diff options
author | Jarkko Hietaniemi <jhi@iki.fi> | 2001-03-08 01:06:13 +0000 |
---|---|---|
committer | Jarkko Hietaniemi <jhi@iki.fi> | 2001-03-08 01:06:13 +0000 |
commit | 50fc42481ed636dd7d07a6d83c1edcbf9d141c4d (patch) | |
tree | 83fb0006f34aeee481645e42e4e6f7441ea8434b /lib | |
parent | a8a2fe91fa45a0af1643d661bc54b66f4ad81bf5 (diff) | |
download | perl-50fc42481ed636dd7d07a6d83c1edcbf9d141c4d.tar.gz |
Upgrade to Unicode 3.1 beta 2001-03-01.
p4raw-id: //depot/perl@9077
Diffstat (limited to 'lib')
46 files changed, 2393 insertions, 541 deletions
diff --git a/lib/unicode/Category.pl b/lib/unicode/Category.pl index bafb18b0e2..8c13cc347e 100644 --- a/lib/unicode/Category.pl +++ b/lib/unicode/Category.pl @@ -1569,15 +1569,30 @@ fffc fffd So 1d670 1d689 Lu 1d68a 1d6a3 Ll 1d6a8 1d6c0 Lu -1d6c1 1d6e1 Ll +1d6c1 Sm +1d6c2 1d6da Ll +1d6db Sm +1d6dc 1d6e1 Ll 1d6e2 1d6fa Lu -1d6fb 1d71b Ll +1d6fb Sm +1d6fc 1d714 Ll +1d715 Sm +1d716 1d71b Ll 1d71c 1d734 Lu -1d735 1d755 Ll +1d735 Sm +1d736 1d74e Ll +1d74f Sm +1d750 1d755 Ll 1d756 1d76e Lu -1d76f 1d78f Ll +1d76f Sm +1d770 1d788 Ll +1d789 Sm +1d78a 1d78f Ll 1d790 1d7a8 Lu -1d7a9 1d7c9 Ll +1d7a9 Sm +1d7aa 1d7c2 Ll +1d7c3 Sm +1d7c4 1d7c9 Ll 1d7ce 1d7ff Nd 20000 2a6d6 Lo 2f800 2fa1d Lo diff --git a/lib/unicode/Decomposition.pl b/lib/unicode/Decomposition.pl index 06686559aa..d061809ed9 100644 --- a/lib/unicode/Decomposition.pl +++ b/lib/unicode/Decomposition.pl @@ -3478,10 +3478,10 @@ ffee <narrow> 25CB 1d164 1D15F 1D172 1d1bb 1D1B9 1D165 1d1bc 1D1BA 1D165 -1d1bd 1D1B9 1D165 1D16E -1d1be 1D1BA 1D165 1D16E -1d1bf 1D1B9 1D165 1D16F -1d1c0 1D1BA 1D165 1D16F +1d1bd 1D1BB 1D16E +1d1be 1D1BC 1D16E +1d1bf 1D1BB 1D16F +1d1c0 1D1BC 1D16F 1d400 <font> 0041 1d401 <font> 0042 1d402 <font> 0043 diff --git a/lib/unicode/EAWidth.txt b/lib/unicode/EAWidth.txt index 16960f13bb..e11f544efb 100644 --- a/lib/unicode/EAWidth.txt +++ b/lib/unicode/EAWidth.txt @@ -9,11 +9,8 @@ # Field 2: East Asian Width property, consisting of one of the following values: # "N", "A", "H", "W", "F", "Na" # - Assigned characters that are not listed explicitly are given the value "N". -# - Characters within ranges marked by "First>" and "Last>" are omitted, -# as in UnicodeData.txt. For example, the following means that -# all characters between 3400 and 4DB5 have the value "W" -# 3400;W;<CJK Ideograph Extension A, First> -# 4DB5;W;<CJK Ideograph Extension A, Last> +# - Characters ranges are specified as for other property files in +# the Unicode Character Database. # # The Unicode name of each character is provided in a comment for help # in identifying the characters. @@ -7180,12 +7177,12 @@ 3011;W # RIGHT BLACK LENTICULAR BRACKET 3012;W # POSTAL MARK 3013;W # GETA MARK -3014;W # LEFT TORTOISE SHELL BRACKET -3015;W # RIGHT TORTOISE SHELL BRACKET +3014;A # LEFT TORTOISE SHELL BRACKET +3015;A # RIGHT TORTOISE SHELL BRACKET 3016;W # LEFT WHITE LENTICULAR BRACKET 3017;W # RIGHT WHITE LENTICULAR BRACKET -3018;W # LEFT WHITE TORTOISE SHELL BRACKET -3019;W # RIGHT WHITE TORTOISE SHELL BRACKET +3018;A # LEFT WHITE TORTOISE SHELL BRACKET +3019;A # RIGHT WHITE TORTOISE SHELL BRACKET 301A;A # LEFT WHITE SQUARE BRACKET 301B;A # RIGHT WHITE SQUARE BRACKET 301C;W # WAVE DASH @@ -8030,10 +8027,8 @@ 33FC;W # IDEOGRAPHIC TELEGRAPH SYMBOL FOR DAY TWENTY-NINE 33FD;W # IDEOGRAPHIC TELEGRAPH SYMBOL FOR DAY THIRTY 33FE;W # IDEOGRAPHIC TELEGRAPH SYMBOL FOR DAY THIRTY-ONE -3400;W # <CJK Ideograph Extension A, First> -4DB5;W # <CJK Ideograph Extension A, Last> -4E00;W # <CJK Ideograph, First> -9FA5;W # <CJK Ideograph, Last> +3400..4DB5;W # <CJK Ideograph Extension A, First>..<CJK Ideograph Extension A, Last> +4E00..9FA5;W # <CJK Ideograph, First>..<CJK Ideograph, Last> A000;W # YI SYLLABLE IT A001;W # YI SYLLABLE IX A002;W # YI SYLLABLE I @@ -9249,16 +9244,11 @@ A4C2;W # YI RADICAL SHOP A4C3;W # YI RADICAL CHE A4C4;W # YI RADICAL ZZIET A4C6;W # YI RADICAL KE -AC00;W # <Hangul Syllable, First> -D7A3;W # <Hangul Syllable, Last> -D800;N # <Non Private Use High Surrogate, First> -DB7F;N # <Non Private Use High Surrogate, Last> -DB80;N # <Private Use High Surrogate, First> -DBFF;N # <Private Use High Surrogate, Last> -DC00;N # <Low Surrogate, First> -DFFF;N # <Low Surrogate, Last> -E000;A # <Private Use, First> -F8FF;A # <Private Use, Last> +AC00..D7A3;W # <Hangul Syllable, First>..<Hangul Syllable, Last> +D800..DB7F;N # <Non Private Use High Surrogate, First>..<Non Private Use High Surrogate, Last> +DB80..DBFF;N # <Private Use High Surrogate, First>..<Private Use High Surrogate, Last> +DC00..DFFF;N # <Low Surrogate, First>..<Low Surrogate, Last> +E000..F8FF;A # <Private Use, First>..<Private Use, Last> F900;W # CJK COMPATIBILITY IDEOGRAPH-F900 F901;W # CJK COMPATIBILITY IDEOGRAPH-F901 F902;W # CJK COMPATIBILITY IDEOGRAPH-F902 @@ -12232,8 +12222,7 @@ FFFD;A # REPLACEMENT CHARACTER 1D7FD;N # MATHEMATICAL MONOSPACE DIGIT SEVEN 1D7FE;N # MATHEMATICAL MONOSPACE DIGIT EIGHT 1D7FF;N # MATHEMATICAL MONOSPACE DIGIT NINE -20000;W # <CJK Ideograph Extension B, First> -2A6D6;W # <CJK Ideograph Extension B, Last> +20000..2A6D6;W # <CJK Ideograph Extension B, First>..<CJK Ideograph Extension B, Last> 2F800;W # CJK COMPATIBILITY IDEOGRAPH-2F800 2F801;W # CJK COMPATIBILITY IDEOGRAPH-2F801 2F802;W # CJK COMPATIBILITY IDEOGRAPH-2F802 @@ -12873,3 +12862,5 @@ E007C;N # TAG VERTICAL LINE E007D;N # TAG RIGHT CURLY BRACKET E007E;N # TAG TILDE E007F;N # CANCEL TAG +F0000..FFFFD;A # <Plane 15 Private Use, First>..<Plane 15 Private Use, Last> +100000..10FFFD;A # <Plane 16 Private Use, First>..<Plane 16 Private Use, Last> diff --git a/lib/unicode/Is/Alnum.pl b/lib/unicode/Is/Alnum.pl index 907d7f85b1..6b09b9c2ce 100644 --- a/lib/unicode/Is/Alnum.pl +++ b/lib/unicode/Is/Alnum.pl @@ -385,7 +385,17 @@ ffda ffdc 1d546 1d54a 1d550 1d552 1d6a3 -1d6a8 1d7c9 +1d6a8 1d6c0 +1d6c2 1d6da +1d6dc 1d6fa +1d6fc 1d714 +1d716 1d734 +1d736 1d74e +1d750 1d76e +1d770 1d788 +1d78a 1d7a8 +1d7aa 1d7c2 +1d7c4 1d7c9 1d7ce 1d7ff 20000 2a6d6 2f800 2fa1d diff --git a/lib/unicode/Is/Alpha.pl b/lib/unicode/Is/Alpha.pl index 4aac73ae8b..2b0676da4a 100644 --- a/lib/unicode/Is/Alpha.pl +++ b/lib/unicode/Is/Alpha.pl @@ -353,7 +353,17 @@ ffda ffdc 1d546 1d54a 1d550 1d552 1d6a3 -1d6a8 1d7c9 +1d6a8 1d6c0 +1d6c2 1d6da +1d6dc 1d6fa +1d6fc 1d714 +1d716 1d734 +1d736 1d74e +1d750 1d76e +1d770 1d788 +1d78a 1d7a8 +1d7aa 1d7c2 +1d7c4 1d7c9 20000 2a6d6 2f800 2fa1d END diff --git a/lib/unicode/Is/L.pl b/lib/unicode/Is/L.pl index 59c2baad4b..62d12e04aa 100644 --- a/lib/unicode/Is/L.pl +++ b/lib/unicode/Is/L.pl @@ -281,7 +281,17 @@ ffda ffdc 1d546 1d54a 1d550 1d552 1d6a3 -1d6a8 1d7c9 +1d6a8 1d6c0 +1d6c2 1d6da +1d6dc 1d6fa +1d6fc 1d714 +1d716 1d734 +1d736 1d74e +1d750 1d76e +1d770 1d788 +1d78a 1d7a8 +1d7aa 1d7c2 +1d7c4 1d7c9 20000 2a6d6 2f800 2fa1d END diff --git a/lib/unicode/Is/LbrkAI.pl b/lib/unicode/Is/LbrkAI.pl index 272f63fc9f..325c0a0b19 100644 --- a/lib/unicode/Is/LbrkAI.pl +++ b/lib/unicode/Is/LbrkAI.pl @@ -2,4 +2,138 @@ # This file is built by mktables.PL from e.g. Unicode.txt. # Any changes made here will be lost! return <<'END'; +00a1 +00a7 00a8 +00aa +00b2 00b3 +00b6 00ba +00bc 00bf +00c6 +00d0 +00d7 00d8 +00de 00e1 +00e6 +00e8 00ea +00ec 00ed +00f0 +00f2 00f3 +00f7 00fa +00fc +00fe +0101 +0111 +0113 +011b +0126 0127 +012b +0131 0133 +0138 +013f 0142 +0144 +0148 014a +014d +0152 0153 +0166 0167 +016b +01ce +01d0 +01d2 +01d4 +01d6 +01d8 +01da +01dc +0251 +0261 +02c7 +02c9 02cb +02cd +02d0 +02d8 02db +02dd +0391 03a1 +03a3 03a9 +03b1 03c1 +03c3 03c9 +0401 +0410 044f +0451 +2016 +2020 2021 +203b +2074 +207f +2081 2084 +2105 +2113 +2121 2122 +212b +2154 2155 +215b +215e +2160 216b +2170 2179 +2190 2199 +21d2 +21d4 +2200 +2202 2203 +2207 2208 +220b +220f +2211 +2215 +221a +221d 2220 +2223 +2225 +2227 222c +222e +2234 2237 +223c 223d +2248 +224c +2252 +2260 2261 +2264 2267 +226a 226b +226e 226f +2282 2283 +2286 2287 +2295 +2299 +22a5 +22bf +2312 +2460 24bf +24d0 24e9 +2500 254b +2550 2574 +2580 258f +2592 2595 +25a0 25a1 +25a3 25a9 +25b2 25b3 +25b6 25b7 +25bc 25bd +25c0 25c1 +25c6 25c7 +25cb +25ce 25d1 +25e2 25e5 +25ef +2605 2606 +2609 +260e 260f +261c +261e +2640 +2642 +2660 2661 +2663 2665 +2667 266a +266c 266d +266f +e000 f8ff +fffd END diff --git a/lib/unicode/Is/LbrkAL.pl b/lib/unicode/Is/LbrkAL.pl index 272f63fc9f..61938d7cdc 100644 --- a/lib/unicode/Is/LbrkAL.pl +++ b/lib/unicode/Is/LbrkAL.pl @@ -2,4 +2,419 @@ # This file is built by mktables.PL from e.g. Unicode.txt. # Any changes made here will be lost! return <<'END'; +0023 +0026 +002a +003c 003e +0040 005a +005e 007a +007e +00a6 +00a9 +00ac +00ae 00af +00b5 +00c0 00c5 +00c7 00cf +00d1 00d6 +00d9 00dd +00e2 00e5 +00e7 +00eb +00ee 00ef +00f1 +00f4 00f6 +00fb +00fd +00ff 0100 +0102 0110 +0112 +0114 011a +011c 0125 +0128 012a +012c 0130 +0134 0137 +0139 013e +0143 +0145 0147 +014b 014c +014e 0151 +0154 0165 +0168 016a +016c 01cd +01cf +01d1 +01d3 +01d5 +01d7 +01d9 +01db +01dd 021f +0222 0233 +0250 +0252 0260 +0262 02ad +02b0 02c6 +02ce 02cf +02d1 02d7 +02dc +02de 02ee +0374 0375 +037a +037e +0384 038a +038c +038e 0390 +03aa 03b0 +03c2 +03ca 03ce +03d0 03d7 +03da 03f5 +0400 +0402 040f +0450 +0452 0482 +048c 04c4 +04c7 04c8 +04cb 04cc +04d0 04f5 +04f8 04f9 +0531 0556 +0559 055f +0561 0587 +05be +05c0 +05c3 +05d0 05ea +05f0 05f4 +060c +061b +061f +0621 063a +0640 064a +066a 066d +0671 06d5 +06e5 06e6 +06e9 +06fa 06fe +0700 070d +0710 +0712 072c +0780 07a5 +0905 0939 +093d +0950 +0958 0961 +0964 0965 +0970 +0985 098c +098f 0990 +0993 09a8 +09aa 09b0 +09b2 +09b6 09b9 +09dc 09dd +09df 09e1 +09f0 09f1 +09f4 09fa +0a05 0a0a +0a0f 0a10 +0a13 0a28 +0a2a 0a30 +0a32 0a33 +0a35 0a36 +0a38 0a39 +0a59 0a5c +0a5e +0a72 0a74 +0a85 0a8b +0a8d +0a8f 0a91 +0a93 0aa8 +0aaa 0ab0 +0ab2 0ab3 +0ab5 0ab9 +0abd +0ad0 +0ae0 +0b05 0b0c +0b0f 0b10 +0b13 0b28 +0b2a 0b30 +0b32 0b33 +0b36 0b39 +0b3d +0b5c 0b5d +0b5f 0b61 +0b70 +0b85 0b8a +0b8e 0b90 +0b92 0b95 +0b99 0b9a +0b9c +0b9e 0b9f +0ba3 0ba4 +0ba8 0baa +0bae 0bb5 +0bb7 0bb9 +0bf0 0bf2 +0c05 0c0c +0c0e 0c10 +0c12 0c28 +0c2a 0c33 +0c35 0c39 +0c60 0c61 +0c85 0c8c +0c8e 0c90 +0c92 0ca8 +0caa 0cb3 +0cb5 0cb9 +0cde +0ce0 0ce1 +0d05 0d0c +0d0e 0d10 +0d12 0d28 +0d2a 0d39 +0d60 0d61 +0d85 0d96 +0d9a 0db1 +0db3 0dbb +0dbd +0dc0 0dc6 +0df4 +0e4f +0f00 0f0a +0f0d 0f17 +0f1a 0f1f +0f2a 0f34 +0f36 +0f38 +0f40 0f47 +0f49 0f6a +0f85 +0f88 0f8b +0fbe 0fc5 +0fc7 0fcc +0fcf +104a 104f +10a0 10c5 +10d0 10f6 +10fb +1200 1206 +1208 1246 +1248 +124a 124d +1250 1256 +1258 +125a 125d +1260 1286 +1288 +128a 128d +1290 12ae +12b0 +12b2 12b5 +12b8 12be +12c0 +12c2 12c5 +12c8 12ce +12d0 12d6 +12d8 12ee +12f0 130e +1310 +1312 1315 +1318 131e +1320 1346 +1348 135a +1362 1368 +1372 137c +13a0 13f4 +1401 1676 +1681 169a +16a0 16f0 +17dc +1800 1805 +1807 180a +1820 1877 +1880 18a8 +1e00 1e9b +1ea0 1ef9 +1f00 1f15 +1f18 1f1d +1f20 1f45 +1f48 1f4d +1f50 1f57 +1f59 +1f5b +1f5d +1f5f 1f7d +1f80 1fb4 +1fb6 1fc4 +1fc6 1fd3 +1fd6 1fdb +1fdd 1fef +1ff2 1ff4 +1ff6 1ffe +2015 +2017 +2022 2023 +2038 +203d 2043 +2048 204d +2070 +2075 207c +2080 +2085 208c +2100 2102 +2104 +2106 2108 +210a 2112 +2114 2115 +2117 2120 +2123 2125 +2127 212a +212c 213a +2153 +2156 215a +215c 215d +215f +216c 216f +217a 2183 +219a 21d1 +21d3 +21d5 21f3 +2201 +2204 2206 +2209 220a +220c 220e +2210 +2214 +2216 2219 +221b 221c +2221 2222 +2224 +2226 +222d +222f 2233 +2238 223b +223e 2247 +2249 224b +224d 2251 +2253 225f +2262 2263 +2268 2269 +226c 226d +2270 2281 +2284 2285 +2288 2294 +2296 2298 +229a 22a4 +22a6 22be +22c0 22f1 +2300 2311 +2313 2328 +232b 237b +237d 239a +2400 2426 +2440 244a +24c0 24cf +24ea +254c 254f +2575 257f +2590 2591 +25a2 +25aa 25b1 +25b4 25b5 +25b8 25bb +25be 25bf +25c2 25c5 +25c8 25ca +25cc 25cd +25d2 25e1 +25e6 25ee +25f0 25f7 +2600 2604 +2607 2608 +260a 260d +2610 2613 +2619 261b +261d +261f 263f +2641 +2643 265f +2662 +2666 +266b +266e +2670 2671 +2701 2704 +2706 2709 +270c 2727 +2729 274b +274d +274f 2752 +2756 +2758 275e +2761 2767 +2776 2794 +2798 27af +27b1 27be +2800 28ff +fb00 fb06 +fb13 fb17 +fb1d +fb1f fb36 +fb38 fb3c +fb3e +fb40 fb41 +fb43 fb44 +fb46 fbb1 +fbd3 fd3d +fd50 fd8f +fd92 fdc7 +fdf0 fdfb +fe6b +fe70 fe72 +fe74 +fe76 fefc +ff66 +ff71 ff9d +ffa0 ffbe +ffc2 ffc7 +ffca ffcf +ffd2 ffd7 +ffda ffdc +ffe8 ffee +10300 1031e +10320 10323 +10330 1034a +10400 10425 +10428 1044d +1d000 1d0f5 +1d100 1d126 +1d12a 1d164 +1d16a 1d16c +1d183 1d184 +1d18c 1d1a9 +1d1ae 1d1dd +1d400 1d454 +1d456 1d49c +1d49e 1d49f +1d4a2 +1d4a5 1d4a6 +1d4a9 1d4ac +1d4ae 1d4b9 +1d4bb +1d4bd 1d4c0 +1d4c2 1d4c3 +1d4c5 1d505 +1d507 1d50a +1d50d 1d514 +1d516 1d51c +1d51e 1d539 +1d53b 1d53e +1d540 1d544 +1d546 +1d54a 1d550 +1d552 1d6a3 +1d6a8 1d7c9 END diff --git a/lib/unicode/Is/LbrkB2.pl b/lib/unicode/Is/LbrkB2.pl index 272f63fc9f..3629979638 100644 --- a/lib/unicode/Is/LbrkB2.pl +++ b/lib/unicode/Is/LbrkB2.pl @@ -2,4 +2,5 @@ # This file is built by mktables.PL from e.g. Unicode.txt. # Any changes made here will be lost! return <<'END'; +2014 END diff --git a/lib/unicode/Is/LbrkBA.pl b/lib/unicode/Is/LbrkBA.pl index 272f63fc9f..ac7db79d7f 100644 --- a/lib/unicode/Is/LbrkBA.pl +++ b/lib/unicode/Is/LbrkBA.pl @@ -2,4 +2,18 @@ # This file is built by mktables.PL from e.g. Unicode.txt. # Any changes made here will be lost! return <<'END'; +0009 +007c +00ad +00b4 +058a +0f0b +1361 +1680 +17d5 +2000 2006 +2008 200a +2010 +2012 2013 +2027 END diff --git a/lib/unicode/Is/LbrkBB.pl b/lib/unicode/Is/LbrkBB.pl index 272f63fc9f..e8b866dfb5 100644 --- a/lib/unicode/Is/LbrkBB.pl +++ b/lib/unicode/Is/LbrkBB.pl @@ -2,4 +2,7 @@ # This file is built by mktables.PL from e.g. Unicode.txt. # Any changes made here will be lost! return <<'END'; +02c8 +02cc +1806 END diff --git a/lib/unicode/Is/LbrkBK.pl b/lib/unicode/Is/LbrkBK.pl index 272f63fc9f..61b23d0523 100644 --- a/lib/unicode/Is/LbrkBK.pl +++ b/lib/unicode/Is/LbrkBK.pl @@ -2,4 +2,6 @@ # This file is built by mktables.PL from e.g. Unicode.txt. # Any changes made here will be lost! return <<'END'; +000c +2028 2029 END diff --git a/lib/unicode/Is/LbrkCB.pl b/lib/unicode/Is/LbrkCB.pl index 272f63fc9f..324033155c 100644 --- a/lib/unicode/Is/LbrkCB.pl +++ b/lib/unicode/Is/LbrkCB.pl @@ -2,4 +2,5 @@ # This file is built by mktables.PL from e.g. Unicode.txt. # Any changes made here will be lost! return <<'END'; +fffc END diff --git a/lib/unicode/Is/LbrkCL.pl b/lib/unicode/Is/LbrkCL.pl index 272f63fc9f..bc7513f85b 100644 --- a/lib/unicode/Is/LbrkCL.pl +++ b/lib/unicode/Is/LbrkCL.pl @@ -2,4 +2,46 @@ # This file is built by mktables.PL from e.g. Unicode.txt. # Any changes made here will be lost! return <<'END'; +0029 +005d +007d +0f3b +0f3d +169c +2046 +207e +208e +232a +3001 3002 +3009 +300b +300d +300f +3011 +3015 +3017 +3019 +301b +301e 301f +fd3f +fe36 +fe38 +fe3a +fe3c +fe3e +fe40 +fe42 +fe44 +fe50 +fe52 +fe5a +fe5c +fe5e +ff09 +ff0c +ff0e +ff3d +ff5d +ff61 +ff63 ff64 END diff --git a/lib/unicode/Is/LbrkCM.pl b/lib/unicode/Is/LbrkCM.pl index 272f63fc9f..4fe37fe086 100644 --- a/lib/unicode/Is/LbrkCM.pl +++ b/lib/unicode/Is/LbrkCM.pl @@ -2,4 +2,122 @@ # This file is built by mktables.PL from e.g. Unicode.txt. # Any changes made here will be lost! return <<'END'; +0000 0008 +000b +000e 001f +007f 009f +0300 034e +0360 0362 +0483 0486 +0488 0489 +0591 05a1 +05a3 05b9 +05bb 05bd +05bf +05c1 05c2 +05c4 +064b 0655 +0670 +06d6 06e4 +06e7 06e8 +06ea 06ed +070f +0711 +0730 074a +07a6 07b0 +0901 0903 +093c +093e 094d +0951 0954 +0962 0963 +0981 0983 +09bc +09be 09c4 +09c7 09c8 +09cb 09cd +09d7 +09e2 09e3 +0a02 +0a3c +0a3e 0a42 +0a47 0a48 +0a4b 0a4d +0a70 0a71 +0a81 0a83 +0abc +0abe 0ac5 +0ac7 0ac9 +0acb 0acd +0b01 0b03 +0b3c +0b3e 0b43 +0b47 0b48 +0b4b 0b4d +0b56 0b57 +0b82 0b83 +0bbe 0bc2 +0bc6 0bc8 +0bca 0bcd +0bd7 +0c01 0c03 +0c3e 0c44 +0c46 0c48 +0c4a 0c4d +0c55 0c56 +0c82 0c83 +0cbe 0cc4 +0cc6 0cc8 +0cca 0ccd +0cd5 0cd6 +0d02 0d03 +0d3e 0d43 +0d46 0d48 +0d4a 0d4d +0d57 +0d82 0d83 +0dca +0dcf 0dd4 +0dd6 +0dd8 0ddf +0df2 0df3 +0e31 +0e34 0e3a +0e47 0e4e +0eb1 +0eb4 0eb9 +0ebb 0ebc +0ec8 0ecd +0f18 0f19 +0f35 +0f37 +0f39 +0f3e 0f3f +0f71 0f84 +0f86 0f87 +0f90 0f97 +0f99 0fbc +0fc6 +102c 1032 +1036 1039 +1056 1059 +1160 11a2 +11a8 11f9 +17b4 17d3 +180b 180e +18a9 +200c 200f +202a 202e +206a 206f +20d0 20e3 +302a 302f +3099 309a +fb1e +fe20 fe23 +fff9 fffb +1d165 1d169 +1d16d 1d182 +1d185 1d18b +1d1aa 1d1ad +e0001 +e0020 e007f END diff --git a/lib/unicode/Is/LbrkCR.pl b/lib/unicode/Is/LbrkCR.pl index 272f63fc9f..61dba33920 100644 --- a/lib/unicode/Is/LbrkCR.pl +++ b/lib/unicode/Is/LbrkCR.pl @@ -2,4 +2,5 @@ # This file is built by mktables.PL from e.g. Unicode.txt. # Any changes made here will be lost! return <<'END'; +000d END diff --git a/lib/unicode/Is/LbrkEX.pl b/lib/unicode/Is/LbrkEX.pl index 272f63fc9f..55d9f40f63 100644 --- a/lib/unicode/Is/LbrkEX.pl +++ b/lib/unicode/Is/LbrkEX.pl @@ -2,4 +2,9 @@ # This file is built by mktables.PL from e.g. Unicode.txt. # Any changes made here will be lost! return <<'END'; +0021 +003f +fe56 fe57 +ff01 +ff1f END diff --git a/lib/unicode/Is/LbrkGL.pl b/lib/unicode/Is/LbrkGL.pl index 272f63fc9f..b0be7a3566 100644 --- a/lib/unicode/Is/LbrkGL.pl +++ b/lib/unicode/Is/LbrkGL.pl @@ -2,4 +2,10 @@ # This file is built by mktables.PL from e.g. Unicode.txt. # Any changes made here will be lost! return <<'END'; +00a0 +0f0c +2007 +2011 +202f +feff END diff --git a/lib/unicode/Is/LbrkHY.pl b/lib/unicode/Is/LbrkHY.pl index 272f63fc9f..2809c2c13c 100644 --- a/lib/unicode/Is/LbrkHY.pl +++ b/lib/unicode/Is/LbrkHY.pl @@ -2,4 +2,5 @@ # This file is built by mktables.PL from e.g. Unicode.txt. # Any changes made here will be lost! return <<'END'; +002d END diff --git a/lib/unicode/Is/LbrkID.pl b/lib/unicode/Is/LbrkID.pl index 272f63fc9f..c0bd0e5758 100644 --- a/lib/unicode/Is/LbrkID.pl +++ b/lib/unicode/Is/LbrkID.pl @@ -2,4 +2,82 @@ # This file is built by mktables.PL from e.g. Unicode.txt. # Any changes made here will be lost! return <<'END'; +1100 1159 +115f +2e80 2e99 +2e9b 2ef3 +2f00 2fd5 +2ff0 2ffb +3000 +3003 3004 +3006 3007 +3012 3013 +3020 3029 +3030 303a +303e 303f +3042 +3044 +3046 +3048 +304a 3062 +3064 3082 +3084 +3086 +3088 308d +308f 3094 +30a2 +30a4 +30a6 +30a8 +30aa 30c2 +30c4 30e2 +30e4 +30e6 +30e8 30ed +30ef 30f4 +30f7 30fa +30fc +30fe +3105 312c +3131 318e +3190 31b7 +3200 321c +3220 3243 +3260 327b +327f 32b0 +32c0 32cb +32d0 32fe +3300 3376 +337b 33dd +33e0 33fe +3400 4db5 +4e00 9fa5 +a000 a48c +a490 a4a1 +a4a4 a4b3 +a4b5 a4c0 +a4c2 a4c4 +a4c6 +ac00 d7a3 +f900 fa2d +fe30 fe34 +fe49 fe4f +fe51 +fe58 +fe5f fe66 +fe68 +ff02 ff03 +ff06 ff07 +ff0a ff0b +ff0d +ff0f ff19 +ff1c ff1e +ff20 ff3a +ff3c +ff3e ff5a +ff5c +ff5e +ffe2 ffe4 +20000 2a6d6 +2f800 2fa1d END diff --git a/lib/unicode/Is/LbrkIN.pl b/lib/unicode/Is/LbrkIN.pl index 272f63fc9f..a2a39d7af0 100644 --- a/lib/unicode/Is/LbrkIN.pl +++ b/lib/unicode/Is/LbrkIN.pl @@ -2,4 +2,5 @@ # This file is built by mktables.PL from e.g. Unicode.txt. # Any changes made here will be lost! return <<'END'; +2024 2026 END diff --git a/lib/unicode/Is/LbrkIS.pl b/lib/unicode/Is/LbrkIS.pl index 272f63fc9f..57cd5426bf 100644 --- a/lib/unicode/Is/LbrkIS.pl +++ b/lib/unicode/Is/LbrkIS.pl @@ -2,4 +2,8 @@ # This file is built by mktables.PL from e.g. Unicode.txt. # Any changes made here will be lost! return <<'END'; +002c +002e +003a 003b +0589 END diff --git a/lib/unicode/Is/LbrkLF.pl b/lib/unicode/Is/LbrkLF.pl index 272f63fc9f..5b539d4925 100644 --- a/lib/unicode/Is/LbrkLF.pl +++ b/lib/unicode/Is/LbrkLF.pl @@ -2,4 +2,5 @@ # This file is built by mktables.PL from e.g. Unicode.txt. # Any changes made here will be lost! return <<'END'; +000a END diff --git a/lib/unicode/Is/LbrkNS.pl b/lib/unicode/Is/LbrkNS.pl index 272f63fc9f..508af979a2 100644 --- a/lib/unicode/Is/LbrkNS.pl +++ b/lib/unicode/Is/LbrkNS.pl @@ -2,4 +2,40 @@ # This file is built by mktables.PL from e.g. Unicode.txt. # Any changes made here will be lost! return <<'END'; +0e5a 0e5b +17d4 +17d6 17da +203c +2044 +3005 +301c +3041 +3043 +3045 +3047 +3049 +3063 +3083 +3085 +3087 +308e +309b 309e +30a1 +30a3 +30a5 +30a7 +30a9 +30c3 +30e3 +30e5 +30e7 +30ee +30f5 30f6 +30fb +30fd +fe54 fe55 +ff1a ff1b +ff65 +ff67 ff70 +ff9e ff9f END diff --git a/lib/unicode/Is/LbrkNU.pl b/lib/unicode/Is/LbrkNU.pl index 272f63fc9f..3224a7238e 100644 --- a/lib/unicode/Is/LbrkNU.pl +++ b/lib/unicode/Is/LbrkNU.pl @@ -2,4 +2,24 @@ # This file is built by mktables.PL from e.g. Unicode.txt. # Any changes made here will be lost! return <<'END'; +0030 0039 +0660 0669 +06f0 06f9 +0966 096f +09e6 09ef +0a66 0a6f +0ae6 0aef +0b66 0b6f +0be7 0bef +0c66 0c6f +0ce6 0cef +0d66 0d6f +0e50 0e59 +0ed0 0ed9 +0f20 0f29 +1040 1049 +1369 1371 +17e0 17e9 +1810 1819 +1d7ce 1d7ff END diff --git a/lib/unicode/Is/LbrkOP.pl b/lib/unicode/Is/LbrkOP.pl index 272f63fc9f..f0548cc6d4 100644 --- a/lib/unicode/Is/LbrkOP.pl +++ b/lib/unicode/Is/LbrkOP.pl @@ -2,4 +2,42 @@ # This file is built by mktables.PL from e.g. Unicode.txt. # Any changes made here will be lost! return <<'END'; +0028 +005b +007b +0f3a +0f3c +169b +201a +201e +2045 +207d +208d +2329 +3008 +300a +300c +300e +3010 +3014 +3016 +3018 +301a +301d +fd3e +fe35 +fe37 +fe39 +fe3b +fe3d +fe3f +fe41 +fe43 +fe59 +fe5b +fe5d +ff08 +ff3b +ff5b +ff62 END diff --git a/lib/unicode/Is/LbrkPO.pl b/lib/unicode/Is/LbrkPO.pl index 272f63fc9f..0d896336d6 100644 --- a/lib/unicode/Is/LbrkPO.pl +++ b/lib/unicode/Is/LbrkPO.pl @@ -2,4 +2,15 @@ # This file is built by mktables.PL from e.g. Unicode.txt. # Any changes made here will be lost! return <<'END'; +0025 +00a2 +00b0 +2030 2037 +20a7 +2103 +2109 +2126 +fe6a +ff05 +ffe0 END diff --git a/lib/unicode/Is/LbrkPR.pl b/lib/unicode/Is/LbrkPR.pl index 272f63fc9f..6ffc77b1f1 100644 --- a/lib/unicode/Is/LbrkPR.pl +++ b/lib/unicode/Is/LbrkPR.pl @@ -2,4 +2,20 @@ # This file is built by mktables.PL from e.g. Unicode.txt. # Any changes made here will be lost! return <<'END'; +0024 +002b +005c +00a3 00a5 +00b1 +09f2 09f3 +0e3f +17db +20a0 20a6 +20a8 20af +2116 +2212 2213 +fe69 +ff04 +ffe1 +ffe5 ffe6 END diff --git a/lib/unicode/Is/LbrkQU.pl b/lib/unicode/Is/LbrkQU.pl index 272f63fc9f..6c9c82a1cc 100644 --- a/lib/unicode/Is/LbrkQU.pl +++ b/lib/unicode/Is/LbrkQU.pl @@ -2,4 +2,12 @@ # This file is built by mktables.PL from e.g. Unicode.txt. # Any changes made here will be lost! return <<'END'; +0022 +0027 +00ab +00bb +2018 2019 +201b 201d +201f +2039 203a END diff --git a/lib/unicode/Is/LbrkSA.pl b/lib/unicode/Is/LbrkSA.pl index 272f63fc9f..16cc627f69 100644 --- a/lib/unicode/Is/LbrkSA.pl +++ b/lib/unicode/Is/LbrkSA.pl @@ -2,4 +2,29 @@ # This file is built by mktables.PL from e.g. Unicode.txt. # Any changes made here will be lost! return <<'END'; +0e01 0e30 +0e32 0e33 +0e40 0e46 +0e81 0e82 +0e84 +0e87 0e88 +0e8a +0e8d +0e94 0e97 +0e99 0e9f +0ea1 0ea3 +0ea5 +0ea7 +0eaa 0eab +0ead 0eb0 +0eb2 0eb3 +0ebd +0ec0 0ec4 +0ec6 +0edc 0edd +1000 1021 +1023 1027 +1029 102a +1050 1055 +1780 17b3 END diff --git a/lib/unicode/Is/LbrkSG.pl b/lib/unicode/Is/LbrkSG.pl index 272f63fc9f..9cf13e9e26 100644 --- a/lib/unicode/Is/LbrkSG.pl +++ b/lib/unicode/Is/LbrkSG.pl @@ -2,4 +2,7 @@ # This file is built by mktables.PL from e.g. Unicode.txt. # Any changes made here will be lost! return <<'END'; +d800 db7f +db80 dbff +dc00 dfff END diff --git a/lib/unicode/Is/LbrkSP.pl b/lib/unicode/Is/LbrkSP.pl index 272f63fc9f..9fc9e99867 100644 --- a/lib/unicode/Is/LbrkSP.pl +++ b/lib/unicode/Is/LbrkSP.pl @@ -2,4 +2,5 @@ # This file is built by mktables.PL from e.g. Unicode.txt. # Any changes made here will be lost! return <<'END'; +0020 END diff --git a/lib/unicode/Is/LbrkSY.pl b/lib/unicode/Is/LbrkSY.pl index 272f63fc9f..405d7d6476 100644 --- a/lib/unicode/Is/LbrkSY.pl +++ b/lib/unicode/Is/LbrkSY.pl @@ -2,4 +2,5 @@ # This file is built by mktables.PL from e.g. Unicode.txt. # Any changes made here will be lost! return <<'END'; +002f END diff --git a/lib/unicode/Is/LbrkZW.pl b/lib/unicode/Is/LbrkZW.pl index 272f63fc9f..040724d455 100644 --- a/lib/unicode/Is/LbrkZW.pl +++ b/lib/unicode/Is/LbrkZW.pl @@ -2,4 +2,5 @@ # This file is built by mktables.PL from e.g. Unicode.txt. # Any changes made here will be lost! return <<'END'; +200b END diff --git a/lib/unicode/Is/Ll.pl b/lib/unicode/Is/Ll.pl index 0e4fb7d901..9befb4d4ae 100644 --- a/lib/unicode/Is/Ll.pl +++ b/lib/unicode/Is/Ll.pl @@ -396,9 +396,14 @@ ff41 ff5a 1d622 1d63b 1d656 1d66f 1d68a 1d6a3 -1d6c1 1d6e1 -1d6fb 1d71b -1d735 1d755 -1d76f 1d78f -1d7a9 1d7c9 +1d6c2 1d6da +1d6dc 1d6e1 +1d6fc 1d714 +1d716 1d71b +1d736 1d74e +1d750 1d755 +1d770 1d788 +1d78a 1d78f +1d7aa 1d7c2 +1d7c4 1d7c9 END diff --git a/lib/unicode/Is/Lower.pl b/lib/unicode/Is/Lower.pl index 0e4fb7d901..9befb4d4ae 100644 --- a/lib/unicode/Is/Lower.pl +++ b/lib/unicode/Is/Lower.pl @@ -396,9 +396,14 @@ ff41 ff5a 1d622 1d63b 1d656 1d66f 1d68a 1d6a3 -1d6c1 1d6e1 -1d6fb 1d71b -1d735 1d755 -1d76f 1d78f -1d7a9 1d7c9 +1d6c2 1d6da +1d6dc 1d6e1 +1d6fc 1d714 +1d716 1d71b +1d736 1d74e +1d750 1d755 +1d770 1d788 +1d78a 1d78f +1d7aa 1d7c2 +1d7c4 1d7c9 END diff --git a/lib/unicode/Is/S.pl b/lib/unicode/Is/S.pl index e5bf015272..943a677171 100644 --- a/lib/unicode/Is/S.pl +++ b/lib/unicode/Is/S.pl @@ -135,4 +135,14 @@ fffc fffd 1d183 1d184 1d18c 1d1a9 1d1ae 1d1dd +1d6c1 +1d6db +1d6fb +1d715 +1d735 +1d74f +1d76f +1d789 +1d7a9 +1d7c3 END diff --git a/lib/unicode/Is/Sm.pl b/lib/unicode/Is/Sm.pl index 730af561f6..66fa288339 100644 --- a/lib/unicode/Is/Sm.pl +++ b/lib/unicode/Is/Sm.pl @@ -37,4 +37,14 @@ ff5c ff5e ffe2 ffe9 ffec +1d6c1 +1d6db +1d6fb +1d715 +1d735 +1d74f +1d76f +1d789 +1d7a9 +1d7c3 END diff --git a/lib/unicode/Is/Word.pl b/lib/unicode/Is/Word.pl index 842eae7a2f..435b3724a1 100644 --- a/lib/unicode/Is/Word.pl +++ b/lib/unicode/Is/Word.pl @@ -386,7 +386,17 @@ ffda ffdc 1d546 1d54a 1d550 1d552 1d6a3 -1d6a8 1d7c9 +1d6a8 1d6c0 +1d6c2 1d6da +1d6dc 1d6fa +1d6fc 1d714 +1d716 1d734 +1d736 1d74e +1d750 1d76e +1d770 1d788 +1d78a 1d7a8 +1d7aa 1d7c2 +1d7c4 1d7c9 1d7ce 1d7ff 20000 2a6d6 2f800 2fa1d diff --git a/lib/unicode/Names.txt b/lib/unicode/Names.txt index 0dbd1f8aca..5499d07d90 100644 --- a/lib/unicode/Names.txt +++ b/lib/unicode/Names.txt @@ -1,7 +1,14 @@ @@@ The Unicode Standard 3.1 -@@@+ Draft U31M001129.lst - Fix misc. typos. - Add annotation for 030D. +@@@+ Draft U31M010208.lst + Punctuation correction in math alphanumerics notice. + Add annotation for FB1E and 05BF. + Add tentative English translations for Byzantine musical subheads. + Extend annotations for 0598 ZARQA and 05AE ZINOR. + Correct placement of Dependent Vowels header in Devanagari. + Update subheads for mensural notation in musical symbols. + Add bra/ket aliases for 3008, 3009. + Add noncharacters for Planes 3..13, 15, 16. + Added alias for 25BD. @@ 0000 C0 Controls and Basic Latin (Basic Latin) 007F @ C0 controls @+ Alias names are those for ISO 6429. @@ -2991,7 +2998,9 @@ = tarha 0597 HEBREW ACCENT REVIA 0598 HEBREW ACCENT ZARQA * - = zinorit + = tsinorit, zinorit; tsinor, zinor + * This character is to be used when Zarqa or Tsinor are placed above, and also for Tsinorit. + x (05AE - hebrew accent zinor) 0599 HEBREW ACCENT PASHTA 059A HEBREW ACCENT YETIV 059B HEBREW ACCENT TEVIR @@ -3016,6 +3025,9 @@ 05AC HEBREW ACCENT ILUY 05AD HEBREW ACCENT DEHI 05AE HEBREW ACCENT ZINOR + = tsinor; zarqa + * This character is to be used when Zarqa or Tsinor are placed above left. + x (0598 - hebrew accent zarqa) 05AF HEBREW MARK MASORA CIRCLE @ Points and punctuation 05B0 HEBREW POINT SHEVA @@ -3038,6 +3050,7 @@ * may be used as a Hebrew accent sof pasuq 05BE HEBREW PUNCTUATION MAQAF 05BF HEBREW POINT RAFE + x (hebrew point judeo-spanish varika - FB1E) 05C0 HEBREW PUNCTUATION PASEQ * = legarmeh * may be treated as spacing punctuation, not as a point @@ -3688,8 +3701,8 @@ 093C DEVANAGARI SIGN NUKTA * for extending the alphabet to new letters 093D DEVANAGARI SIGN AVAGRAHA -093E DEVANAGARI VOWEL SIGN AA @ Dependent vowel signs +093E DEVANAGARI VOWEL SIGN AA 093F DEVANAGARI VOWEL SIGN I * stands to the left of the consonant 0940 DEVANAGARI VOWEL SIGN II @@ -10229,6 +10242,7 @@ x (contains as normal subgroup - 22B3) 25BC BLACK DOWN-POINTING TRIANGLE 25BD WHITE DOWN-POINTING TRIANGLE + = Hamilton operator x (nabla - 2207) 25BE BLACK DOWN-POINTING SMALL TRIANGLE 25BF WHITE DOWN-POINTING SMALL TRIANGLE @@ -11566,10 +11580,14 @@ x (white circle - 25CB) x (large circle - 25EF) 3008 LEFT ANGLE BRACKET + = bra + = z notation left sequence bracket x (less-than sign - 003C) x (single left-pointing angle quotation mark - 2039) x (left-pointing angle bracket - 2329) 3009 RIGHT ANGLE BRACKET + = ket + = z notation right sequence bracket x (greater-than sign - 003E) x (single right-pointing angle quotation mark - 203A) x (right-pointing angle bracket - 232A) @@ -11599,9 +11617,9 @@ 3018 LEFT WHITE TORTOISE SHELL BRACKET 3019 RIGHT WHITE TORTOISE SHELL BRACKET 301A LEFT WHITE SQUARE BRACKET - = z notation left bag bracket + = left abstract syntax bracket 301B RIGHT WHITE SQUARE BRACKET - = z notation right bag bracket + = right abstract syntax bracket 301C WAVE DASH @+ * This character was encoded to match JIS C 6226-1978 1-33 "wave dash". Subsequent revisions of the JIS standard and industry practice have settled on JIS 1-33 as being the fullwidth tilde character. x (wavy dash - 3030) @@ -15131,10 +15149,11 @@ FB16 ARMENIAN SMALL LIGATURE VEW NOW FB17 ARMENIAN SMALL LIGATURE MEN XEH # 0574 056D @ Hebrew presentation forms -@+ See the Hebrew block starting at 0590 FB1D HEBREW LETTER YOD WITH HIRIQ : 05D9 05B4 FB1E HEBREW POINT JUDEO-SPANISH VARIKA + * a glyph variant of 05BF +@+ See the Hebrew block starting at 0590 FB1F HEBREW LIGATURE YIDDISH YOD YOD PATAH : 05F2 05B7 FB20 HEBREW LETTER ALTERNATIVE AYIN @@ -17481,7 +17500,7 @@ FFFF <not a character> 1044C DESERET SMALL LETTER EN 1044D DESERET SMALL LETTER ENG @@ 1D000 Byzantine Musical Symbols 1D0FF -@ Prosodies +@ Prosodies (Prosodics) 1D000 BYZANTINE MUSICAL SYMBOL PSILI 1D001 BYZANTINE MUSICAL SYMBOL DASEIA 1D002 BYZANTINE MUSICAL SYMBOL PERISPOMENI @@ -17504,7 +17523,7 @@ FFFF <not a character> 1D012 BYZANTINE MUSICAL SYMBOL APOSTROFOS DIPLI 1D013 BYZANTINE MUSICAL SYMBOL SYNEVMA 1D014 BYZANTINE MUSICAL SYMBOL THITA -@ Melodimata +@ Melodimata (Melodics) 1D015 BYZANTINE MUSICAL SYMBOL OLIGON ARCHAION 1D016 BYZANTINE MUSICAL SYMBOL GORGON ARCHAION 1D017 BYZANTINE MUSICAL SYMBOL PSILON @@ -17554,7 +17573,7 @@ FFFF <not a character> 1D043 BYZANTINE MUSICAL SYMBOL TROMIKON ALLO 1D044 BYZANTINE MUSICAL SYMBOL STRAGGISMATA 1D045 BYZANTINE MUSICAL SYMBOL GRONTHISMATA -@ Fonitika +@ Fonitika (Vocals) 1D046 BYZANTINE MUSICAL SYMBOL ISON NEO 1D047 BYZANTINE MUSICAL SYMBOL OLIGON NEO 1D048 BYZANTINE MUSICAL SYMBOL OXEIA NEO @@ -17572,7 +17591,7 @@ FFFF <not a character> 1D054 BYZANTINE MUSICAL SYMBOL KRATIMOYPORROON 1D055 BYZANTINE MUSICAL SYMBOL ELAFRON 1D056 BYZANTINE MUSICAL SYMBOL CHAMILI -@ Afona or Ypistaseis +@ Afona or Ypostaseis (Mutes or Hypostases) 1D057 BYZANTINE MUSICAL SYMBOL MIKRON ISON 1D058 BYZANTINE MUSICAL SYMBOL VAREIA NEO 1D059 BYZANTINE MUSICAL SYMBOL PIASMA NEO @@ -17613,7 +17632,7 @@ FFFF <not a character> 1D07C BYZANTINE MUSICAL SYMBOL YFEN KATO 1D07D BYZANTINE MUSICAL SYMBOL YFEN ANO 1D07E BYZANTINE MUSICAL SYMBOL STAVROS -@ Argies +@ Argies (Retards) 1D07F BYZANTINE MUSICAL SYMBOL KLASMA ANO 1D080 BYZANTINE MUSICAL SYMBOL DIPLI ARCHAION 1D081 BYZANTINE MUSICAL SYMBOL KRATIMA ARCHAION @@ -17625,13 +17644,13 @@ FFFF <not a character> 1D087 BYZANTINE MUSICAL SYMBOL TRIPLI 1D088 BYZANTINE MUSICAL SYMBOL TETRAPLI 1D089 BYZANTINE MUSICAL SYMBOL KORONIS -@ Leimmata or Siopes +@ Leimmata or Siopes (Leimmas or Silencers) 1D08A BYZANTINE MUSICAL SYMBOL LEIMMA ENOS CHRONOU 1D08B BYZANTINE MUSICAL SYMBOL LEIMMA DYO CHRONON 1D08C BYZANTINE MUSICAL SYMBOL LEIMMA TRION CHRONON 1D08D BYZANTINE MUSICAL SYMBOL LEIMMA TESSARON CHRONON 1D08E BYZANTINE MUSICAL SYMBOL LEIMMA IMISEOS CHRONOU -@ Synagmata or Gorgotites +@ Synagmata or Gorgotites (Synagmas or Quickeners) 1D08F BYZANTINE MUSICAL SYMBOL GORGON NEO ANO 1D090 BYZANTINE MUSICAL SYMBOL GORGON PARESTIGMENON ARISTERA 1D091 BYZANTINE MUSICAL SYMBOL GORGON PARESTIGMENON DEXIA @@ -17643,7 +17662,7 @@ FFFF <not a character> 1D097 BYZANTINE MUSICAL SYMBOL ARGON 1D098 BYZANTINE MUSICAL SYMBOL IMIDIARGON 1D099 BYZANTINE MUSICAL SYMBOL DIARGON -@ Agogika +@ Agogika (Conduits) 1D09A BYZANTINE MUSICAL SYMBOL AGOGI POLI ARGI 1D09B BYZANTINE MUSICAL SYMBOL AGOGI ARGOTERI 1D09C BYZANTINE MUSICAL SYMBOL AGOGI ARGI @@ -17652,7 +17671,7 @@ FFFF <not a character> 1D09F BYZANTINE MUSICAL SYMBOL AGOGI GORGI 1D0A0 BYZANTINE MUSICAL SYMBOL AGOGI GORGOTERI 1D0A1 BYZANTINE MUSICAL SYMBOL AGOGI POLI GORGI -@ Ichimata and Martyrika +@ Ichimata and Martyrika (Ichimas and Evidentials) 1D0A2 BYZANTINE MUSICAL SYMBOL MARTYRIA PROTOS ICHOS 1D0A3 BYZANTINE MUSICAL SYMBOL MARTYRIA ALLI PROTOS ICHOS 1D0A4 BYZANTINE MUSICAL SYMBOL MARTYRIA DEYTEROS ICHOS @@ -17672,7 +17691,7 @@ FFFF <not a character> 1D0B2 BYZANTINE MUSICAL SYMBOL MARTYRIA PROTOVARYS ICHOS 1D0B3 BYZANTINE MUSICAL SYMBOL MARTYRIA PLAGIOS TETARTOS ICHOS 1D0B4 BYZANTINE MUSICAL SYMBOL GORTHMIKON N APLOUN -@ Fthores +@ Fthores (Destroyers) 1D0B5 BYZANTINE MUSICAL SYMBOL GORTHMIKON N DIPLOUN 1D0B6 BYZANTINE MUSICAL SYMBOL ENARXIS KAI FTHORA VOU 1D0B7 BYZANTINE MUSICAL SYMBOL IMIFONON @@ -17694,7 +17713,7 @@ FFFF <not a character> 1D0C7 BYZANTINE MUSICAL SYMBOL FTHORA NENANO 1D0C8 BYZANTINE MUSICAL SYMBOL CHROA ZYGOS 1D0C9 BYZANTINE MUSICAL SYMBOL CHROA KLITON -@ Alloioseis +@ Alloioseis (Differentiators) 1D0CA BYZANTINE MUSICAL SYMBOL CHROA SPATHI 1D0CB BYZANTINE MUSICAL SYMBOL FTHORA I YFESIS TETARTIMORION 1D0CC BYZANTINE MUSICAL SYMBOL FTHORA ENARMONIOS ANTIFONIA @@ -17710,7 +17729,7 @@ FFFF <not a character> 1D0D6 BYZANTINE MUSICAL SYMBOL YFESIS DIGRAMMOS EX DODEKATA 1D0D7 BYZANTINE MUSICAL SYMBOL YFESIS TRIGRAMMOS OKTO DODEKATA 1D0D8 BYZANTINE MUSICAL SYMBOL GENIKI DIESIS -@ Rythmika +@ Rythmika (Rhythmics) 1D0D9 BYZANTINE MUSICAL SYMBOL GENIKI YFESIS 1D0DA BYZANTINE MUSICAL SYMBOL DIASTOLI APLI MIKRI 1D0DB BYZANTINE MUSICAL SYMBOL DIASTOLI APLI MEGALI @@ -17723,7 +17742,7 @@ FFFF <not a character> 1D0E2 BYZANTINE MUSICAL SYMBOL SIMANSIS ARSEOS 1D0E3 BYZANTINE MUSICAL SYMBOL SIMANSIS ARSEOS DISIMOU 1D0E4 BYZANTINE MUSICAL SYMBOL SIMANSIS ARSEOS TRISIMOU -@ Grammata +@ Grammata (Letters) 1D0E5 BYZANTINE MUSICAL SYMBOL SIMANSIS ARSEOS TETRASIMOU 1D0E6 BYZANTINE MUSICAL SYMBOL DIGRAMMA GG 1D0E7 BYZANTINE MUSICAL SYMBOL DIFTOGGOS OU @@ -17957,27 +17976,32 @@ FFFF <not a character> 1D1B3 MUSICAL SYMBOL WITH FINGERNAILS 1D1B4 MUSICAL SYMBOL DAMP 1D1B5 MUSICAL SYMBOL DAMP ALL +@ Mensural Notation 1D1B6 MUSICAL SYMBOL MAXIMA 1D1B7 MUSICAL SYMBOL LONGA 1D1B8 MUSICAL SYMBOL BREVIS -@ Noteheads 1D1B9 MUSICAL SYMBOL SEMIBREVIS WHITE 1D1BA MUSICAL SYMBOL SEMIBREVIS BLACK -@ Notes 1D1BB MUSICAL SYMBOL MINIMA + : 1D1B9 1D165 1D1BC MUSICAL SYMBOL MINIMA BLACK + : 1D1BA 1D165 1D1BD MUSICAL SYMBOL SEMIMINIMA WHITE + : 1D1BB 1D16E 1D1BE MUSICAL SYMBOL SEMIMINIMA BLACK + : 1D1BC 1D16E 1D1BF MUSICAL SYMBOL FUSA WHITE + : 1D1BB 1D16F 1D1C0 MUSICAL SYMBOL FUSA BLACK -@ Rests + : 1D1BC 1D16F +@ Mensural Rests 1D1C1 MUSICAL SYMBOL LONGA PERFECTA REST 1D1C2 MUSICAL SYMBOL LONGA IMPERFECTA REST 1D1C3 MUSICAL SYMBOL BREVIS REST 1D1C4 MUSICAL SYMBOL SEMIBREVIS REST 1D1C5 MUSICAL SYMBOL MINIMA REST 1D1C6 MUSICAL SYMBOL SEMIMINIMA REST -@ Tempi +@ Mensural Prolations 1D1C7 MUSICAL SYMBOL TEMPUS PERFECTUM CUM PROLATIONE PERFECTA 1D1C8 MUSICAL SYMBOL TEMPUS PERFECTUM CUM PROLATIONE IMPERFECTA 1D1C9 MUSICAL SYMBOL TEMPUS PERFECTUM CUM PROLATIONE PERFECTA DIMINUTION-1 @@ -18004,7 +18028,7 @@ FFFF <not a character> 1D1DC MUSICAL SYMBOL TORCULUS RESUPINUS 1D1DD MUSICAL SYMBOL PES SUBPUNCTIS @@ 1D400 Mathematical Alphanumeric Symbols 1D7FF -@+ To be used for mathematical variables where style variations are important semantically. For general text use standard Latin and Greek letters with markup. +@+ To be used for mathematical variables where style variations are important semantically. For general text, use standard Latin and Greek letters with markup. @ Bold symbols 1D400 MATHEMATICAL BOLD CAPITAL A # <font> 0041 latin capital letter a @@ -20074,6 +20098,7 @@ FFFF <not a character> * the value 1FFFE is guaranteed not to be a Unicode character at all 1FFFF <not a character> * the value 1FFFF is guaranteed not to be a Unicode character at all +@@ 20000 CJK Unified Ideographs Extension B 2A6D6 @@ 2F800 CJK Compatibility Ideographs Supplement 2FA1F 2F800 CJK COMPATIBILITY IDEOGRAPH-2F800 : 4E3D @@ -21165,6 +21190,72 @@ FFFF <not a character> * the value 2FFFE is guaranteed not to be a Unicode character at all 2FFFF <not