mirror of
https://github.com/unicode-org/icu.git
synced 2025-04-08 06:53:45 +00:00
ICU-3737 synchronize translit rules with ICU4J
X-SVN-Rev: 15395
This commit is contained in:
parent
6f1f6cf374
commit
9cc0f7b308
36 changed files with 571 additions and 467 deletions
|
@ -1,12 +1,12 @@
|
|||
// -*- Coding: utf-8; -*-
|
||||
//--------------------------------------------------------------------
|
||||
// Copyright (c) 1999-2002, International Business Machines
|
||||
// Copyright (c) 1999-2004, International Business Machines
|
||||
// Corporation and others. All Rights Reserved.
|
||||
//--------------------------------------------------------------------
|
||||
// THIS IS A MACHINE-GENERATED FILE
|
||||
// Tool: dumpicurules.bat
|
||||
// Tool: dumpICUrules.bat
|
||||
// Source: ../../../impl/data/Transliterator_Any_Accents.txt
|
||||
// Date: Sat Jul 27 10:31:01 2002
|
||||
// Date: Tue May 18 17:24:48 2004
|
||||
//--------------------------------------------------------------------
|
||||
|
||||
// Any_Accents
|
||||
|
|
|
@ -1,12 +1,12 @@
|
|||
// -*- Coding: utf-8; -*-
|
||||
//--------------------------------------------------------------------
|
||||
// Copyright (c) 1999-2002, International Business Machines
|
||||
// Copyright (c) 1999-2004, International Business Machines
|
||||
// Corporation and others. All Rights Reserved.
|
||||
//--------------------------------------------------------------------
|
||||
// THIS IS A MACHINE-GENERATED FILE
|
||||
// Tool: dumpicurules.bat
|
||||
// Tool: dumpICUrules.bat
|
||||
// Source: ../../../impl/data/Transliterator_Any_Publishing.txt
|
||||
// Date: Sat Jul 27 10:31:01 2002
|
||||
// Date: Tue May 18 17:24:48 2004
|
||||
//--------------------------------------------------------------------
|
||||
|
||||
// Any_Publishing
|
||||
|
|
|
@ -1,12 +1,12 @@
|
|||
// -*- Coding: utf-8; -*-
|
||||
//--------------------------------------------------------------------
|
||||
// Copyright (c) 1999-2002, International Business Machines
|
||||
// Copyright (c) 1999-2004, International Business Machines
|
||||
// Corporation and others. All Rights Reserved.
|
||||
//--------------------------------------------------------------------
|
||||
// THIS IS A MACHINE-GENERATED FILE
|
||||
// Tool: dumpicurules.bat
|
||||
// Tool: dumpICUrules.bat
|
||||
// Source: ../../../impl/data/Transliterator_Arabic_Latin.txt
|
||||
// Date: Sat Jul 27 10:31:01 2002
|
||||
// Date: Tue May 18 17:24:48 2004
|
||||
//--------------------------------------------------------------------
|
||||
|
||||
// Arabic_Latin
|
||||
|
|
|
@ -1,12 +1,12 @@
|
|||
// -*- Coding: utf-8; -*-
|
||||
//--------------------------------------------------------------------
|
||||
// Copyright (c) 1999-2002, International Business Machines
|
||||
// Copyright (c) 1999-2004, International Business Machines
|
||||
// Corporation and others. All Rights Reserved.
|
||||
//--------------------------------------------------------------------
|
||||
// THIS IS A MACHINE-GENERATED FILE
|
||||
// Tool: dumpicurules.bat
|
||||
// Tool: dumpICUrules.bat
|
||||
// Source: ../../../impl/data/Transliterator_Bengali_InterIndic.txt
|
||||
// Date: Sat Jul 27 10:31:01 2002
|
||||
// Date: Tue May 18 17:24:48 2004
|
||||
//--------------------------------------------------------------------
|
||||
|
||||
// Bengali_InterIndic
|
||||
|
@ -69,6 +69,7 @@ t_Beng_InterIndic {
|
|||
"\u09B8>\uE038;" // LETTER SA
|
||||
"\u09B9>\uE039;" // LETTER HA
|
||||
"\u09BC>\uE03C;" // SIGN NUKTA
|
||||
"\u09BD>\uE03D;" // SIGN AVAGRAHA
|
||||
"\u09BE>\uE03E;" // VOWEL SIGN AA
|
||||
"\u09BF>\uE03F;" // VOWEL SIGN I
|
||||
"\u09C0>\uE040;" // VOWEL SIGN II
|
||||
|
@ -98,17 +99,18 @@ t_Beng_InterIndic {
|
|||
"\u09ED>\uE06D;" // DIGIT SEVEN
|
||||
"\u09EE>\uE06E;" // DIGIT EIGHT
|
||||
"\u09EF>\uE06F;" // DIGIT NINE
|
||||
"\u09F0>;" // UNMAPPED Bengali-InterIndic: LETTER RA WITH MIDDLE DIAGONAL
|
||||
"\u09F1>;" // UNMAPPED Bengali-InterIndic: LETTER RA WITH LOWER DIAGONAL
|
||||
"\u09F2>;" // UNMAPPED Bengali-InterIndic: RUPEE MARK
|
||||
"\u09F3>;" // UNMAPPED Bengali-InterIndic: RUPEE SIGN
|
||||
"\u09F4>;" // UNMAPPED Bengali-InterIndic: CURRENCY NUMERATOR ONE
|
||||
"\u09F5>;" // UNMAPPED Bengali-InterIndic: CURRENCY NUMERATOR TWO
|
||||
"\u09F6>;" // UNMAPPED Bengali-InterIndic: CURRENCY NUMERATOR THREE
|
||||
"\u09F7>;" // UNMAPPED Bengali-InterIndic: CURRENCY NUMERATOR FOUR
|
||||
"\u09F8>;" // UNMAPPED Bengali-InterIndic: CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR
|
||||
"\u09F9>;" // UNMAPPED Bengali-InterIndic: CURRENCY DENOMINATOR SIXTEEN
|
||||
"\u09FA>;" // ISSHAR
|
||||
"\u09F0>\ue071;" // Bengali-InterIndic: LETTER RA WITH MIDDLE DIAGONAL
|
||||
"\u09F1>\ue072;" // Bengali-InterIndic: LETTER RA WITH LOWER DIAGONAL
|
||||
"\u09F2>\ue073;" // Bengali-InterIndic: RUPEE MARK
|
||||
"\u09F3>\ue074;" // Bengali-InterIndic: RUPEE SIGN
|
||||
"\u09F4>\ue075;" // Bengali-InterIndic: CURRENCY NUMERATOR ONE
|
||||
"\u09F5>\ue076;" // Bengali-InterIndic: CURRENCY NUMERATOR TWO
|
||||
"\u09F6>\ue077;" // Bengali-InterIndic: CURRENCY NUMERATOR THREE
|
||||
"\u09F7>\ue078;" // Bengali-InterIndic: CURRENCY NUMERATOR FOUR
|
||||
"\u09F8>\ue079;" // Bengali-InterIndic: CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR
|
||||
"\u09F9>\ue07A;" // Bengali-InterIndic: CURRENCY DENOMINATOR SIXTEEN
|
||||
"\u09FA>\ue07B;" // ISSHAR
|
||||
|
||||
"\u0964>\ue064;" // DANDA
|
||||
"\u0965>\ue065;" // DOUBLE DANDA
|
||||
// :: NFC (NFD) ;
|
||||
|
|
|
@ -1,12 +1,12 @@
|
|||
// -*- Coding: utf-8; -*-
|
||||
//--------------------------------------------------------------------
|
||||
// Copyright (c) 1999-2002, International Business Machines
|
||||
// Copyright (c) 1999-2004, International Business Machines
|
||||
// Corporation and others. All Rights Reserved.
|
||||
//--------------------------------------------------------------------
|
||||
// THIS IS A MACHINE-GENERATED FILE
|
||||
// Tool: dumpicurules.bat
|
||||
// Tool: dumpICUrules.bat
|
||||
// Source: ../../../impl/data/Transliterator_Cyrillic_Latin.txt
|
||||
// Date: Sat Jul 27 10:31:01 2002
|
||||
// Date: Tue May 18 17:24:48 2004
|
||||
//--------------------------------------------------------------------
|
||||
|
||||
// Cyrillic_Latin
|
||||
|
|
|
@ -1,12 +1,12 @@
|
|||
// -*- Coding: utf-8; -*-
|
||||
//--------------------------------------------------------------------
|
||||
// Copyright (c) 1999-2002, International Business Machines
|
||||
// Copyright (c) 1999-2004, International Business Machines
|
||||
// Corporation and others. All Rights Reserved.
|
||||
//--------------------------------------------------------------------
|
||||
// THIS IS A MACHINE-GENERATED FILE
|
||||
// Tool: dumpicurules.bat
|
||||
// Tool: dumpICUrules.bat
|
||||
// Source: ../../../impl/data/Transliterator_Devanagari_InterIndic.txt
|
||||
// Date: Sat Jul 27 10:31:01 2002
|
||||
// Date: Tue May 18 17:24:48 2004
|
||||
//--------------------------------------------------------------------
|
||||
|
||||
// Devanagari_InterIndic
|
||||
|
@ -25,6 +25,7 @@ t_Deva_InterIndic {
|
|||
"\u0901>\uE001;" // SIGN CANDRABINDU
|
||||
"\u0902>\uE002;" // SIGN ANUSVARA
|
||||
"\u0903>\uE003;" // SIGN VISARGA
|
||||
"\u0904>\uE004;" // SIGN SHORT A
|
||||
"\u0905>\uE005;" // LETTER A
|
||||
"\u0906>\uE006;" // LETTER AA
|
||||
"\u0907>\uE007;" // LETTER I
|
||||
|
@ -126,7 +127,7 @@ t_Deva_InterIndic {
|
|||
"\u096D>\uE06D;" // DIGIT SEVEN
|
||||
"\u096E>\uE06E;" // DIGIT EIGHT
|
||||
"\u096F>\uE06F;" // DIGIT NINE
|
||||
// \u0970>; # UNMAPPED Devanagari-InterIndic: ABBREVIATION SIGN
|
||||
"\u0970>\uE070;" // Devanagari-InterIndic: ABBREVIATION SIGN
|
||||
// :: NFC (NFD) ;
|
||||
}
|
||||
}
|
||||
|
|
|
@ -1,12 +1,12 @@
|
|||
// -*- Coding: utf-8; -*-
|
||||
//--------------------------------------------------------------------
|
||||
// Copyright (c) 1999-2003, International Business Machines
|
||||
// Copyright (c) 1999-2004, International Business Machines
|
||||
// Corporation and others. All Rights Reserved.
|
||||
//--------------------------------------------------------------------
|
||||
// THIS IS A MACHINE-GENERATED FILE
|
||||
// Tool: dumpicurules.bat
|
||||
// Tool: dumpICUrules.bat
|
||||
// Source: ../../../impl/data/Transliterator_Fullwidth_Halfwidth.txt
|
||||
// Date: Sat Jul 27 10:31:01 2002
|
||||
// Date: Tue May 18 17:24:48 2004
|
||||
//--------------------------------------------------------------------
|
||||
|
||||
// Fullwidth_Halfwidth
|
||||
|
|
|
@ -6,7 +6,7 @@
|
|||
// THIS IS A MACHINE-GENERATED FILE
|
||||
// Tool: dumpICUrules.bat
|
||||
// Source: ../../../impl/data/Transliterator_Greek_Latin.txt
|
||||
// Date: Fri Apr 16 10:06:58 2004
|
||||
// Date: Tue May 18 17:24:48 2004
|
||||
//--------------------------------------------------------------------
|
||||
|
||||
// Greek_Latin
|
||||
|
|
|
@ -6,7 +6,7 @@
|
|||
// THIS IS A MACHINE-GENERATED FILE
|
||||
// Tool: dumpICUrules.bat
|
||||
// Source: ../../../impl/data/Transliterator_Greek_Latin_UNGEGN.txt
|
||||
// Date: Fri Apr 16 10:06:58 2004
|
||||
// Date: Tue May 18 17:24:48 2004
|
||||
//--------------------------------------------------------------------
|
||||
|
||||
// Greek_Latin_UNGEGN
|
||||
|
|
|
@ -1,12 +1,12 @@
|
|||
// -*- Coding: utf-8; -*-
|
||||
//--------------------------------------------------------------------
|
||||
// Copyright (c) 1999-2002, International Business Machines
|
||||
// Copyright (c) 1999-2004, International Business Machines
|
||||
// Corporation and others. All Rights Reserved.
|
||||
//--------------------------------------------------------------------
|
||||
// THIS IS A MACHINE-GENERATED FILE
|
||||
// Tool: dumpicurules.bat
|
||||
// Tool: dumpICUrules.bat
|
||||
// Source: ../../../impl/data/Transliterator_Gujarati_InterIndic.txt
|
||||
// Date: Sat Jul 27 10:31:01 2002
|
||||
// Date: Tue May 18 17:24:48 2004
|
||||
//--------------------------------------------------------------------
|
||||
|
||||
// Gujarati_InterIndic
|
||||
|
@ -29,10 +29,11 @@ t_Gujr_InterIndic {
|
|||
"\u0a89>\ue009;" // LETTER U
|
||||
"\u0a8a>\ue00a;" // LETTER UU
|
||||
"\u0a8b>\ue00b;" // LETTER VOCALIC R
|
||||
"\u0a8d>\ue00d;" // UNMAPPED Gujarati-InterIndic: VOWEL CANDRA E
|
||||
"\u0a8c>\ue00c;" // LETTER VOCALLIC L
|
||||
"\u0a8d>\ue00d;" // VOWEL CANDRA E
|
||||
"\u0a8f>\ue00f;" // LETTER E
|
||||
"\u0a90>\ue010;" // LETTER AI
|
||||
"\u0a91>\ue011;" // UNMAPPED Gujarati-InterIndic: VOWEL CANDRA O
|
||||
"\u0a91>\ue011;" // VOWEL CANDRA O
|
||||
"\u0a93>\ue013;" // LETTER O
|
||||
"\u0a94>\ue014;" // LETTER AU
|
||||
"\u0a95>\ue015;" // LETTER KA
|
||||
|
@ -87,6 +88,7 @@ t_Gujr_InterIndic {
|
|||
"\u0acd>\ue04d;" // SIGN VIRAMA
|
||||
"\u0ad0>\ue050;" // OM
|
||||
"\u0ae0>\ue060;" // LETTER VOCALIC RR
|
||||
"\u0ae1>\ue061;" // LETTER VOCALIC LL
|
||||
"\u0ae6>\ue066;" // DIGIT ZERO
|
||||
"\u0ae7>\ue067;" // DIGIT ONE
|
||||
"\u0ae8>\ue068;" // DIGIT TWO
|
||||
|
|
|
@ -1,12 +1,12 @@
|
|||
// -*- Coding: utf-8; -*-
|
||||
//--------------------------------------------------------------------
|
||||
// Copyright (c) 1999-2002, International Business Machines
|
||||
// Copyright (c) 1999-2004, International Business Machines
|
||||
// Corporation and others. All Rights Reserved.
|
||||
//--------------------------------------------------------------------
|
||||
// THIS IS A MACHINE-GENERATED FILE
|
||||
// Tool: dumpicurules.bat
|
||||
// Tool: dumpICUrules.bat
|
||||
// Source: ../../../impl/data/Transliterator_Gurmukhi_InterIndic.txt
|
||||
// Date: Sat Jul 27 10:31:01 2002
|
||||
// Date: Tue May 18 17:24:48 2004
|
||||
//--------------------------------------------------------------------
|
||||
|
||||
// Gurmukhi_InterIndic
|
||||
|
@ -26,7 +26,7 @@ t_Guru_InterIndic {
|
|||
//\u0A38\u0A3C>\uE036; # LETTER SHA
|
||||
//\u0A32\u0A3C>\uE033; # LETTER LLA
|
||||
//\u0A2B\u0A3C>\uE05E; # LETTER FA
|
||||
|
||||
"\u0A01>\uE001;" // SIGN CHANDRABINDU
|
||||
"\u0A02>\uE002;" // SIGN BINDI
|
||||
"\u0A05>\uE005;" // LETTER A
|
||||
"\u0A06>\uE006;" // LETTER AA
|
||||
|
@ -34,7 +34,7 @@ t_Guru_InterIndic {
|
|||
"\u0A08>\uE008;" // LETTER II
|
||||
"\u0A09>\uE009;" // LETTER U
|
||||
"\u0A0A>\uE00A;" // LETTER UU
|
||||
"\u0A0C>;" // UNMAPPED
|
||||
"\u0A0C>\uE032;" // FALLBACK : VOCALLIC LA
|
||||
"\u0A0F>\uE00F;" // LETTER EE
|
||||
"\u0A10>\uE010;" // LETTER AI
|
||||
"\u0A13>\uE013;" // LETTER OO
|
||||
|
@ -70,8 +70,7 @@ t_Guru_InterIndic {
|
|||
"\u0a33>\uE033;" // FALLBACK
|
||||
"\u0A35>\uE035;" // LETTER VA
|
||||
"\u0a36>\ue036;"
|
||||
"\u0A38\\\0a3c>\ue036;"
|
||||
"\u0A37>\uE036;"
|
||||
"\u0A38\\\0a3c>\ue036;" // FALLBACK
|
||||
"\u0A38>\uE038;" // LETTER SA
|
||||
"\u0A39>\uE039;" // LETTER HA
|
||||
"\u0A3C>\uE03C;" // SIGN NUKTA
|
||||
|
@ -98,11 +97,11 @@ t_Guru_InterIndic {
|
|||
"\u0A6D>\uE06D;" // DIGIT SEVEN
|
||||
"\u0A6E>\uE06E;" // DIGIT EIGHT
|
||||
"\u0A6F>\uE06F;" // DIGIT NINE
|
||||
"\u0A70>\uE070;" // TIPPI
|
||||
"\u0A71>\uE071;" // ADDAK
|
||||
"\u0A72>\uE072;" // IRI
|
||||
"\u0A73>\uE073;" // URA
|
||||
"\u0A74>\uE074;" // EK ONKAR
|
||||
"\u0A70>\uE07C;" // TIPPI
|
||||
"\u0A71>\uE07D;" // ADDAK
|
||||
"\u0A72>\uE07E;" // IRI
|
||||
"\u0A73>\uE07F;" // URA
|
||||
"\u0A74>\uE080;" // EK ONKAR
|
||||
"\u0964>\ue064;" // DANDA
|
||||
"\u0965>\ue065;" // DOUBLE DANDA
|
||||
// :: NFC (NFD) ;
|
||||
|
|
|
@ -1,12 +1,12 @@
|
|||
// -*- Coding: utf-8; -*-
|
||||
//--------------------------------------------------------------------
|
||||
// Copyright (c) 1999-2002, International Business Machines
|
||||
// Copyright (c) 1999-2004, International Business Machines
|
||||
// Corporation and others. All Rights Reserved.
|
||||
//--------------------------------------------------------------------
|
||||
// THIS IS A MACHINE-GENERATED FILE
|
||||
// Tool: dumpicurules.bat
|
||||
// Tool: dumpICUrules.bat
|
||||
// Source: ../../../impl/data/Transliterator_Han_Latin.txt
|
||||
// Date: Thu Dec 12 13:02:47 2002
|
||||
// Date: Tue May 18 17:24:48 2004
|
||||
//--------------------------------------------------------------------
|
||||
|
||||
// Han_Latin
|
||||
|
|
|
@ -1,12 +1,12 @@
|
|||
// -*- Coding: utf-8; -*-
|
||||
//--------------------------------------------------------------------
|
||||
// Copyright (c) 1999-2002, International Business Machines
|
||||
// Copyright (c) 1999-2004, International Business Machines
|
||||
// Corporation and others. All Rights Reserved.
|
||||
//--------------------------------------------------------------------
|
||||
// THIS IS A MACHINE-GENERATED FILE
|
||||
// Tool: dumpicurules.bat
|
||||
// Tool: dumpICUrules.bat
|
||||
// Source: ../../../impl/data/Transliterator_Hebrew_Latin.txt
|
||||
// Date: Sat Jul 27 10:31:07 2002
|
||||
// Date: Tue May 18 17:24:49 2004
|
||||
//--------------------------------------------------------------------
|
||||
|
||||
// Hebrew_Latin
|
||||
|
@ -37,7 +37,7 @@ t_Hebr_Latn {
|
|||
// For more information, see"
|
||||
// http://oss.software.ibm.com/icu/userguide/Transliteration.html
|
||||
|
||||
":: [[:Hebrew:] [\u05B0-\u05B9\u05BB-\u05BC\u05C1-\u05C2\u2135-\u2138̄\u05BF]] ;"
|
||||
":: [[:Hebrew:] [\u05B0-\u05B9\u05BB-\u05BC\u05C1-\u05C2\u2135-\u2138̄\u05BF] - [\u05BD]] ;"
|
||||
":: nfkd (nfc) ;"
|
||||
"$letterAfter = [:M:]* [:L:] ;"
|
||||
|
||||
|
|
|
@ -1,12 +1,12 @@
|
|||
// -*- Coding: utf-8; -*-
|
||||
//--------------------------------------------------------------------
|
||||
// Copyright (c) 1999-2002, International Business Machines
|
||||
// Copyright (c) 1999-2004, International Business Machines
|
||||
// Corporation and others. All Rights Reserved.
|
||||
//--------------------------------------------------------------------
|
||||
// THIS IS A MACHINE-GENERATED FILE
|
||||
// Tool: dumpicurules.bat
|
||||
// Tool: dumpICUrules.bat
|
||||
// Source: ../../../impl/data/Transliterator_Hiragana_Katakana.txt
|
||||
// Date: Sat Jul 27 10:31:07 2002
|
||||
// Date: Tue May 18 17:24:49 2004
|
||||
//--------------------------------------------------------------------
|
||||
|
||||
// Hiragana_Katakana
|
||||
|
|
|
@ -1,12 +1,12 @@
|
|||
// -*- Coding: utf-8; -*-
|
||||
//--------------------------------------------------------------------
|
||||
// Copyright (c) 1999-2002, International Business Machines
|
||||
// Copyright (c) 1999-2004, International Business Machines
|
||||
// Corporation and others. All Rights Reserved.
|
||||
//--------------------------------------------------------------------
|
||||
// THIS IS A MACHINE-GENERATED FILE
|
||||
// Tool: dumpicurules.bat
|
||||
// Tool: dumpICUrules.bat
|
||||
// Source: ../../../impl/data/Transliterator_Hiragana_Latin.txt
|
||||
// Date: Sat Jul 27 10:31:07 2002
|
||||
// Date: Tue May 18 17:24:49 2004
|
||||
//--------------------------------------------------------------------
|
||||
|
||||
// Hiragana_Latin
|
||||
|
|
|
@ -1,12 +1,12 @@
|
|||
// -*- Coding: utf-8; -*-
|
||||
//--------------------------------------------------------------------
|
||||
// Copyright (c) 1999-2002, International Business Machines
|
||||
// Copyright (c) 1999-2004, International Business Machines
|
||||
// Corporation and others. All Rights Reserved.
