diff options
author | Chris 'BinGOs' Williams <chris@bingosnet.co.uk> | 2011-11-06 21:59:59 +0000 |
---|---|---|
committer | Chris 'BinGOs' Williams <chris@bingosnet.co.uk> | 2011-11-06 23:49:03 +0000 |
commit | d88bd77ad0e19d4e404b627f2a3b7c8b3a160de0 (patch) | |
tree | e646c7ff05a88060114920dc9f928c17e2d996ec /cpan/Unicode-Collate/Collate/Locale | |
parent | 7c5c3d9b4e6d7073250ddc6f26c36d71eeeb2de7 (diff) | |
download | perl-d88bd77ad0e19d4e404b627f2a3b7c8b3a160de0.tar.gz |
Update Unicode-Collate to CPAN version 0.84
[DELTA]
0.84 Sun Nov 6 14:44:51 2011
- U::C::Locale supports script codes.
- U::C::Locale newly supports locales: fa, sr_Latn, ur.
- added loc_fa.t, loc_srla.t, loc_ur.t in t.
0.83 Sun Oct 30 20:22:04 2011
- mklocale: auto-generate equivalents for suppressed contractions.
* be.txt, bg.txt, kk.txt, mk.txt, ru.txt, sr.txt, uk.txt in data
are simplified.
* but no Locale/*.pl will be modified.
0.82 Sun Oct 30 10:03:48 2011
- U::C::Locale newly supports locales: si, si__dictionary,
sv__reformed, ta, te, th, wae.
- added loc_si.t, loc_sidt.t, loc_svrf.t, loc_ta.t, loc_te.t,
loc_th.t, loc_wae.t in t.
- updated some locales to CLDR 2.0 : sk, sr, sv, uk.
- updated CJK/Pinyin.pm according to CLDR 2.0.
Diffstat (limited to 'cpan/Unicode-Collate/Collate/Locale')
-rw-r--r-- | cpan/Unicode-Collate/Collate/Locale/fa.pl | 49 | ||||
-rw-r--r-- | cpan/Unicode-Collate/Collate/Locale/si.pl | 8 | ||||
-rw-r--r-- | cpan/Unicode-Collate/Collate/Locale/si_dict.pl | 7 | ||||
-rw-r--r-- | cpan/Unicode-Collate/Collate/Locale/sk.pl | 4 | ||||
-rw-r--r-- | cpan/Unicode-Collate/Collate/Locale/sl.pl | 1 | ||||
-rw-r--r-- | cpan/Unicode-Collate/Collate/Locale/sr.pl | 48 | ||||
-rw-r--r-- | cpan/Unicode-Collate/Collate/Locale/sv.pl | 4 | ||||
-rw-r--r-- | cpan/Unicode-Collate/Collate/Locale/sv_refo.pl | 84 | ||||
-rw-r--r-- | cpan/Unicode-Collate/Collate/Locale/ta.pl | 30 | ||||
-rw-r--r-- | cpan/Unicode-Collate/Collate/Locale/te.pl | 7 | ||||
-rw-r--r-- | cpan/Unicode-Collate/Collate/Locale/th.pl | 15 | ||||
-rw-r--r-- | cpan/Unicode-Collate/Collate/Locale/uk.pl | 40 | ||||
-rw-r--r-- | cpan/Unicode-Collate/Collate/Locale/ur.pl | 88 | ||||
-rw-r--r-- | cpan/Unicode-Collate/Collate/Locale/wae.pl | 23 | ||||
-rw-r--r-- | cpan/Unicode-Collate/Collate/Locale/zh_pin.pl | 2 |
15 files changed, 406 insertions, 4 deletions
diff --git a/cpan/Unicode-Collate/Collate/Locale/fa.pl b/cpan/Unicode-Collate/Collate/Locale/fa.pl new file mode 100644 index 0000000000..c413106150 --- /dev/null +++ b/cpan/Unicode-Collate/Collate/Locale/fa.pl @@ -0,0 +1,49 @@ ++{ + entry => <<'ENTRY', # for DUCET v6.0.0 +064E ; [.0000.00A2.0002.064E] # ARABIC FATHA +0650 ; [.0000.00A3.0002.0650] # ARABIC KASRA +064F ; [.0000.00A4.0002.064F] # ARABIC DAMMA +064B ; [.0000.00A5.0002.064B] # ARABIC FATHATAN +064D ; [.0000.00A6.0002.064D] # ARABIC KASRATAN +064C ; [.0000.00A7.0002.064C] # ARABIC DAMMATAN +0622 ; [.1C45.0020.0002.0622][.FFF1.0000.0000.0000] # ARABIC LETTER ALEF WITH MADDA ABOVE +0627 0653 ; [.1C45.0020.0002.0622][.FFF1.0000.0000.0000] # ARABIC LETTER ALEF WITH MADDA ABOVE +0671 ; [.1C46.0021.0002.0671] # ARABIC LETTER ALEF WASLA +0621 ; [.1C46.0020.0002.0621][.FFF1.0000.0000.0000] # ARABIC LETTER HAMZA +0623 ; [.1C46.0021.0002.0623][.FFF1.0000.0000.0000] # ARABIC LETTER ALEF WITH HAMZA ABOVE +0627 0654 ; [.1C46.0021.0002.0623][.FFF1.0000.0000.0000] # ARABIC LETTER ALEF WITH HAMZA ABOVE +0672 ; [.1C46.0022.0002.0672][.FFF1.0000.0000.0000] # ARABIC LETTER ALEF WITH WAVY HAMZA ABOVE +0625 ; [.1C46.0023.0002.0625][.FFF1.0000.0000.0000] # ARABIC LETTER ALEF WITH HAMZA BELOW +0627 0655 ; [.1C46.0023.0002.0625][.FFF1.0000.0000.0000] # ARABIC LETTER ALEF WITH HAMZA BELOW +0673 ; [.1C46.0024.0002.0673][.FFF1.0000.0000.0000] # ARABIC LETTER ALEF WITH WAVY HAMZA BELOW +0624 ; [.1C46.0025.0002.0624][.FFF1.0000.0000.0000] # ARABIC LETTER WAW WITH HAMZA ABOVE +0648 0654 ; [.1C46.0025.0002.0624][.FFF1.0000.0000.0000] # ARABIC LETTER WAW WITH HAMZA ABOVE +06CC 0654 ; [.1C46.0026.0002.06CC][.FFF1.0000.0000.0000] # <ARABIC LETTER FARSI YEH, ARABIC HAMZA ABOVE> +0649 0654 ; [.1C46.0026.0003.0649][.FFF1.0000.0000.0000] # <ARABIC LETTER ALEF MAKSURA, ARABIC HAMZA ABOVE> +0626 ; [.1C46.0026.0004.0626][.FFF1.0000.0000.0000] # ARABIC LETTER YEH WITH HAMZA ABOVE +064A 0654 ; [.1C46.0026.0004.0626][.FFF1.0000.0000.0000] # ARABIC LETTER YEH WITH HAMZA ABOVE +06AA ; [.1CB2.0021.0002.06AA] # ARABIC LETTER SWASH KAF +06AB ; [.1CB2.0022.0002.06AB] # ARABIC LETTER KAF WITH RING +0643 ; [.1CB2.0023.0002.0643] # ARABIC LETTER KAF +06AC ; [.1CB2.0024.0002.06AC] # ARABIC LETTER KAF WITH DOT ABOVE +06AD ; [.1CB2.0025.0002.06AD] # ARABIC LETTER NG +06AE ; [.1CB2.0026.0002.06AE] # ARABIC LETTER KAF WITH THREE DOTS BELOW +0647 ; [.1CE5.0020.0002.0647][.FFF1.0000.0000.0000] # ARABIC LETTER HEH +06D5 ; [.1CE5.0021.0002.06D5][.FFF1.0000.0000.0000] # ARABIC LETTER AE +06C1 ; [.1CE5.0022.0002.06C1][.FFF1.0000.0000.0000] # ARABIC LETTER HEH GOAL +06C2 ; [.1CE5.0022.0002.06C1][.FFF1.0000.0000.0000][.0000.00B1.0002.0654] # ARABIC LETTER HEH GOAL WITH HAMZA ABOVE +0629 ; [.1CE5.0023.0002.0629][.FFF1.0000.0000.0000] # ARABIC LETTER TEH MARBUTA +06C3 ; [.1CE5.0024.0002.06C3][.FFF1.0000.0000.0000] # ARABIC LETTER TEH MARBUTA GOAL +06C0 ; [.1CE5.0025.0002.06C0][.FFF1.0000.0000.0000] # ARABIC LETTER HEH WITH YEH ABOVE +06D5 0654 ; [.1CE5.0025.0002.06C0][.FFF1.0000.0000.0000] # ARABIC LETTER HEH WITH YEH ABOVE +06BE ; [.1CE5.0026.0002.06BE][.FFF1.0000.0000.0000] # ARABIC LETTER HEH DOACHASHMEE +0649 ; [.1CEA.0021.0002.0649] # ARABIC LETTER ALEF MAKSURA +06D2 ; [.1CEA.0022.0002.06D2] # ARABIC LETTER YEH BARREE +06D3 ; [.1CEA.0022.0002.06D2][.0000.00B1.0002.0654] # ARABIC LETTER YEH BARREE WITH HAMZA ABOVE +064A ; [.1CEA.0023.0002.064A] # ARABIC LETTER YEH +06D0 ; [.1CEA.0024.0002.06D0] # ARABIC LETTER E +06D1 ; [.1CEA.0025.0002.06D1] # ARABIC LETTER YEH WITH THREE DOTS BELOW +06CD ; [.1CEA.0026.0002.06CD] # ARABIC LETTER YEH WITH TAIL +06CE ; [.1CEA.0027.0002.06CE] # ARABIC LETTER YEH WITH SMALL V +ENTRY +}; diff --git a/cpan/Unicode-Collate/Collate/Locale/si.pl b/cpan/Unicode-Collate/Collate/Locale/si.pl new file mode 100644 index 0000000000..0e59bb931c --- /dev/null +++ b/cpan/Unicode-Collate/Collate/Locale/si.pl @@ -0,0 +1,8 @@ ++{ + entry => <<'ENTRY', # for DUCET v6.0.0 +0D82 ; [.21F7.0020.0002.0D82][.FFF1.0000.0000.0000] # SINHALA SIGN ANUSVARAYA +0D83 ; [.21F7.0020.0002.0D83][.FFF2.0000.0000.0000] # SINHALA SIGN VISARGAYA +0DA5 ; [.2202.0020.0002.0DA5] # SINHALA LETTER TAALUJA SANYOOGA NAAKSIKYAYA +0DA4 ; [.2203.0020.0002.0DA4] # SINHALA LETTER TAALUJA NAASIKYAYA +ENTRY +}; diff --git a/cpan/Unicode-Collate/Collate/Locale/si_dict.pl b/cpan/Unicode-Collate/Collate/Locale/si_dict.pl new file mode 100644 index 0000000000..6b1b36a631 --- /dev/null +++ b/cpan/Unicode-Collate/Collate/Locale/si_dict.pl @@ -0,0 +1,7 @@ ++{ + entry => <<'ENTRY', # for DUCET v6.0.0 +0D82 ; [.21F7.0020.0002.0D82][.FFF1.0000.0000.0000] # SINHALA SIGN ANUSVARAYA +0D83 ; [.21F7.0020.0002.0D83][.FFF2.0000.0000.0000] # SINHALA SIGN VISARGAYA +0DA5 ; [.2200.0020.0002.0DA2][.2232.0020.0002.0DCA][.2202.0021.0002.0DA5] # SINHALA LETTER TAALUJA SANYOOGA NAAKSIKYAYA +ENTRY +}; diff --git a/cpan/Unicode-Collate/Collate/Locale/sk.pl b/cpan/Unicode-Collate/Collate/Locale/sk.pl index b9b27ad3ee..73c2e46ac9 100644 --- a/cpan/Unicode-Collate/Collate/Locale/sk.pl +++ b/cpan/Unicode-Collate/Collate/Locale/sk.pl @@ -28,6 +28,10 @@ 1ED4 ; [.1725.0020.0008.00D4][.0000.0064.0002.0309] # LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND HOOK ABOVE 1ED9 ; [.1725.0020.0002.00F4][.0000.0070.0002.0323] # LATIN SMALL LETTER O WITH CIRCUMFLEX AND DOT BELOW 1ED8 ; [.1725.0020.0008.00D4][.0000.0070.0002.0323] # LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND DOT BELOW +0159 ; [.1771.0020.0002.0159] # LATIN SMALL LETTER R WITH CARON +0072 030C ; [.1771.0020.0002.0159] # LATIN SMALL LETTER R WITH CARON +0158 ; [.1771.0020.0008.0158] # LATIN CAPITAL LETTER R WITH CARON +0052 030C ; [.1771.0020.0008.0158] # LATIN CAPITAL LETTER R WITH CARON 0161 ; [.17A7.0020.0002.0161] # LATIN SMALL LETTER S WITH CARON 0073 030C ; [.17A7.0020.0002.0161] # LATIN SMALL LETTER S WITH CARON 0160 ; [.17A7.0020.0008.0160] # LATIN CAPITAL LETTER S WITH CARON diff --git a/cpan/Unicode-Collate/Collate/Locale/sl.pl b/cpan/Unicode-Collate/Collate/Locale/sl.pl index d1281feffe..d9a4ae4609 100644 --- a/cpan/Unicode-Collate/Collate/Locale/sl.pl +++ b/cpan/Unicode-Collate/Collate/Locale/sl.pl @@ -1,5 +1,4 @@ +{ -# c-acute not included entry => <<'ENTRY', # for DUCET v6.0.0 010D ; [.15D2.0020.0002.010D] # LATIN SMALL LETTER C WITH CARON 0063 030C ; [.15D2.0020.0002.010D] # LATIN SMALL LETTER C WITH CARON diff --git a/cpan/Unicode-Collate/Collate/Locale/sr.pl b/cpan/Unicode-Collate/Collate/Locale/sr.pl new file mode 100644 index 0000000000..db010969bb --- /dev/null +++ b/cpan/Unicode-Collate/Collate/Locale/sr.pl @@ -0,0 +1,48 @@ ++{ + suppress => [0x0410, 0x0430, 0x04D8, 0x04D9, 0x0413, 0x0433, 0x0415, 0x0435, + 0x0416, 0x0436, 0x0417, 0x0437, 0x0418, 0x0438, 0x0406, 0x0456, + 0x041E, 0x043E, 0x04E8, 0x04E9, 0x041A, 0x043A, 0x0423, 0x0443, + 0x0427, 0x0447, 0x042B, 0x044B, 0x042D, 0x044D, 0x0474, 0x0475], + entry => <<'ENTRY', # for DUCET v6.0.0 +04D1 ; [.1943.0020.0002.0430][.0000.0037.0002.0306] # CYRILLIC SMALL LETTER A WITH BREVE +04D0 ; [.1943.0020.0008.0410][.0000.0037.0002.0306] # CYRILLIC CAPITAL LETTER A WITH BREVE +04D3 ; [.1943.0020.0002.0430][.0000.0047.0002.0308] # CYRILLIC SMALL LETTER A WITH DIAERESIS +04D2 ; [.1943.0020.0008.0410][.0000.0047.0002.0308] # CYRILLIC CAPITAL LETTER A WITH DIAERESIS +04DB ; [.194F.0020.0002.04D9][.0000.0047.0002.0308] # CYRILLIC SMALL LETTER SCHWA WITH DIAERESIS +04DA ; [.194F.0020.0008.04D8][.0000.0047.0002.0308] # CYRILLIC CAPITAL LETTER SCHWA WITH DIAERESIS +0453 ; [.1963.0020.0002.0433][.0000.0032.0002.0301] # CYRILLIC SMALL LETTER GJE +0403 ; [.1963.0020.0008.0413][.0000.0032.0002.0301] # CYRILLIC