ÷ 1F466 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] +÷ 2640 ÷ 0378 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] +÷ 2640 × 0308 ÷ 0378 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] +÷ 2640 ÷ D800 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3] +÷ 2640 × 0308 ÷ D800 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3] ÷ 1F466 ÷ 0020 ÷ # ÷ [0.2] BOY (EBG) ÷ [999.0] SPACE (Other) ÷ [0.3] ÷ 1F466 × 0308 ÷ 0020 ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3] ÷ 1F466 ÷ 000D ÷ # ÷ [0.2] BOY (EBG) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] @@ -733,8 +734,8 @@ ÷ 1F466 × 0308 × 1F3FB ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) × [10.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 1F466 × 200D ÷ # ÷ [0.2] BOY (EBG) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] ÷ 1F466 × 0308 × 200D ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] -÷ 1F466 ÷ 2764 ÷ # ÷ [0.2] BOY (EBG) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 1F466 × 0308 ÷ 2764 ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 1F466 ÷ 2640 ÷ # ÷ [0.2] BOY (EBG) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 1F466 × 0308 ÷ 2640 ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 1F466 ÷ 1F466 ÷ # ÷ [0.2] BOY (EBG) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 1F466 × 0308 ÷ 1F466 ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 1F466 ÷ 0378 ÷ # ÷ [0.2] BOY (EBG) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] @@ -773,8 +774,8 @@ ÷ 0378 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 0378 × 200D ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] ÷ 0378 × 0308 × 200D ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] -÷ 0378 ÷ 2764 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 0378 × 0308 ÷ 2764 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 0378 ÷ 2640 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 0378 × 0308 ÷ 2640 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 0378 ÷ 1F466 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0378 × 0308 ÷ 1F466 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0378 ÷ 0378 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] @@ -813,8 +814,8 @@ ÷ D800 ÷ 0308 ÷ 1F3FB ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ D800 ÷ 200D ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] ÷ D800 ÷ 0308 × 200D ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] -÷ D800 ÷ 2764 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ D800 ÷ 0308 ÷ 2764 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ D800 ÷ 2640 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ D800 ÷ 0308 ÷ 2640 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ D800 ÷ 1F466 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] BOY (EBG) ÷ [0.3] ÷ D800 ÷ 0308 ÷ 1F466 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ D800 ÷ 0378 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] <reserved-0378> (Other) ÷ [0.3] @@ -840,7 +841,7 @@ ÷ 261D × 1F3FB ÷ 261D ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [10.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] ÷ 1F466 × 1F3FB ÷ # ÷ [0.2] BOY (EBG) × [10.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 200D × 1F466 × 1F3FB ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [11.0] BOY (EBG) × [10.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] -÷ 200D × 2764 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [11.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 200D × 2640 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [11.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 200D × 1F466 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [11.0] BOY (EBG) ÷ [0.3] ÷ 1F466 ÷ 1F466 ÷ # ÷ [0.2] BOY (EBG) ÷ [999.0] BOY (EBG) ÷ [0.3] # diff --git a/lib/unicore/auxiliary/GraphemeBreakProperty.txt b/lib/unicore/auxiliary/GraphemeBreakProperty.txt index c5e94a3762..32bb12e47e 100644 --- a/lib/unicore/auxiliary/GraphemeBreakProperty.txt +++ b/lib/unicore/auxiliary/GraphemeBreakProperty.txt @@ -1,6 +1,6 @@ -# GraphemeBreakProperty-9.0.0.txt -# Date: 2016-06-03, 22:23:55 GMT -# © 2016 Unicode®, Inc. +# GraphemeBreakProperty-10.0.0.txt +# Date: 2017-03-12, 07:03:41 GMT +# © 2017 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html # @@ -25,8 +25,11 @@ 0D4E ; Prepend # Lo MALAYALAM LETTER DOT REPH 110BD ; Prepend # Cf KAITHI NUMBER SIGN 111C2..111C3 ; Prepend # Lo [2] SHARADA SIGN JIHVAMULIYA..SHARADA SIGN UPADHMANIYA +11A3A ; Prepend # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA +11A86..11A89 ; Prepend # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA +11D46 ; Prepend # Lo MASARAM GONDI REPHA -# Total code points: 13 +# Total code points: 19 # ================================================ @@ -126,6 +129,7 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF> 0AC7..0AC8 ; Extend # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI 0ACD ; Extend # Mn GUJARATI SIGN VIRAMA 0AE2..0AE3 ; Extend # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0AFA..0AFF ; Extend # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE 0B01 ; Extend # Mn ORIYA SIGN CANDRABINDU 0B3C ; Extend # Mn ORIYA SIGN NUKTA 0B3E ; Extend # Mc ORIYA VOWEL SIGN AA @@ -154,7 +158,8 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF> 0CCC..0CCD ; Extend # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA 0CD5..0CD6 ; Extend # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK 0CE2..0CE3 ; Extend # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL -0D01 ; Extend # Mn MALAYALAM SIGN CANDRABINDU +0D00..0D01 ; Extend # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU +0D3B..0D3C ; Extend # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA 0D3E ; Extend # Mc MALAYALAM VOWEL SIGN AA 0D41..0D44 ; Extend # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR 0D4D ; Extend # Mn MALAYALAM SIGN VIRAMA @@ -243,7 +248,7 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF> 1CED ; Extend # Mn VEDIC SIGN TIRYAK 1CF4 ; Extend # Mn VEDIC TONE CANDRA ABOVE 1CF8..1CF9 ; Extend # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE -1DC0..1DF5 ; Extend # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE +1DC0..1DF9 ; Extend # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW 1DFB..1DFF ; Extend # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 200C ; Extend # Cf ZERO WIDTH NON-JOINER 20D0..20DC ; Extend # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE @@ -353,6 +358,15 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 1171D..1171F ; Extend # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA 11722..11725 ; Extend # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU 11727..1172B ; Extend # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER +11A01..11A06 ; Extend # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O +11A09..11A0A ; Extend # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A33..11A38 ; Extend # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A3B..11A3E ; Extend # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A47 ; Extend # Mn ZANABAZAR SQUARE SUBJOINER +11A51..11A56 ; Extend # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A59..11A5B ; Extend # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A8A..11A96 ; Extend # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A98..11A99 ; Extend # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER 11C30..11C36 ; Extend # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L 11C38..11C3D ; Extend # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA 11C3F ; Extend # Mn BHAIKSUKI SIGN VIRAMA @@ -360,6 +374,11 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 11CAA..11CB0 ; Extend # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA 11CB2..11CB3 ; Extend # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E 11CB5..11CB6 ; Extend # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D31..11D36 ; Extend # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; Extend # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; Extend # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45 ; Extend # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D47 ; Extend # Mn MASARAM GONDI RA-KARA 16AF0..16AF4 ; Extend # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; Extend # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM 16F8F..16F92 ; Extend # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW @@ -387,7 +406,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 1828 +# Total code points: 1901 # ================================================ @@ -472,6 +491,7 @@ E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 1C34..1C35 ; SpacingMark # Mc [2] LEPCHA CONSONANT SIGN NYIN-DO..LEPCHA CONSONANT SIGN KANG 1CE1 ; SpacingMark # Mc VEDIC TONE ATHARVAVEDIC INDEPENDENT SVARITA 1CF2..1CF3 ; SpacingMark # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA +1CF7 ; SpacingMark # Mc VEDIC SIGN ATIKRAMA A823..A824 ; SpacingMark # Mc [2] SYLOTI NAGRI VOWEL SIGN A..SYLOTI NAGRI VOWEL SIGN I A827 ; SpacingMark # Mc SYLOTI NAGRI VOWEL SIGN OO A880..A881 ; SpacingMark # Mc [2] SAURASHTRA SIGN ANUSVARA..SAURASHTRA SIGN VISARGA @@ -529,6 +549,10 @@ ABEC ; SpacingMark # Mc MEETEI MAYEK LUM IYEK 116B6 ; SpacingMark # Mc TAKRI SIGN VIRAMA 11720..11721 ; SpacingMark # Mc [2] AHOM VOWEL SIGN A..AHOM VOWEL SIGN AA 11726 ; SpacingMark # Mc AHOM VOWEL SIGN E +11A07..11A08 ; SpacingMark # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU +11A39 ; SpacingMark # Mc ZANABAZAR SQUARE SIGN VISARGA +11A57..11A58 ; SpacingMark # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU +11A97 ; SpacingMark # Mc SOYOMBO SIGN VISARGA 11C2F ; SpacingMark # Mc BHAIKSUKI VOWEL SIGN AA 11C3E ; SpacingMark # Mc BHAIKSUKI SIGN VISARGA 11CA9 ; SpacingMark # Mc MARCHEN SUBJOINED LETTER YA @@ -538,7 +562,7 @@ ABEC ; SpacingMark # Mc MEETEI MAYEK LUM IYEK 1D166 ; SpacingMark # Mc MUSICAL SYMBOL COMBINING SPRECHGESANG STEM 1D16D ; SpacingMark # Mc MUSICAL SYMBOL COMBINING AUGMENTATION DOT -# Total code points: 341 +# Total code points: 348 # ================================================ @@ -1375,8 +1399,9 @@ D789..D7A3 ; LVT # Lo [27] HANGUL SYLLABLE HIG..HANGUL SYLLABLE HIH 26F9 ; E_Base # So PERSON WITH BALL 270A..270D ; E_Base # So [4] RAISED FIST..WRITING HAND 1F385 ; E_Base # So FATHER CHRISTMAS -1F3C3..1F3C4 ; E_Base # So [2] RUNNER..SURFER -1F3CA..1F3CB ; E_Base # So [2] SWIMMER..WEIGHT LIFTER +1F3C2..1F3C4 ; E_Base # So [3] SNOWBOARDER..SURFER +1F3C7 ; E_Base # So HORSE RACING +1F3CA..1F3CC ; E_Base # So [3] SWIMMER..GOLFER 1F442..1F443 ; E_Base # So [2] EAR..NOSE 1F446..1F450 ; E_Base # So [11] WHITE UP POINTING BACKHAND INDEX..OPEN HANDS SIGN 1F46E ; E_Base # So POLICE OFFICER @@ -1385,7 +1410,7 @@ D789..D7A3 ; LVT # Lo [27] HANGUL SYLLABLE HIG..HANGUL SYLLABLE HIH 1F481..1F483 ; E_Base # So [3] INFORMATION DESK PERSON..DANCER 1F485..1F487 ; E_Base # So [3] NAIL POLISH..HAIRCUT 1F4AA ; E_Base # So FLEXED BICEPS -1F575 ; E_Base # So SLEUTH OR SPY +1F574..1F575 ; E_Base # So [2] MAN IN BUSINESS SUIT LEVITATING..SLEUTH OR SPY 1F57A ; E_Base # So MAN DANCING 1F590 ; E_Base # So RAISED HAND WITH FINGERS SPLAYED 1F595..1F596 ; E_Base # So [2] REVERSED HAND WITH MIDDLE FINGER EXTENDED..RAISED HAND WITH PART BETWEEN MIDDLE AND RING FINGERS @@ -1394,13 +1419,15 @@ D789..D7A3 ; LVT # Lo [27] HANGUL SYLLABLE HIG..HANGUL SYLLABLE HIH 1F6A3 ; E_Base # So ROWBOAT 1F6B4..1F6B6 ; E_Base # So [3] BICYCLIST..PEDESTRIAN 1F6C0 ; E_Base # So BATH -1F918..1F91E ; E_Base # So [7] SIGN OF THE HORNS..HAND WITH INDEX AND MIDDLE FINGERS CROSSED +1F6CC ; E_Base # So SLEEPING ACCOMMODATION +1F918..1F91C ; E_Base # So [5] SIGN OF THE HORNS..RIGHT-FACING FIST +1F91E..1F91F ; E_Base # So [2] HAND WITH INDEX AND MIDDLE FINGERS CROSSED..I LOVE YOU HAND SIGN 1F926 ; E_Base # So FACE PALM -1F930 ; E_Base # So PREGNANT WOMAN -1F933..1F939 ; E_Base # So [7] SELFIE..JUGGLING -1F93C..1F93E ; E_Base # So [3] WRESTLERS..HANDBALL +1F930..1F939 ; E_Base # So [10] PREGNANT WOMAN..JUGGLING +1F93D..1F93E ; E_Base # So [2] WATER POLO..HANDBALL +1F9D1..1F9DD ; E_Base # So [13] ADULT..ELF -# Total code points: 79 +# Total code points: 98 # ================================================ @@ -1416,11 +1443,28 @@ D789..D7A3 ; LVT # Lo [27] HANGUL SYLLABLE HIG..HANGUL SYLLABLE HIH # ================================================ +2640 ; Glue_After_Zwj # So FEMALE SIGN +2642 ; Glue_After_Zwj # So MALE SIGN +2695..2696 ; Glue_After_Zwj # So [2] STAFF OF AESCULAPIUS..SCALES +2708 ; Glue_After_Zwj # So AIRPLANE 2764 ; Glue_After_Zwj # So HEAVY BLACK HEART +1F308 ; Glue_After_Zwj # So RAINBOW +1F33E ; Glue_After_Zwj # So EAR OF RICE +1F373 ; Glue_After_Zwj # So COOKING +1F393 ; Glue_After_Zwj # So GRADUATION CAP +1F3A4 ; Glue_After_Zwj # So MICROPHONE +1F3A8 ; Glue_After_Zwj # So ARTIST PALETTE +1F3EB ; Glue_After_Zwj # So SCHOOL +1F3ED ; Glue_After_Zwj # So FACTORY 1F48B ; Glue_After_Zwj # So KISS MARK +1F4BB..1F4BC ; Glue_After_Zwj # So [2] PERSONAL COMPUTER..BRIEFCASE +1F527 ; Glue_After_Zwj # So WRENCH +1F52C ; Glue_After_Zwj # So MICROSCOPE 1F5E8 ; Glue_After_Zwj # So LEFT SPEECH BUBBLE +1F680 ; Glue_After_Zwj # So ROCKET +1F692 ; Glue_After_Zwj # So FIRE ENGINE -# Total code points: 3 +# Total code points: 22 # ================================================ diff --git a/lib/unicore/auxiliary/LBTest.txt b/lib/unicore/auxiliary/LBTest.txt index 05efcf5a44..6715446aba 100644 --- a/lib/unicore/auxiliary/LBTest.txt +++ b/lib/unicore/auxiliary/LBTest.txt @@ -1,25 +1,28 @@ -# LineBreakTest-9.0.0.txt -# Date: 2016-06-18, 00:42:06 GMT -# © 2016 Unicode®, Inc. +# LineBreakTest-10.0.0.txt +# Date: 2017-04-14, 05:40:30 GMT +# © 2017 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database # For documentation, see http://www.unicode.org/reports/tr44/ # -# Default Line Break Test +# Default Line_Break Test # # Format: -# <string> (# <comment>)? -# <string> contains hex Unicode code points, with -# ÷ wherever there is a break opportunity, and +# <string> (# <comment>)? +# <string> contains hex Unicode code points, with +# ÷ wherever there is a break opportunity, and # × wherever there is not. # <comment> the format can change, but currently it shows: # - the sample character name # - (x) the Line_Break property value for the sample character -# - [x] the rule that determines whether there is a break or not -# Note: The Line Break tests use tailoring of numbers described in Example 7 of Section 8.2 Examples of Customization. -# They also differ from the results produced by a pair table implementation in sequences like: ZW SP CL. +# - [x] the rule that determines whether there is a break or not, +# as listed in the Rules section of LineBreakTest.html +# +# Note: +# The Line_Break tests use tailoring of numbers described in +# Example 7 of Section 8.2, "Examples of Customization" of UAX #14. # # These samples may be extended or changed in the future. # diff --git a/lib/unicore/auxiliary/SBTest.txt b/lib/unicore/auxiliary/SBTest.txt index c7b6465c0c..2985b84cf8 100644 --- a/lib/unicore/auxiliary/SBTest.txt +++ b/lib/unicore/auxiliary/SBTest.txt @@ -1,23 +1,24 @@ -# SentenceBreakTest-9.0.0.txt -# Date: 2016-06-02, 18:28:30 GMT -# © 2016 Unicode®, Inc. +# SentenceBreakTest-10.0.0.txt +# Date: 2017-04-14, 05:40:43 GMT +# © 2017 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database # For documentation, see http://www.unicode.org/reports/tr44/ # -# Default Sentence Break Test +# Default Sentence_Break Test # # Format: -# <string> (# <comment>)? -# <string> contains hex Unicode code points, with -# ÷ wherever there is a break opportunity, and +# <string> (# <comment>)? +# <string> contains hex Unicode code points, with +# ÷ wherever there is a break opportunity, and # × wherever there is not. # <comment> the format can change, but currently it shows: # - the sample character name # - (x) the Sentence_Break property value for the sample character -# - [x] the rule that determines whether there is a break or not +# - [x] the rule that determines whether there is a break or not, +# as listed in the Rules section of SentenceBreakTest.html # # These samples may be extended or changed in the future. # diff --git a/lib/unicore/auxiliary/SentenceBreakProperty.txt b/lib/unicore/auxiliary/SentenceBreakProperty.txt index 9309493cf7..cd698150f4 100644 --- a/lib/unicore/auxiliary/SentenceBreakProperty.txt +++ b/lib/unicore/auxiliary/SentenceBreakProperty.txt @@ -1,6 +1,6 @@ -# SentenceBreakProperty-9.0.0.txt -# Date: 2016-06-01, 10:34:38 GMT -# © 2016 Unicode®, Inc. +# SentenceBreakProperty-10.0.0.txt +# Date: 2017-03-08, 08:42:08 GMT +# © 2017 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html # @@ -97,6 +97,7 @@ 0ACB..0ACC ; Extend # Mc [2] GUJARATI VOWEL SIGN O..GUJARATI VOWEL SIGN AU 0ACD ; Extend # Mn GUJARATI SIGN VIRAMA 0AE2..0AE3 ; Extend # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0AFA..0AFF ; Extend # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE 0B01 ; Extend # Mn ORIYA SIGN CANDRABINDU 0B02..0B03 ; Extend # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA 0B3C ; Extend # Mn ORIYA SIGN NUKTA @@ -138,8 +139,9 @@ 0CCC..0CCD ; Extend # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA 0CD5..0CD6 ; Extend # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK 0CE2..0CE3 ; Extend # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL -0D01 ; Extend # Mn MALAYALAM SIGN CANDRABINDU +0D00..0D01 ; Extend # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU 0D02..0D03 ; Extend # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA +0D3B..0D3C ; Extend # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA 0D3E..0D40 ; Extend # Mc [3] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN II 0D41..0D44 ; Extend # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR 0D46..0D48 ; Extend # Mc [3] MALAYALAM VOWEL SIGN E..MALAYALAM VOWEL SIGN AI @@ -274,8 +276,9 @@ 1CED ; Extend # Mn VEDIC SIGN TIRYAK 1CF2..1CF3 ; Extend # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA 1CF4 ; Extend # Mn VEDIC TONE CANDRA ABOVE +1CF7 ; Extend # Mc VEDIC SIGN ATIKRAMA 1CF8..1CF9 ; Extend # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE -1DC0..1DF5 ; Extend # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE +1DC0..1DF9 ; Extend # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW 1DFB..1DFF ; Extend # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 200C..200D ; Extend # Cf [2] ZERO WIDTH NON-JOINER..ZERO WIDTH JOINER 20D0..20DC ; Extend # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE @@ -439,6 +442,19 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 11722..11725 ; Extend # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU 11726 ; Extend # Mc AHOM VOWEL SIGN E 11727..1172B ; Extend # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER +11A01..11A06 ; Extend # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O +11A07..11A08 ; Extend # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU +11A09..11A0A ; Extend # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A33..11A38 ; Extend # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A39 ; Extend # Mc ZANABAZAR SQUARE SIGN VISARGA +11A3B..11A3E ; Extend # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A47 ; Extend # Mn ZANABAZAR SQUARE SUBJOINER +11A51..11A56 ; Extend # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A57..11A58 ; Extend # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU +11A59..11A5B ; Extend # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A8A..11A96 ; Extend # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A97 ; Extend # Mc SOYOMBO SIGN VISARGA +11A98..11A99 ; Extend # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER 11C2F ; Extend # Mc BHAIKSUKI VOWEL SIGN AA 11C30..11C36 ; Extend # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L 11C38..11C3D ; Extend # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA @@ -451,6 +467,11 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 11CB2..11CB3 ; Extend # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E 11CB4 ; Extend # Mc MARCHEN VOWEL SIGN O 11CB5..11CB6 ; Extend # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D31..11D36 ; Extend # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; Extend # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; Extend # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45 ; Extend # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D47 ; Extend # Mn MASARAM GONDI RA-KARA 16AF0..16AF4 ; Extend # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; Extend # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM 16F51..16F7E ; Extend # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG @@ -479,7 +500,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2197 +# Total code points: 2277 # ================================================ @@ -1859,6 +1880,7 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT 0824 ; OLetter # Lm SAMARITAN MODIFIER LETTER SHORT A 0828 ; OLetter # Lm SAMARITAN MODIFIER LETTER I 0840..0858 ; OLetter # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN +0860..086A ; OLetter # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 08A0..08B4 ; OLetter # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW 08B6..08BD ; OLetter # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON 0904..0939 ; OLetter # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA @@ -1878,6 +1900,7 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT 09DC..09DD ; OLetter # Lo [2] BENGALI LETTER RRA..BENGALI LETTER RHA 09DF..09E1 ; OLetter # Lo [3] BENGALI LETTER YYA..BENGALI LETTER VOCALIC LL 09F0..09F1 ; OLetter # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL +09FC ; OLetter # Lo BENGALI LETTER VEDIC ANUSVARA 0A05..0A0A ; OLetter # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU 0A0F..0A10 ; OLetter # Lo [2] GURMUKHI LETTER EE..GURMUKHI LETTER AI 0A13..0A28 ; OLetter # Lo [22] GURMUKHI LETTER OO..GURMUKHI LETTER NA @@ -2073,12 +2096,12 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT 30A1..30FA ; OLetter # Lo [90] KATAKANA LETTER SMALL A..KATAKANA LETTER VO 30FC..30FE ; OLetter # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK 30FF ; OLetter # Lo KATAKANA DIGRAPH KOTO -3105..312D ; OLetter # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH +3105..312E ; OLetter # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE 3131..318E ; OLetter # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE 31A0..31BA ; OLetter # Lo [27] BOPOMOFO LETTER BU..BOPOMOFO LETTER ZY 31F0..31FF ; OLetter # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO 3400..4DB5 ; OLetter # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 -4E00..9FD5 ; OLetter # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5 +4E00..9FEA ; OLetter # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA A000..A014 ; OLetter # Lo [21] YI SYLLABLE IT..YI SYLLABLE E A015 ; OLetter # Lm YI SYLLABLE WU A016..A48C ; OLetter # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR @@ -2176,7 +2199,7 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 10280..1029C ; OLetter # Lo [29] LYCIAN LETTER A..LYCIAN LETTER X 102A0..102D0 ; OLetter # Lo [49] CARIAN LETTER A..CARIAN LETTER UUU3 10300..1031F ; OLetter # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS -10330..10340 ; OLetter # Lo [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA +1032D..10340 ; OLetter # Lo [20] OLD ITALIC LETTER YE..GOTHIC LETTER PAIRTHRA 10341 ; OLetter # Nl GOTHIC LETTER NINETY 10342..10349 ; OLetter # Lo [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL 1034A ; OLetter # Nl GOTHIC LETTER NINE HUNDRED @@ -2257,11 +2280,21 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 11680..116AA ; OLetter # Lo [43] TAKRI LETTER A..TAKRI LETTER RRA 11700..11719 ; OLetter # Lo [26] AHOM LETTER KA..AHOM LETTER JHA 118FF ; OLetter # Lo WARANG CITI OM +11A00 ; OLetter # Lo ZANABAZAR SQUARE LETTER A +11A0B..11A32 ; OLetter # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA +11A3A ; OLetter # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA +11A50 ; OLetter # Lo SOYOMBO LETTER A +11A5C..11A83 ; OLetter # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA +11A86..11A89 ; OLetter # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA 11AC0..11AF8 ; OLetter # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL 11C00..11C08 ; OLetter # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E ; OLetter # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA 11C40 ; OLetter # Lo BHAIKSUKI SIGN AVAGRAHA 11C72..11C8F ; OLetter # Lo [30] MARCHEN LETTER KA..MARCHEN LETTER A +11D00..11D06 ; OLetter # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E +11D08..11D09 ; OLetter # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O +11D0B..11D30 ; OLetter # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA +11D46 ; OLetter # Lo MASARAM GONDI REPHA 12000..12399 ; OLetter # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; OLetter # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12480..12543 ; OLetter # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU @@ -2277,10 +2310,11 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 16F00..16F44 ; OLetter # Lo [69] MIAO LETTER PA..MIAO LETTER HHA 16F50 ; OLetter # Lo MIAO LETTER NASALIZATION 16F93..16F9F ; OLetter # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 -16FE0 ; OLetter # Lm TANGUT ITERATION MARK +16FE0..16FE1 ; OLetter # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK 17000..187EC ; OLetter # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC 18800..18AF2 ; OLetter # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755 -1B000..1B001 ; OLetter # Lo [2] KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE +1B000..1B11E ; OLetter # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1B170..1B2FB ; OLetter # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 1BC00..1BC6A ; OLetter # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M 1BC70..1BC7C ; OLetter # Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK 1BC80..1BC88 ; OLetter # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL @@ -2323,9 +2357,10 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 2A700..2B734 ; OLetter # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 2B740..2B81D ; OLetter # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; OLetter # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 +2CEB0..2EBE0 ; OLetter # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; OLetter # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D -# Total code points: 113027 +# Total code points: 121354 # ================================================ @@ -2379,12 +2414,13 @@ ABF0..ABF9 ; Numeric # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT N 11730..11739 ; Numeric # Nd [10] AHOM DIGIT ZERO..AHOM DIGIT NINE 118E0..118E9 ; Numeric # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE 11C50..11C59 ; Numeric # Nd [10] BHAIKSUKI DIGIT ZERO..BHAIKSUKI DIGIT NINE +11D50..11D59 ; Numeric # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE 16A60..16A69 ; Numeric # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE 16B50..16B59 ; Numeric # Nd [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE 1D7CE..1D7FF ; Numeric # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE 1E950..1E959 ; Numeric # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE -# Total code points: 572 +# Total code points: 582 # ================================================ @@ -2453,6 +2489,8 @@ FF61 ; STerm # Po HALFWIDTH IDEOGRAPHIC FULL STOP 115C9..115D7 ; STerm # Po [15] SIDDHAM END OF TEXT MARK..SIDDHAM SECTION MARK WITH CIRCLES AND FOUR ENCLOSURES 11641..11642 ; STerm # Po [2] MODI DANDA..MODI DOUBLE DANDA 1173C..1173E ; STerm # Po [3] AHOM SIGN SMALL SECTION..AHOM SIGN RULAI +11A42..11A43 ; STerm # Po [2] ZANABAZAR SQUARE MARK SHAD..ZANABAZAR SQUARE MARK DOUBLE SHAD +11A9B..11A9C ; STerm # Po [2] SOYOMBO MARK SHAD..SOYOMBO MARK DOUBLE SHAD 11C41..11C42 ; STerm # Po [2] BHAIKSUKI DANDA..BHAIKSUKI DOUBLE DANDA 16A6E..16A6F ; STerm # Po [2] MRO DANDA..MRO DOUBLE DANDA 16AF5 ; STerm # Po BASSA VAH FULL STOP @@ -2461,7 +2499,7 @@ FF61 ; STerm # Po HALFWIDTH IDEOGRAPHIC FULL STOP 1BC9F ; STerm # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1DA88 ; STerm # Po SIGNWRITING FULL STOP -# Total code points: 121 +# Total code points: 