|
||||
//--------------------------------------------------------------------
|
||||
// THIS IS A MACHINE-GENERATED FILE
|
||||
// Tool: dumpicurules.bat
|
||||
// Tool: dumpICUrules.bat
|
||||
// Source: ../../../impl/data/Transliterator_InterIndic_Bengali.txt
|
||||
// Date: Sat Jul 27 10:31:07 2002
|
||||
// Date: Tue May 18 17:24:49 2004
|
||||
//--------------------------------------------------------------------
|
||||
|
||||
// InterIndic_Bengali
|
||||
|
@ -22,6 +22,7 @@ t_InterIndic_Beng {
|
|||
"\uE001>\u0981;" // SIGN CANDRABINDU
|
||||
"\uE002>\u0982;" // SIGN ANUSVARA
|
||||
"\uE003>\u0983;" // SIGN VISARGA
|
||||
"\uE004>\u0985;" // FALLBACK TO LETTER A
|
||||
"\uE005>\u0985;" // LETTER A
|
||||
"\uE006>\u0986;" // LETTER AA
|
||||
"\uE007>\u0987;" // LETTER I
|
||||
|
@ -76,7 +77,7 @@ t_InterIndic_Beng {
|
|||
"\uE038>\u09B8;" // LETTER SA
|
||||
"\uE039>\u09B9;" // LETTER HA
|
||||
"\uE03C>\u09BC;" // SIGN NUKTA
|
||||
"\uE03D>;" // FALLBACK BLOW AWAY AVAGRAHA
|
||||
"\uE03D>\u09bd;" // SIGN AVAGRAHA
|
||||
"\uE03E>\u09BE;" // VOWEL SIGN AA
|
||||
"\uE03F>\u09BF;" // VOWEL SIGN I
|
||||
"\uE040>\u09C0;" // VOWEL SIGN II
|
||||
|
@ -98,7 +99,7 @@ t_InterIndic_Beng {
|
|||
"\ue052>;"
|
||||
"\ue053>;"
|
||||
"\ue054>;"
|
||||
"\uE055>;" // UNMAPPED InterIndic-Bengali: LENGTH MARK
|
||||
"\uE055>;" // LENGTH MARK
|
||||
"\uE056>\u09C8;" // REMAP (indicExceptions.txt): \u09d6>\u09c8 = AI LENGTH MARK>VOWEL SIGN AI
|
||||
"\uE057>\u09D7;" // AU LENGTH MARK
|
||||
"\uE058>\u0995\u09BC;" // FALLBACK
|
||||
|
@ -125,20 +126,36 @@ t_InterIndic_Beng {
|
|||
"\uE06D>\u09ED;" // DIGIT SEVEN
|
||||
"\uE06E>\u09EE;" // DIGIT EIGHT
|
||||
"\uE06F>\u09EF;" // DIGIT NINE
|
||||
"\uE070>\u09F0;" // UNMAPPED Bengali-InterIndic: LETTER RA WITH MIDDLE DIAGONAL
|
||||
"\uE071>;"
|
||||
"\ue070>;" // ABBREVIATION SIGN
|
||||
"\ue071>\u09F0;" // LETTER RA WITH MIDDLE DIAGONAL
|
||||
"\ue072>\u09F1;" // LETTER RA WITH LOWER DIAGONAL
|
||||
"\ue073>\u09F2;" // RUPEE MARK
|
||||
"\ue074>\u09F3;" // RUPEE SIGN
|
||||
"\ue075>\u09F4;" // CURRENCY NUMERATOR ONE
|
||||
"\ue076>\u09F5;" // CURRENCY NUMERATOR TWO
|
||||
"\ue077>\u09F6;" // CURRENCY NUMERATOR THREE
|
||||
"\ue078>\u09F7;" // CURRENCY NUMERATOR FOUR
|
||||
"\ue079>\u09F8;" // CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR
|
||||
"\ue07A>\u09F9;" // CURRENCY DENOMINATOR SIXTEEN
|
||||
"\ue07B>\u09FA;" // ISSHAR
|
||||
"\uE07C>;" // TIPPI
|
||||
"\uE07D>;" // ADDAK
|
||||
"\uE07E>;" // IRI
|
||||
"\uE07F>;" // URA
|
||||
"\uE080>;" // EK ONKAR
|
||||
"\uE081>\u09AC;" // FALLBACK FOR ORIYA LETTER WA
|
||||
"0 > \u09E6;" // FALLBACK FOR TAMIL
|
||||
"1 > \u09E7;"
|
||||
"\ue072>;"
|
||||
"\ue073>;"
|
||||
"\ue074>;"
|
||||
|
||||
"\ue075>\u09F5;"
|
||||
"\ue076>\u09F6;"
|
||||
"\ue077>\u09F7;"
|
||||
"\ue078>\u09F8;"
|
||||
"\ue079>\u09F9;"
|
||||
"\ue07A>\u09FA;" // ISSHAR
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
// :: NFC (NFD) ;
|
||||
// eof
|
||||
|
|
|
@ -1,12 +1,12 @@
|
|||
// -*- Coding: utf-8; -*-
|
||||
//--------------------------------------------------------------------
|
||||
// Copyright (c) 1999-2002, International Business Machines
|
||||
// Copyright (c) 1999-2004, International Business Machines
|
||||
// Corporation and others. All Rights Reserved.
|
||||
//--------------------------------------------------------------------
|
||||
// THIS IS A MACHINE-GENERATED FILE
|
||||
// Tool: dumpicurules.bat
|
||||
// Tool: dumpICUrules.bat
|
||||
// Source: ../../../impl/data/Transliterator_InterIndic_Devanagari.txt
|
||||
// Date: Sat Jul 27 10:31:07 2002
|
||||
// Date: Tue May 18 17:24:49 2004
|
||||
//--------------------------------------------------------------------
|
||||
|
||||
// InterIndic_Devanagari
|
||||
|
@ -40,16 +40,11 @@ t_InterIndic_Deva {
|
|||
"\ue055>;" // FALLBACK BLOW AWAY KANNADA AND TELUGU LENGTH MARK
|
||||
"\ue056>;" // FALLBACK BLOW AWAY KANNADA AND TELUGU AI LENGTH MARK
|
||||
"\ue057>;" // FALLBACK BLOW AWAY TAMIL AU LENGTH MARK
|
||||
"\ue070>;" // FALLBACK BLOW AWAY GURMUKHI
|
||||
"\ue071>;" // FALLBACK BLOW AWAY GURMUKHI
|
||||
"\ue072>;" // FALLBACK BLOW AWAY GURMUKHI
|
||||
"\ue073>;" // FALLBACK BLOW AWAY GURMUKHI
|
||||
"\ue074>;" // FALLBACK BLOW AWAY GURMUKHI
|
||||
|
||||
|
||||
"\ue001 > \u0901;" // SIGN CANDRABINDU
|
||||
"\ue002 > \u0902;" // SIGN ANUSVARA
|
||||
"\ue003 > \u0903;" // SIGN VISARGA
|
||||
"\ue004 > \u0904;" // SIGN SHORT A
|
||||
"\ue005 > \u0905;" // LETTER A
|
||||
"\ue006 > \u0906;" // LETTER AA
|
||||
"\ue007 > \u0907;" // LETTER I
|
||||
|
@ -59,13 +54,11 @@ t_InterIndic_Deva {
|
|||
"\ue00b > \u090b;" // LETTER VOCALIC R
|
||||
"\ue00c > \u090c;" // LETTER VOCALIC L
|
||||
"\ue00d > \u090d;" // LETTER CANDRA E (For representing English sounds)
|
||||
"\ue00e > \u090e;" // UNMAPPED LETTER SHORT E(For Southern Scripts)
|
||||
//\ue00e > \u090f;
|
||||
"\ue00e > \u090e;" // LETTER SHORT E(For Southern Scripts)
|
||||
"\ue00f > \u090f;" // LETTER E
|
||||
"\ue010 > \u0910;" // LETTER AI
|
||||
"\ue011 > \u0911;" // LETTER CANDRA O (For representing English sounds)
|
||||
"\ue012 > \u0912;" // UNMAPPED LETTER SHORT O (For Southern Scripts)
|
||||
//\ue012 > \u0913;
|
||||
"\ue012 > \u0912;" // LETTER SHORT O (For Southern Scripts)
|
||||
"\ue013 > \u0913;" // LETTER O
|
||||
"\ue014 > \u0914;" // LETTER AU
|
||||
"\ue015 > \u0915;" // LETTER KA
|
||||
|
@ -117,21 +110,19 @@ t_InterIndic_Deva {
|
|||
"\ue043 > \u0943;" // VOWEL SIGN VOCALIC R
|
||||
"\ue044 > \u0944;" // VOWEL SIGN VOCALIC RR
|
||||
"\ue045 > \u0945;" // VOWEL SIGN CANDRA E
|
||||
"\ue046 > \u0946;" // UNMAPPED VOWEL SIGN SHORT E
|
||||
//\ue046 > \u0947;
|
||||
"\ue046 > \u0946;" // VOWEL SIGN SHORT E
|
||||
"\ue047 > \u0947;" // VOWEL SIGN E
|
||||
"\ue048 > \u0948;" // VOWEL SIGN AI
|
||||
"\ue049 > \u0949;" // VOWEL SIGN CANDRA O
|
||||
"\ue04a > \u094a;" // UNMAPPED VOWEL SIGN SHORT O
|
||||
//\ue04a > \u094b;
|
||||
"\ue04a > \u094a;" // VOWEL SIGN SHORT O
|
||||
"\ue04b > \u094b;" // VOWEL SIGN O
|
||||
"\ue04c > \u094c;" // VOWEL SIGN AU
|
||||
"\ue04d > \u094d;" // SIGN VIRAMA
|
||||
"\ue050 > \u0950;" // OM
|
||||
"\ue051 > \u0951;" // UNMAPPED STRESS SIGN UDATTA
|
||||
"\ue052 > \u0952;" // UNMAPPED STRESS SIGN ANUDATTA
|
||||
"\ue053 > \u0953;" // UNMAPPED GRAVE ACCENT
|
||||
"\ue054 > \u0954;" // UNMAPPED ACUTE ACCENT
|
||||
"\ue051 > \u0951;" // STRESS SIGN UDATTA
|
||||
"\ue052 > \u0952;" // STRESS SIGN ANUDATTA
|
||||
"\ue053 > \u0953;" // GRAVE ACCENT
|
||||
"\ue054 > \u0954;" // ACUTE ACCENT
|
||||
"\ue058 > \u0958;" // LETTER QA (For Urdu)
|
||||
"\ue059 > \u0959;" // LETTER KHHA (For Urdu)
|
||||
"\ue05a > \u095a;" // LETTER GHHA (For Urdu)
|
||||
|
@ -144,8 +135,8 @@ t_InterIndic_Deva {
|
|||
"\ue061 > \u0961;" // LETTER VOCALIC LL
|
||||
"\ue062 > \u0962;" // VOWEL SIGN VOCALIC L
|
||||
"\ue063 > \u0963;" // VOWEL SIGN VOCALIC LL
|
||||
"\ue064 > \u0964;" // UNMAPPED Devanagari-InterIndic: DANDA
|
||||
"\ue065 > \u0965;" // UNMAPPED Devanagari-InterIndic: DOUBLE DANDA
|
||||
"\ue064 > \u0964;" // DANDA
|
||||
"\ue065 > \u0965;" // DOUBLE DANDA
|
||||
"\ue066 > \u0966;" // DIGIT ZERO
|
||||
"\ue067 > \u0967;" // DIGIT ONE
|
||||
"\ue068 > \u0968;" // DIGIT TWO
|
||||
|
@ -156,15 +147,25 @@ t_InterIndic_Deva {
|
|||
"\ue06d > \u096d;" // DIGIT SEVEN
|
||||
"\ue06e > \u096e;" // DIGIT EIGHT
|
||||
"\ue06f > \u096f;" // DIGIT NINE
|
||||
"\ue0f0 > \u0930;" // FALLBACK RA
|
||||
"\ue0f1 > \u0930;" // FALLBACK RA
|
||||
|
||||
"\ue075>;"
|
||||
"\ue076>;"
|
||||
"\ue077>;"
|
||||
"\ue078>;"
|
||||
"\ue079>;"
|
||||
"\ue07A>;"
|
||||
"\ue070>\u0970;" // ABBREVIATION SIGN
|
||||
"\ue071>\u0930;" // LETTER RA WITH MIDDLE DIAGONAL
|
||||
"\ue072>\u0930;" // LETTER RA WITH LOWER DIAGONAL
|
||||
"\ue073>;" // RUPEE MARK
|
||||
"\ue074>\u0930\u0942;" // RUPEE SIGN
|
||||
"\ue075>;" // CURRENCY NUMERATOR ONE
|
||||
"\ue076>;" // CURRENCY NUMERATOR TWO
|
||||
"\ue077>;" // CURRENCY NUMERATOR THREE
|
||||
"\ue078>;" // CURRENCY NUMERATOR FOUR
|
||||
"\ue079>;" // CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR
|
||||
"\ue07A>;" // CURRENCY DENOMINATOR SIXTEEN
|
||||
"\ue07B>;" // ISSHAR
|
||||
"\uE07C>;" // TIPPI
|
||||
"\uE07D>;" // ADDAK
|
||||
"\uE07E>;" // IRI
|
||||
"\uE07F>;" // URA
|
||||
"\uE080>;" // EK ONKAR
|
||||
"\uE081>\u0935;" // FALLBACK FOR ORIYA LETTER WA
|
||||
|
||||
// \u0970 # UNMAPPED Devanagari-InterIndic: ABBREVIATION SIGN
|
||||
// :: NFC;
|
||||
|
|
|
@ -1,12 +1,12 @@
|
|||
// -*- Coding: utf-8; -*-
|
||||
//--------------------------------------------------------------------
|
||||
// Copyright (c) 1999-2002, International Business Machines
|
||||
// Copyright (c) 1999-2004, International Business Machines
|
||||
// Corporation and others. All Rights Reserved.
|
||||
//--------------------------------------------------------------------
|
||||
// THIS IS A MACHINE-GENERATED FILE
|
||||
// Tool: dumpicurules.bat
|
||||
// Tool: dumpICUrules.bat
|
||||
// Source: ../../../impl/data/Transliterator_InterIndic_Gujarati.txt
|
||||
// Date: Sat Jul 27 10:31:07 2002
|
||||
// Date: Tue May 18 17:24:49 2004
|
||||
//--------------------------------------------------------------------
|
||||
|
||||
// InterIndic_Gujarati
|
||||
|
@ -22,6 +22,7 @@ t_InterIndic_Gujr {
|
|||
"\ue001>\u0a81;" // SIGN CANDRABINDU
|
||||
"\ue002>\u0a82;" // SIGN ANUSVARA
|
||||
"\ue003>\u0a83;" // SIGN VISARGA
|
||||
"\uE004>\u0a85;" // FALLBACK TO LETTER A
|
||||
"\ue005>\u0a85;" // LETTER A
|
||||
"\ue006>\u0a86;" // LETTER AA
|
||||
"\ue007>\u0a87;" // LETTER I
|
||||
|
@ -29,7 +30,7 @@ t_InterIndic_Gujr {
|
|||
"\ue009>\u0a89;" // LETTER U
|
||||
"\ue00a>\u0a8a;" // LETTER UU
|
||||
"\ue00b>\u0a8b;" // LETTER VOCALIC R
|
||||
"\ue00c>\u0ab2\u0ac3;" // REMAP (indicExceptions.txt): \u0a8c>\u0ab2\u0ac3 = LETTER VOCALIC L>LETTER LA.VOWEL SIGN VOCALIC R
|
||||
"\ue00c>\u0a8c;" // LETTER VOCALIC L
|
||||
"\ue00d>\u0a8d;" // GUJARATI VOWEL CANDRA E
|
||||
"\ue00e>\u0a8f;" // FALLBACK
|
||||
"\ue00f>\u0a8f;" // InterIndic-Gujarati: LETTER EE (\u0a8f = LETTER E)
|
||||
|
@ -110,7 +111,7 @@ t_InterIndic_Gujr {
|
|||
"\ue05e>\u0aab\u0abc;" // REMAP (indicExceptions.txt): \u0ade>\u0aab\u0abc = LETTER FA>LETTER PHA.SIGN NUKTA
|
||||
"\ue05f>\u0aaf\u0abc;" // REMAP (indicExceptions.txt): \u0adf>\u0aaf\u0abc = LETTER YYA>LETTER YA.SIGN NUKTA
|
||||
"\ue060>\u0ae0;" // LETTER VOCALIC RR
|
||||
"\ue061>\u0ab2\u0ac3;" // REMAP (indicExceptions.txt): \u0ae1>\u0ab2\u0ac3 = LETTER VOCALIC LL>LETTER LA.VOWEL SIGN VOCALIC R
|
||||
"\ue061>\u0ae1;" // LETTER VOCALIC LL
|
||||
"\ue062>\u0abf\u0abc;" // REMAP (indicExceptions.txt): \u0ae2>\u0abf\u0abc = VOWEL SIGN VOCALIC L>VOWEL SIGN I.SIGN NUKTA
|
||||
"\ue063>\u0ac0\u0abc;" // REMAP (indicExceptions.txt): \u0ae3>\u0ac0\u0abc = VOWEL SIGN VOCALIC LL>VOWEL SIGN II.SIGN NUKTA
|
||||
"\uE064>\u0964;" // DANDA
|
||||
|
@ -125,21 +126,27 @@ t_InterIndic_Gujr {
|
|||
"\ue06d>\u0aed;" // DIGIT SEVEN
|
||||
"\ue06e>\u0aee;" // DIGIT EIGHT
|
||||
"\ue06f>\u0aef;" // DIGIT NINE
|
||||
"\ue070>;"
|
||||
"\ue071>;"
|
||||
"\ue072>;"
|
||||
"\ue073>;"
|
||||
"\ue074>;"
|
||||
"\ue075>;"
|
||||
"\ue076>;"
|
||||
"\ue077>;"
|
||||
"\ue078>;"
|
||||
"\ue079>;"
|
||||
"\ue07A>;"
|
||||
"\ue070>;" // ABBREVIATION SIGN
|
||||
"\ue071>\u0ab0;" // LETTER RA WITH MIDDLE DIAGONAL
|
||||
"\ue072>\u0ab0;" // LETTER RA WITH LOWER DIAGONAL
|
||||
"\ue073>;" // RUPEE MARK
|
||||
"\ue074>;" // RUPEE SIGN
|
||||
"\ue075>;" // CURRENCY NUMERATOR ONE
|
||||
"\ue076>;" // CURRENCY NUMERATOR TWO
|
||||
"\ue077>;" // CURRENCY NUMERATOR THREE
|
||||
"\ue078>;" // CURRENCY NUMERATOR FOUR
|
||||
"\ue079>;" // CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR
|
||||
"\ue07A>;" // CURRENCY DENOMINATOR SIXTEEN
|
||||
"\ue07B>;" // ISSHAR
|
||||
"\uE07C>;" // TIPPI
|
||||
"\uE07D>;" // ADDAK
|
||||
"\uE07E>;" // IRI
|
||||
"\uE07F>;" // URA
|
||||
"\uE080>;" // EK ONKAR
|
||||
"\uE081>\u0ab5;" // FALLBACK FOR ORIYA LETTER WA
|
||||
"0 > \u0ae6;" // FALLBACK FOR TAMIL
|
||||
"1 > \u0ae7;"
|
||||
"\ue0f0 > \u0ab0;" // FALLBACK RA
|
||||
"\ue0f1 > \u0ab0;" // FALLBACK RA
|
||||
|
||||
//\ue080>; # UNMAPPED InterIndic-Gujarati: ISSHAR
|
||||
// :: NFC (NFD) ;
|
||||
// eof
|
||||
|
|
|
@ -1,12 +1,12 @@
|
|||
// -*- Coding: utf-8; -*-
|
||||
//--------------------------------------------------------------------
|
||||
// Copyright (c) 1999-2002, International Business Machines
|
||||
// Copyright (c) 1999-2004, International Business Machines
|
||||
// Corporation and others. All Rights Reserved.
|
||||
//--------------------------------------------------------------------
|
||||
// THIS IS A MACHINE-GENERATED FILE
|
||||
// Tool: dumpicurules.bat
|
||||
// Tool: dumpICUrules.bat
|
||||
// Source: ../../../impl/data/Transliterator_InterIndic_Gurmukhi.txt
|
||||
// Date: Sat Jul 27 10:31:07 2002
|
||||
// Date: Tue May 18 17:24:49 2004
|
||||
//--------------------------------------------------------------------
|
||||
|
||||
// InterIndic_Gurmukhi
|
||||
|
@ -22,7 +22,7 @@ t_InterIndic_Guru {
|
|||
"$vowel = [\u0A05-\u0A14 \u0A3e-\u0A4D];"
|
||||
"$consonant = [\u0A15-\u0A39];"
|
||||
|
||||
"\ue001>;" // FALLBACK BLOW AWAY SIGN CHANDRABINDU
|
||||
"\ue001>\u0A01;" // SIGN CHANDRABINDU
|
||||
//rules for BINDI
|
||||
|
||||
// Anusvara is equivalent to BINDI when preceeded by a vowel
|
||||
|
@ -31,7 +31,8 @@ t_InterIndic_Guru {
|
|||
"$consonant{\ue002>\u0a70;" // SIGN TIPPI
|
||||
"\ue002>\u0a02;"
|
||||
|
||||
"\ue003>;" // FALLBACK BLOW AWAY SIGN VISARGA
|
||||
"\ue003>;" // FALLBACK BLOW AWAY SIGN VISARGA
|
||||
"\uE004>\u0a05;" // FALLBACK TO LETTER A
|
||||
"\ue005>\u0a05;" // LETTER A
|
||||
"\ue006>\u0a06;" // LETTER AA
|
||||
"\ue007>\u0a07;" // LETTER I
|
||||
|
@ -120,7 +121,7 @@ t_InterIndic_Guru {
|
|||
"\ue05e>\u0a5e;" // LETTER FA
|
||||
"\ue05f>\u0a2f\u0a3c;" // REMAP (indicExceptions.txt): \u0a5f>\u0a2f = LETTER YYA>LETTER YA
|
||||
"\ue060>\u0a30\u0a3f;" // REMAP (indicExceptions.txt): \u0a60>\u0a30\u0a3f = LETTER VOCALIC RR>LETTER RA.VOWEL SIGN I
|
||||
"\ue061>\u0a33\u0a3c;" //
|
||||
"\ue061>\u0a32\u0a3c;" //
|
||||
"\ue062>\u0a3f\u0a3c;" // REMAP (indicExceptions.txt): \u0a62>\u0a3f\u0a3c = VOWEL SIGN VOCALIC L>VOWEL SIGN I.SIGN NUKTA
|
||||
"\ue063>\u0a40\u0a3c;" // REMAP (indicExceptions.txt): \u0a63>\u0a40\u0a3c = VOWEL SIGN VOCALIC LL>VOWEL SIGN II.SIGN NUKTA
|
||||
"\uE064>\u0964;" // DANDA
|
||||
|
@ -135,27 +136,27 @@ t_InterIndic_Guru {
|
|||
"\ue06d>\u0a6d;" // DIGIT SEVEN
|
||||
"\ue06e>\u0a6e;" // DIGIT EIGHT
|
||||
"\ue06f>\u0a6f;" // DIGIT NINE
|
||||
"\ue070>;" // TIPPI
|
||||
"\ue071>;" // ADDAK
|
||||
"\ue072>;" // IRI
|
||||
"\ue073>;" // URA
|
||||
"\ue074>;" // EK ONKAR
|
||||
"\ue075>;"
|
||||
"\ue076>;"
|
||||
"\ue077>;"
|
||||
"\ue078>;"
|
||||
"\ue079>;"
|
||||
"\ue07A>;"
|
||||
"\ue080>;" // FALLBACK BLOW AWAY ISSHAR
|
||||
"\ue081>;" // FALLBACK BLOW AWAY LETTER E
|
||||
"\ue082>;" // FALLBACK BLOW AWAY LETTER O (\u0a02 = SIGN BINDI)
|
||||
"\ue084>;" // FALLBACK BLOW AWAY VOWEL SIGN E
|
||||
"\ue085>;" // FALLBACK BLOW AWAY VOWEL SIGN O (\u0a05 = LETTER A)
|
||||
"\ue070>;" // ABBREVIATION SIGN
|
||||
"\ue071>\u0a30;" // LETTER RA WITH MIDDLE DIAGONAL
|
||||
"\ue072>\u0a30;" // LETTER RA WITH LOWER DIAGONAL
|
||||
"\ue073>;" // RUPEE MARK
|
||||
"\ue074>;" // RUPEE SIGN
|
||||
"\ue075>;" // CURRENCY NUMERATOR ONE
|
||||
"\ue076>;" // CURRENCY NUMERATOR TWO
|
||||
"\ue077>;" // CURRENCY NUMERATOR THREE
|
||||
"\ue078>;" // CURRENCY NUMERATOR FOUR
|
||||
"\ue079>;" // CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR
|
||||
"\ue07A>;" // CURRENCY DENOMINATOR SIXTEEN
|
||||
"\ue07B>;" // ISSHAR
|
||||
"\uE07C>\u0a70;" // TIPPI
|
||||
"\uE07D>\u0a71;" // ADDAK
|
||||
"\uE07E>\u0a72;" // IRI
|
||||
"\uE07F>\u0a73;" // URA
|
||||
"\uE080>\u0a74;" // EK ONKAR
|
||||
"\uE081>\u0a35;" // FALLBACK FOR ORIYA LETTER WA
|
||||
|
||||
"0 > \u0a66;" // FALLBACK FOR TAMIL
|
||||
"1 > \u0a67;"
|
||||
"\ue0f0 > \u0a30;" // FALLBACK RA
|
||||
"\ue0f1 > \u0a30;" // FALLBACK RA
|
||||
// :: NFC (NFD) ;
|
||||
// eof
|
||||
}
|
||||
|
|
|
@ -1,12 +1,12 @@
|
|||
// -*- Coding: utf-8; -*-
|
||||
//--------------------------------------------------------------------
|
||||
// Copyright (c) 1999-2002, International Business Machines
|
||||
// Copyright (c) 1999-2004, International Business Machines
|
||||
// Corporation and others. All Rights Reserved.