CAPITAL LETTER GJE +04D7 ; [.198B.0020.0002.0435][.0000.0037.0002.0306] # CYRILLIC SMALL LETTER IE WITH BREVE +04D6 ; [.198B.0020.0008.0415][.0000.0037.0002.0306] # CYRILLIC CAPITAL LETTER IE WITH BREVE +04DD ; [.1997.0020.0002.0436][.0000.0047.0002.0308] # CYRILLIC SMALL LETTER ZHE WITH DIAERESIS +04DC ; [.1997.0020.0008.0416][.0000.0047.0002.0308] # CYRILLIC CAPITAL LETTER ZHE WITH DIAERESIS +04DF ; [.19A4.0020.0002.0437][.0000.0047.0002.0308] # CYRILLIC SMALL LETTER ZE WITH DIAERESIS +04DE ; [.19A4.0020.0008.0417][.0000.0047.0002.0308] # CYRILLIC CAPITAL LETTER ZE WITH DIAERESIS +04E5 ; [.19BC.0020.0002.0438][.0000.0047.0002.0308] # CYRILLIC SMALL LETTER I WITH DIAERESIS +04E4 ; [.19BC.0020.0008.0418][.0000.0047.0002.0308] # CYRILLIC CAPITAL LETTER I WITH DIAERESIS +0457 ; [.19C8.0020.0002.0456][.0000.0047.0002.0308] # CYRILLIC SMALL LETTER YI +0407 ; [.19C8.0020.0008.0406][.0000.0047.0002.0308] # CYRILLIC CAPITAL LETTER YI +0439 ; [.19BC.0020.0002.0438][.0000.0037.0002.0306] # CYRILLIC SMALL LETTER SHORT I +0419 ; [.19BC.0020.0008.0418][.0000.0037.0002.0306] # CYRILLIC CAPITAL LETTER SHORT I +04E7 ; [.1A29.0020.0002.043E][.0000.0047.0002.0308] # CYRILLIC SMALL LETTER O WITH DIAERESIS +04E6 ; [.1A29.0020.0008.041E][.0000.0047.0002.0308] # CYRILLIC CAPITAL LETTER O WITH DIAERESIS +04EB ; [.1A31.0020.0002.04E9][.0000.0047.0002.0308] # CYRILLIC SMALL LETTER BARRED O WITH DIAERESIS +04EA ; [.1A31.0020.0008.04E8][.0000.0047.0002.0308] # CYRILLIC CAPITAL LETTER BARRED O WITH DIAERESIS +045C ; [.19DA.0020.0002.043A][.0000.0032.0002.0301] # CYRILLIC SMALL LETTER KJE +040C ; [.19DA.0020.0008.041A][.0000.0032.0002.0301] # CYRILLIC CAPITAL LETTER KJE +045E ; [.1A6B.0020.0002.0443][.0000.0037.0002.0306] # CYRILLIC SMALL LETTER SHORT U +040E ; [.1A6B.0020.0008.0423][.0000.0037.0002.0306] # CYRILLIC CAPITAL LETTER SHORT U +04F1 ; [.1A6B.0020.0002.0443][.0000.0047.0002.0308] # CYRILLIC SMALL LETTER U WITH DIAERESIS +04F0 ; [.1A6B.0020.0008.0423][.0000.0047.0002.0308] # CYRILLIC CAPITAL LETTER U WITH DIAERESIS +04F3 ; [.1A6B.0020.0002.0443][.0000.004D.0002.030B] # CYRILLIC SMALL LETTER U WITH DOUBLE ACUTE +04F2 ; [.1A6B.0020.0008.0423][.0000.004D.0002.030B] # CYRILLIC CAPITAL LETTER U WITH DOUBLE ACUTE +04F5 ; [.1ABE.0020.0002.0447][.0000.0047.0002.0308] # CYRILLIC SMALL LETTER CHE WITH DIAERESIS +04F4 ; [.1ABE.0020.0008.0427][.0000.0047.0002.0308] # CYRILLIC CAPITAL LETTER CHE WITH DIAERESIS +04F9 ; [.1AF1.0020.0002.044B][.0000.0047.0002.0308] # CYRILLIC SMALL LETTER YERU WITH DIAERESIS +04F8 ; [.1AF1.0020.0008.042B][.0000.0047.0002.0308] # CYRILLIC CAPITAL LETTER YERU WITH DIAERESIS +04ED ; [.1B06.0020.0002.044D][.0000.0047.0002.0308] # CYRILLIC SMALL LETTER E WITH DIAERESIS +04EC ; [.1B06.0020.0008.042D][.0000.0047.0002.0308] # CYRILLIC CAPITAL LETTER E WITH DIAERESIS +0477 ; [.1B3C.0020.0002.0475][.0000.0065.0002.030F] # CYRILLIC SMALL LETTER IZHITSA WITH DOUBLE GRAVE ACCENT +0476 ; [.1B3C.0020.0008.0474][.0000.0065.0002.030F] # CYRILLIC CAPITAL LETTER IZHITSA WITH DOUBLE GRAVE ACCENT +ENTRY +}; diff --git a/cpan/Unicode-Collate/Collate/Locale/sv.pl b/cpan/Unicode-Collate/Collate/Locale/sv.pl index 1243167fc3..de95d5fae3 100644 --- a/cpan/Unicode-Collate/Collate/Locale/sv.pl +++ b/cpan/Unicode-Collate/Collate/Locale/sv.pl @@ -8,8 +8,8 @@ 00D0 ; [.15E4.0022.0008.00D0] # LATIN CAPITAL LETTER ETH 00FE ; [.17C9.0020.0003.00FE][.1667.0020.0003.00FE] # LATIN SMALL LETTER THORN 00DE ; [.17C9.0020.0009.00DE][.1667.0020.0009.00DE] # LATIN CAPITAL LETTER THORN -0077 ; [.1812.0020.0003.0077] # LATIN SMALL LETTER W -0057 ; [.1812.0020.0009.0057] # LATIN CAPITAL LETTER W +0077 ; [.1812.0021.0002.0077] # LATIN SMALL LETTER W +0057 ; [.1812.0021.0008.0057] # LATIN CAPITAL LETTER W 00FC ; [.1833.0021.0002.00FC] # LATIN SMALL LETTER U WITH DIAERESIS 0075 0308 ; [.1833.0021.0002.00FC] # LATIN SMALL LETTER U WITH DIAERESIS 00DC ; [.1833.0021.0008.00DC] # LATIN CAPITAL LETTER U WITH DIAERESIS diff --git a/cpan/Unicode-Collate/Collate/Locale/sv_refo.pl b/cpan/Unicode-Collate/Collate/Locale/sv_refo.pl new file mode 100644 index 0000000000..f3a867fc33 --- /dev/null +++ b/cpan/Unicode-Collate/Collate/Locale/sv_refo.pl @@ -0,0 +1,84 @@ ++{ + entry => <<'ENTRY', # for DUCET v6.0.0 +0111 ; [.15E4.0021.0002.0111] # LATIN SMALL LETTER D WITH STROKE +0064 0335 ; [.15E4.0021.0002.0111] # LATIN SMALL LETTER D WITH STROKE +0110 ; [.15E4.0021.0008.0110] # LATIN CAPITAL LETTER D WITH STROKE +0044 0335 ; [.15E4.0021.0008.0110] # LATIN CAPITAL LETTER D WITH STROKE +00F0 ; [.15E4.0022.0002.00F0] # LATIN SMALL LETTER ETH +00D0 ; [.15E4.0022.0008.00D0] # LATIN CAPITAL LETTER ETH +00FE ; [.17C9.0020.0003.00FE][.1667.0020.0003.00FE] # LATIN SMALL LETTER THORN +00DE ; [.17C9.0020.0009.00DE][.1667.0020.0009.00DE] # LATIN CAPITAL LETTER THORN +00FC ; [.1833.0021.0002.00FC] # LATIN SMALL LETTER U WITH DIAERESIS +0075 0308 ; [.1833.0021.0002.00FC] # LATIN SMALL LETTER U WITH DIAERESIS +00DC ; [.1833.0021.0008.00DC] # LATIN