125 # ================================================ diff --git a/lib/unicore/auxiliary/WBTest.txt b/lib/unicore/auxiliary/WBTest.txt index a3a4b0548e..63761026ce 100644 --- a/lib/unicore/auxiliary/WBTest.txt +++ b/lib/unicore/auxiliary/WBTest.txt @@ -1,23 +1,24 @@ -# WordBreakTest-9.0.0.txt -# Date: 2016-06-02, 18:28:31 GMT -# © 2016 Unicode®, Inc. +# WordBreakTest-10.0.0.txt +# Date: 2017-04-14, 05:40:44 GMT +# © 2017 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database # For documentation, see http://www.unicode.org/reports/tr44/ # -# Default Word Break Test +# Default Word_Break Test # # Format: -# <string> (# <comment>)? -# <string> contains hex Unicode code points, with -# ÷ wherever there is a break opportunity, and +# <string> (# <comment>)? +# <string> contains hex Unicode code points, with +# ÷ wherever there is a break opportunity, and # × wherever there is not. # <comment> the format can change, but currently it shows: # - the sample character name # - (x) the Word_Break property value for the sample character -# - [x] the rule that determines whether there is a break or not +# - [x] the rule that determines whether there is a break or not, +# as listed in the Rules section of WordBreakTest.html # # These samples may be extended or changed in the future. # @@ -55,8 +56,8 @@ ÷ 0001 × 0308 ÷ 261D ÷ # ÷ [0.2] <START OF HEADING> (Other) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] ÷ 0001 ÷ 1F3FB ÷ # ÷ [0.2] <START OF HEADING> (Other) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 0001 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] <START OF HEADING> (Other) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] -÷ 0001 ÷ 2764 ÷ # ÷ [0.2] <START OF HEADING> (Other) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 0001 × 0308 ÷ 2764 ÷ # ÷ [0.2] <START OF HEADING> (Other) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 0001 ÷ 2640 ÷ # ÷ [0.2] <START OF HEADING> (Other) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 0001 × 0308 ÷ 2640 ÷ # ÷ [0.2] <START OF HEADING> (Other) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 0001 ÷ 1F466 ÷ # ÷ [0.2] <START OF HEADING> (Other) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0001 × 0308 ÷ 1F466 ÷ # ÷ [0.2] <START OF HEADING> (Other) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0001 × 00AD ÷ # ÷ [0.2] <START OF HEADING> (Other) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3] @@ -117,8 +118,8 @@ ÷ 000D ÷ 0308 ÷ 261D ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [3.1] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] ÷ 000D ÷ 1F3FB ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [3.1] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 000D ÷ 0308 ÷ 1F3FB ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [3.1] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] -÷ 000D ÷ 2764 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [3.1] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 000D ÷ 0308 ÷ 2764 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [3.1] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 000D ÷ 2640 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [3.1] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 000D ÷ 0308 ÷ 2640 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [3.1] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 000D ÷ 1F466 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [3.1] BOY (EBG) ÷ [0.3] ÷ 000D ÷ 0308 ÷ 1F466 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [3.1] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 000D ÷ 00AD ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [3.1] SOFT HYPHEN (Format_FE) ÷ [0.3] @@ -179,8 +180,8 @@ ÷ 000A ÷ 0308 ÷ 261D ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [3.1] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] ÷ 000A ÷ 1F3FB ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [3.1] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 000A ÷ 0308 ÷ 1F3FB ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [3.1] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] -÷ 000A ÷ 2764 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [3.1] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 000A ÷ 0308 ÷ 2764 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [3.1] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 000A ÷ 2640 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [3.1] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 000A ÷ 0308 ÷ 2640 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [3.1] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 000A ÷ 1F466 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [3.1] BOY (EBG) ÷ [0.3] ÷ 000A ÷ 0308 ÷ 1F466 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [3.1] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 000A ÷ 00AD ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [3.1] SOFT HYPHEN (Format_FE) ÷ [0.3] @@ -241,8 +242,8 @@ ÷ 000B ÷ 0308 ÷ 261D ÷ # ÷ [0.2] <LINE TABULATION> (Newline) ÷ [3.1] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] ÷ 000B ÷ 1F3FB ÷ # ÷ [0.2] <LINE TABULATION> (Newline) ÷ [3.1] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 000B ÷ 0308 ÷ 1F3FB ÷ # ÷ [0.2] <LINE TABULATION> (Newline) ÷ [3.1] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] -÷ 000B ÷ 2764 ÷ # ÷ [0.2] <LINE TABULATION> (Newline) ÷ [3.1] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 000B ÷ 0308 ÷ 2764 ÷ # ÷ [0.2] <LINE TABULATION> (Newline) ÷ [3.1] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 000B ÷ 2640 ÷ # ÷ [0.2] <LINE TABULATION> (Newline) ÷ [3.1] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 000B ÷ 0308 ÷ 2640 ÷ # ÷ [0.2] <LINE TABULATION> (Newline) ÷ [3.1] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 000B ÷ 1F466 ÷ # ÷ [0.2] <LINE TABULATION> (Newline) ÷ [3.1] BOY (EBG) ÷ [0.3] ÷ 000B ÷ 0308 ÷ 1F466 ÷ # ÷ [0.2] <LINE TABULATION> (Newline) ÷ [3.1] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 000B ÷ 00AD ÷ # ÷ [0.2] <LINE TABULATION> (Newline) ÷ [3.1] SOFT HYPHEN (Format_FE) ÷ [0.3] @@ -303,8 +304,8 @@ ÷ 3031 × 0308 ÷ 261D ÷ # ÷ [0.2] VERTICAL KANA REPEAT MARK (Katakana) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] ÷ 3031 ÷ 1F3FB ÷ # ÷ [0.2] VERTICAL KANA REPEAT MARK (Katakana) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 3031 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] VERTICAL KANA REPEAT MARK (Katakana) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] -÷ 3031 ÷ 2764 ÷ # ÷ [0.2] VERTICAL KANA REPEAT MARK (Katakana) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 3031 × 0308 ÷ 2764 ÷ # ÷ [0.2] VERTICAL KANA REPEAT MARK (Katakana) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 3031 ÷ 2640 ÷ # ÷ [0.2] VERTICAL KANA REPEAT MARK (Katakana) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 3031 × 0308 ÷ 2640 ÷ # ÷ [0.2] VERTICAL KANA REPEAT MARK (Katakana) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 3031 ÷ 1F466 ÷ # ÷ [0.2] VERTICAL KANA REPEAT MARK (Katakana) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 3031 × 0308 ÷ 1F466 ÷ # ÷ [0.2] VERTICAL KANA REPEAT MARK (Katakana) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 3031 × 00AD ÷ # ÷ [0.2] VERTICAL KANA REPEAT MARK (Katakana) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3] @@ -365,8 +366,8 @@ ÷ 0041 × 0308 ÷ 261D ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (ALetter) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] ÷ 0041 ÷ 1F3FB ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (ALetter) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 0041 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (ALetter) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] -÷ 0041 ÷ 2764 ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (ALetter) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 0041 × 0308 ÷ 2764 ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (ALetter) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 0041 ÷ 2640 ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (ALetter) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 0041 × 0308 ÷ 2640 ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (ALetter) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 0041 ÷ 1F466 ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (ALetter) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0041 × 0308 ÷ 1F466 ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (ALetter) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0041 × 00AD ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (ALetter) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3] @@ -427,8 +428,8 @@ ÷ 003A × 0308 ÷ 261D ÷ # ÷ [0.2] COLON (MidLetter) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] ÷ 003A ÷ 1F3FB ÷ # ÷ [0.2] COLON (MidLetter) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 003A × 0308 ÷ 1F3FB ÷ # ÷ [0.2] COLON (MidLetter) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] -÷ 003A ÷ 2764 ÷ # ÷ [0.2] COLON (MidLetter) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 003A × 0308 ÷ 2764 ÷ # ÷ [0.2] COLON (MidLetter) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 003A ÷ 2640 ÷ # ÷ [0.2] COLON (MidLetter) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 003A × 0308 ÷ 2640 ÷ # ÷ [0.2] COLON (MidLetter) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 003A ÷ 1F466 ÷ # ÷ [0.2] COLON (MidLetter) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 003A × 0308 ÷ 1F466 ÷ # ÷ [0.2] COLON (MidLetter) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 003A × 00AD ÷ # ÷ [0.2] COLON (MidLetter) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3] @@ -489,8 +490,8 @@ ÷ 002C × 0308 ÷ 261D ÷ # ÷ [0.2] COMMA (MidNum) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] ÷ 002C ÷ 1F3FB ÷ # ÷ [0.2] COMMA (MidNum) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 002C × 0308 ÷ 1F3FB ÷ # ÷ [0.2] COMMA (MidNum) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] -÷ 002C ÷ 2764 ÷ # ÷ [0.2] COMMA (MidNum) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 002C × 0308 ÷ 2764 ÷ # ÷ [0.2] COMMA (MidNum) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 002C ÷ 2640 ÷ # ÷ [0.2] COMMA (MidNum) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 002C × 0308 ÷ 2640 ÷ # ÷ [0.2] COMMA (MidNum) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 002C ÷ 1F466 ÷ # ÷ [0.2] COMMA (MidNum) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 002C × 0308 ÷ 1F466 ÷ # ÷ [0.2] COMMA (MidNum) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 002C × 00AD ÷ # ÷ [0.2] COMMA (MidNum) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3] @@ -551,8 +552,8 @@ ÷ 002E × 0308 ÷ 261D ÷ # ÷ [0.2] FULL STOP (MidNumLet) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] ÷ 002E ÷ 1F3FB ÷ # ÷ [0.2] FULL STOP (MidNumLet) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 002E × 0308 ÷ 1F3FB ÷ # ÷ [0.2] FULL STOP (MidNumLet) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] -÷ 002E ÷ 2764 ÷ # ÷ [0.2] FULL STOP (MidNumLet) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 002E × 0308 ÷ 2764 ÷ # ÷ [0.2] FULL STOP (MidNumLet) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 002E ÷ 2640 ÷ # ÷ [0.2] FULL STOP (MidNumLet) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 002E × 0308 ÷ 2640 ÷ # ÷ [0.2] FULL STOP (MidNumLet) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 002E ÷ 1F466 ÷ # ÷ [0.2] FULL STOP (MidNumLet) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 002E × 0308 ÷ 1F466 ÷ # ÷ [0.2] FULL STOP (MidNumLet) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 002E × 00AD ÷ # ÷ [0.2] FULL STOP (MidNumLet) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3] @@ -613,8 +614,8 @@ ÷ 0030 × 0308 ÷ 261D ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] ÷ 0030 ÷ 1F3FB ÷ # ÷ [0.2] DIGIT ZERO (Numeric) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 0030 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] -÷ 0030 ÷ 2764 ÷ # ÷ [0.2] DIGIT ZERO (Numeric) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 0030 × 0308 ÷ 2764 ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 0030 ÷ 2640 ÷ # ÷ [0.2] DIGIT ZERO (Numeric) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 0030 × 0308 ÷ 2640 ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 0030 ÷ 1F466 ÷ # ÷ [0.2] DIGIT ZERO (Numeric) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0030 × 0308 ÷ 1F466 ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0030 × 00AD ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3] @@ -675,8 +676,8 @@ ÷ 005F × 0308 ÷ 261D ÷ # ÷ [0.2] LOW LINE (ExtendNumLet) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] ÷ 005F ÷ 1F3FB ÷ # ÷ [0.2] LOW LINE (ExtendNumLet) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 005F × 0308 ÷ 1F3FB ÷ # ÷ [0.2] LOW LINE (ExtendNumLet) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] -÷ 005F ÷ 2764 ÷ # ÷ [0.2] LOW LINE (ExtendNumLet) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 005F × 0308 ÷ 2764 ÷ # ÷ [0.2] LOW LINE (ExtendNumLet) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 005F ÷ 2640 ÷ # ÷ [0.2] LOW LINE (ExtendNumLet) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 005F × 0308 ÷ 2640 ÷ # ÷ [0.2] LOW LINE (ExtendNumLet) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 005F ÷ 1F466 ÷ # ÷ [0.2] LOW LINE (ExtendNumLet) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 005F × 0308 ÷ 1F466 ÷ # ÷ [0.2] LOW LINE (ExtendNumLet) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 005F × 00AD ÷ # ÷ [0.2] LOW LINE (ExtendNumLet) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3] @@ -737,8 +738,8 @@ ÷ 1F1E6 × 0308 ÷ 261D ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] ÷ 1F1E6 ÷ 1F3FB ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 1F1E6 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] -÷ 1F1E6 ÷ 2764 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 1F1E6 × 0308 ÷ 2764 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 1F1E6 ÷ 2640 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 1F1E6 × 0308 ÷ 2640 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 1F1E6 ÷ 1F466 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 1F1E6 × 0308 ÷ 1F466 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 1F1E6 × 00AD ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3] @@ -799,8 +800,8 @@ ÷ 05D0 × 0308 ÷ 261D ÷ # ÷ [0.2] HEBREW LETTER ALEF (Hebrew_Letter) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] ÷ 05D0 ÷ 1F3FB ÷ # ÷ [0.2] HEBREW LETTER ALEF (Hebrew_Letter) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 05D0 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] HEBREW LETTER ALEF (Hebrew_Letter) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] -÷ 05D0 ÷ 2764 ÷ # ÷ [0.2] HEBREW LETTER ALEF (Hebrew_Letter) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 05D0 × 0308 ÷ 2764 ÷ # ÷ [0.2] HEBREW LETTER ALEF (Hebrew_Letter) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 05D0 ÷ 2640 ÷ # ÷ [0.2] HEBREW LETTER ALEF (Hebrew_Letter) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 05D0 × 0308 ÷ 2640 ÷ # ÷ [0.2] HEBREW LETTER ALEF (Hebrew_Letter) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 05D0 ÷ 1F466 ÷ # ÷ [0.2] HEBREW LETTER ALEF (Hebrew_Letter) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 05D0 × 0308 ÷ 1F466 ÷ # ÷ [0.2] HEBREW LETTER ALEF (Hebrew_Letter) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 05D0 × 00AD ÷ # ÷ [0.2] HEBREW LETTER ALEF (Hebrew_Letter) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3] @@ -861,8 +862,8 @@ ÷ 0022 × 0308 ÷ 261D ÷ # ÷ [0.2] QUOTATION MARK (Double_Quote) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] ÷ 0022 ÷ 1F3FB ÷ # ÷ [0.2] QUOTATION MARK (Double_Quote) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 0022 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] QUOTATION MARK (Double_Quote) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] -÷ 0022 ÷ 2764 ÷ # ÷ [0.2] QUOTATION MARK (Double_Quote) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 0022 × 0308 ÷ 2764 ÷ # ÷ [0.2] QUOTATION MARK (Double_Quote) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 0022 ÷ 2640 ÷ # ÷ [0.2] QUOTATION MARK (Double_Quote) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 0022 × 0308 ÷ 2640 ÷ # ÷ [0.2] QUOTATION MARK (Double_Quote) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 0022 ÷ 1F466 ÷ # ÷ [0.2] QUOTATION MARK (Double_Quote) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0022 × 0308 ÷ 1F466 ÷ # ÷ [0.2] QUOTATION MARK (Double_Quote) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0022 × 00AD ÷ # ÷ [0.2] QUOTATION MARK (Double_Quote) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3] @@ -923,8 +924,8 @@ ÷ 0027 × 0308 ÷ 261D ÷ # ÷ [0.2] APOSTROPHE (Single_Quote) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] ÷ 0027 ÷ 1F3FB ÷ # ÷ [0.2] APOSTROPHE (Single_Quote) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 0027 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] APOSTROPHE (Single_Quote) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] -÷ 0027 ÷ 2764 ÷ # ÷ [0.2] APOSTROPHE (Single_Quote) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 0027 × 0308 ÷ 2764 ÷ # ÷ [0.2] APOSTROPHE (Single_Quote) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 0027 ÷ 2640 ÷ # ÷ [0.2] APOSTROPHE (Single_Quote) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 0027 × 0308 ÷ 2640 ÷ # ÷ [0.2] APOSTROPHE (Single_Quote) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 0027 ÷ 1F466 ÷ # ÷ [0.2] APOSTROPHE (Single_Quote) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0027 × 0308 ÷ 1F466 ÷ # ÷ [0.2] APOSTROPHE (Single_Quote) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0027 × 00AD ÷ # ÷ [0.2] APOSTROPHE (Single_Quote) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3] @@ -985,8 +986,8 @@ ÷ 261D × 0308 ÷ 261D ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] ÷ 261D × 1F3FB ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [14.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 261D × 0308 × 1F3FB ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [4.0] COMBINING DIAERESIS (Extend_FE) × [14.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] -÷ 261D ÷ 2764 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 261D × 0308 ÷ 2764 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 261D ÷ 2640 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 261D × 0308 ÷ 2640 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 261D ÷ 1F466 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 261D × 0308 ÷ 1F466 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 261D × 00AD ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3] @@ -1047,8 +1048,8 @@ ÷ 1F3FB × 0308 ÷ 261D ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] ÷ 1F3FB ÷ 1F3FB ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 1F3FB × 0308 ÷ 1F3FB ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] -÷ 1F3FB ÷ 2764 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 1F3FB × 0308 ÷ 2764 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 1F3FB ÷ 2640 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 1F3FB × 0308 ÷ 2640 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 1F3FB ÷ 1F466 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 1F3FB × 0308 ÷ 1F466 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 1F3FB × 00AD ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3] @@ -1075,68 +1076,68 @@ ÷ 1F3FB × 0308 ÷ 0031 ÷ 002C ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) ÷ [0.3] ÷ 1F3FB ÷ 0031 ÷ 002E × 2060 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [999.0] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) × [4.0] WORD JOINER (Format_FE) ÷ [0.3] ÷ 1F3FB × 0308 ÷ 0031 ÷ 002E × 2060 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) × [4.0] WORD JOINER (Format_FE) ÷ [0.3] -÷ 2764 ÷ 0001 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] <START OF HEADING> (Other) ÷ [0.3] -÷ 2764 × 0308 ÷ 0001 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] <START OF HEADING> (Other) ÷ [0.3] -÷ 2764 ÷ 000D ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [3.2] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] -÷ 2764 × 0308 ÷ 000D ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [3.2] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] -÷ 2764 ÷ 000A ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [3.2] <LINE FEED (LF)> (LF) ÷ [0.3] -÷ 2764 × 0308 ÷ 000A ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [3.2] <LINE FEED (LF)> (LF) ÷ [0.3] -÷ 2764 ÷ 000B ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [3.2] <LINE TABULATION> (Newline) ÷ [0.3] -÷ 2764 × 0308 ÷ 000B ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [3.2] <LINE TABULATION> (Newline) ÷ [0.3] -÷ 2764 ÷ 3031 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] VERTICAL KANA REPEAT MARK (Katakana) ÷ [0.3] -÷ 2764 × 0308 ÷ 3031 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] VERTICAL KANA REPEAT MARK (Katakana) ÷ [0.3] -÷ 2764 ÷ 0041 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] LATIN CAPITAL LETTER A (ALetter) ÷ [0.3] -÷ 2764 × 0308 ÷ 0041 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LATIN CAPITAL LETTER A (ALetter) ÷ [0.3] -÷ 2764 ÷ 003A ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] COLON (MidLetter) ÷ [0.3] -÷ 2764 × 0308 ÷ 003A ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] COLON (MidLetter) ÷ [0.3] -÷ 2764 ÷ 002C ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] COMMA (MidNum) ÷ [0.3] -÷ 2764 × 0308 ÷ 002C ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] COMMA (MidNum) ÷ [0.3] -÷ 2764 ÷ 002E ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] FULL STOP (MidNumLet) ÷ [0.3] -÷ 2764 × 0308 ÷ 002E ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] FULL STOP (MidNumLet) ÷ [0.3] -÷ 2764 ÷ 0030 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] DIGIT ZERO (Numeric) ÷ [0.3] -÷ 2764 × 0308 ÷ 0030 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ZERO (Numeric) ÷ [0.3] -÷ 2764 ÷ 005F ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] LOW LINE (ExtendNumLet) ÷ [0.3] -÷ 2764 × 0308 ÷ 005F ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LOW LINE (ExtendNumLet) ÷ [0.3] -÷ 2764 ÷ 1F1E6 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] -÷ 2764 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] -÷ 2764 ÷ 05D0 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] HEBREW LETTER ALEF (Hebrew_Letter) ÷ [0.3] -÷ 2764 × 0308 ÷ 05D0 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] HEBREW LETTER ALEF (Hebrew_Letter) ÷ [0.3] -÷ 2764 ÷ 0022 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] QUOTATION MARK (Double_Quote) ÷ [0.3] -÷ 2764 × 0308 ÷ 0022 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] QUOTATION MARK (Double_Quote) ÷ [0.3] -÷ 2764 ÷ 0027 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] APOSTROPHE (Single_Quote) ÷ [0.3] -÷ 2764 × 0308 ÷ 0027 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] APOSTROPHE (Single_Quote) ÷ [0.3] -÷ 2764 ÷ 261D ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] -÷ 2764 × 0308 ÷ 261D ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] -÷ 2764 ÷ 1F3FB ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] -÷ 2764 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] -÷ 2764 ÷ 2764 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 2764 × 0308 ÷ 2764 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 2764 ÷ 1F466 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] BOY (EBG) ÷ [0.3] -÷ 2764 × 0308 ÷ 1F466 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] BOY (EBG) ÷ [0.3] -÷ 2764 × 00AD ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3] -÷ 2764 × 0308 × 00AD ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3] -÷ 2764 × 0300 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [4.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3] -÷ 2764 × 0308 × 0300 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) × [4.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3] -÷ 2764 × 200D ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [4.0] ZERO WIDTH JOINER (ZWJ_FE) ÷ [0.3] -÷ 2764 × 0308 × 200D ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) × [4.0] ZERO WIDTH JOINER (ZWJ_FE) ÷ [0.3] -÷ 2764 ÷ 0061 × 2060 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] LATIN SMALL LETTER A (ALetter) × [4.0] WORD JOINER (Format_FE) ÷ [0.3] -÷ 2764 × 0308 ÷ 0061 × 2060 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LATIN SMALL LETTER A (ALetter) × [4.0] WORD JOINER (Format_FE) ÷ [0.3] -÷ 2764 ÷ 0061 ÷ 003A ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) ÷ [0.3] -÷ 2764 × 0308 ÷ 0061 ÷ 003A ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) ÷ [0.3] -÷ 2764 ÷ 0061 ÷ 0027 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (Single_Quote) ÷ [0.3] -÷ 2764 × 0308 ÷ 0061 ÷ 0027 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (Single_Quote) ÷ [0.3] -÷ 2764 ÷ 0061 ÷ 0027 × 2060 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (Single_Quote) × [4.0] WORD JOINER (Format_FE) ÷ [0.3] -÷ 2764 × 0308 ÷ 0061 ÷ 0027 × 2060 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (Single_Quote) × [4.0] WORD JOINER (Format_FE) ÷ [0.3] -÷ 2764 ÷ 0061 ÷ 002C ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) ÷ [0.3] -÷ 2764 × 0308 ÷ 0061 ÷ 002C ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) ÷ [0.3] -÷ 2764 ÷ 0031 ÷ 003A ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) ÷ [0.3] -÷ 2764 × 0308 ÷ 0031 ÷ 003A ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) ÷ [0.3] -÷ 2764 ÷ 0031 ÷ 0027 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] DIGIT ONE (Numeric) ÷ [999.0] APOSTROPHE (Single_Quote) ÷ [0.3] -÷ 2764 × 0308 ÷ 0031 ÷ 0027 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ONE (Numeric) ÷ [999.0] APOSTROPHE (Single_Quote) ÷ [0.3] -÷ 2764 ÷ 0031 ÷ 002C ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) ÷ [0.3] -÷ 2764 × 0308 ÷ 0031 ÷ 002C ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) ÷ [0.3] -÷ 2764 ÷ 0031 ÷ 002E × 2060 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [999.0] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) × [4.0] WORD JOINER (Format_FE) ÷ [0.3] -÷ 2764 × 0308 ÷ 0031 ÷ 002E × 2060 ÷ # ÷ [0.2] HEAVY BLACK HEART (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) × [4.0] WORD JOINER (Format_FE) ÷ [0.3] +÷ 2640 ÷ 0001 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] <START OF HEADING> (Other) ÷ [0.3] +÷ 2640 × 0308 ÷ 0001 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] <START OF HEADING> (Other) ÷ [0.3] +÷ 2640 ÷ 000D ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [3.2] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 2640 × 0308 ÷ 000D ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [3.2] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 2640 ÷ 000A ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [3.2] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 2640 × 0308 ÷ 000A ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [3.2] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 2640 ÷ 000B ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [3.2] <LINE TABULATION> (Newline) ÷ [0.3] +÷ 2640 × 0308 ÷ 000B ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [3.2] <LINE TABULATION> (Newline) ÷ [0.3] +÷ 2640 ÷ 3031 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] VERTICAL KANA REPEAT MARK (Katakana) ÷ [0.3] +÷ 2640 × 0308 ÷ 3031 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] VERTICAL KANA REPEAT MARK (Katakana) ÷ [0.3] +÷ 2640 ÷ 0041 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] LATIN CAPITAL LETTER A (ALetter) ÷ [0.3] +÷ 2640 × 0308 ÷ 0041 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LATIN CAPITAL LETTER A (ALetter) ÷ [0.3] +÷ 2640 ÷ 003A ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] COLON (MidLetter) ÷ [0.3] +÷ 2640 × 0308 ÷ 003A ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] COLON (MidLetter) ÷ [0.3] +÷ 2640 ÷ 002C ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] COMMA (MidNum) ÷ [0.3] +÷ 2640 × 0308 ÷ 002C ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] COMMA (MidNum) ÷ [0.3] +÷ 2640 ÷ 002E ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] FULL STOP (MidNumLet) ÷ [0.3] +÷ 2640 × 0308 ÷ 002E ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] FULL STOP (MidNumLet) ÷ [0.3] +÷ 2640 ÷ 0030 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] DIGIT ZERO (Numeric) ÷ [0.3] +÷ 2640 × 0308 ÷ 0030 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ZERO (Numeric) ÷ [0.3] +÷ 2640 ÷ 005F ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] LOW LINE (ExtendNumLet) ÷ [0.3] +÷ 2640 × 0308 ÷ 005F ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LOW LINE (ExtendNumLet) ÷ [0.3] +÷ 2640 ÷ 1F1E6 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ 2640 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ 2640 ÷ 05D0 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] HEBREW LETTER ALEF (Hebrew_Letter) ÷ [0.3] +÷ 2640 × 0308 ÷ 05D0 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] HEBREW LETTER ALEF (Hebrew_Letter) ÷ [0.3] +÷ 2640 ÷ 0022 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] QUOTATION MARK (Double_Quote) ÷ [0.3] +÷ 2640 × 0308 ÷ 0022 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] QUOTATION MARK (Double_Quote) ÷ [0.3] +÷ 2640 ÷ 0027 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] APOSTROPHE (Single_Quote) ÷ [0.3] +÷ 2640 × 0308 ÷ 0027 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] APOSTROPHE (Single_Quote) ÷ [0.3] +÷ 2640 ÷ 261D ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ 2640 × 0308 ÷ 261D ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ 2640 ÷ 1F3FB ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ 2640 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ 2640 ÷ 2640 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 2640 × 0308 ÷ 2640 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 2640 ÷ 1F466 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] BOY (EBG) ÷ [0.3] +÷ 2640 × 0308 ÷ 1F466 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] BOY (EBG) ÷ [0.3] +÷ 2640 × 00AD ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3] +÷ 2640 × 0308 × 00AD ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3] +÷ 2640 × 0300 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [4.