|
||||
//--------------------------------------------------------------------
|
||||
// THIS IS A MACHINE-GENERATED FILE
|
||||
// Tool: dumpicurules.bat
|
||||
// Tool: dumpICUrules.bat
|
||||
// Source: ../../../impl/data/Transliterator_InterIndic_Kannada.txt
|
||||
// Date: Sat Jul 27 10:31:07 2002
|
||||
// Date: Tue May 18 17:24:49 2004
|
||||
//--------------------------------------------------------------------
|
||||
|
||||
// InterIndic_Kannada
|
||||
|
@ -19,10 +19,11 @@ t_InterIndic_Knda {
|
|||
|
||||
// InterIndic-Kannada
|
||||
//:: NFD (NFC) ;
|
||||
"\ue02b\ue03c>\u0cde;" // LETTER FA
|
||||
"\ue033\ue03c>\u0cde;" // LETTER FA
|
||||
"\ue001>\u0c82;" // REMAP (indicExceptions.txt): \u0c81>\u0c82 = SIGN CANDRABINDU>SIGN ANUSVARA
|
||||
"\ue002>\u0c82;" // SIGN ANUSVARA
|
||||
"\ue003>\u0c83;" // SIGN VISARGA
|
||||
"\uE004>\u0c85;" // FALLBACK TO LETTER A
|
||||
"\ue005>\u0c85;" // LETTER A
|
||||
"\ue006>\u0c86;" // LETTER AA
|
||||
"\ue007>\u0c87;" // LETTER I
|
||||
|
@ -71,15 +72,15 @@ t_InterIndic_Knda {
|
|||
"\ue031>\u0cb1;" // LETTER RRA
|
||||
"\ue032>\u0cb2;" // LETTER LA
|
||||
"\ue033>\u0cb3;" // LETTER LLA
|
||||
"\ue034>\u0cb3;" // REMAP (indicExceptions.txt): \u0cb4>\u0cb3 = LETTER LLLA>LETTER LLA
|
||||
"\ue034>\u0cde;" // REMAP (indicExceptions.txt): \u0cb4>\u0cb3 = LETTER LLLA>LETTER LLA
|
||||
"\ue035>\u0cb5;" // LETTER VA
|
||||
"\ue036>\u0cb6;" // LETTER SHA
|
||||
"\ue037>\u0cb7;" // LETTER SSA
|
||||
"\ue038>\u0cb8;" // LETTER SA
|
||||
"\ue039>\u0cb9;" // LETTER HA
|
||||
|
||||
"\ue03c>;" // FALLBACK BLOW AWAY NUKTA
|
||||
"\ue03d>;" // FALLBACK BLOW AWAY AVAGRAHA
|
||||
"\ue03c>\u0cbc;" // NUKTA
|
||||
"\ue03d>\u0cbd;" // AVAGRAHA
|
||||
|
||||
"\ue03e>\u0cbe;" // VOWEL SIGN AA
|
||||
"\ue03f>\u0cbf;" // VOWEL SIGN I
|
||||
|
@ -118,7 +119,7 @@ t_InterIndic_Knda {
|
|||
"\ue062>\u0cbf;" // REMAP (indicExceptions.txt): \u0ce2>\u0cbf = VOWEL SIGN VOCALIC L>VOWEL SIGN I
|
||||
"\ue063>\u0cc0;" // REMAP (indicExceptions.txt): \u0ce3>\u0cc0 = VOWEL SIGN VOCALIC LL>VOWEL SIGN II
|
||||
"\ue064>'.' ;" // FALLBACK FOR DANDA
|
||||
"\ue065>'.' ;" // FALLBACK FOR DOUBLE DANDA
|
||||
"\ue065>'.' ;" // FALLBACK FOR DOUBLE DANDA
|
||||
"\ue066>\u0ce6;" // DIGIT ZERO
|
||||
"\ue067>\u0ce7;" // DIGIT ONE
|
||||
"\ue068>\u0ce8;" // DIGIT TWO
|
||||
|
@ -129,22 +130,27 @@ t_InterIndic_Knda {
|
|||
"\ue06d>\u0ced;" // DIGIT SEVEN
|
||||
"\ue06e>\u0cee;" // DIGIT EIGHT
|
||||
"\ue06f>\u0cef;" // DIGIT NINE
|
||||
"\ue080>;" // UNMAPPED InterIndic-Kannada: ISSHAR
|
||||
"\ue070>;"
|
||||
"\ue071>;"
|
||||
"\ue072>;"
|
||||
"\ue073>;"
|
||||
"\ue074>;"
|
||||
"\ue075>;"
|
||||
"\ue076>;"
|
||||
"\ue077>;"
|
||||
"\ue078>;"
|
||||
"\ue079>;"
|
||||
"\ue07A>;"
|
||||
"\ue070>;" // ABBREVIATION SIGN
|
||||
"\ue071>\u0cb0;" // LETTER RA WITH MIDDLE DIAGONAL
|
||||
"\ue072>\u0cb0;" // LETTER RA WITH LOWER DIAGONAL
|
||||
"\ue073>;" // RUPEE MARK
|
||||
"\ue074>;" // RUPEE SIGN
|
||||
"\ue075>;" // CURRENCY NUMERATOR ONE
|
||||
"\ue076>;" // CURRENCY NUMERATOR TWO
|
||||
"\ue077>;" // CURRENCY NUMERATOR THREE
|
||||
"\ue078>;" // CURRENCY NUMERATOR FOUR
|
||||
"\ue079>;" // CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR
|
||||
"\ue07A>;" // CURRENCY DENOMINATOR SIXTEEN
|
||||
"\ue07B>;" // ISSHAR
|
||||
"\uE07C>;" // TIPPI
|
||||
"\uE07D>;" // ADDAK
|
||||
"\uE07E>;" // IRI
|
||||
"\uE07F>;" // URA
|
||||
"\uE080>;" // EK ONKAR
|
||||
"\uE081>\u0cb5;" // FALLBACK FOR ORIYA LETTER WA
|
||||
"0 > \u0ce6;" // FALLBACK FOR TAMIL
|
||||
"1 > \u0ce7;"
|
||||
"\ue0f0 > \u0cb0;" // FALLBACK RA
|
||||
"\ue0f1 > \u0cb0;" // FALLBACK RA
|
||||
|
||||
// :: NFC (NFD) ;
|
||||
// eof
|
||||
}
|
||||
|
|
|
@ -1,12 +1,12 @@
|
|||
// -*- Coding: utf-8; -*-
|
||||
//--------------------------------------------------------------------
|
||||
// Copyright (c) 1999-2002, International Business Machines
|
||||
// Copyright (c) 1999-2004, International Business Machines
|
||||
// Corporation and others. All Rights Reserved.
|
||||
//--------------------------------------------------------------------
|
||||
// THIS IS A MACHINE-GENERATED FILE
|
||||
// Tool: dumpicurules.bat
|
||||
// Tool: dumpICUrules.bat
|
||||
// Source: ../../../impl/data/Transliterator_InterIndic_Latin.txt
|
||||
// Date: Sat Jul 27 10:31:07 2002
|
||||
// Date: Tue May 18 17:24:49 2004
|
||||
//--------------------------------------------------------------------
|
||||
|
||||
// InterIndic_Latin
|
||||
|
@ -69,6 +69,7 @@ t_InterIndic_Latn {
|
|||
"$ma=\ue02e;"
|
||||
"$ya=\ue02f;"
|
||||
"$ra=\ue030;"
|
||||
"$vva=\ue081;"
|
||||
"$rra=\ue031;"
|
||||
"$la=\ue032;"
|
||||
"$lla=\ue033;"
|
||||
|
@ -134,23 +135,7 @@ t_InterIndic_Latn {
|
|||
"$seven=\ue06d;" // DIGIT SEVEN
|
||||
"$eight=\ue06e;" // DIGIT EIGHT
|
||||
"$nine=\ue06f;" // DIGIT NINE
|
||||
// For all other scripts
|
||||
"$ecp0=\ue070;"
|
||||
"$ecp1=\ue071;"
|
||||
"$ecp2=\ue072;"
|
||||
"$ecp3=\ue073;"
|
||||
"$ecp4=\ue074;"
|
||||
"$ecp5=\ue075;"
|
||||
"$ecp6=\ue076;"
|
||||
"$ecp7=\ue077;"
|
||||
"$ecp8=\ue078;"
|
||||
"$ecp9=\ue079;"
|
||||
"$ecpA=\ue07a;"
|
||||
"$ecpB=\ue07b;"
|
||||
"$ecpC=\ue07c;"
|
||||
"$ecpD=\ue07d;"
|
||||
"$ecpE=\ue07e;"
|
||||
"$ecpF=\ue07f;"
|
||||
|
||||
// \u0970>; # UNMAPPED ABBREVIATION SIGN
|
||||
"$depVowelAbove=[\ue03e-\ue040\ue045-\ue04c];"
|
||||
"$depVowelBelow=[\ue041-\ue044];"
|
||||
|
@ -360,6 +345,10 @@ t_InterIndic_Latn {
|
|||
"$ra}$x>r;"
|
||||
"$ra$virama>r;"
|
||||
"$ra>ra;"
|
||||
"$vva$virama}$ha>w\u0307'';"
|
||||
"$vva}$x>w\u0307;"
|
||||
"$vva$virama>w\u0307;"
|
||||
"$vva>w\u0307a;"
|
||||
"$rra$virama}$ha>r\u0331'';"
|
||||
"$rra}$x>r\u0331;"
|
||||
"$rra$virama>r\u0331;"
|
||||
|
@ -522,23 +511,35 @@ t_InterIndic_Latn {
|
|||
"$lm >;"
|
||||
"$ailm >;"
|
||||
"$aulm >;"
|
||||
"$ecp0 >;"
|
||||
"$ecp1 >;"
|
||||
"$ecp2 >;"
|
||||
"$ecp3 >;"
|
||||
"$ecp4 >;"
|
||||
"$ecp5 >;"
|
||||
"$ecp6 >;"
|
||||
"$ecp7 >;"
|
||||
"$ecp8 >;"
|
||||
"$ecp9 >;"
|
||||
"$ecpA >;"
|
||||
"$ecpB >;"
|
||||
"$ecpC >;"
|
||||
"$ecpD >;"
|
||||
"$ecpE >;"
|
||||
"$ecpF >;"
|
||||
|
||||
"$danda>'.';"
|
||||
"$doubleDanda>'.';"
|
||||
|
||||
"\ue070>;" // ABBREVIATION SIGN
|
||||
// LETTER RA WITH MIDDLE DIAGONAL
|
||||
"\ue071}$x>ra;"
|
||||
"\ue071$virama>r;"
|
||||
"\ue071>ra;"
|
||||
// LETTER RA WITH LOWER DIAGONAL
|
||||
"\ue072}$x>ra;"
|
||||
"\ue072$virama>r;"
|
||||
"\ue072>ra;"
|
||||
|
||||
"\ue073>;" // RUPEE MARK
|
||||
"\ue074>;" // RUPEE SIGN
|
||||
"\ue075>;" // CURRENCY NUMERATOR ONE
|
||||
"\ue076>;" // CURRENCY NUMERATOR TWO
|
||||
"\ue077>;" // CURRENCY NUMERATOR THREE
|
||||
"\ue078>;" // CURRENCY NUMERATOR FOUR
|
||||
"\ue079>;" // CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR
|
||||
"\ue07A>;" // CURRENCY DENOMINATOR SIXTEEN
|
||||
"\ue07B>;" // ISSHAR
|
||||
"\uE07C>;" // TIPPI
|
||||
"\uE07D>;" // ADDAK
|
||||
"\uE07E>;" // IRI
|
||||
"\uE07F>;" // URA
|
||||
"\uE080>;" // EK ONKAR
|
||||
"\uE004>;" // DEVANAGARI VOWEL SIGN SHORT A
|
||||
|
||||
}
|
||||
}
|
||||
|
|
|
@ -1,12 +1,12 @@
|
|||
// -*- Coding: utf-8; -*-
|
||||
//--------------------------------------------------------------------
|
||||
// Copyright (c) 1999-2002, International Business Machines
|
||||
// Copyright (c) 1999-2004, International Business Machines
|
||||
// Corporation and others. All Rights Reserved.
|
||||
//--------------------------------------------------------------------
|
||||
// THIS IS A MACHINE-GENERATED FILE
|
||||
// Tool: dumpicurules.bat
|
||||
// Tool: dumpICUrules.bat
|
||||
// Source: ../../../impl/data/Transliterator_InterIndic_Malayalam.txt
|
||||
// Date: Sat Jul 27 10:31:07 2002
|
||||
// Date: Tue May 18 17:24:49 2004
|
||||
//--------------------------------------------------------------------
|
||||
|
||||
// InterIndic_Malayalam
|
||||
|
@ -22,6 +22,7 @@ t_InterIndic_Mlym {
|
|||
"\ue001>\u0d02;" // REMAP (indicExceptions.txt): \u0d01>\u0d02 = SIGN CANDRABINDU>SIGN ANUSVARA
|
||||
"\ue002>\u0d02;" // SIGN ANUSVARA
|
||||
"\ue003>\u0d03;" // SIGN VISARGA
|
||||
"\uE004>\u0d05;" // FALLBACK TO LETTER A
|
||||
"\ue005>\u0d05;" // LETTER A
|
||||
"\ue006>\u0d06;" // LETTER AA
|
||||
"\ue007>\u0d07;" // LETTER I
|
||||
|
@ -118,7 +119,7 @@ t_InterIndic_Mlym {
|
|||
"\ue062>;" // FALLBACK BLOW AWAY VOWEL SIGN VOCALIC L
|
||||
"\ue063>;" // FALLBACK BLOW AWAY VOWEL SIGN VOCALIC LL
|
||||
"\ue064>'.' ;" // FALLBACK FOR DANDA
|
||||
"\ue065>'.' ;" // FALLBACK FOR DOUBLE DANDA
|
||||
"\ue065>'.' ;" // FALLBACK FOR DOUBLE DANDA
|
||||
"\ue066>\u0d66;" // DIGIT ZERO
|
||||
"\ue067>\u0d67;" // DIGIT ONE
|
||||
"\ue068>\u0d68;" // DIGIT TWO
|
||||
|
@ -129,23 +130,26 @@ t_InterIndic_Mlym {
|
|||
"\ue06d>\u0d6d;" // DIGIT SEVEN
|
||||
"\ue06e>\u0d6e;" // DIGIT EIGHT
|
||||
"\ue06f>\u0d6f;" // DIGIT NINE
|
||||
"\ue080>;" // UNMAPPED InterIndic-Malayalam: ISSHAR
|
||||
"\ue070>;"
|
||||
"\ue071>;"
|
||||
"\ue072>;"
|
||||
"\ue073>;"
|
||||
"\ue074>;"
|
||||
"\ue075>;"
|
||||
"\ue076>;"
|
||||
"\ue077>;"
|
||||
"\ue078>;"
|
||||
"\ue079>;"
|
||||
"\ue07A>;"
|
||||
"\ue070>;" // ABBREVIATION SIGN
|
||||
"\ue071>\u0d30;" // LETTER RA WITH MIDDLE DIAGONAL
|
||||
"\ue072>\u0d30;" // LETTER RA WITH LOWER DIAGONAL
|
||||
"\ue073>;" // RUPEE MARK
|
||||
"\ue074>;" // RUPEE SIGN
|
||||
"\ue075>;" // CURRENCY NUMERATOR ONE
|
||||
"\ue076>;" // CURRENCY NUMERATOR TWO
|
||||
"\ue077>;" // CURRENCY NUMERATOR THREE
|
||||
"\ue078>;" // CURRENCY NUMERATOR FOUR
|
||||
"\ue079>;" // CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR
|
||||
"\ue07A>;" // CURRENCY DENOMINATOR SIXTEEN
|
||||
"\ue07B>;" // ISSHAR
|
||||
"\uE07C>;" // TIPPI
|
||||
"\uE07D>;" // ADDAK
|
||||
"\uE07E>;" // IRI
|
||||
"\uE07F>;" // URA
|
||||
"\uE080>;" // EK ONKAR
|
||||
"\uE081>\u0d35;" // FALLBACK FOR ORIYA LETTER WA
|
||||
"0 > \u0d66;" // FALLBACK FOR TAMIL
|
||||
"1 > \u0d67;"
|
||||
"\ue0f0 > \u0d30;" // FALLBACK RA
|
||||
"\ue0f1 > \u0d30;" // FALLBACK RA
|
||||
|
||||
|
||||
// :: NFC (NFD) ;
|
||||
// eof
|
||||
|
|
|
@ -1,12 +1,12 @@
|
|||
// -*- Coding: utf-8; -*-
|
||||
//--------------------------------------------------------------------
|
||||
// Copyright (c) 1999-2002, International Business Machines
|
||||
// Copyright (c) 1999-2004, International Business Machines
|
||||
// Corporation and others. All Rights Reserved.
|
||||
//--------------------------------------------------------------------
|
||||
// THIS IS A MACHINE-GENERATED FILE
|
||||
// Tool: dumpicurules.bat
|
||||
// Tool: dumpICUrules.bat
|
||||
// Source: ../../../impl/data/Transliterator_InterIndic_Oriya.txt
|
||||
// Date: Sat Jul 27 10:31:07 2002
|
||||
// Date: Tue May 18 17:24:49 2004
|
||||
//--------------------------------------------------------------------
|
||||
|
||||
// InterIndic_Oriya
|
||||
|
@ -22,6 +22,7 @@ t_InterIndic_Orya {
|
|||
"\ue001>\u0b01;" // SIGN CANDRABINDU
|
||||
"\ue002>\u0b02;" // SIGN ANUSVARA
|
||||
"\ue003>\u0b03;" // SIGN VISARGA
|
||||
"\uE004>\u0b05;" // FALLBACK TO LETTER A
|
||||
"\ue005>\u0b05;" // LETTER A
|
||||
"\ue006>\u0b06;" // LETTER AA
|
||||
"\ue007>\u0b07;" // LETTER I
|
||||
|
@ -36,7 +37,7 @@ t_InterIndic_Orya {
|
|||
"\ue010>\u0b10;" // LETTER AI
|
||||
"\ue011>\u0b13;" // FALLBACK
|
||||
"\ue012>\u0b13;" // FALLBACK
|
||||
"\ue013>\u0b13;" // UNMAPPED InterIndic-Oriya: LETTER OO (\u0b13 = LETTER O)
|
||||
"\ue013>\u0b13;" // FALLBACK LETTER OO (\u0b13 = LETTER O)
|
||||
"\ue014>\u0b14;" // LETTER AU
|
||||
"\ue015>\u0b15;" // LETTER KA
|
||||
"\ue016>\u0b16;" // LETTER KHA
|
||||
|
@ -58,7 +59,7 @@ t_InterIndic_Orya {
|
|||
"\ue026>\u0b26;" // LETTER DA
|
||||
"\ue027>\u0b27;" // LETTER DHA
|
||||
"\ue028>\u0b28;" // LETTER NA
|
||||
"\ue029>\u0b28\u0b3c;" // REMAP (indicExceptions.txt): \u0b29>\u0b28 = LETTER NNNA>LETTER NA
|
||||
"\ue029>\u0b28\u0b3c;" // FALLBACK \u0b29>\u0b28 = LETTER NNNA>LETTER NA
|
||||
"\ue02a>\u0b2a;" // LETTER PA
|
||||
"\ue02b>\u0b2b;" // LETTER PHA
|
||||
"\ue02c>\u0b2c;" // LETTER BA
|
||||
|
@ -69,8 +70,8 @@ t_InterIndic_Orya {
|
|||
"\ue031>\u0b5c;" // LETTER RRA
|
||||
"\ue032>\u0b32;" // LETTER LA
|
||||
"\ue033>\u0b33;" // LETTER LLA
|
||||
"\ue034>\u0b33\u0b3c;" // REMAP (indicExceptions.txt): \u0b34>\u0b33 = LETTER LLLA>LETTER LLA
|
||||
"\ue035>\u0b2c;" // REMAP (indicExceptions.txt): \u0b35>\u0b2c = LETTER VA>LETTER BA
|
||||
"\ue034>\u0b33\u0b3c;" // FALLBACK LETTER LLLA>LETTER LLA
|
||||
"\ue035>\u0b35;" // LETTER VA
|
||||
"\ue036>\u0b36;" // LETTER SHA
|
||||
"\ue037>\u0b37;" // LETTER SSA
|
||||
"\ue038>\u0b38;" // LETTER SA
|
||||
|
@ -83,7 +84,7 @@ t_InterIndic_Orya {
|
|||
"\ue041>\u0b41;" // VOWEL SIGN U
|
||||
"\ue042>\u0b42;" // VOWEL SIGN UU
|
||||
"\ue043>\u0b43;" // VOWEL SIGN VOCALIC R
|
||||
"\ue044>\u0b43\u0b3c;" // REMAP (indicExceptions.txt): \u0b44>\u0b43\u0b3c = VOWEL SIGN VOCALIC RR>VOWEL SIGN VOCALIC R.SIGN NUKTA
|
||||
"\ue044>\u0b43\u0b3c;" // FALLBACK \u0b44>\u0b43\u0b3c = VOWEL SIGN VOCALIC RR>VOWEL SIGN VOCALIC R.SIGN NUKTA
|
||||
"\ue045>\u0b47;" // FALLBACK
|
||||
"\ue046>\u0b47;" // FALLBACK
|
||||
"\ue047>\u0b47;" // VOWEL SIGN E
|
||||
|
@ -93,7 +94,7 @@ t_InterIndic_Orya {
|
|||
"\ue04b>\u0b4b;" // VOWEL SIGN E
|
||||
"\ue04c>\u0b4c;" // VOWEL SIGN AU
|
||||
"\ue04d>\u0b4d;" // SIGN VIRAMA
|
||||
"\ue050>\u0b13\u0b01;" // REMAP (indicExceptions.txt): \u0b50>\u0b13\u0b01 = OM>LETTER O.SIGN CANDRABINDU
|
||||
"\ue050>\u0b13\u0b01;" // FALLBACK \u0b50>\u0b13\u0b01 = OM>LETTER O.SIGN CANDRABINDU
|
||||
"\ue051>;"
|
||||
"\ue052>;"
|
||||
"\ue053>;"
|
||||
|
@ -101,20 +102,20 @@ t_InterIndic_Orya {
|
|||
"\ue055>;" // UNMAPPED InterIndic-Oriya: LENGTH MARK
|
||||
"\ue056>\u0b56;" // AI LENGTH MARK
|
||||
"\ue057>\u0b57;" // AU LENGTH MARK
|
||||
"\ue059>\u0b16\u0b3c;" // REMAP (indicExceptions.txt): \u0b59>\u0b16\u0b3c = LETTER KHHA>LETTER KHA.SIGN NUKTA
|
||||
"\ue059>\u0b16\u0b3c;" // FALLBACK \u0b59>\u0b16\u0b3c = LETTER KHHA>LETTER KHA.SIGN NUKTA
|
||||
"\ue058>\u0b15\u0b3c;" // FALLBACK
|
||||
"\ue05a>\u0b17\u0b3c;" // REMAP (indicExceptions.txt): \u0b5a>\u0b17\u0b3c = LETTER GHHA>LETTER GA.SIGN NUKTA
|
||||
"\ue05b>\u0b1c\u0b3c;" // REMAP (indicExceptions.txt): \u0b5b>\u0b1c\u0b3c = LETTER ZA>LETTER JA.SIGN NUKTA
|
||||
"\ue05a>\u0b17\u0b3c;" // FALLBACK \u0b5a>\u0b17\u0b3c = LETTER GHHA>LETTER GA.SIGN NUKTA
|
||||
"\ue05b>\u0b1c\u0b3c;" // FALLBACK \u0b5b>\u0b1c\u0b3c = LETTER ZA>LETTER JA.SIGN NUKTA
|
||||
"\ue05c>\u0b21\u0b3c;" // FALLBACK
|
||||
"\ue05d>\u0b5d;" // LETTER RHA
|
||||
"\ue05e>\u0b2b\u0b3c;" // REMAP (indicExceptions.txt): \u0b5e>\u0b2b\u0b3c = LETTER FA>LETTER PHA.SIGN NUKTA
|
||||
"\ue05e>\u0b2b\u0b3c;" // FALLBACK \u0b5e>\u0b2b\u0b3c = LETTER FA>LETTER PHA.SIGN NUKTA
|
||||
"\ue05f>\u0b5f;" // LETTER YYA
|
||||
"\ue060>\u0b60;" // LETTER VOCALIC RR
|
||||
"\ue061>\u0b61;" // LETTER VOCALIC LL
|
||||
"\ue062>\u0b56\u0b3c;" // REMAP (indicExceptions.txt): \u0b62>\u0b56\u0b3c = VOWEL SIGN VOCALIC L>AI LENGTH MARK.SIGN NUKTA
|
||||
"\ue063>\u0b57\u0b3c;" // REMAP (indicExceptions.txt): \u0b63>\u0b57\u0b3c = VOWEL SIGN VOCALIC LL>AU LENGTH MARK.SIGN NUKTA
|
||||
"\uE064>\u0964;" // DANDA
|
||||
"\uE065>\u0965;" // DOUBLE DANDA
|
||||
"\ue062>\u0b56\u0b3c;" // FALLBACK \u0b62>\u0b56\u0b3c = VOWEL SIGN VOCALIC L>AI LENGTH MARK.SIGN NUKTA
|
||||
"\ue063>\u0b57\u0b3c;" // FALLBACK \u0b63>\u0b57\u0b3c = VOWEL SIGN VOCALIC LL>AU LENGTH MARK.SIGN NUKTA
|
||||
"\uE064>\u0964;" // DANDA
|
||||
"\uE065>\u0965;" // DOUBLE DANDA
|
||||
"\ue066>\u0b66;" // DIGIT ZERO
|
||||
"\ue067>\u0b67;" // DIGIT ONE
|
||||
"\ue068>\u0b68;" // DIGIT TWO
|
||||
|
@ -125,21 +126,27 @@ t_InterIndic_Orya {
|
|||
"\ue06d>\u0b6d;" // DIGIT SEVEN
|
||||
"\ue06e>\u0b6e;" // DIGIT EIGHT
|
||||
"\ue06f>\u0b6f;" // DIGIT NINE
|
||||
"\ue070>;" // ISSHAR
|
||||
"\ue071>;"
|
||||
"\ue072>;"
|
||||
"\ue073>;"
|
||||
"\ue074>;"
|
||||
"\ue075>;"
|
||||
"\ue076>;"
|
||||
"\ue077>;"
|
||||
"\ue078>;"
|
||||
"\ue079>;"
|
||||
"\ue07A>;"
|
||||
"0 > \u0b66;" // FALLBACK FOR TAMIL
|
||||
"\ue070>;" // ABBREVIATION SIGN
|
||||
"\ue071>\u0b30;" // LETTER RA WITH MIDDLE DIAGONAL
|
||||
"\ue072>\u0b30;" // LETTER RA WITH LOWER DIAGONAL
|
||||
"\ue073>;" // RUPEE MARK
|
||||
"\ue074>;" // RUPEE SIGN
|
||||
"\ue075>;" // CURRENCY NUMERATOR ONE
|
||||
"\ue076>;" // CURRENCY NUMERATOR TWO
|
||||
"\ue077>;" // CURRENCY NUMERATOR THREE
|
||||
"\ue078>;" // CURRENCY NUMERATOR FOUR
|
||||
"\ue079>;" // CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR
|
||||
"\ue07A>;" // CURRENCY DENOMINATOR SIXTEEN
|
||||
"\ue07B>\u0B70;" // ISSHAR
|
||||
"\uE07C>;" // TIPPI
|
||||
"\uE07D>;" // ADDAK
|
||||
"\uE07E>;" // IRI
|
||||
"\uE07F>;" // URA
|
||||
"\uE080>;" // EK ONKAR
|
||||
"\uE081>\u0B71;" // LETTER WA
|
||||
"0 > \u0b66;" // FALLBACK FOR TAMIL
|
||||
"1 > \u0b67;"
|
||||
"\ue0f0 > \u0b30;" // FALLBACK RA
|
||||
"\ue0f1 > \u0b30;" // FALLBACK RA
|
||||
|
||||
// :: NFC (NFD) ;
|
||||
// eof
|
||||
}
|
||||
|
|
|
@ -1,12 +1,12 @@
|
|||
// -*- Coding: utf-8; -*-
|
||||
//--------------------------------------------------------------------
|
||||
// Copyright (c) 1999-2002, International Business Machines
|
||||
// Copyright (c) 1999-2004, International Business Machines
|
||||
// Corporation and others. All Rights Reserved.
