organicmaps/icu
13
Fork 0
mirror of https://github.com/unicode-org/icu.git synced 2025-04-05 21:45:37 +00:00
Code Issues 1 Projects Releases Wiki Activity Actions 12

Regenerated after fixing a number of bugs that showed up when going from 3.0 to 3.1 UCA.

Browse source 
X-SVN-Rev: 8898
This commit is contained in:
Mark Davis 2002-06-15 03:19:51 +00:00
parent bdc01f2749
commit 96f5290e5b
7 changed files with 3979 additions and 3701 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
tools/unicodetools/com/ibm/text/data/CheckCollationValidity.html
View file

@ -1,7 +1,7 @@
<html><body>
<h1
>1. Mismatches when NFD is OFF</h1><h2
>Date:Tue Jun 04 16:46:20 PDT 2002</h2><h2
>Date:Fri Jun 14 20:11:26 PDT 2002</h2><h2
>File Version:-3.1.1d1</h2><p
>Alternate Handling = NON_IGNORABLE</p><table border="1"
><caption
@ -59,10 +59,10 @@
<table border='1' cellspacing='0' cellpadding='2'>
<tr><th>File Order</th><th>Code and Decomp</th><th>Key and Decomp-Key</th></tr>
<tr><td colspan='3'></td><tr>
<tr><td>12573</td><td>F951 CJK COMPATIBILITY IDEOGRAPH-F951<br><964B> </td><td>
<tr><td>11414</td><td>F951 CJK COMPATIBILITY IDEOGRAPH-F951<br><964B> </td><td>
<font color='#009900'>[FF41 96FB | 0020 0020 | 0002 0002 | |]</font><br><font color='#000099'>[FF41 964B | 0020 0020 | 0002 0002 | |]</font>
</td></tr>
<tr><td>12574</td><td>FA09 CJK COMPATIBILITY IDEOGRAPH-FA09<br><964D> </td><td>
<tr><td>11415</td><td>FA09 CJK COMPATIBILITY IDEOGRAPH-FA09<br><964D> </td><td>
[FF41 964D | 0020 0020 | 0002 0002 | |]
</td></tr>
</table>