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3] +÷ 2640 × 0308 × 0300 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) × [4.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3] +÷ 2640 × 200D ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [4.0] ZERO WIDTH JOINER (ZWJ_FE) ÷ [0.3] +÷ 2640 × 0308 × 200D ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) × [4.0] ZERO WIDTH JOINER (ZWJ_FE) ÷ [0.3] +÷ 2640 ÷ 0061 × 2060 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] LATIN SMALL LETTER A (ALetter) × [4.0] WORD JOINER (Format_FE) ÷ [0.3] +÷ 2640 × 0308 ÷ 0061 × 2060 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LATIN SMALL LETTER A (ALetter) × [4.0] WORD JOINER (Format_FE) ÷ [0.3] +÷ 2640 ÷ 0061 ÷ 003A ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) ÷ [0.3] +÷ 2640 × 0308 ÷ 0061 ÷ 003A ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) ÷ [0.3] +÷ 2640 ÷ 0061 ÷ 0027 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (Single_Quote) ÷ [0.3] +÷ 2640 × 0308 ÷ 0061 ÷ 0027 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (Single_Quote) ÷ [0.3] +÷ 2640 ÷ 0061 ÷ 0027 × 2060 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (Single_Quote) × [4.0] WORD JOINER (Format_FE) ÷ [0.3] +÷ 2640 × 0308 ÷ 0061 ÷ 0027 × 2060 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (Single_Quote) × [4.0] WORD JOINER (Format_FE) ÷ [0.3] +÷ 2640 ÷ 0061 ÷ 002C ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) ÷ [0.3] +÷ 2640 × 0308 ÷ 0061 ÷ 002C ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) ÷ [0.3] +÷ 2640 ÷ 0031 ÷ 003A ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) ÷ [0.3] +÷ 2640 × 0308 ÷ 0031 ÷ 003A ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) ÷ [0.3] +÷ 2640 ÷ 0031 ÷ 0027 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] DIGIT ONE (Numeric) ÷ [999.0] APOSTROPHE (Single_Quote) ÷ [0.3] +÷ 2640 × 0308 ÷ 0031 ÷ 0027 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ONE (Numeric) ÷ [999.0] APOSTROPHE (Single_Quote) ÷ [0.3] +÷ 2640 ÷ 0031 ÷ 002C ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) ÷ [0.3] +÷ 2640 × 0308 ÷ 0031 ÷ 002C ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) ÷ [0.3] +÷ 2640 ÷ 0031 ÷ 002E × 2060 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) × [4.0] WORD JOINER (Format_FE) ÷ [0.3] +÷ 2640 × 0308 ÷ 0031 ÷ 002E × 2060 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) × [4.0] WORD JOINER (Format_FE) ÷ [0.3] ÷ 1F466 ÷ 0001 ÷ # ÷ [0.2] BOY (EBG) ÷ [999.0] <START OF HEADING> (Other) ÷ [0.3] ÷ 1F466 × 0308 ÷ 0001 ÷ # ÷ [0.2] BOY (EBG) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] <START OF HEADING> (Other) ÷ [0.3] ÷ 1F466 ÷ 000D ÷ # ÷ [0.2] BOY (EBG) ÷ [3.2] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] @@ -1171,8 +1172,8 @@ ÷ 1F466 × 0308 ÷ 261D ÷ # ÷ [0.2] BOY (EBG) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] ÷ 1F466 × 1F3FB ÷ # ÷ [0.2] BOY (EBG) × [14.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 1F466 × 0308 × 1F3FB ÷ # ÷ [0.2] BOY (EBG) × [4.0] COMBINING DIAERESIS (Extend_FE) × [14.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] -÷ 1F466 ÷ 2764 ÷ # ÷ [0.2] BOY (EBG) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 1F466 × 0308 ÷ 2764 ÷ # ÷ [0.2] BOY (EBG) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 1F466 ÷ 2640 ÷ # ÷ [0.2] BOY (EBG) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 1F466 × 0308 ÷ 2640 ÷ # ÷ [0.2] BOY (EBG) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 1F466 ÷ 1F466 ÷ # ÷ [0.2] BOY (EBG) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 1F466 × 0308 ÷ 1F466 ÷ # ÷ [0.2] BOY (EBG) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 1F466 × 00AD ÷ # ÷ [0.2] BOY (EBG) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3] @@ -1233,8 +1234,8 @@ ÷ 00AD × 0308 ÷ 261D ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] ÷ 00AD ÷ 1F3FB ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 00AD × 0308 ÷ 1F3FB ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] -÷ 00AD ÷ 2764 ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 00AD × 0308 ÷ 2764 ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 00AD ÷ 2640 ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 00AD × 0308 ÷ 2640 ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 00AD ÷ 1F466 ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 00AD × 0308 ÷ 1F466 ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 00AD × 00AD ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3] @@ -1295,8 +1296,8 @@ ÷ 0300 × 0308 ÷ 261D ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] ÷ 0300 ÷ 1F3FB ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 0300 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] -÷ 0300 ÷ 2764 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 0300 × 0308 ÷ 2764 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 0300 ÷ 2640 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 0300 × 0308 ÷ 2640 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 0300 ÷ 1F466 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0300 × 0308 ÷ 1F466 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0300 × 00AD ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3] @@ -1357,8 +1358,8 @@ ÷ 200D × 0308 ÷ 261D ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] ÷ 200D ÷ 1F3FB ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_FE) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 200D × 0308 ÷ 1F3FB ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] -÷ 200D × 2764 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_FE) × [3.3] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 200D × 0308 ÷ 2764 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 200D × 2640 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_FE) × [3.3] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 200D × 0308 ÷ 2640 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 200D × 1F466 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_FE) × [3.3] BOY (EBG) ÷ [0.3] ÷ 200D × 0308 ÷ 1F466 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 200D × 00AD ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_FE) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3] @@ -1419,8 +1420,8 @@ ÷ 0061 × 2060 × 0308 ÷ 261D ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [4.0] WORD JOINER (Format_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] ÷ 0061 × 2060 ÷ 1F3FB ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [4.0] WORD JOINER (Format_FE) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 0061 × 2060 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [4.0] WORD JOINER (Format_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] -÷ 0061 × 2060 ÷ 2764 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [4.0] WORD JOINER (Format_FE) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 0061 × 2060 × 0308 ÷ 2764 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [4.0] WORD JOINER (Format_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 0061 × 2060 ÷ 2640 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [4.0] WORD JOINER (Format_FE) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 0061 × 2060 × 0308 ÷ 2640 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [4.0] WORD JOINER (Format_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 0061 × 2060 ÷ 1F466 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [4.0] WORD JOINER (Format_FE) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0061 × 2060 × 0308 ÷ 1F466 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [4.0] WORD JOINER (Format_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0061 × 2060 × 00AD ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [4.0] WORD JOINER (Format_FE) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3] @@ -1481,8 +1482,8 @@ ÷ 0061 ÷ 003A × 0308 ÷ 261D ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] ÷ 0061 ÷ 003A ÷ 1F3FB ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 0061 ÷ 003A × 0308 ÷ 1F3FB ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] -÷ 0061 ÷ 003A ÷ 2764 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 0061 ÷ 003A × 0308 ÷ 2764 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 0061 ÷ 003A ÷ 2640 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 0061 ÷ 003A × 0308 ÷ 2640 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 0061 ÷ 003A ÷ 1F466 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0061 ÷ 003A × 0308 ÷ 1F466 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0061 ÷ 003A × 00AD ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3] @@ -1543,8 +1544,8 @@ ÷ 0061 ÷ 0027 × 0308 ÷ 261D ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (Single_Quote) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] ÷ 0061 ÷ 0027 ÷ 1F3FB ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (Single_Quote) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 0061 ÷ 0027 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (Single_Quote) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] -÷ 0061 ÷ 0027 ÷ 2764 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (Single_Quote) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 0061 ÷ 0027 × 0308 ÷ 2764 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (Single_Quote) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 0061 ÷ 0027 ÷ 2640 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (Single_Quote) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 0061 ÷ 0027 × 0308 ÷ 2640 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (Single_Quote) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 0061 ÷ 0027 ÷ 1F466 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (Single_Quote) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0061 ÷ 0027 × 0308 ÷ 1F466 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (Single_Quote) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0061 ÷ 0027 × 00AD ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (Single_Quote) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3] @@ -1605,8 +1606,8 @@ ÷ 0061 ÷ 0027 × 2060 × 0308 ÷ 261D ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (Single_Quote) × [4.0] WORD JOINER (Format_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] ÷ 0061 ÷ 0027 × 2060 ÷ 1F3FB ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (Single_Quote) × [4.0] WORD JOINER (Format_FE) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 0061 ÷ 0027 × 2060 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (Single_Quote) × [4.0] WORD JOINER (Format_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] -÷ 0061 ÷ 0027 × 2060 ÷ 2764 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (Single_Quote) × [4.0] WORD JOINER (Format_FE) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 0061 ÷ 0027 × 2060 × 0308 ÷ 2764 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (Single_Quote) × [4.0] WORD JOINER (Format_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 0061 ÷ 0027 × 2060 ÷ 2640 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (Single_Quote) × [4.0] WORD JOINER (Format_FE) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 0061 ÷ 0027 × 2060 × 0308 ÷ 2640 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (Single_Quote) × [4.0] WORD JOINER (Format_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 0061 ÷ 0027 × 2060 ÷ 1F466 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (Single_Quote) × [4.0] WORD JOINER (Format_FE) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0061 ÷ 0027 × 2060 × 0308 ÷ 1F466 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (Single_Quote) × [4.0] WORD JOINER (Format_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0061 ÷ 0027 × 2060 × 00AD ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (Single_Quote) × [4.0] WORD JOINER (Format_FE) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3] @@ -1667,8 +1668,8 @@ ÷ 0061 ÷ 002C × 0308 ÷ 261D ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] ÷ 0061 ÷ 002C ÷ 1F3FB ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 0061 ÷ 002C × 0308 ÷ 1F3FB ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] -÷ 0061 ÷ 002C ÷ 2764 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 0061 ÷ 002C × 0308 ÷ 2764 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 0061 ÷ 002C ÷ 2640 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 0061 ÷ 002C × 0308 ÷ 2640 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 0061 ÷ 002C ÷ 1F466 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0061 ÷ 002C × 0308 ÷ 1F466 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0061 ÷ 002C × 00AD ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3] @@ -1729,8 +1730,8 @@ ÷ 0031 ÷ 003A × 0308 ÷ 261D ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] ÷ 0031 ÷ 003A ÷ 1F3FB ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 0031 ÷ 003A × 0308 ÷ 1F3FB ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] -÷ 0031 ÷ 003A ÷ 2764 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 0031 ÷ 003A × 0308 ÷ 2764 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 0031 ÷ 003A ÷ 2640 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 0031 ÷ 003A × 0308 ÷ 2640 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 0031 ÷ 003A ÷ 1F466 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0031 ÷ 003A × 0308 ÷ 1F466 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0031 ÷ 003A × 00AD ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3] @@ -1791,8 +1792,8 @@ ÷ 0031 ÷ 0027 × 0308 ÷ 261D ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] APOSTROPHE (Single_Quote) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] ÷ 0031 ÷ 0027 ÷ 1F3FB ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] APOSTROPHE (Single_Quote) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 0031 ÷ 0027 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] APOSTROPHE (Single_Quote) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] -÷ 0031 ÷ 0027 ÷ 2764 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] APOSTROPHE (Single_Quote) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 0031 ÷ 0027 × 0308 ÷ 2764 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] APOSTROPHE (Single_Quote) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 0031 ÷ 0027 ÷ 2640 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] APOSTROPHE (Single_Quote) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 0031 ÷ 0027 × 0308 ÷ 2640 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] APOSTROPHE (Single_Quote) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 0031 ÷ 0027 ÷ 1F466 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] APOSTROPHE (Single_Quote) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0031 ÷ 0027 × 0308 ÷ 1F466 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] APOSTROPHE (Single_Quote) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0031 ÷ 0027 × 00AD ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] APOSTROPHE (Single_Quote) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3] @@ -1853,8 +1854,8 @@ ÷ 0031 ÷ 002C × 0308 ÷ 261D ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] ÷ 0031 ÷ 002C ÷ 1F3FB ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 0031 ÷ 002C × 0308 ÷ 1F3FB ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] -÷ 0031 ÷ 002C ÷ 2764 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 0031 ÷ 002C × 0308 ÷ 2764 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 0031 ÷ 002C ÷ 2640 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 0031 ÷ 002C × 0308 ÷ 2640 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 0031 ÷ 002C ÷ 1F466 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0031 ÷ 002C × 0308 ÷ 1F466 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0031 ÷ 002C × 00AD ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3] @@ -1915,8 +1916,8 @@ ÷ 0031 ÷ 002E × 2060 × 0308 ÷ 261D ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) × [4.0] WORD JOINER (Format_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] ÷ 0031 ÷ 002E × 2060 ÷ 1F3FB ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) × [4.0] WORD JOINER (Format_FE) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 0031 ÷ 002E × 2060 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) × [4.0] WORD JOINER (Format_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] -÷ 0031 ÷ 002E × 2060 ÷ 2764 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) × [4.0] WORD JOINER (Format_FE) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] -÷ 0031 ÷ 002E × 2060 × 0308 ÷ 2764 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) × [4.0] WORD JOINER (Format_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 0031 ÷ 002E × 2060 ÷ 2640 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) × [4.0] WORD JOINER (Format_FE) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 0031 ÷ 002E × 2060 × 0308 ÷ 2640 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) × [4.0] WORD JOINER (Format_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 0031 ÷ 002E × 2060 ÷ 1F466 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) × [4.0] WORD JOINER (Format_FE) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0031 ÷ 002E × 2060 × 0308 ÷ 1F466 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) × [4.0] WORD JOINER (Format_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0031 ÷ 002E × 2060 × 00AD ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) × [4.0] WORD JOINER (Format_FE) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3] @@ -1966,7 +1967,7 @@ ÷ 261D × 1F3FB ÷ 261D ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [14.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] ÷ 1F466 × 1F3FB ÷ # ÷ [0.2] BOY (EBG) × [14.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] ÷ 200D × 1F466 × 1F3FB ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_FE) × [3.3] BOY (EBG) × [14.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] -÷ 200D × 2764 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_FE) × [3.3] HEAVY BLACK HEART (Glue_After_Zwj) ÷ [0.3] +÷ 200D × 2640 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_FE) × [3.3] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] ÷ 200D × 1F466 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_FE) × [3.3] BOY (EBG) ÷ [0.3] ÷ 1F466 ÷ 1F466 ÷ # ÷ [0.2] BOY (EBG) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0061 × 0308 × 200D × 0308 × 0062 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [4.0] COMBINING DIAERESIS (Extend_FE) × [4.0] ZERO WIDTH JOINER (ZWJ_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) × [5.0] LATIN SMALL LETTER B (ALetter) ÷ [0.3] diff --git a/lib/unicore/auxiliary/WordBreakProperty.txt b/lib/unicore/auxiliary/WordBreakProperty.txt index 6ccba54650..4c5440a894 100644 --- a/lib/unicore/auxiliary/WordBreakProperty.txt +++ b/lib/unicore/auxiliary/WordBreakProperty.txt @@ -1,6 +1,6 @@ -# WordBreakProperty-9.0.0.txt -# Date: 2016-06-01, 10:34:38 GMT -# © 2016 Unicode®, Inc. +# WordBreakProperty-10.0.0.txt +# Date: 2017-03-10, 02:00:42 GMT +# © 2017 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html # @@ -133,6 +133,7 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW 0ACB..0ACC ; Extend # Mc [2] GUJARATI VOWEL SIGN O..GUJARATI VOWEL SIGN AU 0ACD ; Extend # Mn GUJARATI SIGN VIRAMA 0AE2..0AE3 ; Extend # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0AFA..0AFF ; Extend # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE 0B01 ; Extend # Mn ORIYA SIGN CANDRABINDU 0B02..0B03 ; Extend # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA 0B3C ; Extend # Mn ORIYA SIGN NUKTA @@ -174,8 +175,9 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW 0CCC..0CCD ; Extend # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA 0CD5..0CD6 ; Extend # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK 0CE2..0CE3 ; Extend # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL -0D01 ; Extend # Mn MALAYALAM SIGN CANDRABINDU +0D00..0D01 ; Extend # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU 0D02..0D03 ; Extend # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA +0D3B..0D3C ; Extend # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA 0D3E..0D40 ; Extend # Mc [3] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN II 0D41..0D44 ; Extend # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR 0D46..0D48 ; Extend # Mc [3] MALAYALAM VOWEL SIGN E..MALAYALAM VOWEL SIGN AI @@ -310,8 +312,9 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW 1CED ; Extend # Mn VEDIC SIGN TIRYAK 1CF2..1CF3 ; Extend # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA 1CF4 ; Extend # Mn VEDIC TONE CANDRA ABOVE +1CF7 ; Extend # Mc VEDIC SIGN ATIKRAMA 1CF8..1CF9 ; Extend # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE -1DC0..1DF5 ; Extend # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE +1DC0..1DF9 ; Extend # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW 1DFB..1DFF ; Extend # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 200C ; Extend # Cf ZERO WIDTH NON-JOINER 20D0..20DC ; Extend # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE @@ -475,6 +478,19 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 11722..11725 ; Extend # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU 11726 ; Extend # Mc AHOM VOWEL SIGN E 11727..1172B ; Extend # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER +11A01..11A06 ; Extend # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O +11A07..11A08 ; Extend # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU +11A09..11A0A ; Extend # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A33..11A38 ; Extend # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A39 ; Extend # Mc ZANABAZAR SQUARE SIGN VISARGA +11A3B..11A3E ; Extend # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A47 ; Extend # Mn ZANABAZAR SQUARE SUBJOINER +11A51..11A56 ; Extend # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A57..11A58 ; Extend # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU +11A59..11A5B ; Extend # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A8A..11A96 ; Extend # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A97 ; Extend # Mc SOYOMBO SIGN VISARGA +11A98..11A99 ; Extend # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER 11C2F ; Extend # Mc BHAIKSUKI VOWEL SIGN AA 11C30..11C36 ; Extend # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L 11C38..11C3D ; Extend # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA @@ -487,6 +503,11 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 11CB2..11CB3 ; Extend # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E 11CB4 ; Extend # Mc MARCHEN VOWEL SIGN O 11CB5..11CB6 ; Extend # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D31..11D36 ; Extend # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; Extend # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; Extend # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45 ; Extend # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D47 ; Extend # Mn MASARAM GONDI RA-KARA 16AF0..16AF4 ; Extend # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; Extend # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM 16F51..16F7E ; Extend # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG @@ -515,7 +536,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2196 +# Total code points: 2276 # ================================================ @@ -580,10 +601,15 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK 0294 ; ALetter # Lo LATIN LETTER GLOTTAL STOP 0295..02AF ; ALetter # L& [27] LATIN LETTER PHARYNGEAL VOICED FRICATIVE..