|
||||
//--------------------------------------------------------------------
|
||||
// THIS IS A MACHINE-GENERATED FILE
|
||||
// Tool: dumpicurules.bat
|
||||
// Tool: dumpICUrules.bat
|
||||
// Source: ../../../impl/data/Transliterator_InterIndic_Tamil.txt
|
||||
// Date: Sat Jul 27 10:31:07 2002
|
||||
// Date: Tue May 18 17:24:49 2004
|
||||
//--------------------------------------------------------------------
|
||||
|
||||
// InterIndic_Tamil
|
||||
|
@ -22,6 +22,7 @@ t_InterIndic_Taml {
|
|||
"\ue001>\u0b82;" // FALLBACK SIGN CANDRABINDU
|
||||
"\ue002>\u0b82;" // SIGN ANUSVARA
|
||||
"\ue003>\u0b83;" // SIGN VISARGA
|
||||
"\uE004>\u0b85;" // FALLBACK TO LETTER A
|
||||
"\ue005>\u0b85;" // LETTER A
|
||||
"\ue006>\u0b86;" // LETTER AA
|
||||
"\ue007>\u0b87;" // LETTER I
|
||||
|
@ -29,7 +30,7 @@ t_InterIndic_Taml {
|
|||
"\ue009>\u0b89;" // LETTER U
|
||||
"\ue00a>\u0b8a;" // LETTER UU
|
||||
"\ue00b>\u0bb0\u0bbf;" // REMAP (indicExceptions.txt): \u0b8b>\u0bb0\u0bbf = LETTER VOCALIC R>LETTER RA.VOWEL SIGN I
|
||||
"\ue00c>\u0b87;" // REMAP (indicExceptions.txt): \u0b8c>\u0b87 = LETTER VOCALIC L>LETTER I
|
||||
"\ue00c>\u0bb2;" // FALLBACK LETTER LA
|
||||
"\ue00d>\u0b8f;" // FALLBACK
|
||||
"\ue00e>\u0b8e;" // LETTER E
|
||||
"\ue00f>\u0b8f;" // LETTER EE
|
||||
|
@ -115,11 +116,11 @@ t_InterIndic_Taml {
|
|||
"\ue05e>\u0baa;" // REMAP (indicExceptions.txt): \u0bde>\u0baa = LETTER FA>LETTER PA
|
||||
"\ue05f>\u0baf;" // REMAP (indicExceptions.txt): \u0bdf>\u0baf = LETTER YYA>LETTER YA
|
||||
"\ue060>\u0bb0\u0bbf;" // REMAP (indicExceptions.txt): \u0be0>\u0bb0\u0bbf = LETTER VOCALIC RR>LETTER RA.VOWEL SIGN I
|
||||
"\ue061>\u0b88;" // REMAP (indicExceptions.txt): \u0be1>\u0b88 = LETTER VOCALIC LL>LETTER II
|
||||
"\ue062>\u0bbf;"// FALLBACK VOWEL SIGN VOCALIC L
|
||||
"\ue063>\u0bc0;"// FALLBACK VOWEL SIGN VOCALIC LL
|
||||
"\ue061>\u0bb3;" // FALLBACK LETTER LLA
|
||||
"\ue062>\u0bbf;" // FALLBACK VOWEL SIGN VOCALIC L
|
||||
"\ue063>\u0bc0;" // FALLBACK VOWEL SIGN VOCALIC LL
|
||||
"\ue064>'.' ;" // FALLBACK FOR DANDA
|
||||
"\ue065>'.' ;" // FALLBACK FOR DOUBLE DANDA
|
||||
"\ue065>'.' ;" // FALLBACK FOR DOUBLE DANDA
|
||||
|
||||
"\ue066>\u0030;" // FALLBACK DIGIT ZERO
|
||||
|
||||
|
@ -137,26 +138,29 @@ t_InterIndic_Taml {
|
|||
"\ue06e>\u0bee;" // DIGIT EIGHT
|
||||
"\ue06f>\u0bef;" // DIGIT NINE
|
||||
|
||||
"1000 >\u0BF2;" // UNMAPPED Tamil-InterIndic: NUMBER ONE THOUSAND
|
||||
"100 >\u0BF1;" // UNMAPPED Tamil-InterIndic: NUMBER ONE HUNDRED
|
||||
"10 >\u0BF0;" // UNMAPPED Tamil-InterIndic: NUMBER TEN
|
||||
"\ue070>;" // ABBREVIATION SIGN
|
||||
"\ue071>\u0bc0;" // LETTER RA WITH MIDDLE DIAGONAL
|
||||
"\ue072>\u0bc0;" // LETTER RA WITH LOWER DIAGONAL
|
||||
"\ue073>;" // RUPEE MARK
|
||||
"\ue074>;" // RUPEE SIGN
|
||||
"\ue075>;" // CURRENCY NUMERATOR ONE
|
||||
"\ue076>;" // CURRENCY NUMERATOR TWO
|
||||
"\ue077>;" // CURRENCY NUMERATOR THREE
|
||||
"\ue078>;" // CURRENCY NUMERATOR FOUR
|
||||
"\ue079>;" // CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR
|
||||
"\ue07A>;" // CURRENCY DENOMINATOR SIXTEEN
|
||||
"\ue07B>;" // ISSHAR
|
||||
"\uE07C>;" // TIPPI
|
||||
"\uE07D>;" // ADDAK
|
||||
"\uE07E>;" // IRI
|
||||
"\uE07F>;" // URA
|
||||
"\uE080>;" // EK ONKAR
|
||||
"\uE081>\u0bb5;" // FALLBACK FOR ORIYA LETTER WA
|
||||
|
||||
"1000 >\u0BF2;" // NUMBER ONE THOUSAND
|
||||
"100 >\u0BF1;" // NUMBER ONE HUNDRED
|
||||
"10 >\u0BF0;" // NUMBER TEN
|
||||
|
||||
|
||||
"\ue080>;" // UNMAPPED InterIndic-Tamil: ISSHAR
|
||||
"\ue070>\u0BF0;"
|
||||
"\ue071>\u0BF2;"
|
||||
"\ue072>\u0BF1;"
|
||||
"\ue073>;"
|
||||
"\ue074>;"
|
||||
"\ue075>;"
|
||||
"\ue076>;"
|
||||
"\ue077>;"
|
||||
"\ue078>;"
|
||||
"\ue079>;"
|
||||
"\ue07A>;"
|
||||
"\ue0f0 > \u0bb0;" // FALLBACK RA
|
||||
"\ue0f1 > \u0bb0;" // FALLBACK RA
|
||||
// :: NFC (NFD) ;
|
||||
// eof
|
||||
}
|
||||
|
|
|
@ -1,12 +1,12 @@
|
|||
// -*- Coding: utf-8; -*-
|
||||
//--------------------------------------------------------------------
|
||||
// Copyright (c) 1999-2002, International Business Machines
|
||||
// Copyright (c) 1999-2004, International Business Machines
|
||||
// Corporation and others. All Rights Reserved.
|
||||
//--------------------------------------------------------------------
|
||||
// THIS IS A MACHINE-GENERATED FILE
|
||||
// Tool: dumpicurules.bat
|
||||
// Tool: dumpICUrules.bat
|
||||
// Source: ../../../impl/data/Transliterator_InterIndic_Telugu.txt
|
||||
// Date: Sat Jul 27 10:31:07 2002
|
||||
// Date: Tue May 18 17:24:49 2004
|
||||
//--------------------------------------------------------------------
|
||||
|
||||
// InterIndic_Telugu
|
||||
|
@ -22,6 +22,7 @@ t_InterIndic_Telu {
|
|||
"\ue001>\u0c01;" // SIGN CANDRABINDU
|
||||
"\ue002>\u0c02;" // SIGN ANUSVARA
|
||||
"\ue003>\u0c03;" // SIGN VISARGA
|
||||
"\uE004>\u0c05;" // FALLBACK TO LETTER A
|
||||
"\ue005>\u0c05;" // LETTER A
|
||||
"\ue006>\u0c06;" // LETTER AA
|
||||
"\ue007>\u0c07;" // LETTER I
|
||||
|
@ -88,9 +89,11 @@ t_InterIndic_Telu {
|
|||
"\ue043>\u0c43;" // VOWEL SIGN VOCALIC R
|
||||
"\ue044>\u0c44;" // VOWEL SIGN VOCALIC RR
|
||||
"\ue045>\u0c46;" // VOWEL SIGN CANDRA E>VOWEL SIGN E
|
||||
"\ue046>\u0c46;" // VOWEL SIGN E
|
||||
"\ue047>\u0c47;" // VOWEL SIGN EE
|
||||
"\ue048>\u0c48;" // VOWEL SIGN AI
|
||||
"\ue049>\u0c4a;" // REMAP (indicExceptions.txt): \u0c49>\u0c4a = VOWEL SIGN CANDRA O>VOWEL SIGN O
|
||||
"\ue04a>\u0c4a;" // VOWEL SIGN O
|
||||
"\ue04b>\u0c4b;" // VOWEL SIGN OO
|
||||
"\ue04c>\u0c4c;" // VOWEL SIGN AU
|
||||
"\ue04d>\u0c4d;" // SIGN VIRAMA
|
||||
|
@ -115,7 +118,7 @@ t_InterIndic_Telu {
|
|||
"\ue062>\u0c3f;" // REMAP (indicExceptions.txt): \u0c62>\u0c3f = VOWEL SIGN VOCALIC L>VOWEL SIGN I
|
||||
"\ue063>\u0c40;" // REMAP (indicExceptions.txt): \u0c63>\u0c40 = VOWEL SIGN VOCALIC LL>VOWEL SIGN II
|
||||
"\ue064>'.' ;" // FALLBACK FOR DANDA
|
||||
"\ue065>'.' ;" // FALLBACK FOR DOUBLE DANDA
|
||||
"\ue065>'.' ;" // FALLBACK FOR DOUBLE DANDA
|
||||
"\ue066>\u0c66;" // DIGIT ZERO
|
||||
"\ue067>\u0c67;" // DIGIT ONE
|
||||
"\ue068>\u0c68;" // DIGIT TWO
|
||||
|
@ -126,27 +129,28 @@ t_InterIndic_Telu {
|
|||
"\ue06d>\u0c6d;" // DIGIT SEVEN
|
||||
"\ue06e>\u0c6e;" // DIGIT EIGHT
|
||||
"\ue06f>\u0c6f;" // DIGIT NINE
|
||||
// \ue080>; # UNMAPPED InterIndic-Telugu: ISSHAR
|
||||
|
||||
|
||||
"\ue046>\u0c46;" // VOWEL SIGN E
|
||||
"\ue04a>\u0c4a;" // VOWEL SIGN O
|
||||
"\ue070>;"
|
||||
"\ue071>;"
|
||||
"\ue072>;"
|
||||
"\ue073>;"
|
||||
"\ue074>;"
|
||||
"\ue075>;"
|
||||
"\ue076>;"
|
||||
"\ue077>;"
|
||||
"\ue078>;"
|
||||
"\ue079>;"
|
||||
"\ue07A>;"
|
||||
|
||||
"\ue070>;" // ABBREVIATION SIGN
|
||||
"\ue071>\u0c30;" // LETTER RA WITH MIDDLE DIAGONAL
|
||||
"\ue072>\u0c30;" // LETTER RA WITH LOWER DIAGONAL
|
||||
"\ue073>;" // RUPEE MARK
|
||||
"\ue074>;" // RUPEE SIGN
|
||||
"\ue075>;" // CURRENCY NUMERATOR ONE
|
||||
"\ue076>;" // CURRENCY NUMERATOR TWO
|
||||
"\ue077>;" // CURRENCY NUMERATOR THREE
|
||||
"\ue078>;" // CURRENCY NUMERATOR FOUR
|
||||
"\ue079>;" // CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR
|
||||
"\ue07A>;" // CURRENCY DENOMINATOR SIXTEEN
|
||||
"\ue07B>;" // ISSHAR
|
||||
"\uE07C>;" // TIPPI
|
||||
"\uE07D>;" // ADDAK
|
||||
"\uE07E>;" // IRI
|
||||
"\uE07F>;" // URA
|
||||
"\uE080>;" // EK ONKAR
|
||||
"\uE081>\u0c35;" // FALLBACK FOR ORIYA LETTER WA
|
||||
"0 > \u0c66;" // FALLBACK FOR TAMIL
|
||||
"1 > \u0c67;"
|
||||
"\ue0f0 > \u0c30;" // FALLBACK RA
|
||||
"\ue0f1 > \u0c30;" // FALLBACK RA
|
||||
|
||||
// :: NFC (NFD) ;
|
||||
// eof
|
||||
}
|
||||
|
|
|
@ -1,12 +1,12 @@
|
|||
// -*- Coding: utf-8; -*-
|
||||
//--------------------------------------------------------------------
|
||||
// Copyright (c) 1999-2002, International Business Machines
|
||||
// Copyright (c) 1999-2004, International Business Machines
|
||||
// Corporation and others. All Rights Reserved.
|
||||
//--------------------------------------------------------------------
|
||||
// THIS IS A MACHINE-GENERATED FILE
|
||||
// Tool: dumpicurules.bat
|
||||
// Tool: dumpICUrules.bat
|
||||
// Source: ../../../impl/data/Transliterator_Kannada_InterIndic.txt
|
||||
// Date: Sat Jul 27 10:31:07 2002
|
||||
// Date: Tue May 18 17:24:49 2004
|
||||
//--------------------------------------------------------------------
|
||||
|
||||
// Kannada_InterIndic
|
||||
|
@ -76,6 +76,8 @@ t_Knda_InterIndic {
|
|||
"\u0CB7>\uE037;" // LETTER SSA
|
||||
"\u0CB8>\uE038;" // LETTER SA
|
||||
"\u0CB9>\uE039;" // LETTER HA
|
||||
"\u0CBC>\uE03C;" // SIGN NUKTA
|
||||
"\u0CBD>\uE03D;" // AVAGRAHA
|
||||
"\u0CBE>\uE03E;" // VOWEL SIGN AA
|
||||
"\u0CBF>\uE03F;" // VOWEL SIGN I
|
||||
"\u0CC1>\uE041;" // VOWEL SIGN U
|
||||
|
@ -87,7 +89,7 @@ t_Knda_InterIndic {
|
|||
"\u0CCD>\uE04D;" // SIGN VIRAMA
|
||||
"\u0CD5>\uE055;" // LENGTH MARK
|
||||
"\u0CD6>\uE056;" // AI LENGTH MARK
|
||||
"\u0CDE>\uE05E;" // LETTER FA
|
||||
"\u0CDE>\uE034;" // LETTER LLLA
|
||||
"\u0CE0>\uE060;" // LETTER VOCALIC RR
|
||||
"\u0CE1>\uE061;" // LETTER VOCALIC LL
|
||||
"\u0CE6>\uE066;" // DIGIT ZERO
|
||||
|
|
|
@ -1,12 +1,12 @@
|
|||
// -*- Coding: utf-8; -*-
|
||||
//--------------------------------------------------------------------
|
||||
// Copyright (c) 1999-2002, International Business Machines
|
||||
// Copyright (c) 1999-2004, International Business Machines
|
||||
// Corporation and others. All Rights Reserved.
|
||||
//--------------------------------------------------------------------
|
||||
// THIS IS A MACHINE-GENERATED FILE
|
||||
// Tool: dumpicurules.bat
|
||||
// Tool: dumpICUrules.bat
|
||||
// Source: ../../../impl/data/Transliterator_Latin_InterIndic.txt
|
||||
// Date: Sat Jul 27 10:31:07 2002
|
||||
// Date: Tue May 18 17:24:49 2004
|
||||
//--------------------------------------------------------------------
|
||||
|
||||
// Latin_InterIndic
|
||||
|
@ -75,6 +75,7 @@ t_Latn_InterIndic {
|
|||
"$lla=\ue033;"
|
||||
"$ela=\ue034;" //compatibility
|
||||
"$va=\ue035;"
|
||||
"$vva=\ue081;"
|
||||
"$sha=\ue036;"
|
||||
"$ssa=\ue037;"
|
||||
"$sa=\ue038;"
|
||||
|
@ -293,6 +294,7 @@ t_Latn_InterIndic {
|
|||
"l\u0323>$lla|$virama;"
|
||||
"l>$la|$virama;"
|
||||
"v>$va|$virama;"
|
||||
"w\u0307>$vva|$virama;"
|
||||
"w>$va|$virama;"
|
||||
"sh>$sha|$virama;"
|
||||
"ss>$ssa|$virama;"
|
||||
|
|
|
@ -1,12 +1,12 @@
|
|||
// -*- Coding: utf-8; -*-
|
||||
//--------------------------------------------------------------------
|
||||
// Copyright (c) 1999-2002, International Business Machines
|
||||
// Copyright (c) 1999-2004, International Business Machines
|
||||
// Corporation and others. All Rights Reserved.
|
||||
//--------------------------------------------------------------------
|
||||
// THIS IS A MACHINE-GENERATED FILE
|
||||
// Tool: dumpicurules.bat
|
||||
// Tool: dumpICUrules.bat
|
||||
// Source: ../../../impl/data/Transliterator_Latin_Jamo.txt
|
||||
// Date: Sat Jul 27 10:31:07 2002
|
||||
// Date: Tue May 18 17:24:49 2004
|
||||
//--------------------------------------------------------------------
|
||||
|
||||
// Latin_Jamo
|
||||
|
|
|
@ -1,12 +1,12 @@
|
|||
// -*- Coding: utf-8; -*-
|
||||
//--------------------------------------------------------------------
|
||||
// Copyright (c) 1999-2002, International Business Machines
|
||||
// Copyright (c) 1999-2004, International Business Machines
|
||||
// Corporation and others. All Rights Reserved.
|
||||
//--------------------------------------------------------------------
|
||||
// THIS IS A MACHINE-GENERATED FILE
|
||||
// Tool: dumpicurules.bat
|
||||
// Tool: dumpICUrules.bat
|
||||
// Source: ../../../impl/data/Transliterator_Latin_Katakana.txt
|
||||
// Date: Sat Jul 27 10:31:07 2002
|
||||
// Date: Tue May 18 17:24:49 2004
|
||||
//--------------------------------------------------------------------
|
||||
|
||||
// Latin_Katakana
|
||||
|
|
|
@ -1,12 +1,12 @@
|
|||
// -*- Coding: utf-8; -*-
|
||||
//--------------------------------------------------------------------
|
||||
// Copyright (c) 1999-2002, International Business Machines
|
||||
// Copyright (c) 1999-2004, International Business Machines
|
||||
// Corporation and others. All Rights Reserved.
|
||||
//--------------------------------------------------------------------
|
||||
// THIS IS A MACHINE-GENERATED FILE
|
||||
// Tool: dumpicurules.bat
|
||||
// Tool: dumpICUrules.bat
|
||||
// Source: ../../../impl/data/Transliterator_Malayalam_InterIndic.txt
|
||||
// Date: Sat Jul 27 10:31:07 2002
|
||||
// Date: Tue May 18 17:24:49 2004
|
||||
//--------------------------------------------------------------------
|
||||
|
||||
// Malayalam_InterIndic
|
||||
|
|
|
@ -1,12 +1,12 @@
|
|||
// -*- Coding: utf-8; -*-
|
||||
//--------------------------------------------------------------------
|
||||
// Copyright (c) 1999-2002, International Business Machines
|
||||
// Copyright (c) 1999-2004, International Business Machines
|
||||
// Corporation and others. All Rights Reserved.
|
||||
//--------------------------------------------------------------------
|
||||
// THIS IS A MACHINE-GENERATED FILE
|
||||
// Tool: dumpicurules.bat
|
||||
// Tool: dumpICUrules.bat
|
||||
// Source: ../../../impl/data/Transliterator_Oriya_InterIndic.txt
|
||||
// Date: Sat Jul 27 10:31:07 2002
|
||||
// Date: Tue May 18 17:24:49 2004
|
||||
//--------------------------------------------------------------------
|
||||
|
||||
// Oriya_InterIndic
|
||||
|
@ -69,6 +69,7 @@ t_Orya_InterIndic {
|
|||
"\u0B30>\uE030;" // LETTER RA
|
||||
"\u0B32>\uE032;" // LETTER LA
|
||||
"\u0B33>\uE033;" // LETTER LLA
|
||||
"\u0B35>\uE035;" // LETTER VA
|
||||
"\u0B36>\uE036;" // LETTER SHA
|
||||
"\u0B37>\uE037;" // LETTER SSA
|
||||
"\u0B38>\uE038;" // LETTER SA
|
||||
|
@ -86,6 +87,8 @@ t_Orya_InterIndic {
|
|||
"\u0B4D>\uE04D;" // SIGN VIRAMA
|
||||
"\u0B56>\uE056;" // AI LENGTH MARK
|
||||
"\u0B57>\uE057;" // AU LENGTH MARK
|
||||
"\u0964>\ue064;" // DANDA
|
||||
"\u0965>\ue065;" // DOUBLE DANDA
|
||||
//
|
||||
"\u0B5F>\uE05F;" // LETTER YYA
|
||||
"\u0B60>\uE060;" // LETTER VOCALIC RR
|
||||
|
@ -100,7 +103,8 @@ t_Orya_InterIndic {
|
|||
"\u0B6D>\uE06D;" // DIGIT SEVEN
|
||||
"\u0B6E>\uE06E;" // DIGIT EIGHT
|
||||
"\u0B6F>\uE06F;" // DIGIT NINE
|
||||
"\u0B70>\uE070;" // ISSHAR
|
||||
"\u0B70>\ue07B;" // ISSHAR
|
||||
"\u0B71>\ue081;" // LETTER WA
|
||||
// :: NFC (NFD) ;
|
||||
// eof
|
||||
}
|
||||
|
|
|
@ -1,12 +1,12 @@
|
|||
// -*- Coding: utf-8; -*-
|
||||
//--------------------------------------------------------------------
|
||||
// Copyright (c) 1999-2002, International Business Machines
|
||||
// Copyright (c) 1999-2004, International Business Machines
|
||||
// Corporation and others. All Rights Reserved.
|
||||
//--------------------------------------------------------------------
|
||||
// THIS IS A MACHINE-GENERATED FILE
|
||||
// Tool: dumpicurules.bat
|
||||
// Tool: dumpICUrules.bat
|
||||
// Source: ../../../impl/data/Transliterator_Tamil_InterIndic.txt
|
||||
// Date: Sat Jul 27 10:31:07 2002
|
||||
// Date: Tue May 18 17:24:49 2004
|
||||
//--------------------------------------------------------------------
|
||||
|
||||
// Tamil_InterIndic
|
||||
|
|
|
@ -1,12 +1,12 @@
|
|||
// -*- Coding: utf-8; -*-
|
||||
//--------------------------------------------------------------------
|
||||
// Copyright (c) 1999-2002, International Business Machines
|
||||
// Copyright (c) 1999-2004, International Business Machines
|
||||
// Corporation and others. All Rights Reserved.