84
tools/unicodetools/com/ibm/text/data/FractionalUCA.txt
View file

@ -1,5 +1,5 @@
# Fractional UCA Table, generated from standard UCA
# M. Davis, Thu Jun 13 14:09:47 PDT 2002
# M. Davis, Fri Jun 14 20:11:34 PDT 2002
# VERSION: UCA=3.1.1d1, UCD=3.2.0
# Generated processed version, as described in ICU design document.
@ -285,6 +285,7 @@ DB40 DC7C; [,,]
DB40 DC7D; [,,]
DB40 DC7E; [,,]
DB40 DC7F; [,,]
DBFF; [,,]
FEFF; [,,]
FFF9; [,,]
FFFA; [,,]
@ -8017,6 +8018,9 @@ D835 DFA8; [51 56, 05, 95]
03EF; [51 66, 05, 05]
03EE; [51 66, 05, 8F]
0430; [52 20, 05, 05]
0410; [52 20, 05, 8F]
0430 0306; [52 22, 05, 05]
04D1; [52 22, 05, 05]
0410 0306; [52 22, 05, 8F]
@ -8027,6 +8031,9 @@ D835 DFA8; [51 56, 05, 95]
0410 0308; [52 24, 05, 8F]
04D2; [52 24, 05, 8F]
04D9; [52 26, 05, 05]
04D8; [52 26, 05, 8F]
04D9 0308; [52 28, 05, 05]
04DB; [52 28, 05, 05]
04D8 0308; [52 28, 05, 8F]
@ -8041,6 +8048,8 @@ D835 DFA8; [51 56, 05, 95]
0432; [52 2E, 05, 05]
0412; [52 2E, 05, 8F]
0433; [52 30, 05, 05]
0413; [52 30, 05, 8F]
0491; [52 30, 05, 09][, DF 79, 09]
0490; [52 30, 05, 93][, DF 79, 09]
@ -8066,6 +8075,8 @@ D835 DFA8; [51 56, 05, 95]
0499; [52 3C, 05, 05]
0498; [52 3C, 05, 8F]
0435; [52 3E, 05, 05]
0415; [52 3E, 05, 8F]
0450; [52 3E, 05, 05][, 8F, 05]
0400; [52 3E, 05, 8F][, 8F, 05]
0451; [52 3E, 05, 05][, 9D, 05]
@ -8079,6 +8090,8 @@ D835 DFA8; [51 56, 05, 95]
0454; [52 42, 05, 05]
0404; [52 42, 05, 8F]
0436; [52 44, 05, 05]
0416; [52 44, 05, 8F]
04C2; [52 44, 05, 05][, 91, 05]
04C1; [52 44, 05, 8F][, 91, 05]
@ -8090,6 +8103,9 @@ D835 DFA8; [51 56, 05, 95]
0497; [52 48, 05, 05]
0496; [52 48, 05, 8F]
0437; [52 4A, 05, 05]
0417; [52 4A, 05, 8F]
0437 0308; [52 4C, 05, 05]
04DF; [52 4C, 05, 05]
0417 0308; [52 4C, 05, 8F]
@ -8101,6 +8117,8 @@ D835 DFA8; [51 56, 05, 95]
04E1; [52 50, 05, 05]
04E0; [52 50, 05, 8F]
0438; [52 52, 05, 05]
0418; [52 52, 05, 8F]
045D; [52 52, 05, 05][, 8F, 05]
040D; [52 52, 05, 8F][, 8F, 05]
04E3; [52 52, 05, 05][, AB, 05]
@ -8111,6 +8129,9 @@ D835 DFA8; [51 56, 05, 95]
0418 0308; [52 54, 05, 8F]
04E4; [52 54, 05, 8F]
0456; [52 56, 05, 05]
0406; [52 56, 05, 8F]
0456 0308; [52 58, 05, 05]
0457; [52 58, 05, 05]
0406 0308; [52 58, 05, 8F]
@ -8124,6 +8145,9 @@ D835 DFA8; [51 56, 05, 95]
0458; [52 5C, 05, 05]
0408; [52 5C, 05, 8F]
043A; [52 5E, 05, 05]
041A; [52 5E, 05, 8F]
049B; [52 60, 05, 05]
049A; [52 60, 05, 8F]
@ -8163,11 +8187,17 @@ D835 DFA8; [51 56, 05, 95]
045A; [52 78, 05, 05]
040A; [52 78, 05, 8F]
043E; [52 7A, 05, 05]
041E; [52 7A, 05, 8F]
043E 0308; [52 7C, 05, 05]
04E7; [52 7C, 05, 05]
041E 0308; [52 7C, 05, 8F]
04E6; [52 7C, 05, 8F]
04E9; [52 7E, 05, 05]
04E8; [52 7E, 05, 8F]
04E9 0308; [52 80, 05, 05]
04EB; [52 80, 05, 05]
04E8 0308; [52 80, 05, 8F]
@ -8210,6 +8240,8 @@ D835 DFA8; [51 56, 05, 95]
041A 0301; [52 96, 05, 8F]
041A 0341; [52 96, 05, 8F]
0443; [52 98, 05, 05]
0423; [52 98, 05, 8F]
04EF; [52 98, 05, 05][, AB, 05]
04EE; [52 98, 05, 8F][, AB, 05]
@ -8267,6 +8299,9 @@ D835 DFA8; [51 56, 05, 95]
04B5; [52 B8, 05, 05]
04B4; [52 B8, 05, 8F]
0447; [52 BA, 05, 05]
0427; [52 BA, 05, 8F]
0447 0308; [52 BC, 05, 05]
04F5; [52 BC, 05, 05]
0427 0308; [52 BC, 05, 8F]
@ -8299,6 +8334,9 @@ D835 DFA8; [51 56, 05, 95]
044A; [52 CE, 05, 05]
042A; [52 CE, 05, 8F]
044B; [52 D0, 05, 05]
042B; [52 D0, 05, 8F]
044B 0308; [52 D2, 05, 05]
04F9; [52 D2, 05, 05]
042B 0308; [52 D2, 05, 8F]
@ -8313,6 +8351,9 @@ D835 DFA8; [51 56, 05, 95]
0463; [52 D8, 05, 05]
0462; [52 D8, 05, 8F]
044D; [52 DA, 05, 05]
042D; [52 DA, 05, 8F]
044D 0308; [52 DC, 05, 05]
04ED; [52 DC, 05, 05]
042D 0308; [52 DC, 05, 8F]
@ -8348,6 +8389,9 @@ D835 DFA8; [51 56, 05, 95]
0473; [52 F0, 05, 05]
0472; [52 F0, 05, 8F]
0475; [52 F2, 05, 05]
0474; [52 F2, 05, 8F]
0475 030F; [52 F4, 05, 05]
0477; [52 F4, 05, 05]
0474 030F; [52 F4, 05, 8F]
@ -8772,6 +8816,7 @@ FBF8; [57 30, 05, 2D][58 25, 05, 2D]
FBF7; [57 30, 05, 31][58 25, 05, 31]
FBF6; [57 30, 05, 33][58 25, 05, 33]
0627; [57 32, 05, 05]
FE8E; [57 32, 05, 31]
FE8D; [57 32, 05, 33]
FD3C; [57 32, D4 3D, 31]
@ -9577,6 +9622,7 @@ FBA6; [57 FC, 05, 33]
FBA5; [58 05, D4 CD, 31]
FBA4; [58 05, D4 CD, 33]
0648; [58 07, 05, 05]
06E5; [58 07, 05, 05]
FEEE; [58 07, 05, 31]
FEED; [58 07, 05, 33]
@ -9623,6 +9669,7 @@ FEEF; [58 1B, 05, 33]
FC90; [58 1B, 05, 31][, D4 ED, 31]
FC5D; [58 1B, 05, 33][, D4 ED, 33]
064A; [58 1D, 05, 05]
06E6; [58 1D, 05, 05]
FEF3; [58 1D, 05, 2D]
FEF4; [58 1D, 05, 2F]
@ -10735,6 +10782,8 @@ FBB0; [58 29, D4 CD, 33]
09E3; [5F 90, 05, 05]
09C7; [5F 92, 05, 05]
09C8; [5F 94, 05, 05]
09C7 09BE; [5F 96, 05, 05]
@ -11103,6 +11152,8 @@ FBB0; [58 29, D4 CD, 33]
0B43; [62 8C, 05, 05]
0B47; [62 8E, 05, 05]
0B47 0B56; [62 90, 05, 05]
0B48; [62 90, 05, 05]
@ -11138,6 +11189,8 @@ FBB0; [58 29, D4 CD, 33]
0B90; [63 32, 05, 05]
0B92; [63 34, 05, 05]
0B93; [63 36, 05, 05]
0B92 0BD7; [63 38, 05, 05]
@ -11197,6 +11250,10 @@ FBB0; [58 29, D4 CD, 33]
0BC2; [63 6E, 05, 05]
0BC6; [63 70, 05, 05]
0BC7; [63 72, 05, 05]
0BC8; [63 74, 05, 05]
0BC6 0BBE; [63 76, 05, 05]
@ -11328,6 +11385,8 @@ FBB0; [58 29, D4 CD, 33]
0C44; [64 92, 05, 05]
0C46; [64 94, 05, 05]
0C47; [64 96, 05, 05]
0C46 0C56; [64 98, 05, 05]
@ -11451,6 +11510,8 @@ FBB0; [58 29, D4 CD, 33]
0CBE; [65 88, 05, 05]
0CBF; [65 8A, 05, 05]
0CBF 0CD5; [65 8C, 05, 05]
0CC0; [65 8C, 05, 05]
@ -11462,6 +11523,8 @@ FBB0; [58 29, D4 CD, 33]
0CC4; [65 94, 05, 05]
0CC6; [65 96, 05, 05]
0CC6 0CD5; [65 98, 05, 05]
0CC7; [65 98, 05, 05]
@ -11597,6 +11660,10 @@ FBB0; [58 29, D4 CD, 33]
0D43; [66 92, 05, 05]
0D46; [66 94, 05, 05]
0D47; [66 96, 05, 05]
0D48; [66 98, 05, 05]
0D46 0D3E; [66 9A, 05, 05]
@ -11748,6 +11815,8 @@ FBB0; [58 29, D4 CD, 33]
0DD8; [67 A6, 05, 05]
0DD9; [67 A8, 05, 05]
0DD9 0DCA; [67 AA, 05, 05]
0DDA; [67 AA, 05, 05]
@ -11898,6 +11967,8 @@ FBB0; [58 29, D4 CD, 33]
0E4C; [68 A0, 05, 05]
0E4D; [68 A2, 05, 05]
0E81; [69 20, 05, 05]
0E82; [69 22, 05, 05]
@ -11995,6 +12066,8 @@ FBB0; [58 29, D4 CD, 33]
0ECC; [69 7C, 05, 05]
0ECD; [69 7E, 05, 05]
0F40; [6A 20, 05, 05]
0F69; [6A 20, 05, 05][6A 9E, 05, 05]
@ -12124,10 +12197,15 @@ FBB0; [58 29, D4 CD, 33]
0F62; [6A 90, 05, 05]
0F6A; [6A 90, 05, 09][, DF 79, 09]
0FB2; [6A 92, 05, 05]
0FBC; [6A 92, 05, 09][, DF 79, 09]
0FB2 0F71; [6A 92, 05, 05][6A B4, 05, 05]
0F63; [6A 94, 05, 05]
0FB3; [6A 96, 05, 05]
0FB3 0F71; [6A 96, 05, 05][6A B4, 05, 05]
0F64; [6A 98, 05, 05]
0FB4; [6A 9A, 05, 05]
@ -12157,6 +12235,8 @@ FBB0; [58 29, D4 CD, 33]
0F8B; [6A B2, 05, 05]
0F71; [6A B4, 05, 05]
0F72; [6A B6, 05, 05]
0F71 0F72; [6A B8, 05, 05]
@ -12272,6 +12352,8 @@ FBB0; [58 29, D4 CD, 33]
1024; [6B 6A, 05, 05]
1025; [6B 6C, 05, 05]
1025 102E; [6B 6E, 05, 05]
1026; [6B 6E, 05, 05]