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL 02B0..02C1 ; ALetter # Lm [18] MODIFIER LETTER SMALL H..MODIFIER LETTER REVERSED GLOTTAL STOP +02C2..02C5 ; ALetter # Sk [4] MODIFIER LETTER LEFT ARROWHEAD..MODIFIER LETTER DOWN ARROWHEAD 02C6..02D1 ; ALetter # Lm [12] MODIFIER LETTER CIRCUMFLEX ACCENT..MODIFIER LETTER HALF TRIANGULAR COLON +02D2..02D7 ; ALetter # Sk [6] MODIFIER LETTER CENTRED RIGHT HALF RING..MODIFIER LETTER MINUS SIGN +02DE..02DF ; ALetter # Sk [2] MODIFIER LETTER RHOTIC HOOK..MODIFIER LETTER CROSS ACCENT 02E0..02E4 ; ALetter # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP 02EC ; ALetter # Lm MODIFIER LETTER VOICING +02ED ; ALetter # Sk MODIFIER LETTER UNASPIRATED 02EE ; ALetter # Lm MODIFIER LETTER DOUBLE APOSTROPHE +02EF..02FF ; ALetter # Sk [17] MODIFIER LETTER LOW DOWN ARROWHEAD..MODIFIER LETTER LOW LEFT ARROW 0370..0373 ; ALetter # L& [4] GREEK CAPITAL LETTER HETA..GREEK SMALL LETTER ARCHAIC SAMPI 0374 ; ALetter # Lm GREEK NUMERAL SIGN 0376..0377 ; ALetter # L& [2] GREEK CAPITAL LETTER PAMPHYLIAN DIGAMMA..GREEK SMALL LETTER PAMPHYLIAN DIGAMMA @@ -623,6 +649,7 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK 0824 ; ALetter # Lm SAMARITAN MODIFIER LETTER SHORT A 0828 ; ALetter # Lm SAMARITAN MODIFIER LETTER I 0840..0858 ; ALetter # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN +0860..086A ; ALetter # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 08A0..08B4 ; ALetter # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW 08B6..08BD ; ALetter # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON 0904..0939 ; ALetter # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA @@ -642,6 +669,7 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK 09DC..09DD ; ALetter # Lo [2] BENGALI LETTER RRA..BENGALI LETTER RHA 09DF..09E1 ; ALetter # Lo [3] BENGALI LETTER YYA..BENGALI LETTER VOCALIC LL 09F0..09F1 ; ALetter # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL +09FC ; ALetter # Lo BENGALI LETTER VEDIC ANUSVARA 0A05..0A0A ; ALetter # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU 0A0F..0A10 ; ALetter # Lo [2] GURMUKHI LETTER EE..GURMUKHI LETTER AI 0A13..0A28 ; ALetter # Lo [22] GURMUKHI LETTER OO..GURMUKHI LETTER NA @@ -847,7 +875,7 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK 3005 ; ALetter # Lm IDEOGRAPHIC ITERATION MARK 303B ; ALetter # Lm VERTICAL IDEOGRAPHIC ITERATION MARK 303C ; ALetter # Lo MASU MARK -3105..312D ; ALetter # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH +3105..312E ; ALetter # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE 3131..318E ; ALetter # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE 31A0..31BA ; ALetter # Lo [27] BOPOMOFO LETTER BU..BOPOMOFO LETTER ZY A000..A014 ; ALetter # Lo [21] YI SYLLABLE IT..YI SYLLABLE E @@ -867,10 +895,12 @@ A69C..A69D ; ALetter # Lm [2] MODIFIER LETTER CYRILLIC HARD SIGN..MODIFIER A6A0..A6E5 ; ALetter # Lo [70] BAMUM LETTER A..BAMUM LETTER KI A6E6..A6EF ; ALetter # Nl [10] BAMUM LETTER MO..BAMUM LETTER KOGHOM A717..A71F ; ALetter # Lm [9] MODIFIER LETTER DOT VERTICAL BAR..MODIFIER LETTER LOW INVERTED EXCLAMATION MARK +A720..A721 ; ALetter # Sk [2] MODIFIER LETTER STRESS AND HIGH TONE..MODIFIER LETTER STRESS AND LOW TONE A722..A76F ; ALetter # L& [78] LATIN CAPITAL LETTER EGYPTOLOGICAL ALEF..LATIN SMALL LETTER CON A770 ; ALetter # Lm MODIFIER LETTER US A771..A787 ; ALetter # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER INSULAR T A788 ; ALetter # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT +A789..A78A ; ALetter # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; ALetter # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; ALetter # Lo LATIN LETTER SINOLOGICAL DOT A790..A7AE ; ALetter # L& [31] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER SMALL CAPITAL I @@ -904,6 +934,7 @@ AB11..AB16 ; ALetter # Lo [6] ETHIOPIC SYLLABLE DZU..ETHIOPIC SYLLABLE DZO AB20..AB26 ; ALetter # Lo [7] ETHIOPIC SYLLABLE CCHHA..ETHIOPIC SYLLABLE CCHHO AB28..AB2E ; ALetter # Lo [7] ETHIOPIC SYLLABLE BBA..ETHIOPIC SYLLABLE BBO AB30..AB5A ; ALetter # L& [43] LATIN SMALL LETTER BARRED ALPHA..LATIN SMALL LETTER Y WITH SHORT RIGHT LEG +AB5B ; ALetter # Sk MODIFIER BREVE WITH INVERTED BREVE AB5C..AB5F ; ALetter # Lm [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U WITH LEFT HOOK AB60..AB65 ; ALetter # L& [6] LATIN SMALL LETTER SAKHA YAT..GREEK LETTER SMALL CAPITAL OMEGA AB70..ABBF ; ALetter # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA @@ -938,7 +969,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 10280..1029C ; ALetter # Lo [29] LYCIAN LETTER A..LYCIAN LETTER X 102A0..102D0 ; ALetter # Lo [49] CARIAN LETTER A..CARIAN LETTER UUU3 10300..1031F ; ALetter # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS -10330..10340 ; ALetter # Lo [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA +1032D..10340 ; ALetter # Lo [20] OLD ITALIC LETTER YE..GOTHIC LETTER PAIRTHRA 10341 ; ALetter # Nl GOTHIC LETTER NINETY 10342..10349 ; ALetter # Lo [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL 1034A ; ALetter # Nl GOTHIC LETTER NINE HUNDRED @@ -1024,11 +1055,21 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 11680..116AA ; ALetter # Lo [43] TAKRI LETTER A..TAKRI LETTER RRA 118A0..118DF ; ALetter # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 118FF ; ALetter # Lo WARANG CITI OM +11A00 ; ALetter # Lo ZANABAZAR SQUARE LETTER A +11A0B..11A32 ; ALetter # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA +11A3A ; ALetter # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA +11A50 ; ALetter # Lo SOYOMBO LETTER A +11A5C..11A83 ; ALetter # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA +11A86..11A89 ; ALetter # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA 11AC0..11AF8 ; ALetter # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL 11C00..11C08 ; ALetter # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E ; ALetter # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA 11C40 ; ALetter # Lo BHAIKSUKI SIGN AVAGRAHA 11C72..11C8F ; ALetter # Lo [30] MARCHEN LETTER KA..MARCHEN LETTER A +11D00..11D06 ; ALetter # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E +11D08..11D09 ; ALetter # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O +11D0B..11D30 ; ALetter # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA +11D46 ; ALetter # Lo MASARAM GONDI REPHA 12000..12399 ; ALetter # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; ALetter # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12480..12543 ; ALetter # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU @@ -1044,7 +1085,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 16F00..16F44 ; ALetter # Lo [69] MIAO LETTER PA..MIAO LETTER HHA 16F50 ; ALetter # Lo MIAO LETTER NASALIZATION 16F93..16F9F ; ALetter # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 -16FE0 ; ALetter # Lm TANGUT ITERATION MARK +16FE0..16FE1 ; ALetter # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK 1BC00..1BC6A ; ALetter # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M 1BC70..1BC7C ; ALetter # Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK 1BC80..1BC88 ; ALetter # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL @@ -1118,13 +1159,12 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1F150..1F169 ; ALetter # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; ALetter # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 27992 +# Total code points: 28179 # ================================================ 003A ; MidLetter # Po COLON 00B7 ; MidLetter # Po MIDDLE DOT -02D7 ; MidLetter # Sk MODIFIER LETTER MINUS SIGN 0387 ; MidLetter # Po GREEK ANO TELEIA 05F4 ; MidLetter # Po HEBREW PUNCTUATION GERSHAYIM 2027 ; MidLetter # Po HYPHENATION POINT @@ -1132,7 +1172,7 @@ FE13 ; MidLetter # Po PRESENTATION FORM FOR VERTICAL COLON FE55 ; MidLetter # Po SMALL COLON FF1A ; MidLetter # Po FULLWIDTH COLON -# Total code points: 9 +# Total code points: 8 # ================================================ @@ -1217,12 +1257,13 @@ ABF0..ABF9 ; Numeric # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT N 11730..11739 ; Numeric # Nd [10] AHOM DIGIT ZERO..AHOM DIGIT NINE 118E0..118E9 ; Numeric # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE 11C50..11C59 ; Numeric # Nd [10] BHAIKSUKI DIGIT ZERO..BHAIKSUKI DIGIT NINE +11D50..11D59 ; Numeric # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE 16A60..16A69 ; Numeric # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE 16B50..16B59 ; Numeric # Nd [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE 1D7CE..1D7FF ; Numeric # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE 1E950..1E959 ; Numeric # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE -# Total code points: 571 +# Total code points: 581 # ================================================ @@ -1242,8 +1283,9 @@ FF3F ; ExtendNumLet # Pc FULLWIDTH LOW LINE 26F9 ; E_Base # So PERSON WITH BALL 270A..270D ; E_Base # So [4] RAISED FIST..WRITING HAND 1F385 ; E_Base # So FATHER CHRISTMAS -1F3C3..1F3C4 ; E_Base # So [2] RUNNER..SURFER -1F3CA..1F3CB ; E_Base # So [2] SWIMMER..WEIGHT LIFTER +1F3C2..1F3C4 ; E_Base # So [3] SNOWBOARDER..SURFER +1F3C7 ; E_Base # So HORSE RACING +1F3CA..1F3CC ; E_Base # So [3] SWIMMER..GOLFER 1F442..1F443 ; E_Base # So [2] EAR..NOSE 1F446..1F450 ; E_Base # So [11] WHITE UP POINTING BACKHAND INDEX..OPEN HANDS SIGN 1F46E ; E_Base # So POLICE OFFICER @@ -1252,7 +1294,7 @@ FF3F ; ExtendNumLet # Pc FULLWIDTH LOW LINE 1F481..1F483 ; E_Base # So [3] INFORMATION DESK PERSON..DANCER 1F485..1F487 ; E_Base # So [3] NAIL POLISH..HAIRCUT 1F4AA ; E_Base # So FLEXED BICEPS -1F575 ; E_Base # So SLEUTH OR SPY +1F574..1F575 ; E_Base # So [2] MAN IN BUSINESS SUIT LEVITATING..SLEUTH OR SPY 1F57A ; E_Base # So MAN DANCING 1F590 ; E_Base # So RAISED HAND WITH FINGERS SPLAYED 1F595..1F596 ; E_Base # So [2] REVERSED HAND WITH MIDDLE FINGER EXTENDED..RAISED HAND WITH PART BETWEEN MIDDLE AND RING FINGERS @@ -1261,13 +1303,15 @@ FF3F ; ExtendNumLet # Pc FULLWIDTH LOW LINE 1F6A3 ; E_Base # So ROWBOAT 1F6B4..1F6B6 ; E_Base # So [3] BICYCLIST..PEDESTRIAN 1F6C0 ; E_Base # So BATH -1F918..1F91E ; E_Base # So [7] SIGN OF THE HORNS..HAND WITH INDEX AND MIDDLE FINGERS CROSSED +1F6CC ; E_Base # So SLEEPING ACCOMMODATION +1F918..1F91C ; E_Base # So [5] SIGN OF THE HORNS..RIGHT-FACING FIST +1F91E..1F91F ; E_Base # So [2] HAND WITH INDEX AND MIDDLE FINGERS CROSSED..I LOVE YOU HAND SIGN 1F926 ; E_Base # So FACE PALM -1F930 ; E_Base # So PREGNANT WOMAN -1F933..1F939 ; E_Base # So [7] SELFIE..JUGGLING -1F93C..1F93E ; E_Base # So [3] WRESTLERS..HANDBALL +1F930..1F939 ; E_Base # So [10] PREGNANT WOMAN..JUGGLING +1F93D..1F93E ; E_Base # So [2] WATER POLO..HANDBALL +1F9D1..1F9DD ; E_Base # So [13] ADULT..ELF -# Total code points: 79 +# Total code points: 98 # ================================================ @@ -1283,11 +1327,28 @@ FF3F ; ExtendNumLet # Pc FULLWIDTH LOW LINE # ================================================ +2640 ; Glue_After_Zwj # So FEMALE SIGN +2642 ; Glue_After_Zwj # So MALE SIGN +2695..2696 ; Glue_After_Zwj # So [2] STAFF OF AESCULAPIUS..SCALES +2708 ; Glue_After_Zwj # So AIRPLANE 2764 ; Glue_After_Zwj # So HEAVY BLACK HEART +1F308 ; Glue_After_Zwj # So RAINBOW +1F33E ; Glue_After_Zwj # So EAR OF RICE +1F373 ; Glue_After_Zwj # So COOKING +1F393 ; Glue_After_Zwj # So GRADUATION CAP +1F3A4 ; Glue_After_Zwj # So MICROPHONE +1F3A8 ; Glue_After_Zwj # So ARTIST PALETTE +1F3EB ; Glue_After_Zwj # So SCHOOL +1F3ED ; Glue_After_Zwj # So FACTORY 1F48B ; Glue_After_Zwj # So KISS MARK +1F4BB..1F4BC ; Glue_After_Zwj # So [2] PERSONAL COMPUTER..BRIEFCASE +1F527 ; Glue_After_Zwj # So WRENCH +1F52C ; Glue_After_Zwj # So MICROSCOPE 1F5E8 ; Glue_After_Zwj # So LEFT SPEECH BUBBLE +1F680 ; Glue_After_Zwj # So ROCKET +1F692 ; Glue_After_Zwj # So FIRE ENGINE -# Total code points: 3 +# Total code points: 22 # ================================================ diff --git a/lib/unicore/extracted/DBidiClass.txt b/lib/unicore/extracted/DBidiClass.txt index 451cef2a63..ca9cc6ad9a 100644 --- a/lib/unicore/extracted/DBidiClass.txt +++ b/lib/unicore/extracted/DBidiClass.txt @@ -1,6 +1,6 @@ -# DerivedBidiClass-9.0.0.txt -# Date: 2016-06-01, 10:34:22 GMT -# © 2016 Unicode®, Inc. +# DerivedBidiClass-10.0.0.txt +# Date: 2017-03-08, 08:41:46 GMT +# © 2017 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html # @@ -14,44 +14,21 @@ # reserved for right-to-left scripts are given either types R or AL. # # The unassigned code points that default to AL are in the ranges: -# [\u0600-\u07BF \u08A0-\u08FF \uFB50-\uFDCF \uFDF0-\uFDFF \uFE70-\uFEFF \U0001EE00-\U0001EEFF] +# [\u0600-\u07BF \u0860-\u086F \u08A0-\u08FF +# \uFB50-\uFDCF \uFDF0-\uFDFF \uFE70-\uFEFF \U0001EE00-\U0001EEFF] # -# Arabic: U+0600 - U+06FF -# Syriac: U+0700 - U+074F -# Arabic_Supplement: U+0750 - U+077F -# Thaana: U+0780 - U+07BF -# Arabic Extended-A: U+08A0 - U+08FF -# Arabic_Presentation_Forms_A: -# U+FB50 - U+FDCF -# U+FDF0 - U+FDFF -# Arabic_Presentation_Forms_B: -# U+FE70 - U+FEFF -# Arabic Mathematical Alphabetic Symbols: -# U+1EE00 - U+1EEFF +# This includes code points in the Arabic, Syriac, and Thaana blocks, among others. # # The unassigned code points that default to R are in the ranges: -# [\u0590-\u05FF \u07C0-\u089F \uFB1D-\uFB4F \U00010800-\U00010FFF \U0001E800-\U0001EDFF \U0001EF00-\U0001EFFF] +# [\u0590-\u05FF \u07C0-\u085F \u0870-\u089F \uFB1D-\uFB4F +# \U00010800-\U00010FFF \U0001E800-\U0001EDFF \U0001EF00-\U0001EFFF] # -# Hebrew: U+0590 - U+05FF -# NKo: U+07C0 - U+07FF -# Cypriot_Syllabary: U+10800 - U+1083F -# Phoenician: U+10900 - U+1091F -# Lydian: U+10920 - U+1093F -# Meroitic Hieroglyphs: -# U+10980 - U+1099F -# Meroitic Cursive: U+109A0 - U+109FF -# Kharoshthi: U+10A00 - U+10A5F -# and any others in the ranges: -# U+0800 - U+089F, -# U+FB1D - U+FB4F, -# U+10840 - U+10FFF, -# U+1E800 - U+1EDFF, -# U+1EF00 - U+1EFFF +# This includes code points in the Hebrew, NKo, and Phoenician blocks, among others. # # The unassigned code points that default to ET are in the range: # [\u20A0-\u20CF] # -# Currency Symbols: U+20A0 - U+20CF +# This consists of code points in the Currency Symbols block. # # The unassigned code points that default to BN have one of the following properties: # Default_Ignorable_Code_Point @@ -138,6 +115,8 @@ 09F0..09F1 ; L # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL 09F4..09F9 ; L # No [6] BENGALI CURRENCY NUMERATOR ONE..BENGALI CURRENCY DENOMINATOR SIXTEEN 09FA ; L # So BENGALI ISSHAR +09FC ; L # Lo BENGALI LETTER VEDIC ANUSVARA +09FD ; L # Po BENGALI ABBREVIATION SIGN 0A03 ; L # Mc GURMUKHI SIGN VISARGA 0A05..0A0A ; L # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU 0A0F..0A10 ; L # Lo [2] GURMUKHI LETTER EE..GURMUKHI LETTER AI @@ -463,6 +442,7 @@ 1CEE..1CF1 ; L # Lo [4] VEDIC SIGN HEXIFORM LONG ANUSVARA..VEDIC SIGN ANUSVARA UBHAYATO MUKHA 1CF2..1CF3 ; L # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA 1CF5..1CF6 ; L # Lo [2] VEDIC SIGN JIHVAMULIYA..VEDIC SIGN UPADHMANIYA +1CF7 ; L # Mc VEDIC SIGN ATIKRAMA 1D00..1D2B ; L # L& [44] LATIN LETTER SMALL CAPITAL A..CYRILLIC LETTER SMALL CAPITAL EL 1D2C..1D6A ; L # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI 1D6B..1D77 ; L # L& [13] LATIN SMALL LETTER UE..LATIN SMALL LETTER TURNED G @@ -553,7 +533,7 @@ 30A1..30FA ; L # Lo [90] KATAKANA LETTER SMALL A..KATAKANA LETTER VO 30FC..30FE ; L # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK 30FF ; L # Lo KATAKANA DIGRAPH KOTO -3105..312D ; L # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH +3105..312E ; L # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE 3131..318E ; L # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE 3190..3191 ; L # So [2] IDEOGRAPHIC ANNOTATION LINKING MARK..IDEOGRAPHIC ANNOTATION REVERSE MARK 3192..3195 ; L # No [4] IDEOGRAPHIC ANNOTATION ONE MARK..IDEOGRAPHIC ANNOTATION FOUR MARK @@ -574,7 +554,7 @@ 337B..33DD ; L # So [99] SQUARE ERA NAME HEISEI..SQUARE WB 33E0..33FE ; L # So [31] IDEOGRAPHIC TELEGRAPH SYMBOL FOR DAY ONE..IDEOGRAPHIC TELEGRAPH SYMBOL FOR DAY THIRTY-ONE 3400..4DB5 ; L # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 -4E00..9FD5 ; L # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5 +4E00..9FEA ; L # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA A000..A014 ; L # Lo [21] YI SYLLABLE IT..YI SYLLABLE E A015 ; L # Lm YI SYLLABLE WU A016..A48C ; L # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR @@ -728,7 +708,7 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER 102A0..102D0 ; L # Lo [49] CARIAN LETTER A..CARIAN LETTER UUU3 10300..1031F ; L # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS 10320..10323 ; L # No [4] OLD ITALIC NUMERAL ONE..OLD ITALIC NUMERAL FIFTY -10330..10340 ; L # Lo [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA +1032D..10340 ; L # Lo [20] OLD ITALIC LETTER YE..GOTHIC LETTER PAIRTHRA 10341 ; L # Nl GOTHIC LETTER NINETY 10342..10349 ; L # Lo [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL 1034A ; L # Nl GOTHIC LETTER NINE HUNDRED @@ -862,6 +842,19 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER 118E0..118E9 ; L # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE 118EA..118F2 ; L # No [9] WARANG CITI NUMBER TEN..WARANG CITI NUMBER NINETY 118FF ; L # Lo WARANG CITI OM +11A00 ; L # Lo ZANABAZAR SQUARE LETTER A +11A07..11A08 ; L # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU +11A0B..11A32 ; L # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA +11A39 ; L # Mc ZANABAZAR SQUARE SIGN VISARGA +11A3A ; L # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA +11A3F..11A46 ; L # Po [8] ZANABAZAR SQUARE INITIAL HEAD MARK..ZANABAZAR SQUARE CLOSING DOUBLE-LINED HEAD MARK +11A50 ; L # Lo SOYOMBO LETTER A +11A57..11A58 ; L # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU +11A5C..11A83 ; L # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA +11A86..11A89 ; L # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA +11A97 ; L # Mc SOYOMBO SIGN VISARGA +11A9A..11A9C ; L # Po [3] SOYOMBO MARK TSHEG..SOYOMBO MARK DOUBLE SHAD +11A9E..11AA2 ; L # Po [5] SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME..SOYOMBO TERMINAL MARK-2 11AC0..11AF8 ; L # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL 11C00..11C08 ; L # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E ; L # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA @@ -877,6 +870,11 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER 11CA9 ; L # Mc MARCHEN SUBJOINED LETTER YA 11CB1 ; L # Mc MARCHEN VOWEL SIGN I 11CB4 ; L # Mc MARCHEN VOWEL SIGN O +11D00..11D06 ; L # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E +11D08..11D09 ; L # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O +11D0B..11D30 ; L # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA +11D46 ; L # Lo MASARAM GONDI REPHA +11D50..11D59 ; L # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE 12000..12399 ; L # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; L # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12470..12474 ; L # Po [5] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON @@ -903,10 +901,11 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER 16F50 ; L # Lo MIAO LETTER NASALIZATION 16F51..16F7E ; L # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG 16F93..16F9F ; L # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 -16FE0 ; L # Lm TANGUT ITERATION MARK +16FE0..16FE1 ; L # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK 17000..187EC ; L # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC 18800..18AF2 ; L # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755 -1B000..1B001 ; L # Lo [2] KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE +1B000..1B11E ; L # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1B170..1B2FB ; L # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 1BC00..1BC6A ; L # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M 1BC70..1BC7C ; L # Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK 1BC80..1BC88 ; L # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL @@ -975,12 +974,13 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER 2A700..2B734 ; L # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 2B740..2B81D ; L # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; L # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 +2CEB0..2EBE0 ; L # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; L # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D F0000..FFFFD ; L # Co [65534] <private-use-F0000>..<private-use-FFFFD> 100000..10FFFD; L # Co [65534] <private-use-100000>..<private-use-10FFFD> -# The above property value applies to 841609 code points not listed here. -# Total code points: 1097280 +# The above property value applies to 833103 code points not listed here. +# Total code points: 1097124 # ================================================ @@ -1012,7 +1012,8 @@ F0000..FFFFD ; L # Co [65534] <private-use-F0000>..<private-use-FFFFD> 0840..0858 ; R # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 085C..085D ; R # Cn [2] <reserved-085C>..<reserved-085D> 085E ; R # Po MANDAIC PUNCTUATION -085F..089F ; R # Cn [65] <reserved-085F>..<reserved-089F> +085F ; R # Cn <reserved-085F> +0870..089F ; R # Cn [48] <reserved-0870>..<reserved-089F> 200F ; R # Cf RIGHT-TO-LEFT MARK FB1D ; R # Lo HEBREW LETTER YOD WITH HIRIQ FB1F..FB28 ; R # Lo [10] HEBREW LIGATURE YIDDISH YOD YOD PATAH..HEBREW LETTER WIDE TAV @@ -1129,7 +1130,7 @@ FB46..FB4F ; R # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATURE AL 1E960..1EDFF ; R # Cn [1184] <reserved-1E960>..<reserved-1EDFF> 1EF00..1EFFF ; R # Cn [256] <reserved-1EF00>..<reserved-1EFFF> -# Total code points: 4070 +# Total code points: 4054 # ================================================ @@ -1187,8 +1188,8 @@ FF0D ; ES # Pd FULLWIDTH HYPHEN-MINUS 0E3F ; ET # Sc THAI CURRENCY SYMBOL BAHT 17DB ; ET # Sc KHMER CURRENCY SYMBOL RIEL 2030..2034 ; ET # Po [5] PER MILLE SIGN..TRIPLE PRIME -20A0..20BE ; ET # Sc [31] EURO-CURRENCY SIGN..LARI SIGN -20BF..20CF ; ET # Cn [17] <reserved-20BF>..<reserved-20CF> +20A0..20BF ; ET # Sc [32] EURO-CURRENCY SIGN..BITCOIN SIGN +20C0..20CF ; ET # Cn [16] <reserved-20C0>..<reserved-20CF> 212E ; ET # So ESTIMATED SYMBOL 2213 ; ET # Sm MINUS-OR-PLUS SIGN A838 ; ET # Sc NORTH INDIC RUPEE MARK @@ -1443,8 +1444,7 @@ FF1A ; CS # Po FULLWIDTH COLON 239B..23B3 ; ON # Sm [25] LEFT PARENTHESIS UPPER HOOK..SUMMATION BOTTOM 23B4..23DB ; ON # So [40] TOP SQUARE BRACKET..FUSE 23DC..23E1 ; ON # Sm [6] TOP PARENTHESIS..BOTTOM TORTOISE SHELL BRACKET -23E2..23FE ; ON # So [29] WHITE TRAPEZIUM..POWER SLEEP SYMBOL -2400..2426 ; ON # So [39] SYMBOL FOR NULL..SYMBOL FOR SUBSTITUTE FORM TWO +23E2..2426 ; ON # So [69] WHITE TRAPEZIUM..SYMBOL FOR SUBSTITUTE FORM TWO 2440..244A ; ON # So [11] OCR HOOK..OCR DOUBLE BACKSLASH 2460..2487 ; ON # No [40] CIRCLED DIGIT ONE..PARENTHESIZED NUMBER TWENTY 24EA..24FF ; ON # No [22] CIRCLED DIGIT ZERO..NEGATIVE CIRCLED DIGIT ZERO @@ -1529,7 +1529,7 @@ FF1A ; CS # Po FULLWIDTH COLON 2B76..2B95 ; ON # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW 2B98..2BB9 ; ON # So [34] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..UP ARROWHEAD IN A RECTANGLE BOX 2BBD..2BC8 ; ON # So [12] BALLOT BOX WITH LIGHT X..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED -2BCA..2BD1 ; ON # So [8] TOP HALF BLACK CIRCLE..UNCERTAINTY SIGN +2BCA..2BD2 ; ON # So [9] TOP HALF BLACK CIRCLE..GROUP MARK 2BEC..2BEF ; ON # So [4] LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS..DOWNWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS 2CE5..2CEA ; ON # So [6] COPTIC SYMBOL MI RO..COPTIC SYMBOL SHIMA SIMA 2CF9..2CFC ; ON # Po [4] COPTIC OLD NUBIAN FULL STOP..COPTIC OLD NUBIAN VERSE DIVIDER @@ -1572,7 +1572,7 @@ FF1A ; CS # Po FULLWIDTH COLON 2E40 ; ON # Pd DOUBLE HYPHEN 2E41 ; ON # Po REVERSED COMMA 2E42 ; ON # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK -2E43..2E44 ; ON # Po [2] DASH WITH LEFT UPTURN..DOUBLE SUSPENSION MARK +2E43..2E49 ; ON # Po [7] DASH WITH LEFT UPTURN..DOUBLE STACKED COMMA 2E80..2E99 ; ON # So [26] CJK RADICAL REPEAT..CJK RADICAL RAP 2E9B..2EF3 ; ON # So [89] CJK RADICAL CHOKE..CJK RADICAL C-SIMPLIFIED TURTLE 2F00..2FD5 ; ON # So [214] KANGXI RADICAL ONE..KANGXI RADICAL FLUTE @@ -1737,11 +1737,12 @@ FFFC..FFFD ; ON # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTE 1F0D1..1F0F5 ; ON # So [37] PLAYING CARD ACE OF CLUBS..PLAYING CARD TRUMP-21 1F10B..1F10C ; ON # No [2] DINGBAT CIRCLED SANS-SERIF DIGIT ZERO..DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ZERO 1F16A..1F16B ; ON # So [2] RAISED MC SIGN..RAISED MD SIGN +1F260..1F265 ; ON # So [6] ROUNDED SYMBOL FOR FU..ROUNDED SYMBOL FOR CAI 1F300..1F3FA ; ON # So [251] CYCLONE..AMPHORA 1F3FB..1F3FF ; ON # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6 -1F400..1F6D2 ; ON # So [723] RAT..SHOPPING TROLLEY +1F400..1F6D4 ; ON # So [725] RAT..PAGODA 1F6E0..1F6EC ; ON # So [13] HAMMER AND WRENCH..AIRPLANE ARRIVING -1F6F0..1F6F6 ; ON # So [7] SATELLITE..CANOE +1F6F0..1F6F8 ; ON # So [9] SATELLITE..FLYING SAUCER 1F700..1F773 ; ON # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE 1F780..1F7D4 ; ON # So [85] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..HEAVY TWELVE POINTED PINWHEEL STAR 1F800..1F80B ; ON # So [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD @@ -1749,16 +1750,15 @@ FFFC..FFFD ; ON # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTE 1F850..1F859 ; ON # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW 1F860..1F887 ; ON # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW 1F890..1F8AD ; ON # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS -1F910..1F91E ; ON # So [15] ZIPPER-MOUTH FACE..HAND WITH INDEX AND MIDDLE FINGERS CROSSED -1F920..1F927 ; ON # So [8] FACE WITH COWBOY HAT..SNEEZING FACE -1F930 ; ON # So PREGNANT WOMAN -1F933..1F93E ; ON # So [12] SELFIE..HANDBALL -1F940..1F94B ; ON # So [12] WILTED FLOWER..MARTIAL ARTS UNIFORM -1F950..1F95E ; ON # So [15] CROISSANT..PANCAKES -1F980..1F991 ; ON # So [18] CRAB..SQUID +1F900..1F90B ; ON # So [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT +1F910..1F93E ; ON # So [47] ZIPPER-MOUTH FACE..HANDBALL +1F940..1F94C ; ON # So [13] WILTED FLOWER..CURLING STONE +1F950..1F96B ; ON # So [28] CROISSANT..CANNED FOOD +1F980..1F997 ; ON # So [24] CRAB..CRICKET 1F9C0 ; ON # So CHEESE WEDGE +1F9D0..1F9E6 ; ON # So [23] FACE WITH MONOCLE..SOCKS -# Total code points: 5267 +# Total code points: 5350 # ================================================ @@ -1859,6 +1859,7 @@ FFFFE..FFFFF ; BN # Cn [2] <noncharacter-FFFFE>..<noncharacter-FFFFF> 0AC7..0AC8 ; NSM # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI 0ACD ; NSM # Mn GUJARATI SIGN VIRAMA 0AE2..0AE3 ; NSM # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0AFA..0AFF ; NSM # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE 0B01 ; NSM # Mn ORIYA SIGN CANDRABINDU 0B3C ; NSM # Mn ORIYA SIGN NUKTA 0B3F ; NSM # Mn ORIYA VOWEL SIGN I @@ -1879,7 +1880,8 @@ FFFFE..FFFFF ; BN # Cn [2] <noncharacter-FFFFE>..<noncharacter-FFFFF> 0CBC ; NSM # Mn KANNADA SIGN NUKTA 0CCC..0CCD ; NSM # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA 0CE2..0CE3 ; NSM # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL -0D01 ; NSM # Mn MALAYALAM SIGN CANDRABINDU +0D00..0D01 ; NSM # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU +0D3B..0D3C ; NSM # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA 0D41..0D44 ; NSM # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR 0D4D ; NSM # Mn MALAYALAM SIGN VIRAMA 0D62..0D63 ; NSM # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL @@ -1964,7 +1966,7 @@ FFFFE..FFFFF ; BN # Cn [2] <noncharacter-FFFFE>..<noncharacter-FFFFF> 1CED ; NSM # Mn VEDIC SIGN TIRYAK 1CF4 ; NSM # Mn VEDIC TONE CANDRA ABOVE 1CF8..1CF9 ; NSM # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE -1DC0..1DF5 ; NSM # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE +1DC0..1DF9 ; NSM # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW 1DFB..1DFF ; NSM # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 20D0..20DC ; NSM # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE 20DD..20E0 ; NSM # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH @@ -2066,12 +2068,26 @@ FE20..FE2F ; NSM # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC 1171D..1171F ; NSM # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA 11722..11725 ; NSM # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU 11727..1172B ; NSM # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER +11A01..11A06 ; NSM # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O +11A09..11A0A ; NSM # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A33..11A38 ; NSM # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A3B..11A3E ; NSM # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A47 ; NSM # Mn ZANABAZAR SQUARE SUBJOINER +11A51..11A56 ; NSM # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A59..11A5B ; NSM # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A8A..11A96 ; NSM # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A98..11A99 ; NSM # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER 11C30..11C36 ; NSM # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L 11C38..11C3D ; NSM # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA 11C92..11CA7 ; NSM # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA 11CAA..11CB0 ; NSM # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA 11CB2..11CB3 ; NSM # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E 11CB5..11CB6 ; NSM # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D31..11D36 ; NSM # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; NSM # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; NSM # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45 ; NSM # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D47 ; NSM # Mn MASARAM GONDI RA-KARA 16AF0..16AF4 ; NSM # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; NSM # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM 16F8F..16F92 ; NSM # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW @@ -2096,7 +2112,7 @@ FE20..FE2F ; NSM # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC 1E944..1E94A ; NSM # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0100..E01EF ; NSM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 1700 +# Total code points: 1773 # ================================================ @@ -2131,6 +2147,8 @@ E0100..E01EF ; NSM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 074D..07A5 ; AL # Lo [89] SYRIAC LETTER SOGDIAN ZHAIN..THAANA LETTER WAAVU 07B1 ; AL # Lo THAANA LETTER NAA 07B2..07BF ; AL # Cn [14] <reserved-07B2>..<reserved-07BF> +0860..086A ; AL # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA +086B..086F ; AL # Cn [5] <reserved-086B>..<reserved-086F> 08A0..08B4 ; AL # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW 08B5 ; AL # Cn <reserved-08B5> 08B6..08BD ; AL # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON @@ -2219,7 +2237,7 @@ FEFD..FEFE ; AL # Cn [2] <reserved-FEFD>..<reserved-FEFE> 1EEBC..1EEEF ; AL # Cn [52] <reserved-1EEBC>..<reserved-1EEEF> 1EEF2..1EEFF ; AL # Cn [14] <reserved-1EEF2>..