|
||||
//--------------------------------------------------------------------
|
||||
// THIS IS A MACHINE-GENERATED FILE
|
||||
// Tool: dumpicurules.bat
|
||||
// Tool: dumpICUrules.bat
|
||||
// Source: ../../../impl/data/Transliterator_Telugu_InterIndic.txt
|
||||
// Date: Sat Jul 27 10:31:07 2002
|
||||
// Date: Tue May 18 17:24:49 2004
|
||||
//--------------------------------------------------------------------
|
||||
|
||||
// Telugu_InterIndic
|
||||
|
@ -90,8 +90,6 @@ t_Telu_InterIndic {
|
|||
"\u0C56>\uE056;" // AI LENGTH MARK
|
||||
"\u0C60>\uE060;" // LETTER VOCALIC RR
|
||||
"\u0C61>\uE061;" // LETTER VOCALIC LL
|
||||
"\u0C64>\uE064;"
|
||||
"\u0C65>\uE065;"
|
||||
"\u0C66>\uE066;" // DIGIT ZERO
|
||||
"\u0C67>\uE067;" // DIGIT ONE
|
||||
"\u0C68>\uE068;" // DIGIT TWO
|
||||
|
|
|
@ -1,11 +1,11 @@
|
|||
//--------------------------------------------------------------------
|
||||
// Copyright (c) 1999-2002, International Business Machines
|
||||
// Copyright (c) 1999-2004, International Business Machines
|
||||
// Corporation and others. All Rights Reserved.
|
||||
//--------------------------------------------------------------------
|
||||
// THIS IS A MACHINE-GENERATED FILE
|
||||
// Tool: dumpicurules.bat
|
||||
// Tool: dumpICUrules.bat
|
||||
// Source: Transliterator_index.txt
|
||||
// Date: Sat Jul 27 10:31:01 2002
|
||||
// Date: Tue May 18 17:24:48 2004
|
||||
//--------------------------------------------------------------------
|
||||
|
||||
//--------------------------------------------------------------------
|
||||
|
@ -74,8 +74,9 @@ translit_index {
|
|||
{ "Latin-Arabic", "file", "t_Arab_Latn", "REVERSE" },
|
||||
{ "Arabic-Latin", "file", "t_Arab_Latn", "FORWARD" },
|
||||
|
||||
{ "Latin-Han", "file", "t_Hani_Latn", "REVERSE" },
|
||||
{ "Han-Latin", "file", "t_Hani_Latn", "FORWARD" },
|
||||
//Latin-Han:file:Transliterator_Han_Latin.txt:UTF8:REVERSE # no round trip!
|
||||
{ "Latin-Han", "alias", "null", "" },
|
||||
|
||||
// Comment these out; they are only for testing
|
||||
// Latin-Han/definition:file:Transliterator_Han_Latin_Definition.txt:UTF8:REVERSE
|
||||
|
@ -111,7 +112,7 @@ translit_index {
|
|||
// Thai-Logical also converts spaces to semicolons. That has to be done before we insert latin spaces
|
||||
|
||||
{ "Thai-Latin", "alias", "[[", "thai", "] \u0E01-\u0E3A\u0E40-\u0E5B];NFD;Thai-ThaiSemi;Any-BreakInternal;Thai-ThaiLogical;ThaiLogical-Latin;NFC", "" },
|
||||
{ "Latin-Thai", "alias", "[[", "Latin", "][", "Mn", "][", "Me", "] \ \;0-9|~\u00A7\u00AB\u00BB\u02B9\u0374\u2021];NFD;Latin-ThaiLogical;ThaiLogical-Thai;NFC", "" },
|
||||
{ "Latin-Thai", "alias", "[[", "Latin", "][", "Mn", "][", "Me", "] \ \;0-9|~\u00A7\u00AB\u00BB\u02B9\u0374\u2021\u02CC];NFD;Latin-ThaiLogical;ThaiLogical-Thai;NFC", "" },
|
||||
|
||||
// end of Thai Stuff
|
||||
|
||||
|
@ -170,60 +171,60 @@ translit_index {
|
|||
{ "Latin-Malayalam", "alias", "['.0-9A-Za-z~\u00C0-\u00C5\u00C7-\u00CF\u00D1-\u00D6\u00D9-\u00DD\u00E0-\u00E5\u00E7-\u00EF\u00F1-\u00F6\u00F9-\u00FD\u00FF-\u010F\u0112-\u0125\u0128-\u0130\u0134-\u0137\u0139-\u013E\u0143-\u0148\u014C-\u0151\u0154-\u0165\u0168-\u017E\u01A0-\u01A1\u01AF-\u01B0\u01CD-\u01DC\u01DE-\u01E3\u01E6-\u01ED\u01F0\u01F4-\u01F5\u01F8-\u021B\u021E-\u021F\u0226-\u0233\u0301\u0303-\u0304\u0306-\u0307\u0310\u0314-\u0315\u0323\u0325\u0331\u0341\u0344\u0385-\u0386\u0388-\u038A\u038C\u038E-\u0390\u03AC-\u03B0\u03CC-\u03CE\u03D3\u0403\u040C\u040E\u0419\u0439\u0453\u045C\u045E\u04C1-\u04C2\u04D0-\u04D1\u04D6-\u04D7\u04E2-\u04E3\u04EE-\u04EF\u1E00-\u1E99\u1EA0-\u1EF9\u1F01\u1F03-\u1F05\u1F07\u1F09\u1F0B-\u1F0D\u1F0F\u1F11\u1F13-\u1F15\u1F19\u1F1B-\u1F1D\u1F21\u1F23-\u1F25\u1F27\u1F29\u1F2B-\u1F2D\u1F2F\u1F31\u1F33-\u1F35\u1F37\u1F39\u1F3B-\u1F3D\u1F3F\u1F41\u1F43-\u1F45\u1F49\u1F4B-\u1F4D\u1F51\u1F53-\u1F55\u1F57\u1F59\u1F5B\u1F5D\u1F5F\u1F61\u1F63-\u1F65\u1F67\u1F69\u1F6B-\u1F6D\u1F6F\u1F71\u1F73\u1F75\u1F77\u1F79\u1F7B\u1F7D\u1F81\u1F83-\u1F85\u1F87\u1F89\u1F8B-\u1F8D\u1F8F\u1F91\u1F93-\u1F95\u1F97\u1F99\u1F9B-\u1F9D\u1F9F\u1FA1\u1FA3-\u1FA5\u1FA7\u1FA9\u1FAB-\u1FAD\u1FAF-\u1FB1\u1FB4\u1FB8-\u1FB9\u1FBB\u1FC4\u1FC9\u1FCB\u1FCE\u1FD0-\u1FD1\u1FD3\u1FD8-\u1FD9\u1FDB\u1FDE\u1FE0-\u1FE1\u1FE3\u1FE5\u1FE8-\u1FE9\u1FEB-\u1FEC\u1FEE\u1FF4\u1FF9\u1FFB\u212A-\u212B\uE04D\uE064];NFD;Lower;Latin-InterIndic;InterIndic-Malayalam;NFC", "" },
|
||||
|
||||
//Indic-Latin transliterators
|
||||
{ "Devanagari-Latin", "alias", "[\u0901-\u0903\u0905-\u0939\u093C-\u094D\u0950-\u0954\u0958-\u096F];NFD;Devanagari-InterIndic;InterIndic-Latin;NFC", "" },
|
||||
{ "Bengali-Latin", "alias", "[\u0964-\u0965\u0981-\u0983\u0985-\u098C\u098F-\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09BC\u09BE-\u09C4\u09C7-\u09C8\u09CB-\u09CD\u09D7\u09DC-\u09DD\u09DF-\u09E3\u09E6-\u09FA];NFD;Bengali-InterIndic;InterIndic-Latin;NFC", "" },
|
||||
{ "Gurmukhi-Latin", "alias", "[\u0964-\u0965\u0A02\u0A05-\u0A0A\u0A0F-\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32-\u0A33\u0A35-\u0A36\u0A38-\u0A39\u0A3C\u0A3E-\u0A42\u0A47-\u0A48\u0A4B-\u0A4D\u0A59-\u0A5C\u0A5E\u0A66-\u0A74];NFD;Gurmukhi-InterIndic;InterIndic-Latin;NFC", "" },
|
||||
{ "Gujarati-Latin", "alias", "[\u0964-\u0965\u0A81-\u0A83\u0A85-\u0A8B\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2-\u0AB3\u0AB5-\u0AB9\u0ABC-\u0AC5\u0AC7-\u0AC9\u0ACB-\u0ACD\u0AD0\u0AE0\u0AE6-\u0AEF];NFD;Gujarati-InterIndic;InterIndic-Latin;NFC", "" },
|
||||
{ "Oriya-Latin", "alias", "[\u0B01-\u0B03\u0B05-\u0B0C\u0B0F-\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32-\u0B33\u0B36-\u0B39\u0B3C-\u0B43\u0B47-\u0B48\u0B4B-\u0B4D\u0B56-\u0B57\u0B5C-\u0B5D\u0B5F-\u0B61\u0B66-\u0B70];NFD;Oriya-InterIndic;InterIndic-Latin;NFC", "" },
|
||||
{ "Devanagari-Latin", "alias", "[\u0901-\u0903\u0904\u0905-\u0939\u093C-\u094D\u0950-\u0954\u0958-\u096F];NFD;Devanagari-InterIndic;InterIndic-Latin;NFC", "" },
|
||||
{ "Bengali-Latin", "alias", "[\u0964-\u0965\u0981-\u0983\u0985-\u098C\u098F-\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09BC-\u09C4\u09C7-\u09C8\u09CB-\u09CD\u09D7\u09DC-\u09DD\u09DF-\u09E3\u09E6-\u09FA];NFD;Bengali-InterIndic;InterIndic-Latin;NFC", "" },
|
||||
{ "Gurmukhi-Latin", "alias", "[\u0964-\u0965\u0A01\u0A02\u0A05-\u0A0A\u0A0F-\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32-\u0A33\u0A35-\u0A36\u0A38-\u0A39\u0A3C\u0A3E-\u0A42\u0A47-\u0A48\u0A4B-\u0A4D\u0A59-\u0A5C\u0A5E\u0A66-\u0A74];NFD;Gurmukhi-InterIndic;InterIndic-Latin;NFC", "" },
|
||||
{ "Gujarati-Latin", "alias", "[\u0964-\u0965\u0A81-\u0A83\u0A85-\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2-\u0AB3\u0AB5-\u0AB9\u0ABC-\u0AC5\u0AC7-\u0AC9\u0ACB-\u0ACD\u0AD0\u0AE0\u0AE1\u0AE6-\u0AEF];NFD;Gujarati-InterIndic;InterIndic-Latin;NFC", "" },
|
||||
{ "Oriya-Latin", "alias", "[\u0964-\u0965\u0B01-\u0B03\u0B05-\u0B0C\u0B0F-\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32-\u0B33\u0B35\u0B36-\u0B39\u0B3C-\u0B43\u0B47-\u0B48\u0B4B-\u0B4D\u0B56-\u0B57\u0B5C-\u0B5D\u0B5F-\u0B61\u0B66-\u0B70\u0B71];NFD;Oriya-InterIndic;InterIndic-Latin;NFC", "" },
|
||||
{ "Tamil-Latin", "alias", "[0\u0B82-\u0B83\u0B85-\u0B8A\u0B8E-\u0B90\u0B92-\u0B95\u0B99-\u0B9A\u0B9C\u0B9E-\u0B9F\u0BA3-\u0BA4\u0BA8-\u0BAA\u0BAE-\u0BB5\u0BB7-\u0BB9\u0BBE-\u0BC2\u0BC6-\u0BC8\u0BCA-\u0BCD\u0BD7\u0BE7-\u0BF2];NFD;Tamil-InterIndic;InterIndic-Latin;NFC", "" },
|
||||
{ "Telugu-Latin", "alias", "[\u0C01-\u0C03\u0C05-\u0C0C\u0C0E-\u0C10\u0C12-\u0C28\u0C2A-\u0C33\u0C35-\u0C39\u0C3E-\u0C44\u0C46-\u0C48\u0C4A-\u0C4D\u0C55-\u0C56\u0C60-\u0C61\u0C66-\u0C6F];NFD;Telugu-InterIndic;InterIndic-Latin;NFC", "" },
|
||||
{ "Kannada-Latin", "alias", "[\u0C82-\u0C83\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CBE-\u0CC4\u0CC6-\u0CC8\u0CCA-\u0CCD\u0CD5-\u0CD6\u0CDE\u0CE0-\u0CE1\u0CE6-\u0CEF];NFD;Kannada-InterIndic;InterIndic-Latin;NFC", "" },
|
||||
{ "Kannada-Latin", "alias", "[\u0C82-\u0C83\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CBC-\u0CC4\u0CC6-\u0CC8\u0CCA-\u0CCD\u0CD5-\u0CD6\u0CDE\u0CE0-\u0CE1\u0CE6-\u0CEF];NFD;Kannada-InterIndic;InterIndic-Latin;NFC", "" },
|
||||
{ "Malayalam-Latin", "alias", "[\u0D02-\u0D03\u0D05-\u0D0C\u0D0E-\u0D10\u0D12-\u0D28\u0D2A-\u0D39\u0D3E-\u0D43\u0D46-\u0D48\u0D4A-\u0D4D\u0D57\u0D60-\u0D61\u0D66-\u0D6F];NFD;Malayalam-InterIndic;InterIndic-Latin;NFC", "" },
|
||||
|
||||
{ "Devanagari-Bengali", "alias", "[\u0901-\u0903\u0905-\u0939\u093C-\u094D\u0950-\u0954\u0958-\u096F];NFD;Devanagari-InterIndic;InterIndic-Bengali;NFC", "" },
|
||||
{ "Devanagari-Gurmukhi", "alias", "[\u0901-\u0903\u0905-\u0939\u093C-\u094D\u0950-\u0954\u0958-\u096F];NFD;Devanagari-InterIndic;InterIndic-Gurmukhi;NFC", "" },
|
||||
{ "Devanagari-Gujarati", "alias", "[\u0901-\u0903\u0905-\u0939\u093C-\u094D\u0950-\u0954\u0958-\u096F];NFD;Devanagari-InterIndic;InterIndic-Gujarati;NFC", "" },
|
||||
{ "Devanagari-Oriya", "alias", "[\u0901-\u0903\u0905-\u0939\u093C-\u094D\u0950-\u0954\u0958-\u096F];NFD;Devanagari-InterIndic;InterIndic-Oriya;NFC", "" },
|
||||
{ "Devanagari-Tamil", "alias", "[\u0901-\u0903\u0905-\u0939\u093C-\u094D\u0950-\u0954\u0958-\u096F];NFD;Devanagari-InterIndic;InterIndic-Tamil;NFC", "" },
|
||||
{ "Devanagari-Telugu", "alias", "[\u0901-\u0903\u0905-\u0939\u093C-\u094D\u0950-\u0954\u0958-\u096F];NFD;Devanagari-InterIndic;InterIndic-Telugu;NFC", "" },
|
||||
{ "Devanagari-Kannada", "alias", "[\u0901-\u0903\u0905-\u0939\u093C-\u094D\u0950-\u0954\u0958-\u096F];NFD;Devanagari-InterIndic;InterIndic-Kannada;NFC", "" },
|
||||
{ "Devanagari-Malayalam", "alias", "[\u0901-\u0903\u0905-\u0939\u093C-\u094D\u0950-\u0954\u0958-\u096F];NFD;Devanagari-InterIndic;InterIndic-Malayalam;NFC", "" },
|
||||
{ "Devanagari-Bengali", "alias", "[\u0901-\u0903\u0904\u0905-\u0939\u093C-\u094D\u0950-\u0954\u0958-\u096F];NFD;Devanagari-InterIndic;InterIndic-Bengali;NFC", "" },
|
||||
{ "Devanagari-Gurmukhi", "alias", "[\u0901-\u0903\u0904\u0905-\u0939\u093C-\u094D\u0950-\u0954\u0958-\u096F];NFD;Devanagari-InterIndic;InterIndic-Gurmukhi;NFC", "" },
|
||||
{ "Devanagari-Gujarati", "alias", "[\u0901-\u0903\u0904\u0905-\u0939\u093C-\u094D\u0950-\u0954\u0958-\u096F];NFD;Devanagari-InterIndic;InterIndic-Gujarati;NFC", "" },
|
||||
{ "Devanagari-Oriya", "alias", "[\u0901-\u0903\u0904\u0905-\u0939\u093C-\u094D\u0950-\u0954\u0958-\u096F];NFD;Devanagari-InterIndic;InterIndic-Oriya;NFC", "" },
|
||||
{ "Devanagari-Tamil", "alias", "[\u0901-\u0903\u0904\u0905-\u0939\u093C-\u094D\u0950-\u0954\u0958-\u096F];NFD;Devanagari-InterIndic;InterIndic-Tamil;NFC", "" },
|
||||
{ "Devanagari-Telugu", "alias", "[\u0901-\u0903\u0904\u0905-\u0939\u093C-\u094D\u0950-\u0954\u0958-\u096F];NFD;Devanagari-InterIndic;InterIndic-Telugu;NFC", "" },
|
||||
{ "Devanagari-Kannada", "alias", "[\u0901-\u0903\u0904\u0905-\u0939\u093C-\u094D\u0950-\u0954\u0958-\u096F];NFD;Devanagari-InterIndic;InterIndic-Kannada;NFC", "" },
|
||||
{ "Devanagari-Malayalam", "alias", "[\u0901-\u0903\u0904\u0905-\u0939\u093C-\u094D\u0950-\u0954\u0958-\u096F];NFD;Devanagari-InterIndic;InterIndic-Malayalam;NFC", "" },
|
||||
|
||||
{ "Bengali-Devanagari", "alias", "[\u0964-\u0965\u0981-\u0983\u0985-\u098C\u098F-\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09BC\u09BE-\u09C4\u09C7-\u09C8\u09CB-\u09CD\u09D7\u09DC-\u09DD\u09DF-\u09E3\u09E6-\u09FA];NFD;Bengali-InterIndic;InterIndic-Devanagari;NFC", "" },
|
||||
{ "Bengali-Gurmukhi", "alias", "[\u0964-\u0965\u0981-\u0983\u0985-\u098C\u098F-\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09BC\u09BE-\u09C4\u09C7-\u09C8\u09CB-\u09CD\u09D7\u09DC-\u09DD\u09DF-\u09E3\u09E6-\u09FA];NFD;Bengali-InterIndic;InterIndic-Gurmukhi;NFC", "" },
|
||||
{ "Bengali-Gujarati", "alias", "[\u0964-\u0965\u0981-\u0983\u0985-\u098C\u098F-\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09BC\u09BE-\u09C4\u09C7-\u09C8\u09CB-\u09CD\u09D7\u09DC-\u09DD\u09DF-\u09E3\u09E6-\u09FA];NFD;Bengali-InterIndic;InterIndic-Gujarati;NFC", "" },
|
||||
{ "Bengali-Oriya", "alias", "[\u0964-\u0965\u0981-\u0983\u0985-\u098C\u098F-\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09BC\u09BE-\u09C4\u09C7-\u09C8\u09CB-\u09CD\u09D7\u09DC-\u09DD\u09DF-\u09E3\u09E6-\u09FA];NFD;Bengali-InterIndic;InterIndic-Oriya;NFC", "" },
|
||||
{ "Bengali-Tamil", "alias", "[\u0964-\u0965\u0981-\u0983\u0985-\u098C\u098F-\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09BC\u09BE-\u09C4\u09C7-\u09C8\u09CB-\u09CD\u09D7\u09DC-\u09DD\u09DF-\u09E3\u09E6-\u09FA];NFD;Bengali-InterIndic;InterIndic-Tamil;NFC", "" },
|
||||
{ "Bengali-Telugu", "alias", "[\u0964-\u0965\u0981-\u0983\u0985-\u098C\u098F-\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09BC\u09BE-\u09C4\u09C7-\u09C8\u09CB-\u09CD\u09D7\u09DC-\u09DD\u09DF-\u09E3\u09E6-\u09FA];NFD;Bengali-InterIndic;InterIndic-Telugu;NFC", "" },
|
||||
{ "Bengali-Kannada", "alias", "[\u0964-\u0965\u0981-\u0983\u0985-\u098C\u098F-\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09BC\u09BE-\u09C4\u09C7-\u09C8\u09CB-\u09CD\u09D7\u09DC-\u09DD\u09DF-\u09E3\u09E6-\u09FA];NFD;Bengali-InterIndic;InterIndic-Kannada;NFC", "" },
|
||||
{ "Bengali-Malayalam", "alias", "[\u0964-\u0965\u0981-\u0983\u0985-\u098C\u098F-\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09BC\u09BE-\u09C4\u09C7-\u09C8\u09CB-\u09CD\u09D7\u09DC-\u09DD\u09DF-\u09E3\u09E6-\u09FA];NFD;Bengali-InterIndic;InterIndic-Malayalam;NFC", "" },
|
||||
{ "Bengali-Devanagari", "alias", "[\u0964-\u0965\u0981-\u0983\u0985-\u098C\u098F-\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09BC-\u09C4\u09C7-\u09C8\u09CB-\u09CD\u09D7\u09DC-\u09DD\u09DF-\u09E3\u09E6-\u09FA];NFD;Bengali-InterIndic;InterIndic-Devanagari;NFC", "" },
|
||||
{ "Bengali-Gurmukhi", "alias", "[\u0964-\u0965\u0981-\u0983\u0985-\u098C\u098F-\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09BC-\u09C4\u09C7-\u09C8\u09CB-\u09CD\u09D7\u09DC-\u09DD\u09DF-\u09E3\u09E6-\u09FA];NFD;Bengali-InterIndic;InterIndic-Gurmukhi;NFC", "" },
|
||||
{ "Bengali-Gujarati", "alias", "[\u0964-\u0965\u0981-\u0983\u0985-\u098C\u098F-\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09BC-\u09C4\u09C7-\u09C8\u09CB-\u09CD\u09D7\u09DC-\u09DD\u09DF-\u09E3\u09E6-\u09FA];NFD;Bengali-InterIndic;InterIndic-Gujarati;NFC", "" },
|
||||
{ "Bengali-Oriya", "alias", "[\u0964-\u0965\u0981-\u0983\u0985-\u098C\u098F-\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09BC-\u09C4\u09C7-\u09C8\u09CB-\u09CD\u09D7\u09DC-\u09DD\u09DF-\u09E3\u09E6-\u09FA];NFD;Bengali-InterIndic;InterIndic-Oriya;NFC", "" },
|
||||
{ "Bengali-Tamil", "alias", "[\u0964-\u0965\u0981-\u0983\u0985-\u098C\u098F-\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09BC-\u09C4\u09C7-\u09C8\u09CB-\u09CD\u09D7\u09DC-\u09DD\u09DF-\u09E3\u09E6-\u09FA];NFD;Bengali-InterIndic;InterIndic-Tamil;NFC", "" },
|
||||
{ "Bengali-Telugu", "alias", "[\u0964-\u0965\u0981-\u0983\u0985-\u098C\u098F-\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09BC-\u09C4\u09C7-\u09C8\u09CB-\u09CD\u09D7\u09DC-\u09DD\u09DF-\u09E3\u09E6-\u09FA];NFD;Bengali-InterIndic;InterIndic-Telugu;NFC", "" },
|
||||
{ "Bengali-Kannada", "alias", "[\u0964-\u0965\u0981-\u0983\u0985-\u098C\u098F-\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09BC-\u09C4\u09C7-\u09C8\u09CB-\u09CD\u09D7\u09DC-\u09DD\u09DF-\u09E3\u09E6-\u09FA];NFD;Bengali-InterIndic;InterIndic-Kannada;NFC", "" },
|
||||
{ "Bengali-Malayalam", "alias", "[\u0964-\u0965\u0981-\u0983\u0985-\u098C\u098F-\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09BC-\u09C4\u09C7-\u09C8\u09CB-\u09CD\u09D7\u09DC-\u09DD\u09DF-\u09E3\u09E6-\u09FA];NFD;Bengali-InterIndic;InterIndic-Malayalam;NFC", "" },
|
||||
|
||||
{ "Gurmukhi-Devanagari", "alias", "[\u0964-\u0965\u0A02\u0A05-\u0A0A\u0A0F-\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32-\u0A33\u0A35-\u0A36\u0A38-\u0A39\u0A3C\u0A3E-\u0A42\u0A47-\u0A48\u0A4B-\u0A4D\u0A59-\u0A5C\u0A5E\u0A66-\u0A74];NFD;Gurmukhi-InterIndic;InterIndic-Devanagari;NFC", "" },
|
||||
{ "Gurmukhi-Bengali", "alias", "[\u0964-\u0965\u0A02\u0A05-\u0A0A\u0A0F-\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32-\u0A33\u0A35-\u0A36\u0A38-\u0A39\u0A3C\u0A3E-\u0A42\u0A47-\u0A48\u0A4B-\u0A4D\u0A59-\u0A5C\u0A5E\u0A66-\u0A74];NFD;Gurmukhi-InterIndic;InterIndic-Bengali;NFC", "" },
|
||||
{ "Gurmukhi-Gujarati", "alias", "[\u0964-\u0965\u0A02\u0A05-\u0A0A\u0A0F-\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32-\u0A33\u0A35-\u0A36\u0A38-\u0A39\u0A3C\u0A3E-\u0A42\u0A47-\u0A48\u0A4B-\u0A4D\u0A59-\u0A5C\u0A5E\u0A66-\u0A74];NFD;Gurmukhi-InterIndic;InterIndic-Gujarati;NFC", "" },
|
||||
{ "Gurmukhi-Oriya", "alias", "[\u0964-\u0965\u0A02\u0A05-\u0A0A\u0A0F-\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32-\u0A33\u0A35-\u0A36\u0A38-\u0A39\u0A3C\u0A3E-\u0A42\u0A47-\u0A48\u0A4B-\u0A4D\u0A59-\u0A5C\u0A5E\u0A66-\u0A74];NFD;Gurmukhi-InterIndic;InterIndic-Oriya;NFC", "" },
|
||||
{ "Gurmukhi-Tamil", "alias", "[\u0964-\u0965\u0A02\u0A05-\u0A0A\u0A0F-\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32-\u0A33\u0A35-\u0A36\u0A38-\u0A39\u0A3C\u0A3E-\u0A42\u0A47-\u0A48\u0A4B-\u0A4D\u0A59-\u0A5C\u0A5E\u0A66-\u0A74];NFD;Gurmukhi-InterIndic;InterIndic-Tamil;NFC", "" },
|
||||
{ "Gurmukhi-Telugu", "alias", "[\u0964-\u0965\u0A02\u0A05-\u0A0A\u0A0F-\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32-\u0A33\u0A35-\u0A36\u0A38-\u0A39\u0A3C\u0A3E-\u0A42\u0A47-\u0A48\u0A4B-\u0A4D\u0A59-\u0A5C\u0A5E\u0A66-\u0A74];NFD;Gurmukhi-InterIndic;InterIndic-Telugu;NFC", "" },
|
||||
{ "Gurmukhi-Kannada", "alias", "[\u0964-\u0965\u0A02\u0A05-\u0A0A\u0A0F-\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32-\u0A33\u0A35-\u0A36\u0A38-\u0A39\u0A3C\u0A3E-\u0A42\u0A47-\u0A48\u0A4B-\u0A4D\u0A59-\u0A5C\u0A5E\u0A66-\u0A74];NFD;Gurmukhi-InterIndic;InterIndic-Kannada;NFC", "" },
|
||||
{ "Gurmukhi-Malayalam", "alias", "[\u0964-\u0965\u0A02\u0A05-\u0A0A\u0A0F-\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32-\u0A33\u0A35-\u0A36\u0A38-\u0A39\u0A3C\u0A3E-\u0A42\u0A47-\u0A48\u0A4B-\u0A4D\u0A59-\u0A5C\u0A5E\u0A66-\u0A74];NFD;Gurmukhi-InterIndic;InterIndic-Malayalam;NFC", "" },
|
||||
{ "Gurmukhi-Devanagari", "alias", "[\u0964-\u0965\u0A01\u0A02\u0A05-\u0A0A\u0A0F-\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32-\u0A33\u0A35-\u0A36\u0A38-\u0A39\u0A3C\u0A3E-\u0A42\u0A47-\u0A48\u0A4B-\u0A4D\u0A59-\u0A5C\u0A5E\u0A66-\u0A74];NFD;Gurmukhi-InterIndic;InterIndic-Devanagari;NFC", "" },
|
||||
{ "Gurmukhi-Bengali", "alias", "[\u0964-\u0965\u0A01\u0A02\u0A05-\u0A0A\u0A0F-\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32-\u0A33\u0A35-\u0A36\u0A38-\u0A39\u0A3C\u0A3E-\u0A42\u0A47-\u0A48\u0A4B-\u0A4D\u0A59-\u0A5C\u0A5E\u0A66-\u0A74];NFD;Gurmukhi-InterIndic;InterIndic-Bengali;NFC", "" },