a character> * the value 2FFFF is guaranteed not to be a Unicode character at all +@@ 3FF80 Unassigned 3FFFF +@ Not character codes +3FFFE <not a character> + * the value 3FFFE is guaranteed not to be a Unicode character at all +3FFFF <not a character> + * the value 3FFFF is guaranteed not to be a Unicode character at all +@@ 4FF80 Unassigned 4FFFF +@ Not character codes +4FFFE <not a character> + * the value 4FFFE is guaranteed not to be a Unicode character at all +4FFFF <not a character> + * the value 4FFFF is guaranteed not to be a Unicode character at all +@@ 5FF80 Unassigned 5FFFF +@ Not character codes +5FFFE <not a character> + * the value 5FFFE is guaranteed not to be a Unicode character at all +5FFFF <not a character> + * the value 5FFFF is guaranteed not to be a Unicode character at all +@@ 6FF80 Unassigned 6FFFF +@ Not character codes +6FFFE <not a character> + * the value 6FFFE is guaranteed not to be a Unicode character at all +6FFFF <not a character> + * the value 6FFFF is guaranteed not to be a Unicode character at all +@@ 7FF80 Unassigned 7FFFF +@ Not character codes +7FFFE <not a character> + * the value 7FFFE is guaranteed not to be a Unicode character at all +7FFFF <not a character> + * the value 7FFFF is guaranteed not to be a Unicode character at all +@@ 8FF80 Unassigned 8FFFF +@ Not character codes +8FFFE <not a character> + * the value 8FFFE is guaranteed not to be a Unicode character at all +8FFFF <not a character> + * the value 8FFFF is guaranteed not to be a Unicode character at all +@@ 9FF80 Unassigned 9FFFF +@ Not character codes +9FFFE <not a character> + * the value 9FFFE is guaranteed not to be a Unicode character at all +9FFFF <not a character> + * the value 9FFFF is guaranteed not to be a Unicode character at all +@@ AFF80 Unassigned AFFFF +@ Not character codes +AFFFE <not a character> + * the value AFFFE is guaranteed not to be a Unicode character at all +AFFFF <not a character> + * the value AFFFF is guaranteed not to be a Unicode character at all +@@ BFF80 Unassigned BFFFF +@ Not character codes +BFFFE <not a character> + * the value BFFFE is guaranteed not to be a Unicode character at all +BFFFF <not a character> + * the value BFFFF is guaranteed not to be a Unicode character at all +@@ CFF80 Unassigned CFFFF +@ Not character codes +CFFFE <not a character> + * the value CFFFE is guaranteed not to be a Unicode character at all +CFFFF <not a character> + * the value CFFFF is guaranteed not to be a Unicode character at all +@@ DFF80 Unassigned DFFFF +@ Not character codes +DFFFE <not a character> + * the value DFFFE is guaranteed not to be a Unicode character at all +DFFFF <not a character> + * the value DFFFF is guaranteed not to be a Unicode character at all @@ E0000 Tags E007F @ Tag identifiers E0001 LANGUAGE TAG @@ -21271,3 +21362,15 @@ EFFFE <not a character> * the value EFFFE is guaranteed not to be a Unicode character at all EFFFF <not a character> * the value EFFFF is guaranteed not to be a Unicode character at all +@@ FFF80 Private Use FFFFF +@ Not character codes +FFFFE <not a character> + * the value FFFFE is guaranteed not to be a Unicode character at all +FFFFF <not a character> + * the value FFFFF is guaranteed not to be a Unicode character at all +@@ 10FF80 Private Use 10FFFF +@ Not character codes +10FFFE <not a character> + * the value 10FFFE is guaranteed not to be a Unicode character at all +10FFFF <not a character> + * the value 10FFFF is guaranteed not to be a Unicode character at all diff --git a/lib/unicode/PropList.txt b/lib/unicode/PropList.txt index 9f01398f30..7c833ae77c 100644 --- a/lib/unicode/PropList.txt +++ b/lib/unicode/PropList.txt @@ -1,526 +1,535 @@ -# Unicode Character Database Extended Properties +# PropList-3.1.0.txt +# +# Unicode Character Database: Extended Properties # For documentation, see PropList.html -# Date: 2001-01-26 15:40:20.0 GMT [MD] -# Note: Unassigned and Noncharacter codepoints are excluded, -# except when listing Noncharacter. +# Date: 2001-03-02 00:06:33.9 GMT [MD] +# Note: Unassigned and Noncharacter codepoints are omitted, +# except when listing Noncharacter or Cn. # ================================================ - -# ================================================ -# BidiMirrored (listing UnicodeData.txt, field 9: see UnicodeData.html) # ================================================ -0009..000D; White_space # Cc [5] <control>..<control> -0020 ; White_space # Zs SPACE -0085 ; White_space # Cc <control> -00A0 ; White_space # Zs NO-BREAK SPACE -1680 ; White_space # Zs OGHAM SPACE MARK -2000..200B; White_space # Zs [12] EN QUAD..ZERO WIDTH SPACE -2028 ; White_space # Zl LINE SEPARATOR -2029 ; White_space # Zp PARAGRAPH SEPARATOR -202F ; White_space # Zs NARROW NO-BREAK SPACE -3000 ; White_space # Zs IDEOGRAPHIC SPACE +0009..000D ; White_space # Cc [5] <control>..<control> +0020 ; White_space # Zs SPACE +0085 ; White_space # Cc <control> +00A0 ; White_space # Zs NO-BREAK SPACE +1680 ; White_space # Zs OGHAM SPACE MARK +2000..200A ; White_space # Zs [11] EN QUAD..HAIR SPACE +2028 ; White_space # Zl LINE SEPARATOR +2029 ; White_space # Zp PARAGRAPH SEPARATOR +202F ; White_space # Zs NARROW NO-BREAK SPACE +3000 ; White_space # Zs IDEOGRAPHIC SPACE -# Total code points: 25 +# Total code points: 24 # ================================================ -200E..200F; Bidi_Control # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK -202A..202E; Bidi_Control # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE +200E..200F ; Bidi_Control # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK +202A..202E ; Bidi_Control # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE # Total code points: 7 # ================================================ -200C..200D; Join_Control # Cf [2] ZERO WIDTH NON-JOINER..ZERO WIDTH JOINER +200C..200D ; Join_Control # Cf [2] ZERO WIDTH NON-JOINER..ZERO WIDTH JOINER # Total code points: 2 # ================================================ -002D ; Dash # Pd HYPHEN-MINUS -00AD ; Dash # Pd SOFT HYPHEN -058A ; Dash # Pd ARMENIAN HYPHEN -1806 ; Dash # Pd MONGOLIAN TODO SOFT HYPHEN -2010..2015; Dash # Pd [6] HYPHEN..HORIZONTAL BAR -207B ; Dash # Sm SUPERSCRIPT MINUS -208B ; Dash # Sm SUBSCRIPT MINUS -2212 ; Dash # Sm MINUS SIGN -301C ; Dash # Pd WAVE DASH -3030 ; Dash # Pd WAVY DASH -FE31..FE32; Dash # Pd [2] PRESENTATION FORM FOR VERTICAL EM DASH..PRESENTATION FORM FOR VERTICAL EN DASH -FE58 ; Dash # Pd SMALL EM DASH -FE63 ; Dash # Pd SMALL HYPHEN-MINUS -FF0D ; Dash # Pd FULLWIDTH HYPHEN-MINUS +002D ; Dash # Pd HYPHEN-MINUS +00AD ; Dash # Pd SOFT HYPHEN +058A ; Dash # Pd ARMENIAN HYPHEN +1806 ; Dash # Pd MONGOLIAN TODO SOFT HYPHEN +2010..2015 ; Dash # Pd [6] HYPHEN..HORIZONTAL BAR +207B ; Dash # Sm SUPERSCRIPT MINUS +208B ; Dash # Sm SUBSCRIPT MINUS +2212 ; Dash # Sm MINUS SIGN +301C ; Dash # Pd WAVE DASH +3030 ; Dash # Pd WAVY DASH +FE31..FE32 ; Dash # Pd [2] PRESENTATION FORM FOR VERTICAL EM DASH..PRESENTATION FORM FOR VERTICAL EN DASH +FE58 ; Dash # Pd SMALL EM DASH +FE63 ; Dash # Pd SMALL HYPHEN-MINUS +FF0D ; Dash # Pd FULLWIDTH HYPHEN-MINUS # Total code points: 20 # ================================================ -002D ; Hyphen # Pd HYPHEN-MINUS -00AD ; Hyphen # Pd SOFT HYPHEN -058A ; Hyphen # Pd ARMENIAN HYPHEN -1806 ; Hyphen # Pd MONGOLIAN TODO SOFT HYPHEN -2010..2011; Hyphen # Pd [2] HYPHEN..NON-BREAKING HYPHEN -30FB ; Hyphen # Pc KATAKANA MIDDLE DOT -FE63 ; Hyphen # Pd SMALL HYPHEN-MINUS -FF0D ; Hyphen # Pd FULLWIDTH HYPHEN-MINUS -FF65 ; Hyphen # Pc HALFWIDTH KATAKANA MIDDLE DOT +002D ; Hyphen # Pd HYPHEN-MINUS +00AD ; Hyphen # Pd SOFT HYPHEN +058A ; Hyphen # Pd ARMENIAN HYPHEN +1806 ; Hyphen # Pd MONGOLIAN TODO SOFT HYPHEN +2010..2011 ; Hyphen # Pd [2] HYPHEN..NON-BREAKING HYPHEN +30FB ; Hyphen # Pc KATAKANA MIDDLE DOT +FE63 ; Hyphen # Pd SMALL HYPHEN-MINUS +FF0D ; Hyphen # Pd FULLWIDTH HYPHEN-MINUS +FF65 ; Hyphen # Pc HALFWIDTH KATAKANA MIDDLE DOT # Total code points: 10 # ================================================ -0022 ; Quotation_Mark # Po QUOTATION MARK -0027 ; Quotation_Mark # Po APOSTROPHE -00AB ; Quotation_Mark # Pi LEFT-POINTING DOUBLE ANGLE QUOTATION MARK -00BB ; Quotation_Mark # Pf RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK -2018 ; Quotation_Mark # Pi LEFT SINGLE QUOTATION MARK -2019 ; Quotation_Mark # Pf RIGHT SINGLE QUOTATION MARK -201A ; Quotation_Mark # Ps SINGLE LOW-9 QUOTATION MARK -201B..201C; Quotation_Mark # Pi [2] SINGLE HIGH-REVERSED-9 QUOTATION MARK..LEFT DOUBLE QUOTATION MARK -201D ; Quotation_Mark # Pf RIGHT DOUBLE QUOTATION MARK -201E ; Quotation_Mark # Ps DOUBLE LOW-9 QUOTATION MARK -201F ; Quotation_Mark # Pi DOUBLE HIGH-REVERSED-9 QUOTATION MARK -2039 ; Quotation_Mark # Pi SINGLE LEFT-POINTING ANGLE QUOTATION MARK -203A ; Quotation_Mark # Pf SINGLE RIGHT-POINTING ANGLE QUOTATION MARK -300C ; Quotation_Mark # Ps LEFT CORNER BRACKET -300D ; Quotation_Mark # Pe RIGHT CORNER BRACKET -300E ; Quotation_Mark # Ps LEFT WHITE CORNER BRACKET -300F ; Quotation_Mark # Pe RIGHT WHITE CORNER BRACKET -301D ; Quotation_Mark # Ps REVERSED DOUBLE PRIME QUOTATION MARK -301E..301F; Quotation_Mark # Pe [2] DOUBLE PRIME QUOTATION MARK..LOW DOUBLE PRIME QUOTATION MARK -FE41 ; Quotation_Mark # Ps PRESENTATION FORM FOR VERTICAL LEFT CORNER BRACKET -FE42 ; Quotation_Mark # Pe PRESENTATION FORM FOR VERTICAL RIGHT CORNER BRACKET -FE43 ; Quotation_Mark # Ps PRESENTATION FORM FOR VERTICAL LEFT WHITE CORNER BRACKET -FE44 ; Quotation_Mark # Pe PRESENTATION FORM FOR VERTICAL RIGHT WHITE CORNER BRACKET -FF02 ; Quotation_Mark # Po FULLWIDTH QUOTATION MARK -FF07 ; Quotation_Mark # Po FULLWIDTH APOSTROPHE -FF62 ; Quotation_Mark # Ps HALFWIDTH LEFT CORNER BRACKET -FF63 ; Quotation_Mark # Pe HALFWIDTH RIGHT CORNER BRACKET +0022 ; Quotation_Mark # Po QUOTATION MARK +0027 ; Quotation_Mark # Po APOSTROPHE +00AB ; Quotation_Mark # Pi LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +00BB ; Quotation_Mark # Pf RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +2018 ; Quotation_Mark # Pi LEFT SINGLE QUOTATION MARK +2019 ; Quotation_Mark # Pf RIGHT SINGLE QUOTATION MARK +201A ; Quotation_Mark # Ps SINGLE LOW-9 QUOTATION MARK +201B..201C ; Quotation_Mark # Pi [2] SINGLE HIGH-REVERSED-9 QUOTATION MARK..LEFT DOUBLE QUOTATION MARK +201D ; Quotation_Mark # Pf RIGHT DOUBLE QUOTATION MARK +201E ; Quotation_Mark # Ps DOUBLE LOW-9 QUOTATION MARK +201F ; Quotation_Mark # Pi DOUBLE HIGH-REVERSED-9 QUOTATION MARK +2039 ; Quotation_Mark # Pi SINGLE LEFT-POINTING ANGLE QUOTATION MARK +203A ; Quotation_Mark # Pf SINGLE RIGHT-POINTING ANGLE QUOTATION MARK +300C ; Quotation_Mark # Ps LEFT CORNER BRACKET +300D ; Quotation_Mark # Pe RIGHT CORNER BRACKET +300E ; Quotation_Mark # Ps LEFT WHITE CORNER BRACKET +300F ; Quotation_Mark # Pe RIGHT WHITE CORNER BRACKET +301D ; Quotation_Mark # Ps REVERSED DOUBLE PRIME QUOTATION MARK +301E..301F ; Quotation_Mark # Pe [2] DOUBLE PRIME QUOTATION MARK..LOW DOUBLE PRIME QUOTATION MARK +FE41 ; Quotation_Mark # Ps PRESENTATION FORM FOR VERTICAL LEFT CORNER BRACKET +FE42 ; Quotation_Mark # Pe PRESENTATION FORM FOR VERTICAL RIGHT CORNER BRACKET +FE43 ; Quotation_Mark # Ps PRESENTATION FORM FOR VERTICAL LEFT WHITE CORNER BRACKET +FE44 ; Quotation_Mark # Pe PRESENTATION FORM FOR VERTICAL RIGHT WHITE CORNER BRACKET +FF02 ; Quotation_Mark # Po FULLWIDTH QUOTATION MARK +FF07 ; Quotation_Mark # Po FULLWIDTH APOSTROPHE +FF62 ; Quotation_Mark # Ps HALFWIDTH LEFT CORNER BRACKET +FF63 ; Quotation_Mark # Pe HALFWIDTH RIGHT CORNER BRACKET # Total code points: 29 # ================================================ -0021 ; Terminal_Punctuation # Po EXCLAMATION MARK -002C ; Terminal_Punctuation # Po COMMA -002E ; Terminal_Punctuation # Po FULL STOP -003A..003B; Terminal_Punctuation # Po [2] COLON..SEMICOLON -003F ; Terminal_Punctuation # Po QUESTION MARK -037E ; Terminal_Punctuation # Po GREEK QUESTION MARK -0387 ; Terminal_Punctuation # Po GREEK ANO TELEIA -0589 ; Terminal_Punctuation # Po ARMENIAN FULL STOP -060C ; Terminal_Punctuation # Po ARABIC COMMA -061B ; Terminal_Punctuation # Po ARABIC SEMICOLON -061F ; Terminal_Punctuation # Po ARABIC QUESTION MARK -06D4 ; Terminal_Punctuation # Po ARABIC FULL STOP -0700..070A; Terminal_Punctuation # Po [11] SYRIAC END OF PARAGRAPH..SYRIAC CONTRACTION -070C ; Terminal_Punctuation # Po SYRIAC HARKLEAN METOBELUS -0964..0965; Terminal_Punctuation # Po [2] DEVANAGARI DANDA..DEVANAGARI DOUBLE DANDA -0E5A..0E5B; Terminal_Punctuation # Po [2] THAI CHARACTER ANGKHANKHU..THAI CHARACTER KHOMUT -104A..104B; Terminal_Punctuation # Po [2] MYANMAR SIGN LITTLE SECTION..MYANMAR SIGN SECTION -1361..1368; Terminal_Punctuation # Po [8] ETHIOPIC WORDSPACE..ETHIOPIC PARAGRAPH SEPARATOR -166D..166E; Terminal_Punctuation # Po [2] CANADIAN SYLLABICS CHI SIGN..CANADIAN SYLLABICS FULL STOP -16EB..16ED; Terminal_Punctuation # Po [3] RUNIC SINGLE PUNCTUATION..RUNIC CROSS PUNCTUATION -17D4..17D6; Terminal_Punctuation # Po [3] KHMER SIGN KHAN..KHMER SIGN CAMNUC PII KUUH -17DA ; Terminal_Punctuation # Po KHMER SIGN KOOMUUT -1802..1805; Terminal_Punctuation # Po [4] MONGOLIAN COMMA..MONGOLIAN FOUR DOTS -1808..1809; Terminal_Punctuation # Po [2] MONGOLIAN MANCHU COMMA..MONGOLIAN MANCHU FULL STOP -203C..203D; Terminal_Punctuation # Po [2] DOUBLE EXCLAMATION MARK..INTERROBANG -2048..2049; Terminal_Punctuation # Po [2] QUESTION EXCLAMATION MARK..EXCLAMATION QUESTION MARK -3001..3002; Terminal_Punctuation # Po [2] IDEOGRAPHIC COMMA..IDEOGRAPHIC FULL STOP -FE50..FE52; Terminal_Punctuation # Po [3] SMALL COMMA..SMALL FULL STOP -FE54..FE57; Terminal_Punctuation # Po [4] SMALL SEMICOLON..SMALL EXCLAMATION MARK -FF01 ; Terminal_Punctuation # Po FULLWIDTH EXCLAMATION MARK -FF0C ; Terminal_Punctuation # Po FULLWIDTH COMMA -FF0E ; Terminal_Punctuation # Po FULLWIDTH FULL STOP -FF1A..FF1B; Terminal_Punctuation # Po [2] FULLWIDTH COLON..FULLWIDTH SEMICOLON -FF1F ; Terminal_Punctuation # Po FULLWIDTH QUESTION MARK -FF61 ; Terminal_Punctuation # Po HALFWIDTH IDEOGRAPHIC FULL STOP -FF64 ; Terminal_Punctuation # Po HALFWIDTH IDEOGRAPHIC COMMA +0021 ; Terminal_Punctuation # Po EXCLAMATION MARK +002C ; Terminal_Punctuation # Po COMMA +002E ; Terminal_Punctuation # Po FULL STOP +003A..003B ; Terminal_Punctuation # Po [2] COLON..SEMICOLON +003F ; Terminal_Punctuation # Po QUESTION MARK +037E ; Terminal_Punctuation # Po GREEK QUESTION MARK +0387 ; Terminal_Punctuation # Po GREEK ANO TELEIA +0589 ; Terminal_Punctuation # Po ARMENIAN FULL STOP +060C ; Terminal_Punctuation # Po ARABIC COMMA +061B ; Terminal_Punctuation # Po ARABIC SEMICOLON +061F ; Terminal_Punctuation # Po ARABIC QUESTION MARK +06D4 ; Terminal_Punctuation # Po ARABIC FULL STOP +0700..070A ; Terminal_Punctuation # Po [11] SYRIAC END OF PARAGRAPH..SYRIAC CONTRACTION +070C ; Terminal_Punctuation # Po SYRIAC HARKLEAN METOBELUS +0964..0965 ; Terminal_Punctuation # Po [2] DEVANAGARI DANDA..DEVANAGARI DOUBLE DANDA +0E5A..0E5B ; Terminal_Punctuation # Po [2] THAI CHARACTER ANGKHANKHU..THAI CHARACTER KHOMUT +104A..104B ; Terminal_Punctuation # Po [2] MYANMAR SIGN LITTLE SECTION..MYANMAR SIGN SECTION +1361..1368 ; Terminal_Punctuation # Po [8] ETHIOPIC WORDSPACE..ETHIOPIC PARAGRAPH SEPARATOR +166D..166E ; Terminal_Punctuation # Po [2] CANADIAN SYLLABICS CHI SIGN..CANADIAN SYLLABICS FULL STOP +16EB..16ED ; Terminal_Punctuation # Po [3] RUNIC SINGLE PUNCTUATION..RUNIC CROSS PUNCTUATION +17D4..17D6 ; Terminal_Punctuation # Po [3] KHMER SIGN KHAN..KHMER SIGN CAMNUC PII KUUH +17DA ; Terminal_Punctuation # Po KHMER SIGN KOOMUUT +1802..1805 ; Terminal_Punctuation # Po [4] MONGOLIAN COMMA..MONGOLIAN FOUR DOTS +1808..1809 ; Terminal_Punctuation # Po [2] MONGOLIAN MANCHU COMMA..MONGOLIAN MANCHU FULL STOP +203C..203D ; Terminal_Punctuation # Po [2] DOUBLE EXCLAMATION MARK..INTERROBANG +2048..2049 ; Terminal_Punctuation # Po [2] QUESTION EXCLAMATION MARK..EXCLAMATION QUESTION MARK +3001..3002 ; Terminal_Punctuation # Po [2] IDEOGRAPHIC COMMA..IDEOGRAPHIC FULL STOP +FE50..FE52 ; Terminal_Punctuation # Po [3] SMALL COMMA..SMALL FULL STOP +FE54..FE57 ; Terminal_Punctuation # Po [4] SMALL SEMICOLON..SMALL EXCLAMATION MARK +FF01 ; Terminal_Punctuation # Po FULLWIDTH EXCLAMATION MARK +FF0C ; Terminal_Punctuation # Po FULLWIDTH COMMA +FF0E ; Terminal_Punctuation # Po FULLWIDTH FULL STOP +FF1A..FF1B ; Terminal_Punctuation # Po [2] FULLWIDTH COLON..FULLWIDTH SEMICOLON +FF1F ; Terminal_Punctuation # Po FULLWIDTH QUESTION MARK +FF61 ; Terminal_Punctuation # Po HALFWIDTH IDEOGRAPHIC FULL STOP +FF64 ; Terminal_Punctuation # Po HALFWIDTH IDEOGRAPHIC COMMA # Total code points: 75 # ================================================ -0028 ; Other_Math # Ps LEFT PARENTHESIS -0029 ; Other_Math # Pe RIGHT PARENTHESIS -002A ; Other_Math # Po ASTERISK -002D ; Other_Math # Pd HYPHEN-MINUS -002F ; Other_Math # Po SOLIDUS -005B ; Other_Math # Ps LEFT SQUARE BRACKET -005C ; Other_Math # Po REVERSE SOLIDUS -005D ; Other_Math # Pe RIGHT SQUARE BRACKET -005E ; Other_Math # Sk CIRCUMFLEX ACCENT -007B ; Other_Math # Ps LEFT CURLY BRACKET -007D ; Other_Math # Pe RIGHT CURLY BRACKET -2016 ; Other_Math # Po DOUBLE VERTICAL LINE -2032..2034; Other_Math # Po [3] PRIME..TRIPLE PRIME -207D ; Other_Math # Ps SUPERSCRIPT LEFT PARENTHESIS -207E ; Other_Math # Pe SUPERSCRIPT RIGHT PARENTHESIS -208D ; Other_Math # Ps SUBSCRIPT LEFT PARENTHESIS -208E ; Other_Math # Pe SUBSCRIPT RIGHT PARENTHESIS -20D0..20DC; Other_Math # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE -20E1 ; Other_Math # Mn COMBINING LEFT RIGHT ARROW ABOVE -2102 ; Other_Math # L& DOUBLE-STRUCK CAPITAL C -210A..2113; Other_Math # L& [10] SCRIPT SMALL G..SCRIPT SMALL L -2115 ; Other_Math # L& DOUBLE-STRUCK CAPITAL N -2119..211D; Other_Math # L& [5] DOUBLE-STRUCK CAPITAL P..DOUBLE-STRUCK CAPITAL R -2124 ; Other_Math # L& DOUBLE-STRUCK CAPITAL Z -2128 ; Other_Math # L& BLACK-LETTER CAPITAL Z -212C..212D; Other_Math # L& [2] SCRIPT CAPITAL B..BLACK-LETTER CAPITAL C -212F..2131; Other_Math # L& [3] SCRIPT SMALL E..SCRIPT CAPITAL F -2133..2134; Other_Math # L& [2] SCRIPT CAPITAL M..SCRIPT SMALL O -2135..2138; Other_Math # Lo [4] ALEF SYMBOL..DALET SYMBOL -2329 ; Other_Math # Ps LEFT-POINTING ANGLE BRACKET -232A ; Other_Math # Pe RIGHT-POINTING ANGLE BRACKET -300A ; Other_Math # Ps LEFT DOUBLE ANGLE BRACKET -300B ; Other_Math # Pe RIGHT DOUBLE ANGLE BRACKET -301A ; Other_Math # Ps LEFT WHITE SQUARE BRACKET -301B ; Other_Math # Pe RIGHT WHITE SQUARE BRACKET -FE35 ; Other_Math # Ps PRESENTATION FORM FOR VERTICAL LEFT PARENTHESIS -FE36 ; Other_Math # Pe PRESENTATION FORM FOR VERTICAL RIGHT PARENTHESIS -FE37 ; Other_Math # Ps PRESENTATION FORM FOR VERTICAL LEFT CURLY BRACKET -FE38 ; Other_Math # Pe PRESENTATION FORM FOR VERTICAL RIGHT CURLY BRACKET -FE59 ; Other_Math # Ps SMALL LEFT PARENTHESIS -FE5A ; Other_Math # Pe SMALL RIGHT PARENTHESIS -FE5B ; Other_Math # Ps SMALL LEFT CURLY BRACKET -FE5C ; Other_Math # Pe SMALL RIGHT CURLY BRACKET -FE61 ; Other_Math # Po SMALL ASTERISK -FE63 ; Other_Math # Pd SMALL HYPHEN-MINUS -FE68 ; Other_Math # Po SMALL REVERSE SOLIDUS -FF08 ; Other_Math # Ps FULLWIDTH LEFT PARENTHESIS -FF09 ; Other_Math # Pe FULLWIDTH RIGHT PARENTHESIS -FF0A ; Other_Math # Po FULLWIDTH ASTERISK -FF0D ; Other_Math # Pd FULLWIDTH HYPHEN-MINUS -FF0F ; Other_Math # Po FULLWIDTH SOLIDUS -FF3B ; Other_Math # Ps FULLWIDTH LEFT SQUARE BRACKET -FF3C ; Other_Math # Po FULLWIDTH REVERSE SOLIDUS -FF3D ; Other_Math # Pe FULLWIDTH RIGHT SQUARE BRACKET -FF3E ; Other_Math # Sk FULLWIDTH CIRCUMFLEX ACCENT -FF5B ; Other_Math # Ps FULLWIDTH LEFT CURLY BRACKET -FF5D ; Other_Math # Pe FULLWIDTH RIGHT CURLY BRACKET -1D400..1D454; Other_Math # L& [85] MATHEMATICAL BOLD CAPITAL A..MATHEMATICAL ITALIC SMALL G -1D456..1D49C; Other_Math # L& [71] MATHEMATICAL ITALIC SMALL I..MATHEMATICAL SCRIPT CAPITAL A -1D49E..1D49F; Other_Math # L& [2] MATHEMATICAL SCRIPT CAPITAL C..MATHEMATICAL SCRIPT CAPITAL D -1D4A2 ; Other_Math # L& MATHEMATICAL SCRIPT CAPITAL G -1D4A5..1D4A6; Other_Math # L& [2] MATHEMATICAL SCRIPT CAPITAL J..MATHEMATICAL SCRIPT CAPITAL K -1D4A9..1D4AC; Other_Math # L& [4] MATHEMATICAL SCRIPT CAPITAL N..MATHEMATICAL SCRIPT CAPITAL Q -1D4AE..1D4B9; Other_Math # L& [12] MATHEMATICAL SCRIPT CAPITAL S..MATHEMATICAL SCRIPT SMALL D -1D4BB ; Other_Math # L& MATHEMATICAL SCRIPT SMALL F -1D4BD..1D4C0; Other_Math # L& [4] MATHEMATICAL SCRIPT SMALL H..MATHEMATICAL SCRIPT SMALL K -1D4C2..1D4C3; Other_Math # L& [2] MATHEMATICAL SCRIPT SMALL M..MATHEMATICAL SCRIPT SMALL N -1D4C5..1D505; Other_Math # L& [65] MATHEMATICAL SCRIPT SMALL P..MATHEMATICAL FRAKTUR CAPITAL B -1D507..1D50A; Other_Math # L& [4] MATHEMATICAL FRAKTUR CAPITAL D..MATHEMATICAL FRAKTUR CAPITAL G -1D50D..1D514; Other_Math # L& [8] MATHEMATICAL FRAKTUR CAPITAL J..MATHEMATICAL FRAKTUR CAPITAL Q -1D516..1D51C; Other_Math # L& [7] MATHEMATICAL FRAKTUR CAPITAL S..MATHEMATICAL FRAKTUR CAPITAL Y -1D51E..1D539; Other_Math # L& [28] MATHEMATICAL FRAKTUR SMALL A..MATHEMATICAL DOUBLE-STRUCK CAPITAL B -1D53B..1D53E; Other_Math # L& [4] MATHEMATICAL DOUBLE-STRUCK CAPITAL D..MATHEMATICAL DOUBLE-STRUCK CAPITAL G -1D540..1D544; Other_Math # L& [5] MATHEMATICAL DOUBLE-STRUCK CAPITAL I..MATHEMATICAL DOUBLE-STRUCK CAPITAL M -1D546 ; Other_Math # L& MATHEMATICAL DOUBLE-STRUCK CAPITAL O -1D54A..1D550; Other_Math # L& [7] MATHEMATICAL DOUBLE-STRUCK CAPITAL S..MATHEMATICAL DOUBLE-STRUCK CAPITAL Y -1D552..1D6A3; Other_Math # L& [338] MATHEMATICAL DOUBLE-STRUCK SMALL A..MATHEMATICAL MONOSPACE SMALL Z -1D6A8..1D7C9; Other_Math # L& [290] MATHEMATICAL BOLD CAPITAL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC PI SYMBOL -1D7CE..1D7FF; Other_Math # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE - -# Total code points: 1082 +0028 ; Other_Math # Ps LEFT PARENTHESIS +0029 ; Other_Math # Pe RIGHT PARENTHESIS +002A ; Other_Math # Po ASTERISK +002D ; Other_Math # Pd HYPHEN-MINUS +002F ; Other_Math # Po SOLIDUS +005B ; Other_Math # Ps LEFT SQUARE BRACKET +005C ; Other_Math # Po REVERSE SOLIDUS +005D ; Other_Math # Pe RIGHT SQUARE BRACKET +005E ; Other_Math # Sk CIRCUMFLEX ACCENT +007B ; Other_Math # Ps LEFT CURLY BRACKET +007D ; Other_Math # Pe RIGHT CURLY BRACKET +2016 ; Other_Math # Po DOUBLE VERTICAL LINE +2032..2034 ; Other_Math # Po [3] PRIME..TRIPLE PRIME +207D ; Other_Math # Ps SUPERSCRIPT LEFT PARENTHESIS +207E ; Other_Math # Pe SUPERSCRIPT RIGHT PARENTHESIS +208D ; Other_Math # Ps SUBSCRIPT LEFT PARENTHESIS +208E ; Other_Math # Pe SUBSCRIPT RIGHT PARENTHESIS +20D0..20DC ; Other_Math # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE +20E1 ; Other_Math # Mn COMBINING LEFT RIGHT ARROW ABOVE +2102 ; Other_Math # L& DOUBLE-STRUCK CAPITAL C +210A..2113 ; Other_Math # L& [10] SCRIPT SMALL G..SCRIPT SMALL L +2115 ; Other_Math # L& DOUBLE-STRUCK CAPITAL N +2119..211D ; Other_Math # L& [5] DOUBLE-STRUCK CAPITAL P..DOUBLE-STRUCK CAPITAL R +2124 ; Other_Math # L& DOUBLE-STRUCK CAPITAL Z +2128 ; Other_Math # L& BLACK-LETTER CAPITAL Z +212C..212D ; Other_Math # L& [2] SCRIPT CAPITAL B..BLACK-LETTER CAPITAL C +212F..2131 ; Other_Math # L& [3] SCRIPT SMALL E..SCRIPT CAPITAL F +2133..2134 ; Other_Math # L& [2] SCRIPT CAPITAL M..SCRIPT SMALL O +2135..2138 ; Other_Math # Lo [4] ALEF SYMBOL..DALET SYMBOL +2329 ; Other_Math # Ps LEFT-POINTING ANGLE BRACKET +232A ; Other_Math # Pe RIGHT-POINTING ANGLE BRACKET +300A ; Other_Math # Ps LEFT DOUBLE ANGLE BRACKET +300B ; Other_Math # Pe RIGHT DOUBLE ANGLE BRACKET +301A ; Other_Math # Ps LEFT WHITE SQUARE BRACKET +301B ; Other_Math # Pe RIGHT WHITE SQUARE BRACKET +FE35 ; Other_Math # Ps PRESENTATION FORM FOR VERTICAL LEFT PARENTHESIS +FE36 ; Other_Math # Pe PRESENTATION FORM FOR VERTICAL RIGHT PARENTHESIS +FE37 ; Other_Math # Ps PRESENTATION FORM FOR VERTICAL LEFT CURLY BRACKET +FE38 ; Other_Math # Pe PRESENTATION FORM FOR VERTICAL RIGHT CURLY BRACKET +FE59 ; Other_Math # Ps SMALL LEFT PARENTHESIS +FE5A ; Other_Math # Pe SMALL RIGHT PARENTHESIS +FE5B ; Other_Math # Ps SMALL LEFT CURLY BRACKET +FE5C ; Other_Math # Pe SMALL RIGHT CURLY BRACKET +FE61 ; Other_Math # Po SMALL ASTERISK +FE63 ; Other_Math # Pd SMALL HYPHEN-MINUS +FE68 ; Other_Math # Po SMALL REVERSE SOLIDUS +FF08 ; Other_Math # Ps FULLWIDTH LEFT PARENTHESIS +FF09 ; Other_Math # Pe FULLWIDTH RIGHT PARENTHESIS +FF0A ; Other_Math # Po FULLWIDTH ASTERISK +FF0D ; Other_Math # Pd FULLWIDTH HYPHEN-MINUS +FF0F ; Other_Math # Po FULLWIDTH SOLIDUS +FF3B ; Other_Math # Ps FULLWIDTH LEFT SQUARE BRACKET +FF3C ; Other_Math # Po FULLWIDTH REVERSE SOLIDUS +FF3D ; Other_Math # Pe FULLWIDTH RIGHT SQUARE BRACKET +FF3E ; Other_Math # Sk FULLWIDTH CIRCUMFLEX ACCENT +FF5B ; Other_Math # Ps FULLWIDTH LEFT CURLY BRACKET +FF5D ; Other_Math # Pe FULLWIDTH RIGHT CURLY BRACKET +1D400..1D454 ; Other_Math # L& [85] MATHEMATICAL BOLD CAPITAL A..MATHEMATICAL ITALIC SMALL G +1D456..1D49C ; Other_Math # L& [71] MATHEMATICAL ITALIC SMALL I..MATHEMATICAL SCRIPT CAPITAL A +1D49E..1D49F ; Other_Math # L& [2] MATHEMATICAL SCRIPT CAPITAL C..MATHEMATICAL SCRIPT CAPITAL D +1D4A2 ; Other_Math # L& MATHEMATICAL SCRIPT CAPITAL G +1D4A5..1D4A6 ; Other_Math # L& [2] MATHEMATICAL SCRIPT CAPITAL J..MATHEMATICAL SCRIPT CAPITAL K +1D4A9..1D4AC ; Other_Math # L& [4] MATHEMATICAL SCRIPT CAPITAL N..MATHEMATICAL SCRIPT CAPITAL Q +1D4AE..1D4B9 ; Other_Math # L& [12] MATHEMATICAL SCRIPT CAPITAL S..MATHEMATICAL SCRIPT SMALL D +1D4BB ; Other_Math # L& MATHEMATICAL SCRIPT SMALL F +1D4BD..1D4C0 ; Other_Math # L& [4] MATHEMATICAL SCRIPT SMALL H..MATHEMATICAL SCRIPT SMALL K +1D4C2..1D4C3 ; Other_Math # L& [2] MATHEMATICAL SCRIPT SMALL M..MATHEMATICAL SCRIPT SMALL N +1D4C5..1D505 ; Other_Math # L& [65] MATHEMATICAL SCRIPT SMALL P..MATHEMATICAL FRAKTUR CAPITAL B +1D507..1D50A ; Other_Math # L& [4] MATHEMATICAL FRAKTUR CAPITAL D..MATHEMATICAL FRAKTUR CAPITAL G +1D50D..1D514 ; Other_Math # L& [8] MATHEMATICAL FRAKTUR CAPITAL J..MATHEMATICAL FRAKTUR CAPITAL Q +1D516..1D51C ; Other_Math # L& [7] MATHEMATICAL FRAKTUR CAPITAL S..MATHEMATICAL FRAKTUR CAPITAL Y +1D51E..1D539 ; Other_Math # L& [28] MATHEMATICAL FRAKTUR SMALL A..MATHEMATICAL DOUBLE-STRUCK CAPITAL B +1D53B..1D53E ; Other_Math # L& [4] MATHEMATICAL DOUBLE-STRUCK CAPITAL D..MATHEMATICAL DOUBLE-STRUCK CAPITAL G +1D540..1D544 ; Other_Math # L& [5] MATHEMATICAL DOUBLE-STRUCK CAPITAL I..MATHEMATICAL DOUBLE-STRUCK CAPITAL M +1D546 ; Other_Math # L& MATHEMATICAL DOUBLE-STRUCK CAPITAL O +1D54A..1D550 ; Other_Math # L& [7] MATHEMATICAL DOUBLE-STRUCK CAPITAL S..MATHEMATICAL DOUBLE-STRUCK CAPITAL Y +1D552..1D6A3 ; Other_Math # L& [338] MATHEMATICAL DOUBLE-STRUCK SMALL A..MATHEMATICAL MONOSPACE SMALL Z +1D6A8..1D6C0 ; Other_Math # L& [25] MATHEMATICAL BOLD CAPITAL ALPHA..MATHEMATICAL BOLD CAPITAL OMEGA +1D6C2..1D6DA ; Other_Math # L& [25] MATHEMATICAL BOLD SMALL ALPHA..MATHEMATICAL BOLD SMALL OMEGA +1D6DC..1D6FA ; Other_Math # L& [31] MATHEMATICAL BOLD EPSILON SYMBOL..MATHEMATICAL ITALIC CAPITAL OMEGA +1D6FC..1D714 ; Other_Math # L& [25] MATHEMATICAL ITALIC SMALL ALPHA..MATHEMATICAL ITALIC SMALL OMEGA +1D716..1D734 ; Other_Math # L& [31] MATHEMATICAL ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD ITALIC CAPITAL OMEGA +1D736..1D74E ; Other_Math # L& [25] MATHEMATICAL BOLD ITALIC SMALL ALPHA..MATHEMATICAL BOLD ITALIC SMALL OMEGA +1D750..1D76E ; Other_Math # L& [31] MATHEMATICAL BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD CAPITAL OMEGA +1D770..1D788 ; Other_Math # L& [25] MATHEMATICAL SANS-SERIF BOLD SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD SMALL OMEGA +1D78A..1D7A8 ; Other_Math # L& [31] MATHEMATICAL SANS-SERIF BOLD EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL OMEGA +1D7AA..1D7C2 ; Other_Math # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA +1D7C4..1D7C9 ; Other_Math # L& [6] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC PI SYMBOL +1D7CE..1D7FF ; Other_Math # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE + +# Total code points: 1072 # ================================================ -0030..0039; Hex_Digit # Nd [10] DIGIT ZERO..DIGIT NINE -0041..0046; Hex_Digit # L& [6] LATIN CAPITAL LETTER A..LATIN CAPITAL LETTER F -0061..0066; Hex_Digit # L& [6] LATIN SMALL LETTER A..LATIN SMALL LETTER F -FF10..FF19; Hex_Digit # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE -FF21..FF26; Hex_Digit # L& [6] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER F -FF41..FF46; Hex_Digit # L& [6] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER F -1D7CE..1D7FF; Hex_Digit # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE +0030..0039 ; Hex_Digit # Nd [10] DIGIT ZERO..DIGIT NINE +0041..0046 ; Hex_Digit # L& [6] LATIN CAPITAL LETTER A..LATIN CAPITAL LETTER F +0061..0066 ; Hex_Digit # L& [6] LATIN SMALL LETTER A..LATIN SMALL LETTER F +FF10..FF19 ; Hex_Digit # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE +FF21..FF26 ; Hex_Digit # L& [6] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER F +FF41..FF46 ; Hex_Digit # L& [6] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER F +1D7CE..1D7FF ; Hex_Digit # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE # Total code points: 94 # ================================================ -0345 ; Other_Alphabetic # Mn COMBINING GREEK YPOGEGRAMMENI -05B0..05B9; Other_Alphabetic # Mn [10] HEBREW POINT SHEVA..HEBREW POINT HOLAM -05BB..05BD; Other_Alphabetic # Mn [3] HEBREW POINT QUBUTS..HEBREW POINT METEG -05BF ; Other_Alphabetic # Mn HEBREW POINT RAFE -05C1..05C2; Other_Alphabetic # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT -05C4 ; Other_Alphabetic # Mn HEBREW MARK UPPER DOT -064B..0655; Other_Alphabetic # Mn [11] ARABIC FATHATAN..ARABIC HAMZA BELOW -0670 ; Other_Alphabetic # Mn ARABIC LETTER SUPERSCRIPT ALEF -06D6..06DC; Other_Alphabetic # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN -06E1..06E4; Other_Alphabetic # Mn [4] ARABIC SMALL HIGH DOTLESS HEAD OF KHAH..ARABIC SMALL HIGH MADDA -06E7..06E8; Other_Alphabetic # Mn [2] ARABIC SMALL HIGH YEH..ARABIC SMALL HIGH NOON -06ED ; Other_Alphabetic # Mn ARABIC SMALL LOW MEEM -0711 ; Other_Alphabetic # Mn SYRIAC LETTER SUPERSCRIPT ALAPH -0730..073F; Other_Alphabetic # Mn [16] SYRIAC PTHAHA ABOVE..SYRIAC RWAHA -07A6..07B0; Other_Alphabetic # Mn [11] THAANA ABAFILI..THAANA SUKUN -0901..0902; Other_Alphabetic # Mn [2] DEVANAGARI SIGN CANDRABINDU..DEVANAGARI SIGN ANUSVARA -0903 ; Other_Alphabetic # Mc DEVANAGARI SIGN VISARGA -093E..0940; Other_Alphabetic # Mc [3] DEVANAGARI VOWEL SIGN AA..DEVANAGARI VOWEL SIGN II -0941..0948; Other_Alphabetic # Mn [8] DEVANAGARI VOWEL SIGN U..DEVANAGARI VOWEL SIGN AI -0949..094C; Other_Alphabetic # Mc [4] DEVANAGARI VOWEL SIGN CANDRA O..DEVANAGARI VOWEL SIGN AU -0962..0963; Other_Alphabetic # Mn [2] DEVANAGARI VOWEL SIGN VOCALIC L..DEVANAGARI VOWEL SIGN VOCALIC LL -0981 ; Other_Alphabetic # Mn BENGALI SIGN CANDRABINDU -0982..0983; Other_Alphabetic # Mc [2] BENGALI SIGN ANUSVARA..BENGALI SIGN VISARGA -09BE..09C0; Other_Alphabetic # Mc [3] BENGALI VOWEL SIGN AA..BENGALI VOWEL SIGN II -09C1..09C4; Other_Alphabetic # Mn [4] BENGALI VOWEL SIGN U..BENGALI VOWEL SIGN VOCALIC RR -09C7..09C8; Other_Alphabetic # Mc [2] BENGALI VOWEL SIGN E..BENGALI VOWEL SIGN AI -09CB..09CC; Other_Alphabetic # Mc [2] BENGALI VOWEL SIGN O..BENGALI VOWEL SIGN AU -09D7 ; Other_Alphabetic # Mc BENGALI AU LENGTH MARK -09E2..09E3; Other_Alphabetic # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL -0A02 ; Other_Alphabetic # Mn GURMUKHI SIGN BINDI -0A3E..0A40; Other_Alphabetic # Mc [3] GURMUKHI VOWEL SIGN AA..GURMUKHI VOWEL SIGN II -0A41..0A42; Other_Alphabetic # Mn [2] GURMUKHI VOWEL SIGN U..GURMUKHI VOWEL SIGN UU -0A47..0A48; Other_Alphabetic # Mn [2] GURMUKHI VOWEL SIGN EE..GURMUKHI VOWEL SIGN AI -0A4B..0A4C; Other_Alphabetic # Mn [2] GURMUKHI VOWEL SIGN OO..GURMUKHI VOWEL SIGN AU -0A70..0A71; Other_Alphabetic # Mn [2] GURMUKHI TIPPI..GURMUKHI ADDAK -0A81..0A82; Other_Alphabetic # Mn [2] GUJARATI SIGN CANDRABINDU..GUJARATI SIGN ANUSVARA -0A83 ; Other_Alphabetic # Mc GUJARATI SIGN VISARGA -0ABE..0AC0; Other_Alphabetic # Mc [3] GUJARATI VOWEL SIGN AA..GUJARATI VOWEL SIGN II -0AC1..0AC5; Other_Alphabetic # Mn [5] GUJARATI VOWEL SIGN U..GUJARATI VOWEL SIGN CANDRA E -0AC7..0AC8; Other_Alphabetic # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI -0AC9 ; Other_Alphabetic # Mc GUJARATI VOWEL SIGN CANDRA O -0ACB..0ACC; Other_Alphabetic # Mc [2] GUJARATI VOWEL SIGN O..GUJARATI VOWEL SIGN AU -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 -0B3F ; Other_Alphabetic # Mn ORIYA VOWEL SIGN I -0B40 ; Other_Alphabetic # Mc ORIYA VOWEL SIGN II -0B41..0B43; Other_Alphabetic # Mn [3] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC R -0B47..0B48; Other_Alphabetic # Mc [2] ORIYA VOWEL SIGN E..ORIYA VOWEL SIGN AI -0B4B..0B4C; Other_Alphabetic # Mc [2] ORIYA VOWEL SIGN O..ORIYA VOWEL SIGN AU -0B56 ; Other_Alphabetic # Mn ORIYA AI LENGTH MARK -0B57 ; Other_Alphabetic # Mc ORIYA AU LENGTH MARK -0B82 ; Other_Alphabetic # Mn TAMIL SIGN ANUSVARA -0B83 ; Other_Alphabetic # Mc TAMIL SIGN VISARGA -0BBE..0BBF; Other_Alphabetic # Mc [2] TAMIL VOWEL SIGN AA..TAMIL VOWEL SIGN I -0BC0 ; Other_Alphabetic # Mn TAMIL VOWEL SIGN II -0BC1..0BC2; Other_Alphabetic # Mc [2] TAMIL VOWEL SIGN U..TAMIL VOWEL SIGN UU -0BC6..0BC8; Other_Alphabetic # Mc [3] TAMIL VOWEL SIGN E..TAMIL VOWEL SIGN AI -0BCA..0BCC; Other_Alphabetic # Mc [3] TAMIL VOWEL SIGN O..TAMIL VOWEL SIGN AU -0BD7 ; Other_Alphabetic # Mc TAMIL AU LENGTH MARK -0C01..0C03; Other_Alphabetic # Mc [3] TELUGU SIGN CANDRABINDU..TELUGU SIGN VISARGA -0C3E..0C40; Other_Alphabetic # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II -0C41..0C44; Other_Alphabetic # Mc [4] TELUGU VOWEL SIGN U..TELUGU VOWEL SIGN VOCALIC RR -0C46..0C48; Other_Alphabetic # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI -0C4A..0C4C; Other_Alphabetic # Mn [3] TELUGU VOWEL SIGN O..TELUGU VOWEL SIGN AU -0C55..0C56; Other_Alphabetic # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK -0C82..0C83; Other_Alphabetic # Mc [2] KANNADA SIGN ANUSVARA..KANNADA SIGN VISARGA -0CBE ; Other_Alphabetic # Mc KANNADA VOWEL SIGN AA -0CBF ; Other_Alphabetic # Mn KANNADA VOWEL SIGN I -0CC0..0CC4; Other_Alphabetic # Mc [5] KANNADA VOWEL SIGN II..KANNADA VOWEL SIGN VOCALIC RR -0CC6 ; Other_Alphabetic # Mn KANNADA VOWEL SIGN E -0CC7..0CC8; Other_Alphabetic # Mc [2] KANNADA VOWEL SIGN EE..KANNADA VOWEL SIGN AI -0CCA..0CCB; Other_Alphabetic # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO -0CCC ; Other_Alphabetic # Mn KANNADA VOWEL SIGN AU -0CD5..0CD6; Other_Alphabetic # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK -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..0D43; Other_Alphabetic # Mn [3] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC R -0D46..0D48; Other_Alphabetic # Mc [3] MALAYALAM VOWEL SIGN E..MALAYALAM VOWEL SIGN AI -0D4A..0D4C; Other_Alphabetic # Mc [3] MALAYALAM VOWEL SIGN O..MALAYALAM VOWEL SIGN AU -0D57 ; Other_Alphabetic # Mc MALAYALAM AU LENGTH MARK -0D82..0D83; Other_Alphabetic # Mc [2] SINHALA SIGN ANUSVARAYA..SINHALA SIGN VISARGAYA -0DCF..0DD1; Other_Alphabetic # Mc [3] SINHALA VOWEL SIGN AELA-PILLA..SINHALA VOWEL SIGN DIGA AEDA-PILLA -0DD2..0DD4; Other_Alphabetic # Mn [3] SINHALA VOWEL SIGN KETTI IS-PILLA..SINHALA VOWEL SIGN KETTI PAA-PILLA -0DD6 ; Other_Alphabetic # Mn SINHALA VOWEL SIGN DIGA PAA-PILLA -0DD8..0DDF; Other_Alphabetic # Mc [8] SINHALA VOWEL SIGN GAETTA-PILLA..SINHALA VOWEL SIGN GAYANUKITTA -0DF2..0DF3; Other_Alphabetic # Mc [2] SINHALA VOWEL SIGN DIGA GAETTA-PILLA..SINHALA VOWEL SIGN DIGA GAYANUKITTA -0E31 ; Other_Alphabetic # Mn THAI CHARACTER MAI HAN-AKAT -0E34..0E3A; Other_Alphabetic # Mn [7] THAI CHARACTER SARA I..THAI CHARACTER PHINTHU -0E4D ; Other_Alphabetic # Mn THAI CHARACTER NIKHAHIT -0EB1 ; Other_Alphabetic # Mn LAO VOWEL SIGN MAI KAN -0EB4..0EB9; Other_Alphabetic # Mn [6] LAO VOWEL SIGN I..LAO VOWEL SIGN UU -0EBB..0EBC; Other_Alphabetic # Mn [2] LAO VOWEL SIGN MAI KON..LAO SEMIVOWEL SIGN LO -0ECD ; Other_Alphabetic # Mn LAO NIGGAHITA -0F71..0F7E; Other_Alphabetic # Mn [14] TIBETAN VOWEL SIGN AA..TIBETAN SIGN RJES SU NGA RO -0F7F ; Other_Alphabetic # Mc TIBETAN SIGN RNAM BCAD -0F80..0F81; Other_Alphabetic # Mn [2] TIBETAN VOWEL SIGN REVERSED I..TIBETAN VOWEL SIGN REVERSED II -0F90..0F97; Other_Alphabetic # Mn [8] TIBETAN SUBJOINED LETTER KA..TIBETAN SUBJOINED LETTER JA -0F99..0FBC; Other_Alphabetic # Mn [36] TIBETAN SUBJOINED LETTER NYA..TIBETAN SUBJOINED LETTER FIXED-FORM RA -102C ; Other_Alphabetic # Mc MYANMAR VOWEL SIGN AA -102D..1030; Other_Alphabetic # Mn [4] MYANMAR VOWEL SIGN I..MYANMAR VOWEL SIGN UU -1031 ; Other_Alphabetic # Mc MYANMAR VOWEL SIGN E -1032 ; Other_Alphabetic # Mn MYANMAR VOWEL SIGN AI -1036 ; Other_Alphabetic # Mn MYANMAR SIGN ANUSVARA -1038 ; Other_Alphabetic # Mc MYANMAR SIGN VISARGA -1056..1057; Other_Alphabetic # Mc [2] MYANMAR VOWEL SIGN VOCALIC R..MYANMAR VOWEL SIGN VOCALIC RR -1058..1059; Other_Alphabetic # Mn [2] MYANMAR VOWEL SIGN VOCALIC L..MYANMAR VOWEL SIGN VOCALIC LL -16EE..16F0; Other_Alphabetic # Nl [3] RUNIC ARLAUG SYMBOL..RUNIC BELGTHOR SYMBOL -17B4..17B6; Other_Alphabetic # Mc [3] KHMER VOWEL INHERENT AQ..KHMER VOWEL SIGN AA -17B7..17BD; Other_Alphabetic # Mn [7] KHMER VOWEL SIGN I..KHMER VOWEL SIGN UA -17BE..17C5; Other_Alphabetic # Mc [8] KHMER VOWEL SIGN OE..KHMER VOWEL SIGN AU -17C6 ; Other_Alphabetic # Mn KHMER SIGN NIKAHIT -17C7..17C8; Other_Alphabetic # Mc [2] KHMER SIGN REAHMUK..KHMER SIGN YUUKALEAPINTU -18A9 ; Other_Alphabetic # Mn MONGOLIAN LETTER ALI GALI DAGALGA -2160..2183; Other_Alphabetic # Nl [36] ROMAN NUMERAL ONE..ROMAN NUMERAL REVERSED ONE HUNDRED -FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA -1034A ; Other_Alphabetic # Nl GOTHIC LETTER NINE HUNDRED +0345 ; Other_Alphabetic # Mn COMBINING GREEK YPOGEGRAMMENI +05B0..05B9 ; Other_Alphabetic # Mn [10] HEBREW POINT SHEVA..HEBREW POINT HOLAM +05BB..05BD ; Other_Alphabetic # Mn [3] HEBREW POINT QUBUTS..HEBREW POINT METEG +05BF ; Other_Alphabetic # Mn HEBREW POINT RAFE +05C1..05C2 ; Other_Alphabetic # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT +05C4 ; Other_Alphabetic # Mn HEBREW MARK UPPER DOT +064B..0655 ; Other_Alphabetic # Mn [11] ARABIC FATHATAN..ARABIC HAMZA BELOW +0670 ; Other_Alphabetic # Mn ARABIC LETTER SUPERSCRIPT ALEF +06D6..06DC ; Other_Alphabetic # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN +06E1..06E4 ; Other_Alphabetic # Mn [4] ARABIC SMALL HIGH DOTLESS HEAD OF KHAH..ARABIC SMALL HIGH MADDA +06E7..06E8 ; Other_Alphabetic # Mn [2] ARABIC SMALL HIGH YEH..ARABIC SMALL HIGH NOON +06ED ; Other_Alphabetic # Mn ARABIC SMALL LOW MEEM +0711 ; Other_Alphabetic # Mn SYRIAC LETTER SUPERSCRIPT ALAPH +0730..073F ; Other_Alphabetic # Mn [16] SYRIAC PTHAHA ABOVE..SYRIAC RWAHA +07A6..07B0 ; Other_Alphabetic # Mn [11] THAANA ABAFILI..THAANA SUKUN +0901..0902 ; Other_Alphabetic # Mn [2] DEVANAGARI SIGN CANDRABINDU..DEVANAGARI SIGN ANUSVARA +0903 ; Other_Alphabetic # Mc DEVANAGARI SIGN VISARGA +093E..0940 ; Other_Alphabetic # Mc [3] DEVANAGARI VOWEL SIGN AA..DEVANAGARI VOWEL SIGN II +0941..0948 ; Other_Alphabetic # Mn [8] DEVANAGARI VOWEL SIGN U..DEVANAGARI VOWEL SIGN AI +0949..094C ; Other_Alphabetic # Mc [4] DEVANAGARI VOWEL SIGN CANDRA O..DEVANAGARI VOWEL SIGN AU +0962..0963 ; Other_Alphabetic # Mn [2] DEVANAGARI VOWEL SIGN VOCALIC L..DEVANAGARI VOWEL SIGN VOCALIC LL +0981 ; Other_Alphabetic # Mn BENGALI SIGN CANDRABINDU +0982..0983 ; Other_Alphabetic # Mc [2] BENGALI SIGN ANUSVARA..BENGALI SIGN VISARGA +09BE..09C0 ; Other_Alphabetic # Mc [3] BENGALI VOWEL SIGN AA..BENGALI VOWEL SIGN II +09C1..09C4 ; Other_Alphabetic # Mn [4] BENGALI VOWEL SIGN U..BENGALI VOWEL SIGN VOCALIC RR +09C7..09C8 ; Other_Alphabetic # Mc [2] BENGALI VOWEL SIGN E..BENGALI VOWEL SIGN AI +09CB..09CC ; Other_Alphabetic # Mc [2] BENGALI VOWEL SIGN O..BENGALI VOWEL SIGN AU +09D7 ; Other_Alphabetic # Mc BENGALI AU LENGTH MARK +09E2..09E3 ; Other_Alphabetic # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL +0A02 ; Other_Alphabetic # Mn GURMUKHI SIGN BINDI +0A3E..0A40 ; Other_Alphabetic # Mc [3] GURMUKHI VOWEL SIGN AA..GURMUKHI VOWEL SIGN II +0A41..0A42 ; Other_Alphabetic # Mn [2] GURMUKHI VOWEL SIGN U..GURMUKHI VOWEL SIGN UU +0A47..0A48 ; Other_Alphabetic # Mn [2] GURMUKHI VOWEL SIGN EE..GURMUKHI VOWEL SIGN AI +0A4B..0A4C ; Other_Alphabetic # Mn [2] GURMUKHI VOWEL SIGN OO..GURMUKHI VOWEL SIGN AU +0A70..0A71 ; Other_Alphabetic # Mn [2] GURMUKHI TIPPI..GURMUKHI ADDAK +0A81..0A82 ; Other_Alphabetic # Mn [2] GUJARATI SIGN CANDRABINDU..GUJARATI SIGN ANUSVARA +0A83 ; Other_Alphabetic # Mc GUJARATI SIGN VISARGA +0ABE..0AC0 ; Other_Alphabetic # Mc [3] GUJARATI VOWEL SIGN AA..GUJARATI VOWEL SIGN II +0AC1..0AC5 ; Other_Alphabetic # Mn [5] GUJARATI VOWEL SIGN U..GUJARATI VOWEL SIGN CANDRA E +0AC7..0AC8 ; Other_Alphabetic # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI +0AC9 ; Other_Alphabetic # Mc GUJARATI VOWEL SIGN CANDRA O +0ACB..0ACC ; Other_Alphabetic # Mc [2] GUJARATI VOWEL SIGN O..GUJARATI VOWEL SIGN AU +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 +0B3F ; Other_Alphabetic # Mn ORIYA VOWEL SIGN I +0B40 ; Other_Alphabetic # Mc ORIYA VOWEL SIGN II +0B41..0B43 ; Other_Alphabetic # Mn [3] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC R +0B47..0B48 ; Other_Alphabetic # Mc [2] ORIYA VOWEL SIGN E..ORIYA VOWEL SIGN AI +0B4B..0B4C ; Other_Alphabetic # Mc [2] ORIYA VOWEL SIGN O..ORIYA VOWEL SIGN AU +0B56 ; Other_Alphabetic # Mn ORIYA AI LENGTH MARK +0B57 ; Other_Alphabetic # Mc ORIYA AU LENGTH MARK +0B82 ; Other_Alphabetic # Mn TAMIL SIGN ANUSVARA +0B83 ; Other_Alphabetic # Mc TAMIL SIGN VISARGA +0BBE..0BBF ; Other_Alphabetic # Mc [2] TAMIL VOWEL SIGN AA..TAMIL VOWEL SIGN I +0BC0 ; Other_Alphabetic # Mn TAMIL VOWEL SIGN II +0BC1..0BC2 ; Other_Alphabetic # Mc [2] TAMIL VOWEL SIGN U..TAMIL VOWEL SIGN UU +0BC6..0BC8 ; Other_Alphabetic # Mc [3] TAMIL VOWEL SIGN E..TAMIL VOWEL SIGN AI +0BCA..0BCC ; Other_Alphabetic # Mc [3] TAMIL VOWEL SIGN O..TAMIL VOWEL SIGN AU +0BD7 ; Other_Alphabetic # Mc TAMIL AU LENGTH MARK +0C01..0C03 ; Other_Alphabetic # Mc [3] TELUGU SIGN CANDRABINDU..TELUGU SIGN VISARGA +0C3E..0C40 ; Other_Alphabetic # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II +0C41..0C44 ; Other_Alphabetic # Mc [4] TELUGU VOWEL SIGN U..TELUGU VOWEL SIGN VOCALIC RR +0C46..0C48 ; Other_Alphabetic # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI +0C4A..0C4C ; Other_Alphabetic # Mn [3] TELUGU VOWEL SIGN O..TELUGU VOWEL SIGN AU +0C55..0C56 ; Other_Alphabetic # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK +0C82..0C83 ; Other_Alphabetic # Mc [2] KANNADA SIGN ANUSVARA..KANNADA SIGN VISARGA +0CBE ; Other_Alphabetic # Mc KANNADA VOWEL SIGN AA +0CBF ; Other_Alphabetic # Mn KANNADA VOWEL SIGN I +0CC0..0CC4 ; Other_Alphabetic # Mc [5] KANNADA VOWEL SIGN II..KANNADA VOWEL SIGN VOCALIC RR +0CC6 ; Other_Alphabetic # Mn KANNADA VOWEL SIGN E +0CC7..0CC8 ; Other_Alphabetic # Mc [2] KANNADA VOWEL SIGN EE..KANNADA VOWEL SIGN AI +0CCA..0CCB ; Other_Alphabetic # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO +0CCC ; Other_Alphabetic # Mn KANNADA VOWEL SIGN AU +0CD5..0CD6 ; Other_Alphabetic # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK +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..0D43 ; Other_Alphabetic # Mn [3] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC R +0D46..0D48 ; Other_Alphabetic # Mc [3] MALAYALAM VOWEL SIGN E..MALAYALAM VOWEL SIGN AI +0D4A..0D4C ; Other_Alphabetic # Mc [3] MALAYALAM VOWEL SIGN O..MALAYALAM VOWEL SIGN AU +0D57 ; Other_Alphabetic # Mc MALAYALAM AU LENGTH MARK +0D82..0D83 ; Other_Alphabetic # Mc [2] SINHALA SIGN ANUSVARAYA..SINHALA SIGN VISARGAYA +0DCF..0DD1 ; Other_Alphabetic # Mc [3] SINHALA VOWEL SIGN AELA-PILLA..SINHALA VOWEL SIGN DIGA AEDA-PILLA +0DD2..0DD4 ; Other_Alphabetic # Mn [3] SINHALA VOWEL SIGN KETTI IS-PILLA..SINHALA VOWEL SIGN KETTI PAA-PILLA +0DD6 ; Other_Alphabetic # Mn SINHALA VOWEL SIGN DIGA PAA-PILLA +0DD8..0DDF ; Other_Alphabetic # Mc [8] SINHALA VOWEL SIGN GAETTA-PILLA..SINHALA VOWEL SIGN GAYANUKITTA +0DF2..0DF3 ; Other_Alphabetic # Mc [2] SINHALA VOWEL SIGN DIGA GAETTA-PILLA..SINHALA VOWEL SIGN DIGA GAYANUKITTA +0E31 ; Other_Alphabetic # Mn THAI CHARACTER MAI HAN-AKAT +0E34..0E3A ; Other_Alphabetic # Mn [7] THAI CHARACTER SARA I..THAI CHARACTER PHINTHU +0E4D ; Other_Alphabetic # Mn THAI CHARACTER NIKHAHIT +0EB1 ; Other_Alphabetic # Mn LAO VOWEL SIGN MAI KAN +0EB4..0EB9 ; Other_Alphabetic # Mn [6] LAO VOWEL SIGN I..LAO VOWEL SIGN UU +0EBB..0EBC ; Other_Alphabetic # Mn [2] LAO VOWEL SIGN MAI KON..LAO SEMIVOWEL SIGN LO +0ECD ; Other_Alphabetic # Mn LAO NIGGAHITA +0F71..0F7E ; Other_Alphabetic # Mn [14] TIBETAN VOWEL SIGN AA..TIBETAN SIGN RJES SU NGA RO +0F7F ; Other_Alphabetic # Mc TIBETAN SIGN RNAM BCAD +0F80..0F81 ; Other_Alphabetic # Mn [2] TIBETAN VOWEL SIGN REVERSED I..TIBETAN VOWEL SIGN REVERSED II +0F90..0F97 ; Other_Alphabetic # Mn [8] TIBETAN SUBJOINED LETTER KA..TIBETAN SUBJOINED LETTER JA +0F99..0FBC ; Other_Alphabetic # Mn [36] TIBETAN SUBJOINED LETTER NYA..TIBETAN SUBJOINED LETTER FIXED-FORM RA +102C ; Other_Alphabetic # Mc MYANMAR VOWEL SIGN AA +102D..1030 ; Other_Alphabetic # Mn [4] MYANMAR VOWEL SIGN I..MYANMAR VOWEL SIGN UU +1031 ; Other_Alphabetic # Mc MYANMAR VOWEL SIGN E +1032 ; Other_Alphabetic # Mn MYANMAR VOWEL SIGN AI +1036 ; Other_Alphabetic # Mn MYANMAR SIGN ANUSVARA +1038 ; Other_Alphabetic # Mc MYANMAR SIGN VISARGA +1056..1057 ; Other_Alphabetic # Mc [2] MYANMAR VOWEL SIGN VOCALIC R..MYANMAR VOWEL SIGN VOCALIC RR +1058..1059 ; Other_Alphabetic # Mn [2] MYANMAR VOWEL SIGN VOCALIC L..MYANMAR VOWEL SIGN VOCALIC LL +16EE..16F0 ; Other_Alphabetic # Nl [3] RUNIC ARLAUG SYMBOL..RUNIC BELGTHOR SYMBOL +17B4..17B6 ; Other_Alphabetic # Mc [3] KHMER VOWEL INHERENT AQ..KHMER VOWEL SIGN AA +17B7..17BD ; Other_Alphabetic # Mn [7] KHMER VOWEL SIGN I..KHMER VOWEL SIGN UA +17BE..17C5 ; Other_Alphabetic # Mc [8] KHMER VOWEL SIGN OE..KHMER VOWEL SIGN AU +17C6 ; Other_Alphabetic # Mn KHMER SIGN NIKAHIT +17C7..17C8 ; Other_Alphabetic # Mc [2] KHMER SIGN REAHMUK..KHMER SIGN YUUKALEAPINTU +18A9 ; Other_Alphabetic # Mn MONGOLIAN LETTER ALI GALI DAGALGA +2160..2183 ; Other_Alphabetic # Nl [36] ROMAN NUMERAL ONE..ROMAN NUMERAL REVERSED ONE HUNDRED +FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA +1034A ; Other_Alphabetic # Nl GOTHIC LETTER NINE HUNDRED # Total code points: 391 # ================================================ -3006 ; Ideographic # Lo IDEOGRAPHIC CLOSING MARK -3007 ; Ideographic # Nl IDEOGRAPHIC NUMBER ZERO -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..9FA5; Ideographic # Lo [20902] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FA5 -F900..FA2D; Ideographic # Lo [302] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA2D -20000..2A6D6; Ideographic # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6 -2F800..2FA1D; Ideographic # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D +3006 ; Ideographic # Lo IDEOGRAPHIC CLOSING MARK +3007 ; Ideographic # Nl IDEOGRAPHIC NUMBER ZERO +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..9FA5 ; Ideographic # Lo [20902] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FA5 +F900..FA2D ; Ideographic # Lo [302] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA2D +20000..2A6D6 ; Ideographic # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6 +2F800..2FA1D ; Ideographic # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D # Total code points: 71053 # ================================================ -005E ; Diacritic # Sk CIRCUMFLEX ACCENT -0060 ; Diacritic # Sk GRAVE ACCENT -00A8 ; Diacritic # Sk DIAERESIS -00AF ; Diacritic # Sk MACRON -00B4 ; Diacritic # Sk ACUTE ACCENT -00B7 ; Diacritic # Po MIDDLE DOT -00B8 ; Diacritic # Sk CEDILLA -02B0..02B8; Diacritic # Lm [9] MODIFIER LETTER SMALL H..MODIFIER LETTER SMALL Y -02B9..02BA; Diacritic # Sk [2] MODIFIER LETTER PRIME..MODIFIER LETTER DOUBLE PRIME -02BB..02C1; Diacritic # Lm [7] MODIFIER LETTER TURNED COMMA..MODIFIER LETTER REVERSED GLOTTAL STOP -02C2..02CF; Diacritic # Sk [14] MODIFIER LETTER LEFT ARROWHEAD..MODIFIER LETTER LOW ACUTE ACCENT -02D0..02D1; Diacritic # Lm [2] MODIFIER LETTER TRIANGULAR COLON..MODIFIER LETTER HALF TRIANGULAR COLON -02D2..02DF; Diacritic # Sk [14] MODIFIER LETTER CENTRED RIGHT HALF RING..MODIFIER LETTER CROSS ACCENT -02E0..02E4; Diacritic # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP -02E5..02ED; Diacritic # Sk [9] MODIFIER LETTER EXTRA-HIGH TONE BAR..MODIFIER LETTER UNASPIRATED -02EE ; Diacritic # Lm MODIFIER LETTER DOUBLE APOSTROPHE -0300..034E; Diacritic # Mn [79] COMBINING GRAVE ACCENT..COMBINING UPWARDS ARROW BELOW -0360..0362; Diacritic # Mn [3] COMBINING DOUBLE TILDE..COMBINING DOUBLE RIGHTWARDS ARROW BELOW -0374..0375; Diacritic # Sk [2] GREEK NUMERAL SIGN..GREEK LOWER NUMERAL SIGN -037A ; Diacritic # Lm GREEK YPOGEGRAMMENI -0384..0385; Diacritic # Sk [2] GREEK TONOS..GREEK DIALYTIKA TONOS -0483..0486; Diacritic # Mn [4] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC PSILI PNEUMATA -0559 ; Diacritic # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING -0591..05A1; Diacritic # Mn [17] HEBREW ACCENT ETNAHTA..HEBREW ACCENT PAZER -05A3..05B9; Diacritic # Mn [23] HEBREW ACCENT MUNAH..HEBREW POINT HOLAM -05BB..05BD; Diacritic # Mn [3] HEBREW POINT QUBUTS..HEBREW POINT METEG -05BF ; Diacritic # Mn HEBREW POINT RAFE -05C1..05C2; Diacritic # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT -05C4 ; Diacritic # Mn HEBREW MARK UPPER DOT -064B..0652; Diacritic # Mn [8] ARABIC FATHATAN..ARABIC SUKUN -06DF..06E0; Diacritic # Mn [2] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH UPRIGHT RECTANGULAR ZERO -06E5..06E6; Diacritic # Lm [2] ARABIC SMALL WAW..ARABIC SMALL YEH -06EA..06EC; Diacritic # Mn [3] ARABIC EMPTY CENTRE LOW STOP..ARABIC ROUNDED HIGH STOP WITH FILLED CENTRE -0730..074A; Diacritic # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH -07A6..07B0; Diacritic # Mn [11] THAANA ABAFILI..THAANA SUKUN -093C ; Diacritic # Mn DEVANAGARI SIGN NUKTA -094D ; Diacritic # Mn DEVANAGARI SIGN VIRAMA -0951..0954; Diacritic # Mn [4] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI ACUTE ACCENT -09BC ; Diacritic # Mn BENGALI SIGN NUKTA -09CD ; Diacritic # Mn BENGALI SIGN VIRAMA -0A3C ; Diacritic # Mn GURMUKHI SIGN NUKTA -0A4D ; Diacritic # Mn GURMUKHI SIGN VIRAMA -0ABC ; Diacritic # Mn GUJARATI SIGN NUKTA -0ACD ; Diacritic # Mn GUJARATI SIGN VIRAMA -0B3C ; Diacritic # Mn ORIYA SIGN NUKTA -0B4D ; Diacritic # Mn ORIYA SIGN VIRAMA -0BCD ; Diacritic # Mn TAMIL SIGN VIRAMA -0C4D ; Diacritic # Mn TELUGU SIGN VIRAMA -0CCD ; Diacritic # Mn KANNADA SIGN 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 -0E4E ; Diacritic # Mn THAI CHARACTER YAMAKKAN -0EC8..0ECC; Diacritic # Mn [5] LAO TONE MAI EK..LAO CANCELLATION MARK -0F18..0F19; Diacritic # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS -0F35 ; Diacritic # Mn TIBETAN MARK NGAS BZUNG NYI ZLA -0F37 ; Diacritic # Mn TIBETAN MARK NGAS BZUNG SGOR RTAGS -0F39 ; Diacritic # Mn TIBETAN MARK TSA -PHRU -0F3E..0F3F; Diacritic # Mc [2] TIBETAN SIGN YAR TSHES..TIBETAN SIGN MAR TSHES -0F82..0F84; Diacritic # Mn [3] TIBETAN SIGN NYI ZLA NAA DA..TIBETAN MARK HALANTA -0F86..0F87; Diacritic # Mn [2] TIBETAN SIGN LCI RTAGS..TIBETAN SIGN YANG RTAGS -0FC6 ; Diacritic # Mn TIBETAN SYMBOL PADMA GDAN -1037 ; Diacritic # Mn MYANMAR SIGN DOT BELOW -1039 ; Diacritic # Mn MYANMAR SIGN VIRAMA -17C9..17D3; Diacritic # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT -1FBD ; Diacritic # Sk GREEK KORONIS -1FBF..1FC1; Diacritic # Sk [3] GREEK PSILI..GREEK DIALYTIKA AND PERISPOMENI -1FCD..1FCF; Diacritic # Sk [3] GREEK PSILI AND VARIA..GREEK PSILI AND PERISPOMENI -1FDD..1FDF; Diacritic # Sk [3] GREEK DASIA AND VARIA..GREEK DASIA AND PERISPOMENI -1FED..1FEF; Diacritic # Sk [3] GREEK DIALYTIKA AND VARIA..GREEK VARIA -1FFD..1FFE; Diacritic # Sk [2] GREEK OXIA..GREEK DASIA -302A..302F; Diacritic # Mn [6] IDEOGRAPHIC LEVEL TONE MARK..HANGUL DOUBLE DOT TONE MARK -3099..309A; Diacritic # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK -309B..309C; Diacritic # Sk [2] KATAKANA-HIRAGANA VOICED SOUND MARK..KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK -30FC ; Diacritic # Lm KATAKANA-HIRAGANA PROLONGED SOUND MARK -FB1E ; Diacritic # Mn HEBREW POINT JUDEO-SPANISH VARIKA -FE20..FE23; Diacritic # Mn [4] COMBINING LIGATURE LEFT HALF..COMBINING DOUBLE TILDE RIGHT HALF -FF3E ; Diacritic # Sk FULLWIDTH CIRCUMFLEX ACCENT -FF40 ; Diacritic # Sk FULLWIDTH GRAVE ACCENT -FF70 ; Diacritic # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK -FF9E..FF9F; Diacritic # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK -FFE3 ; Diacritic # Sk FULLWIDTH MACRON -1D167..1D169; Diacritic # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 -1D16D..1D172; Diacritic # Mc [6] MUSICAL SYMBOL COMBINING AUGMENTATION DOT..MUSICAL SYMBOL COMBINING FLAG-5 -1D17B..1D182; Diacritic # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE -1D185..1D18B; Diacritic # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE -1D1AA..1D1AD; Diacritic # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO +005E ; Diacritic # Sk CIRCUMFLEX ACCENT +0060 ; Diacritic # Sk GRAVE ACCENT +00A8 ; Diacritic # Sk DIAERESIS +00AF ; Diacritic # Sk MACRON +00B4 ; Diacritic # Sk ACUTE ACCENT +00B7 ; Diacritic # Po MIDDLE DOT +00B8 ; Diacritic # Sk CEDILLA +02B0..02B8 ; Diacritic # Lm [9] MODIFIER LETTER SMALL H..MODIFIER LETTER SMALL Y +02B9..02BA ; Diacritic # Sk [2] MODIFIER LETTER PRIME..MODIFIER LETTER DOUBLE PRIME +02BB..02C1 ; Diacritic # Lm [7] MODIFIER LETTER TURNED COMMA..MODIFIER LETTER REVERSED GLOTTAL STOP +02C2..02CF ; Diacritic # Sk [14] MODIFIER LETTER LEFT ARROWHEAD..MODIFIER LETTER LOW ACUTE ACCENT +02D0..02D1 ; Diacritic # Lm [2] MODIFIER LETTER TRIANGULAR COLON..MODIFIER LETTER HALF TRIANGULAR COLON +02D2..02DF ; Diacritic # Sk [14] MODIFIER LETTER CENTRED RIGHT HALF RING..MODIFIER LETTER CROSS ACCENT +02E0..02E4 ; Diacritic # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP +02E5..02ED ; Diacritic # Sk [9] MODIFIER LETTER EXTRA-HIGH TONE BAR..MODIFIER LETTER UNASPIRATED +02EE ; Diacritic # Lm MODIFIER LETTER DOUBLE APOSTROPHE +0300..034E ; Diacritic # Mn [79] COMBINING GRAVE ACCENT..COMBINING UPWARDS ARROW BELOW +0360..0362 ; Diacritic # Mn [3] COMBINING DOUBLE TILDE..COMBINING DOUBLE RIGHTWARDS ARROW BELOW +0374..0375 ; Diacritic # Sk [2] GREEK NUMERAL SIGN..GREEK LOWER NUMERAL SIGN +037A ; Diacritic # Lm GREEK YPOGEGRAMMENI +0384..0385 ; Diacritic # Sk [2] GREEK TONOS..GREEK DIALYTIKA TONOS +0483..0486 ; Diacritic # Mn [4] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC PSILI PNEUMATA +0559 ; Diacritic # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING +0591..05A1 ; Diacritic # Mn [17] HEBREW ACCENT ETNAHTA..HEBREW ACCENT PAZER +05A3..05B9 ; Diacritic # Mn [23] HEBREW ACCENT MUNAH..HEBREW POINT HOLAM +05BB..05BD ; Diacritic # Mn [3] HEBREW POINT