<reserved-1EEFF> -# Total code points: 1420 +# Total code points: 1436 # ================================================ diff --git a/lib/unicore/extracted/DBinaryProperties.txt b/lib/unicore/extracted/DBinaryProperties.txt index 4ee02c50da..8036034e25 100644 --- a/lib/unicore/extracted/DBinaryProperties.txt +++ b/lib/unicore/extracted/DBinaryProperties.txt @@ -1,6 +1,6 @@ -# DerivedBinaryProperties-9.0.0.txt -# Date: 2016-03-02, 18:54:56 GMT -# © 2016 Unicode®, Inc. +# DerivedBinaryProperties-10.0.0.txt +# Date: 2017-02-14, 04:26:02 GMT +# © 2017 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html # diff --git a/lib/unicore/extracted/DCombiningClass.txt b/lib/unicore/extracted/DCombiningClass.txt index cebc7b810b..209fe980b7 100644 --- a/lib/unicore/extracted/DCombiningClass.txt +++ b/lib/unicore/extracted/DCombiningClass.txt @@ -1,6 +1,6 @@ -# DerivedCombiningClass-9.0.0.txt -# Date: 2016-06-01, 10:34:23 GMT -# © 2016 Unicode®, Inc. +# DerivedCombiningClass-10.0.0.txt +# Date: 2017-03-08, 08:41:47 GMT +# © 2017 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html # @@ -178,6 +178,7 @@ 0830..083E ; 0 # Po [15] SAMARITAN PUNCTUATION NEQUDAA..SAMARITAN PUNCTUATION ANNAAU 0840..0858 ; 0 # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 085E ; 0 # Po MANDAIC PUNCTUATION +0860..086A ; 0 # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 08A0..08B4 ; 0 # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW 08B6..08BD ; 0 # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON 08E2 ; 0 # Cf ARABIC DISPUTED END OF AYAH @@ -224,6 +225,8 @@ 09F4..09F9 ; 0 # No [6] BENGALI CURRENCY NUMERATOR ONE..BENGALI CURRENCY DENOMINATOR SIXTEEN 09FA ; 0 # So BENGALI ISSHAR 09FB ; 0 # Sc BENGALI GANDA MARK +09FC ; 0 # Lo BENGALI LETTER VEDIC ANUSVARA +09FD ; 0 # Po BENGALI ABBREVIATION SIGN 0A01..0A02 ; 0 # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI 0A03 ; 0 # Mc GURMUKHI SIGN VISARGA 0A05..0A0A ; 0 # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU @@ -265,6 +268,7 @@ 0AF0 ; 0 # Po GUJARATI ABBREVIATION SIGN 0AF1 ; 0 # Sc GUJARATI RUPEE SIGN 0AF9 ; 0 # Lo GUJARATI LETTER ZHA +0AFA..0AFF ; 0 # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE 0B01 ; 0 # Mn ORIYA SIGN CANDRABINDU 0B02..0B03 ; 0 # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA 0B05..0B0C ; 0 # Lo [8] ORIYA LETTER A..ORIYA LETTER VOCALIC L @@ -351,7 +355,7 @@ 0CE2..0CE3 ; 0 # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL 0CE6..0CEF ; 0 # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE 0CF1..0CF2 ; 0 # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA -0D01 ; 0 # Mn MALAYALAM SIGN CANDRABINDU +0D00..0D01 ; 0 # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU 0D02..0D03 ; 0 # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA 0D05..0D0C ; 0 # Lo [8] MALAYALAM LETTER A..MALAYALAM LETTER VOCALIC L 0D0E..0D10 ; 0 # Lo [3] MALAYALAM LETTER E..MALAYALAM LETTER AI @@ -659,6 +663,7 @@ 1CEE..1CF1 ; 0 # Lo [4] VEDIC SIGN HEXIFORM LONG ANUSVARA..VEDIC SIGN ANUSVARA UBHAYATO MUKHA 1CF2..1CF3 ; 0 # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA 1CF5..1CF6 ; 0 # Lo [2] VEDIC SIGN JIHVAMULIYA..VEDIC SIGN UPADHMANIYA +1CF7 ; 0 # Mc VEDIC SIGN ATIKRAMA 1D00..1D2B ; 0 # L& [44] LATIN LETTER SMALL CAPITAL A..CYRILLIC LETTER SMALL CAPITAL EL 1D2C..1D6A ; 0 # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI 1D6B..1D77 ; 0 # L& [13] LATIN SMALL LETTER UE..LATIN SMALL LETTER TURNED G @@ -735,7 +740,7 @@ 208D ; 0 # Ps SUBSCRIPT LEFT PARENTHESIS 208E ; 0 # Pe SUBSCRIPT RIGHT PARENTHESIS 2090..209C ; 0 # Lm [13] LATIN SUBSCRIPT SMALL LETTER A..LATIN SUBSCRIPT SMALL LETTER T -20A0..20BE ; 0 # Sc [31] EURO-CURRENCY SIGN..LARI SIGN +20A0..20BF ; 0 # Sc [32] EURO-CURRENCY SIGN..BITCOIN SIGN 20DD..20E0 ; 0 # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH 20E2..20E4 ; 0 # Me [3] COMBINING ENCLOSING SCREEN..COMBINING ENCLOSING UPWARD POINTING TRIANGLE 2100..2101 ; 0 # So [2] ACCOUNT OF..ADDRESSED TO THE SUBJECT @@ -811,8 +816,7 @@ 239B..23B3 ; 0 # Sm [25] LEFT PARENTHESIS UPPER HOOK..SUMMATION BOTTOM 23B4..23DB ; 0 # So [40] TOP SQUARE BRACKET..FUSE 23DC..23E1 ; 0 # Sm [6] TOP PARENTHESIS..BOTTOM TORTOISE SHELL BRACKET -23E2..23FE ; 0 # So [29] WHITE TRAPEZIUM..POWER SLEEP SYMBOL -2400..2426 ; 0 # So [39] SYMBOL FOR NULL..SYMBOL FOR SUBSTITUTE FORM TWO +23E2..2426 ; 0 # So [69] WHITE TRAPEZIUM..SYMBOL FOR SUBSTITUTE FORM TWO 2440..244A ; 0 # So [11] OCR HOOK..OCR DOUBLE BACKSLASH 2460..249B ; 0 # No [60] CIRCLED DIGIT ONE..NUMBER TWENTY FULL STOP 249C..24E9 ; 0 # So [78] PARENTHESIZED LATIN SMALL LETTER A..CIRCLED LATIN SMALL LETTER Z @@ -898,7 +902,7 @@ 2B76..2B95 ; 0 # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW 2B98..2BB9 ; 0 # So [34] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..UP ARROWHEAD IN A RECTANGLE BOX 2BBD..2BC8 ; 0 # So [12] BALLOT BOX WITH LIGHT X..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED -2BCA..2BD1 ; 0 # So [8] TOP HALF BLACK CIRCLE..UNCERTAINTY SIGN +2BCA..2BD2 ; 0 # So [9] TOP HALF BLACK CIRCLE..GROUP MARK 2BEC..2BEF ; 0 # So [4] LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS..DOWNWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS 2C00..2C2E ; 0 # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE 2C30..2C5E ; 0 # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE @@ -963,7 +967,7 @@ 2E40 ; 0 # Pd DOUBLE HYPHEN 2E41 ; 0 # Po REVERSED COMMA 2E42 ; 0 # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK -2E43..2E44 ; 0 # Po [2] DASH WITH LEFT UPTURN..DOUBLE SUSPENSION MARK +2E43..2E49 ; 0 # Po [7] DASH WITH LEFT UPTURN..DOUBLE STACKED COMMA 2E80..2E99 ; 0 # So [26] CJK RADICAL REPEAT..CJK RADICAL RAP 2E9B..2EF3 ; 0 # So [89] CJK RADICAL CHOKE..CJK RADICAL C-SIMPLIFIED TURTLE 2F00..2FD5 ; 0 # So [214] KANGXI RADICAL ONE..KANGXI RADICAL FLUTE @@ -1015,7 +1019,7 @@ 30FB ; 0 # Po KATAKANA MIDDLE DOT 30FC..30FE ; 0 # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK 30FF ; 0 # Lo KATAKANA DIGRAPH KOTO -3105..312D ; 0 # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH +3105..312E ; 0 # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE 3131..318E ; 0 # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE 3190..3191 ; 0 # So [2] IDEOGRAPHIC ANNOTATION LINKING MARK..IDEOGRAPHIC ANNOTATION REVERSE MARK 3192..3195 ; 0 # No [4] IDEOGRAPHIC ANNOTATION ONE MARK..IDEOGRAPHIC ANNOTATION FOUR MARK @@ -1037,7 +1041,7 @@ 3300..33FF ; 0 # So [256] SQUARE APAATO..SQUARE GAL 3400..4DB5 ; 0 # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 4DC0..4DFF ; 0 # So [64] HEXAGRAM FOR THE CREATIVE HEAVEN..HEXAGRAM FOR BEFORE COMPLETION -4E00..9FD5 ; 0 # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5 +4E00..9FEA ; 0 # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA A000..A014 ; 0 # Lo [21] YI SYLLABLE IT..YI SYLLABLE E A015 ; 0 # Lm YI SYLLABLE WU A016..A48C ; 0 # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR @@ -1336,7 +1340,7 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 102E1..102FB ; 0 # No [27] COPTIC EPACT DIGIT ONE..COPTIC EPACT NUMBER NINE HUNDRED 10300..1031F ; 0 # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS 10320..10323 ; 0 # No [4] OLD ITALIC NUMERAL ONE..OLD ITALIC NUMERAL FIFTY -10330..10340 ; 0 # Lo [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA +1032D..10340 ; 0 # Lo [20] OLD ITALIC LETTER YE..GOTHIC LETTER PAIRTHRA 10341 ; 0 # Nl GOTHIC LETTER NINETY 10342..10349 ; 0 # Lo [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL 1034A ; 0 # Nl GOTHIC LETTER NINE HUNDRED @@ -1564,6 +1568,28 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 118E0..118E9 ; 0 # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE 118EA..118F2 ; 0 # No [9] WARANG CITI NUMBER TEN..WARANG CITI NUMBER NINETY 118FF ; 0 # Lo WARANG CITI OM +11A00 ; 0 # Lo ZANABAZAR SQUARE LETTER A +11A01..11A06 ; 0 # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O +11A07..11A08 ; 0 # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU +11A09..11A0A ; 0 # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A0B..11A32 ; 0 # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA +11A33 ; 0 # Mn ZANABAZAR SQUARE FINAL CONSONANT MARK +11A35..11A38 ; 0 # Mn [4] ZANABAZAR SQUARE SIGN CANDRABINDU..ZANABAZAR SQUARE SIGN ANUSVARA +11A39 ; 0 # Mc ZANABAZAR SQUARE SIGN VISARGA +11A3A ; 0 # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA +11A3B..11A3E ; 0 # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A3F..11A46 ; 0 # Po [8] ZANABAZAR SQUARE INITIAL HEAD MARK..ZANABAZAR SQUARE CLOSING DOUBLE-LINED HEAD MARK +11A50 ; 0 # Lo SOYOMBO LETTER A +11A51..11A56 ; 0 # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A57..11A58 ; 0 # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU +11A59..11A5B ; 0 # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A5C..11A83 ; 0 # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA +11A86..11A89 ; 0 # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA +11A8A..11A96 ; 0 # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A97 ; 0 # Mc SOYOMBO SIGN VISARGA +11A98 ; 0 # Mn SOYOMBO GEMINATION MARK +11A9A..11A9C ; 0 # Po [3] SOYOMBO MARK TSHEG..SOYOMBO MARK DOUBLE SHAD +11A9E..11AA2 ; 0 # Po [5] SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME..SOYOMBO TERMINAL MARK-2 11AC0..11AF8 ; 0 # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL 11C00..11C08 ; 0 # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E ; 0 # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA @@ -1584,6 +1610,17 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 11CB2..11CB3 ; 0 # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E 11CB4 ; 0 # Mc MARCHEN VOWEL SIGN O 11CB5..11CB6 ; 0 # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D00..11D06 ; 0 # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E +11D08..11D09 ; 0 # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O +11D0B..11D30 ; 0 # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA +11D31..11D36 ; 0 # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; 0 # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; 0 # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D41 ; 0 # Mn [3] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI SIGN VISARGA +11D43 ; 0 # Mn MASARAM GONDI SIGN CANDRA +11D46 ; 0 # Lo MASARAM GONDI REPHA +11D47 ; 0 # Mn MASARAM GONDI RA-KARA +11D50..11D59 ; 0 # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE 12000..12399 ; 0 # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; 0 # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12470..12474 ; 0 # Po [5] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON @@ -1611,10 +1648,11 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 16F51..16F7E ; 0 # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG 16F8F..16F92 ; 0 # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW 16F93..16F9F ; 0 # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 -16FE0 ; 0 # Lm TANGUT ITERATION MARK +16FE0..16FE1 ; 0 # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK 17000..187EC ; 0 # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC 18800..18AF2 ; 0 # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755 -1B000..1B001 ; 0 # Lo [2] KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE +1B000..1B11E ; 0 # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1B170..1B2FB ; 0 # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 1BC00..1BC6A ; 0 # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M 1BC70..1BC7C ; 0 # Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK 1BC80..1BC88 ; 0 # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL @@ -1741,11 +1779,12 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1F210..1F23B ; 0 # So [44] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-914D 1F240..1F248 ; 0 # So [9] TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C..TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557 1F250..1F251 ; 0 # So [2] CIRCLED IDEOGRAPH ADVANTAGE..CIRCLED IDEOGRAPH ACCEPT +1F260..1F265 ; 0 # So [6] ROUNDED SYMBOL FOR FU..ROUNDED SYMBOL FOR CAI 1F300..1F3FA ; 0 # So [251] CYCLONE..AMPHORA 1F3FB..1F3FF ; 0 # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6 -1F400..1F6D2 ; 0 # So [723] RAT..SHOPPING TROLLEY +1F400..1F6D4 ; 0 # So [725] RAT..PAGODA 1F6E0..1F6EC ; 0 # So [13] HAMMER AND WRENCH..AIRPLANE ARRIVING -1F6F0..1F6F6 ; 0 # So [7] SATELLITE..CANOE +1F6F0..1F6F8 ; 0 # So [9] SATELLITE..FLYING SAUCER 1F700..1F773 ; 0 # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE 1F780..1F7D4 ; 0 # So [85] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..HEAVY TWELVE POINTED PINWHEEL STAR 1F800..1F80B ; 0 # So [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD @@ -1753,18 +1792,18 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1F850..1F859 ; 0 # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW 1F860..1F887 ; 0 # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW 1F890..1F8AD ; 0 # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS -1F910..1F91E ; 0 # So [15] ZIPPER-MOUTH FACE..HAND WITH INDEX AND MIDDLE FINGERS CROSSED -1F920..1F927 ; 0 # So [8] FACE WITH COWBOY HAT..SNEEZING FACE -1F930 ; 0 # So PREGNANT WOMAN -1F933..1F93E ; 0 # So [12] SELFIE..HANDBALL -1F940..1F94B ; 0 # So [12] WILTED FLOWER..MARTIAL ARTS UNIFORM -1F950..1F95E ; 0 # So [15] CROISSANT..PANCAKES -1F980..1F991 ; 0 # So [18] CRAB..SQUID +1F900..1F90B ; 0 # So [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT +1F910..1F93E ; 0 # So [47] ZIPPER-MOUTH FACE..HANDBALL +1F940..1F94C ; 0 # So [13] WILTED FLOWER..CURLING STONE +1F950..1F96B ; 0 # So [28] CROISSANT..CANNED FOOD +1F980..1F997 ; 0 # So [24] CRAB..CRICKET 1F9C0 ; 0 # So CHEESE WEDGE +1F9D0..1F9E6 ; 0 # So [23] FACE WITH MONOCLE..SOCKS 20000..2A6D6 ; 0 # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6 2A700..2B734 ; 0 # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 2B740..2B81D ; 0 # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; 0 # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 +2CEB0..2EBE0 ; 0 # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; 0 # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D E0001 ; 0 # Cf LANGUAGE TAG E0020..E007F ; 0 # Cf [96] TAG SPACE..CANCEL TAG @@ -1772,8 +1811,8 @@ E0100..E01EF ; 0 # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 F0000..FFFFD ; 0 # Co [65534] <private-use-F0000>..<private-use-FFFFD> 100000..10FFFD; 0 # Co [65534] <private-use-100000>..<private-use-10FFFD> -# The above property value applies to 848407 code points not listed here. -# Total code points: 1113298 +# The above property value applies to 839889 code points not listed here. +# Total code points: 1113286 # ================================================ @@ -1818,9 +1857,10 @@ A9B3 ; 7 # Mn JAVANESE SIGN CECAK TELU 114C3 ; 7 # Mn TIRHUTA SIGN NUKTA 115C0 ; 7 # Mn SIDDHAM SIGN NUKTA 116B7 ; 7 # Mn TAKRI SIGN NUKTA +11D42 ; 7 # Mn MASARAM GONDI SIGN NUKTA 1E94A ; 7 # Mn ADLAM NUKTA -# Total code points: 22 +# Total code points: 23 # ================================================ @@ -1842,6 +1882,7 @@ A9B3 ; 7 # Mn JAVANESE SIGN CECAK TELU 0BCD ; 9 # Mn TAMIL SIGN VIRAMA 0C4D ; 9 # Mn TELUGU SIGN VIRAMA 0CCD ; 9 # Mn KANNADA SIGN VIRAMA +0D3B..0D3C ; 9 # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA 0D4D ; 9 # Mn MALAYALAM SIGN VIRAMA 0DCA ; 9 # Mn SINHALA SIGN AL-LAKUNA 0E3A ; 9 # Mn THAI CHARACTER PHINTHU @@ -1877,9 +1918,13 @@ ABED ; 9 # Mn MEETEI MAYEK APUN IYEK 1163F ; 9 # Mn MODI SIGN VIRAMA 116B6 ; 9 # Mc TAKRI SIGN VIRAMA 1172B ; 9 # Mn AHOM SIGN KILLER +11A34 ; 9 # Mn ZANABAZAR SQUARE SIGN VIRAMA +11A47 ; 9 # Mn ZANABAZAR SQUARE SUBJOINER +11A99 ; 9 # Mn SOYOMBO SUBJOINER 11C3F ; 9 # Mn BHAIKSUKI SIGN VIRAMA +11D44..11D45 ; 9 # Mn [2] MASARAM GONDI SIGN HALANTA..MASARAM GONDI VIRAMA -# Total code points: 47 +# Total code points: 54 # ================================================ @@ -2275,6 +2320,7 @@ FB1E ; 26 # Mn HEBREW POINT JUDEO-SPANISH VARIKA 1DC2 ; 220 # Mn COMBINING SNAKE BELOW 1DCA ; 220 # Mn COMBINING LATIN SMALL LETTER R BELOW 1DCF ; 220 # Mn COMBINING ZIGZAG BELOW +1DF9 ; 220 # Mn COMBINING WIDE INVERTED BRIDGE BELOW 1DFD ; 220 # Mn COMBINING ALMOST EQUAL TO BELOW 1DFF ; 220 # Mn COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 20E8 ; 220 # Mn COMBINING TRIPLE UNDERDOT @@ -2291,7 +2337,7 @@ FE27..FE2D ; 220 # Mn [7] COMBINING LIGATURE LEFT HALF BELOW..COMBINING CON 1D18A..1D18B ; 220 # Mn [2] MUSICAL SYMBOL COMBINING DOUBLE TONGUE..MUSICAL SYMBOL COMBINING TRIPLE TONGUE 1E8D0..1E8D6 ; 220 # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS -# Total code points: 153 +# Total code points: 154 # ================================================ @@ -2326,9 +2372,10 @@ FE27..FE2D ; 220 # Mn [7] COMBINING LIGATURE LEFT HALF BELOW..COMBINING CON 05AE ; 228 # Mn HEBREW ACCENT ZINOR 18A9 ; 228 # Mn MONGOLIAN LETTER ALI GALI DAGALGA +1DF7..1DF8 ; 228 # Mn [2] COMBINING KAVYKA ABOVE LEFT..COMBINING DOT ABOVE LEFT 302B ; 228 # Mn IDEOGRAPHIC RISING TONE MARK -# Total code points: 3 +# Total code points: 5 # ================================================ @@ -2454,9 +2501,10 @@ FE2E..FE2F ; 230 # Mn [2] COMBINING CYRILLIC TITLO LEFT HALF..COMBINING CYR 0315 ; 232 # Mn COMBINING COMMA ABOVE RIGHT 031A ; 232 # Mn COMBINING LEFT ANGLE ABOVE 0358 ; 232 # Mn COMBINING DOT ABOVE RIGHT +1DF6 ; 232 # Mn COMBINING KAVYKA ABOVE RIGHT 302C ; 232 # Mn IDEOGRAPHIC DEPARTING TONE MARK -# Total code points: 4 +# Total code points: 5 # ================================================ diff --git a/lib/unicore/extracted/DDecompositionType.txt b/lib/unicore/extracted/DDecompositionType.txt index 84365059cd..96006dcd95 100644 --- a/lib/unicore/extracted/DDecompositionType.txt +++ b/lib/unicore/extracted/DDecompositionType.txt @@ -1,6 +1,6 @@ -# DerivedDecompositionType-9.0.0.txt -# Date: 2016-03-02, 18:54:58 GMT -# © 2016 Unicode®, Inc. +# DerivedDecompositionType-10.0.0.txt +# Date: 2017-02-14, 04:26:05 GMT +# © 2017 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html # diff --git a/lib/unicore/extracted/DEastAsianWidth.txt b/lib/unicore/extracted/DEastAsianWidth.txt index 678a91ab39..b4180028f6 100644 --- a/lib/unicore/extracted/DEastAsianWidth.txt +++ b/lib/unicore/extracted/DEastAsianWidth.txt @@ -1,6 +1,6 @@ -# DerivedEastAsianWidth-9.0.0.txt -# Date: 2016-06-01, 10:34:25 GMT -# © 2016 Unicode®, Inc. +# DerivedEastAsianWidth-10.0.0.txt +# Date: 2017-03-08, 08:41:49 GMT +# © 2017 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html # @@ -196,6 +196,7 @@ 0840..0858 ; N # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 0859..085B ; N # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK 085E ; N # Po MANDAIC PUNCTUATION +0860..086A ; N # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 08A0..08B4 ; N # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW 08B6..08BD ; N # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON 08D4..08E1 ; N # Mn [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA @@ -247,6 +248,8 @@ 09F4..09F9 ; N # No [6] BENGALI CURRENCY NUMERATOR ONE..BENGALI CURRENCY DENOMINATOR SIXTEEN 09FA ; N # So BENGALI ISSHAR 09FB ; N # Sc BENGALI GANDA MARK +09FC ; N # Lo BENGALI LETTER VEDIC ANUSVARA +09FD ; N # Po BENGALI ABBREVIATION SIGN 0A01..0A02 ; N # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI 0A03 ; N # Mc GURMUKHI SIGN VISARGA 0A05..0A0A ; N # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU @@ -291,6 +294,7 @@ 0AF0 ; N # Po GUJARATI ABBREVIATION SIGN 0AF1 ; N # Sc GUJARATI RUPEE SIGN 0AF9 ; N # Lo GUJARATI LETTER ZHA +0AFA..0AFF ; N # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE 0B01 ; N # Mn ORIYA SIGN CANDRABINDU 0B02..0B03 ; N # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA 0B05..0B0C ; N # Lo [8] ORIYA LETTER A..ORIYA LETTER VOCALIC L @@ -382,11 +386,12 @@ 0CE2..0CE3 ; N # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL 0CE6..0CEF ; N # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE 0CF1..0CF2 ; N # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA -0D01 ; N # Mn MALAYALAM SIGN CANDRABINDU +0D00..0D01 ; N # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU 0D02..0D03 ; N # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA 0D05..0D0C ; N # Lo [8] MALAYALAM LETTER A..MALAYALAM LETTER VOCALIC L 0D0E..0D10 ; N # Lo [3] MALAYALAM LETTER E..MALAYALAM LETTER AI 0D12..0D3A ; N # Lo [41] MALAYALAM LETTER O..MALAYALAM LETTER TTTA +0D3B..0D3C ; N # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA 0D3D ; N # Lo MALAYALAM SIGN AVAGRAHA 0D3E..0D40 ; N # Mc [3] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN II 0D41..0D44 ; N # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR @@ -715,6 +720,7 @@ 1CF2..1CF3 ; N # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA 1CF4 ; N # Mn VEDIC TONE CANDRA ABOVE 1CF5..1CF6 ; N # Lo [2] VEDIC SIGN JIHVAMULIYA..VEDIC SIGN UPADHMANIYA +1CF7 ; N # Mc VEDIC SIGN ATIKRAMA 1CF8..1CF9 ; N # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE 1D00..1D2B ; N # L& [44] LATIN LETTER SMALL CAPITAL A..CYRILLIC LETTER SMALL CAPITAL EL 1D2C..1D6A ; N # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI @@ -722,7 +728,7 @@ 1D78 ; N # Lm MODIFIER LETTER CYRILLIC EN 1D79..1D9A ; N # L& [34] LATIN SMALL LETTER INSULAR G..LATIN SMALL LETTER EZH WITH RETROFLEX HOOK 1D9B..1DBF ; N # Lm [37] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL THETA -1DC0..1DF5 ; N # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE +1DC0..1DF9 ; N # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW 1DFB..1DFF ; N # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 1E00..1F15 ; N # L& [278] LATIN CAPITAL LETTER A WITH RING BELOW..GREEK SMALL LETTER EPSILON WITH DASIA AND OXIA 1F18..1F1D ; N # L& [6] GREEK CAPITAL LETTER EPSILON WITH PSILI..GREEK CAPITAL LETTER EPSILON WITH DASIA AND OXIA @@ -795,7 +801,7 @@ 2090..209C ; N # Lm [13] LATIN SUBSCRIPT SMALL LETTER A..LATIN SUBSCRIPT SMALL LETTER T 20A0..20A8 ; N # Sc [9] EURO-CURRENCY SIGN..RUPEE SIGN 20AA..20AB ; N # Sc [2] NEW SHEQEL SIGN..DONG SIGN -20AD..20BE ; N # Sc [18] KIP SIGN..LARI SIGN +20AD..20BF ; N # Sc [19] KIP SIGN..BITCOIN SIGN 20D0..20DC ; N # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE 20DD..20E0 ; N # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH 20E1 ; N # Mn COMBINING LEFT RIGHT ARROW ABOVE @@ -907,8 +913,7 @@ 23E2..23E8 ; N # So [7] WHITE TRAPEZIUM..DECIMAL EXPONENT SYMBOL 23ED..23EF ; N # So [3] BLACK RIGHT-POINTING DOUBLE TRIANGLE WITH VERTICAL BAR..BLACK RIGHT-POINTING TRIANGLE WITH DOUBLE VERTICAL BAR 23F1..23F2 ; N # So [2] STOPWATCH..TIMER CLOCK -23F4..23FE ; N # So [11] BLACK MEDIUM LEFT-POINTING TRIANGLE..POWER SLEEP SYMBOL -2400..2426 ; N # So [39] SYMBOL FOR NULL..SYMBOL FOR SUBSTITUTE FORM TWO +23F4..2426 ; N # So [51] BLACK MEDIUM LEFT-POINTING TRIANGLE..SYMBOL FOR SUBSTITUTE FORM TWO 2440..244A ; N # So [11] OCR HOOK..OCR DOUBLE BACKSLASH 24EA ; N # No CIRCLED DIGIT ZERO 254C..254F ; N # So [4] BOX DRAWINGS LIGHT DOUBLE DASH HORIZONTAL..BOX DRAWINGS HEAVY DOUBLE DASH VERTICAL @@ -1027,7 +1032,7 @@ 2B76..2B95 ; N # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW 2B98..2BB9 ; N # So [34] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..UP ARROWHEAD IN A RECTANGLE BOX 2BBD..2BC8 ; N # So [12] BALLOT BOX WITH LIGHT X..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED -2BCA..2BD1 ; N # So [8] TOP HALF BLACK CIRCLE..UNCERTAINTY SIGN +2BCA..2BD2 ; N # So [9] TOP HALF BLACK CIRCLE..GROUP MARK 2BEC..2BEF ; N # So [4] LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS..DOWNWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS 2C00..2C2E ; N # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE 2C30..2C5E ; N # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE @@ -1095,7 +1100,7 @@ 2E40 ; N # Pd DOUBLE HYPHEN 2E41 ; N # Po REVERSED COMMA 2E42 ; N # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK -2E43..2E44 ; N # Po [2] DASH WITH LEFT UPTURN..DOUBLE SUSPENSION MARK +2E43..2E49 ; N # Po [7] DASH WITH LEFT UPTURN..DOUBLE STACKED COMMA 303F ; N # So IDEOGRAPHIC HALF FILL SPACE 4DC0..4DFF ; N # So [64] HEXAGRAM FOR THE CREATIVE HEAVEN..HEXAGRAM FOR BEFORE COMPLETION A4D0..A4F7 ; N # Lo [40] LISU LETTER BA..LISU LETTER OE @@ -1311,7 +1316,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 102E1..102FB ; N # No [27] COPTIC EPACT DIGIT ONE..COPTIC EPACT NUMBER NINE HUNDRED 10300..1031F ; N # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS 10320..10323 ; N # No [4] OLD ITALIC NUMERAL ONE..OLD ITALIC NUMERAL FIFTY -10330..10340 ; N # Lo [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA +1032D..10340 ; N # Lo [20] OLD ITALIC LETTER YE..GOTHIC LETTER PAIRTHRA 10341 ; N # Nl GOTHIC LETTER NINETY 10342..10349 ; N # Lo [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL 1034A ; N # Nl GOTHIC LETTER NINE HUNDRED @@ -1554,6 +1559,28 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 118E0..118E9 ; N # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE 118EA..118F2 ; N # No [9] WARANG CITI NUMBER TEN..WARANG CITI NUMBER NINETY 118FF ; N # Lo WARANG CITI OM +11A00 ; N # Lo ZANABAZAR SQUARE LETTER A +11A01..11A06 ; N # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O +11A07..11A08 ; N # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU +11A09..11A0A ; N # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A0B..11A32 ; N # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA +11A33..11A38 ; N # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A39 ; N # Mc ZANABAZAR SQUARE SIGN VISARGA +11A3A ; N # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA +11A3B..11A3E ; N # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A3F..11A46 ; N # Po [8] ZANABAZAR SQUARE INITIAL HEAD MARK..ZANABAZAR SQUARE CLOSING DOUBLE-LINED HEAD MARK +11A47 ; N # Mn ZANABAZAR SQUARE SUBJOINER +11A50 ; N # Lo SOYOMBO LETTER A +11A51..11A56 ; N # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A57..11A58 ; N # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU +11A59..11A5B ; N # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A5C..11A83 ; N # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA +11A86..11A89 ; N # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA +11A8A..11A96 ; N # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A97 ; N # Mc SOYOMBO SIGN VISARGA +11A98..11A99 ; N # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER +11A9A..11A9C ; N # Po [3] SOYOMBO MARK TSHEG..SOYOMBO MARK DOUBLE SHAD +11A9E..11AA2 ; N # Po [5] SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME..SOYOMBO TERMINAL MARK-2 11AC0..11AF8 ; N # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL 11C00..11C08 ; N # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E ; N # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA @@ -1575,6 +1602,16 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 11CB2..11CB3 ; N # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E 11CB4 ; N # Mc MARCHEN VOWEL SIGN O 11CB5..11CB6 ; N # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D00..11D06 ; N # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E +11D08..11D09 ; N # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O +11D0B..11D30 ; N # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA +11D31..11D36 ; N # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; N # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; N # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45 ; N # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D46 ; N # Lo MASARAM GONDI REPHA +11D47 ; N # Mn MASARAM GONDI RA-KARA +11D50..11D59 ; N # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE 12000..12399 ; N # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; N # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12470..12474 ; N # Po [5] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON @@ -1761,6 +1798,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 1F650..1F67F ; N # So [48] NORTH WEST POINTING LEAF..REVERSE CHECKER BOARD 1F6C6..1F6CB ; N # So [6] TRIANGLE WITH ROUNDED CORNERS..COUCH AND LAMP 1F6CD..1F6CF ; N # So [3] SHOPPING BAGS..BED +1F6D3..1F6D4 ; N # So [2] STUPA..PAGODA 1F6E0..1F6EA ; N # So [11] HAMMER AND WRENCH..NORTHEAST-POINTING AIRPLANE 1F6F0..1F6F3 ; N # So [4] SATELLITE..PASSENGER SHIP 1F700..1F773 ; N # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE @@ -1770,11 +1808,12 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 1F850..1F859 ; N # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW 1F860..1F887 ; N # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW 1F890..1F8AD ; N # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS +1F900..1F90B ; N # So [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT E0001 ; N # Cf LANGUAGE TAG E0020..E007F ; N # Cf [96] TAG SPACE..CANCEL TAG -# The above property value applies to 770633 code points not listed here. -# Total code points: 794146 +# The above property value applies to 769609 code points not listed here. +# Total code points: 793401 # ================================================ @@ -2098,7 +2137,7 @@ FFED..FFEE ; H # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 30FB ; W # Po KATAKANA MIDDLE DOT 30FC..30FE ; W # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK 30FF ; W # Lo KATAKANA DIGRAPH KOTO -3105..312D ; W # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH +3105..312E ; W # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE 3131..318E ; W # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE 3190..3191 ; W # So [2] IDEOGRAPHIC ANNOTATION LINKING MARK..IDEOGRAPHIC ANNOTATION REVERSE MARK 3192..3195 ; W # No [4] IDEOGRAPHIC ANNOTATION ONE MARK..IDEOGRAPHIC ANNOTATION FOUR MARK @@ -2119,8 +2158,8 @@ FFED..FFEE ; H # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 3300..33FF ; W # So [256] SQUARE APAATO..SQUARE GAL 3400..4DB5 ; W # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 4DB6..4DBF ; W # Cn [10] <reserved-4DB6>..