|
||||
{ "Gurmukhi-Gujarati", "alias", "[\u0964-\u0965\u0A01\u0A02\u0A05-\u0A0A\u0A0F-\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32-\u0A33\u0A35-\u0A36\u0A38-\u0A39\u0A3C\u0A3E-\u0A42\u0A47-\u0A48\u0A4B-\u0A4D\u0A59-\u0A5C\u0A5E\u0A66-\u0A74];NFD;Gurmukhi-InterIndic;InterIndic-Gujarati;NFC", "" },
|
||||
{ "Gurmukhi-Oriya", "alias", "[\u0964-\u0965\u0A01\u0A02\u0A05-\u0A0A\u0A0F-\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32-\u0A33\u0A35-\u0A36\u0A38-\u0A39\u0A3C\u0A3E-\u0A42\u0A47-\u0A48\u0A4B-\u0A4D\u0A59-\u0A5C\u0A5E\u0A66-\u0A74];NFD;Gurmukhi-InterIndic;InterIndic-Oriya;NFC", "" },
|
||||
{ "Gurmukhi-Tamil", "alias", "[\u0964-\u0965\u0A01\u0A02\u0A05-\u0A0A\u0A0F-\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32-\u0A33\u0A35-\u0A36\u0A38-\u0A39\u0A3C\u0A3E-\u0A42\u0A47-\u0A48\u0A4B-\u0A4D\u0A59-\u0A5C\u0A5E\u0A66-\u0A74];NFD;Gurmukhi-InterIndic;InterIndic-Tamil;NFC", "" },
|
||||
{ "Gurmukhi-Telugu", "alias", "[\u0964-\u0965\u0A01\u0A02\u0A05-\u0A0A\u0A0F-\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32-\u0A33\u0A35-\u0A36\u0A38-\u0A39\u0A3C\u0A3E-\u0A42\u0A47-\u0A48\u0A4B-\u0A4D\u0A59-\u0A5C\u0A5E\u0A66-\u0A74];NFD;Gurmukhi-InterIndic;InterIndic-Telugu;NFC", "" },
|
||||
{ "Gurmukhi-Kannada", "alias", "[\u0964-\u0965\u0A01\u0A02\u0A05-\u0A0A\u0A0F-\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32-\u0A33\u0A35-\u0A36\u0A38-\u0A39\u0A3C\u0A3E-\u0A42\u0A47-\u0A48\u0A4B-\u0A4D\u0A59-\u0A5C\u0A5E\u0A66-\u0A74];NFD;Gurmukhi-InterIndic;InterIndic-Kannada;NFC", "" },
|
||||
{ "Gurmukhi-Malayalam", "alias", "[\u0964-\u0965\u0A01\u0A02\u0A05-\u0A0A\u0A0F-\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32-\u0A33\u0A35-\u0A36\u0A38-\u0A39\u0A3C\u0A3E-\u0A42\u0A47-\u0A48\u0A4B-\u0A4D\u0A59-\u0A5C\u0A5E\u0A66-\u0A74];NFD;Gurmukhi-InterIndic;InterIndic-Malayalam;NFC", "" },
|
||||
|
||||
{ "Gujarati-Devanagari", "alias", "[\u0964-\u0965\u0A81-\u0A83\u0A85-\u0A8B\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2-\u0AB3\u0AB5-\u0AB9\u0ABC-\u0AC5\u0AC7-\u0AC9\u0ACB-\u0ACD\u0AD0\u0AE0\u0AE6-\u0AEF];NFD;Gujarati-InterIndic;InterIndic-Devanagari;NFC", "" },
|
||||
{ "Gujarati-Bengali", "alias", "[\u0964-\u0965\u0A81-\u0A83\u0A85-\u0A8B\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2-\u0AB3\u0AB5-\u0AB9\u0ABC-\u0AC5\u0AC7-\u0AC9\u0ACB-\u0ACD\u0AD0\u0AE0\u0AE6-\u0AEF];NFD;Gujarati-InterIndic;InterIndic-Bengali;NFC", "" },
|
||||
{ "Gujarati-Gurmukhi", "alias", "[\u0964-\u0965\u0A81-\u0A83\u0A85-\u0A8B\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2-\u0AB3\u0AB5-\u0AB9\u0ABC-\u0AC5\u0AC7-\u0AC9\u0ACB-\u0ACD\u0AD0\u0AE0\u0AE6-\u0AEF];NFD;Gujarati-InterIndic;InterIndic-Gurmukhi;NFC", "" },
|
||||
{ "Gujarati-Oriya", "alias", "[\u0964-\u0965\u0A81-\u0A83\u0A85-\u0A8B\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2-\u0AB3\u0AB5-\u0AB9\u0ABC-\u0AC5\u0AC7-\u0AC9\u0ACB-\u0ACD\u0AD0\u0AE0\u0AE6-\u0AEF];NFD;Gujarati-InterIndic;InterIndic-Oriya;NFC", "" },
|
||||
{ "Gujarati-Tamil", "alias", "[\u0964-\u0965\u0A81-\u0A83\u0A85-\u0A8B\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2-\u0AB3\u0AB5-\u0AB9\u0ABC-\u0AC5\u0AC7-\u0AC9\u0ACB-\u0ACD\u0AD0\u0AE0\u0AE6-\u0AEF];NFD;Gujarati-InterIndic;InterIndic-Tamil;NFC", "" },
|
||||
{ "Gujarati-Telugu", "alias", "[\u0964-\u0965\u0A81-\u0A83\u0A85-\u0A8B\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2-\u0AB3\u0AB5-\u0AB9\u0ABC-\u0AC5\u0AC7-\u0AC9\u0ACB-\u0ACD\u0AD0\u0AE0\u0AE6-\u0AEF];NFD;Gujarati-InterIndic;InterIndic-Telugu;NFC", "" },
|
||||
{ "Gujarati-Kannada", "alias", "[\u0964-\u0965\u0A81-\u0A83\u0A85-\u0A8B\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2-\u0AB3\u0AB5-\u0AB9\u0ABC-\u0AC5\u0AC7-\u0AC9\u0ACB-\u0ACD\u0AD0\u0AE0\u0AE6-\u0AEF];NFD;Gujarati-InterIndic;InterIndic-Kannada;NFC", "" },
|
||||
{ "Gujarati-Malayalam", "alias", "[\u0964-\u0965\u0A81-\u0A83\u0A85-\u0A8B\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2-\u0AB3\u0AB5-\u0AB9\u0ABC-\u0AC5\u0AC7-\u0AC9\u0ACB-\u0ACD\u0AD0\u0AE0\u0AE6-\u0AEF];NFD;Gujarati-InterIndic;InterIndic-Malayalam;NFC", "" },
|
||||
{ "Gujarati-Devanagari", "alias", "[\u0964-\u0965\u0A81-\u0A83\u0A85-\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2-\u0AB3\u0AB5-\u0AB9\u0ABC-\u0AC5\u0AC7-\u0AC9\u0ACB-\u0ACD\u0AD0\u0AE0\u0AE1\u0AE6-\u0AEF];NFD;Gujarati-InterIndic;InterIndic-Devanagari;NFC", "" },
|
||||
{ "Gujarati-Bengali", "alias", "[\u0964-\u0965\u0A81-\u0A83\u0A85-\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2-\u0AB3\u0AB5-\u0AB9\u0ABC-\u0AC5\u0AC7-\u0AC9\u0ACB-\u0ACD\u0AD0\u0AE0\u0AE1\u0AE6-\u0AEF];NFD;Gujarati-InterIndic;InterIndic-Bengali;NFC", "" },
|
||||
{ "Gujarati-Gurmukhi", "alias", "[\u0964-\u0965\u0A81-\u0A83\u0A85-\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2-\u0AB3\u0AB5-\u0AB9\u0ABC-\u0AC5\u0AC7-\u0AC9\u0ACB-\u0ACD\u0AD0\u0AE0\u0AE1\u0AE6-\u0AEF];NFD;Gujarati-InterIndic;InterIndic-Gurmukhi;NFC", "" },
|
||||
{ "Gujarati-Oriya", "alias", "[\u0964-\u0965\u0A81-\u0A83\u0A85-\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2-\u0AB3\u0AB5-\u0AB9\u0ABC-\u0AC5\u0AC7-\u0AC9\u0ACB-\u0ACD\u0AD0\u0AE0\u0AE1\u0AE6-\u0AEF];NFD;Gujarati-InterIndic;InterIndic-Oriya;NFC", "" },
|
||||
{ "Gujarati-Tamil", "alias", "[\u0964-\u0965\u0A81-\u0A83\u0A85-\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2-\u0AB3\u0AB5-\u0AB9\u0ABC-\u0AC5\u0AC7-\u0AC9\u0ACB-\u0ACD\u0AD0\u0AE0\u0AE1\u0AE6-\u0AEF];NFD;Gujarati-InterIndic;InterIndic-Tamil;NFC", "" },
|
||||
{ "Gujarati-Telugu", "alias", "[\u0964-\u0965\u0A81-\u0A83\u0A85-\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2-\u0AB3\u0AB5-\u0AB9\u0ABC-\u0AC5\u0AC7-\u0AC9\u0ACB-\u0ACD\u0AD0\u0AE0\u0AE1\u0AE6-\u0AEF];NFD;Gujarati-InterIndic;InterIndic-Telugu;NFC", "" },
|
||||
{ "Gujarati-Kannada", "alias", "[\u0964-\u0965\u0A81-\u0A83\u0A85-\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2-\u0AB3\u0AB5-\u0AB9\u0ABC-\u0AC5\u0AC7-\u0AC9\u0ACB-\u0ACD\u0AD0\u0AE0\u0AE1\u0AE6-\u0AEF];NFD;Gujarati-InterIndic;InterIndic-Kannada;NFC", "" },
|
||||
{ "Gujarati-Malayalam", "alias", "[\u0964-\u0965\u0A81-\u0A83\u0A85-\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2-\u0AB3\u0AB5-\u0AB9\u0ABC-\u0AC5\u0AC7-\u0AC9\u0ACB-\u0ACD\u0AD0\u0AE0\u0AE1\u0AE6-\u0AEF];NFD;Gujarati-InterIndic;InterIndic-Malayalam;NFC", "" },
|
||||
|
||||
{ "Oriya-Devanagari", "alias", "[\u0B01-\u0B03\u0B05-\u0B0C\u0B0F-\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32-\u0B33\u0B36-\u0B39\u0B3C-\u0B43\u0B47-\u0B48\u0B4B-\u0B4D\u0B56-\u0B57\u0B5C-\u0B5D\u0B5F-\u0B61\u0B66-\u0B70];NFD;Oriya-InterIndic;InterIndic-Devanagari;NFC", "" },
|
||||
{ "Oriya-Bengali", "alias", "[\u0B01-\u0B03\u0B05-\u0B0C\u0B0F-\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32-\u0B33\u0B36-\u0B39\u0B3C-\u0B43\u0B47-\u0B48\u0B4B-\u0B4D\u0B56-\u0B57\u0B5C-\u0B5D\u0B5F-\u0B61\u0B66-\u0B70];NFD;Oriya-InterIndic;InterIndic-Bengali;NFC", "" },
|
||||
{ "Oriya-Gurmukhi", "alias", "[\u0B01-\u0B03\u0B05-\u0B0C\u0B0F-\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32-\u0B33\u0B36-\u0B39\u0B3C-\u0B43\u0B47-\u0B48\u0B4B-\u0B4D\u0B56-\u0B57\u0B5C-\u0B5D\u0B5F-\u0B61\u0B66-\u0B70];NFD;Oriya-InterIndic;InterIndic-Gurmukhi;NFC", "" },
|
||||
{ "Oriya-Gujarati", "alias", "[\u0B01-\u0B03\u0B05-\u0B0C\u0B0F-\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32-\u0B33\u0B36-\u0B39\u0B3C-\u0B43\u0B47-\u0B48\u0B4B-\u0B4D\u0B56-\u0B57\u0B5C-\u0B5D\u0B5F-\u0B61\u0B66-\u0B70];NFD;Oriya-InterIndic;InterIndic-Gujarati;NFC", "" },
|
||||
{ "Oriya-Tamil", "alias", "[\u0B01-\u0B03\u0B05-\u0B0C\u0B0F-\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32-\u0B33\u0B36-\u0B39\u0B3C-\u0B43\u0B47-\u0B48\u0B4B-\u0B4D\u0B56-\u0B57\u0B5C-\u0B5D\u0B5F-\u0B61\u0B66-\u0B70];NFD;Oriya-InterIndic;InterIndic-Tamil;NFC", "" },
|
||||
{ "Oriya-Telugu", "alias", "[\u0B01-\u0B03\u0B05-\u0B0C\u0B0F-\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32-\u0B33\u0B36-\u0B39\u0B3C-\u0B43\u0B47-\u0B48\u0B4B-\u0B4D\u0B56-\u0B57\u0B5C-\u0B5D\u0B5F-\u0B61\u0B66-\u0B70];NFD;Oriya-InterIndic;InterIndic-Telugu;NFC", "" },
|
||||
{ "Oriya-Kannada", "alias", "[\u0B01-\u0B03\u0B05-\u0B0C\u0B0F-\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32-\u0B33\u0B36-\u0B39\u0B3C-\u0B43\u0B47-\u0B48\u0B4B-\u0B4D\u0B56-\u0B57\u0B5C-\u0B5D\u0B5F-\u0B61\u0B66-\u0B70];NFD;Oriya-InterIndic;InterIndic-Kannada;NFC", "" },
|
||||
{ "Oriya-Malayalam", "alias", "[\u0B01-\u0B03\u0B05-\u0B0C\u0B0F-\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32-\u0B33\u0B36-\u0B39\u0B3C-\u0B43\u0B47-\u0B48\u0B4B-\u0B4D\u0B56-\u0B57\u0B5C-\u0B5D\u0B5F-\u0B61\u0B66-\u0B70];NFD;Oriya-InterIndic;InterIndic-Malayalam;NFC", "" },
|
||||
{ "Oriya-Devanagari", "alias", "[\u0B01-\u0B03\u0B05-\u0B0C\u0B0F-\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32-\u0B33\u0B35-\u0B39\u0B3C-\u0B43\u0B47-\u0B48\u0B4B-\u0B4D\u0B56-\u0B57\u0B5C-\u0B5D\u0B5F-\u0B61\u0B66-\u0B71];NFD;Oriya-InterIndic;InterIndic-Devanagari;NFC", "" },
|
||||
{ "Oriya-Bengali", "alias", "[\u0B01-\u0B03\u0B05-\u0B0C\u0B0F-\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32-\u0B33\u0B35-\u0B39\u0B3C-\u0B43\u0B47-\u0B48\u0B4B-\u0B4D\u0B56-\u0B57\u0B5C-\u0B5D\u0B5F-\u0B61\u0B66-\u0B71];NFD;Oriya-InterIndic;InterIndic-Bengali;NFC", "" },
|
||||
{ "Oriya-Gurmukhi", "alias", "[\u0B01-\u0B03\u0B05-\u0B0C\u0B0F-\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32-\u0B33\u0B35-\u0B39\u0B3C-\u0B43\u0B47-\u0B48\u0B4B-\u0B4D\u0B56-\u0B57\u0B5C-\u0B5D\u0B5F-\u0B61\u0B66-\u0B71];NFD;Oriya-InterIndic;InterIndic-Gurmukhi;NFC", "" },
|
||||
{ "Oriya-Gujarati", "alias", "[\u0B01-\u0B03\u0B05-\u0B0C\u0B0F-\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32-\u0B33\u0B35-\u0B39\u0B3C-\u0B43\u0B47-\u0B48\u0B4B-\u0B4D\u0B56-\u0B57\u0B5C-\u0B5D\u0B5F-\u0B61\u0B66-\u0B71];NFD;Oriya-InterIndic;InterIndic-Gujarati;NFC", "" },
|
||||
{ "Oriya-Tamil", "alias", "[\u0B01-\u0B03\u0B05-\u0B0C\u0B0F-\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32-\u0B33\u0B35-\u0B39\u0B3C-\u0B43\u0B47-\u0B48\u0B4B-\u0B4D\u0B56-\u0B57\u0B5C-\u0B5D\u0B5F-\u0B61\u0B66-\u0B71];NFD;Oriya-InterIndic;InterIndic-Tamil;NFC", "" },
|
||||
{ "Oriya-Telugu", "alias", "[\u0B01-\u0B03\u0B05-\u0B0C\u0B0F-\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32-\u0B33\u0B35-\u0B39\u0B3C-\u0B43\u0B47-\u0B48\u0B4B-\u0B4D\u0B56-\u0B57\u0B5C-\u0B5D\u0B5F-\u0B61\u0B66-\u0B71];NFD;Oriya-InterIndic;InterIndic-Telugu;NFC", "" },
|
||||
{ "Oriya-Kannada", "alias", "[\u0B01-\u0B03\u0B05-\u0B0C\u0B0F-\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32-\u0B33\u0B35-\u0B39\u0B3C-\u0B43\u0B47-\u0B48\u0B4B-\u0B4D\u0B56-\u0B57\u0B5C-\u0B5D\u0B5F-\u0B61\u0B66-\u0B71];NFD;Oriya-InterIndic;InterIndic-Kannada;NFC", "" },
|
||||
{ "Oriya-Malayalam", "alias", "[\u0B01-\u0B03\u0B05-\u0B0C\u0B0F-\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32-\u0B33\u0B35-\u0B39\u0B3C-\u0B43\u0B47-\u0B48\u0B4B-\u0B4D\u0B56-\u0B57\u0B5C-\u0B5D\u0B5F-\u0B61\u0B66-\u0B71];NFD;Oriya-InterIndic;InterIndic-Malayalam;NFC", "" },
|
||||
|
||||
{ "Tamil-Devanagari", "alias", "[0\u0B82-\u0B83\u0B85-\u0B8A\u0B8E-\u0B90\u0B92-\u0B95\u0B99-\u0B9A\u0B9C\u0B9E-\u0B9F\u0BA3-\u0BA4\u0BA8-\u0BAA\u0BAE-\u0BB5\u0BB7-\u0BB9\u0BBE-\u0BC2\u0BC6-\u0BC8\u0BCA-\u0BCD\u0BD7\u0BE7-\u0BF2];NFD;Tamil-InterIndic;InterIndic-Devanagari;NFC", "" },
|
||||
{ "Tamil-Bengali", "alias", "[0\u0B82-\u0B83\u0B85-\u0B8A\u0B8E-\u0B90\u0B92-\u0B95\u0B99-\u0B9A\u0B9C\u0B9E-\u0B9F\u0BA3-\u0BA4\u0BA8-\u0BAA\u0BAE-\u0BB5\u0BB7-\u0BB9\u0BBE-\u0BC2\u0BC6-\u0BC8\u0BCA-\u0BCD\u0BD7\u0BE7-\u0BF2];NFD;Tamil-InterIndic;InterIndic-Bengali;NFC", "" },
|
||||
|
@ -243,14 +244,14 @@ translit_index {
|
|||
{ "Telugu-Kannada", "alias", "[\u0C01-\u0C03\u0C05-\u0C0C\u0C0E-\u0C10\u0C12-\u0C28\u0C2A-\u0C33\u0C35-\u0C39\u0C3E-\u0C44\u0C46-\u0C48\u0C4A-\u0C4D\u0C55-\u0C56\u0C60-\u0C61\u0C66-\u0C6F];NFD;Telugu-InterIndic;InterIndic-Kannada;NFC", "" },
|
||||
{ "Telugu-Malayalam", "alias", "[\u0C01-\u0C03\u0C05-\u0C0C\u0C0E-\u0C10\u0C12-\u0C28\u0C2A-\u0C33\u0C35-\u0C39\u0C3E-\u0C44\u0C46-\u0C48\u0C4A-\u0C4D\u0C55-\u0C56\u0C60-\u0C61\u0C66-\u0C6F];NFD;Telugu-InterIndic;InterIndic-Malayalam;NFC", "" },
|
||||
|
||||
{ "Kannada-Devanagari", "alias", "[\u0C82-\u0C83\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CBE-\u0CC4\u0CC6-\u0CC8\u0CCA-\u0CCD\u0CD5-\u0CD6\u0CDE\u0CE0-\u0CE1\u0CE6-\u0CEF];NFD;Kannada-InterIndic;InterIndic-Devanagari;NFC", "" },
|
||||
{ "Kannada-Bengali", "alias", "[\u0C82-\u0C83\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CBE-\u0CC4\u0CC6-\u0CC8\u0CCA-\u0CCD\u0CD5-\u0CD6\u0CDE\u0CE0-\u0CE1\u0CE6-\u0CEF];NFD;Kannada-InterIndic;InterIndic-Bengali;NFC", "" },
|
||||
{ "Kannada-Gurmukhi", "alias", "[\u0C82-\u0C83\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CBE-\u0CC4\u0CC6-\u0CC8\u0CCA-\u0CCD\u0CD5-\u0CD6\u0CDE\u0CE0-\u0CE1\u0CE6-\u0CEF];NFD;Kannada-InterIndic;InterIndic-Gurmukhi;NFC", "" },
|
||||
{ "Kannada-Gujarati", "alias", "[\u0C82-\u0C83\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CBE-\u0CC4\u0CC6-\u0CC8\u0CCA-\u0CCD\u0CD5-\u0CD6\u0CDE\u0CE0-\u0CE1\u0CE6-\u0CEF];NFD;Kannada-InterIndic;InterIndic-Gujarati;NFC", "" },
|
||||
{ "Kannada-Oriya", "alias", "[\u0C82-\u0C83\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CBE-\u0CC4\u0CC6-\u0CC8\u0CCA-\u0CCD\u0CD5-\u0CD6\u0CDE\u0CE0-\u0CE1\u0CE6-\u0CEF];NFD;Kannada-InterIndic;InterIndic-Oriya;NFC", "" },
|
||||
{ "Kannada-Tamil", "alias", "[\u0C82-\u0C83\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CBE-\u0CC4\u0CC6-\u0CC8\u0CCA-\u0CCD\u0CD5-\u0CD6\u0CDE\u0CE0-\u0CE1\u0CE6-\u0CEF];NFD;Kannada-InterIndic;InterIndic-Tamil;NFC", "" },
|
||||
{ "Kannada-Telugu", "alias", "[\u0C82-\u0C83\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CBE-\u0CC4\u0CC6-\u0CC8\u0CCA-\u0CCD\u0CD5-\u0CD6\u0CDE\u0CE0-\u0CE1\u0CE6-\u0CEF];NFD;Kannada-InterIndic;InterIndic-Telugu;NFC", "" },
|
||||
{ "Kannada-Malayalam", "alias", "[\u0C82-\u0C83\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CBE-\u0CC4\u0CC6-\u0CC8\u0CCA-\u0CCD\u0CD5-\u0CD6\u0CDE\u0CE0-\u0CE1\u0CE6-\u0CEF];NFD;Kannada-InterIndic;InterIndic-Malayalam;NFC", "" },
|
||||
{ "Kannada-Devanagari", "alias", "[\u0C82-\u0C83\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CBC\u0CBD\u0CBE-\u0CC4\u0CC6-\u0CC8\u0CCA-\u0CCD\u0CD5-\u0CD6\u0CDE\u0CE0-\u0CE1\u0CE6-\u0CEF];NFD;Kannada-InterIndic;InterIndic-Devanagari;NFC", "" },
|
||||
{ "Kannada-Bengali", "alias", "[\u0C82-\u0C83\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CBC\u0CBD\u0CBE-\u0CC4\u0CC6-\u0CC8\u0CCA-\u0CCD\u0CD5-\u0CD6\u0CDE\u0CE0-\u0CE1\u0CE6-\u0CEF];NFD;Kannada-InterIndic;InterIndic-Bengali;NFC", "" },
|
||||
{ "Kannada-Gurmukhi", "alias", "[\u0C82-\u0C83\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CBC\u0CBD\u0CBE-\u0CC4\u0CC6-\u0CC8\u0CCA-\u0CCD\u0CD5-\u0CD6\u0CDE\u0CE0-\u0CE1\u0CE6-\u0CEF];NFD;Kannada-InterIndic;InterIndic-Gurmukhi;NFC", "" },
|
||||
{ "Kannada-Gujarati", "alias", "[\u0C82-\u0C83\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CBC\u0CBD\u0CBE-\u0CC4\u0CC6-\u0CC8\u0CCA-\u0CCD\u0CD5-\u0CD6\u0CDE\u0CE0-\u0CE1\u0CE6-\u0CEF];NFD;Kannada-InterIndic;InterIndic-Gujarati;NFC", "" },
|
||||
{ "Kannada-Oriya", "alias", "[\u0C82-\u0C83\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CBC\u0CBD\u0CBE-\u0CC4\u0CC6-\u0CC8\u0CCA-\u0CCD\u0CD5-\u0CD6\u0CDE\u0CE0-\u0CE1\u0CE6-\u0CEF];NFD;Kannada-InterIndic;InterIndic-Oriya;NFC", "" },
|
||||
{ "Kannada-Tamil", "alias", "[\u0C82-\u0C83\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CBC\u0CBD\u0CBE-\u0CC4\u0CC6-\u0CC8\u0CCA-\u0CCD\u0CD5-\u0CD6\u0CDE\u0CE0-\u0CE1\u0CE6-\u0CEF];NFD;Kannada-InterIndic;InterIndic-Tamil;NFC", "" },
|
||||
{ "Kannada-Telugu", "alias", "[\u0C82-\u0C83\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CBC\u0CBD\u0CBE-\u0CC4\u0CC6-\u0CC8\u0CCA-\u0CCD\u0CD5-\u0CD6\u0CDE\u0CE0-\u0CE1\u0CE6-\u0CEF];NFD;Kannada-InterIndic;InterIndic-Telugu;NFC", "" },
|
||||
{ "Kannada-Malayalam", "alias", "[\u0C82-\u0C83\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CBC\u0CBD\u0CBE-\u0CC4\u0CC6-\u0CC8\u0CCA-\u0CCD\u0CD5-\u0CD6\u0CDE\u0CE0-\u0CE1\u0CE6-\u0CEF];NFD;Kannada-InterIndic;InterIndic-Malayalam;NFC", "" },
|
||||
|
||||
{ "Malayalam-Devanagari", "alias", "[\u0D02-\u0D03\u0D05-\u0D0C\u0D0E-\u0D10\u0D12-\u0D28\u0D2A-\u0D39\u0D3E-\u0D43\u0D46-\u0D48\u0D4A-\u0D4D\u0D57\u0D60-\u0D61\u0D66-\u0D6F];NFD;Malayalam-InterIndic;InterIndic-Devanagari;NFC", "" },
|
||||
{ "Malayalam-Bengali", "alias", "[\u0D02-\u0D03\u0D05-\u0D0C\u0D0E-\u0D10\u0D12-\u0D28\u0D2A-\u0D39\u0D3E-\u0D43\u0D46-\u0D48\u0D4A-\u0D4D\u0D57\u0D60-\u0D61\u0D66-\u0D6F];NFD;Malayalam-InterIndic;InterIndic-Bengali;NFC", "" },
|
||||
|
|
|
@ -66,6 +66,8 @@ TransliteratorRoundTripTest::runIndexedTest(int32_t index, UBool exec,
|
|||
CASE(7,Testel);
|
||||
CASE(8,TestDevanagariLatin);
|
||||
CASE(9,TestInterIndic);
|
||||
CASE(10, TestHebrew);
|
||||
CASE(11, TestArabic);
|
||||
default: name = ""; break;
|
||||
}
|
||||
}
|
||||
|
@ -1114,6 +1116,63 @@ void TransliteratorRoundTripTest::Testel() {
|
|||
delete legal;
|
||||
}
|
||||
|
||||
|
||||
void TransliteratorRoundTripTest::TestArabic() {
|
||||
/*
|
||||
UnicodeString ARABIC("[\\u060C\\u061B\\u061F\\u0621\\u0627-\\u063A\\u0641-\\u0655\\u0660-\\u066C\\u067E\\u0686\\u0698\\u06A4\\u06AD\\u06AF\\u06CB-\\u06CC\\u06F0-\\u06F9]");
|
||||
//long start = System.currentTimeMillis();
|
||||
Legal *legal = new Legal();
|
||||
RTTest test("Latin-Arabic");
|
||||
test.test("[a-zA-Z\\u02BE\\u02BF]", ARABIC, "[a-zA-Z\\u02BE\\u02BF\\u207F]",this, quick, legal); //
|
||||
//showElapsed(start, "TestArabic");
|
||||
delete legal;
|
||||
*/
|
||||
infoln("TestArabic comented out due to failures.");
|
||||
}
|
||||
class LegalHebrew : public Legal {
|
||||
private:
|
||||
UnicodeSet FINAL;
|
||||
UnicodeSet NON_FINAL;
|
||||
UnicodeSet LETTER;
|
||||
public:
|
||||
LegalHebrew(UErrorCode& error);
|
||||
virtual ~LegalHebrew() {}
|
||||
virtual UBool is(const UnicodeString& sourceString) const;
|
||||
};
|
||||
|
||||
LegalHebrew::LegalHebrew(UErrorCode& error){
|
||||
FINAL.applyPattern("[\\u05DA\\u05DD\\u05DF\\u05E3\\u05E5]", error);
|
||||
NON_FINAL.applyPattern("[\\u05DB\\u05DE\\u05E0\\u05E4\\u05E6]", error);
|
||||
LETTER.applyPattern("[:letter:]", error);
|
||||
}
|
||||
UBool LegalHebrew::is(const UnicodeString& sourceString)const{
|
||||
|
||||
if (sourceString.length() == 0) return TRUE;
|
||||
// don't worry about surrogates.