84
tools/unicodetools/com/ibm/text/data/FractionalUCA_long.txt
View file

@ -1,5 +1,5 @@
# Fractional UCA Table, generated from standard UCA
# M. Davis, Thu Jun 13 14:09:47 PDT 2002
# M. Davis, Fri Jun 14 20:11:34 PDT 2002
# VERSION: UCA=3.1.1d1, UCD=3.2.0
# Generated processed version, as described in ICU design document.
@ -285,6 +285,7 @@ DB40 DC7C; [,,] # [0000.0000.0000] # TAG VERTICAL LINE
DB40 DC7D; [,,] # [0000.0000.0000] # TAG RIGHT CURLY BRACKET
DB40 DC7E; [,,] # [0000.0000.0000] # TAG TILDE
DB40 DC7F; [,,] # [0000.0000.0000] # CANCEL TAG
DBFF; [,,] # [0000.0000.0000] # <surrogate-DBFF>
FEFF; [,,] # [0000.0000.0000] # ZERO WIDTH NO-BREAK SPACE
FFF9; [,,] # [0000.0000.0000] # INTERLINEAR ANNOTATION ANCHOR
FFFA; [,,] # [0000.0000.0000] # INTERLINEAR ANNOTATION SEPARATOR
@ -8017,6 +8018,9 @@ D835 DFA8; [51 56, 05, 95] # [0CAC.0020.000B] # MATHEMATICAL SANS-SERIF BOLD
03EF; [51 66, 05, 05] # [0CB4.0020.0002] # COPTIC SMALL LETTER DEI
03EE; [51 66, 05, 8F] # [0CB4.0020.0008] # COPTIC CAPITAL LETTER DEI
0430; [52 20, 05, 05] # [0CB5.0020.0002] # CYRILLIC SMALL LETTER A
0410; [52 20, 05, 8F] # [0CB5.0020.0008] # CYRILLIC CAPITAL LETTER A
0430 0306; [52 22, 05, 05] # [0CB9.0020.0002] # CYRILLIC SMALL LETTER A
04D1; [52 22, 05, 05] # [0CB9.0020.0002] # CYRILLIC SMALL LETTER A WITH BREVE
0410 0306; [52 22, 05, 8F] # [0CB9.0020.0008] # CYRILLIC CAPITAL LETTER A
@ -8027,6 +8031,9 @@ D835 DFA8; [51 56, 05, 95] # [0CAC.0020.000B] # MATHEMATICAL SANS-SERIF BOLD
0410 0308; [52 24, 05, 8F] # [0CBD.0020.0008] # CYRILLIC CAPITAL LETTER A
04D2; [52 24, 05, 8F] # [0CBD.0020.0008] # CYRILLIC CAPITAL LETTER A WITH DIAERESIS
04D9; [52 26, 05, 05] # [0CC1.0020.0002] # CYRILLIC SMALL LETTER SCHWA
04D8; [52 26, 05, 8F] # [0CC1.0020.0008] # CYRILLIC CAPITAL LETTER SCHWA
04D9 0308; [52 28, 05, 05] # [0CC5.0020.0002] # CYRILLIC SMALL LETTER SCHWA
04DB; [52 28, 05, 05] # [0CC5.0020.0002] # CYRILLIC SMALL LETTER SCHWA WITH DIAERESIS
04D8 0308; [52 28, 05, 8F] # [0CC5.0020.0008] # CYRILLIC CAPITAL LETTER SCHWA
@ -8041,6 +8048,8 @@ D835 DFA8; [51 56, 05, 95] # [0CAC.0020.000B] # MATHEMATICAL SANS-SERIF BOLD
0432; [52 2E, 05, 05] # [0CD1.0020.0002] # CYRILLIC SMALL LETTER VE
0412; [52 2E, 05, 8F] # [0CD1.0020.0008] # CYRILLIC CAPITAL LETTER VE
0433; [52 30, 05, 05] # [0CD5.0020.0002] # CYRILLIC SMALL LETTER GHE
0413; [52 30, 05, 8F] # [0CD5.0020.0008] # CYRILLIC CAPITAL LETTER GHE
0491; [52 30, 05, 09][, DF 79, 09] # [0CD5.0020.0004][0000.0154.0004] # CYRILLIC SMALL LETTER GHE WITH UPTURN
0490; [52 30, 05, 93][, DF 79, 09] # [0CD5.0020.000A][0000.0154.0004] # CYRILLIC CAPITAL LETTER GHE WITH UPTURN
@ -8066,6 +8075,8 @@ D835 DFA8; [51 56, 05, 95] # [0CAC.0020.000B] # MATHEMATICAL SANS-SERIF BOLD
0499; [52 3C, 05, 05] # [0CED.0020.0002] # CYRILLIC SMALL LETTER ZE WITH DESCENDER
0498; [52 3C, 05, 8F] # [0CED.0020.0008] # CYRILLIC CAPITAL LETTER ZE WITH DESCENDER
0435; [52 3E, 05, 05] # [0CF1.0020.0002] # CYRILLIC SMALL LETTER IE
0415; [52 3E, 05, 8F] # [0CF1.0020.0008] # CYRILLIC CAPITAL LETTER IE
0450; [52 3E, 05, 05][, 8F, 05] # [0CF1.0020.0002][0000.0035.0002] # CYRILLIC SMALL LETTER IE WITH GRAVE
0400; [52 3E, 05, 8F][, 8F, 05] # [0CF1.0020.0008][0000.0035.0002] # CYRILLIC CAPITAL LETTER IE WITH GRAVE
0451; [52 3E, 05, 05][, 9D, 05] # [0CF1.0020.0002][0000.0047.0002] # CYRILLIC SMALL LETTER IO
@ -8079,6 +8090,8 @@ D835 DFA8; [51 56, 05, 95] # [0CAC.0020.000B] # MATHEMATICAL SANS-SERIF BOLD
0454; [52 42, 05, 05] # [0CF9.0020.0002] # CYRILLIC SMALL LETTER UKRAINIAN IE
0404; [52 42, 05, 8F] # [0CF9.0020.0008] # CYRILLIC CAPITAL LETTER UKRAINIAN IE
0436; [52 44, 05, 05] # [0CFD.0020.0002] # CYRILLIC SMALL LETTER ZHE