QUBUTS..HEBREW POINT METEG +05BF ; Diacritic # Mn HEBREW POINT RAFE +05C1..05C2 ; Diacritic # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT +05C4 ; Diacritic # Mn HEBREW MARK UPPER DOT +064B..0652 ; Diacritic # Mn [8] ARABIC FATHATAN..ARABIC SUKUN +06DF..06E0 ; Diacritic # Mn [2] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH UPRIGHT RECTANGULAR ZERO +06E5..06E6 ; Diacritic # Lm [2] ARABIC SMALL WAW..ARABIC SMALL YEH +06EA..06EC ; Diacritic # Mn [3] ARABIC EMPTY CENTRE LOW STOP..ARABIC ROUNDED HIGH STOP WITH FILLED CENTRE +0730..074A ; Diacritic # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH +07A6..07B0 ; Diacritic # Mn [11] THAANA ABAFILI..THAANA SUKUN +093C ; Diacritic # Mn DEVANAGARI SIGN NUKTA +094D ; Diacritic # Mn DEVANAGARI SIGN VIRAMA +0951..0954 ; Diacritic # Mn [4] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI ACUTE ACCENT +09BC ; Diacritic # Mn BENGALI SIGN NUKTA +09CD ; Diacritic # Mn BENGALI SIGN VIRAMA +0A3C ; Diacritic # Mn GURMUKHI SIGN NUKTA +0A4D ; Diacritic # Mn GURMUKHI SIGN VIRAMA +0ABC ; Diacritic # Mn GUJARATI SIGN NUKTA +0ACD ; Diacritic # Mn GUJARATI SIGN VIRAMA +0B3C ; Diacritic # Mn ORIYA SIGN NUKTA +0B4D ; Diacritic # Mn ORIYA SIGN VIRAMA +0BCD ; Diacritic # Mn TAMIL SIGN VIRAMA +0C4D ; Diacritic # Mn TELUGU SIGN VIRAMA +0CCD ; Diacritic # Mn KANNADA SIGN 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 +0E4E ; Diacritic # Mn THAI CHARACTER YAMAKKAN +0EC8..0ECC ; Diacritic # Mn [5] LAO TONE MAI EK..LAO CANCELLATION MARK +0F18..0F19 ; Diacritic # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS +0F35 ; Diacritic # Mn TIBETAN MARK NGAS BZUNG NYI ZLA +0F37 ; Diacritic # Mn TIBETAN MARK NGAS BZUNG SGOR RTAGS +0F39 ; Diacritic # Mn TIBETAN MARK TSA -PHRU +0F3E..0F3F ; Diacritic # Mc [2] TIBETAN SIGN YAR TSHES..TIBETAN SIGN MAR TSHES +0F82..0F84 ; Diacritic # Mn [3] TIBETAN SIGN NYI ZLA NAA DA..TIBETAN MARK HALANTA +0F86..0F87 ; Diacritic # Mn [2] TIBETAN SIGN LCI RTAGS..TIBETAN SIGN YANG RTAGS +0FC6 ; Diacritic # Mn TIBETAN SYMBOL PADMA GDAN +1037 ; Diacritic # Mn MYANMAR SIGN DOT BELOW +1039 ; Diacritic # Mn MYANMAR SIGN VIRAMA +17C9..17D3 ; Diacritic # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT +1FBD ; Diacritic # Sk GREEK KORONIS +1FBF..1FC1 ; Diacritic # Sk [3] GREEK PSILI..GREEK DIALYTIKA AND PERISPOMENI +1FCD..1FCF ; Diacritic # Sk [3] GREEK PSILI AND VARIA..GREEK PSILI AND PERISPOMENI +1FDD..1FDF ; Diacritic # Sk [3] GREEK DASIA AND VARIA..GREEK DASIA AND PERISPOMENI +1FED..1FEF ; Diacritic # Sk [3] GREEK DIALYTIKA AND VARIA..GREEK VARIA +1FFD..1FFE ; Diacritic # Sk [2] GREEK OXIA..GREEK DASIA +302A..302F ; Diacritic # Mn [6] IDEOGRAPHIC LEVEL TONE MARK..HANGUL DOUBLE DOT TONE MARK +3099..309A ; Diacritic # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK +309B..309C ; Diacritic # Sk [2] KATAKANA-HIRAGANA VOICED SOUND MARK..KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK +30FC ; Diacritic # Lm KATAKANA-HIRAGANA PROLONGED SOUND MARK +FB1E ; Diacritic # Mn HEBREW POINT JUDEO-SPANISH VARIKA +FE20..FE23 ; Diacritic # Mn [4] COMBINING LIGATURE LEFT HALF..COMBINING DOUBLE TILDE RIGHT HALF +FF3E ; Diacritic # Sk FULLWIDTH CIRCUMFLEX ACCENT +FF40 ; Diacritic # Sk FULLWIDTH GRAVE ACCENT +FF70 ; Diacritic # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK +FF9E..FF9F ; Diacritic # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK +FFE3 ; Diacritic # Sk FULLWIDTH MACRON +1D167..1D169 ; Diacritic # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 +1D16D..1D172 ; Diacritic # Mc [6] MUSICAL SYMBOL COMBINING AUGMENTATION DOT..MUSICAL SYMBOL COMBINING FLAG-5 +1D17B..1D182 ; Diacritic # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE +1D185..1D18B ; Diacritic # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE +1D1AA..1D1AD ; Diacritic # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO # Total code points: 384 # ================================================ -00B7 ; Extender # Po MIDDLE DOT -02D0..02D1; Extender # Lm [2] MODIFIER LETTER TRIANGULAR COLON..MODIFIER LETTER HALF TRIANGULAR COLON -0640 ; Extender # Lm ARABIC TATWEEL -0E46 ; Extender # Lm THAI CHARACTER MAIYAMOK -0EC6 ; Extender # Lm LAO KO LA -1843 ; Extender # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN -3005 ; Extender # Lm IDEOGRAPHIC ITERATION MARK -3031..3035; Extender # Lm [5] VERTICAL KANA REPEAT MARK..VERTICAL KANA REPEAT MARK LOWER HALF -309D..309E; Extender # Lm [2] HIRAGANA ITERATION MARK..HIRAGANA VOICED ITERATION MARK -30FC..30FE; Extender # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK -FF70 ; Extender # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK +00B7 ; Extender # Po MIDDLE DOT +02D0..02D1 ; Extender # Lm [2] MODIFIER LETTER TRIANGULAR COLON..MODIFIER LETTER HALF TRIANGULAR COLON +0640 ; Extender # Lm ARABIC TATWEEL +0E46 ; Extender # Lm THAI CHARACTER MAIYAMOK +0EC6 ; Extender # Lm LAO KO LA +1843 ; Extender # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN +3005 ; Extender # Lm IDEOGRAPHIC ITERATION MARK +3031..3035 ; Extender # Lm [5] VERTICAL KANA REPEAT MARK..VERTICAL KANA REPEAT MARK LOWER HALF +309D..309E ; Extender # Lm [2] HIRAGANA ITERATION MARK..HIRAGANA VOICED ITERATION MARK +30FC..30FE ; Extender # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK +FF70 ; Extender # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK # Total code points: 19 # ================================================ -02B0..02B8; Other_Lowercase # Lm [9] MODIFIER LETTER SMALL H..MODIFIER LETTER SMALL Y -02C0..02C1; Other_Lowercase # Lm [2] MODIFIER LETTER GLOTTAL STOP..MODIFIER LETTER REVERSED GLOTTAL STOP -02E0..02E4; Other_Lowercase # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP -0345 ; Other_Lowercase # Mn COMBINING GREEK YPOGEGRAMMENI -037A ; Other_Lowercase # Lm GREEK YPOGEGRAMMENI -2170..217F; Other_Lowercase # Nl [16] SMALL ROMAN NUMERAL ONE..SMALL ROMAN NUMERAL ONE THOUSAND -24D0..24E9; Other_Lowercase # So [26] CIRCLED LATIN SMALL LETTER A..CIRCLED LATIN SMALL LETTER Z +02B0..02B8 ; Other_Lowercase # Lm [9] MODIFIER LETTER SMALL H..MODIFIER LETTER SMALL Y +02C0..02C1 ; Other_Lowercase # Lm [2] MODIFIER LETTER GLOTTAL STOP..MODIFIER LETTER REVERSED GLOTTAL STOP +02E0..02E4 ; Other_Lowercase # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP +0345 ; Other_Lowercase # Mn COMBINING GREEK YPOGEGRAMMENI +037A ; Other_Lowercase # Lm GREEK YPOGEGRAMMENI +2170..217F ; Other_Lowercase # Nl [16] SMALL ROMAN NUMERAL ONE..SMALL ROMAN NUMERAL ONE THOUSAND +24D0..24E9 ; Other_Lowercase # So [26] CIRCLED LATIN SMALL LETTER A..CIRCLED LATIN SMALL LETTER Z # Total code points: 60 # ================================================ -2160..216F; Other_Uppercase # Nl [16] ROMAN NUMERAL ONE..ROMAN NUMERAL ONE THOUSAND -24B6..24CF; Other_Uppercase # So [26] CIRCLED LATIN CAPITAL LETTER A..CIRCLED LATIN CAPITAL LETTER Z +2160..216F ; Other_Uppercase # Nl [16] ROMAN NUMERAL ONE..ROMAN NUMERAL ONE THOUSAND +24B6..24CF ; Other_Uppercase # So [26] CIRCLED LATIN CAPITAL LETTER A..CIRCLED LATIN CAPITAL LETTER Z # Total code points: 42 # ================================================ -FDD0..FDEF; Noncharacter_Code_Point # Cn [32] -FFFE..FFFF; Noncharacter_Code_Point # Cn [2] -1FFFE..1FFFF; Noncharacter_Code_Point # Cn [2] -2FFFE..2FFFF; Noncharacter_Code_Point # Cn [2] -3FFFE..3FFFF; Noncharacter_Code_Point # Cn [2] -4FFFE..4FFFF; Noncharacter_Code_Point # Cn [2] -5FFFE..5FFFF; Noncharacter_Code_Point # Cn [2] -6FFFE..6FFFF; Noncharacter_Code_Point # Cn [2] -7FFFE..7FFFF; Noncharacter_Code_Point # Cn [2] -8FFFE..8FFFF; Noncharacter_Code_Point # Cn [2] -9FFFE..9FFFF; Noncharacter_Code_Point # Cn [2] -AFFFE..AFFFF; Noncharacter_Code_Point # Cn [2] -BFFFE..BFFFF; Noncharacter_Code_Point # Cn [2] -CFFFE..CFFFF; Noncharacter_Code_Point # Cn [2] -DFFFE..DFFFF; Noncharacter_Code_Point # Cn [2] -EFFFE..EFFFF; Noncharacter_Code_Point # Cn [2] -FFFFE..FFFFF; Noncharacter_Code_Point # Cn [2] -10FFFE..10FFFF; Noncharacter_Code_Point # Cn [2] +FDD0..FDEF ; Noncharacter_Code_Point # Cn [32] +FFFE..FFFF ; Noncharacter_Code_Point # Cn [2] +1FFFE..1FFFF ; Noncharacter_Code_Point # Cn [2] +2FFFE..2FFFF ; Noncharacter_Code_Point # Cn [2] +3FFFE..3FFFF ; Noncharacter_Code_Point # Cn [2] +4FFFE..4FFFF ; Noncharacter_Code_Point # Cn [2] +5FFFE..5FFFF ; Noncharacter_Code_Point # Cn [2] +6FFFE..6FFFF ; Noncharacter_Code_Point # Cn [2] +7FFFE..7FFFF ; Noncharacter_Code_Point # Cn [2] +8FFFE..8FFFF ; Noncharacter_Code_Point # Cn [2] +9FFFE..9FFFF ; Noncharacter_Code_Point # Cn [2] +AFFFE..AFFFF ; Noncharacter_Code_Point # Cn [2] +BFFFE..BFFFF ; Noncharacter_Code_Point # Cn [2] +CFFFE..CFFFF ; Noncharacter_Code_Point # Cn [2] +DFFFE..DFFFF ; Noncharacter_Code_Point # Cn [2] +EFFFE..EFFFF ; Noncharacter_Code_Point # Cn [2] +FFFFE..FFFFF ; Noncharacter_Code_Point # Cn [2] +10FFFE..10FFFF; Noncharacter_Code_Point # Cn [2] # Total code points: 66 diff --git a/lib/unicode/ReadMe.txt b/lib/unicode/ReadMe.txt index b8a643ca27..13dc401dbd 100644 --- a/lib/unicode/ReadMe.txt +++ b/lib/unicode/ReadMe.txt @@ -1,13 +1,38 @@ -August 30, 2000 +March 1, 2001 -This directory contains the first update release for Unicode 3.0. +This directory contains the beta files for the minor release +Unicode 3.1. This release consists of corrections and additions to the Unicode Character Database for the Unicode Standard, -Version 3.0.1. +Version 3.1. Detailed documentation of the files constituting the Unicode Character Database (contributory data files for the standard itself) can now be found in -UnicodeCharacterDatabase.html. +UnicodeCharacterDatabase.html. See also UnicodeData.html, +PropList.html, NamesList.html, and DerivedProperties.html +for specific details about particular files or sets of +files. + +Unihan-3.1.txt is a very large file, so it is also provided in +three different compressed formats: + +Unihan-3.1.zip for Windows. (Use winzip) +Unihan-3.1.Z for Unix. (Use uncompress) +Unihan-3.1.gz for Unix. (Use gzip) + +UCDwithoutUnihan.zip is a Windows winzip file that contains +all of the Unicode Character Database files except +Unihan-3.1.txt and this ReadMe.txt file. This file is +provided for convenience when downloading files from the +Unicode Character Database. Note that the files are zipped in +exactly the same format they have on the server (with Unix +line endings). From a browser, right-clicking on this file +entry will allow automatic download and unzipping on a +Windows system with winzip installed. + + + + diff --git a/lib/unicode/Scripts.txt b/lib/unicode/Scripts.txt new file mode 100644 index 0000000000..bee337f851 --- /dev/null +++ b/lib/unicode/Scripts.txt @@ -0,0 +1,652 @@ +# Scripts-3.1.0.txt +# +# For documentation, see UTR #24: Script Names +# http://www.unicode.org/unicode/reports/tr24/ +# Date: 2001-03-02 00:06:02.6 GMT [MD] +# Note: Unassigned and Noncharacter codepoints are omitted, +# except when listing Noncharacter or Cn. +# ================================================ + + +# ================================================ +# Script +# ================================================ + +0041..005A ; LATIN # L& [26] LATIN CAPITAL LETTER A..LATIN CAPITAL LETTER Z +0061..007A ; LATIN # L& [26] LATIN SMALL LETTER A..LATIN SMALL LETTER Z +00AA ; LATIN # L& FEMININE ORDINAL INDICATOR +00BA ; LATIN # L& MASCULINE ORDINAL INDICATOR +00C0..00D6 ; LATIN # L& [23] LATIN CAPITAL LETTER A WITH GRAVE..LATIN CAPITAL LETTER O WITH DIAERESIS +00D8..00F6 ; LATIN # L& [31] LATIN CAPITAL LETTER O WITH STROKE..LATIN SMALL LETTER O WITH DIAERESIS +00F8..01BA ; LATIN # L& [195] LATIN SMALL LETTER O WITH STROKE..LATIN SMALL LETTER EZH WITH TAIL +01BB ; LATIN # Lo LATIN LETTER TWO WITH STROKE +01BC..01BF ; LATIN # L& [4] LATIN CAPITAL LETTER TONE FIVE..LATIN LETTER WYNN +01C0..01C3 ; LATIN # Lo [4] LATIN LETTER DENTAL CLICK..LATIN LETTER RETROFLEX CLICK +01C4..021F ; LATIN # L& [92] LATIN CAPITAL LETTER DZ WITH CARON..LATIN SMALL LETTER H WITH CARON +0222..0233 ; LATIN # L& [18] LATIN CAPITAL LETTER OU..LATIN SMALL LETTER Y WITH MACRON +0250..02AD ; LATIN # L& [94] LATIN SMALL LETTER TURNED A..LATIN LETTER BIDENTAL PERCUSSIVE +02B0..02B8 ; LATIN # Lm [9] MODIFIER LETTER SMALL H..MODIFIER LETTER SMALL Y +02E0..02E4 ; LATIN # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP +1E00..1E9B ; LATIN # L& [156] LATIN CAPITAL LETTER A WITH RING BELOW..LATIN SMALL LETTER LONG S WITH DOT ABOVE +1EA0..1EF9 ; LATIN # L& [90] LATIN CAPITAL LETTER A WITH DOT BELOW..LATIN SMALL LETTER Y WITH TILDE +207F ; LATIN # L& SUPERSCRIPT LATIN SMALL LETTER N +212A..212B ; LATIN # L& [2] KELVIN SIGN..ANGSTROM SIGN +FB00..FB06 ; LATIN # L& [7] LATIN SMALL LIGATURE FF..LATIN SMALL LIGATURE ST +FF21..FF3A ; LATIN # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER Z +FF41..FF5A ; LATIN # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER Z + +# Total code points: 838 + +# ================================================ + +00B5 ; GREEK # L& MICRO SIGN +037A ; GREEK # Lm GREEK YPOGEGRAMMENI +0386 ; GREEK # L& GREEK CAPITAL LETTER ALPHA WITH TONOS +0388..038A ; GREEK # L& [3] GREEK CAPITAL LETTER EPSILON WITH TONOS..GREEK CAPITAL LETTER IOTA WITH TONOS +038C ; GREEK # L& GREEK CAPITAL LETTER OMICRON WITH TONOS +038E..03A1 ; GREEK # L& [20] GREEK CAPITAL LETTER UPSILON WITH TONOS..GREEK CAPITAL LETTER RHO +03A3..03CE ; GREEK # L& [44] GREEK CAPITAL LETTER SIGMA..GREEK SMALL LETTER OMEGA WITH TONOS +03D0..03D7 ; GREEK # L& [8] GREEK BETA SYMBOL..GREEK KAI SYMBOL +03DA..03F5 ; GREEK # L& [28] GREEK LETTER STIGMA..GREEK LUNATE EPSILON SYMBOL +1F00..1F15 ; GREEK # L& [22] GREEK SMALL LETTER ALPHA WITH PSILI..GREEK SMALL LETTER EPSILON WITH DASIA AND OXIA +1F18..1F1D ; GREEK # L& [6] GREEK CAPITAL LETTER EPSILON WITH PSILI..GREEK CAPITAL LETTER EPSILON WITH DASIA AND OXIA +1F20..1F45 ; GREEK # L& [38] GREEK SMALL LETTER ETA WITH PSILI..GREEK SMALL LETTER OMICRON WITH DASIA AND OXIA +1F48..1F4D ; GREEK # L& [6] GREEK CAPITAL LETTER OMICRON WITH PSILI..GREEK CAPITAL LETTER OMICRON WITH DASIA AND OXIA +1F50..1F57 ; GREEK # L& [8] GREEK SMALL LETTER UPSILON WITH PSILI..GREEK SMALL LETTER UPSILON WITH DASIA AND PERISPOMENI +1F59 ; GREEK # L& GREEK CAPITAL LETTER UPSILON WITH DASIA +1F5B ; GREEK # L& GREEK CAPITAL LETTER UPSILON WITH DASIA AND VARIA +1F5D ; GREEK # L& GREEK CAPITAL LETTER UPSILON WITH DASIA AND OXIA +1F5F..1F7D ; GREEK # L& [31] GREEK CAPITAL LETTER UPSILON WITH DASIA AND PERISPOMENI..GREEK SMALL LETTER OMEGA WITH OXIA +1F80..1FB4 ; GREEK # L& [53] GREEK SMALL LETTER ALPHA WITH PSILI AND YPOGEGRAMMENI..GREEK SMALL LETTER ALPHA WITH OXIA AND YPOGEGRAMMENI +1FB6..1FBC ; GREEK # L& [7] GREEK SMALL LETTER ALPHA WITH PERISPOMENI..GREEK CAPITAL LETTER ALPHA WITH PROSGEGRAMMENI +1FBE ; GREEK # L& GREEK PROSGEGRAMMENI +1FC2..1FC4 ; GREEK # L& [3] GREEK SMALL LETTER ETA WITH VARIA AND YPOGEGRAMMENI..GREEK SMALL LETTER ETA WITH OXIA AND YPOGEGRAMMENI +1FC6..1FCC ; GREEK # L& [7] GREEK SMALL LETTER ETA WITH PERISPOMENI..GREEK CAPITAL LETTER ETA WITH PROSGEGRAMMENI +1FD0..1FD3 ; GREEK # L& [4] GREEK SMALL LETTER IOTA WITH VRACHY..GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA +1FD6..1FDB ; GREEK # L& [6] GREEK SMALL LETTER IOTA WITH PERISPOMENI..GREEK CAPITAL LETTER IOTA WITH OXIA +1FE0..1FEC ; GREEK # L& [13] GREEK SMALL LETTER UPSILON WITH VRACHY..GREEK CAPITAL LETTER RHO WITH DASIA +1FF2..1FF4 ; GREEK # L& [3] GREEK SMALL LETTER OMEGA WITH VARIA AND YPOGEGRAMMENI..GREEK SMALL LETTER OMEGA WITH OXIA AND YPOGEGRAMMENI +1FF6..1FFC ; GREEK # L& [7] GREEK SMALL LETTER OMEGA WITH PERISPOMENI..GREEK CAPITAL LETTER OMEGA WITH PROSGEGRAMMENI +2126 ; GREEK # L& OHM SIGN + +# Total code points: 326 + +# ================================================ + +0400..0481 ; CYRILLIC # L& [130] CYRILLIC CAPITAL LETTER IE WITH GRAVE..CYRILLIC SMALL LETTER KOPPA +0483..0486 ; CYRILLIC # Mn [4] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC PSILI PNEUMATA +048C..04C4 ; CYRILLIC # L& [57] CYRILLIC CAPITAL LETTER SEMISOFT SIGN..CYRILLIC SMALL LETTER KA WITH HOOK +04C7..04C8 ; CYRILLIC # L& [2] CYRILLIC CAPITAL LETTER EN WITH HOOK..CYRILLIC SMALL LETTER EN WITH HOOK +04CB..04CC ; CYRILLIC # L& [2] CYRILLIC CAPITAL LETTER KHAKASSIAN CHE..CYRILLIC SMALL LETTER KHAKASSIAN CHE +04D0..04F5 ; CYRILLIC # L& [38] CYRILLIC CAPITAL LETTER A WITH BREVE..CYRILLIC SMALL LETTER CHE WITH DIAERESIS +04F8..04F9 ; CYRILLIC # L& [2] CYRILLIC CAPITAL LETTER YERU WITH DIAERESIS..CYRILLIC SMALL LETTER YERU WITH DIAERESIS + +# Total code points: 235 + +# ================================================ + +0531..0556 ; ARMENIAN # L& [38] ARMENIAN CAPITAL LETTER AYB..ARMENIAN CAPITAL LETTER FEH +0559 ; ARMENIAN # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING +0561..0587 ; ARMENIAN # L& [39] ARMENIAN SMALL LETTER AYB..ARMENIAN SMALL LIGATURE ECH YIWN +FB13..FB17 ; ARMENIAN # L& [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SMALL LIGATURE MEN XEH + +# Total code points: 83 + +# ================================================ + +05D0..05EA ; HEBREW # Lo [27] HEBREW LETTER ALEF..HEBREW LETTER TAV +05F0..05F2 ; HEBREW # Lo [3] HEBREW LIGATURE YIDDISH DOUBLE VAV..HEBREW LIGATURE YIDDISH DOUBLE YOD +FB1D ; HEBREW # Lo HEBREW LETTER YOD WITH HIRIQ +FB1F..FB28 ; HEBREW # Lo [10] HEBREW LIGATURE YIDDISH YOD YOD PATAH..HEBREW LETTER WIDE TAV +FB2A..FB36 ; HEBREW # Lo [13] HEBREW LETTER SHIN WITH SHIN DOT..HEBREW LETTER ZAYIN WITH DAGESH +FB38..FB3C ; HEBREW # Lo [5] HEBREW LETTER TET WITH DAGESH..HEBREW LETTER LAMED WITH DAGESH +FB3E ; HEBREW # Lo HEBREW LETTER MEM WITH DAGESH +FB40..FB41 ; HEBREW # Lo [2] HEBREW LETTER NUN WITH DAGESH..HEBREW LETTER SAMEKH WITH DAGESH +FB43..FB44 ; HEBREW # Lo [2] HEBREW LETTER FINAL PE WITH DAGESH..HEBREW LETTER PE WITH DAGESH +FB46..FB4F ; HEBREW # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATURE ALEF LAMED + +# Total code points: 74 + +# ================================================ + +0621..063A ; ARABIC # Lo [26] ARABIC LETTER HAMZA..ARABIC LETTER GHAIN +0641..064A ; ARABIC # Lo [10] ARABIC LETTER FEH..ARABIC LETTER YEH +0671..06D3 ; ARABIC # Lo [99] ARABIC LETTER ALEF WASLA..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE +06D5 ; ARABIC # Lo ARABIC LETTER AE +06E5..06E6 ; ARABIC # Lm [2] ARABIC SMALL WAW..ARABIC SMALL YEH +06FA..06FC ; ARABIC # Lo [3] ARABIC LETTER SHEEN WITH DOT BELOW..ARABIC LETTER GHAIN WITH DOT BELOW +FB50..FBB1 ; ARABIC # Lo [98] ARABIC LETTER ALEF WASLA ISOLATED FORM..