<reserved-4DBF> -4E00..9FD5 ; W # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5 -9FD6..9FFF ; W # Cn [42] <reserved-9FD6>..<reserved-9FFF> +4E00..9FEA ; W # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA +9FEB..9FFF ; W # Cn [21] <reserved-9FEB>..<reserved-9FFF> A000..A014 ; W # Lo [21] YI SYLLABLE IT..YI SYLLABLE E A015 ; W # Lm YI SYLLABLE WU A016..A48C ; W # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR @@ -2175,10 +2214,11 @@ FE64..FE66 ; W # Sm [3] SMALL LESS-THAN SIGN..SMALL EQUALS SIGN FE68 ; W # Po SMALL REVERSE SOLIDUS FE69 ; W # Sc SMALL DOLLAR SIGN FE6A..FE6B ; W # Po [2] SMALL PERCENT SIGN..SMALL COMMERCIAL AT -16FE0 ; W # Lm TANGUT ITERATION MARK +16FE0..16FE1 ; W # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK 17000..187EC ; W # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC 18800..18AF2 ; W # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755 -1B000..1B001 ; W # Lo [2] KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE +1B000..1B11E ; W # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1B170..1B2FB ; W # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 1F004 ; W # So MAHJONG TILE RED DRAGON 1F0CF ; W # So PLAYING CARD BLACK JOKER 1F18E ; W # So NEGATIVE SQUARED AB @@ -2187,6 +2227,7 @@ FE6A..FE6B ; W # Po [2] SMALL PERCENT SIGN..SMALL COMMERCIAL AT 1F210..1F23B ; W # So [44] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-914D 1F240..1F248 ; W # So [9] TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C..TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557 1F250..1F251 ; W # So [2] CIRCLED IDEOGRAPH ADVANTAGE..CIRCLED IDEOGRAPH ACCEPT +1F260..1F265 ; W # So [6] ROUNDED SYMBOL FOR FU..ROUNDED SYMBOL FOR CAI 1F300..1F320 ; W # So [33] CYCLONE..SHOOTING STAR 1F32D..1F335 ; W # So [9] HOT DOG..CACTUS 1F337..1F37C ; W # So [70] TULIP..BABY BOTTLE @@ -2211,15 +2252,13 @@ FE6A..FE6B ; W # Po [2] SMALL PERCENT SIGN..SMALL COMMERCIAL AT 1F6CC ; W # So SLEEPING ACCOMMODATION 1F6D0..1F6D2 ; W # So [3] PLACE OF WORSHIP..SHOPPING TROLLEY 1F6EB..1F6EC ; W # So [2] AIRPLANE DEPARTURE..AIRPLANE ARRIVING -1F6F4..1F6F6 ; W # So [3] SCOOTER..CANOE -1F910..1F91E ; W # So [15] ZIPPER-MOUTH FACE..HAND WITH INDEX AND MIDDLE FINGERS CROSSED -1F920..1F927 ; W # So [8] FACE WITH COWBOY HAT..SNEEZING FACE -1F930 ; W # So PREGNANT WOMAN -1F933..1F93E ; W # So [12] SELFIE..HANDBALL -1F940..1F94B ; W # So [12] WILTED FLOWER..MARTIAL ARTS UNIFORM -1F950..1F95E ; W # So [15] CROISSANT..PANCAKES -1F980..1F991 ; W # So [18] CRAB..SQUID +1F6F4..1F6F8 ; W # So [5] SCOOTER..FLYING SAUCER +1F910..1F93E ; W # So [47] ZIPPER-MOUTH FACE..HANDBALL +1F940..1F94C ; W # So [13] WILTED FLOWER..CURLING STONE +1F950..1F96B ; W # So [28] CROISSANT..CANNED FOOD +1F980..1F997 ; W # So [24] CRAB..CRICKET 1F9C0 ; W # So CHEESE WEDGE +1F9D0..1F9E6 ; W # So [23] FACE WITH MONOCLE..SOCKS 20000..2A6D6 ; W # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6 2A6D7..2A6FF ; W # Cn [41] <reserved-2A6D7>..<reserved-2A6FF> 2A700..2B734 ; W # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 @@ -2227,12 +2266,14 @@ FE6A..FE6B ; W # Po [2] SMALL PERCENT SIGN..SMALL COMMERCIAL AT 2B740..2B81D ; W # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B81E..2B81F ; W # Cn [2] <reserved-2B81E>..<reserved-2B81F> 2B820..2CEA1 ; W # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 -2CEA2..2F7FF ; W # Cn [10590] <reserved-2CEA2>..<reserved-2F7FF> +2CEA2..2CEAF ; W # Cn [14] <reserved-2CEA2>..<reserved-2CEAF> +2CEB0..2EBE0 ; W # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 +2EBE1..2F7FF ; W # Cn [3103] <reserved-2EBE1>..<reserved-2F7FF> 2F800..2FA1D ; W # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D 2FA1E..2FFFD ; W # Cn [1504] <reserved-2FA1E>..<reserved-2FFFD> 30000..3FFFD ; W # Cn [65534] <reserved-30000>..<reserved-3FFFD> -# Total code points: 180889 +# Total code points: 181634 # ================================================ diff --git a/lib/unicore/extracted/DGeneralCategory.txt b/lib/unicore/extracted/DGeneralCategory.txt index 96dfb56f0e..bc7f5e84ea 100644 --- a/lib/unicore/extracted/DGeneralCategory.txt +++ b/lib/unicore/extracted/DGeneralCategory.txt @@ -1,6 +1,6 @@ -# DerivedGeneralCategory-9.0.0.txt -# Date: 2016-06-01, 10:34:26 GMT -# © 2016 Unicode®, Inc. +# DerivedGeneralCategory-10.0.0.txt +# Date: 2017-03-08, 08:41:49 GMT +# © 2017 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html # @@ -37,7 +37,8 @@ 082E..082F ; Cn # [2] <reserved-082E>..<reserved-082F> 083F ; Cn # <reserved-083F> 085C..085D ; Cn # [2] <reserved-085C>..<reserved-085D> -085F..089F ; Cn # [65] <reserved-085F>..<reserved-089F> +085F ; Cn # <reserved-085F> +086B..089F ; Cn # [53] <reserved-086B>..<reserved-089F> 08B5 ; Cn # <reserved-08B5> 08BE..08D3 ; Cn # [22] <reserved-08BE>..<reserved-08D3> 0984 ; Cn # <reserved-0984> @@ -53,7 +54,7 @@ 09D8..09DB ; Cn # [4] <reserved-09D8>..<reserved-09DB> 09DE ; Cn # <reserved-09DE> 09E4..09E5 ; Cn # [2] <reserved-09E4>..<reserved-09E5> -09FC..0A00 ; Cn # [5] <reserved-09FC>..<reserved-0A00> +09FE..0A00 ; Cn # [3] <reserved-09FE>..<reserved-0A00> 0A04 ; Cn # <reserved-0A04> 0A0B..0A0E ; Cn # [4] <reserved-0A0B>..<reserved-0A0E> 0A11..0A12 ; Cn # [2] <reserved-0A11>..<reserved-0A12> @@ -83,7 +84,7 @@ 0AD1..0ADF ; Cn # [15] <reserved-0AD1>..<reserved-0ADF> 0AE4..0AE5 ; Cn # [2] <reserved-0AE4>..<reserved-0AE5> 0AF2..0AF8 ; Cn # [7] <reserved-0AF2>..<reserved-0AF8> -0AFA..0B00 ; Cn # [7] <reserved-0AFA>..<reserved-0B00> +0B00 ; Cn # <reserved-0B00> 0B04 ; Cn # <reserved-0B04> 0B0D..0B0E ; Cn # [2] <reserved-0B0D>..<reserved-0B0E> 0B11..0B12 ; Cn # [2] <reserved-0B11>..<reserved-0B12> @@ -139,11 +140,10 @@ 0CDF ; Cn # <reserved-0CDF> 0CE4..0CE5 ; Cn # [2] <reserved-0CE4>..<reserved-0CE5> 0CF0 ; Cn # <reserved-0CF0> -0CF3..0D00 ; Cn # [14] <reserved-0CF3>..<reserved-0D00> +0CF3..0CFF ; Cn # [13] <reserved-0CF3>..<reserved-0CFF> 0D04 ; Cn # <reserved-0D04> 0D0D ; Cn # <reserved-0D0D> 0D11 ; Cn # <reserved-0D11> -0D3B..0D3C ; Cn # [2] <reserved-0D3B>..<reserved-0D3C> 0D45 ; Cn # <reserved-0D45> 0D49 ; Cn # <reserved-0D49> 0D50..0D53 ; Cn # [4] <reserved-0D50>..<reserved-0D53> @@ -250,9 +250,8 @@ 1C4A..1C4C ; Cn # [3] <reserved-1C4A>..<reserved-1C4C> 1C89..1CBF ; Cn # [55] <reserved-1C89>..<reserved-1CBF> 1CC8..1CCF ; Cn # [8] <reserved-1CC8>..<reserved-1CCF> -1CF7 ; Cn # <reserved-1CF7> 1CFA..1CFF ; Cn # [6] <reserved-1CFA>..<reserved-1CFF> -1DF6..1DFA ; Cn # [5] <reserved-1DF6>..<reserved-1DFA> +1DFA ; Cn # <reserved-1DFA> 1F16..1F17 ; Cn # [2] <reserved-1F16>..<reserved-1F17> 1F1E..1F1F ; Cn # [2] <reserved-1F1E>..<reserved-1F1F> 1F46..1F47 ; Cn # [2] <reserved-1F46>..<reserved-1F47> @@ -273,17 +272,16 @@ 2072..2073 ; Cn # [2] <reserved-2072>..<reserved-2073> 208F ; Cn # <reserved-208F> 209D..209F ; Cn # [3] <reserved-209D>..<reserved-209F> -20BF..20CF ; Cn # [17] <reserved-20BF>..<reserved-20CF> +20C0..20CF ; Cn # [16] <reserved-20C0>..<reserved-20CF> 20F1..20FF ; Cn # [15] <reserved-20F1>..<reserved-20FF> 218C..218F ; Cn # [4] <reserved-218C>..<reserved-218F> -23FF ; Cn # <reserved-23FF> 2427..243F ; Cn # [25] <reserved-2427>..<reserved-243F> 244B..245F ; Cn # [21] <reserved-244B>..<reserved-245F> 2B74..2B75 ; Cn # [2] <reserved-2B74>..<reserved-2B75> 2B96..2B97 ; Cn # [2] <reserved-2B96>..<reserved-2B97> 2BBA..2BBC ; Cn # [3] <reserved-2BBA>..<reserved-2BBC> 2BC9 ; Cn # <reserved-2BC9> -2BD2..2BEB ; Cn # [26] <reserved-2BD2>..<reserved-2BEB> +2BD3..2BEB ; Cn # [25] <reserved-2BD3>..<reserved-2BEB> 2BF0..2BFF ; Cn # [16] <reserved-2BF0>..<reserved-2BFF> 2C2F ; Cn # <reserved-2C2F> 2C5F ; Cn # <reserved-2C5F> @@ -302,7 +300,7 @@ 2DCF ; Cn # <reserved-2DCF> 2DD7 ; Cn # <reserved-2DD7> 2DDF ; Cn # <reserved-2DDF> -2E45..2E7F ; Cn # [59] <reserved-2E45>..<reserved-2E7F> +2E4A..2E7F ; Cn # [54] <reserved-2E4A>..<reserved-2E7F> 2E9A ; Cn # <reserved-2E9A> 2EF4..2EFF ; Cn # [12] <reserved-2EF4>..<reserved-2EFF> 2FD6..2FEF ; Cn # [26] <reserved-2FD6>..<reserved-2FEF> @@ -310,14 +308,14 @@ 3040 ; Cn # <reserved-3040> 3097..3098 ; Cn # [2] <reserved-3097>..<reserved-3098> 3100..3104 ; Cn # [5] <reserved-3100>..<reserved-3104> -312E..3130 ; Cn # [3] <reserved-312E>..<reserved-3130> +312F..3130 ; Cn # [2] <reserved-312F>..<reserved-3130> 318F ; Cn # <reserved-318F> 31BB..31BF ; Cn # [5] <reserved-31BB>..<reserved-31BF> 31E4..31EF ; Cn # [12] <reserved-31E4>..<reserved-31EF> 321F ; Cn # <reserved-321F> 32FF ; Cn # <reserved-32FF> 4DB6..4DBF ; Cn # [10] <reserved-4DB6>..<reserved-4DBF> -9FD6..9FFF ; Cn # [42] <reserved-9FD6>..<reserved-9FFF> +9FEB..9FFF ; Cn # [21] <reserved-9FEB>..<reserved-9FFF> A48D..A48F ; Cn # [3] <reserved-A48D>..<reserved-A48F> A4C7..A4CF ; Cn # [9] <reserved-A4C7>..<reserved-A4CF> A62C..A63F ; Cn # [20] <reserved-A62C>..<reserved-A63F> @@ -396,7 +394,7 @@ FFFE..FFFF ; Cn # [2] <noncharacter-FFFE>..<noncharacter-FFFF> 1029D..1029F ; Cn # [3] <reserved-1029D>..<reserved-1029F> 102D1..102DF ; Cn # [15] <reserved-102D1>..<reserved-102DF> 102FC..102FF ; Cn # [4] <reserved-102FC>..<reserved-102FF> -10324..1032F ; Cn # [12] <reserved-10324>..<reserved-1032F> +10324..1032C ; Cn # [9] <reserved-10324>..<reserved-1032C> 1034B..1034F ; Cn # [5] <reserved-1034B>..<reserved-1034F> 1037B..1037F ; Cn # [5] <reserved-1037B>..<reserved-1037F> 1039E ; Cn # <reserved-1039E> @@ -500,7 +498,11 @@ FFFE..FFFF ; Cn # [2] <noncharacter-FFFE>..<noncharacter-FFFF> 1172C..1172F ; Cn # [4] <reserved-1172C>..<reserved-1172F> 11740..1189F ; Cn # [352] <reserved-11740>..<reserved-1189F> 118F3..118FE ; Cn # [12] <reserved-118F3>..<reserved-118FE> -11900..11ABF ; Cn # [448] <reserved-11900>..<reserved-11ABF> +11900..119FF ; Cn # [256] <reserved-11900>..<reserved-119FF> +11A48..11A4F ; Cn # [8] <reserved-11A48>..<reserved-11A4F> +11A84..11A85 ; Cn # [2] <reserved-11A84>..<reserved-11A85> +11A9D ; Cn # <reserved-11A9D> +11AA3..11ABF ; Cn # [29] <reserved-11AA3>..<reserved-11ABF> 11AF9..11BFF ; Cn # [263] <reserved-11AF9>..<reserved-11BFF> 11C09 ; Cn # <reserved-11C09> 11C37 ; Cn # <reserved-11C37> @@ -508,7 +510,14 @@ FFFE..FFFF ; Cn # [2] <noncharacter-FFFE>..<noncharacter-FFFF> 11C6D..11C6F ; Cn # [3] <reserved-11C6D>..<reserved-11C6F> 11C90..11C91 ; Cn # [2] <reserved-11C90>..<reserved-11C91> 11CA8 ; Cn # <reserved-11CA8> -11CB7..11FFF ; Cn # [841] <reserved-11CB7>..<reserved-11FFF> +11CB7..11CFF ; Cn # [73] <reserved-11CB7>..<reserved-11CFF> +11D07 ; Cn # <reserved-11D07> +11D0A ; Cn # <reserved-11D0A> +11D37..11D39 ; Cn # [3] <reserved-11D37>..<reserved-11D39> +11D3B ; Cn # <reserved-11D3B> +11D3E ; Cn # <reserved-11D3E> +11D48..11D4F ; Cn # [8] <reserved-11D48>..<reserved-11D4F> +11D5A..11FFF ; Cn # [678] <reserved-11D5A>..<reserved-11FFF> 1239A..123FF ; Cn # [102] <reserved-1239A>..<reserved-123FF> 1246F ; Cn # <reserved-1246F> 12475..1247F ; Cn # [11] <reserved-12475>..<reserved-1247F> @@ -529,10 +538,11 @@ FFFE..FFFF ; Cn # [2] <noncharacter-FFFE>..<noncharacter-FFFF> 16F45..16F4F ; Cn # [11] <reserved-16F45>..<reserved-16F4F> 16F7F..16F8E ; Cn # [16] <reserved-16F7F>..<reserved-16F8E> 16FA0..16FDF ; Cn # [64] <reserved-16FA0>..<reserved-16FDF> -16FE1..16FFF ; Cn # [31] <reserved-16FE1>..<reserved-16FFF> +16FE2..16FFF ; Cn # [30] <reserved-16FE2>..<reserved-16FFF> 187ED..187FF ; Cn # [19] <reserved-187ED>..<reserved-187FF> 18AF3..1AFFF ; Cn # [9485] <reserved-18AF3>..<reserved-1AFFF> -1B002..1BBFF ; Cn # [3070] <reserved-1B002>..<reserved-1BBFF> +1B11F..1B16F ; Cn # [81] <reserved-1B11F>..<reserved-1B16F> +1B2FC..1BBFF ; Cn # [2308] <reserved-1B2FC>..<reserved-1BBFF> 1BC6B..1BC6F ; Cn # [5] <reserved-1BC6B>..<reserved-1BC6F> 1BC7D..1BC7F ; Cn # [3] <reserved-1BC7D>..<reserved-1BC7F> 1BC89..1BC8F ; Cn # [7] <reserved-1BC89>..<reserved-1BC8F> @@ -624,29 +634,30 @@ FFFE..FFFF ; Cn # [2] <noncharacter-FFFE>..<noncharacter-FFFF> 1F203..1F20F ; Cn # [13] <reserved-1F203>..<reserved-1F20F> 1F23C..1F23F ; Cn # [4] <reserved-1F23C>..<reserved-1F23F> 1F249..1F24F ; Cn # [7] <reserved-1F249>..<reserved-1F24F> -1F252..1F2FF ; Cn # [174] <reserved-1F252>..<reserved-1F2FF> -1F6D3..1F6DF ; Cn # [13] <reserved-1F6D3>..<reserved-1F6DF> +1F252..1F25F ; Cn # [14] <reserved-1F252>..<reserved-1F25F> +1F266..1F2FF ; Cn # [154] <reserved-1F266>..<reserved-1F2FF> +1F6D5..1F6DF ; Cn # [11] <reserved-1F6D5>..<reserved-1F6DF> 1F6ED..1F6EF ; Cn # [3] <reserved-1F6ED>..<reserved-1F6EF> -1F6F7..1F6FF ; Cn # [9] <reserved-1F6F7>..<reserved-1F6FF> +1F6F9..1F6FF ; Cn # [7] <reserved-1F6F9>..<reserved-1F6FF> 1F774..1F77F ; Cn # [12] <reserved-1F774>..<reserved-1F77F> 1F7D5..1F7FF ; Cn # [43] <reserved-1F7D5>..<reserved-1F7FF> 1F80C..1F80F ; Cn # [4] <reserved-1F80C>..<reserved-1F80F> 1F848..1F84F ; Cn # [8] <reserved-1F848>..<reserved-1F84F> 1F85A..1F85F ; Cn # [6] <reserved-1F85A>..<reserved-1F85F> 1F888..1F88F ; Cn # [8] <reserved-1F888>..<reserved-1F88F> -1F8AE..1F90F ; Cn # [98] <reserved-1F8AE>..<reserved-1F90F> -1F91F ; Cn # <reserved-1F91F> -1F928..1F92F ; Cn # [8] <reserved-1F928>..<reserved-1F92F> -1F931..1F932 ; Cn # [2] <reserved-1F931>..<reserved-1F932> +1F8AE..1F8FF ; Cn # [82] <reserved-1F8AE>..<reserved-1F8FF> +1F90C..1F90F ; Cn # [4] <reserved-1F90C>..<reserved-1F90F> 1F93F ; Cn # <reserved-1F93F> -1F94C..1F94F ; Cn # [4] <reserved-1F94C>..<reserved-1F94F> -1F95F..1F97F ; Cn # [33] <reserved-1F95F>..<reserved-1F97F> -1F992..1F9BF ; Cn # [46] <reserved-1F992>..<reserved-1F9BF> -1F9C1..1FFFF ; Cn # [1599] <reserved-1F9C1>..<noncharacter-1FFFF> +1F94D..1F94F ; Cn # [3] <reserved-1F94D>..<reserved-1F94F> +1F96C..1F97F ; Cn # [20] <reserved-1F96C>..<reserved-1F97F> +1F998..1F9BF ; Cn # [40] <reserved-1F998>..<reserved-1F9BF> +1F9C1..1F9CF ; Cn # [15] <reserved-1F9C1>..<reserved-1F9CF> +1F9E7..1FFFF ; Cn # [1561] <reserved-1F9E7>..<noncharacter-1FFFF> 2A6D7..2A6FF ; Cn # [41] <reserved-2A6D7>..<reserved-2A6FF> 2B735..2B73F ; Cn # [11] <reserved-2B735>..<reserved-2B73F> 2B81E..2B81F ; Cn # [2] <reserved-2B81E>..<reserved-2B81F> -2CEA2..2F7FF ; Cn # [10590] <reserved-2CEA2>..<reserved-2F7FF> +2CEA2..2CEAF ; Cn # [14] <reserved-2CEA2>..<reserved-2CEAF> +2EBE1..2F7FF ; Cn # [3103] <reserved-2EBE1>..<reserved-2F7FF> 2FA1E..E0000 ; Cn # [722403] <reserved-2FA1E>..<reserved-E0000> E0002..E001F ; Cn # [30] <reserved-E0002>..<reserved-E001F> E0080..E00FF ; Cn # [128] <reserved-E0080>..<reserved-E00FF> @@ -654,7 +665,7 @@ E01F0..EFFFF ; Cn # [65040] <reserved-E01F0>..<noncharacter-EFFFF> FFFFE..FFFFF ; Cn # [2] <noncharacter-FFFFE>..<noncharacter-FFFFF> 10FFFE..10FFFF; Cn # [2] <noncharacter-10FFFE>..<noncharacter-10FFFF> -# Total code points: 846359 +# Total code points: 837841 # ================================================ @@ -2007,9 +2018,9 @@ FF70 ; Lm # HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK 16B40..16B43 ; Lm # [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM 16F93..16F9F ; Lm # [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 -16FE0 ; Lm # TANGUT ITERATION MARK +16FE0..16FE1 ; Lm # [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK -# Total code points: 249 +# Total code points: 250 # ================================================ @@ -2037,6 +2048,7 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK 07CA..07EA ; Lo # [33] NKO LETTER A..NKO LETTER JONA RA 0800..0815 ; Lo # [22] SAMARITAN LETTER ALAF..SAMARITAN LETTER TAAF 0840..0858 ; Lo # [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN +0860..086A ; Lo # [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 08A0..08B4 ; Lo # [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW 08B6..08BD ; Lo # [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON 0904..0939 ; Lo # [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA @@ -2055,6 +2067,7 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK 09DC..09DD ; Lo # [2] BENGALI LETTER RRA..BENGALI LETTER RHA 09DF..09E1 ; Lo # [3] BENGALI LETTER YYA..BENGALI LETTER VOCALIC LL 09F0..09F1 ; Lo # [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL +09FC ; Lo # BENGALI LETTER VEDIC ANUSVARA 0A05..0A0A ; Lo # [6] GURMUKHI LETTER A..GURMUKHI LETTER UU 0A0F..0A10 ; Lo # [2] GURMUKHI LETTER EE..GURMUKHI LETTER AI 0A13..0A28 ; Lo # [22] GURMUKHI LETTER OO..GURMUKHI LETTER NA @@ -2230,12 +2243,12 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK 309F ; Lo # HIRAGANA DIGRAPH YORI 30A1..30FA ; Lo # [90] KATAKANA LETTER SMALL A..KATAKANA LETTER VO 30FF ; Lo # KATAKANA DIGRAPH KOTO -3105..312D ; Lo # [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH +3105..312E ; Lo # [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE 3131..318E ; Lo # [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE 31A0..31BA ; Lo # [27] BOPOMOFO LETTER BU..BOPOMOFO LETTER ZY 31F0..31FF ; Lo # [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO 3400..4DB5 ; Lo # [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 -4E00..9FD5 ; Lo # [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5 +4E00..9FEA ; Lo # [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA A000..A014 ; Lo # [21] YI SYLLABLE IT..YI SYLLABLE E A016..A48C ; Lo # [1143] YI SYLLABLE BIT..YI SYLLABLE YYR A4D0..A4F7 ; Lo # [40] LISU LETTER BA..LISU LETTER OE @@ -2319,7 +2332,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 10280..1029C ; Lo # [29] LYCIAN LETTER A..LYCIAN LETTER X 102A0..102D0 ; Lo # [49] CARIAN LETTER A..CARIAN LETTER UUU3 10300..1031F ; Lo # [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS -10330..10340 ; Lo # [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA +1032D..10340 ; Lo # [20] OLD ITALIC LETTER YE..GOTHIC LETTER PAIRTHRA 10342..10349 ; Lo # [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL 10350..10375 ; Lo # [38] OLD PERMIC LETTER AN..OLD PERMIC LETTER IA 10380..1039D ; Lo # [30] UGARITIC LETTER ALPA..UGARITIC LETTER SSU @@ -2397,11 +2410,21 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 11680..116AA ; Lo # [43] TAKRI LETTER A..TAKRI LETTER RRA 11700..11719 ; Lo # [26] AHOM LETTER KA..AHOM LETTER JHA 118FF ; Lo # WARANG CITI OM +11A00 ; Lo # ZANABAZAR SQUARE LETTER A +11A0B..11A32 ; Lo # [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA +11A3A ; Lo # ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA +11A50 ; Lo # SOYOMBO LETTER A +11A5C..11A83 ; Lo # [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA +11A86..11A89 ; Lo # [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA 11AC0..11AF8 ; Lo # [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL 11C00..11C08 ; Lo # [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E ; Lo # [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA 11C40 ; Lo # BHAIKSUKI SIGN AVAGRAHA 11C72..11C8F ; Lo # [30] MARCHEN LETTER KA..MARCHEN LETTER A +11D00..11D06 ; Lo # [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E +11D08..11D09 ; Lo # [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O +11D0B..11D30 ; Lo # [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA +11D46 ; Lo # MASARAM GONDI REPHA 12000..12399 ; Lo # [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12480..12543 ; Lo # [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU 13000..1342E ; Lo # [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032 @@ -2416,7 +2439,8 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 16F50 ; Lo # MIAO LETTER NASALIZATION 17000..187EC ; Lo # [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC 18800..18AF2 ; Lo # [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755 -1B000..1B001 ; Lo # [2] KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE +1B000..1B11E ; Lo # [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1B170..1B2FB ; Lo # [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 1BC00..1BC6A ; Lo # [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M 1BC70..1BC7C ; Lo # [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK 1BC80..1BC88 ; Lo # [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL @@ -2459,9 +2483,10 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 2A700..2B734 ; Lo # [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 2B740..2B81D ; Lo # [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; Lo # [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 +2CEB0..2EBE0 ; Lo # [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; Lo # [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D -# Total code points: 112721 +# Total code points: 121047 # ================================================ @@ -2517,6 +2542,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 0AC7..0AC8 ; Mn # [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI 0ACD ; Mn # GUJARATI SIGN VIRAMA 0AE2..0AE3 ; Mn # [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0AFA..0AFF ; Mn # [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE 0B01 ; Mn # ORIYA SIGN CANDRABINDU 0B3C ; Mn # ORIYA SIGN NUKTA 0B3F ; Mn # ORIYA VOWEL SIGN I @@ -2539,7 +2565,8 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 0CC6 ; Mn # KANNADA VOWEL SIGN E 0CCC..0CCD ; Mn # [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA 0CE2..0CE3 ; Mn # [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL -0D01 ; Mn # MALAYALAM SIGN CANDRABINDU +0D00..0D01 ; Mn # [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU +0D3B..0D3C ; Mn # [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA 0D41..0D44 ; Mn # [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR 0D4D ; Mn # MALAYALAM SIGN VIRAMA 0D62..0D63 ; Mn # [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL @@ -2623,7 +2650,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 1CED ; Mn # VEDIC SIGN TIRYAK 1CF4 ; Mn # VEDIC TONE CANDRA ABOVE 1CF8..1CF9 ; Mn # [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE -1DC0..1DF5 ; Mn # [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE +1DC0..1DF9 ; Mn # [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW 1DFB..1DFF ; Mn # [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 20D0..20DC ; Mn # [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE 20E1 ; Mn # COMBINING LEFT RIGHT ARROW ABOVE @@ -2722,6 +2749,15 @@ FE20..FE2F ; Mn # [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITL 1171D..1171F ; Mn # [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA 11722..11725 ; Mn # [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU 11727..1172B ; Mn # [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER +11A01..11A06 ; Mn # [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O +11A09..11A0A ; Mn # [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A33..11A38 ; Mn # [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A3B..11A3E ; Mn # [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A47 ; Mn # ZANABAZAR SQUARE SUBJOINER +11A51..11A56 ; Mn # [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A59..11A5B ; Mn # [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A8A..11A96 ; Mn # [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A98..11A99 ; Mn # [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER 11C30..11C36 ; Mn # [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L 11C38..11C3D ; Mn # [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA 11C3F ; Mn # BHAIKSUKI SIGN VIRAMA @@ -2729,6 +2765,11 @@ FE20..FE2F ; Mn # [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITL 11CAA..11CB0 ; Mn # [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA 11CB2..11CB3 ; Mn # [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E 11CB5..11CB6 ; Mn # [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D31..11D36 ; Mn # [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; Mn # MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; Mn # [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45 ; Mn # [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D47 ; Mn # MASARAM GONDI RA-KARA 16AF0..16AF4 ; Mn # [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; Mn # [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM 16F8F..16F92 ; Mn # [4] MIAO TONE RIGHT..MIAO TONE BELOW @@ -2753,7 +2794,7 @@ FE20..FE2F ; Mn # [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITL 1E944..1E94A ; Mn # [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0100..E01EF ; Mn # [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 1690 +# Total code points: 1763 # ================================================ @@ -2858,6 +2899,7 @@ A670..A672 ; Me # [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRIL 1C34..1C35 ; Mc # [2] LEPCHA CONSONANT SIGN NYIN-DO..LEPCHA CONSONANT SIGN KANG 1CE1 ; Mc # VEDIC TONE ATHARVAVEDIC INDEPENDENT SVARITA 1CF2..1CF3 ; Mc # [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA +1CF7 ; Mc # VEDIC SIGN ATIKRAMA 302E..302F ; Mc # [2] HANGUL SINGLE DOT TONE MARK..HANGUL DOUBLE DOT TONE MARK A823..A824 ; Mc # [2] SYLOTI NAGRI VOWEL SIGN A..SYLOTI NAGRI VOWEL SIGN I A827 ; Mc # SYLOTI NAGRI VOWEL SIGN OO @@ -2918,6 +2960,10 @@ ABEC ; Mc # MEETEI MAYEK LUM IYEK 116B6 ; Mc # TAKRI SIGN VIRAMA 11720..11721 ; Mc # [2] AHOM VOWEL SIGN A..AHOM VOWEL SIGN AA 11726 ; Mc # AHOM VOWEL SIGN E +11A07..11A08 ; Mc # [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU +11A39 ; Mc # ZANABAZAR SQUARE SIGN VISARGA +11A57..11A58 ; Mc # [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU +11A97 ; Mc # SOYOMBO SIGN VISARGA 11C2F ; Mc # BHAIKSUKI VOWEL SIGN AA 11C3E ; Mc # BHAIKSUKI SIGN VISARGA 11CA9 ; Mc # MARCHEN SUBJOINED LETTER YA @@ -2927,7 +2973,7 @@ ABEC ; Mc # MEETEI MAYEK LUM IYEK 1D165..1D166 ; Mc # [2] MUSICAL SYMBOL COMBINING STEM..MUSICAL SYMBOL COMBINING SPRECHGESANG STEM 1D16D..1D172 ; Mc # [6] MUSICAL SYMBOL COMBINING AUGMENTATION DOT..MUSICAL SYMBOL COMBINING FLAG-5 -# Total code points: 394 +# Total code points: 401 # ================================================ @@ -2983,12 +3029,13 @@ FF10..FF19 ; Nd # [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 11730..11739 ; Nd # [10] AHOM DIGIT ZERO..AHOM DIGIT NINE 118E0..118E9 ; Nd # [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE 11C50..11C59 ; Nd # [10] BHAIKSUKI DIGIT ZERO..BHAIKSUKI DIGIT NINE +11D50..11D59 ; Nd # [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE 16A60..16A69 ; Nd # [10] MRO DIGIT ZERO..MRO DIGIT NINE 16B50..16B59 ; Nd # [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE 1D7CE..1D7FF ; Nd # [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE 1E950..1E959 ; Nd # [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE -# Total code points: 580 +# Total code points: 590 # ================================================ @@ -3392,6 +3439,7 @@ FF3F ; Pc # FULLWIDTH LOW LINE 085E ; Po # MANDAIC PUNCTUATION 0964..0965 ; Po # [2] DEVANAGARI DANDA..DEVANAGARI DOUBLE DANDA 0970 ; Po # DEVANAGARI ABBREVIATION SIGN +09FD ; Po # BENGALI ABBREVIATION SIGN 0AF0 ; Po # GUJARATI ABBREVIATION SIGN 0DF4 ; Po # SINHALA PUNCTUATION KUNDDALIYA 0E4F ; Po # THAI CHARACTER FONGMAN @@ -3443,7 +3491,7 @@ FF3F ; Pc # FULLWIDTH LOW LINE 2E30..2E39 ; Po # [10] RING POINT..TOP HALF SECTION SIGN 2E3C..2E3F ; Po # [4] STENOGRAPHIC FULL STOP..CAPITULUM 2E41 ; Po # REVERSED COMMA -2E43..2E44 ; Po # [2] DASH WITH LEFT UPTURN..DOUBLE SUSPENSION MARK +2E43..2E49 ; Po # [7] DASH WITH LEFT UPTURN..DOUBLE STACKED COMMA 3001..3003 ; Po # [3] IDEOGRAPHIC COMMA..DITTO MARK 303D ; Po # PART ALTERNATION MARK 30FB ; Po # KATAKANA MIDDLE DOT @@ -3515,6 +3563,9 @@ FF64..FF65 ; Po # [2] HALFWIDTH IDEOGRAPHIC COMMA..HALFWIDTH KATAKANA MIDDL 11641..11643 ; Po # [3] MODI DANDA..MODI ABBREVIATION SIGN 11660..1166C ; Po # [13] MONGOLIAN BIRGA WITH ORNAMENT..MONGOLIAN TURNED SWIRL BIRGA WITH DOUBLE ORNAMENT 1173C..1173E ; Po # [3] AHOM SIGN SMALL SECTION..AHOM SIGN RULAI +11A3F..11A46 ; Po # [8] ZANABAZAR SQUARE INITIAL HEAD MARK..ZANABAZAR SQUARE CLOSING DOUBLE-LINED HEAD MARK +11A9A..11A9C ; Po # [3] SOYOMBO MARK TSHEG..SOYOMBO MARK DOUBLE SHAD +11A9E..11AA2 ; Po # [5] SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME..SOYOMBO TERMINAL MARK-2 11C41..11C45 ; Po # [5] BHAIKSUKI DANDA..BHAIKSUKI GAP FILLER-2 11C70..11C71 ; Po # [2] MARCHEN HEAD MARK..MARCHEN MARK SHAD 12470..12474 ; Po # [5] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON @@ -3526,7 +3577,7 @@ FF64..FF65 ; Po # [2] HALFWIDTH IDEOGRAPHIC COMMA..HALFWIDTH KATAKANA MIDDL 1DA87..1DA8B ; Po # [5] SIGNWRITING COMMA..SIGNWRITING PARENTHESIS 1E95E..1E95F ; Po # [2] ADLAM INITIAL EXCLAMATION MARK..ADLAM INITIAL QUESTION MARK -# Total code points: 544 +# Total code points: 566 # ================================================ @@ -3613,7 +3664,7 @@ FFE9..FFEC ; Sm # [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS ARROW 0BF9 ; Sc # TAMIL RUPEE SIGN 0E3F ; Sc # THAI CURRENCY SYMBOL BAHT 17DB ; Sc # KHMER CURRENCY SYMBOL RIEL -20A0..20BE ; Sc # [31] EURO-CURRENCY SIGN..LARI SIGN +20A0..20BF ; Sc # [32] EURO-CURRENCY SIGN..BITCOIN SIGN A838 ; Sc # NORTH INDIC RUPEE MARK FDFC ; Sc # RIAL SIGN FE69 ; Sc # SMALL DOLLAR SIGN @@ -3621,7 +3672,7 @@ FF04 ; Sc # FULLWIDTH DOLLAR SIGN FFE0..FFE1 ; Sc # [2] FULLWIDTH CENT SIGN..FULLWIDTH POUND SIGN FFE5..FFE6 ; Sc # [2] FULLWIDTH YEN SIGN..FULLWIDTH WON SIGN -# Total code points: 53 +# Total code points: 54 # ================================================ @@ -3728,8 +3779,7 @@ FFE3 ; Sk # FULLWIDTH MACRON 232B..237B ; So # [81] ERASE TO THE LEFT..NOT CHECK MARK 237D..239A ; So # [30] SHOULDERED OPEN BOX..CLEAR SCREEN SYMBOL 23B4..23DB ; So # [40] TOP SQUARE BRACKET..FUSE -23E2..23FE ; So # [29] WHITE TRAPEZIUM..POWER SLEEP SYMBOL -2400..2426 ; So # [39] SYMBOL FOR NULL..SYMBOL FOR SUBSTITUTE FORM TWO +23E2..2426 ; So # [69] WHITE TRAPEZIUM..SYMBOL FOR SUBSTITUTE FORM TWO 2440..244A ; So # [11] OCR HOOK..OCR DOUBLE BACKSLASH 249C..24E9 ; So # [78] PARENTHESIZED LATIN SMALL LETTER A..CIRCLED LATIN SMALL LETTER Z 2500..25B6 ; So # [183] BOX DRAWINGS LIGHT HORIZONTAL..BLACK RIGHT-POINTING TRIANGLE @@ -3745,7 +3795,7 @@ FFE3 ; Sk # FULLWIDTH MACRON 2B76..2B95 ; So # [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW 2B98..2BB9 ; So # [34] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..UP ARROWHEAD IN A RECTANGLE BOX 2BBD..2BC8 ; So # [12] BALLOT BOX WITH LIGHT X..