0416; [52 44, 05, 8F] # [0CFD.0020.0008] # CYRILLIC CAPITAL LETTER ZHE
04C2; [52 44, 05, 05][, 91, 05] # [0CFD.0020.0002][0000.0037.0002] # CYRILLIC SMALL LETTER ZHE WITH BREVE
04C1; [52 44, 05, 8F][, 91, 05] # [0CFD.0020.0008][0000.0037.0002] # CYRILLIC CAPITAL LETTER ZHE WITH BREVE
@ -8090,6 +8103,9 @@ D835 DFA8; [51 56, 05, 95] # [0CAC.0020.000B] # MATHEMATICAL SANS-SERIF BOLD
0497; [52 48, 05, 05] # [0D05.0020.0002] # CYRILLIC SMALL LETTER ZHE WITH DESCENDER
0496; [52 48, 05, 8F] # [0D05.0020.0008] # CYRILLIC CAPITAL LETTER ZHE WITH DESCENDER
0437; [52 4A, 05, 05] # [0D09.0020.0002] # CYRILLIC SMALL LETTER ZE
0417; [52 4A, 05, 8F] # [0D09.0020.0008] # CYRILLIC CAPITAL LETTER ZE
0437 0308; [52 4C, 05, 05] # [0D0D.0020.0002] # CYRILLIC SMALL LETTER ZE
04DF; [52 4C, 05, 05] # [0D0D.0020.0002] # CYRILLIC SMALL LETTER ZE WITH DIAERESIS
0417 0308; [52 4C, 05, 8F] # [0D0D.0020.0008] # CYRILLIC CAPITAL LETTER ZE
@ -8101,6 +8117,8 @@ D835 DFA8; [51 56, 05, 95] # [0CAC.0020.000B] # MATHEMATICAL SANS-SERIF BOLD
04E1; [52 50, 05, 05] # [0D15.0020.0002] # CYRILLIC SMALL LETTER ABKHASIAN DZE
04E0; [52 50, 05, 8F] # [0D15.0020.0008] # CYRILLIC CAPITAL LETTER ABKHASIAN DZE
0438; [52 52, 05, 05] # [0D19.0020.0002] # CYRILLIC SMALL LETTER I
0418; [52 52, 05, 8F] # [0D19.0020.0008] # CYRILLIC CAPITAL LETTER I
045D; [52 52, 05, 05][, 8F, 05] # [0D19.0020.0002][0000.0035.0002] # CYRILLIC SMALL LETTER I WITH GRAVE
040D; [52 52, 05, 8F][, 8F, 05] # [0D19.0020.0008][0000.0035.0002] # CYRILLIC CAPITAL LETTER I WITH GRAVE
04E3; [52 52, 05, 05][, AB, 05] # [0D19.0020.0002][0000.005A.0002] # CYRILLIC SMALL LETTER I WITH MACRON
@ -8111,6 +8129,9 @@ D835 DFA8; [51 56, 05, 95] # [0CAC.0020.000B] # MATHEMATICAL SANS-SERIF BOLD
0418 0308; [52 54, 05, 8F] # [0D1D.0020.0008] # CYRILLIC CAPITAL LETTER I
04E4; [52 54, 05, 8F] # [0D1D.0020.0008] # CYRILLIC CAPITAL LETTER I WITH DIAERESIS
0456; [52 56, 05, 05] # [0D21.0020.0002] # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
0406; [52 56, 05, 8F] # [0D21.0020.0008] # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
0456 0308; [52 58, 05, 05] # [0D25.0020.0002] # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
0457; [52 58, 05, 05] # [0D25.0020.0002] # CYRILLIC SMALL LETTER YI
0406 0308; [52 58, 05, 8F] # [0D25.0020.0008] # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
@ -8124,6 +8145,9 @@ D835 DFA8; [51 56, 05, 95] # [0CAC.0020.000B] # MATHEMATICAL SANS-SERIF BOLD
0458; [52 5C, 05, 05] # [0D2D.0020.0002] # CYRILLIC SMALL LETTER JE
0408; [52 5C, 05, 8F] # [0D2D.0020.0008] # CYRILLIC CAPITAL LETTER JE
043A; [52 5E, 05, 05] # [0D31.0020.0002] # CYRILLIC SMALL LETTER KA
041A; [52 5E, 05, 8F] # [0D31.0020.0008] # CYRILLIC CAPITAL LETTER KA
049B; [52 60, 05, 05] # [0D35.0020.0002] # CYRILLIC SMALL LETTER KA WITH DESCENDER
049A; [52 60, 05, 8F] # [0D35.0020.0008] # CYRILLIC CAPITAL LETTER KA WITH DESCENDER
@ -8163,11 +8187,17 @@ D835 DFA8; [51 56, 05, 95] # [0CAC.0020.000B] # MATHEMATICAL SANS-SERIF BOLD
045A; [52 78, 05, 05] # [0D65.0020.0002] # CYRILLIC SMALL LETTER NJE
040A; [52 78, 05, 8F] # [0D65.0020.0008] # CYRILLIC CAPITAL LETTER NJE
043E; [52 7A, 05, 05] # [0D69.0020.0002] # CYRILLIC SMALL LETTER O
041E; [52 7A, 05, 8F] # [0D69.0020.0008] # CYRILLIC CAPITAL LETTER O
043E 0308; [52 7C, 05, 05] # [0D6D.0020.0002] # CYRILLIC SMALL LETTER O
04E7; [52 7C, 05, 05] # [0D6D.0020.0002] # CYRILLIC SMALL LETTER O WITH DIAERESIS
041E 0308; [52 7C, 05, 8F] # [0D6D.0020.0008] # CYRILLIC CAPITAL LETTER O
04E6; [52 7C, 05, 8F] # [0D6D.0020.0008] # CYRILLIC CAPITAL LETTER O WITH DIAERESIS
04E9; [52 7E, 05, 05] # [0D71.0020.0002] # CYRILLIC SMALL LETTER BARRED O
04E8; [52 7E, 05, 8F] # [0D71.0020.0008] # CYRILLIC CAPITAL LETTER BARRED O