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE FINAL FORM +FBD3..FD3D ; ARABIC # Lo [363] ARABIC LETTER NG ISOLATED FORM..ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM +FD50..FD8F ; ARABIC # Lo [64] ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM..ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM +FD92..FDC7 ; ARABIC # Lo [54] ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM..ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM +FDF0..FDFB ; ARABIC # Lo [12] ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM..ARABIC LIGATURE JALLAJALALOUHOU +FE70..FE72 ; ARABIC # Lo [3] ARABIC FATHATAN ISOLATED FORM..ARABIC DAMMATAN ISOLATED FORM +FE74 ; ARABIC # Lo ARABIC KASRATAN ISOLATED FORM +FE76..FEFC ; ARABIC # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LAM WITH ALEF FINAL FORM + +# Total code points: 871 + +# ================================================ + +0710 ; SYRIAC # Lo SYRIAC LETTER ALAPH +0711 ; SYRIAC # Mn SYRIAC LETTER SUPERSCRIPT ALAPH +0712..072C ; SYRIAC # Lo [27] SYRIAC LETTER BETH..SYRIAC LETTER TAW +0730..074A ; SYRIAC # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH + +# Total code points: 56 + +# ================================================ + +0780..07A5 ; THAANA # Lo [38] THAANA LETTER HAA..THAANA LETTER WAAVU +07A6..07B0 ; THAANA # Mn [11] THAANA ABAFILI..THAANA SUKUN + +# Total code points: 49 + +# ================================================ + +0901..0902 ; DEVANAGARI # Mn [2] DEVANAGARI SIGN CANDRABINDU..DEVANAGARI SIGN ANUSVARA +0903 ; DEVANAGARI # Mc DEVANAGARI SIGN VISARGA +0905..0939 ; DEVANAGARI # Lo [53] DEVANAGARI LETTER A..DEVANAGARI LETTER HA +093C ; DEVANAGARI # Mn DEVANAGARI SIGN NUKTA +093D ; DEVANAGARI # Lo DEVANAGARI SIGN AVAGRAHA +093E..0940 ; DEVANAGARI # Mc [3] DEVANAGARI VOWEL SIGN AA..DEVANAGARI VOWEL SIGN II +0941..0948 ; DEVANAGARI # Mn [8] DEVANAGARI VOWEL SIGN U..DEVANAGARI VOWEL SIGN AI +0949..094C ; DEVANAGARI # Mc [4] DEVANAGARI VOWEL SIGN CANDRA O..DEVANAGARI VOWEL SIGN AU +094D ; DEVANAGARI # Mn DEVANAGARI SIGN VIRAMA +0950 ; DEVANAGARI # Lo DEVANAGARI OM +0951..0954 ; DEVANAGARI # Mn [4] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI ACUTE ACCENT +0958..0961 ; DEVANAGARI # Lo [10] DEVANAGARI LETTER QA..DEVANAGARI LETTER VOCALIC LL +0962..0963 ; DEVANAGARI # Mn [2] DEVANAGARI VOWEL SIGN VOCALIC L..DEVANAGARI VOWEL SIGN VOCALIC LL +0966..096F ; DEVANAGARI # Nd [10] DEVANAGARI DIGIT ZERO..DEVANAGARI DIGIT NINE + +# Total code points: 101 + +# ================================================ + +0981 ; BENGALI # Mn BENGALI SIGN CANDRABINDU +0985..098C ; BENGALI # Lo [8] BENGALI LETTER A..BENGALI LETTER VOCALIC L +098F..0990 ; BENGALI # Lo [2] BENGALI LETTER E..BENGALI LETTER AI +0993..09A8 ; BENGALI # Lo [22] BENGALI LETTER O..BENGALI LETTER NA +09AA..09B0 ; BENGALI # Lo [7] BENGALI LETTER PA..BENGALI LETTER RA +09B2 ; BENGALI # Lo BENGALI LETTER LA +09B6..09B9 ; BENGALI # Lo [4] BENGALI LETTER SHA..BENGALI LETTER HA +09BC ; BENGALI # Mn BENGALI SIGN NUKTA +09BE..09C0 ; BENGALI # Mc [3] BENGALI VOWEL SIGN AA..BENGALI VOWEL SIGN II +09C1..09C4 ; BENGALI # Mn [4] BENGALI VOWEL SIGN U..BENGALI VOWEL SIGN VOCALIC RR +09C7..09C8 ; BENGALI # Mc [2] BENGALI VOWEL SIGN E..BENGALI VOWEL SIGN AI +09CB..09CC ; BENGALI # Mc [2] BENGALI VOWEL SIGN O..BENGALI VOWEL SIGN AU +09CD ; BENGALI # Mn BENGALI SIGN VIRAMA +09D7 ; BENGALI # Mc BENGALI AU LENGTH MARK +09DC..09DD ; BENGALI # Lo [2] BENGALI LETTER RRA..BENGALI LETTER RHA +09DF..09E1 ; BENGALI # Lo [3] BENGALI LETTER YYA..BENGALI LETTER VOCALIC LL +09E2..09E3 ; BENGALI # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL +09E6..09EF ; BENGALI # Nd [10] BENGALI DIGIT ZERO..BENGALI DIGIT NINE +09F0..09F1 ; BENGALI # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL + +# Total code points: 78 + +# ================================================ + +0A02 ; GURMUKHI # Mn GURMUKHI SIGN BINDI +0A05..0A0A ; GURMUKHI # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU +0A0F..0A10 ; GURMUKHI # Lo [2] GURMUKHI LETTER EE..GURMUKHI LETTER AI +0A13..0A28 ; GURMUKHI # Lo [22] GURMUKHI LETTER OO..GURMUKHI LETTER NA +0A2A..0A30 ; GURMUKHI # Lo [7] GURMUKHI LETTER PA..GURMUKHI LETTER RA +0A32..0A33 ; GURMUKHI # Lo [2] GURMUKHI LETTER LA..GURMUKHI LETTER LLA +0A35..0A36 ; GURMUKHI # Lo [2] GURMUKHI LETTER VA..GURMUKHI LETTER SHA +0A38..0A39 ; GURMUKHI # Lo [2] GURMUKHI LETTER SA..GURMUKHI LETTER HA +0A3C ; GURMUKHI # Mn GURMUKHI SIGN NUKTA +0A3E..0A40 ; GURMUKHI # Mc [3] GURMUKHI VOWEL SIGN AA..GURMUKHI VOWEL SIGN II +0A41..0A42 ; GURMUKHI # Mn [2] GURMUKHI VOWEL SIGN U..GURMUKHI VOWEL SIGN UU +0A47..0A48 ; GURMUKHI # Mn [2] GURMUKHI VOWEL SIGN EE..GURMUKHI VOWEL SIGN AI +0A4B..0A4D ; GURMUKHI # Mn [3] GURMUKHI VOWEL SIGN OO..GURMUKHI SIGN VIRAMA +0A59..0A5C ; GURMUKHI # Lo [4] GURMUKHI LETTER KHHA..GURMUKHI LETTER RRA +0A5E ; GURMUKHI # Lo GURMUKHI LETTER FA +0A66..0A6F ; GURMUKHI # Nd [10] GURMUKHI DIGIT ZERO..GURMUKHI DIGIT NINE +0A70..0A71 ; GURMUKHI # Mn [2] GURMUKHI TIPPI..GURMUKHI ADDAK +0A72..0A74 ; GURMUKHI # Lo [3] GURMUKHI IRI..GURMUKHI EK ONKAR + +# Total code points: 75 + +# ================================================ + +0A81..0A82 ; GUJARATI # Mn [2] GUJARATI SIGN CANDRABINDU..GUJARATI SIGN ANUSVARA +0A83 ; GUJARATI # Mc GUJARATI SIGN VISARGA +0A85..0A8B ; GUJARATI # Lo [7] GUJARATI LETTER A..GUJARATI LETTER VOCALIC R +0A8D ; GUJARATI # Lo GUJARATI VOWEL CANDRA E +0A8F..0A91 ; GUJARATI # Lo [3] GUJARATI LETTER E..GUJARATI VOWEL CANDRA O +0A93..0AA8 ; GUJARATI # Lo [22] GUJARATI LETTER O..GUJARATI LETTER NA +0AAA..0AB0 ; GUJARATI # Lo [7] GUJARATI LETTER PA..GUJARATI LETTER RA +0AB2..0AB3 ; GUJARATI # Lo [2] GUJARATI LETTER LA..GUJARATI LETTER LLA +0AB5..0AB9 ; GUJARATI # Lo [5] GUJARATI LETTER VA..GUJARATI LETTER HA +0ABC ; GUJARATI # Mn GUJARATI SIGN NUKTA +0ABD ; GUJARATI # Lo GUJARATI SIGN AVAGRAHA +0ABE..0AC0 ; GUJARATI # Mc [3] GUJARATI VOWEL SIGN AA..GUJARATI VOWEL SIGN II +0AC1..0AC5 ; GUJARATI # Mn [5] GUJARATI VOWEL SIGN U..GUJARATI VOWEL SIGN CANDRA E +0AC7..0AC8 ; GUJARATI # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI +0AC9 ; GUJARATI # Mc GUJARATI VOWEL SIGN CANDRA O +0ACB..0ACC ; GUJARATI # Mc [2] GUJARATI VOWEL SIGN O..GUJARATI VOWEL SIGN AU +0ACD ; GUJARATI # Mn GUJARATI SIGN VIRAMA +0AD0 ; GUJARATI # Lo GUJARATI OM +0AE0 ; GUJARATI # Lo GUJARATI LETTER VOCALIC RR +0AE6..0AEF ; GUJARATI # Nd [10] GUJARATI DIGIT ZERO..GUJARATI DIGIT NINE + +# Total code points: 78 + +# ================================================ + +0B01 ; ORIYA # Mn ORIYA SIGN CANDRABINDU +0B02..0B03 ; ORIYA # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA +0B05..0B0C ; ORIYA # Lo [8] ORIYA LETTER A..ORIYA LETTER VOCALIC L +0B0F..0B10 ; ORIYA # Lo [2] ORIYA LETTER E..ORIYA LETTER AI +0B13..0B28 ; ORIYA # Lo [22] ORIYA LETTER O..ORIYA LETTER NA +0B2A..0B30 ; ORIYA # Lo [7] ORIYA LETTER PA..ORIYA LETTER RA +0B32..0B33 ; ORIYA # Lo [2] ORIYA LETTER LA..ORIYA LETTER LLA +0B36..0B39 ; ORIYA # Lo [4] ORIYA LETTER SHA..ORIYA LETTER HA +0B3C ; ORIYA # Mn ORIYA SIGN NUKTA +0B3D ; ORIYA # Lo ORIYA SIGN AVAGRAHA +0B3E ; ORIYA # Mc ORIYA VOWEL SIGN AA +0B3F ; ORIYA # Mn ORIYA VOWEL SIGN I +0B40 ; ORIYA # Mc ORIYA VOWEL SIGN II +0B41..0B43 ; ORIYA # Mn [3] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC R +0B47..0B48 ; ORIYA # Mc [2] ORIYA VOWEL SIGN E..ORIYA VOWEL SIGN AI +0B4B..0B4C ; ORIYA # Mc [2] ORIYA VOWEL SIGN O..ORIYA VOWEL SIGN AU +0B4D ; ORIYA # Mn ORIYA SIGN VIRAMA +0B56 ; ORIYA # Mn ORIYA AI LENGTH MARK +0B57 ; ORIYA # Mc ORIYA AU LENGTH MARK +0B5C..0B5D ; ORIYA # Lo [2] ORIYA LETTER RRA..ORIYA LETTER RHA +0B5F..0B61 ; ORIYA # Lo [3] ORIYA LETTER YYA..ORIYA LETTER VOCALIC LL +0B66..0B6F ; ORIYA # Nd [10] ORIYA DIGIT ZERO..ORIYA DIGIT NINE + +# Total code points: 78 + +# ================================================ + +0B82 ; TAMIL # Mn TAMIL SIGN ANUSVARA +0B83 ; TAMIL # Mc TAMIL SIGN VISARGA +0B85..0B8A ; TAMIL # Lo [6] TAMIL LETTER A..TAMIL LETTER UU +0B8E..0B90 ; TAMIL # Lo [3] TAMIL LETTER E..TAMIL LETTER AI +0B92..0B95 ; TAMIL # Lo [4] TAMIL LETTER O..TAMIL LETTER KA +0B99..0B9A ; TAMIL # Lo [2] TAMIL LETTER NGA..TAMIL LETTER CA +0B9C ; TAMIL # Lo TAMIL LETTER JA +0B9E..0B9F ; TAMIL # Lo [2] TAMIL LETTER NYA..TAMIL LETTER TTA +0BA3..0BA4 ; TAMIL # Lo [2] TAMIL LETTER NNA..TAMIL LETTER TA +0BA8..0BAA ; TAMIL # Lo [3] TAMIL LETTER NA..TAMIL LETTER PA +0BAE..0BB5 ; TAMIL # Lo [8] TAMIL LETTER MA..TAMIL LETTER VA +0BB7..0BB9 ; TAMIL # Lo [3] TAMIL LETTER SSA..TAMIL LETTER HA +0BBE..0BBF ; TAMIL # Mc [2] TAMIL VOWEL SIGN AA..TAMIL VOWEL SIGN I +0BC0 ; TAMIL # Mn TAMIL VOWEL SIGN II +0BC1..0BC2 ; TAMIL # Mc [2] TAMIL VOWEL SIGN U..TAMIL VOWEL SIGN UU +0BC6..0BC8 ; TAMIL # Mc [3] TAMIL VOWEL SIGN E..TAMIL VOWEL SIGN AI +0BCA..0BCC ; TAMIL # Mc [3] TAMIL VOWEL SIGN O..TAMIL VOWEL SIGN AU +0BCD ; TAMIL # Mn TAMIL SIGN VIRAMA +0BD7 ; TAMIL # Mc TAMIL AU LENGTH MARK +0BE7..0BEF ; TAMIL # Nd [9] TAMIL DIGIT ONE..TAMIL DIGIT NINE +0BF0..0BF2 ; TAMIL # No [3] TAMIL NUMBER TEN..TAMIL NUMBER ONE THOUSAND + +# Total code points: 61 + +# ================================================ + +0C01..0C03 ; TELUGU # Mc [3] TELUGU SIGN CANDRABINDU..TELUGU SIGN VISARGA +0C05..0C0C ; TELUGU # Lo [8] TELUGU LETTER A..TELUGU LETTER VOCALIC L +0C0E..0C10 ; TELUGU # Lo [3] TELUGU LETTER E..TELUGU LETTER AI +0C12..0C28 ; TELUGU # Lo [23] TELUGU LETTER O..TELUGU LETTER NA +0C2A..0C33 ; TELUGU # Lo [10] TELUGU LETTER PA..TELUGU LETTER LLA +0C35..0C39 ; TELUGU # Lo [5] TELUGU LETTER VA..TELUGU LETTER HA +0C3E..0C40 ; TELUGU # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II +0C41..0C44 ; TELUGU # Mc [4] TELUGU VOWEL SIGN U..TELUGU VOWEL SIGN VOCALIC RR +0C46..0C48 ; TELUGU # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI +0C4A..0C4D ; TELUGU # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA +0C55..0C56 ; TELUGU # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK +0C60..0C61 ; TELUGU # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL +0C66..0C6F ; TELUGU # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE + +# Total code points: 80 + +# ================================================ + +0C82..0C83 ; KANNADA # Mc [2] KANNADA SIGN ANUSVARA..KANNADA SIGN VISARGA +0C85..0C8C ; KANNADA # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L +0C8E..0C90 ; KANNADA # Lo [3] KANNADA LETTER E..KANNADA LETTER AI +0C92..0CA8 ; KANNADA # Lo [23] KANNADA LETTER O..KANNADA LETTER NA +0CAA..0CB3 ; KANNADA # Lo [10] KANNADA LETTER PA..KANNADA LETTER LLA +0CB5..0CB9 ; KANNADA # Lo [5] KANNADA LETTER VA..KANNADA LETTER HA +0CBE ; KANNADA # Mc KANNADA VOWEL SIGN AA +0CBF ; KANNADA # Mn KANNADA VOWEL SIGN I +0CC0..0CC4 ; KANNADA # Mc [5] KANNADA VOWEL SIGN II..KANNADA VOWEL SIGN VOCALIC RR +0CC6 ; KANNADA # Mn KANNADA VOWEL SIGN E +0CC7..0CC8 ; KANNADA # Mc [2] KANNADA VOWEL SIGN EE..KANNADA VOWEL SIGN AI +0CCA..0CCB ; KANNADA # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO +0CCC..0CCD ; KANNADA # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA +0CD5..0CD6 ; KANNADA # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK +0CDE ; KANNADA # Lo KANNADA LETTER FA +0CE0..0CE1 ; KANNADA # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL +0CE6..0CEF ; KANNADA # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE + +# Total code points: 80 + +# ================================================ + +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..0D28 ; MALAYALAM # Lo [23] MALAYALAM LETTER O..MALAYALAM LETTER NA +0D2A..0D39 ; MALAYALAM # Lo [16] MALAYALAM LETTER PA..MALAYALAM LETTER HA +0D3E..0D40 ; MALAYALAM # Mc [3] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN II +0D41..0D43 ; MALAYALAM # Mn [3] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC R +0D46..0D48 ; MALAYALAM # Mc [3] MALAYALAM VOWEL SIGN E..MALAYALAM VOWEL SIGN AI +0D4A..0D4C ; MALAYALAM # Mc [3] MALAYALAM VOWEL SIGN O..MALAYALAM VOWEL SIGN AU +0D4D ; MALAYALAM # Mn MALAYALAM SIGN VIRAMA +0D57 ; MALAYALAM # Mc MALAYALAM AU LENGTH MARK +0D60..0D61 ; MALAYALAM # Lo [2] MALAYALAM LETTER VOCALIC RR..MALAYALAM LETTER VOCALIC LL +0D66..0D6F ; MALAYALAM # Nd [10] MALAYALAM DIGIT ZERO..MALAYALAM DIGIT NINE + +# Total code points: 78 + +# ================================================ + +0D82..0D83 ; SINHALA # Mc [2] SINHALA SIGN ANUSVARAYA..SINHALA SIGN VISARGAYA +0D85..0D96 ; SINHALA # Lo [18] SINHALA LETTER AYANNA..SINHALA LETTER AUYANNA +0D9A..0DB1 ; SINHALA # Lo [24] SINHALA LETTER ALPAPRAANA KAYANNA..SINHALA LETTER DANTAJA NAYANNA +0DB3..0DBB ; SINHALA # Lo [9] SINHALA LETTER SANYAKA DAYANNA..SINHALA LETTER RAYANNA +0DBD ; SINHALA # Lo SINHALA LETTER DANTAJA LAYANNA +0DC0..0DC6 ; SINHALA # Lo [7] SINHALA LETTER VAYANNA..SINHALA LETTER FAYANNA +0DCA ; SINHALA # Mn SINHALA SIGN AL-LAKUNA +0DCF..0DD1 ; SINHALA # Mc [3] SINHALA VOWEL SIGN AELA-PILLA..SINHALA VOWEL SIGN DIGA AEDA-PILLA +0DD2..0DD4 ; SINHALA # Mn [3] SINHALA VOWEL SIGN KETTI IS-PILLA..SINHALA VOWEL SIGN KETTI PAA-PILLA +0DD6 ; SINHALA # Mn SINHALA VOWEL SIGN DIGA PAA-PILLA +0DD8..0DDF ; SINHALA # Mc [8] SINHALA VOWEL SIGN GAETTA-PILLA..SINHALA VOWEL SIGN GAYANUKITTA +0DF2..0DF3 ; SINHALA # Mc [2] SINHALA VOWEL SIGN DIGA GAETTA-PILLA..SINHALA VOWEL SIGN DIGA GAYANUKITTA + +# Total code points: 79 + +# ================================================ + +0E01..0E30 ; THAI # Lo [48] THAI CHARACTER KO KAI..THAI CHARACTER SARA A +0E31 ; THAI # Mn THAI CHARACTER MAI HAN-AKAT +0E32..0E33 ; THAI # Lo [2] THAI CHARACTER SARA AA..THAI CHARACTER SARA AM +0E34..0E3A ; THAI # Mn [7] THAI CHARACTER SARA I..THAI CHARACTER PHINTHU +0E40..0E45 ; THAI # Lo [6] THAI CHARACTER SARA E..THAI CHARACTER LAKKHANGYAO +0E46 ; THAI # Lm THAI CHARACTER MAIYAMOK +0E47..0E4E ; THAI # Mn [8] THAI CHARACTER MAITAIKHU..THAI CHARACTER YAMAKKAN +0E50..0E59 ; THAI # Nd [10] THAI DIGIT ZERO..THAI DIGIT NINE + +# Total code points: 83 + +# ================================================ + +0E81..0E82 ; LAO # Lo [2] LAO LETTER KO..LAO LETTER KHO SUNG +0E84 ; LAO # Lo LAO LETTER KHO TAM +0E87..0E88 ; LAO # Lo [2] LAO LETTER NGO..LAO LETTER CO +0E8A ; LAO # Lo LAO LETTER SO TAM +0E8D ; LAO # Lo LAO LETTER NYO +0E94..0E97 ; LAO # Lo [4] LAO LETTER DO..LAO LETTER THO TAM +0E99..0E9F ; LAO # Lo [7] LAO LETTER NO..LAO LETTER FO SUNG +0EA1..0EA3 ; LAO # Lo [3] LAO LETTER MO..LAO LETTER LO LING +0EA5 ; LAO # Lo LAO LETTER LO LOOT +0EA7 ; LAO # Lo LAO LETTER WO +0EAA..0EAB ; LAO # Lo [2] LAO LETTER SO SUNG..LAO LETTER HO SUNG +0EAD..0EB0 ; LAO # Lo [4] LAO LETTER O..LAO VOWEL SIGN A +0EB1 ; LAO # Mn LAO VOWEL SIGN MAI KAN +0EB2..0EB3 ; LAO # Lo [2] LAO VOWEL SIGN AA..LAO VOWEL SIGN AM +0EB4..0EB9 ; LAO # Mn [6] LAO VOWEL SIGN I..LAO VOWEL SIGN UU +0EBB..0EBC ; LAO # Mn [2] LAO VOWEL SIGN MAI KON..LAO SEMIVOWEL SIGN LO +0EBD ; LAO # Lo LAO SEMIVOWEL SIGN NYO +0EC0..0EC4 ; LAO # Lo [5] LAO VOWEL SIGN E..LAO VOWEL SIGN AI +0EC6 ; LAO # Lm LAO KO LA +0EC8..0ECD ; LAO # Mn [6] LAO TONE MAI EK..LAO NIGGAHITA +0ED0..0ED9 ; LAO # Nd [10] LAO DIGIT ZERO..LAO DIGIT NINE +0EDC..0EDD ; LAO # Lo [2] LAO HO NO..LAO HO MO + +# Total code points: 65 + +# ================================================ + +0F00 ; TIBETAN # Lo TIBETAN SYLLABLE OM +0F18..0F19 ; TIBETAN # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS +0F20..0F29 ; TIBETAN # Nd [10] TIBETAN DIGIT ZERO..TIBETAN DIGIT NINE +0F2A..0F33 ; TIBETAN # No [10] TIBETAN DIGIT HALF ONE..TIBETAN DIGIT HALF ZERO +0F35 ; TIBETAN # Mn TIBETAN MARK NGAS BZUNG NYI ZLA +0F37 ; TIBETAN # Mn TIBETAN MARK NGAS BZUNG SGOR RTAGS +0F39 ; TIBETAN # Mn TIBETAN MARK TSA -PHRU +0F40..0F47 ; TIBETAN # Lo [8] TIBETAN LETTER KA..TIBETAN LETTER JA +0F49..0F6A ; TIBETAN # Lo [34] TIBETAN LETTER NYA..TIBETAN LETTER FIXED-FORM RA +0F71..0F7E ; TIBETAN # Mn [14] TIBETAN VOWEL SIGN AA..TIBETAN SIGN RJES SU NGA RO +0F7F ; TIBETAN # Mc TIBETAN SIGN RNAM BCAD +0F80..0F84 ; TIBETAN # Mn [5] TIBETAN VOWEL SIGN REVERSED I..TIBETAN MARK HALANTA +0F86..0F87 ; TIBETAN # Mn [2] TIBETAN SIGN LCI RTAGS..TIBETAN SIGN YANG RTAGS +0F88..0F8B ; TIBETAN # Lo [4] TIBETAN SIGN LCE TSA CAN..TIBETAN SIGN GRU MED RGYINGS +0F90..0F97 ; TIBETAN # Mn [8] TIBETAN SUBJOINED LETTER KA..TIBETAN SUBJOINED LETTER JA +0F99..0FBC ; TIBETAN # Mn [36] TIBETAN SUBJOINED LETTER NYA..TIBETAN SUBJOINED LETTER FIXED-FORM RA +0FC6 ; TIBETAN # Mn TIBETAN SYMBOL PADMA GDAN + +# Total code points: 139 + +# ================================================ + +1000..1021 ; MYANMAR # Lo [34] MYANMAR LETTER KA..MYANMAR LETTER A +1023..1027 ; MYANMAR # Lo [5] MYANMAR LETTER I..MYANMAR LETTER E +1029..102A ; MYANMAR # Lo [2] MYANMAR LETTER O..MYANMAR LETTER AU +102C ; MYANMAR # Mc MYANMAR VOWEL SIGN AA +102D..1030 ; MYANMAR # Mn [4] MYANMAR VOWEL SIGN I..MYANMAR VOWEL SIGN UU +1031 ; MYANMAR # Mc MYANMAR VOWEL SIGN E +1032 ; MYANMAR # Mn MYANMAR VOWEL SIGN AI +1036..1037 ; MYANMAR # Mn [2] MYANMAR SIGN ANUSVARA..MYANMAR SIGN DOT BELOW +1038 ; MYANMAR # Mc MYANMAR SIGN VISARGA +1039 ; MYANMAR # Mn MYANMAR SIGN VIRAMA +1040..1049 ; MYANMAR # Nd [10] MYANMAR DIGIT ZERO..MYANMAR DIGIT NINE +1050..1055 ; MYANMAR # Lo [6] MYANMAR LETTER SHA..MYANMAR LETTER VOCALIC LL +1056..1057 ; MYANMAR # Mc [2] MYANMAR VOWEL SIGN VOCALIC R..MYANMAR VOWEL SIGN VOCALIC RR +1058..1059 ; MYANMAR # Mn [2] MYANMAR VOWEL SIGN VOCALIC L..MYANMAR VOWEL SIGN VOCALIC LL + +# Total code points: 72 + +# ================================================ + +10A0..10C5 ; GEORGIAN # L& [38] GEORGIAN CAPITAL LETTER AN..GEORGIAN CAPITAL LETTER HOE +10D0..10F6 ; GEORGIAN # Lo [39] GEORGIAN LETTER AN..GEORGIAN LETTER FI + +# Total code points: 77 + +# ================================================ + +1100..1159 ; HANGUL # Lo [90] HANGUL CHOSEONG KIYEOK..HANGUL CHOSEONG YEORINHIEUH +115F..11A2 ; HANGUL # Lo [68] HANGUL CHOSEONG FILLER..HANGUL JUNGSEONG SSANGARAEA +11A8..11F9 ; HANGUL # Lo [82] HANGUL JONGSEONG KIYEOK..HANGUL JONGSEONG YEORINHIEUH +3131..318E ; HANGUL # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE +AC00..D7A3 ; HANGUL # Lo [11172] HANGUL SYLLABLE GA..HANGUL SYLLABLE HIH +FFA0..FFBE ; HANGUL # Lo [31] HALFWIDTH HANGUL FILLER..HALFWIDTH