|
||||
for (int i = 0; i < sourceString.length(); ++i) {
|
||||
UChar ch = sourceString.charAt(i);
|
||||
UChar next = i+1 == sourceString.length() ? 0x0000 : sourceString.charAt(i);
|
||||
if (FINAL.contains(ch)) {
|
||||
if (LETTER.contains(next)) return FALSE;
|
||||
} else if (NON_FINAL.contains(ch)) {
|
||||
if (!LETTER.contains(next)) return FALSE;
|
||||
}
|
||||
}
|
||||
return TRUE;
|
||||
}
|
||||
void TransliteratorRoundTripTest::TestHebrew() {
|
||||
//long start = System.currentTimeMillis();
|
||||
UErrorCode error = U_ZERO_ERROR;
|
||||
LegalHebrew* legal = new LegalHebrew(error);
|
||||
if(U_FAILURE(error)){
|
||||
errln("Could not construct LegalHebrew object. Error: %s", u_errorName(error));
|
||||
return;
|
||||
}
|
||||
RTTest test("Latin-Hebrew");
|
||||
test.test("[a-zA-Z\\u02BC\\u02BB]", "[[:hebrew:]-[\\u05BD\\uFB00-\\uFBFF]]", "[\\u05F0\\u05F1\\u05F2]", this, quick, legal);
|
||||
//showElapsed(start, "TestHebrew");
|
||||
delete legal;
|
||||
}
|
||||
void TransliteratorRoundTripTest::TestCyrillic() {
|
||||
RTTest test("Latin-Cyrillic");
|
||||
Legal *legal = new Legal();
|
||||
|
@ -1138,7 +1197,7 @@ class LegalIndic :public Legal{
|
|||
public:
|
||||
LegalIndic(){
|
||||
UErrorCode status = U_ZERO_ERROR;
|
||||
vowelSignSet.addAll( UnicodeSet("[\\u0902\\u0903\\u093e-\\u094c\\u0962\\u0963]",status));/* Devanagari */
|
||||
vowelSignSet.addAll( UnicodeSet("[\\u0902\\u0903\\u0904\\u093e-\\u094c\\u0962\\u0963]",status));/* Devanagari */
|
||||
vowelSignSet.addAll( UnicodeSet("[\\u0982\\u0983\\u09be-\\u09cc\\u09e2\\u09e3\\u09D7]",status));/* Bengali */
|
||||
vowelSignSet.addAll( UnicodeSet("[\\u0a02\\u0a03\\u0a3e-\\u0a4c\\u0a62\\u0a63\\u0a70\\u0a71]",status));/* Gurmukhi */
|
||||
vowelSignSet.addAll( UnicodeSet("[\\u0a82\\u0a83\\u0abe-\\u0acc\\u0ae2\\u0ae3]",status));/* Gujarati */
|
||||
|
@ -1148,8 +1207,8 @@ public:
|
|||
vowelSignSet.addAll( UnicodeSet("[\\u0c82\\u0c83\\u0cbe-\\u0ccc\\u0ce2\\u0ce3\\u0cd5\\u0cd6]",status));/* Kannada */
|
||||
vowelSignSet.addAll( UnicodeSet("[\\u0d02\\u0d03\\u0d3e-\\u0d4c\\u0d62\\u0d63\\u0d57]",status));/* Malayalam */
|
||||
|
||||
avagraha.addAll(UnicodeSet("[\\u093d\\u0abd\\u0b3d]",status));
|
||||
nukta.addAll(UnicodeSet("[\\u093c\\u09bc\\u0a3c\\u0abc\\u0b3c]",status));
|
||||
avagraha.addAll(UnicodeSet("[\\u093d\\u09bd\\u0abd\\u0b3d\\u0cbd]",status));
|
||||
nukta.addAll(UnicodeSet("[\\u093c\\u09bc\\u0a3c\\u0abc\\u0b3c\\u0cbc]",status));
|
||||
virama.addAll(UnicodeSet("[\\u094d\\u09cd\\u0a4d\\u0acd\\u0b4d\\u0bcd\\u0c4d\\u0ccd\\u0d4d]",status));
|
||||
sanskritStressSigns.addAll(UnicodeSet("[\\u0951\\u0952\\u0953\\u0954]",status));
|
||||
chandrabindu.addAll(UnicodeSet("[\\u0901\\u0981\\u0A81\\u0b01\\u0c01]",status));
|
||||
|
@ -1216,16 +1275,9 @@ void TransliteratorRoundTripTest::TestDevanagariLatin() {
|
|||
RTTest test("Latin-Devanagari");
|
||||
Legal *legal = new LegalIndic();
|
||||
|
||||
if (isICUVersionAtLeast(ICU_30)) {
|
||||
infoln("Warning: TestDevanagariLatin needs to be updated to remove Unicode 3.2 filter");
|
||||
// We temporarily filter against Unicode 3.2, but we only do this
|
||||
// before version 3.0.
|
||||
test.test(UnicodeString(latinForIndic, ""),
|
||||
UnicodeString("[[:Devanagari:]&[:Age=3.2:]]", ""), NULL, this, quick,
|
||||
legal, 50);
|
||||
} else {
|
||||
logln("Warning: TestDevanagariLatin needs to be updated to remove Unicode 3.2 filter");
|
||||
}
|
||||
test.test(UnicodeString(latinForIndic, ""),
|
||||
UnicodeString("[[:Devanagari:][\\u094d][\\u0964\\u0965]]", ""), "[\\u0965\\u0904]", this, quick,
|
||||
legal, 50);
|
||||
|
||||
delete legal;
|
||||
}
|
||||
|
@ -1234,16 +1286,16 @@ void TransliteratorRoundTripTest::TestDevanagariLatin() {
|
|||
static const int32_t INTER_INDIC_ARRAY_WIDTH = 4;
|
||||
static const char * const interIndicArray[] = {
|
||||
"BENGALI-DEVANAGARI", "[:BENGALI:]", "[:Devanagari:]",
|
||||
"[\\u0951-\\u0954\\u0943-\\u0949\\u094a\\u0962\\u0963\\u090D\\u090e\\u0911\\u0912\\u0929\\u0933\\u0934\\u0935\\u093d\\u0950\\u0958\\u0959\\u095a\\u095b\\u095e\\u09f0\\u09f1]", /*roundtrip exclusions*/
|
||||
"[\\u0904\\u0951-\\u0954\\u0943-\\u0949\\u094a\\u0962\\u0963\\u090D\\u090e\\u0911\\u0912\\u0929\\u0933\\u0934\\u0935\\u093d\\u0950\\u0958\\u0959\\u095a\\u095b\\u095e\\u09f0\\u09f1\\u09f2-\\u09fa]", /*roundtrip exclusions*/
|
||||
|
||||
"DEVANAGARI-BENGALI", "[:Devanagari:]", "[:BENGALI:]",
|
||||
"[\\u0951-\\u0954\\u09D7\\u090D\\u090e\\u0911\\u0912\\u0929\\u0933\\u0934\\u0935\\u093d\\u0950\\u0958\\u0959\\u095a\\u095b\\u095e\\u09f0\\u09f1]", /*roundtrip exclusions*/
|
||||
"[\\u0951-\\u0954\\u0951-\\u0954\\u09D7\\u090D\\u090e\\u0911\\u0912\\u0929\\u0933\\u0934\\u0935\\u093d\\u0950\\u0958\\u0959\\u095a\\u095b\\u095e\\u09f0\\u09f1\\u09f2-\\u09fa]", /*roundtrip exclusions*/
|
||||
|
||||
"GURMUKHI-DEVANAGARI", "[:GURMUKHI:]", "[:Devanagari:]",
|
||||
"[\\u0901\\u0902\\u0936\\u0933\\u0951-\\u0954\\u0902\\u0903\\u0943-\\u0949\\u094a\\u0962\\u0963\\u090B\\u090C\\u090D\\u090e\\u0911\\u0912\\u0934\\u0937\\u093D\\u0950\\u0960\\u0961\\u0a72\\u0a73\\u0a74]", /*roundtrip exclusions*/
|
||||
"[\\u0904\\u0901\\u0902\\u0936\\u0933\\u0951-\\u0954\\u0902\\u0903\\u0943-\\u0949\\u094a\\u0962\\u0963\\u090B\\u090C\\u090D\\u090e\\u0911\\u0912\\u0934\\u0937\\u093D\\u0950\\u0960\\u0961\\u0a72\\u0a73\\u0a74]", /*roundtrip exclusions*/
|
||||
|
||||
"DEVANAGARI-GURMUKHI", "[:Devanagari:]", "[:GURMUKHI:]",
|
||||
"[\\u0A02\\u0946\\u0A5C\\u0951-\\u0954\\u0A70\\u0A71\\u090B\\u090C\\u090D\\u090e\\u0911\\u0912\\u0934\\u0937\\u093D\\u0950\\u0960\\u0961\\u0a72\\u0a73\\u0a74]", /*roundtrip exclusions*/
|
||||
"[\\u0904\\u0A02\\u0946\\u0A5C\\u0951-\\u0954\\u0A70\\u0A71\\u090B\\u090C\\u090D\\u090e\\u0911\\u0912\\u0934\\u0937\\u093D\\u0950\\u0960\\u0961\\u0a72\\u0a73\\u0a74]", /*roundtrip exclusions*/
|
||||
|
||||
"GUJARATI-DEVANAGARI", "[:GUJARATI:]", "[:Devanagari:]",
|
||||
"[\\u0946\\u094A\\u0962\\u0963\\u0951-\\u0954\\u0961\\u090c\\u090e\\u0912]", /*roundtrip exclusions*/
|
||||
|
@ -1252,73 +1304,73 @@ static const char * const interIndicArray[] = {
|
|||
"[\\u0951-\\u0954\\u0961\\u090c\\u090e\\u0912]", /*roundtrip exclusions*/
|
||||
|
||||
"ORIYA-DEVANAGARI", "[:ORIYA:]", "[:Devanagari:]",
|
||||
"[\\u0943-\\u094a\\u0962\\u0963\\u0951-\\u0954\\u0950\\u090D\\u090e\\u0912\\u0911\\u0931\\u0935]", /*roundtrip exclusions*/
|
||||
"[\\u0904\\u0943-\\u094a\\u0962\\u0963\\u0951-\\u0954\\u0950\\u090D\\u090e\\u0912\\u0911\\u0931\\u0935]", /*roundtrip exclusions*/
|
||||
|
||||
"DEVANAGARI-ORIYA", "[:Devanagari:]", "[:ORIYA:]",
|
||||
"[\\u0b5f\\u0b56\\u0b57\\u0950\\u090D\\u090e\\u0912\\u0911\\u0931\\u0935]", /*roundtrip exclusions*/
|
||||
"[\\u0b5f\\u0b56\\u0b57\\u0b70\\u0b71\\u0950\\u090D\\u090e\\u0912\\u0911\\u0931]", /*roundtrip exclusions*/
|
||||
|
||||
"Tamil-DEVANAGARI", "[:tamil:]", "[:Devanagari:]",
|
||||
"[\\u0901\\u093c\\u0943-\\u094a\\u0951-\\u0954\\u0962\\u0963\\u090B\\u090C\\u090D\\u0911\\u0916\\u0917\\u0918\\u091B\\u091D\\u0920\\u0921\\u0922\\u0925\\u0926\\u0927\\u092B\\u092C\\u092D\\u0936\\u093d\\u0950[\\u0958-\\u0961]]", /*roundtrip exclusions*/
|
||||
"[\\u0901\\u0904\\u093c\\u0943-\\u094a\\u0951-\\u0954\\u0962\\u0963\\u090B\\u090C\\u090D\\u0911\\u0916\\u0917\\u0918\\u091B\\u091D\\u0920\\u0921\\u0922\\u0925\\u0926\\u0927\\u092B\\u092C\\u092D\\u0936\\u093d\\u0950[\\u0958-\\u0961]]", /*roundtrip exclusions*/
|
||||
|
||||
"DEVANAGARI-Tamil", "[:Devanagari:]", "[:tamil:]",
|
||||
"[\\u0bd7]", /*roundtrip exclusions*/
|
||||
|
||||
"Telugu-DEVANAGARI", "[:telugu:]", "[:Devanagari:]",
|
||||
"[\\u093c\\u0950\\u0945\\u0949\\u0951-\\u0954\\u0962\\u0963\\u090D\\u0911\\u093d\\u0929\\u0934[\\u0958-\\u095f]]", /*roundtrip exclusions*/
|
||||
"[\\u0904\\u093c\\u0950\\u0945\\u0949\\u0951-\\u0954\\u0962\\u0963\\u090D\\u0911\\u093d\\u0929\\u0934[\\u0958-\\u095f]]", /*roundtrip exclusions*/
|
||||
|
||||
"DEVANAGARI-TELUGU", "[:Devanagari:]", "[:TELUGU:]",
|
||||
"[\\u0c55\\u0c56\\u0950\\u090D\\u0911\\u093d\\u0929\\u0934[\\u0958-\\u095f]]", /*roundtrip exclusions*/
|
||||
|
||||
"KANNADA-DEVANAGARI", "[:KANNADA:]", "[:Devanagari:]",
|
||||
"[\\u0901\\u0946\\u093c\\u0950\\u0945\\u0949\\u0951-\\u0954\\u0962\\u0963\\u0950\\u090D\\u0911\\u093d\\u0929\\u0934[\\u0958-\\u095f]]", /*roundtrip exclusions*/
|
||||
"[\\u0901\\u0904\\u0946\\u093c\\u0950\\u0945\\u0949\\u0951-\\u0954\\u0962\\u0963\\u0950\\u090D\\u0911\\u093d\\u0929\\u0934[\\u0958-\\u095f]]", /*roundtrip exclusions*/
|
||||
|
||||
"DEVANAGARI-KANNADA", "[:Devanagari:]", "[:KANNADA:]",
|
||||
"[\\u0cde\\u0cd5\\u0cd6\\u0950\\u090D\\u0911\\u093d\\u0929\\u0934[\\u0958-\\u095f]]", /*roundtrip exclusions*/
|
||||
"[{\\u0cb0\\u0cbc}{\\u0cb3\\u0cbc}\\u0cde\\u0cd5\\u0cd6\\u0950\\u090D\\u0911\\u093d\\u0929\\u0934[\\u0958-\\u095f]]", /*roundtrip exclusions*/
|
||||
|
||||
"MALAYALAM-DEVANAGARI", "[:MALAYALAM:]", "[:Devanagari:]",
|
||||
"[\\u0901\\u094a\\u094b\\u094c\\u093c\\u0950\\u0944\\u0945\\u0949\\u0951-\\u0954\\u0962\\u0963\\u090D\\u0911\\u093d\\u0929\\u0934[\\u0958-\\u095f]]", /*roundtrip exclusions*/
|
||||
"[\\u0901\\u0904\\u094a\\u094b\\u094c\\u093c\\u0950\\u0944\\u0945\\u0949\\u0951-\\u0954\\u0962\\u0963\\u090D\\u0911\\u093d\\u0929\\u0934[\\u0958-\\u095f]]", /*roundtrip exclusions*/
|
||||
|
||||
"DEVANAGARI-MALAYALAM", "[:Devanagari:]", "[:MALAYALAM:]",
|
||||
"[\\u0d4c\\u0d57\\u0950\\u090D\\u0911\\u093d\\u0929\\u0934[\\u0958-\\u095f]]", /*roundtrip exclusions*/
|
||||
|
||||
"GURMUKHI-BENGALI", "[:GURMUKHI:]", "[:BENGALI:]",
|
||||
"[\\u0981\\u0982\\u09b6\\u09e2\\u09e3\\u09c3\\u09c4\\u09d7\\u098B\\u098C\\u09B7\\u09E0\\u09E1\\u09F0\\u09F1]", /*roundtrip exclusions*/
|
||||
"[\\u0981\\u0982\\u09b6\\u09e2\\u09e3\\u09c3\\u09c4\\u09d7\\u098B\\u098C\\u09B7\\u09E0\\u09E1\\u09F0\\u09F1\\u09f2-\\u09fa]", /*roundtrip exclusions*/
|
||||
|
||||
"BENGALI-GURMUKHI", "[:BENGALI:]", "[:GURMUKHI:]",
|
||||
"[\\u0A02\\u0a5c\\u0a47\\u0a70\\u0a71\\u0A33\\u0A35\\u0A59\\u0A5A\\u0A5B\\u0A5E\\u0A72\\u0A73\\u0A74]", /*roundtrip exclusions*/
|
||||
|
||||
"GUJARATI-BENGALI", "[:GUJARATI:]", "[:BENGALI:]",
|
||||
"[\\u09d7\\u09e2\\u09e3\\u098c\\u09e1\\u09f0\\u09f1]", /*roundtrip exclusions*/
|
||||
"[\\u09d7\\u09e2\\u09e3\\u098c\\u09e1\\u09f0\\u09f1\\u09f2-\\u09fa]", /*roundtrip exclusions*/
|
||||
|
||||
"BENGALI-GUJARATI", "[:BENGALI:]", "[:GUJARATI:]",
|
||||
"[\\u0A82\\u0a83\\u0Ac9\\u0Ac5\\u0ac7\\u0A8D\\u0A91\\u0AB3\\u0AB5\\u0ABD\\u0AD0]", /*roundtrip exclusions*/
|
||||
|
||||
"ORIYA-BENGALI", "[:ORIYA:]", "[:BENGALI:]",
|
||||
"[\\u09c4\\u09e2\\u09e3\\u09f0\\u09f1]", /*roundtrip exclusions*/
|
||||
"[\\u09c4\\u09e2\\u09e3\\u09f0\\u09f1\\u09f2-\\u09fa]", /*roundtrip exclusions*/
|
||||
|
||||
"BENGALI-ORIYA", "[:BENGALI:]", "[:ORIYA:]",
|
||||
"[\\u0b5f\\u0b56\\u0b33\\u0b3d]", /*roundtrip exclusions*/
|
||||
"[\\u0b35\\u0b71\\u0b5f\\u0b56\\u0b33\\u0b3d]", /*roundtrip exclusions*/
|
||||
|
||||
"Tamil-BENGALI", "[:tamil:]", "[:BENGALI:]",
|
||||
"[\\u0981\\u09bc\\u09c3\\u09c4\\u09e2\\u09e3\\u09f0\\u09f1\\u098B\\u098C\\u0996\\u0997\\u0998\\u099B\\u099D\\u09A0\\u09A1\\u09A2\\u09A5\\u09A6\\u09A7\\u09AB\\u09AC\\u09AD\\u09B6\\u09DC\\u09DD\\u09DF\\u09E0\\u09E1]", /*roundtrip exclusions*/
|
||||
"[\\u0981\\u09bc\\u09c3\\u09c4\\u09e2\\u09e3\\u09f0\\u09f1\\u098B\\u098C\\u0996\\u0997\\u0998\\u099B\\u099D\\u09A0\\u09A1\\u09A2\\u09A5\\u09A6\\u09A7\\u09AB\\u09AC\\u09AD\\u09B6\\u09DC\\u09DD\\u09DF\\u09E0\\u09E1\\u09f2-\\u09fa]", /*roundtrip exclusions*/
|
||||
|
||||
"BENGALI-Tamil", "[:BENGALI:]", "[:tamil:]",
|
||||
"[\\u0bc6\\u0bc7\\u0bca\\u0B8E\\u0B92\\u0BA9\\u0BB1\\u0BB3\\u0BB4\\u0BB5]", /*roundtrip exclusions*/
|
||||
|
||||
"Telugu-BENGALI", "[:telugu:]", "[:BENGALI:]",
|
||||
"[\\u09e2\\u09e3\\u09bc\\u09d7\\u09f0\\u09f1\\u09dc\\u09dd\\u09df]", /*roundtrip exclusions*/
|
||||
"[\\u09e2\\u09e3\\u09bc\\u09d7\\u09f0\\u09f1\\u09dc\\u09dd\\u09df\\u09f2-\\u09fa]", /*roundtrip exclusions*/
|
||||
|
||||
"BENGALI-TELUGU", "[:BENGALI:]", "[:TELUGU:]",
|
||||
"[\\u0c55\\u0c56\\u0c47\\u0c46\\u0c4a\\u0C0E\\u0C12\\u0C31\\u0C33\\u0C35]", /*roundtrip exclusions*/
|
||||
|
||||
"KANNADA-BENGALI", "[:KANNADA:]", "[:BENGALI:]",