CAPITAL LETTER U WITH DIAERESIS +0055 0308 ; [.1833.0021.0008.00DC] # LATIN CAPITAL LETTER U WITH DIAERESIS +01DC ; [.1833.0021.0002.00FC][.0000.0035.0002.0300] # LATIN SMALL LETTER U WITH DIAERESIS AND GRAVE +01DB ; [.1833.0021.0008.00DC][.0000.0035.0002.0300] # LATIN CAPITAL LETTER U WITH DIAERESIS AND GRAVE +01D8 ; [.1833.0021.0002.00FC][.0000.0032.0002.0301] # LATIN SMALL LETTER U WITH DIAERESIS AND ACUTE +01D7 ; [.1833.0021.0008.00DC][.0000.0032.0002.0301] # LATIN CAPITAL LETTER U WITH DIAERESIS AND ACUTE +01D6 ; [.1833.0021.0002.00FC][.0000.005B.0002.0304] # LATIN SMALL LETTER U WITH DIAERESIS AND MACRON +01D5 ; [.1833.0021.0008.00DC][.0000.005B.0002.0304] # LATIN CAPITAL LETTER U WITH DIAERESIS AND MACRON +01DA ; [.1833.0021.0002.00FC][.0000.0041.0002.030C] # LATIN SMALL LETTER U WITH DIAERESIS AND CARON +01D9 ; [.1833.0021.0008.00DC][.0000.0041.0002.030C] # LATIN CAPITAL LETTER U WITH DIAERESIS AND CARON +0171 ; [.1833.0022.0002.0171] # LATIN SMALL LETTER U WITH DOUBLE ACUTE +0075 030B ; [.1833.0022.0002.0171] # LATIN SMALL LETTER U WITH DOUBLE ACUTE +0170 ; [.1833.0022.0008.0170] # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE +0055 030B ; [.1833.0022.0008.0170] # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE +00E5 ; [.18B9.0020.0002.00E5] # LATIN SMALL LETTER A WITH RING ABOVE +0061 030A ; [.18B9.0020.0002.00E5] # LATIN SMALL LETTER A WITH RING ABOVE +00C5 ; [.18B9.0020.0008.00C5] # LATIN CAPITAL LETTER A WITH RING ABOVE +0041 030A ; [.18B9.0020.0008.00C5] # LATIN CAPITAL LETTER A WITH RING ABOVE +212B ; [.18B9.0020.0008.00C5] # ANGSTROM SIGN +01FB ; [.18B9.0020.0002.00E5][.0000.0032.0002.0301] # LATIN SMALL LETTER A WITH RING ABOVE AND ACUTE +01FA ; [.18B9.0020.0008.00C5][.0000.0032.0002.0301] # LATIN CAPITAL LETTER A WITH RING ABOVE AND ACUTE +00E4 ; [.18BA.0020.0002.00E4] # LATIN SMALL LETTER A WITH DIAERESIS +0061 0308 ; [.18BA.0020.0002.00E4] # LATIN SMALL LETTER A WITH DIAERESIS +00C4 ; [.18BA.0020.0008.00C4] # LATIN CAPITAL LETTER A WITH DIAERESIS +0041 0308 ; [.18BA.0020.0008.00C4] # LATIN CAPITAL LETTER A WITH DIAERESIS +01DF ; [.18BA.0020.0002.00E4][.0000.005B.0002.0304] # LATIN SMALL LETTER A WITH DIAERESIS AND MACRON +01DE ; [.18BA.0020.0008.00C4][.0000.005B.0002.0304] # LATIN CAPITAL LETTER A WITH DIAERESIS AND MACRON +00E6 ; [.18BA.0021.0002.00E6] # LATIN SMALL LETTER AE +00C6 ; [.18BA.0021.0008.00C6] # LATIN CAPITAL LETTER AE +1D2D ; [.18BA.0021.0014.1D2D] # MODIFIER LETTER CAPITAL AE +01FD ; [.18BA.0021.0002.00E6][.0000.0032.0002.0301] # LATIN SMALL LETTER AE WITH ACUTE +01FC ; [.18BA.0021.0008.00C6][.0000.0032.0002.0301] # LATIN CAPITAL LETTER AE WITH ACUTE +01E3 ; [.18BA.0021.0002.00E6][.0000.005B.0002.0304] # LATIN SMALL LETTER AE WITH MACRON +01E2 ; [.18BA.0021.0008.00C6][.0000.005B.0002.0304] # LATIN CAPITAL LETTER AE WITH MACRON +0119 ; [.18BA.0022.0002.0119] # LATIN SMALL LETTER E WITH OGONEK +0065 0328 ; [.18BA.0022.0002.0119] # LATIN SMALL LETTER E WITH OGONEK +0118 ; [.18BA.0022.0008.0118] # LATIN CAPITAL LETTER E WITH OGONEK +0045 0328 ; [.18BA.0022.0008.0118] # LATIN CAPITAL LETTER E WITH OGONEK +00F6 ; [.18BB.0020.0002.00F6] # LATIN SMALL LETTER O WITH DIAERESIS +006F 0308 ; [.18BB.0020.0002.00F6] # LATIN SMALL LETTER O WITH DIAERESIS +00D6 ; [.18BB.0020.0008.00D6] # LATIN CAPITAL LETTER O WITH DIAERESIS +004F 0308 ; [.18BB.0020.0008.00D6] # LATIN CAPITAL LETTER O WITH DIAERESIS +022B ; [.18BB.0020.0002.00F6][.0000.005B.0002.0304] # LATIN SMALL LETTER O WITH DIAERESIS AND MACRON +022A ; [.18BB.0020.0008.00D6][.0000.005B.0002.0304] # LATIN CAPITAL LETTER O WITH DIAERESIS AND MACRON +00F8 ; [.18BB.0021.0002.00F8] # LATIN SMALL LETTER O WITH STROKE +006F 0338 ; [.18BB.0021.0002.00F8] # LATIN SMALL LETTER O WITH STROKE +00D8 ; [.18BB.0021.0008.00D8] # LATIN CAPITAL LETTER O WITH STROKE +004F 0338 ; [.18BB.0021.0008.00D8] # LATIN CAPITAL LETTER O WITH STROKE +01FF ; [.18BB.0021.0002.00F8][.0000.0032.0002.0301] # LATIN SMALL LETTER O WITH STROKE AND ACUTE +01FE ; [.18BB.0021.0008.00D8][.0000.0032.0002.0301] # LATIN CAPITAL LETTER O WITH STROKE AND ACUTE +0151 ; [.18BB.0022.0002.0151] # LATIN SMALL LETTER O WITH DOUBLE ACUTE +006F 030B ; [.18BB.0022.0002.0151] # LATIN SMALL LETTER O WITH DOUBLE ACUTE +0150 ; [.18BB.0022.0008.0150] # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE +004F 030B ; [.18BB.0022.0008.0150] # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE +0153 ; [.18BB.0023.0002.0153] # LATIN SMALL LIGATURE OE +0152 ; [.18BB.0023.0008.0152] # LATIN CAPITAL LIGATURE OE +00F4 ; [.18BB.0024.0002.00F4] # LATIN SMALL LETTER O WITH CIRCUMFLEX +006F 0302 ; [.18BB.0024.0002.00F4] # LATIN SMALL LETTER O WITH CIRCUMFLEX +00D4 ; [.18BB.0024.0008.00D4] # LATIN CAPITAL LETTER O WITH CIRCUMFLEX +004F 0302 ; [.18BB.0024.0008.00D4] # LATIN CAPITAL LETTER O WITH CIRCUMFLEX +1ED3 ; [.18BB.0024.0002.00F4][.0000.0035.0002.0300] # LATIN SMALL LETTER O WITH CIRCUMFLEX AND GRAVE +1ED2 ; [.18BB.0024.0008.00D4][.0000.0035.0002.0300] # LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND GRAVE +1ED1 ; [.18BB.0024.0002.00F4][.0000.0032.0002.0301] # LATIN SMALL LETTER O WITH CIRCUMFLEX AND ACUTE +1ED0 ; [.18BB.0024.0008.00D4][.0000.0032.0002.0301] # LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND ACUTE +1ED7 ; [.18BB.0024.0002.00F4][.0000.004E.0002.0303] # LATIN SMALL LETTER O WITH CIRCUMFLEX AND TILDE +1ED6 ; [.18BB.0024.0008.00D4][.0000.004E.0002.0303] # LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND TILDE +1ED5 ; [.18BB.0024.0002.00F4][.0000.0064.0002.0309] # LATIN SMALL LETTER O WITH CIRCUMFLEX AND HOOK ABOVE +1ED4 ; [.18BB.0024.0008.00D4][.0000.0064.0002.0309] # LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND HOOK ABOVE +1ED9 ; [.18BB.0024.0002.00F4][.0000.0070.0002.0323] # LATIN SMALL LETTER O WITH CIRCUMFLEX AND DOT BELOW +1ED8 ; [.18BB.0024.0008.00D4][.0000.0070.0002.0323] # LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND DOT BELOW +ENTRY +}; diff --git a/cpan/Unicode-Collate/Collate/Locale/ta.pl b/cpan/Unicode-Collate/Collate/Locale/ta.pl new file mode 100644 index 0000000000..ef5223e854 --- /dev/null +++ b/cpan/Unicode-Collate/Collate/Locale/ta.pl @@ -0,0 +1,30 @@ ++{ + entry => <<'ENTRY', # for DUCET v6.0.0 +0B82 ; [.20E7.0020.0002.0B82][.FFF1.0000.0000.0000] # TAMIL SIGN ANUSVARA +0B95 0BCD ; [.20E8.0020.0002.0B95][.FFF1.0000.0000.0000] # <TAMIL LETTER KA, TAMIL SIGN VIRAMA> +0B99 0BCD ; [.20E9.0020.0002.0B99][.FFF1.0000.0000.0000] # <TAMIL LETTER NGA, TAMIL SIGN VIRAMA> +0B9A 0BCD ; [.20EA.0020.0002.0B9A][.FFF1.0000.0000.0000] # <TAMIL LETTER CA, TAMIL SIGN VIRAMA> +0B9E 0BCD ; [.20EB.0020.0002.0B9E][.FFF1.0000.0000.0000] # <TAMIL LETTER NYA, TAMIL SIGN VIRAMA> +0B9F 0BCD ; [.20EC.0020.0002.0B9F][.FFF1.0000.0000.0000] # <TAMIL LETTER TTA, TAMIL SIGN VIRAMA> +0BA3 0BCD ; [.20ED.0020.0002.0BA3][.FFF1.0000.0000.0000] # <TAMIL LETTER NNA, TAMIL SIGN VIRAMA> +0BA4 0BCD ; [.20EE.0020.0002.0BA4][.FFF1.0000.0000.0000] # <TAMIL LETTER TA, TAMIL SIGN VIRAMA> +0BA8 0BCD ; [.20EF.0020.0002.0BA8][.FFF1.0000.0000.0000] # <TAMIL LETTER NA, TAMIL SIGN VIRAMA> +0BAA 0BCD ; [.20F0.0020.0002.0BAA][.FFF1.0000.0000.0000] # <TAMIL LETTER PA, TAMIL SIGN VIRAMA> +0BAE 0BCD ; [.20F1.0020.0002.0BAE][.FFF1.0000.0000.0000] # <TAMIL LETTER MA, TAMIL SIGN VIRAMA> +0BAF 0BCD ; [.20F2.0020.0002.0BAF][.FFF1.0000.0000.0000] # <TAMIL LETTER YA, TAMIL SIGN VIRAMA> +0BB0 0BCD ; [.20F3.0020.0002.0BB0][.FFF1.0000.0000.0000] # <TAMIL LETTER RA, TAMIL SIGN VIRAMA> +0BB2 0BCD ; [.20F4.0020.0002.0BB2][.FFF1.0000.0000.0000] # <TAMIL LETTER LA, TAMIL SIGN VIRAMA> +0BB5 0BCD ; [.20F5.0020.0002.0BB5][.FFF1.0000.0000.0000] # <TAMIL LETTER VA, TAMIL SIGN VIRAMA> +0BB4 0BCD ; [.20F6.0020.0002.0BB4][.FFF1.0000.0000.0000] # <TAMIL LETTER LLLA, TAMIL SIGN VIRAMA> +0BB3 0BCD ; [.20F7.0020.0002.0BB3][.FFF1.0000.0000.0000] # <TAMIL LETTER LLA, TAMIL SIGN VIRAMA> +0BB1 0BCD ; [.20F8.0020.0002.0BB1][.FFF1.0000.0000.0000] # <TAMIL LETTER RRA, TAMIL SIGN VIRAMA> +0BA9 0BCD ; [.20F9.0020.0002.0BA9][.FFF1.0000.0000.0000] # <TAMIL LETTER NNNA, TAMIL SIGN VIRAMA> +0B9C 0BCD ; [.20FA.0020.0002.0B9C][.FFF1.0000.0000.0000] # <TAMIL LETTER JA, TAMIL SIGN VIRAMA> +0BB6 0BCD ; [.20FB.0020.0002.0BB6][.FFF1.0000.0000.0000] # <TAMIL LETTER SHA, TAMIL SIGN VIRAMA> +0BB7 0BCD ; [.20FC.0020.0002.0BB7][.FFF1.0000.0000.0000] # <TAMIL LETTER SSA, TAMIL SIGN VIRAMA> +0BB8 0BCD ; [.20FD.0020.0002.0BB8][.FFF1.0000.0000.0000] # <TAMIL LETTER SA, TAMIL SIGN VIRAMA> +0BB9 0BCD ; [.20FE.0020.0002.0BB9][.FFF1.0000.0000.0000] # <TAMIL LETTER HA, TAMIL SIGN VIRAMA> +0B95 0BCD 0BB7 0BCD ; [.20FF.0020.0002.0B95][.FFF1.0000.0000.0000] # <TAMIL LETTER KA, TAMIL SIGN VIRAMA, TAMIL LETTER SSA, TAMIL SIGN VIRAMA> +0B95 0BCD 0BB7 ; [.20FF.0020.0002.0B95][.FFF2.0000.0000.0000] # <TAMIL LETTER KA, TAMIL SIGN VIRAMA, TAMIL LETTER SSA> +ENTRY +}; diff --git a/cpan/Unicode-Collate/Collate/Locale/te.pl b/cpan/Unicode-Collate/Collate/Locale/te.pl new file mode 100644 index 0000000000..fd32bc6542 --- /dev/null +++ b/cpan/Unicode-Collate/Collate/Locale/te.pl @@ -0,0 +1,7 @@ ++{ + entry => <<'ENTRY', # for DUCET v6.0.0 +0C01 ; [.211C.0020.0002.0C01][.FFF1.0000.0000.0000] # TELUGU SIGN CANDRABINDU +0C02 ; [.211C.0020.0002.0C02][.FFF2.0000.0000.0000] # TELUGU SIGN ANUSVARA +0C03 ; [.211C.0020.0002.0C03][.FFF3.0000.0000.0000] # TELUGU SIGN VISARGA +ENTRY +}; diff --git a/cpan/Unicode-Collate/Collate/Locale/th.pl b/cpan/Unicode-Collate/Collate/Locale/th.pl new file mode 100644 index 0000000000..6fe86cce69 --- /dev/null +++ b/cpan/Unicode-Collate/Collate/Locale/th.pl @@ -0,0 +1,15 @@ ++{ + entry => <<'ENTRY', # for DUCET v6.0.0 +0E2F ; [*0480.0020.0002.0E2F][*FFF1.0000.0000.0000] # THAI CHARACTER PAIYANNOI +0E46 ; [*0480.0020.0002.0E46][*FFF2.0000.0000.0000] # THAI CHARACTER MAIYAMOK +0E4C ; [.0000.011D.0002.0E4C] # THAI CHARACTER THANTHAKHAT +0E47 ; [.0000.011E.0002.0E47] # THAI CHARACTER MAITAIKHU +0E48 ; [.0000.011F.0002.0E48] # THAI CHARACTER MAI EK +0E49 ; [.0000.0120.0002.0E49] # THAI CHARACTER MAI THO +0E4A ; [.0000.0121.0002.0E4A] # THAI CHARACTER MAI TRI +0E4B ; [.0000.0122.0002.0E4B] # THAI CHARACTER MAI CHATTAWA +0E4D ; [.23C3.0020.0002.0E4D] # THAI CHARACTER NIKHAHIT +0E45 ; [.23C6.0020.0003.0E45] # THAI CHARACTER LAKKHANGYAO +0E3A ; [.23D4.0020.0002.0E3A] # THAI CHARACTER PHINTHU +ENTRY +}; diff --git a/cpan/Unicode-Collate/Collate/Locale/uk.pl b/cpan/Unicode-Collate/Collate/Locale/uk.pl index 9f24b3250e..3b3db69bf5 100644 --- a/cpan/Unicode-Collate/Collate/Locale/uk.pl +++ b/cpan/Unicode-Collate/Collate/Locale/uk.pl @@ -1,6 +1,46 @@ +{ + suppress => [0x0410, 0x0430, 0x04D8, 0x04D9, 0x0413, 0x0433, 0x0415, 0x0435, + 0x0416, 0x0436, 0x0417, 0x0437, 0x041E, 0x043E, 0x04E8, 0x04E9, + 0x041A, 0x043A, 0x0423, 0x0443, 0x0427, 0x0447, 0x042B, 0x044B, + 0x042D, 0x044D, 0x0474, 0x0475], entry => <<'ENTRY', # for DUCET v6.0.0 0491 ; [.1964.0020.0002.0491] # CYRILLIC SMALL LETTER GHE WITH UPTURN 0490 ; [.1964.0020.0008.0490] # CYRILLIC CAPITAL LETTER GHE WITH UPTURN +044C ; [.1B15.0020.0002.044C] # CYRILLIC SMALL LETTER SOFT SIGN +042C ; [.1B15.0020.0008.042C] # CYRILLIC CAPITAL LETTER SOFT SIGN +04D1 ; [.1943.0020.0002.0430][.0000.0037.0002.0306] # CYRILLIC SMALL LETTER A WITH BREVE +04D0 ; [.1943.0020.0008.0410][.0000.0037.0002.0306] # CYRILLIC CAPITAL LETTER A WITH BREVE +04D3 ; [.1943.0020.0002.0430][.0000.0047.0002.0308] # CYRILLIC SMALL LETTER A WITH DIAERESIS +04D2 ; [.1943.0020.0008.0410][.0000.0047.0002.0308] # CYRILLIC CAPITAL LETTER A WITH DIAERESIS +04DB ; [.194F.0020.0002.04D9][.0000.0047.0002.0308] # CYRILLIC SMALL LETTER SCHWA WITH DIAERESIS +04DA ; [.194F.0020.0008.04D8][.0000.0047.0002.0308] # CYRILLIC CAPITAL LETTER SCHWA WITH DIAERESIS +0453 ; [.1963.0020.0002.0433][.0000.0032.0002.0301] # CYRILLIC SMALL LETTER GJE +0403 ; [.1963.0020.0008.0413][.0000.0032.0002.0301] # CYRILLIC CAPITAL LETTER GJE +04D7 ; [.198B.0020.0002.0435][.0000.0037.0002.0306] # CYRILLIC SMALL LETTER IE WITH BREVE +04D6 ; [.198B.0020.0008.0415][.0000.0037.0002.0306] # CYRILLIC CAPITAL LETTER IE WITH BREVE +04DD ; [.1997.0020.0002.0436][.0000.0047.0002.0308] # CYRILLIC SMALL LETTER ZHE WITH DIAERESIS +04DC ; [.1997.0020.0008.0416][.0000.0047.0002.0308] # CYRILLIC CAPITAL LETTER ZHE WITH DIAERESIS +04DF ; [.19A4.0020.0002.0437][.0000.0047.0002.0308] # CYRILLIC SMALL LETTER ZE WITH DIAERESIS +04DE ; [.19A4.0020.0008.0417][.0000.0047.0002.0308] # CYRILLIC CAPITAL LETTER ZE WITH DIAERESIS +04E7 ; [.1A29.0020.0002.043E][.0000.0047.0002.0308] # CYRILLIC SMALL LETTER O WITH DIAERESIS +04E6 ; [.1A29.0020.0008.041E][.0000.0047.0002.0308] # CYRILLIC CAPITAL LETTER O WITH DIAERESIS +04EB ; [.1A31.0020.0002.04E9][.0000.0047.0002.0308] # CYRILLIC SMALL LETTER BARRED O WITH DIAERESIS +04EA ; [.1A31.0020.0008.04E8][.0000.0047.0002.0308] # CYRILLIC CAPITAL LETTER BARRED O WITH DIAERESIS +045C ; [.19DA.0020.0002.043A][.0000.0032.0002.0301] # CYRILLIC SMALL LETTER KJE +040C ; [.19DA.0020.0008.041A][.0000.0032.0002.0301] # CYRILLIC CAPITAL LETTER KJE +045E ; [.1A6B.0020.0002.0443][.0000.0037.0002.0306] # CYRILLIC SMALL LETTER SHORT U +040E ; [.1A6B.0020.0008.0423][.0000.0037.0002.0306] # CYRILLIC CAPITAL LETTER SHORT U +04F1 ; [.1A6B.0020.0002.0443][.0000.0047.0002.0308] # CYRILLIC SMALL LETTER U WITH DIAERESIS +04F0 ; [.1A6B.0020.0008.0423][.0000.0047.0002.0308] # CYRILLIC CAPITAL LETTER U WITH DIAERESIS +04F3 ; [.1A6B.0020.0002.0443][.0000.004D.0002.030B] # CYRILLIC SMALL LETTER U WITH DOUBLE ACUTE +04F2 ; [.1A6B.0020.0008.0423][.0000.004D.0002.030B] # CYRILLIC CAPITAL LETTER U WITH DOUBLE ACUTE +04F5 ; [.1ABE.0020.0002.0447][.0000.0047.0002.0308] # CYRILLIC SMALL LETTER CHE WITH DIAERESIS +04F4 ; [.1ABE.0020.0008.0427][.0000.0047.0002.0308] # CYRILLIC CAPITAL LETTER CHE WITH DIAERESIS +04F9 ; [.1AF1.0020.0002.044B][.0000.0047.0002.0308] # CYRILLIC SMALL LETTER YERU WITH DIAERESIS +04F8 ; [.1AF1.0020.0008.042B][.0000.0047.0002.0308] # CYRILLIC CAPITAL LETTER YERU WITH DIAERESIS +04ED ; [.1B06.0020.0002.044D][.0000.0047.0002.0308] # CYRILLIC SMALL LETTER E WITH DIAERESIS +04EC ; [.1B06.0020.0008.042D][.0000.0047.0002.0308] # CYRILLIC CAPITAL LETTER E WITH DIAERESIS +0477 ; [.1B3C.0020.0002.0475][.0000.0065.0002.030F] # CYRILLIC SMALL LETTER IZHITSA WITH DOUBLE GRAVE ACCENT +0476 ; [.1B3C.0020.0008.0474][.0000.0065.0002.030F] # CYRILLIC CAPITAL LETTER IZHITSA WITH DOUBLE GRAVE ACCENT ENTRY }; diff --git a/cpan/Unicode-Collate/Collate/Locale/ur.pl b/cpan/Unicode-Collate/Collate/Locale/ur.pl new file mode 100644 index 0000000000..5b4f72960f --- /dev/null +++ b/cpan/Unicode-Collate/Collate/Locale/ur.pl @@ -0,0 +1,88 @@ ++{ + entry => <<'ENTRY', # for DUCET v6.0.0 +0627 ; [.1C43.0020.0002.0627] # ARABIC LETTER ALEF +0623 ; [.1C43.0021.0002.0623] # ARABIC LETTER ALEF WITH HAMZA ABOVE +0627 0654 ; [.1C43.0021.0002.0623] # ARABIC LETTER ALEF WITH HAMZA ABOVE +0622 ; [.1C43.0020.0002.0622][.FFF1.0000.0000.0000] # ARABIC LETTER ALEF WITH MADDA ABOVE +0627 0653 ; [.1C43.0020.0002.0622][.FFF1.0000.0000.0000] # ARABIC LETTER ALEF WITH MADDA ABOVE +0628 ; [.1C43.0020.0002.0628][.FFF2.0000.0000.0000] # ARABIC LETTER BEH +0628 06BE ; [.1C43.0020.0002.0628][.FFF3.0000.0000.0000] # <ARABIC LETTER BEH, ARABIC LETTER HEH DOACHASHMEE> +067E ; [.1C43.0020.0002.067E][.FFF4.0000.0000.0000] # ARABIC LETTER PEH +067E 06BE ; [.1C43.0020.0002.067E][.FFF5.0000.0000.0000] # <ARABIC LETTER PEH, ARABIC LETTER HEH DOACHASHMEE> +062A ; [.1C43.0020.0002.062A][.FFF6.0000.0000.0000] # ARABIC LETTER TEH +062A 06BE ; [.1C43.0020.0002.062A][.FFF7.0000.0000.0000] # <ARABIC LETTER TEH, ARABIC LETTER HEH DOACHASHMEE> +0679 ; [.1C43.0020.0002.0679][.FFF8.0000.0000.0000] # ARABIC LETTER TTEH +0679 06BE ; [.1C43.0020.0002.0679][.FFF9.0000.0000.0000] # <ARABIC LETTER TTEH, ARABIC LETTER HEH DOACHASHMEE> +062B ; [.1C43.0020.0002.062B][.FFFA.0000.0000.0000] # ARABIC LETTER THEH +062C ; [.1C43.0020.0002.062C][.FFFB.0000.0000.0000] # ARABIC LETTER JEEM +062C 06BE ; [.1C44.0020.0002.062C][.FFF1.0000.0000.0000] # <ARABIC LETTER JEEM, ARABIC LETTER HEH DOACHASHMEE> +0686 ; [.1C44.0020.0002.0686][.FFF2.0000.0000.0000] # ARABIC LETTER TCHEH +0686 06BE ; [.1C44.0020.0002.0686][.FFF3.0000.0000.0000] # <ARABIC LETTER TCHEH, ARABIC LETTER HEH DOACHASHMEE> +062D ; [.1C44.0020.0002.062D][.FFF4.0000.0000.0000] # ARABIC LETTER HAH +062E ; [.1C44.0020.0002.062E][.FFF5.0000.0000.0000] # ARABIC LETTER KHAH +062F ; [.1C44.0020.0002.062F][.FFF6.0000.0000.0000] # ARABIC LETTER DAL +062F 06BE ; [.1C44.0020.0002.062F][.FFF7.0000.0000.0000] # <ARABIC LETTER DAL, ARABIC LETTER HEH DOACHASHMEE> +0688 ; [.1C44.0020.0002.0688][.FFF8.0000.0000.0000] # ARABIC LETTER DDAL +0688 06BE ; [.1C44.0020.0002.0688][.FFF9.0000.0000.0000] # <ARABIC LETTER DDAL, ARABIC LETTER HEH DOACHASHMEE> +0630 ; [.1C44.0020.0002.0630][.FFFA.0000.0000.0000] # ARABIC LETTER THAL +0631 ; [.1C44.0020.0002.0631][.FFFB.0000.0000.0000] # ARABIC LETTER REH +0631 06BE ; [.1C45.0020.0002.0631][.FFF1.0000.0000.0000] # <ARABIC LETTER REH, ARABIC LETTER HEH DOACHASHMEE> +0691 ; [.1C45.0020.0002.0691][.FFF2.0000.0000.0000] # ARABIC LETTER RREH +0691 06BE ; [.1C45.0020.0002.0691][.FFF3.0000.0000.0000] # <ARABIC LETTER RREH, ARABIC LETTER HEH DOACHASHMEE> +0632 ; [.1C45.0020.0002.0632][.FFF4.0000.0000.0000] # ARABIC LETTER ZAIN +0698 ; [.1C45.0020.0002.0698][.FFF5.0000.0000.0000] # ARABIC LETTER JEH +0633 ; [.1C45.0020.0002.0633][.FFF6.0000.0000.0000] # ARABIC LETTER SEEN +0634 ; [.1C45.0020.0002.0634][.FFF7.0000.0000.0000] # ARABIC LETTER SHEEN +0635 ; [.1C45.0020.0002.0635][.FFF8.0000.0000.0000] # ARABIC LETTER SAD +0636 ; [.1C45.0020.0002.0636][.FFF9.0000.0000.0000] # ARABIC LETTER DAD +0637 ; [.1C45.0020.0002.0637][.FFFA.0000.0000.0000] # ARABIC LETTER TAH +0638 ; [.1C45.0020.0002.0638][.FFFB.0000.0000.0000] # ARABIC LETTER ZAH +0639 ; [.1C46.0020.0002.0639][.FFF1.0000.0000.0000] # ARABIC LETTER AIN +063A ; [.1C46.0020.0002.063A][.FFF2.0000.0000.0000] # ARABIC LETTER GHAIN +0641 ; [.1C46.0020.0002.0641][.FFF3.0000.0000.0000] # ARABIC LETTER FEH +0642 ; [.1C46.0020.0002.0642][.FFF4.0000.0000.0000] # ARABIC LETTER QAF +06A9 ; [.1C46.0020.0002.06A9][.FFF5.0000.0000.0000] # ARABIC LETTER KEHEH +06A9 06BE ; [.1C46.0020.0002.06A9][.FFF6.0000.0000.0000] # <ARABIC LETTER KEHEH, ARABIC LETTER HEH DOACHASHMEE> +06AF ; [.1C46.0020.0002.06AF][.FFF7.0000.0000.0000] # ARABIC LETTER GAF +06AF 06BE ; [.1C46.0020.0002.06AF][.FFF8.0000.0000.0000] # <ARABIC LETTER GAF, ARABIC LETTER HEH DOACHASHMEE> +0644 ; [.1C46.0020.0002.0644][.FFF9.0000.0000.0000] # ARABIC LETTER LAM +0644 06BE ; [.1C46.0020.0002.0644][.FFFA.0000.0000.0000] # <ARABIC LETTER LAM, ARABIC LETTER HEH DOACHASHMEE> +0645 ; [.1C46.0020.0002.0645][.FFFB.0000.0000.0000] # ARABIC LETTER MEEM +0645 06BE ; [.1C47.0020.0002.0645][.FFF1.0000.0000.0000] # <ARABIC LETTER MEEM, ARABIC LETTER HEH DOACHASHMEE> +0646 ; [.1C47.0020.0002.0646][.FFF2.0000.0000.0000] # ARABIC LETTER NOON +0646 06BE ; [.1C47.0020.0002.0646][.FFF3.0000.0000.0000] # <ARABIC LETTER NOON, ARABIC LETTER HEH DOACHASHMEE> +06BA ; [.1C47.0020.0002.06BA][.FFF4.0000.0000.0000] # ARABIC LETTER NOON GHUNNA +06BA 06BE ; [.1C47.0020.0002.06BA][.FFF5.0000.0000.0000] # <ARABIC LETTER NOON GHUNNA, ARABIC LETTER HEH DOACHASHMEE> +0648 ; [.1C47.0020.0002.0648][.FFF6.0000.0000.0000] # ARABIC LETTER WAW +0624 ; [.1C47.0021.0002.0624][.FFF6.0000.0000.0000] # ARABIC LETTER WAW WITH HAMZA ABOVE +0648 0654 ; [.1C47.0021.0002.0624][.FFF6.0000.0000.0000] # ARABIC LETTER WAW WITH HAMZA ABOVE +0648 06BE ; [.1C47.0020.0002.0648][.FFF7.0000.0000.0000] # <ARABIC LETTER WAW, ARABIC LETTER HEH DOACHASHMEE> +06C1 ; [.1C47.0020.0002.06C1][.FFF8.0000.0000.0000] # ARABIC LETTER HEH GOAL +06C2 ; [.1C47.0021.0002.06C2][.FFF8.0000.0000.0000] # ARABIC LETTER HEH GOAL WITH HAMZA ABOVE +06C1 0654 ; [.1C47.0021.0002.06C2][.FFF8.0000.0000.0000] # ARABIC LETTER HEH GOAL WITH HAMZA ABOVE +06BE ; [.1C47.0020.0002.06BE][.FFF9.0000.0000.0000] # ARABIC LETTER HEH DOACHASHMEE +06C3 ; [.1C47.0020.0002.06C3][.FFFA.0000.0000.0000] # ARABIC LETTER TEH MARBUTA GOAL +0621 ; [.1C47.0020.0002.0621][.FFFB.0000.0000.0000] # ARABIC LETTER HAMZA +06CC ; [.1C48.0020.0002.06CC][.FFF1.0000.0000.0000] # ARABIC LETTER FARSI YEH +0626 ; [.1C48.0021.0002.0626][.FFF1.0000.0000.0000] # ARABIC LETTER YEH WITH HAMZA ABOVE +064A 0654 ; [.1C48.0021.0002.0626][.FFF1.0000.0000.0000] # ARABIC LETTER YEH WITH HAMZA ABOVE +06CC 06BE ; [.1C48.0020.0002.06CC][.FFF2.0000.0000.0000] # <ARABIC LETTER FARSI YEH, ARABIC LETTER HEH DOACHASHMEE> +06D2 ; [.1C48.0020.0002.06D2][.FFF3.0000.0000.0000] # ARABIC LETTER YEH BARREE +06D3 ; [.1C48.0021.0002.06D3][.FFF3.0000.0000.0000] # ARABIC LETTER YEH BARREE WITH HAMZA ABOVE +06D2 0654 ; [.1C48.0021.0002.06D3][.FFF3.0000.0000.0000] # ARABIC LETTER YEH BARREE WITH HAMZA ABOVE +0652 ; [.0000.00A2.0002.0652] # ARABIC SUKUN +064E ; [.0000.00A3.0002.064E] # ARABIC FATHA +0650 ; [.0000.00A4.0002.0650] # ARABIC KASRA +064F ; [.0000.00A5.0002.064F] # ARABIC DAMMA +0670 ; [.0000.00A6.0002.0670] # ARABIC LETTER SUPERSCRIPT ALEF +0656 ; [.0000.00A7.0002.0656] # ARABIC SUBSCRIPT ALEF +0657 ; [.0000.00A8.0002.0657] # ARABIC INVERTED DAMMA +064B ; [.0000.00A9.0002.064B] # ARABIC FATHATAN +064D ; [.0000.00AA.0002.064D] # ARABIC KASRATAN +064C ; [.0000.00AB.0002.064C] # ARABIC DAMMATAN +0654 ; [.0000.00AC.0002.0654] # ARABIC HAMZA ABOVE +0651 ; [.0000.00AD.0002.0651] # ARABIC SHADDA +0658 ; [.0000.00AE.0002.0658] # ARABIC MARK NOON GHUNNA +0653 ; [.0000.00AF.0002.0653] # ARABIC MADDAH ABOVE +ENTRY +}; diff --git a/cpan/Unicode-Collate/Collate/Locale/wae.pl b/cpan/Unicode-Collate/Collate/Locale/wae.pl new file mode 100644 index 0000000000..abada128dc --- /dev/null +++ b/cpan/Unicode-Collate/Collate/Locale/wae.pl @@ -0,0 +1,23 @@ ++{ + entry => <<'ENTRY', # for DUCET v6.0.0 +0061 0061 ; [.15A3.0020.0002.0061][.0000.0032.0002.0301] # <LATIN SMALL LETTER A, LATIN SMALL LETTER A> +00E4 00E4 ; [.15A3.0020.0002.0061][.0000.004E.0002.0303] # <LATIN SMALL LETTER A WITH DIAERESIS, LATIN SMALL LETTER A WITH DIAERESIS> +00E4 0061 0308 ; [.15A3.0020.0002.0061][.0000.004E.0002.0303] # <LATIN SMALL LETTER A WITH DIAERESIS, LATIN SMALL LETTER A, COMBINING DIAERESIS> +0061 0308 00E4 ; [.15A3.0020.0002.0061][.0000.004E.0002.0303] # <LATIN SMALL LETTER A, COMBINING DIAERESIS, LATIN SMALL LETTER A WITH DIAERESIS> +0061 0308 0061 0308 ; [.15A3.0020.0002.0061][.0000.004E.0002.0303] # <LATIN SMALL LETTER A, COMBINING DIAERESIS, LATIN SMALL LETTER A, COMBINING DIAERESIS> +0065 0065 ; [.15FF.0020.0002.0065][.0000.0032.0002.0301] # <LATIN SMALL LETTER E, LATIN SMALL LETTER E> +0069 0069 ; [.1680.0020.0002.0069][.0000.0032.0002.0301] # <LATIN SMALL LETTER I, LATIN SMALL LETTER I> +006F 006F ; [.1724.0020.0002.006F][.0000.0032.0002.0301] # <LATIN SMALL LETTER O, LATIN SMALL LETTER O> +00F6 00F6 ; [.1724.0020.0002.006F][.0000.004E.0002.0303] # <LATIN SMALL LETTER O WITH DIAERESIS, LATIN SMALL LETTER O WITH DIAERESIS> +00F6 006F 0308 ; [.1724.0020.0002.006F][.0000.004E.0002.0303] # <LATIN SMALL LETTER O WITH DIAERESIS, LATIN SMALL LETTER O, COMBINING DIAERESIS> +006F 0308 00F6 ; [.1724.0020.0002.006F][.0000.004E.0002.0303] # <LATIN SMALL LETTER O, COMBINING DIAERESIS, LATIN SMALL LETTER O WITH DIAERESIS> +006F 0308 006F 0308 ; [.1724.0020.0002.006F][.0000.004E.0002.0303] # <LATIN SMALL LETTER O, COMBINING DIAERESIS, LATIN SMALL LETTER O, COMBINING DIAERESIS> +0063 0068 ; [.15D1.0020.0002.0063][.0000.0041.0002.030C] # <LATIN SMALL LETTER C, LATIN SMALL LETTER H> +0073 0063 0068 ; [.17A6.0020.0002.0073][.0000.0041.0002.030C] # <LATIN SMALL LETTER S, LATIN SMALL LETTER C, LATIN SMALL LETTER H> +0075 0075 ; [.17E9.0020.0002.0075][.0000.0032.0002.0301] # <LATIN SMALL LETTER U, LATIN SMALL LETTER U> +00FC 00FC ; [.17E9.0020.0002.0075][.0000.004E.0002.0303] # <LATIN SMALL LETTER U WITH DIAERESIS, LATIN SMALL LETTER U WITH DIAERESIS> +00FC 0075 0308 ; [.17E9.0020.0002.0075][.0000.004E.0002.0303] # <LATIN SMALL LETTER U WITH DIAERESIS, LATIN SMALL LETTER U, COMBINING DIAERESIS> +0075 0308 00FC ; [.17E9.0020.0002.0075][.0000.004E.0002.0303] # <LATIN SMALL LETTER U, COMBINING DIAERESIS, LATIN SMALL LETTER U WITH DIAERESIS> +0075 0308 0075 0308 ; [.17E9.0020.0002.0075][.0000.004E.0002.0303] # <LATIN SMALL LETTER U, COMBINING DIAERESIS, LATIN SMALL LETTER U, COMBINING DIAERESIS> +ENTRY +}; diff --git a/cpan/Unicode-Collate/Collate/Locale/zh_pin.pl b/cpan/Unicode-Collate/Collate/Locale/zh_pin.pl index 480cc3fa93..7b8974671c 100644 --- a/cpan/Unicode-Collate/Collate/Locale/zh_pin.pl +++ b/cpan/Unicode-Collate/Collate/Locale/zh_pin.pl @@ -208,6 +208,6 @@ use Unicode::Collate::CJK::Pinyin; 0075 0308 ; [.17E9.0025.0002.00FC] # LATIN SMALL LETTER U WITH DIAERESIS 00DC ; [.17E9.0025.0008.00DC] # LATIN CAPITAL LETTER U WITH DIAERESIS 0055 0308 ; [.17E9.0025.0008.00DC] # LATIN CAPITAL LETTER U WITH DIAERESIS -3007 ; [.A3E5.0020.0002.3007] # IDEOGRAPHIC NUMBER ZERO +3007 ; [.A3F6.0020.0002.3007] # IDEOGRAPHIC NUMBER ZERO ENTRY }; |