HANGUL LETTER HIEUH +FFC2..FFC7 ; HANGUL # Lo [6] HALFWIDTH HANGUL LETTER A..HALFWIDTH HANGUL LETTER E +FFCA..FFCF ; HANGUL # Lo [6] HALFWIDTH HANGUL LETTER YEO..HALFWIDTH HANGUL LETTER OE +FFD2..FFD7 ; HANGUL # Lo [6] HALFWIDTH HANGUL LETTER YO..HALFWIDTH HANGUL LETTER YU +FFDA..FFDC ; HANGUL # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I + +# Total code points: 11558 + +# ================================================ + +1200..1206 ; ETHIOPIC # Lo [7] ETHIOPIC SYLLABLE HA..ETHIOPIC SYLLABLE HO +1208..1246 ; ETHIOPIC # Lo [63] ETHIOPIC SYLLABLE LA..ETHIOPIC SYLLABLE QO +1248 ; ETHIOPIC # Lo ETHIOPIC SYLLABLE QWA +124A..124D ; ETHIOPIC # Lo [4] ETHIOPIC SYLLABLE QWI..ETHIOPIC SYLLABLE QWE +1250..1256 ; ETHIOPIC # Lo [7] ETHIOPIC SYLLABLE QHA..ETHIOPIC SYLLABLE QHO +1258 ; ETHIOPIC # Lo ETHIOPIC SYLLABLE QHWA +125A..125D ; ETHIOPIC # Lo [4] ETHIOPIC SYLLABLE QHWI..ETHIOPIC SYLLABLE QHWE +1260..1286 ; ETHIOPIC # Lo [39] ETHIOPIC SYLLABLE BA..ETHIOPIC SYLLABLE XO +1288 ; ETHIOPIC # Lo ETHIOPIC SYLLABLE XWA +128A..128D ; ETHIOPIC # Lo [4] ETHIOPIC SYLLABLE XWI..ETHIOPIC SYLLABLE XWE +1290..12AE ; ETHIOPIC # Lo [31] ETHIOPIC SYLLABLE NA..ETHIOPIC SYLLABLE KO +12B0 ; ETHIOPIC # Lo ETHIOPIC SYLLABLE KWA +12B2..12B5 ; ETHIOPIC # Lo [4] ETHIOPIC SYLLABLE KWI..ETHIOPIC SYLLABLE KWE +12B8..12BE ; ETHIOPIC # Lo [7] ETHIOPIC SYLLABLE KXA..ETHIOPIC SYLLABLE KXO +12C0 ; ETHIOPIC # Lo ETHIOPIC SYLLABLE KXWA +12C2..12C5 ; ETHIOPIC # Lo [4] ETHIOPIC SYLLABLE KXWI..ETHIOPIC SYLLABLE KXWE +12C8..12CE ; ETHIOPIC # Lo [7] ETHIOPIC SYLLABLE WA..ETHIOPIC SYLLABLE WO +12D0..12D6 ; ETHIOPIC # Lo [7] ETHIOPIC SYLLABLE PHARYNGEAL A..ETHIOPIC SYLLABLE PHARYNGEAL O +12D8..12EE ; ETHIOPIC # Lo [23] ETHIOPIC SYLLABLE ZA..ETHIOPIC SYLLABLE YO +12F0..130E ; ETHIOPIC # Lo [31] ETHIOPIC SYLLABLE DA..ETHIOPIC SYLLABLE GO +1310 ; ETHIOPIC # Lo ETHIOPIC SYLLABLE GWA +1312..1315 ; ETHIOPIC # Lo [4] ETHIOPIC SYLLABLE GWI..ETHIOPIC SYLLABLE GWE +1318..131E ; ETHIOPIC # Lo [7] ETHIOPIC SYLLABLE GGA..ETHIOPIC SYLLABLE GGO +1320..1346 ; ETHIOPIC # Lo [39] ETHIOPIC SYLLABLE THA..ETHIOPIC SYLLABLE TZO +1348..135A ; ETHIOPIC # Lo [19] ETHIOPIC SYLLABLE FA..ETHIOPIC SYLLABLE FYA +1369..1371 ; ETHIOPIC # Nd [9] ETHIOPIC DIGIT ONE..ETHIOPIC DIGIT NINE +1372..137C ; ETHIOPIC # No [11] ETHIOPIC NUMBER TEN..ETHIOPIC NUMBER TEN THOUSAND + +# Total code points: 337 + +# ================================================ + +13A0..13F4 ; CHEROKEE # Lo [85] CHEROKEE LETTER A..CHEROKEE LETTER YV + +# Total code points: 85 + +# ================================================ + +1401..166C ; CANADIAN-ABORIGINAL # Lo [620] CANADIAN SYLLABICS E..CANADIAN SYLLABICS CARRIER TTSA +166F..1676 ; CANADIAN-ABORIGINAL # Lo [8] CANADIAN SYLLABICS QAI..CANADIAN SYLLABICS NNGAA + +# Total code points: 628 + +# ================================================ + +1681..169A ; OGHAM # Lo [26] OGHAM LETTER BEITH..OGHAM LETTER PEITH + +# Total code points: 26 + +# ================================================ + +16A0..16EA ; RUNIC # Lo [75] RUNIC LETTER FEHU FEOH FE F..RUNIC LETTER X +16EE..16F0 ; RUNIC # Nl [3] RUNIC ARLAUG SYMBOL..RUNIC BELGTHOR SYMBOL + +# Total code points: 78 + +# ================================================ + +1780..17B3 ; KHMER # Lo [52] KHMER LETTER KA..KHMER INDEPENDENT VOWEL QAU +17B4..17B6 ; KHMER # Mc [3] KHMER VOWEL INHERENT AQ..KHMER VOWEL SIGN AA +17B7..17BD ; KHMER # Mn [7] KHMER VOWEL SIGN I..KHMER VOWEL SIGN UA +17BE..17C5 ; KHMER # Mc [8] KHMER VOWEL SIGN OE..KHMER VOWEL SIGN AU +17C6 ; KHMER # Mn KHMER SIGN NIKAHIT +17C7..17C8 ; KHMER # Mc [2] KHMER SIGN REAHMUK..KHMER SIGN YUUKALEAPINTU +17C9..17D3 ; KHMER # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT +17E0..17E9 ; KHMER # Nd [10] KHMER DIGIT ZERO..KHMER DIGIT NINE + +# Total code points: 94 + +# ================================================ + +1810..1819 ; MONGOLIAN # Nd [10] MONGOLIAN DIGIT ZERO..MONGOLIAN DIGIT NINE +1820..1842 ; MONGOLIAN # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI +1843 ; MONGOLIAN # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN +1844..1877 ; MONGOLIAN # Lo [52] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER MANCHU ZHA +1880..18A8 ; MONGOLIAN # Lo [41] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER MANCHU ALI GALI BHA +18A9 ; MONGOLIAN # Mn MONGOLIAN LETTER ALI GALI DAGALGA + +# Total code points: 140 + +# ================================================ + +3041..3094 ; HIRAGANA # Lo [84] HIRAGANA LETTER SMALL A..HIRAGANA LETTER VU +309D..309E ; HIRAGANA # Lm [2] HIRAGANA ITERATION MARK..HIRAGANA VOICED ITERATION MARK + +# Total code points: 86 + +# ================================================ + +30A1..30FA ; KATAKANA # Lo [90] KATAKANA LETTER SMALL A..KATAKANA LETTER VO +30FD..30FE ; KATAKANA # Lm [2] KATAKANA ITERATION MARK..KATAKANA VOICED ITERATION MARK +FF66..FF6F ; KATAKANA # Lo [10] HALFWIDTH KATAKANA LETTER WO..HALFWIDTH KATAKANA LETTER SMALL TU +FF71..FF9D ; KATAKANA # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAKANA LETTER N + +# Total code points: 147 + +# ================================================ + +3105..312C ; BOPOMOFO # Lo [40] BOPOMOFO LETTER B..BOPOMOFO LETTER GN +31A0..31B7 ; BOPOMOFO # Lo [24] BOPOMOFO LETTER BU..BOPOMOFO FINAL LETTER H + +# Total code points: 64 + +# ================================================ + +2E80..2E99 ; HAN # So [26] CJK RADICAL REPEAT..CJK RADICAL RAP +2E9B..2EF3 ; HAN # So [89] CJK RADICAL CHOKE..CJK RADICAL C-SIMPLIFIED TURTLE +2F00..2FD5 ; HAN # So [214] KANGXI RADICAL ONE..KANGXI RADICAL FLUTE +3005 ; HAN # Lm IDEOGRAPHIC ITERATION MARK +3007 ; HAN # Nl IDEOGRAPHIC NUMBER ZERO +3021..3029 ; HAN # Nl [9] HANGZHOU NUMERAL ONE..HANGZHOU NUMERAL NINE +3038..303A ; HAN # Nl [3] HANGZHOU NUMERAL TEN..HANGZHOU NUMERAL THIRTY +3400..4DB5 ; HAN # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 +4E00..9FA5 ; HAN # Lo [20902] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FA5 +F900..FA2D ; HAN # Lo [302] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA2D +20000..2A6D6 ; HAN # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6 +2F800..2FA1D ; HAN # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D + +# Total code points: 71382 + +# ================================================ + +A000..A48C ; YI # Lo [1165] YI SYLLABLE IT..YI SYLLABLE YYR +A490..A4A1 ; YI # So [18] YI RADICAL QOT..YI RADICAL GA +A4A4..A4B3 ; YI # So [16] YI RADICAL DDUR..YI RADICAL JO +A4B5..A4C0 ; YI # So [12] YI RADICAL JJY..YI RADICAL SHAT +A4C2..A4C4 ; YI # So [3] YI RADICAL SHOP..YI RADICAL ZZIET +A4C6 ; YI # So YI RADICAL KE + +# Total code points: 1215 + +# ================================================ + +10300..1031E ; OLD-ITALIC # Lo [31] OLD ITALIC LETTER A..OLD ITALIC LETTER UU + +# Total code points: 31 + +# ================================================ + +10330..10349 ; GOTHIC # Lo [26] GOTHIC LETTER AHSA..GOTHIC LETTER OTHAL +1034A ; GOTHIC # Nl GOTHIC LETTER NINE HUNDRED + +# Total code points: 27 + +# ================================================ + +10400..10425 ; DESERET # L& [38] DESERET CAPITAL LETTER LONG I..DESERET CAPITAL LETTER ENG +10428..1044D ; DESERET # L& [38] DESERET SMALL LETTER LONG I..DESERET SMALL LETTER ENG + +# Total code points: 76 + +# ================================================ + +0300..034E ; INHERITED # Mn [79] COMBINING GRAVE ACCENT..COMBINING UPWARDS ARROW BELOW +0360..0362 ; INHERITED # Mn [3] COMBINING DOUBLE TILDE..COMBINING DOUBLE RIGHTWARDS ARROW BELOW +0488..0489 ; INHERITED # Me [2] COMBINING CYRILLIC HUNDRED THOUSANDS SIGN..COMBINING CYRILLIC MILLIONS SIGN +0591..05A1 ; INHERITED # Mn [17] HEBREW ACCENT ETNAHTA..HEBREW ACCENT PAZER +05A3..05B9 ; INHERITED # Mn [23] HEBREW ACCENT MUNAH..HEBREW POINT HOLAM +05BB..05BD ; INHERITED # Mn [3] HEBREW POINT QUBUTS..HEBREW POINT METEG +05BF ; INHERITED # Mn HEBREW POINT RAFE +05C1..05C2 ; INHERITED # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT +05C4 ; INHERITED # Mn HEBREW MARK UPPER DOT +064B..0655 ; INHERITED # Mn [11] ARABIC FATHATAN..ARABIC HAMZA BELOW +0670 ; INHERITED # Mn ARABIC LETTER SUPERSCRIPT ALEF +06D6..06DC ; INHERITED # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN +06DD..06DE ; INHERITED # Me [2] ARABIC END OF AYAH..ARABIC START OF RUB EL HIZB +06DF..06E4 ; INHERITED # Mn [6] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH MADDA +06E7..06E8 ; INHERITED # Mn [2] ARABIC SMALL HIGH YEH..ARABIC SMALL HIGH NOON +06EA..06ED ; INHERITED # Mn [4] ARABIC EMPTY CENTRE LOW STOP..ARABIC SMALL LOW MEEM +20D0..20DC ; INHERITED # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE +20DD..20E0 ; INHERITED # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH +20E1 ; INHERITED # Mn COMBINING LEFT RIGHT ARROW ABOVE +20E2..20E3 ; INHERITED # Me [2] COMBINING ENCLOSING SCREEN..COMBINING ENCLOSING KEYCAP +302A..302F ; INHERITED # Mn [6] IDEOGRAPHIC LEVEL TONE MARK..HANGUL DOUBLE DOT TONE MARK +3099..309A ; INHERITED # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK +FB1E ; INHERITED # Mn HEBREW POINT JUDEO-SPANISH VARIKA +FE20..FE23 ; INHERITED # Mn [4] COMBINING LIGATURE LEFT HALF..COMBINING DOUBLE TILDE RIGHT HALF +1D167..1D169 ; INHERITED # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 +1D17B..1D182 ; INHERITED # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE +1D185..1D18B ; INHERITED # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE +1D1AA..1D1AD ; INHERITED # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO + +# Total code points: 219 + diff --git a/lib/unicode/Unicode.txt b/lib/unicode/Unicode.txt index 72d7f78d75..90f047aceb 100644 --- a/lib/unicode/Unicode.txt +++ b/lib/unicode/Unicode.txt @@ -11187,10 +11187,10 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1D1BA;MUSICAL SYMBOL SEMIBREVIS BLACK;So;0;L;;;;;N;;;;; 1D1BB;MUSICAL SYMBOL MINIMA;So;0;L;1D1B9 1D165;;;;N;;;;; 1D1BC;MUSICAL SYMBOL MINIMA BLACK;So;0;L;1D1BA 1D165;;;;N;;;;; -1D1BD;MUSICAL SYMBOL SEMIMINIMA WHITE;So;0;L;1D1B9 1D165 1D16E;;;;N;;;;; -1D1BE;MUSICAL SYMBOL SEMIMINIMA BLACK;So;0;L;1D1BA 1D165 1D16E;;;;N;;;;; -1D1BF;MUSICAL SYMBOL FUSA WHITE;So;0;L;1D1B9 1D165 1D16F;;;;N;;;;; -1D1C0;MUSICAL SYMBOL FUSA BLACK;So;0;L;1D1BA 1D165 1D16F;;;;N;;;;; +1D1BD;MUSICAL SYMBOL SEMIMINIMA WHITE;So;0;L;1D1BB 1D16E;;;;N;;;;; +1D1BE;MUSICAL SYMBOL SEMIMINIMA BLACK;So;0;L;1D1BC 1D16E;;;;N;;;;; +1D1BF;MUSICAL SYMBOL FUSA WHITE;So;0;L;1D1BB 1D16F;;;;N;;;;; +1D1C0;MUSICAL SYMBOL FUSA BLACK;So;0;L;1D1BC 1D16F;;;;N;;;;; 1D1C1;MUSICAL SYMBOL LONGA PERFECTA REST;So;0;L;;;;;N;;;;; 1D1C2;MUSICAL SYMBOL LONGA IMPERFECTA REST;So;0;L;;;;;N;;;;; 1D1C3;MUSICAL SYMBOL BREVIS REST;So;0;L;;;;;N;;;;; @@ -11896,7 +11896,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1D6BE;MATHEMATICAL BOLD CAPITAL CHI;Lu;0;L;<font> 03A7;;;;N;;;;; 1D6BF;MATHEMATICAL BOLD CAPITAL PSI;Lu;0;L;<font> 03A8;;;;N;;;;; 1D6C0;MATHEMATICAL BOLD CAPITAL OMEGA;Lu;0;L;<font> 03A9;;;;N;;;;; -1D6C1;MATHEMATICAL BOLD NABLA;Ll;0;L;<font> 2207;;;;N;;;;; +1D6C1;MATHEMATICAL BOLD NABLA;Sm;0;L;<font> 2207;;;;N;;;;; 1D6C2;MATHEMATICAL BOLD SMALL ALPHA;Ll;0;L;<font> 03B1;;;;N;;;;; 1D6C3;MATHEMATICAL BOLD SMALL BETA;Ll;0;L;<font> 03B2;;;;N;;;;; 1D6C4;MATHEMATICAL BOLD SMALL GAMMA;Ll;0;L;<font> 03B3;;;;N;;;;; @@ -11922,7 +11922,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1D6D8;MATHEMATICAL BOLD SMALL CHI;Ll;0;L;<font> 03C7;;;;N;;;;; 1D6D9;MATHEMATICAL BOLD SMALL PSI;Ll;0;L;<font> 03C8;;;;N;;;;; 1D6DA;MATHEMATICAL BOLD SMALL OMEGA;Ll;0;L;<font> 03C9;;;;N;;;;; -1D6DB;MATHEMATICAL BOLD PARTIAL DIFFERENTIAL;Ll;0;L;<font> 2202;;;;N;;;;; +1D6DB;MATHEMATICAL BOLD PARTIAL DIFFERENTIAL;Sm;0;L;<font> 2202;;;;N;;;;; 1D6DC;MATHEMATICAL BOLD EPSILON SYMBOL;Ll;0;L;<font> 03F5;;;;N;;;;; 1D6DD;MATHEMATICAL BOLD THETA SYMBOL;Ll;0;L;<font> 03D1;;;;N;;;;; 1D6DE;MATHEMATICAL BOLD KAPPA SYMBOL;Ll;0;L;<font> 03F0;;;;N;;;;; @@ -11954,7 +11954,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1D6F8;MATHEMATICAL ITALIC CAPITAL CHI;Lu;0;L;<font> 03A7;;;;N;;;;; 1D6F9;MATHEMATICAL ITALIC CAPITAL PSI;Lu;0;L;<font> 03A8;;;;N;;;;; 1D6FA;MATHEMATICAL ITALIC CAPITAL OMEGA;Lu;0;L;<font> 03A9;;;;N;;;;; -1D6FB;MATHEMATICAL ITALIC NABLA;Ll;0;L;<font> 2207;;;;N;;;;; +1D6FB;MATHEMATICAL ITALIC NABLA;Sm;0;L;<font> 2207;;;;N;;;;; 1D6FC;MATHEMATICAL ITALIC SMALL ALPHA;Ll;0;L;<font> 03B1;;;;N;;;;; 1D6FD;MATHEMATICAL ITALIC SMALL BETA;Ll;0;L;<font> 03B2;;;;N;;;;; 1D6FE;MATHEMATICAL ITALIC SMALL GAMMA;Ll;0;L;<font> 03B3;;;;N;;;;; @@ -11980,7 +11980,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1D712;MATHEMATICAL ITALIC SMALL CHI;Ll;0;L;<font> 03C7;;;;N;;;;; 1D713;MATHEMATICAL ITALIC SMALL PSI;Ll;0;L;<font> 03C8;;;;N;;;;; 1D714;MATHEMATICAL ITALIC SMALL OMEGA;Ll;0;L;<font> 03C9;;;;N;;;;; -1D715;MATHEMATICAL ITALIC PARTIAL DIFFERENTIAL;Ll;0;L;<font> 2202;;;;N;;;;; +1D715;MATHEMATICAL ITALIC PARTIAL DIFFERENTIAL;Sm;0;L;<font> 2202;;;;N;;;;; 1D716;MATHEMATICAL ITALIC EPSILON SYMBOL;Ll;0;L;<font> 03F5;;;;N;;;;; 1D717;MATHEMATICAL ITALIC THETA SYMBOL;Ll;0;L;<font> 03D1;;;;N;;;;; 1D718;MATHEMATICAL ITALIC KAPPA SYMBOL;Ll;0;L;<font> 03F0;;;;N;;;;; @@ -12012,7 +12012,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1D732;MATHEMATICAL BOLD ITALIC CAPITAL CHI;Lu;0;L;<font> 03A7;;;;N;;;;; 1D733;MATHEMATICAL BOLD ITALIC CAPITAL PSI;Lu;0;L;<font> 03A8;;;;N;;;;; 1D734;MATHEMATICAL BOLD ITALIC CAPITAL OMEGA;Lu;0;L;<font> 03A9;;;;N;;;;; -1D735;MATHEMATICAL BOLD ITALIC NABLA;Ll;0;L;<font> 2207;;;;N;;;;; +1D735;MATHEMATICAL BOLD ITALIC NABLA;Sm;0;L;<font> 2207;;;;N;;;;; 1D736;MATHEMATICAL BOLD ITALIC SMALL ALPHA;Ll;0;L;<font> 03B1;;;;N;;;;; 1D737;MATHEMATICAL BOLD ITALIC SMALL BETA;Ll;0;L;<font> 03B2;;;;N;;;;; 1D738;MATHEMATICAL BOLD ITALIC SMALL GAMMA;Ll;0;L;<font> 03B3;;;;N;;;;; @@ -12038,7 +12038,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1D74C;MATHEMATICAL BOLD ITALIC SMALL CHI;Ll;0;L;<font> 03C7;;;;N;;;;; 1D74D;MATHEMATICAL BOLD ITALIC SMALL PSI;Ll;0;L;<font> 03C8;;;;N;;;;; 1D74E;MATHEMATICAL BOLD ITALIC SMALL OMEGA;Ll;0;L;<font> 03C9;;;;N;;;;; -1D74F;MATHEMATICAL BOLD ITALIC PARTIAL DIFFERENTIAL;Ll;0;L;<font> 2202;;;;N;;;;; +1D74F;MATHEMATICAL BOLD ITALIC PARTIAL DIFFERENTIAL;Sm;0;L;<font> 2202;;;;N;;;;; 1D750;MATHEMATICAL BOLD ITALIC EPSILON SYMBOL;Ll;0;L;<font> 03F5;;;;N;;;;; 1D751;MATHEMATICAL BOLD ITALIC THETA SYMBOL;Ll;0;L;<font> 03D1;;;;N;;;;; 1D752;MATHEMATICAL BOLD ITALIC KAPPA SYMBOL;Ll;0;L;<font> 03F0;;;;N;;;;; @@ -12070,7 +12070,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1D76C;MATHEMATICAL SANS-SERIF BOLD CAPITAL CHI;Lu;0;L;<font> 03A7;;;;N;;;;; 1D76D;MATHEMATICAL SANS-SERIF BOLD CAPITAL PSI;Lu;0;L;<font> 03A8;;;;N;;;;; 1D76E;MATHEMATICAL SANS-SERIF BOLD CAPITAL OMEGA;Lu;0;L;<font> 03A9;;;;N;;;;; -1D76F;MATHEMATICAL SANS-SERIF BOLD NABLA;Ll;0;L;<font> 2207;;;;N;;;;; +1D76F;MATHEMATICAL SANS-SERIF BOLD NABLA;Sm;0;L;<font> 2207;;;;N;;;;; 1D770;MATHEMATICAL SANS-SERIF BOLD SMALL ALPHA;Ll;0;L;<font> 03B1;;;;N;;;;; 1D771;MATHEMATICAL SANS-SERIF BOLD SMALL BETA;Ll;0;L;<font> 03B2;;;;N;;;;; 1D772;MATHEMATICAL SANS-SERIF BOLD SMALL GAMMA;Ll;0;L;<font> 03B3;;;;N;;;;; @@ -12096,7 +12096,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1D786;MATHEMATICAL SANS-SERIF BOLD SMALL CHI;Ll;0;L;<font> 03C7;;;;N;;;;; 1D787;MATHEMATICAL SANS-SERIF BOLD SMALL PSI;Ll;0;L;<font> 03C8;;;;N;;;;; 1D788;MATHEMATICAL SANS-SERIF BOLD SMALL OMEGA;Ll;0;L;<font> 03C9;;;;N;;;;; -1D789;MATHEMATICAL SANS-SERIF BOLD PARTIAL DIFFERENTIAL;Ll;0;L;<font> 2202;;;;N;;;;; +1D789;MATHEMATICAL SANS-SERIF BOLD PARTIAL DIFFERENTIAL;Sm;0;L;<font> 2202;;;;N;;;;; 1D78A;MATHEMATICAL SANS-SERIF BOLD EPSILON SYMBOL;Ll;0;L;<font> 03F5;;;;N;;;;; 1D78B;MATHEMATICAL SANS-SERIF BOLD THETA SYMBOL;Ll;0;L;<font> 03D1;;;;N;;;;; 1D78C;MATHEMATICAL SANS-SERIF BOLD KAPPA SYMBOL;Ll;0;L;<font> 03F0;;;;N;;;;; @@ -12128,7 +12128,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1D7A6;MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL CHI;Lu;0;L;<font> 03A7;;;;N;;;;; 1D7A7;MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL PSI;Lu;0;L;<font> 03A8;;;;N;;;;; 1D7A8;MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL OMEGA;Lu;0;L;<font> 03A9;;;;N;;;;; -1D7A9;MATHEMATICAL SANS-SERIF BOLD ITALIC NABLA;Ll;0;L;<font> 2207;;;;N;;;;; +1D7A9;MATHEMATICAL SANS-SERIF BOLD ITALIC NABLA;Sm;0;L;<font> 2207;;;;N;;;;; 1D7AA;MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA;Ll;0;L;<font> 03B1;;;;N;;;;; 1D7AB;MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL BETA;Ll;0;L;<font> 03B2;;;;N;;;;; 1D7AC;MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL GAMMA;Ll;0;L;<font> 03B3;;;;N;;;;; @@ -12154,7 +12154,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1D7C0;MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL CHI;Ll;0;L;<font> 03C7;;;;N;;;;; 1D7C1;MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL PSI;Ll;0;L;<font> 03C8;;;;N;;;;; 1D7C2;MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA;Ll;0;L;<font> 03C9;;;;N;;;;; -1D7C3;MATHEMATICAL SANS-SERIF BOLD ITALIC PARTIAL DIFFERENTIAL;Ll;0;L;<font> 2202;;;;N;;;;; +1D7C3;MATHEMATICAL SANS-SERIF BOLD ITALIC PARTIAL DIFFERENTIAL;Sm;0;L;<font> 2202;;;;N;;;;; 1D7C4;MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL;Ll;0;L;<font> 03F5;;;;N;;;;; 1D7C5;MATHEMATICAL SANS-SERIF BOLD ITALIC THETA SYMBOL;Ll;0;L;<font> 03D1;;;;N;;;;; 1D7C6;MATHEMATICAL SANS-SERIF BOLD ITALIC KAPPA SYMBOL;Ll;0;L;<font> 03F0;;;;N;;;;; diff --git a/lib/unicode/mktables.PL b/lib/unicode/mktables.PL index dbc2ed1842..818785452b 100755 --- a/lib/unicode/mktables.PL +++ b/lib/unicode/mktables.PL @@ -273,7 +273,7 @@ while (<UD>) { next if /^#/; next if /^$/; chomp; - ($code, $last, $name) = split(/; */); + ($code, $last, $name) = /^([0-9a-f]+)\.\.([0-9a-f]); (.+)/i; if ($name) { print OUT "$code $last $name\n"; $name =~ s/\s+//g; @@ -323,7 +323,7 @@ sub proplist { elsif ($table =~ /^IsLbrk/) { open(UD, "LineBrk.txt") or warn "Can't open $table: $!"; - $split = '($code, $brk, $name) = split(/;/);'; + $split = '($code, $brk, $name) = /^([0-9a-f]+);(\w+) # (.+)/i;'; } else { open(UD, $UnicodeData) or warn "Can't open $UnicodeData: $!"; diff --git a/lib/unicode/version b/lib/unicode/version index 7fb1269f95..9d956cb05c 100644 --- a/lib/unicode/version +++ b/lib/unicode/version @@ -1 +1 @@ -3.1 beta 2001-02-11 +3.1 beta 2001-03-01 |