04E9 0308; [52 80, 05, 05] # [0D75.0020.0002] # CYRILLIC SMALL LETTER BARRED O
04EB; [52 80, 05, 05] # [0D75.0020.0002] # CYRILLIC SMALL LETTER BARRED O WITH DIAERESIS
04E8 0308; [52 80, 05, 8F] # [0D75.0020.0008] # CYRILLIC CAPITAL LETTER BARRED O
@ -8210,6 +8240,8 @@ D835 DFA8; [51 56, 05, 95] # [0CAC.0020.000B] # MATHEMATICAL SANS-SERIF BOLD
041A 0301; [52 96, 05, 8F] # [0DA1.0020.0008] # CYRILLIC CAPITAL LETTER KA
041A 0341; [52 96, 05, 8F] # [0DA1.0020.0008] # CYRILLIC CAPITAL LETTER KA
0443; [52 98, 05, 05] # [0DA5.0020.0002] # CYRILLIC SMALL LETTER U
0423; [52 98, 05, 8F] # [0DA5.0020.0008] # CYRILLIC CAPITAL LETTER U
04EF; [52 98, 05, 05][, AB, 05] # [0DA5.0020.0002][0000.005A.0002] # CYRILLIC SMALL LETTER U WITH MACRON
04EE; [52 98, 05, 8F][, AB, 05] # [0DA5.0020.0008][0000.005A.0002] # CYRILLIC CAPITAL LETTER U WITH MACRON
@ -8267,6 +8299,9 @@ D835 DFA8; [51 56, 05, 95] # [0CAC.0020.000B] # MATHEMATICAL SANS-SERIF BOLD
04B5; [52 B8, 05, 05] # [0DE5.0020.0002] # CYRILLIC SMALL LIGATURE TE TSE
04B4; [52 B8, 05, 8F] # [0DE5.0020.0008] # CYRILLIC CAPITAL LIGATURE TE TSE
0447; [52 BA, 05, 05] # [0DE9.0020.0002] # CYRILLIC SMALL LETTER CHE
0427; [52 BA, 05, 8F] # [0DE9.0020.0008] # CYRILLIC CAPITAL LETTER CHE
0447 0308; [52 BC, 05, 05] # [0DED.0020.0002] # CYRILLIC SMALL LETTER CHE
04F5; [52 BC, 05, 05] # [0DED.0020.0002] # CYRILLIC SMALL LETTER CHE WITH DIAERESIS
0427 0308; [52 BC, 05, 8F] # [0DED.0020.0008] # CYRILLIC CAPITAL LETTER CHE
@ -8299,6 +8334,9 @@ D835 DFA8; [51 56, 05, 95] # [0CAC.0020.000B] # MATHEMATICAL SANS-SERIF BOLD
044A; [52 CE, 05, 05] # [0E11.0020.0002] # CYRILLIC SMALL LETTER HARD SIGN
042A; [52 CE, 05, 8F] # [0E11.0020.0008] # CYRILLIC CAPITAL LETTER HARD SIGN
044B; [52 D0, 05, 05] # [0E15.0020.0002] # CYRILLIC SMALL LETTER YERU
042B; [52 D0, 05, 8F] # [0E15.0020.0008] # CYRILLIC CAPITAL LETTER YERU
044B 0308; [52 D2, 05, 05] # [0E19.0020.0002] # CYRILLIC SMALL LETTER YERU
04F9; [52 D2, 05, 05] # [0E19.0020.0002] # CYRILLIC SMALL LETTER YERU WITH DIAERESIS
042B 0308; [52 D2, 05, 8F] # [0E19.0020.0008] # CYRILLIC CAPITAL LETTER YERU
@ -8313,6 +8351,9 @@ D835 DFA8; [51 56, 05, 95] # [0CAC.0020.000B] # MATHEMATICAL SANS-SERIF BOLD
0463; [52 D8, 05, 05] # [0E25.0020.0002] # CYRILLIC SMALL LETTER YAT
0462; [52 D8, 05, 8F] # [0E25.0020.0008] # CYRILLIC CAPITAL LETTER YAT
044D; [52 DA, 05, 05] # [0E29.0020.0002] # CYRILLIC SMALL LETTER E
042D; [52 DA, 05, 8F] # [0E29.0020.0008] # CYRILLIC CAPITAL LETTER E
044D 0308; [52 DC, 05, 05] # [0E2D.0020.0002] # CYRILLIC SMALL LETTER E
04ED; [52 DC, 05, 05] # [0E2D.0020.0002] # CYRILLIC SMALL LETTER E WITH DIAERESIS
042D 0308; [52 DC, 05, 8F] # [0E2D.0020.0008] # CYRILLIC CAPITAL LETTER E
@ -8348,6 +8389,9 @@ D835 DFA8; [51 56, 05, 95] # [0CAC.0020.000B] # MATHEMATICAL SANS-SERIF BOLD
0473; [52 F0, 05, 05] # [0E55.0020.0002] # CYRILLIC SMALL LETTER FITA
0472; [52 F0, 05, 8F] # [0E55.0020.0008] # CYRILLIC CAPITAL LETTER FITA
0475; [52 F2, 05, 05] # [0E59.0020.0002] # CYRILLIC SMALL LETTER IZHITSA
0474; [52 F2, 05, 8F] # [0E59.0020.0008] # CYRILLIC CAPITAL LETTER IZHITSA
0475 030F; [52 F4, 05, 05] # [0E5D.0020.0002] # CYRILLIC SMALL LETTER IZHITSA
0477; [52 F4, 05, 05] # [0E5D.0020.0002] # CYRILLIC SMALL LETTER IZHITSA WITH DOUBLE GRAVE ACCENT
0474 030F; [52 F4, 05, 8F] # [0E5D.0020.0008] # CYRILLIC CAPITAL LETTER IZHITSA
@ -8772,6 +8816,7 @@ FBF8; [57 30, 05, 2D][58 25, 05, 2D] # [0ED5.0020.0017][0F4D.0020.0017] # ARA
FBF7; [57 30, 05, 31][58 25, 05, 31] # [0ED5.0020.0019][0F4D.0020.0019] # ARABIC LIGATURE YEH WITH HAMZA ABOVE WITH E FINAL FORM
FBF6; [57 30, 05, 33][58 25, 05, 33] # [0ED5.0020.001A][0F4D.0020.001A] # ARABIC LIGATURE YEH WITH HAMZA ABOVE WITH E ISOLATED FORM