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED -2BCA..2BD1 ; So # [8] TOP HALF BLACK CIRCLE..UNCERTAINTY SIGN +2BCA..2BD2 ; So # [9] TOP HALF BLACK CIRCLE..GROUP MARK 2BEC..2BEF ; So # [4] LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS..DOWNWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS 2CE5..2CEA ; So # [6] COPTIC SYMBOL MI RO..COPTIC SYMBOL SHIMA SIMA 2E80..2E99 ; So # [26] CJK RADICAL REPEAT..CJK RADICAL RAP @@ -3818,10 +3868,11 @@ FFFC..FFFD ; So # [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1F210..1F23B ; So # [44] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-914D 1F240..1F248 ; So # [9] TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C..TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557 1F250..1F251 ; So # [2] CIRCLED IDEOGRAPH ADVANTAGE..CIRCLED IDEOGRAPH ACCEPT +1F260..1F265 ; So # [6] ROUNDED SYMBOL FOR FU..ROUNDED SYMBOL FOR CAI 1F300..1F3FA ; So # [251] CYCLONE..AMPHORA -1F400..1F6D2 ; So # [723] RAT..SHOPPING TROLLEY +1F400..1F6D4 ; So # [725] RAT..PAGODA 1F6E0..1F6EC ; So # [13] HAMMER AND WRENCH..AIRPLANE ARRIVING -1F6F0..1F6F6 ; So # [7] SATELLITE..CANOE +1F6F0..1F6F8 ; So # [9] SATELLITE..FLYING SAUCER 1F700..1F773 ; So # [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE 1F780..1F7D4 ; So # [85] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..HEAVY TWELVE POINTED PINWHEEL STAR 1F800..1F80B ; So # [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD @@ -3829,16 +3880,15 @@ FFFC..FFFD ; So # [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1F850..1F859 ; So # [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW 1F860..1F887 ; So # [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW 1F890..1F8AD ; So # [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS -1F910..1F91E ; So # [15] ZIPPER-MOUTH FACE..HAND WITH INDEX AND MIDDLE FINGERS CROSSED -1F920..1F927 ; So # [8] FACE WITH COWBOY HAT..SNEEZING FACE -1F930 ; So # PREGNANT WOMAN -1F933..1F93E ; So # [12] SELFIE..HANDBALL -1F940..1F94B ; So # [12] WILTED FLOWER..MARTIAL ARTS UNIFORM -1F950..1F95E ; So # [15] CROISSANT..PANCAKES -1F980..1F991 ; So # [18] CRAB..SQUID +1F900..1F90B ; So # [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT +1F910..1F93E ; So # [47] ZIPPER-MOUTH FACE..HANDBALL +1F940..1F94C ; So # [13] WILTED FLOWER..CURLING STONE +1F950..1F96B ; So # [28] CROISSANT..CANNED FOOD +1F980..1F997 ; So # [24] CRAB..CRICKET 1F9C0 ; So # CHEESE WEDGE +1F9D0..1F9E6 ; So # [23] FACE WITH MONOCLE..SOCKS -# Total code points: 5777 +# Total code points: 5855 # ================================================ diff --git a/lib/unicore/extracted/DJoinGroup.txt b/lib/unicore/extracted/DJoinGroup.txt index 548621d918..d1318f75fc 100644 --- a/lib/unicore/extracted/DJoinGroup.txt +++ b/lib/unicore/extracted/DJoinGroup.txt @@ -1,6 +1,6 @@ -# DerivedJoiningGroup-9.0.0.txt -# Date: 2016-03-02, 18:54:59 GMT -# © 2016 Unicode®, Inc. +# DerivedJoiningGroup-10.0.0.txt +# Date: 2017-02-17, 04:46:04 GMT +# © 2017 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html # @@ -633,4 +633,70 @@ # Total code points: 1 +# ================================================ + +0860 ; Malayalam_Nga # Lo SYRIAC LETTER MALAYALAM NGA + +# Total code points: 1 + +# ================================================ + +0861 ; Malayalam_Ja # Lo SYRIAC LETTER MALAYALAM JA + +# Total code points: 1 + +# ================================================ + +0862 ; Malayalam_Nya # Lo SYRIAC LETTER MALAYALAM NYA + +# Total code points: 1 + +# ================================================ + +0863 ; Malayalam_Tta # Lo SYRIAC LETTER MALAYALAM TTA + +# Total code points: 1 + +# ================================================ + +0864 ; Malayalam_Nna # Lo SYRIAC LETTER MALAYALAM NNA + +# Total code points: 1 + +# ================================================ + +0865 ; Malayalam_Nnna # Lo SYRIAC LETTER MALAYALAM NNNA + +# Total code points: 1 + +# ================================================ + +0866 ; Malayalam_Bha # Lo SYRIAC LETTER MALAYALAM BHA + +# Total code points: 1 + +# ================================================ + +0867 ; Malayalam_Ra # Lo SYRIAC LETTER MALAYALAM RA + +# Total code points: 1 + +# ================================================ + +0868 ; Malayalam_Lla # Lo SYRIAC LETTER MALAYALAM LLA + +# Total code points: 1 + +# ================================================ + +0869 ; Malayalam_Llla # Lo SYRIAC LETTER MALAYALAM LLLA + +# Total code points: 1 + +# ================================================ + +086A ; Malayalam_Ssa # Lo SYRIAC LETTER MALAYALAM SSA + +# Total code points: 1 + # EOF diff --git a/lib/unicore/extracted/DJoinType.txt b/lib/unicore/extracted/DJoinType.txt index 0fb5439afd..ea351f5eff 100644 --- a/lib/unicore/extracted/DJoinType.txt +++ b/lib/unicore/extracted/DJoinType.txt @@ -1,6 +1,6 @@ -# DerivedJoiningType-9.0.0.txt -# Date: 2016-06-01, 10:34:26 GMT -# © 2016 Unicode®, Inc. +# DerivedJoiningType-10.0.0.txt +# Date: 2017-03-08, 08:41:50 GMT +# © 2017 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html # @@ -64,6 +64,9 @@ 0848 ; D # Lo MANDAIC LETTER ATT 084A..0853 ; D # Lo [10] MANDAIC LETTER AK..MANDAIC LETTER AR 0855 ; D # Lo MANDAIC LETTER AT +0860 ; D # Lo SYRIAC LETTER MALAYALAM NGA +0862..0865 ; D # Lo [4] SYRIAC LETTER MALAYALAM NYA..SYRIAC LETTER MALAYALAM NNNA +0868 ; D # Lo SYRIAC LETTER MALAYALAM LLA 08A0..08A9 ; D # Lo [10] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER YEH WITH TWO DOTS BELOW AND DOT ABOVE 08AF..08B0 ; D # Lo [2] ARABIC LETTER SAD WITH THREE DOTS BELOW..ARABIC LETTER GAF WITH INVERTED STROKE 08B3..08B4 ; D # Lo [2] ARABIC LETTER AIN WITH THREE DOTS BELOW..ARABIC LETTER KAF WITH DOT BELOW @@ -90,7 +93,7 @@ A840..A871 ; D # Lo [50] PHAGS-PA LETTER KA..PHAGS-PA SUBJOINED LETTER RA 10BAD..10BAE ; D # No [2] PSALTER PAHLAVI NUMBER TEN..PSALTER PAHLAVI NUMBER TWENTY 1E900..1E943 ; D # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 501 +# Total code points: 507 # ================================================ @@ -128,6 +131,8 @@ A840..A871 ; D # Lo [50] PHAGS-PA LETTER KA..PHAGS-PA SUBJOINED LETTER RA 0846..0847 ; R # Lo [2] MANDAIC LETTER AZ..MANDAIC LETTER IT 0849 ; R # Lo MANDAIC LETTER AKSA 0854 ; R # Lo MANDAIC LETTER ASH +0867 ; R # Lo SYRIAC LETTER MALAYALAM RA +0869..086A ; R # Lo [2] SYRIAC LETTER MALAYALAM LLLA..SYRIAC LETTER MALAYALAM SSA 08AA..08AC ; R # Lo [3] ARABIC LETTER REH WITH LOOP..ARABIC LETTER ROHINGYA YEH 08AE ; R # Lo ARABIC LETTER DAL WITH THREE DOTS BELOW 08B1..08B2 ; R # Lo [2] ARABIC LETTER STRAIGHT WAW..ARABIC LETTER ZAIN WITH INVERTED V ABOVE @@ -148,7 +153,7 @@ A840..A871 ; D # Lo [50] PHAGS-PA LETTER KA..PHAGS-PA SUBJOINED LETTER RA 10B91 ; R # Lo PSALTER PAHLAVI LETTER TAW 10BA9..10BAC ; R # No [4] PSALTER PAHLAVI NUMBER ONE..PSALTER PAHLAVI NUMBER FOUR -# Total code points: 112 +# Total code points: 115 # ================================================ @@ -218,6 +223,7 @@ A872 ; L # Lo PHAGS-PA SUPERFIXED LETTER RA 0AC7..0AC8 ; T # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI 0ACD ; T # Mn GUJARATI SIGN VIRAMA 0AE2..0AE3 ; T # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0AFA..0AFF ; T # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE 0B01 ; T # Mn ORIYA SIGN CANDRABINDU 0B3C ; T # Mn ORIYA SIGN NUKTA 0B3F ; T # Mn ORIYA VOWEL SIGN I @@ -240,7 +246,8 @@ A872 ; L # Lo PHAGS-PA SUPERFIXED LETTER RA 0CC6 ; T # Mn KANNADA VOWEL SIGN E 0CCC..0CCD ; T # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA 0CE2..0CE3 ; T # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL -0D01 ; T # Mn MALAYALAM SIGN CANDRABINDU +0D00..0D01 ; T # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU +0D3B..0D3C ; T # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA 0D41..0D44 ; T # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR 0D4D ; T # Mn MALAYALAM SIGN VIRAMA 0D62..0D63 ; T # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL @@ -325,7 +332,7 @@ A872 ; L # Lo PHAGS-PA SUPERFIXED LETTER RA 1CED ; T # Mn VEDIC SIGN TIRYAK 1CF4 ; T # Mn VEDIC TONE CANDRA ABOVE 1CF8..1CF9 ; T # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE -1DC0..1DF5 ; T # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE +1DC0..1DF9 ; T # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW 1DFB..1DFF ; T # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 200B ; T # Cf ZERO WIDTH SPACE 200E..200F ; T # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK @@ -435,6 +442,15 @@ FFF9..FFFB ; T # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATI 1171D..1171F ; T # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA 11722..11725 ; T # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU 11727..1172B ; T # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER +11A01..11A06 ; T # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O +11A09..11A0A ; T # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A33..11A38 ; T # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A3B..11A3E ; T # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A47 ; T # Mn ZANABAZAR SQUARE SUBJOINER +11A51..11A56 ; T # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A59..11A5B ; T # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A8A..11A96 ; T # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A98..11A99 ; T # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER 11C30..11C36 ; T # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L 11C38..11C3D ; T # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA 11C3F ; T # Mn BHAIKSUKI SIGN VIRAMA @@ -442,6 +458,11 @@ FFF9..FFFB ; T # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATI 11CAA..11CB0 ; T # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA 11CB2..11CB3 ; T # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E 11CB5..11CB6 ; T # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D31..11D36 ; T # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; T # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; T # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45 ; T # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D47 ; T # Mn MASARAM GONDI RA-KARA 16AF0..16AF4 ; T # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; T # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM 16F8F..16F92 ; T # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW @@ -470,6 +491,6 @@ E0001 ; T # Cf LANGUAGE TAG E0020..E007F ; T # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; T # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 1839 +# Total code points: 1912 # EOF diff --git a/lib/unicore/extracted/DLineBreak.txt b/lib/unicore/extracted/DLineBreak.txt index f9140d86e1..aff9e19c0a 100644 --- a/lib/unicore/extracted/DLineBreak.txt +++ b/lib/unicore/extracted/DLineBreak.txt @@ -1,6 +1,6 @@ -# DerivedLineBreak-9.0.0.txt -# Date: 2016-06-01, 10:34:26 GMT -# © 2016 Unicode®, Inc. +# DerivedLineBreak-10.0.0.txt +# Date: 2017-03-08, 08:41:50 GMT +# © 2017 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html # @@ -24,8 +24,8 @@ E000..F8FF ; XX # Co [6400] <private-use-E000>..<private-use-F8FF> F0000..FFFFD ; XX # Co [65534] <private-use-F0000>..<private-use-FFFFD> 100000..10FFFD; XX # Co [65534] <private-use-100000>..<private-use-10FFFD> -# The above property value applies to 766379 code points not listed here. -# Total code points: 903847 +# The above property value applies to 765432 code points not listed here. +# Total code points: 902900 # ================================================ @@ -283,10 +283,10 @@ FE54..FE55 ; NS # Po [2] SMALL SEMICOLON..SMALL COLON FF1A..FF1B ; NS # Po [2] FULLWIDTH COLON..FULLWIDTH SEMICOLON FF65 ; NS # Po HALFWIDTH KATAKANA MIDDLE DOT FF9E..FF9F ; NS # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK -16FE0 ; NS # Lm TANGUT ITERATION MARK +16FE0..16FE1 ; NS # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK 1F679..1F67B ; NS # So [3] HEAVY INTERROBANG ORNAMENT..HEAVY SANS-SERIF INTERROBANG ORNAMENT -# Total code points: 30 +# Total code points: 31 # ================================================ @@ -363,7 +363,8 @@ FE13..FE14 ; IS # Po [2] PRESENTATION FORM FOR VERTICAL COLON..PRESENTATION 20A8..20B5 ; PR # Sc [14] RUPEE SIGN..CEDI SIGN 20B7..20BA ; PR # Sc [4] SPESMILO SIGN..TURKISH LIRA SIGN 20BC..20BD ; PR # Sc [2] MANAT SIGN..RUBLE SIGN -20BF..20CF ; PR # Cn [17] <reserved-20BF>..<reserved-20CF> +20BF ; PR # Sc BITCOIN SIGN +20C0..20CF ; PR # Cn [16] <reserved-20C0>..<reserved-20CF> 2116 ; PR # So NUMERO SIGN 2212..2213 ; PR # Sm [2] MINUS SIGN..MINUS-OR-PLUS SIGN FE69 ; PR # Sc SMALL DOLLAR SIGN @@ -455,12 +456,13 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 11730..11739 ; NU # Nd [10] AHOM DIGIT ZERO..AHOM DIGIT NINE 118E0..118E9 ; NU # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE 11C50..11C59 ; NU # Nd [10] BHAIKSUKI DIGIT ZERO..BHAIKSUKI DIGIT NINE +11D50..11D59 ; NU # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE 16A60..16A69 ; NU # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE 16B50..16B59 ; NU # Nd [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE 1D7CE..1D7FF ; NU # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE 1E950..1E959 ; NU # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE -# Total code points: 572 +# Total code points: 582 # ================================================ @@ -568,6 +570,7 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 0830..083E ; AL # Po [15] SAMARITAN PUNCTUATION NEQUDAA..SAMARITAN PUNCTUATION ANNAAU 0840..0858 ; AL # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 085E ; AL # Po MANDAIC PUNCTUATION +0860..086A ; AL # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 08A0..08B4 ; AL # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW 08B6..08BD ; AL # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON 08E2 ; AL # Cf ARABIC DISPUTED END OF AYAH @@ -591,6 +594,8 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 09F0..09F1 ; AL # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL 09F4..09F8 ; AL # No [5] BENGALI CURRENCY NUMERATOR ONE..BENGALI CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR 09FA ; AL # So BENGALI ISSHAR +09FC ; AL # Lo BENGALI LETTER VEDIC ANUSVARA +09FD ; AL # Po BENGALI ABBREVIATION SIGN 0A05..0A0A ; AL # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU 0A0F..0A10 ; AL # Lo [2] GURMUKHI LETTER EE..GURMUKHI LETTER AI 0A13..0A28 ; AL # Lo [22] GURMUKHI LETTER OO..GURMUKHI LETTER NA @@ -925,8 +930,7 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 23B4..23DB ; AL # So [40] TOP SQUARE BRACKET..FUSE 23DC..23E1 ; AL # Sm [6] TOP PARENTHESIS..BOTTOM TORTOISE SHELL BRACKET 23E2..23EF ; AL # So [14] WHITE TRAPEZIUM..BLACK RIGHT-POINTING TRIANGLE WITH DOUBLE VERTICAL BAR -23F4..23FE ; AL # So [11] BLACK MEDIUM LEFT-POINTING TRIANGLE..POWER SLEEP SYMBOL -2400..2426 ; AL # So [39] SYMBOL FOR NULL..SYMBOL FOR SUBSTITUTE FORM TWO +23F4..2426 ; AL # So [51] BLACK MEDIUM LEFT-POINTING TRIANGLE..SYMBOL FOR SUBSTITUTE FORM TWO 2440..244A ; AL # So [11] OCR HOOK..OCR DOUBLE BACKSLASH 24FF ; AL # No NEGATIVE CIRCLED DIGIT ZERO 254C..254F ; AL # So [4] BOX DRAWINGS LIGHT DOUBLE DASH HORIZONTAL..BOX DRAWINGS HEAVY DOUBLE DASH VERTICAL @@ -987,7 +991,7 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 2B76..2B95 ; AL # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW 2B98..2BB9 ; AL # So [34] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..UP ARROWHEAD IN A RECTANGLE BOX 2BBD..2BC8 ; AL # So [12] BALLOT BOX WITH LIGHT X..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED -2BCA..2BD1 ; AL # So [8] TOP HALF BLACK CIRCLE..UNCERTAINTY SIGN +2BCA..2BD2 ; AL # So [9] TOP HALF BLACK CIRCLE..GROUP MARK 2BEC..2BEF ; AL # So [4] LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS..DOWNWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS 2C00..2C2E ; AL # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE 2C30..2C5E ; AL # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE @@ -1129,7 +1133,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 102E1..102FB ; AL # No [27] COPTIC EPACT DIGIT ONE..COPTIC EPACT NUMBER NINE HUNDRED 10300..1031F ; AL # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS 10320..10323 ; AL # No [4] OLD ITALIC NUMERAL ONE..OLD ITALIC NUMERAL FIFTY -10330..10340 ; AL # Lo [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA +1032D..10340 ; AL # Lo [20] OLD ITALIC LETTER YE..GOTHIC LETTER PAIRTHRA 10341 ; AL # Nl GOTHIC LETTER NINETY 10342..10349 ; AL # Lo [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL 1034A ; AL # Nl GOTHIC LETTER NINE HUNDRED @@ -1256,12 +1260,24 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 118A0..118DF ; AL # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 118EA..118F2 ; AL # No [9] WARANG CITI NUMBER TEN..WARANG CITI NUMBER NINETY 118FF ; AL # Lo WARANG CITI OM +11A00 ; AL # Lo ZANABAZAR SQUARE LETTER A +11A0B..11A32 ; AL # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA +11A3A ; AL # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA +11A40 ; AL # Po ZANABAZAR SQUARE CLOSING HEAD MARK +11A46 ; AL # Po ZANABAZAR SQUARE CLOSING DOUBLE-LINED HEAD MARK +11A50 ; AL # Lo SOYOMBO LETTER A +11A5C..11A83 ; AL # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA +11A86..11A89 ; AL # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA 11AC0..11AF8 ; AL # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL 11C00..11C08 ; AL # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E ; AL # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA 11C40 ; AL # Lo BHAIKSUKI SIGN AVAGRAHA 11C5A..11C6C ; AL # No [19] BHAIKSUKI NUMBER ONE..BHAIKSUKI HUNDREDS UNIT MARK 11C72..11C8F ; AL # Lo [30] MARCHEN LETTER KA..MARCHEN LETTER A +11D00..11D06 ; AL # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E +11D08..11D09 ; AL # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O +11D0B..11D30 ; AL # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA +11D46 ; AL # Lo MASARAM GONDI REPHA 12000..12399 ; AL # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; AL # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12480..12543 ; AL # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU @@ -1409,8 +1425,9 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1F850..1F859 ; AL # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW 1F860..1F887 ; AL # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW 1F890..1F8AD ; AL # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS +1F900..1F90B ; AL # So [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT -# Total code points: 19523 +# Total code points: 19690 # ================================================ @@ -1480,7 +1497,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 30EF..30F4 ; ID # Lo [6] KATAKANA LETTER WA..KATAKANA LETTER VU 30F7..30FA ; ID # Lo [4] KATAKANA LETTER VA..KATAKANA LETTER VO 30FF ; ID # Lo KATAKANA DIGRAPH KOTO -3105..312D ; ID # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH +3105..312E ; ID # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE 3131..318E ; ID # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE 3190..3191 ; ID # So [2] IDEOGRAPHIC ANNOTATION LINKING MARK..IDEOGRAPHIC ANNOTATION REVERSE MARK 3192..3195 ; ID # No [4] IDEOGRAPHIC ANNOTATION ONE MARK..IDEOGRAPHIC ANNOTATION FOUR MARK @@ -1500,8 +1517,8 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 3300..33FF ; ID # So [256] SQUARE APAATO..SQUARE GAL 3400..4DB5 ; ID # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 4DB6..4DBF ; ID # Cn [10] <reserved-4DB6>..<reserved-4DBF> -4E00..9FD5 ; ID # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5 -9FD6..9FFF ; ID # Cn [42] <reserved-9FD6>..<reserved-9FFF> +4E00..9FEA ; ID # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA +9FEB..9FFF ; ID # Cn [21] <reserved-9FEB>..<reserved-9FFF> A000..A014 ; ID # Lo [21] YI SYLLABLE IT..YI SYLLABLE E A016..A48C ; ID # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR A490..A4C6 ; ID # So [55] YI RADICAL QOT..YI RADICAL KE @@ -1552,7 +1569,8 @@ FFE3 ; ID # Sk FULLWIDTH MACRON FFE4 ; ID # So FULLWIDTH BROKEN BAR 17000..187EC ; ID # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC 18800..18AF2 ; ID # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755 -1B000..1B001 ; ID # Lo [2] KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE +1B000..1B11E ; ID # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1B170..1B2FB ; ID # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 1F000..1F02B ; ID # So [44] MAHJONG TILE EAST WIND..MAHJONG TILE BACK 1F02C..1F02F ; ID # Cn [4] <reserved-1F02C>..<reserved-1F02F> 1F030..1F093 ; ID # So [100] DOMINO TILE HORIZONTAL BACK..DOMINO TILE VERTICAL-06-06 @@ -1576,14 +1594,17 @@ FFE4 ; ID # So FULLWIDTH BROKEN BAR 1F240..1F248 ; ID # So [9] TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C..TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557 1F249..1F24F ; ID # Cn [7] <reserved-1F249>..<reserved-1F24F> 1F250..1F251 ; ID # So [2] CIRCLED IDEOGRAPH ADVANTAGE..CIRCLED IDEOGRAPH ACCEPT -1F252..1F2FF ; ID # Cn [174] <reserved-1F252>..<reserved-1F2FF> +1F252..1F25F ; ID # Cn [14] <reserved-1F252>..<reserved-1F25F> +1F260..1F265 ; ID # So [6] ROUNDED SYMBOL FOR FU..ROUNDED SYMBOL FOR CAI +1F266..1F2FF ; ID # Cn [154] <reserved-1F266>..<reserved-1F2FF> 1F300..1F384 ; ID # So [133] CYCLONE..CHRISTMAS TREE 1F386..1F39B ; ID # So [22] FIREWORKS..CONTROL KNOBS 1F39E..1F3B4 ; ID # So [23] FILM FRAMES..FLOWER PLAYING CARDS 1F3B7..1F3BB ; ID # So [5] SAXOPHONE..VIOLIN -1F3BD..1F3C2 ; ID # So [6] RUNNING SHIRT WITH SASH..SNOWBOARDER -1F3C5..1F3C9 ; ID # So [5] SPORTS MEDAL..RUGBY FOOTBALL -1F3CC..1F3FA ; ID # So [47] GOLFER..AMPHORA +1F3BD..1F3C1 ; ID # So [5] RUNNING SHIRT WITH SASH..CHEQUERED FLAG +1F3C5..1F3C6 ; ID # So [2] SPORTS MEDAL..TROPHY +1F3C8..1F3C9 ; ID # So [2] AMERICAN FOOTBALL..RUGBY FOOTBALL +1F3CD..1F3FA ; ID # So [46] RACING MOTORCYCLE..AMPHORA 1F400..1F441 ; ID # So [66] RAT..EYE 1F444..1F445 ; ID # So [2] MOUTH..TONGUE 1F451..1F465 ; ID # So [21] CROWN..BUSTS IN SILHOUETTE @@ -1601,7 +1622,7 @@ FFE4 ; ID # So FULLWIDTH BROKEN BAR 1F4B3..1F4FF ; ID # So [77] CREDIT CARD..PRAYER BEADS 1F507..1F516 ; ID # So [16] SPEAKER WITH CANCELLATION STROKE..BOOKMARK 1F525..1F531 ; ID # So [13] FIRE..TRIDENT EMBLEM -1F54A..1F574 ; ID # So [43] DOVE OF PEACE..MAN IN BUSINESS SUIT LEVITATING +1F54A..1F573 ; ID # So [42] DOVE OF PEACE..HOLE 1F576..1F579 ; ID # So [4] DARK SUNGLASSES..JOYSTICK 1F57B..1F58F ; ID # So [21] LEFT HAND TELEPHONE RECEIVER..TURNED OK HAND SIGN 1F591..1F594 ; ID # So [4] REVERSED RAISED HAND WITH FINGERS SPLAYED..REVERSED VICTORY HAND @@ -1612,35 +1633,38 @@ FFE4 ; ID # So FULLWIDTH BROKEN BAR 1F680..1F6A2 ; ID # So [35] ROCKET..SHIP 1F6A4..1F6B3 ; ID # So [16] SPEEDBOAT..NO BICYCLES 1F6B7..1F6BF ; ID # So [9] NO PEDESTRIANS..SHOWER -1F6C1..1F6D2 ; ID # So [18] BATHTUB..SHOPPING TROLLEY -1F6D3..1F6DF ; ID # Cn [13] <reserved-1F6D3>..<reserved-1F6DF> +1F6C1..1F6CB ; ID # So [11] BATHTUB..COUCH AND LAMP +1F6CD..1F6D4 ; ID # So [8] SHOPPING BAGS..PAGODA +1F6D5..1F6DF ; ID # Cn [11] <reserved-1F6D5>..<reserved-1F6DF> 1F6E0..1F6EC ; ID # So [13] HAMMER AND WRENCH..AIRPLANE ARRIVING 1F6ED..1F6EF ; ID # Cn [3] <reserved-1F6ED>..<reserved-1F6EF> -1F6F0..1F6F6 ; ID # So [7] SATELLITE..CANOE -1F6F7..1F6FF ; ID # Cn [9] <reserved-1F6F7>..<reserved-1F6FF> +1F6F0..1F6F8 ; ID # So [9] SATELLITE..FLYING SAUCER +1F6F9..1F6FF ; ID # Cn [7] <reserved-1F6F9>..<reserved-1F6FF> 1F774..1F77F ; ID # Cn [12] <reserved-1F774>..<reserved-1F77F> 1F7D5..1F7FF ; ID # Cn [43] <reserved-1F7D5>..<reserved-1F7FF> 1F80C..1F80F ; ID # Cn [4] <reserved-1F80C>..<reserved-1F80F> 1F848..1F84F ; ID # Cn [8] <reserved-1F848>..<reserved-1F84F> 1F85A..1F85F ; ID # Cn [6] <reserved-1F85A>..<reserved-1F85F> 1F888..1F88F ; ID # Cn [8] <reserved-1F888>..<reserved-1F88F> -1F8AE..1F90F ; ID # Cn [98] <reserved-1F8AE>..<reserved-1F90F> +1F8AE..1F8FF ; ID # Cn [82] <reserved-1F8AE>..<reserved-1F8FF> +1F90C..1F90F ; ID # Cn [4] <reserved-1F90C>..<reserved-1F90F> 1F910..1F917 ; ID # So [8] ZIPPER-MOUTH FACE..HUGGING FACE -1F91F ; ID # Cn <reserved-1F91F> +1F91D ; ID # So HANDSHAKE 1F920..1F925 ; ID # So [6] FACE WITH COWBOY HAT..LYING FACE -1F927 ; ID # So SNEEZING FACE -1F928..1F92F ; ID # Cn [8] <reserved-1F928>..<reserved-1F92F> -1F931..1F932 ; ID # Cn [2] <reserved-1F931>..<reserved-1F932> -1F93A..1F93B ; ID # So [2] FENCER..MODERN PENTATHLON +1F927..1F92F ; ID # So [9] SNEEZING FACE..SHOCKED FACE WITH EXPLODING HEAD +1F93A..1F93C ; ID # So [3] FENCER..WRESTLERS 1F93F ; ID # Cn <reserved-1F93F> -1F940..1F94B ; ID # So [12] WILTED FLOWER..MARTIAL ARTS UNIFORM -1F94C..1F94F ; ID # Cn [4] <reserved-1F94C>..<reserved-1F94F> -1F950..1F95E ; ID # So [15] CROISSANT..PANCAKES -1F95F..1F97F ; ID # Cn [33] <reserved-1F95F>..<reserved-1F97F> -1F980..1F991 ; ID # So [18] CRAB..SQUID -1F992..1F9BF ; ID # Cn [46] <reserved-1F992>..<reserved-1F9BF> +1F940..1F94C ; ID # So [13] WILTED FLOWER..CURLING STONE +1F94D..1F94F ; ID # Cn [3] <reserved-1F94D>..<reserved-1F94F> +1F950..1F96B ; ID # So [28] CROISSANT..CANNED FOOD +1F96C..1F97F ; ID # Cn [20] <reserved-1F96C>..<reserved-1F97F> +1F980..1F997 ; ID # So [24] CRAB..CRICKET +1F998..1F9BF ; ID # Cn [40] <reserved-1F998>..<reserved-1F9BF> 1F9C0 ; ID # So CHEESE WEDGE -1F9C1..1FFFD ; ID # Cn [1597] <reserved-1F9C1>..