0627; [57 32, 05, 05] # [0ED6.0020.0002] # ARABIC LETTER ALEF
FE8E; [57 32, 05, 31] # [0ED6.0020.0019] # ARABIC LETTER ALEF FINAL FORM
FE8D; [57 32, 05, 33] # [0ED6.0020.001A] # ARABIC LETTER ALEF ISOLATED FORM
FD3C; [57 32, D4 3D, 31] # [0ED6.00BD.0019] # ARABIC LIGATURE ALEF WITH FATHATAN FINAL FORM
@ -9577,6 +9622,7 @@ FBA6; [57 FC, 05, 33] # [0F3B.0020.001A] # ARABIC LETTER HEH GOAL ISOLATED FO
FBA5; [58 05, D4 CD, 31] # [0F3D.00CC.0019] # ARABIC LETTER HEH WITH YEH ABOVE FINAL FORM
FBA4; [58 05, D4 CD, 33] # [0F3D.00CC.001A] # ARABIC LETTER HEH WITH YEH ABOVE ISOLATED FORM
0648; [58 07, 05, 05] # [0F3E.0020.0002] # ARABIC LETTER WAW
06E5; [58 07, 05, 05] # [0F3E.0020.0002] # ARABIC SMALL WAW
FEEE; [58 07, 05, 31] # [0F3E.0020.0019] # ARABIC LETTER WAW FINAL FORM
FEED; [58 07, 05, 33] # [0F3E.0020.001A] # ARABIC LETTER WAW ISOLATED FORM
@ -9623,6 +9669,7 @@ FEEF; [58 1B, 05, 33] # [0F48.0020.001A] # ARABIC LETTER ALEF MAKSURA ISOLATE
FC90; [58 1B, 05, 31][, D4 ED, 31] # [0F48.0020.0019][0000.00CE.0019] # ARABIC LIGATURE ALEF MAKSURA WITH SUPERSCRIPT ALEF FINAL FORM
FC5D; [58 1B, 05, 33][, D4 ED, 33] # [0F48.0020.001A][0000.00CE.001A] # ARABIC LIGATURE ALEF MAKSURA WITH SUPERSCRIPT ALEF ISOLATED FORM
064A; [58 1D, 05, 05] # [0F49.0020.0002] # ARABIC LETTER YEH
06E6; [58 1D, 05, 05] # [0F49.0020.0002] # ARABIC SMALL YEH
FEF3; [58 1D, 05, 2D] # [0F49.0020.0017] # ARABIC LETTER YEH INITIAL FORM
FEF4; [58 1D, 05, 2F] # [0F49.0020.0018] # ARABIC LETTER YEH MEDIAL FORM
@ -10735,6 +10782,8 @@ FBB0; [58 29, D4 CD, 33] # [0F4F.00CC.001A] # ARABIC LETTER YEH BARREE WITH H
09E3; [5F 90, 05, 05] # [1156.0020.0002] # BENGALI VOWEL SIGN VOCALIC LL
09C7; [5F 92, 05, 05] # [1157.0020.0002] # BENGALI VOWEL SIGN E
09C8; [5F 94, 05, 05] # [1158.0020.0002] # BENGALI VOWEL SIGN AI
09C7 09BE; [5F 96, 05, 05] # [1159.0020.0002] # BENGALI VOWEL SIGN E
@ -11103,6 +11152,8 @@ FBB0; [58 29, D4 CD, 33] # [0F4F.00CC.001A] # ARABIC LETTER YEH BARREE WITH H
0B43; [62 8C, 05, 05] # [120A.0020.0002] # ORIYA VOWEL SIGN VOCALIC R
0B47; [62 8E, 05, 05] # [120B.0020.0002] # ORIYA VOWEL SIGN E
0B47 0B56; [62 90, 05, 05] # [120C.0020.0002] # ORIYA VOWEL SIGN E
0B48; [62 90, 05, 05] # [120C.0020.0002] # ORIYA VOWEL SIGN AI
@ -11138,6 +11189,8 @@ FBB0; [58 29, D4 CD, 33] # [0F4F.00CC.001A] # ARABIC LETTER YEH BARREE WITH H
0B90; [63 32, 05, 05] # [121B.0020.0002] # TAMIL LETTER AI
0B92; [63 34, 05, 05] # [121C.0020.0002] # TAMIL LETTER O
0B93; [63 36, 05, 05] # [121D.0020.0002] # TAMIL LETTER OO
0B92 0BD7; [63 38, 05, 05] # [121E.0020.0002] # TAMIL LETTER O
@ -11197,6 +11250,10 @@ FBB0; [58 29, D4 CD, 33] # [0F4F.00CC.001A] # ARABIC LETTER YEH BARREE WITH H
0BC2; [63 6E, 05, 05] # [1239.0020.0002] # TAMIL VOWEL SIGN UU
0BC6; [63 70, 05, 05] # [123A.0020.0002] # TAMIL VOWEL SIGN E
0BC7; [63 72, 05, 05] # [123B.0020.0002] # TAMIL VOWEL SIGN EE
0BC8; [63 74, 05, 05] # [123C.0020.0002] # TAMIL VOWEL SIGN AI
0BC6 0BBE; [63 76, 05, 05] # [123D.0020.0002] # TAMIL VOWEL SIGN E
@ -11328,6 +11385,8 @@ FBB0; [58 29, D4 CD, 33] # [0F4F.00CC.001A] # ARABIC LETTER YEH BARREE WITH H
0C44; [64 92, 05, 05] # [127B.0020.0002] # TELUGU VOWEL SIGN VOCALIC RR
0C46; [64 94, 05, 05] # [127C.0020.0002] # TELUGU VOWEL SIGN E
0C47; [64 96, 05, 05] # [127D.0020.0002] # TELUGU VOWEL SIGN EE
0C46 0C56; [64 98, 05, 05] # [127E.0020.0002] # TELUGU VOWEL SIGN E
@ -11451,6 +11510,8 @@ FBB0; [58 29, D4 CD, 33] # [0F4F.00CC.001A] # ARABIC LETTER YEH BARREE WITH H
0CBE; [65 88, 05, 05] # [12B9.0020.0002] # KANNADA VOWEL SIGN AA
0CBF; [65 8A, 05, 05] # [12BA.0020.0002] # KANNADA VOWEL SIGN I
0CBF 0CD5; [65 8C, 05, 05] # [12BB.0020.0002] # KANNADA VOWEL SIGN I
0CC0; [65 8C, 05, 05] # [12BB.0020.0002] # KANNADA VOWEL SIGN II
@ -11462,6 +11523,8 @@ FBB0; [58 29, D4 CD, 33] # [0F4F.00CC.001A] # ARABIC LETTER YEH BARREE WITH H
0CC4; [65 94, 05, 05] # [12BF.0020.0002] # KANNADA VOWEL SIGN VOCALIC RR
0CC6; [65 96, 05, 05] # [12C0.0020.0002] # KANNADA VOWEL SIGN E
0CC6 0CD5; [65 98, 05, 05] # [12C1.0020.0002] # KANNADA VOWEL SIGN E
0CC7; [65 98, 05, 05] # [12C1.0020.0002] # KANNADA VOWEL SIGN EE
@ -11597,6 +11660,10 @@ FBB0; [58 29, D4 CD, 33] # [0F4F.00CC.001A] # ARABIC LETTER YEH BARREE WITH H
0D43; [66 92, 05, 05] # [1302.0020.0002] # MALAYALAM VOWEL SIGN VOCALIC R
0D46; [66 94, 05, 05] # [1303.0020.0002] # MALAYALAM VOWEL SIGN E
0D47; [66 96, 05, 05] # [1304.0020.0002] # MALAYALAM VOWEL SIGN EE
0D48; [66 98, 05, 05] # [1305.0020.0002] # MALAYALAM VOWEL SIGN AI
0D46 0D3E; [66 9A, 05, 05] # [1306.0020.0002] # MALAYALAM VOWEL SIGN E
@ -11748,6 +11815,8 @@ FBB0; [58 29, D4 CD, 33] # [0F4F.00CC.001A] # ARABIC LETTER YEH BARREE WITH H
0DD8; [67 A6, 05, 05] # [134E.0020.0002] # SINHALA VOWEL SIGN GAETTA-PILLA
0DD9; [67 A8, 05, 05] # [134F.0020.0002] # SINHALA VOWEL SIGN KOMBUVA
0DD9 0DCA; [67 AA, 05, 05] # [1350.0020.0002] # SINHALA VOWEL SIGN KOMBUVA
0DDA; [67 AA, 05, 05] # [1350.0020.0002] # SINHALA VOWEL SIGN DIGA KOMBUVA
@ -11898,6 +11967,8 @@ FBB0; [58 29, D4 CD, 33] # [0F4F.00CC.001A] # ARABIC LETTER YEH BARREE WITH H
0E4C; [68 A0, 05, 05] # [1398.0020.0002] # THAI CHARACTER THANTHAKHAT
0E4D; [68 A2, 05, 05] # [1399.0020.0002] # THAI CHARACTER NIKHAHIT
0E81; [69 20, 05, 05] # [139A.0020.0002] # LAO LETTER KO
0E82; [69 22, 05, 05] # [139B.0020.0002] # LAO LETTER KHO SUNG
@ -11995,6 +12066,8 @@ FBB0; [58 29, D4 CD, 33] # [0F4F.00CC.001A] # ARABIC LETTER YEH BARREE WITH H
0ECC; [69 7C, 05, 05] # [13C8.0020.0002] # LAO CANCELLATION MARK
0ECD; [69 7E, 05, 05] # [13C9.0020.0002] # LAO NIGGAHITA
0F40; [6A 20, 05, 05] # [13CA.0020.0002] # TIBETAN LETTER KA
0F69; [6A 20, 05, 05][6A 9E, 05, 05] # [13CA.0020.0002][1409.0020.0002] # TIBETAN LETTER KSSA
@ -12124,10 +12197,15 @@ FBB0; [58 29, D4 CD, 33] # [0F4F.00CC.001A] # ARABIC LETTER YEH BARREE WITH H
0F62; [6A 90, 05, 05] # [1402.0020.0002] # TIBETAN LETTER RA
0F6A; [6A 90, 05, 09][, DF 79, 09] # [1402.0020.0004][0000.0154.0004] # TIBETAN LETTER FIXED-FORM RA
0FB2; [6A 92, 05, 05] # [1403.0020.0002] # TIBETAN SUBJOINED LETTER RA
0FBC; [6A 92, 05, 09][, DF 79, 09] # [1403.0020.0004][0000.0154.0004] # TIBETAN SUBJOINED LETTER FIXED-FORM RA
0FB2 0F71; [6A 92, 05, 05][6A B4, 05, 05] # [1403.0020.0002][1414.0020.0002] # TIBETAN SUBJOINED LETTER RA
0F63; [6A 94, 05, 05] # [1404.0020.0002] # TIBETAN LETTER LA
0FB3; [6A 96, 05, 05] # [1405.0020.0002] # TIBETAN SUBJOINED LETTER LA
0FB3 0F71; [6A 96, 05, 05][6A B4, 05, 05] # [1405.0020.0002][1414.0020.0002] # TIBETAN SUBJOINED LETTER LA
0F64; [6A 98, 05, 05] # [1406.0020.0002] # TIBETAN LETTER SHA
0FB4; [6A 9A, 05, 05] # [1407.0020.0002] # TIBETAN SUBJOINED LETTER SHA
@ -12157,6 +12235,8 @@ FBB0; [58 29, D4 CD, 33] # [0F4F.00CC.001A] # ARABIC LETTER YEH BARREE WITH H
0F8B; [6A B2, 05, 05] # [1413.0020.0002] # TIBETAN SIGN GRU MED RGYINGS
0F71; [6A B4, 05, 05] # [1414.0020.0002] # TIBETAN VOWEL SIGN AA
0F72; [6A B6, 05, 05] # [1415.0020.0002] # TIBETAN VOWEL SIGN I
0F71 0F72; [6A B8, 05, 05] # [1416.0020.0002] # TIBETAN VOWEL SIGN AA
@ -12272,6 +12352,8 @@ FBB0; [58 29, D4 CD, 33] # [0F4F.00CC.001A] # ARABIC LETTER YEH BARREE WITH H
1024; [6B 6A, 05, 05] # [1449.0020.0002] # MYANMAR LETTER II
1025; [6B 6C, 05, 05] # [144A.0020.0002] # MYANMAR LETTER U
1025 102E; [6B 6E, 05, 05] # [144B.0020.0002] # MYANMAR LETTER U
1026; [6B 6E, 05, 05] # [144B.0020.0002] # MYANMAR LETTER UU