<reserved-1FFFD> +1F9C1..1F9CF ; ID # Cn [15] <reserved-1F9C1>..<reserved-1F9CF> +1F9D0 ; ID # So FACE WITH MONOCLE +1F9DE..1F9E6 ; ID # So [9] GENIE..SOCKS +1F9E7..1FFFD ; ID # Cn [1559] <reserved-1F9E7>..<reserved-1FFFD> 20000..2A6D6 ; ID # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6 2A6D7..2A6FF ; ID # Cn [41] <reserved-2A6D7>..<reserved-2A6FF> 2A700..2B734 ; ID # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 @@ -1648,12 +1672,14 @@ FFE4 ; ID # So FULLWIDTH BROKEN BAR 2B740..2B81D ; ID # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B81E..2B81F ; ID # Cn [2] <reserved-2B81E>..<reserved-2B81F> 2B820..2CEA1 ; ID # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 -2CEA2..2F7FF ; ID # Cn [10590] <reserved-2CEA2>..<reserved-2F7FF> +2CEA2..2CEAF ; ID # Cn [14] <reserved-2CEA2>..<reserved-2CEAF> +2CEB0..2EBE0 ; ID # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 +2EBE1..2F7FF ; ID # Cn [3103] <reserved-2EBE1>..<reserved-2F7FF> 2F800..2FA1D ; ID # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D 2FA1E..2FFFD ; ID # Cn [1504] <reserved-2FA1E>..<reserved-2FFFD> 30000..3FFFD ; ID # Cn [65534] <reserved-30000>..<reserved-3FFFD> -# Total code points: 172133 +# Total code points: 172784 # ================================================ @@ -1752,6 +1778,7 @@ FE19 ; IN # Po PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS 0ACB..0ACC ; CM # Mc [2] GUJARATI VOWEL SIGN O..GUJARATI VOWEL SIGN AU 0ACD ; CM # Mn GUJARATI SIGN VIRAMA 0AE2..0AE3 ; CM # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0AFA..0AFF ; CM # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE 0B01 ; CM # Mn ORIYA SIGN CANDRABINDU 0B02..0B03 ; CM # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA 0B3C ; CM # Mn ORIYA SIGN NUKTA @@ -1793,8 +1820,9 @@ FE19 ; IN # Po PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS 0CCC..0CCD ; CM # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA 0CD5..0CD6 ; CM # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK 0CE2..0CE3 ; CM # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL -0D01 ; CM # Mn MALAYALAM SIGN CANDRABINDU +0D00..0D01 ; CM # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU 0D02..0D03 ; CM # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA +0D3B..0D3C ; CM # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA 0D3E..0D40 ; CM # Mc [3] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN II 0D41..0D44 ; CM # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR 0D46..0D48 ; CM # Mc [3] MALAYALAM VOWEL SIGN E..MALAYALAM VOWEL SIGN AI @@ -1880,8 +1908,9 @@ FE19 ; IN # Po PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS 1CED ; CM # Mn VEDIC SIGN TIRYAK 1CF2..1CF3 ; CM # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA 1CF4 ; CM # Mn VEDIC TONE CANDRA ABOVE +1CF7 ; CM # Mc VEDIC SIGN ATIKRAMA 1CF8..1CF9 ; CM # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE -1DC0..1DF5 ; CM # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE +1DC0..1DF9 ; CM # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW 1DFB..1DFF ; CM # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 200C ; CM # Cf ZERO WIDTH NON-JOINER 200E..200F ; CM # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK @@ -2035,6 +2064,19 @@ FFF9..FFFB ; CM # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTAT 116B0..116B5 ; CM # Mn [6] TAKRI VOWEL SIGN U..TAKRI VOWEL SIGN AU 116B6 ; CM # Mc TAKRI SIGN VIRAMA 116B7 ; CM # Mn TAKRI SIGN NUKTA +11A01..11A06 ; CM # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O +11A07..11A08 ; CM # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU +11A09..11A0A ; CM # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A33..11A38 ; CM # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A39 ; CM # Mc ZANABAZAR SQUARE SIGN VISARGA +11A3B..11A3E ; CM # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A47 ; CM # Mn ZANABAZAR SQUARE SUBJOINER +11A51..11A56 ; CM # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A57..11A58 ; CM # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU +11A59..11A5B ; CM # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A8A..11A96 ; CM # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A97 ; CM # Mc SOYOMBO SIGN VISARGA +11A98..11A99 ; CM # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER 11C2F ; CM # Mc BHAIKSUKI VOWEL SIGN AA 11C30..11C36 ; CM # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L 11C38..11C3D ; CM # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA @@ -2047,6 +2089,11 @@ FFF9..FFFB ; CM # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTAT 11CB2..11CB3 ; CM # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E 11CB4 ; CM # Mc MARCHEN VOWEL SIGN O 11CB5..11CB6 ; CM # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D31..11D36 ; CM # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; CM # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; CM # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45 ; CM # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D47 ; CM # Mn MASARAM GONDI RA-KARA 16AF0..16AF4 ; CM # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; CM # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM 16F51..16F7E ; CM # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG @@ -2078,7 +2125,7 @@ E0001 ; CM # Cf LANGUAGE TAG E0020..E007F ; CM # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; CM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2090 +# Total code points: 2170 # ================================================ @@ -2102,9 +2149,12 @@ A8FC ; BB # Po DEVANAGARI SIGN SIDDHAM 111DB ; BB # Po SHARADA SIGN SIDDHAM 115C1 ; BB # Po SIDDHAM SIGN SIDDHAM 11660..1166C ; BB # Po [13] MONGOLIAN BIRGA WITH ORNAMENT..MONGOLIAN TURNED SWIRL BIRGA WITH DOUBLE ORNAMENT +11A3F ; BB # Po ZANABAZAR SQUARE INITIAL HEAD MARK +11A45 ; BB # Po ZANABAZAR SQUARE INITIAL DOUBLE-LINED HEAD MARK +11A9E..11AA0 ; BB # Po [3] SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME..SOYOMBO HEAD MARK WITH MOON AND SUN 11C70 ; BB # Po MARCHEN HEAD MARK -# Total code points: 37 +# Total code points: 42 # ================================================ @@ -2158,7 +2208,7 @@ A8FC ; BB # Po DEVANAGARI SIGN SIDDHAM 2E3C..2E3E ; BA # Po [3] STENOGRAPHIC FULL STOP..WIGGLY VERTICAL LINE 2E40 ; BA # Pd DOUBLE HYPHEN 2E41 ; BA # Po REVERSED COMMA -2E43..2E44 ; BA # Po [2] DASH WITH LEFT UPTURN..DOUBLE SUSPENSION MARK +2E43..2E49 ; BA # Po [7] DASH WITH LEFT UPTURN..DOUBLE STACKED COMMA 3000 ; BA # Zs IDEOGRAPHIC SPACE A4FE..A4FF ; BA # Po [2] LISU PUNCTUATION COMMA..LISU PUNCTUATION FULL STOP A60D ; BA # Po VAI COMMA @@ -2193,6 +2243,9 @@ ABEB ; BA # Po MEETEI MAYEK CHEIKHEI 115C9..115D7 ; BA # Po [15] SIDDHAM END OF TEXT MARK..SIDDHAM SECTION MARK WITH CIRCLES AND FOUR ENCLOSURES 11641..11642 ; BA # Po [2] MODI DANDA..MODI DOUBLE DANDA 1173C..1173E ; BA # Po [3] AHOM SIGN SMALL SECTION..AHOM SIGN RULAI +11A41..11A44 ; BA # Po [4] ZANABAZAR SQUARE MARK TSHEG..ZANABAZAR SQUARE MARK LONG TSHEG +11A9A..11A9C ; BA # Po [3] SOYOMBO MARK TSHEG..SOYOMBO MARK DOUBLE SHAD +11AA1..11AA2 ; BA # Po [2] SOYOMBO TERMINAL MARK-1..SOYOMBO TERMINAL MARK-2 11C41..11C45 ; BA # Po [5] BHAIKSUKI DANDA..BHAIKSUKI GAP FILLER-2 12470..12474 ; BA # Po [5] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON 16A6E..16A6F ; BA # Po [2] MRO DANDA..MRO DOUBLE DANDA @@ -2202,7 +2255,7 @@ ABEB ; BA # Po MEETEI MAYEK CHEIKHEI 1BC9F ; BA # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1DA87..1DA8A ; BA # Po [4] SIGNWRITING COMMA..SIGNWRITING COLON -# Total code points: 218 +# Total code points: 232 # ================================================ @@ -3462,8 +3515,9 @@ FF70 ; CJ # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK 26F9 ; EB # So PERSON WITH BALL 270A..270D ; EB # So [4] RAISED FIST..WRITING HAND 1F385 ; EB # So FATHER CHRISTMAS -1F3C3..1F3C4 ; EB # So [2] RUNNER..SURFER -1F3CA..1F3CB ; EB # So [2] SWIMMER..WEIGHT LIFTER +1F3C2..1F3C4 ; EB # So [3] SNOWBOARDER..SURFER +1F3C7 ; EB # So HORSE RACING +1F3CA..1F3CC ; EB # So [3] SWIMMER..GOLFER 1F442..1F443 ; EB # So [2] EAR..NOSE 1F446..1F450 ; EB # So [11] WHITE UP POINTING BACKHAND INDEX..OPEN HANDS SIGN 1F466..1F469 ; EB # So [4] BOY..WOMAN @@ -3473,7 +3527,7 @@ FF70 ; CJ # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK 1F481..1F483 ; EB # So [3] INFORMATION DESK PERSON..DANCER 1F485..1F487 ; EB # So [3] NAIL POLISH..HAIRCUT 1F4AA ; EB # So FLEXED BICEPS -1F575 ; EB # So SLEUTH OR SPY +1F574..1F575 ; EB # So [2] MAN IN BUSINESS SUIT LEVITATING..SLEUTH OR SPY 1F57A ; EB # So MAN DANCING 1F590 ; EB # So RAISED HAND WITH FINGERS SPLAYED 1F595..1F596 ; EB # So [2] REVERSED HAND WITH MIDDLE FINGER EXTENDED..RAISED HAND WITH PART BETWEEN MIDDLE AND RING FINGERS @@ -3482,13 +3536,15 @@ FF70 ; CJ # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK 1F6A3 ; EB # So ROWBOAT 1F6B4..1F6B6 ; EB # So [3] BICYCLIST..PEDESTRIAN 1F6C0 ; EB # So BATH -1F918..1F91E ; EB # So [7] SIGN OF THE HORNS..HAND WITH INDEX AND MIDDLE FINGERS CROSSED +1F6CC ; EB # So SLEEPING ACCOMMODATION +1F918..1F91C ; EB # So [5] SIGN OF THE HORNS..RIGHT-FACING FIST +1F91E..1F91F ; EB # So [2] HAND WITH INDEX AND MIDDLE FINGERS CROSSED..I LOVE YOU HAND SIGN 1F926 ; EB # So FACE PALM -1F930 ; EB # So PREGNANT WOMAN -1F933..1F939 ; EB # So [7] SELFIE..JUGGLING -1F93C..1F93E ; EB # So [3] WRESTLERS..HANDBALL +1F930..1F939 ; EB # So [10] PREGNANT WOMAN..JUGGLING +1F93D..1F93E ; EB # So [2] WATER POLO..HANDBALL +1F9D1..1F9DD ; EB # So [13] ADULT..ELF -# Total code points: 83 +# Total code points: 102 # ================================================ diff --git a/lib/unicore/extracted/DNumType.txt b/lib/unicore/extracted/DNumType.txt index bebcee6643..42dfba2bd7 100644 --- a/lib/unicore/extracted/DNumType.txt +++ b/lib/unicore/extracted/DNumType.txt @@ -1,6 +1,6 @@ -# DerivedNumericType-9.0.0.txt -# Date: 2016-03-02, 18:55:01 GMT -# © 2016 Unicode®, Inc. +# DerivedNumericType-10.0.0.txt +# Date: 2017-02-14, 04:26:10 GMT +# © 2017 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html # @@ -249,11 +249,12 @@ FF10..FF19 ; Decimal # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 11730..11739 ; Decimal # Nd [10] AHOM DIGIT ZERO..AHOM DIGIT NINE 118E0..118E9 ; Decimal # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE 11C50..11C59 ; Decimal # Nd [10] BHAIKSUKI DIGIT ZERO..BHAIKSUKI DIGIT NINE +11D50..11D59 ; Decimal # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE 16A60..16A69 ; Decimal # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE 16B50..16B59 ; Decimal # Nd [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE 1D7CE..1D7FF ; Decimal # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE 1E950..1E959 ; Decimal # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE -# Total code points: 580 +# Total code points: 590 # EOF diff --git a/lib/unicore/extracted/DNumValues.txt b/lib/unicore/extracted/DNumValues.txt index 8a4909f5ad..e8fffb3ba9 100644 --- a/lib/unicore/extracted/DNumValues.txt +++ b/lib/unicore/extracted/DNumValues.txt @@ -1,6 +1,6 @@ -# DerivedNumericValues-9.0.0.txt -# Date: 2016-03-02, 18:55:01 GMT -# © 2016 Unicode®, Inc. +# DerivedNumericValues-10.0.0.txt +# Date: 2017-02-14, 04:26:10 GMT +# © 2017 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html # @@ -101,6 +101,7 @@ FF10 ; 0.0 ; ; 0 # Nd FULLWIDTH DIGIT ZERO 11730 ; 0.0 ; ; 0 # Nd AHOM DIGIT ZERO 118E0 ; 0.0 ; ; 0 # Nd WARANG CITI DIGIT ZERO 11C50 ; 0.0 ; ; 0 # Nd BHAIKSUKI DIGIT ZERO +11D50 ; 0.0 ; ; 0 # Nd MASARAM GONDI DIGIT ZERO 16A60 ; 0.0 ; ; 0 # Nd MRO DIGIT ZERO 16B50 ; 0.0 ; ; 0 # Nd PAHAWH HMONG DIGIT ZERO 1D7CE ; 0.0 ; ; 0 # Nd MATHEMATICAL BOLD DIGIT ZERO @@ -112,7 +113,7 @@ FF10 ; 0.0 ; ; 0 # Nd FULLWIDTH DIGIT ZERO 1F100..1F101 ; 0.0 ; ; 0 # No [2] DIGIT ZERO FULL STOP..DIGIT ZERO COMMA 1F10B..1F10C ; 0.0 ; ; 0 # No [2] DINGBAT CIRCLED SANS-SERIF DIGIT ZERO..DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ZERO -# Total code points: 74 +# Total code points: 75 # ================================================ @@ -446,6 +447,7 @@ FF11 ; 1.0 ; ; 1 # Nd FULLWIDTH DIGIT ONE 118E1 ; 1.0 ; ; 1 # Nd WARANG CITI DIGIT ONE 11C51 ; 1.0 ; ; 1 # Nd BHAIKSUKI DIGIT ONE 11C5A ; 1.0 ; ; 1 # No BHAIKSUKI NUMBER ONE +11D51 ; 1.0 ; ; 1 # Nd MASARAM GONDI DIGIT ONE 12415 ; 1.0 ; ; 1 # Nl CUNEIFORM NUMERIC SIGN ONE GESH2 1241E ; 1.0 ; ; 1 # Nl CUNEIFORM NUMERIC SIGN ONE GESHU 1242C ; 1.0 ; ; 1 # Nl CUNEIFORM NUMERIC SIGN ONE SHARU @@ -465,7 +467,7 @@ FF11 ; 1.0 ; ; 1 # Nd FULLWIDTH DIGIT ONE 1F102 ; 1.0 ; ; 1 # No DIGIT ONE COMMA 2092A ; 1.0 ; ; 1 # Lo CJK UNIFIED IDEOGRAPH-2092A -# Total code points: 121 +# Total code points: 122 # ================================================ @@ -571,6 +573,7 @@ FF12 ; 2.0 ; ; 2 # Nd FULLWIDTH DIGIT TWO 118E2 ; 2.0 ; ; 2 # Nd WARANG CITI DIGIT TWO 11C52 ; 2.0 ; ; 2 # Nd BHAIKSUKI DIGIT TWO 11C5B ; 2.0 ; ; 2 # No BHAIKSUKI NUMBER TWO +11D52 ; 2.0 ; ; 2 # Nd MASARAM GONDI DIGIT TWO 12400 ; 2.0 ; ; 2 # Nl CUNEIFORM NUMERIC SIGN TWO ASH 12416 ; 2.0 ; ; 2 # Nl CUNEIFORM NUMERIC SIGN TWO GESH2 1241F ; 2.0 ; ; 2 # Nl CUNEIFORM NUMERIC SIGN TWO GESHU @@ -594,7 +597,7 @@ FF12 ; 2.0 ; ; 2 # Nd FULLWIDTH DIGIT TWO 1F103 ; 2.0 ; ; 2 # No DIGIT TWO COMMA 22390 ; 2.0 ; ; 2 # Lo CJK UNIFIED IDEOGRAPH-22390 -# Total code points: 121 +# Total code points: 122 # ================================================ @@ -694,6 +697,7 @@ FF13 ; 3.0 ; ; 3 # Nd FULLWIDTH DIGIT THREE 118E3 ; 3.0 ; ; 3 # Nd WARANG CITI DIGIT THREE 11C53 ; 3.0 ; ; 3 # Nd BHAIKSUKI DIGIT THREE 11C5C ; 3.0 ; ; 3 # No BHAIKSUKI NUMBER THREE +11D53 ; 3.0 ; ; 3 # Nd MASARAM GONDI DIGIT THREE 12401 ; 3.0 ; ; 3 # Nl CUNEIFORM NUMERIC SIGN THREE ASH 12408 ; 3.0 ; ; 3 # Nl CUNEIFORM NUMERIC SIGN THREE DISH 12417 ; 3.0 ; ; 3 # Nl CUNEIFORM NUMERIC SIGN THREE GESH2 @@ -721,7 +725,7 @@ FF13 ; 3.0 ; ; 3 # Nd FULLWIDTH DIGIT THREE 22998 ; 3.0 ; ; 3 # Lo CJK UNIFIED IDEOGRAPH-22998 23B1B ; 3.0 ; ; 3 # Lo CJK UNIFIED IDEOGRAPH-23B1B -# Total code points: 123 +# Total code points: 124 # ================================================ @@ -815,6 +819,7 @@ FF14 ; 4.0 ; ; 4 # Nd FULLWIDTH DIGIT FOUR 118E4 ; 4.0 ; ; 4 # Nd WARANG CITI DIGIT FOUR 11C54 ; 4.0 ; ; 4 # Nd BHAIKSUKI DIGIT FOUR 11C5D ; 4.0 ; ; 4 # No BHAIKSUKI NUMBER FOUR +11D54 ; 4.0 ; ; 4 # Nd MASARAM GONDI DIGIT FOUR 12402 ; 4.0 ; ; 4 # Nl CUNEIFORM NUMERIC SIGN FOUR ASH 12409 ; 4.0 ; ; 4 # Nl CUNEIFORM NUMERIC SIGN FOUR DISH 1240F ; 4.0 ; ; 4 # Nl CUNEIFORM NUMERIC SIGN FOUR U @@ -842,7 +847,7 @@ FF14 ; 4.0 ; ; 4 # Nd FULLWIDTH DIGIT FOUR 200E2 ; 4.0 ; ; 4 # Lo CJK UNIFIED IDEOGRAPH-200E2 2626D ; 4.0 ; ; 4 # Lo CJK UNIFIED IDEOGRAPH-2626D -# Total code points: 115 +# Total code points: 116 # ================================================ @@ -941,6 +946,7 @@ FF15 ; 5.0 ; ; 5 # Nd FULLWIDTH DIGIT FIVE 118E5 ; 5.0 ; ; 5 # Nd WARANG CITI DIGIT FIVE 11C55 ; 5.0 ; ; 5 # Nd BHAIKSUKI DIGIT FIVE 11C5E ; 5.0 ; ; 5 # No BHAIKSUKI NUMBER FIVE +11D55 ; 5.0 ; ; 5 # Nd MASARAM GONDI DIGIT FIVE 12403 ; 5.0 ; ; 5 # Nl CUNEIFORM NUMERIC SIGN FIVE ASH 1240A ; 5.0 ; ; 5 # Nl CUNEIFORM NUMERIC SIGN FIVE DISH 12410 ; 5.0 ; ; 5 # Nl CUNEIFORM NUMERIC SIGN FIVE U @@ -965,7 +971,7 @@ FF15 ; 5.0 ; ; 5 # Nd FULLWIDTH DIGIT FIVE 1F106 ; 5.0 ; ; 5 # No DIGIT FIVE COMMA 20121 ; 5.0 ; ; 5 # Lo CJK UNIFIED IDEOGRAPH-20121 -# Total code points: 113 +# Total code points: 114 # ================================================ @@ -1055,6 +1061,7 @@ FF16 ; 6.0 ; ; 6 # Nd FULLWIDTH DIGIT SIX 118E6 ; 6.0 ; ; 6 # Nd WARANG CITI DIGIT SIX 11C56 ; 6.0 ; ; 6 # Nd BHAIKSUKI DIGIT SIX 11C5F ; 6.0 ; ; 6 # No BHAIKSUKI NUMBER SIX +11D56 ; 6.0 ; ; 6 # Nd MASARAM GONDI DIGIT SIX 12404 ; 6.0 ; ; 6 # Nl CUNEIFORM NUMERIC SIGN SIX ASH 1240B ; 6.0 ; ; 6 # Nl CUNEIFORM NUMERIC SIGN SIX DISH 12411 ; 6.0 ; ; 6 # Nl CUNEIFORM NUMERIC SIGN SIX U @@ -1076,7 +1083,7 @@ FF16 ; 6.0 ; ; 6 # Nd FULLWIDTH DIGIT SIX 1F107 ; 6.0 ; ; 6 # No DIGIT SIX COMMA 20AEA ; 6.0 ; ; 6 # Lo CJK UNIFIED IDEOGRAPH-20AEA -# Total code points: 100 +# Total code points: 101 # ================================================ @@ -1164,6 +1171,7 @@ FF17 ; 7.0 ; ; 7 # Nd FULLWIDTH DIGIT SEVEN 118E7 ; 7.0 ; ; 7 # Nd WARANG CITI DIGIT SEVEN 11C57 ; 7.0 ; ; 7 # Nd BHAIKSUKI DIGIT SEVEN 11C60 ; 7.0 ; ; 7 # No BHAIKSUKI NUMBER SEVEN +11D57 ; 7.0 ; ; 7 # Nd MASARAM GONDI DIGIT SEVEN 12405 ; 7.0 ; ; 7 # Nl CUNEIFORM NUMERIC SIGN SEVEN ASH 1240C ; 7.0 ; ; 7 # Nl CUNEIFORM NUMERIC SIGN SEVEN DISH 12412 ; 7.0 ; ; 7 # Nl CUNEIFORM NUMERIC SIGN SEVEN U @@ -1184,7 +1192,7 @@ FF17 ; 7.0 ; ; 7 # Nd FULLWIDTH DIGIT SEVEN 1F108 ; 7.0 ; ; 7 # No DIGIT SEVEN COMMA 20001 ; 7.0 ; ; 7 # Lo CJK UNIFIED IDEOGRAPH-20001 -# Total code points: 99 +# Total code points: 100 # ================================================ @@ -1270,6 +1278,7 @@ FF18 ; 8.0 ; ; 8 # Nd FULLWIDTH DIGIT EIGHT 118E8 ; 8.0 ; ; 8 # Nd WARANG CITI DIGIT EIGHT 11C58 ; 8.0 ; ; 8 # Nd BHAIKSUKI DIGIT EIGHT 11C61 ; 8.0 ; ; 8 # No BHAIKSUKI NUMBER EIGHT +11D58 ; 8.0 ; ; 8 # Nd MASARAM GONDI DIGIT EIGHT 12406 ; 8.0 ; ; 8 # Nl CUNEIFORM NUMERIC SIGN EIGHT ASH 1240D ; 8.0 ; ; 8 # Nl CUNEIFORM NUMERIC SIGN EIGHT DISH 12413 ; 8.0 ; ; 8 # Nl CUNEIFORM NUMERIC SIGN EIGHT U @@ -1289,7 +1298,7 @@ FF18 ; 8.0 ; ; 8 # Nd FULLWIDTH DIGIT EIGHT 1E958 ; 8.0 ; ; 8 # Nd ADLAM DIGIT EIGHT 1F109 ; 8.0 ; ; 8 # No DIGIT EIGHT COMMA -# Total code points: 95 +# Total code points: 96 # ================================================ @@ -1376,6 +1385,7 @@ FF19 ; 9.0 ; ; 9 # Nd FULLWIDTH DIGIT NINE 118E9 ; 9.0 ; ; 9 # Nd WARANG CITI DIGIT NINE 11C59 ; 9.0 ; ; 9 # Nd BHAIKSUKI DIGIT NINE 11C62 ; 9.0 ; ; 9 # No BHAIKSUKI NUMBER NINE +11D59 ; 9.0 ; ; 9 # Nd MASARAM GONDI DIGIT NINE 12407 ; 9.0 ; ; 9 # Nl CUNEIFORM NUMERIC SIGN NINE ASH 1240E ; 9.0 ; ; 9 # Nl CUNEIFORM NUMERIC SIGN NINE DISH 12414 ; 9.0 ; ; 9 # Nl CUNEIFORM NUMERIC SIGN NINE U @@ -1396,7 +1406,7 @@ FF19 ; 9.0 ; ; 9 # Nd FULLWIDTH DIGIT NINE 1F10A ; 9.0 ; ; 9 # No DIGIT NINE COMMA 2F890 ; 9.0 ; ; 9 # Lo CJK COMPATIBILITY IDEOGRAPH-2F890 -# Total code points: 99 +# Total code points: 100 # ================================================ diff --git a/lib/unicore/version b/lib/unicore/version index f7ee06693c..a13e7b9c87 100644 --- a/lib/unicore/version +++ b/lib/unicore/version @@ -1 +1 @@ -9.0.0 +10.0.0 diff --git a/regcharclass.h b/regcharclass.h index 3ae0fc7166..17812c56b6 100644 --- a/regcharclass.h +++ b/regcharclass.h @@ -1855,50 +1855,51 @@ /* Generated from: * 59e717586b720a821ee0d7397679d5322e38b49f6fb7840545aedf669c733b70 lib/Unicode/UCD.pm - * 47cb62a53beea6d0263e2147331c7e751853c9327225d95bbe2d9e1dc3e1aa44 lib/unicore/ArabicShaping.txt - * 153f0a100c315f9f3945e78f57137611d36c44b3a975919c499fd403413fede8 lib/unicore/BidiBrackets.txt - * fbe806975c1bf9fc9960bbaa39ff6290c42c7da8315f9cd459109b024cc1c485 lib/unicore/BidiMirroring.txt - * 612127d4889032e55d82522e4a0c19793bda8aa8da14ecb3c696d17c83e6be13 lib/unicore/Blocks.txt - * 37d40cf8c2c35637f4a04e746814e1fc4eb764c272bed9238a87ee96a4866857 lib/unicore/CaseFolding.txt - * 5623df16856ad4007c60bdfff6f054e087521becd24cb4006be69c3a1d851aee lib/unicore/CompositionExclusions.txt - * 5cb15b04693c43df16e0d304deca049e93b001445d163184e0ff1b7c8c852146 lib/unicore/DAge.txt - * 6662c7e30b572df5d948c092692f52bcc79ab36d49a063a73d6435042db6fb3b lib/unicore/DCoreProperties.txt - * 02d8e12cea7c61a9f3cc5fbf8eaceadf8da23fe83d60c64cf647088830b810cc lib/unicore/DNormalizationProps.txt - * 3382cb4980e0021e9d4312f2d099315cfab6100ce0ff63a22d6937bfa720bcb7 lib/unicore/EastAsianWidth.txt - * cb02ff25c375e78c82afffc852180eae7fc17c2f4434e697107720d05c52b26e lib/unicore/HangulSyllableType.txt - * 850043bc9db08eddb271e43ed9176b865df76745a5fb6e9a4a1d9e54e5036471 lib/unicore/IndicPositionalCategory.txt - * 90a3a00a5f5810850986c9279849b03c2f3133cfeeefb0554e851dd5ad7324dc lib/unicore/IndicSyllabicCategory.txt - * bbd36a8d27f76e0fe0f2b0ca2827ac80da4b4a8d5247f0b0670fcaaac68ae6e1 lib/unicore/Jamo.txt - * e2698584982ccd96e0c688bbcd4d2c48a23805baa0a0084388ef2e50ebd30aad lib/unicore/LineBreak.txt - * 9d5353b1d318e72a63a49aa6a6a051d350382ea44b2cf31fe925bb94ce7e129b lib/unicore/NameAliases.txt - * 009477f536f63016d901aeb1a4c820ad291e30e72ee9eb9ac1dfb6294a8a9bcc lib/unicore/NamedSequences.txt - * f413ea8dbd3858de72f3148b47dd0586019761357d1481e3b65f3a025bc27f82 lib/unicore/PropList.txt - * 56582d9875c1997876cf09305ccfc83448195de5d84d6374c78efaffeca4dfd7 lib/unicore/PropValueAliases.txt - * 047ab0f815b6d1b30a863d6fcbd49e6358e168a3bd6c7189e80ab9863957d222 lib/unicore/PropertyAliases.txt - * cde011921972dffe3e30dcbc7afbf069bf2eb01269097111dd7533b4c524caac lib/unicore/ScriptExtensions.txt - * fba415952f5654145acad220dc2b878f815c673474d2bb4928934e3ba6ccca1d lib/unicore/Scripts.txt - * dfc4f159c5c68328114ff17cd520451714a72ff48657287e5fe2f64344980695 lib/unicore/SpecialCasing.txt - * 68dfc414d28257b9b5d6ddbb8b466c768c00ebdf6cbf7784364a9b6cad55ee8f lib/unicore/UnicodeData.txt - * c76e7ed44a602f85161758ec54d2bcbcb7baf38f97720605a3e81ce02af47061 lib/unicore/auxiliary/GCBTest.txt - * 4bb8931857e0a698fd2ec4a51a84c6de33e48a50d8b4bf0b57d960c41d77a191 lib/unicore/auxiliary/GraphemeBreakProperty.txt - * 0c609ae4a32a89905c004010ef29885df3c60a941311a1a6e16003333d7fcdc8 lib/unicore/auxiliary/LBTest.txt - * 26afdd5f38561167807b0f191af55b05761029ae6be2b7fe85b88f28effc66b5 lib/unicore/auxiliary/SBTest.txt - * 53982766eeaf26674e7e2ec956c52846d52992ea9f4f1a202d488fb5cd76dd10 lib/unicore/auxiliary/SentenceBreakProperty.txt - * 7f60beacc5ec5671edb56db36defc90cfc0016de4fd2bdfde7a3e4ec209840ce lib/unicore/auxiliary/WBTest.txt - * cb2db065c77287e0f1d35b8c9b473d848b7566a1670439f67c357ca393084043 lib/unicore/auxiliary/WordBreakProperty.txt - * 73573a4bee7f7377d936bc1710cd578001d00ba516e72ee54e906ae51a8c1fcb lib/unicore/extracted/DBidiClass.txt - * ae8f55d8bb2bb69a63f70eef38cf5921fc3ba8e06d4d88f37950d32313a14754 lib/unicore/extracted/DBinaryProperties.txt - * cf263ac4848d47264300139f97ed15c2c22896d2cef411483cbe292098c08bea lib/unicore/extracted/DCombiningClass.txt - * 5bac89caf8d1fa23fcbbbf4d49ea0699b680ef1a73cbfa0daaac38c993906a74 lib/unicore/extracted/DDecompositionType.txt - * e17138d36cd91f0e0d16437780a887c5ac637bde0de370b96f08a3424fcc322f lib/unicore/extracted/DEastAsianWidth.txt - * fad25c183f4d439622c6be33c22ed709cdc4ac19feef0250527cf319a06952fe lib/unicore/extracted/DGeneralCategory.txt - * c0d080b188fbe67dead10a3897dd2ca23da862c7f0b03508a92dcf27cd7e1f41 lib/unicore/extracted/DJoinGroup.txt - * 3a8f8642084ed23b0de52af72dea0ff3d0b6928e6c7442832c663899e2b85e9d lib/unicore/extracted/DJoinType.txt - * 37f6186253da9824bdb27f4ad867bfe8c25d4dc6bdb2f05585e40a034675a348 lib/unicore/extracted/DLineBreak.txt - * ef24061b5a5dc93d7e90c2e34530ec757180ee75d872cba65ffc946e52624ae8 lib/unicore/extracted/DNumType.txt - * a197371fec9a1b517058b440841f60f9378d81682084eef8db22a88cb2f96e90 lib/unicore/extracted/DNumValues.txt + * ff4404ec64f308bdf7714c50f9fdf0d1d0bf3c34db4d0a67e58ef0c6f88e818f lib/unicore/ArabicShaping.txt + * 292171a0a1c13d7e581e8781eb4cdf248243b1ab267354a63c7a14429dea2740 lib/unicore/BidiBrackets.txt + * 8f2695cc42989a79a715ab0d2892bd0c998759180cfdfb998674447f48231940 lib/unicore/BidiMirroring.txt + * 5ae1649a42ed8ae8cb885af79563f00a9ae17e602405a56ed8aca214da14eea7 lib/unicore/Blocks.txt + * 97b43ed3f4b80572c2114200e5e43a6b923d984c74a6caaf27de5b8462c04cb0 lib/unicore/CaseFolding.txt + * eedcf6932b4081ee65878454588c803af910a5aed7c8c67e3c38701cbee9b9e4 lib/unicore/CompositionExclusions.txt + * 90e48995643f45b08f0ef67fb90de3bb18e26765272bcc0c35c840cbc10b37c1 lib/unicore/DAge.txt + * e6ca152259189ec4bc2297e93c6c88f86e162cc52814198263497f3c9b46cbe9 lib/unicore/DCoreProperties.txt + * 3e255ccdff4b00cfe0be53bbd583e4fe2e7d4039138579543548a5ecfce45242 lib/unicore/DNormalizationProps.txt + * 9f34e2d3ea27ca82f4f14b62411861d1f07c4b9e296d54da112a09cad5b9a48d lib/unicore/EastAsianWidth.txt + * 983810c739b56b9ff0fcb5db018c67d584ee515e8a5f4d9348c79ee85167ec37 lib/unicore/HangulSyllableType.txt + * 7d514a779ee4baf91262bd83c400cb502c3e435dba4b880c876506be32b8e1d0 lib/unicore/IndicPositionalCategory.txt + * f6acead8f84df5c72f3fb70dfc9375279926e4d8ef3480ffff3723095e9804aa lib/unicore/IndicSyllabicCategory.txt + * c8ed526f70443535ca6b705980a08c774017ff17e921202dcb7b71ae554047b6 lib/unicore/Jamo.txt + * 6b204c3727b77699d04a574b22b1e44facab038642095b8565b49762970d9bf8 lib/unicore/LineBreak.txt + * f2357d2bd3526b9e830de72ab038dcfc65a2dff24bcb4c6325c92071eb341f88 lib/unicore/NameAliases.txt + * 6c3e6bd1e58b640076a23b83318a8bf6a691d7fc2b2106114d77c5c5a898bced lib/unicore/NamedSequences.txt + * 58dbf8fedbd5bf67a3bd5c10eda2f2acf2eae59df5f77884a6f158e98f75cf8c lib/unicore/PropList.txt + * a6b0467c3cc7aa4e57d4e5cc7f6e9562b79cf4426dfe438517c28b368ed3e673 lib/unicore/PropValueAliases.txt + * 9ca521224e08d30696516ae6bc3d4434659c45df16047c0d31e440783c163a3b lib/unicore/PropertyAliases.txt + * 3fd0d744a816ddfd06809f92151ae4a73ec970ac2006806c269732d8951f3911 lib/unicore/ScriptExtensions.txt + * d02e24e4c516e9090b6bc9c2d2c8f4c89510b6ed8c5e859d0a861b0dc5cf372d lib/unicore/Scripts.txt + * e9947a0e86f27353f0e776403c4826675001210bd39d7114118a8864a57f7472 lib/unicore/SpecialCasing.txt + * 52423e4d7492167b62f518f68d54db88930abbbff7f11edfcaec8f726498cab1 lib/unicore/UnicodeData.txt + * f28caf260635cebf25fd58124bdc9aa22af08ba4d039ffc584365fb41a31cda5 lib/unicore/VerticalOrientation.txt + * 718d174957712410bfad782b10d557e1047574d7ef1642d6bb122f8ca5662c82 lib/unicore/auxiliary/GCBTest.txt + * 3b66caefc4fa877d0e50dbbbfa39658c86e29b26c6f206f68d7aec192d4c59b6 lib/unicore/auxiliary/GraphemeBreakProperty.txt + * 2aad3836c37fc4c2fa2a24f21586fb3a931dacaf0a1c845a6dc6395f30bd79a7 lib/unicore/auxiliary/LBTest.txt + * eacc03e39dddc60cc59ec9bd274b8ac8dfa25d61745ef0d5c8aa1c151a5b68ba lib/unicore/auxiliary/SBTest.txt + * e45fa8195bb413b901cc1e3772dfea2cead86805d46a51e3480a5a256e8c24d9 lib/unicore/auxiliary/SentenceBreakProperty.txt + * 95789f62e3b1e781dc9ed78f3983d39ff1a5e36ff0b497d6e610446df902b0f6 lib/unicore/auxiliary/WBTest.txt + * c207e8ebd06ee591a27b1087f2971f4cd93e960103c453d85d1d9ba26fb8b202 lib/unicore/auxiliary/WordBreakProperty.txt + * a3c0839826a30166b2bb06ba58df403547b8c3d9eae995ef889d20d115f4b223 lib/unicore/extracted/DBidiClass.txt + * 280afe22f6c4d56566d17d6d1400f33465a979c96f3d99ff3bff9bd14d17e734 lib/unicore/extracted/DBinaryProperties.txt + * db7fd6a5e6f068c47dbc3b74fb633fb1d09d17073410fe435295d05ce925c5f6 lib/unicore/extracted/DCombiningClass.txt + * 8204c07a7c217bdf22525030ad7b4fb991edf463bffcca7e6dba46b9992e0d99 lib/unicore/extracted/DDecompositionType.txt + * e343113719b660bdd81217ec101ce751f844fca0e8d6f15fb21c8ee7dfe7c14c lib/unicore/extracted/DEastAsianWidth.txt + * 07c55b0ed7271fe1a5f4d68059291288b1a8ad61940602d18956fd87390c2d9e lib/unicore/extracted/DGeneralCategory.txt + * d788b9362ec7681e98f8b9d6ef276546e1a6207dda05317ede55bd686b0940a9 lib/unicore/extracted/DJoinGroup.txt + * ebbea3c93eeb7431378885aebac0490d77f6900239c9176f90b6fee030903d96 lib/unicore/extracted/DJoinType.txt + * be0f129691d479aa38646e4ca0ec1ee576ae7f75b0300a5624a7fa862fa8abba lib/unicore/extracted/DLineBreak.txt + * 92449d354d9f6b6f2f97a292ebb59f6344ffdeb83d120d7d23e569c43ba67cd5 lib/unicore/extracted/DNumType.txt + * e3a319527153b0c6c0c549b40fc6f3a01a7a0dcd6620784391db25901df3b154 lib/unicore/extracted/DNumValues.txt * fd5dda65f76b9209787c5d0bb99f4cde8708c0bf86bcefe344d2d474a0306e28 lib/unicore/mktables - * cdecb300baad839a6f62791229f551a4fa33f3cbdca08e378dc976466354e778 lib/unicore/version + * 21653d2744fdd071f9ef138c805393901bb9547cf3e777ebf50215a191f986ea lib/unicore/version * 913d2f93f3cb6cdf1664db888bf840bc4eb074eef824e082fceda24a9445e60c regen/charset_translations.pl * 9ea6338945a7d70e5ea4b31ac7856c0b521df96be002e94b4b3b7d31debbf3ab regen/regcharclass.pl * 393f8d882713a3ba227351ad0f00ea4839fda74fcf77dcd1cdf31519925adba5 regen/regcharclass_multi_char_folds.pl diff --git a/unicode_constants.h b/unicode_constants.h index 318b9015ae..0bd08139aa 100644 --- a/unicode_constants.h +++ b/unicode_constants.h @@ -45,7 +45,7 @@ bytes. =cut */ -#define UNICODE_MAJOR_VERSION 9 +#define UNICODE_MAJOR_VERSION 10 #define UNICODE_DOT_VERSION 0 #define UNICODE_DOT_DOT_VERSION 0 @@ -177,7 +177,7 @@ bytes. #endif /* EBCDIC 037 */ /* The number of code points not matching \pC */ -#define NON_OTHER_COUNT_FOR_USE_ONLY_BY_REGCOMP_DOT_C 128021 +#define NON_OTHER_COUNT_FOR_USE_ONLY_BY_REGCOMP_DOT_C 136539 /* The highest code point that has any type of case change */ #define HIGHEST_CASE_CHANGING_CP_FOR_USE_ONLY_BY_UTF8_DOT_C 0x1E943 |