6
tools/unicodetools/com/ibm/text/data/FractionalUCA_summary.txt
View file

@ -219,7 +219,7 @@ Last: 50A4 LATIN LETTER BIDENTAL PERCUSSIVE
First: 5120, U+03B1 GREEK SMALL LETTER ALPHA
Last: 5166 COPTIC CAPITAL LETTER DEI
First: 5222, U+0430 CYRILLIC SMALL LETTER A
First: 5220, U+0430 CYRILLIC SMALL LETTER A
Last: 52F8 CYRILLIC LETTER PALOCHKA
First: 5420, U+10D0 GEORGIAN LETTER AN
@ -283,10 +283,10 @@ First: 6720, U+0D85 SINHALA LETTER AYANNA
Last: 67B6 SINHALA VOWEL SIGN DIGA GAYANUKITTA
First: 6820, U+0E01 THAI CHARACTER KO KAI
Last: 68A0 THAI CHARACTER THANTHAKHAT
Last: 68A2 THAI CHARACTER NIKHAHIT
First: 6920, U+0E81 LAO LETTER KO
Last: 697C LAO CANCELLATION MARK
Last: 697E LAO NIGGAHITA
First: 6A20, U+0F40 TIBETAN LETTER KA
Last: 6AD2 TIBETAN MARK HALANTA

2405
tools/unicodetools/com/ibm/text/data/UCA_Rules.txt
View file

File diff suppressed because it is too large Load diff

2
tools/unicodetools/com/ibm/text/data/UCA_Rules.xml
View file

File diff suppressed because one or more lines are too long

5093
tools/unicodetools/com/ibm/text/data/UCA_Rules_With_Names.txt
View file

File diff suppressed because it is too large Load diff