|
||||
"[\\u0981\\u09e2\\u09e3\\u09bc\\u09d7\\u09f0\\u09f1\\u09dc\\u09dd\\u09df]", /*roundtrip exclusions*/
|
||||
"[\\u0981\\u09e2\\u09e3\\u09bc\\u09d7\\u09dc\\u09dd\\u09df\\u09f0\\u09f1\\u09f2-\\u09fa]", /*roundtrip exclusions*/
|
||||
|
||||
"BENGALI-KANNADA", "[:BENGALI:]", "[:KANNADA:]",
|
||||
"[\\u0cc6\\u0cca\\u0cd5\\u0cd6\\u0cc7\\u0C8E\\u0C92\\u0CB1\\u0cb3\\u0cb5\\u0cde]", /*roundtrip exclusions*/
|
||||
"[{\\u0cb0\\u0cbc}{\\u0cb3\\u0cbc}\\u0cc6\\u0cca\\u0cd5\\u0cd6\\u0cc7\\u0C8E\\u0C92\\u0CB1\\u0cb3\\u0cb5\\u0cde]", /*roundtrip exclusions*/
|
||||
|
||||
"MALAYALAM-BENGALI", "[:MALAYALAM:]", "[:BENGALI:]",
|
||||
"[\\u0981\\u09e2\\u09e3\\u09bc\\u09c4\\u09f0\\u09f1\\u09dc\\u09dd\\u09df]", /*roundtrip exclusions*/
|
||||
"[\\u0981\\u09e2\\u09e3\\u09bc\\u09c4\\u09f0\\u09f1\\u09dc\\u09dd\\u09df\\u09dc\\u09dd\\u09df\\u09f2-\\u09fa]", /*roundtrip exclusions*/
|
||||
|
||||
"BENGALI-MALAYALAM", "[:BENGALI:]", "[:MALAYALAM:]",
|
||||
"[\\u0d46\\u0d4a\\u0d47\\u0d31-\\u0d35\\u0d0e\\u0d12]", /*roundtrip exclusions*/
|
||||
|
@ -1327,16 +1379,16 @@ static const char * const interIndicArray[] = {
|
|||
"[\\u0A02\\u0ab3\\u0ab6\\u0A70\\u0a71\\u0a82\\u0a83\\u0ac3\\u0ac4\\u0ac5\\u0ac9\\u0a5c\\u0a72\\u0a73\\u0a74\\u0a8b\\u0a8d\\u0a91\\u0abd]", /*roundtrip exclusions*/
|
||||
|
||||
"GURMUKHI-GUJARATI", "[:GURMUKHI:]", "[:GUJARATI:]",
|
||||
"[\\u0A81\\u0A82\\u0ab3\\u0ab6\\u0A70\\u0a71\\u0a82\\u0a83\\u0ac3\\u0ac4\\u0ac5\\u0ac9\\u0a5c\\u0a72\\u0a73\\u0a74\\u0a8b\\u0a8d\\u0a91\\u0ab7\\u0abd\\u0ad0\\u0ae0]", /*roundtrip exclusions*/
|
||||
"[\\u0a5c\\u0A70\\u0a71\\u0a72\\u0a73\\u0a74\\u0a82\\u0a83\\u0a8b\\u0a8c\\u0a8d\\u0a91\\u0ab3\\u0ab6\\u0ab7\\u0abd\\u0ac3\\u0ac4\\u0ac5\\u0ac9\\u0ad0\\u0ae0\\u0ae1]", /*roundtrip exclusions*/
|
||||
|
||||
"ORIYA-GURMUKHI", "[:ORIYA:]", "[:GURMUKHI:]",
|
||||
"[\\u0A01\\u0A02\\u0a5c\\u0a21\\u0a47\\u0a71\\u0b02\\u0b03\\u0b33\\u0b36\\u0b43\\u0b56\\u0b57\\u0B0B\\u0B0C\\u0B37\\u0B3D\\u0B5F\\u0B60\\u0B61\\u0a35\\u0a72\\u0a73\\u0a74]", /*roundtrip exclusions*/
|
||||
|
||||
"GURMUKHI-ORIYA", "[:GURMUKHI:]", "[:ORIYA:]",
|
||||
"[\\u0b01\\u0b02\\u0b03\\u0b33\\u0b36\\u0b43\\u0b56\\u0b57\\u0B0B\\u0B0C\\u0B37\\u0B3D\\u0B5F\\u0B60\\u0B61]", /*roundtrip exclusions*/
|
||||
"[\\u0b01\\u0b02\\u0b03\\u0b33\\u0b36\\u0b43\\u0b56\\u0b57\\u0B0B\\u0B0C\\u0B37\\u0B3D\\u0B5F\\u0B60\\u0B61\\u0b70\\u0b71]", /*roundtrip exclusions*/
|
||||
|
||||
"TAMIL-GURMUKHI", "[:TAMIL:]", "[:GURMUKHI:]",
|
||||
"[\\u0A02\\u0a33\\u0a36\\u0a3c\\u0a70\\u0a71\\u0a47\\u0A16\\u0A17\\u0A18\\u0A1B\\u0A1D\\u0A20\\u0A21\\u0A22\\u0A25\\u0A26\\u0A27\\u0A2B\\u0A2C\\u0A2D\\u0A59\\u0A5A\\u0A5B\\u0A5C\\u0A5E\\u0A72\\u0A73\\u0A74]", /*roundtrip exclusions*/
|
||||
"[\\u0A01\\u0A02\\u0a33\\u0a36\\u0a3c\\u0a70\\u0a71\\u0a47\\u0A16\\u0A17\\u0A18\\u0A1B\\u0A1D\\u0A20\\u0A21\\u0A22\\u0A25\\u0A26\\u0A27\\u0A2B\\u0A2C\\u0A2D\\u0A59\\u0A5A\\u0A5B\\u0A5C\\u0A5E\\u0A72\\u0A73\\u0A74]", /*roundtrip exclusions*/
|
||||
|
||||
"GURMUKHI-TAMIL", "[:GURMUKHI:]", "[:TAMIL:]",
|
||||
"[\\u0b82\\u0bc6\\u0bca\\u0bd7\\u0bb7\\u0bb3\\u0b83\\u0B8E\\u0B92\\u0BA9\\u0BB1\\u0BB4]", /*roundtrip exclusions*/
|
||||
|
@ -1348,25 +1400,25 @@ static const char * const interIndicArray[] = {
|
|||
"[\\u0c01\\u0c02\\u0c03\\u0c33\\u0c36\\u0c44\\u0c43\\u0c46\\u0c4a\\u0c56\\u0c55\\u0C0B\\u0C0C\\u0C0E\\u0C12\\u0C31\\u0C37\\u0C60\\u0C61]", /*roundtrip exclusions*/
|
||||
|
||||
"KANNADA-GURMUKHI", "[:KANNADA:]", "[:GURMUKHI:]",
|
||||
"[\\u0A02\\u0a33\\u0a36\\u0a3c\\u0a70\\u0a71\\u0A59\\u0A5A\\u0A5B\\u0A5C\\u0A5E\\u0A72\\u0A73\\u0A74]", /*roundtrip exclusions*/
|
||||
"[\\u0A01\\u0A02\\u0a33\\u0a36\\u0a3c\\u0a70\\u0a71\\u0A59\\u0A5A\\u0A5B\\u0A5C\\u0A5E\\u0A72\\u0A73\\u0A74]", /*roundtrip exclusions*/
|
||||
|
||||
"GURMUKHI-KANNADA", "[:GURMUKHI:]", "[:KANNADA:]",
|
||||
"[\\u0c82\\u0c83\\u0cb3\\u0cb6\\u0cc4\\u0cc3\\u0cc6\\u0cca\\u0cd5\\u0cd6\\u0C8B\\u0C8C\\u0C8E\\u0C92\\u0CB1\\u0CB7\\u0CE0\\u0CE1]", /*roundtrip exclusions*/
|
||||
"[{\\u0cb0\\u0cbc}{\\u0cb3\\u0cbc}\\u0c82\\u0c83\\u0cb3\\u0cb6\\u0cc4\\u0cc3\\u0cc6\\u0cca\\u0cd5\\u0cd6\\u0C8B\\u0C8C\\u0C8E\\u0C92\\u0CB1\\u0CB7\\u0cbd\\u0CE0\\u0CE1\\u0cde]", /*roundtrip exclusions*/
|
||||
|
||||
"MALAYALAM-GURMUKHI", "[:MALAYALAM:]", "[:GURMUKHI:]",
|
||||
"[\\u0A02\\u0a4b\\u0a4c\\u0a33\\u0a36\\u0a3c\\u0a70\\u0a71\\u0A59\\u0A5A\\u0A5B\\u0A5C\\u0A5E\\u0A72\\u0A73\\u0A74]", /*roundtrip exclusions*/
|
||||
"[\\u0A01\\u0A02\\u0a4b\\u0a4c\\u0a33\\u0a36\\u0a3c\\u0a70\\u0a71\\u0A59\\u0A5A\\u0A5B\\u0A5C\\u0A5E\\u0A72\\u0A73\\u0A74]", /*roundtrip exclusions*/
|
||||
|
||||
"GURMUKHI-MALAYALAM", "[:GURMUKHI:]", "[:MALAYALAM:]",
|
||||
"[\\u0d02\\u0d03\\u0d33\\u0d36\\u0d43\\u0d46\\u0d4a\\u0d4c\\u0d57\\u0D0B\\u0D0C\\u0D0E\\u0D12\\u0D31\\u0D34\\u0D37\\u0D60\\u0D61]", /*roundtrip exclusions*/
|
||||
|
||||
"GUJARATI-ORIYA", "[:GUJARATI:]", "[:ORIYA:]",
|
||||
"[\\u0b56\\u0b57\\u0B0C\\u0B5F\\u0B61]", /*roundtrip exclusions*/
|
||||
"[\\u0b56\\u0b57\\u0B0C\\u0B5F\\u0B61\\u0b70\\u0b71]", /*roundtrip exclusions*/
|
||||
|
||||
"ORIYA-GUJARATI", "[:ORIYA:]", "[:GUJARATI:]",
|
||||
"[\\u0Ac4\\u0Ac5\\u0Ac9\\u0Ac7\\u0A8D\\u0A91\\u0AB5\\u0Ad0]", /*roundtrip exclusions*/
|
||||
|
||||
"TAMIL-GUJARATI", "[:TAMIL:]", "[:GUJARATI:]",
|
||||
"[\\u0A81\\u0abc\\u0ac3\\u0Ac4\\u0Ac5\\u0Ac9\\u0Ac7\\u0A8B\\u0A8D\\u0A91\\u0A96\\u0A97\\u0A98\\u0A9B\\u0A9D\\u0AA0\\u0AA1\\u0AA2\\u0AA5\\u0AA6\\u0AA7\\u0AAB\\u0AAC\\u0AAD\\u0AB6\\u0ABD\\u0AD0\\u0AE0]", /*roundtrip exclusions*/
|
||||
"[\\u0A81\\u0a8c\\u0abc\\u0ac3\\u0Ac4\\u0Ac5\\u0Ac9\\u0Ac7\\u0A8B\\u0A8D\\u0A91\\u0A96\\u0A97\\u0A98\\u0A9B\\u0A9D\\u0AA0\\u0AA1\\u0AA2\\u0AA5\\u0AA6\\u0AA7\\u0AAB\\u0AAC\\u0AAD\\u0AB6\\u0ABD\\u0AD0\\u0AE0\\u0AE1]", /*roundtrip exclusions*/
|
||||
|
||||
"GUJARATI-TAMIL", "[:GUJARATI:]", "[:TAMIL:]",
|
||||
"[\\u0Bc6\\u0Bca\\u0Bd7\\u0B8E\\u0B92\\u0BA9\\u0BB1\\u0BB4]", /*roundtrip exclusions*/
|
||||
|
@ -1381,7 +1433,7 @@ static const char * const interIndicArray[] = {
|
|||
"[\\u0A81\\u0abc\\u0Ac5\\u0Ac9\\u0A8D\\u0A91\\u0ABD\\u0Ad0]", /*roundtrip exclusions*/
|
||||
|
||||
"GUJARATI-KANNADA", "[:GUJARATI:]", "[:KANNADA:]",
|
||||
"[\\u0cc6\\u0cca\\u0cd5\\u0cd6\\u0C8C\\u0C8E\\u0C92\\u0CB1\\u0CDE\\u0CE1]", /*roundtrip exclusions*/
|
||||
"[{\\u0cb0\\u0cbc}{\\u0cb3\\u0cbc}\\u0cc6\\u0cca\\u0cd5\\u0cd6\\u0C8C\\u0C8E\\u0C92\\u0CB1\\u0CDE\\u0CE1]", /*roundtrip exclusions*/
|
||||
|
||||
"MALAYALAM-GUJARATI", "[:MALAYALAM:]", "[:GUJARATI:]",
|
||||
"[\\u0A81\\u0ac4\\u0acb\\u0acc\\u0abc\\u0Ac5\\u0Ac9\\u0A8D\\u0A91\\u0ABD\\u0Ad0]", /*roundtrip exclusions*/
|
||||
|
@ -1390,25 +1442,25 @@ static const char * const interIndicArray[] = {
|
|||
"[\\u0d46\\u0d4a\\u0d4c\\u0d55\\u0d57\\u0D0C\\u0D0E\\u0D12\\u0D31\\u0D34\\u0D61]", /*roundtrip exclusions*/
|
||||
|
||||
"TAMIL-ORIYA", "[:TAMIL:]", "[:ORIYA:]",
|
||||
"[\\u0B01\\u0b3c\\u0b43\\u0b56\\u0B0B\\u0B0C\\u0B16\\u0B17\\u0B18\\u0B1B\\u0B1D\\u0B20\\u0B21\\u0B22\\u0B25\\u0B26\\u0B27\\u0B2B\\u0B2C\\u0B2D\\u0B36\\u0B3D\\u0B5C\\u0B5D\\u0B5F\\u0B60\\u0B61]", /*roundtrip exclusions*/
|
||||
"[\\u0B01\\u0b3c\\u0b43\\u0b56\\u0B0B\\u0B0C\\u0B16\\u0B17\\u0B18\\u0B1B\\u0B1D\\u0B20\\u0B21\\u0B22\\u0B25\\u0B26\\u0B27\\u0B2B\\u0B2C\\u0B2D\\u0B36\\u0B3D\\u0B5C\\u0B5D\\u0B5F\\u0B60\\u0B61\\u0b70\\u0b71]", /*roundtrip exclusions*/
|
||||
|
||||
"ORIYA-TAMIL", "[:ORIYA:]", "[:TAMIL:]",
|
||||
"[\\u0bc6\\u0bca\\u0bc7\\u0B8E\\u0B92\\u0BA9\\u0BB1\\u0BB4\\u0BB5]", /*roundtrip exclusions*/
|
||||
|
||||
"TELUGU-ORIYA", "[:TELUGU:]", "[:ORIYA:]",
|
||||
"[\\u0b3c\\u0b57\\u0b56\\u0B3D\\u0B5C\\u0B5D\\u0B5F]", /*roundtrip exclusions*/
|
||||
"[\\u0b3c\\u0b57\\u0b56\\u0B3D\\u0B5C\\u0B5D\\u0B5F\\u0b70\\u0b71]", /*roundtrip exclusions*/
|
||||
|
||||
"ORIYA-TELUGU", "[:ORIYA:]", "[:TELUGU:]",
|
||||
"[\\u0c44\\u0c46\\u0c4a\\u0c55\\u0c47\\u0C0E\\u0C12\\u0C31\\u0C35]", /*roundtrip exclusions*/
|
||||
|
||||
"KANNADA-ORIYA", "[:KANNADA:]", "[:ORIYA:]",
|
||||
"[\\u0B01\\u0b3c\\u0b57\\u0B3D\\u0B5C\\u0B5D\\u0B5F]", /*roundtrip exclusions*/
|
||||
"[\\u0B01\\u0b3c\\u0b57\\u0B3D\\u0B5C\\u0B5D\\u0B5F\\u0b70\\u0b71]", /*roundtrip exclusions*/
|
||||
|
||||
"ORIYA-KANNADA", "[:ORIYA:]", "[:KANNADA:]",
|
||||
"[\\u0cc4\\u0cc6\\u0cca\\u0cd5\\u0cc7\\u0C8E\\u0C92\\u0CB1\\u0CB5\\u0CDE]", /*roundtrip exclusions*/
|
||||
"[{\\u0cb0\\u0cbc}{\\u0cb3\\u0cbc}\\u0cc4\\u0cc6\\u0cca\\u0cd5\\u0cc7\\u0C8E\\u0C92\\u0CB1\\u0CB5\\u0CDE]", /*roundtrip exclusions*/
|
||||
|
||||
"MALAYALAM-ORIYA", "[:MALAYALAM:]", "[:ORIYA:]",
|
||||
"[\\u0B01\\u0b3c\\u0b56\\u0B3D\\u0B5C\\u0B5D\\u0B5F]", /*roundtrip exclusions*/
|
||||
"[\\u0B01\\u0b3c\\u0b56\\u0B3D\\u0B5C\\u0B5D\\u0B5F\\u0b70\\u0b71]", /*roundtrip exclusions*/
|
||||
|
||||
"ORIYA-MALAYALAM", "[:ORIYA:]", "[:MALAYALAM:]",
|
||||
"[\\u0D47\\u0D46\\u0D4a\\u0D0E\\u0D12\\u0D31\\u0D34\\u0D35]", /*roundtrip exclusions*/
|
||||
|
@ -1423,7 +1475,7 @@ static const char * const interIndicArray[] = {
|
|||
"[\\u0bd7\\u0bc6\\u0ba9\\u0bb4]", /*roundtrip exclusions*/
|
||||
|
||||
"TAMIL-KANNADA", "[:TAMIL:]", "[:KANNADA:]",
|
||||
"[\\u0cc3\\u0cc4\\u0cc6\\u0cc7\\u0cd5\\u0cd6\\u0C8B\\u0C8C\\u0C96\\u0C97\\u0C98\\u0C9B\\u0C9D\\u0CA0\\u0CA1\\u0CA2\\u0CA5\\u0CA6\\u0CA7\\u0CAB\\u0CAC\\u0CAD\\u0CB6\\u0CDE\\u0CE0\\u0CE1]", /*roundtrip exclusions*/
|
||||
"[\\u0cc3\\u0cc4\\u0cc6\\u0cc7\\u0cd5\\u0cd6\\u0C8B\\u0C8C\\u0C96\\u0C97\\u0C98\\u0C9B\\u0C9D\\u0CA0\\u0CA1\\u0CA2\\u0CA5\\u0CA6\\u0CA7\\u0CAB\\u0CAC\\u0CAD\\u0CB6\\u0cbc\\u0cbd\\u0CDE\\u0CE0\\u0CE1]", /*roundtrip exclusions*/
|
||||
|
||||
"MALAYALAM-TAMIL", "[:MALAYALAM:]", "[:TAMIL:]",
|
||||
"[\\u0ba9]", /*roundtrip exclusions*/
|
||||
|
@ -1435,7 +1487,7 @@ static const char * const interIndicArray[] = {
|
|||
"[\\u0C01\\u0c3f\\u0c46\\u0c48\\u0c4a]", /*roundtrip exclusions*/
|
||||
|
||||
"TELUGU-KANNADA", "[:TELUGU:]", "[:KANNADA:]",
|
||||
"[\\u0cc8\\u0cd5\\u0cd6\\u0CDE]", /*roundtrip exclusions*/
|
||||
"[\\u0cc8\\u0cd5\\u0cd6\\u0cbc\\u0cbd\\u0CDE]", /*roundtrip exclusions*/
|
||||
|
||||
"MALAYALAM-TELUGU", "[:MALAYALAM:]", "[:TELUGU:]",
|
||||
"[\\u0C01\\u0c44\\u0c4a\\u0c4c\\u0c4b\\u0c55\\u0c56]", /*roundtrip exclusions*/
|
||||
|
@ -1444,22 +1496,22 @@ static const char * const interIndicArray[] = {
|
|||
"[\\u0d4c\\u0d57\\u0D34]", /*roundtrip exclusions*/
|
||||
|
||||
"MALAYALAM-KANNADA", "[:MALAYALAM:]", "[:KANNADA:]",
|
||||
"[\\u0cc4\\u0cc6\\u0cca\\u0ccc\\u0ccb\\u0cd5\\u0cd6\\u0cDe]", /*roundtrip exclusions*/
|
||||
"[\\u0cbc\\u0cbd\\u0cc4\\u0cc6\\u0cca\\u0ccc\\u0ccb\\u0cd5\\u0cd6\\u0cDe]", /*roundtrip exclusions*/
|
||||
|
||||
"KANNADA-MALAYALAM", "[:KANNADA:]", "[:MALAYALAM:]",
|
||||
"[\\u0d4c\\u0d57\\u0d46\\u0D34]", /*roundtrip exclusions*/
|
||||
|
||||
"Latin-Bengali",latinForIndic, "[[:Bengali:][\\u0964\\u0965]]",
|
||||
"[\\u0965\\u09f0\\u09f1]" /*roundtrip exclusions*/ ,
|
||||
"[\\u0965\\u09f0-\\u09fa]" /*roundtrip exclusions*/ ,
|
||||
|
||||
"Latin-Gurmukhi", latinForIndic, "[[:Gurmukhi:][\\u0964\\u0965]]",
|
||||
"[\\u0965\\u0a02\\u0a72\\u0a73\\u0a74]" /*roundtrip exclusions*/,
|
||||
"[\\u0a01\\u0965\\u0a02\\u0a72\\u0a73\\u0a74]" /*roundtrip exclusions*/,
|
||||
|
||||
"Latin-Gujarati",latinForIndic, "[[:Gujarati:][\\u0964\\u0965]]",
|
||||
"[\\u0965]" /*roundtrip exclusions*/,
|
||||
|
||||
"Latin-Oriya",latinForIndic, "[[:Oriya:][\\u0964\\u0965]]",
|
||||
"[\\u0965]" /*roundtrip exclusions*/,
|
||||
"[\\u0965\\u0b70]" /*roundtrip exclusions*/,
|
||||
|
||||
"Latin-Tamil",latinForIndic, "[:Tamil:]",
|
||||
NULL /*roundtrip exclusions*/,
|
||||
|
@ -1494,24 +1546,11 @@ void TransliteratorRoundTripTest::TestInterIndic() {
|
|||
RTTest test(interIndicArray[i*INTER_INDIC_ARRAY_WIDTH + 0]);
|
||||
Legal *legal = new LegalIndic();
|
||||
|
||||
if (isICUVersionAtLeast(ICU_30)) {
|
||||
infoln("Warning: TestDevanagariLatin needs to be updated to remove Unicode 3.2 filter");
|
||||
// We temporarily filter against Unicode 3.2, but we only do this
|
||||
// before version 3.0.
|
||||
UnicodeString temp1 = "[";
|
||||
temp1.append(interIndicArray[i*INTER_INDIC_ARRAY_WIDTH + 1]);
|
||||
temp1.append("& [:Age=3.2:]]");
|
||||
UnicodeString temp2 = "[";
|
||||
temp2.append(interIndicArray[i*INTER_INDIC_ARRAY_WIDTH + 2]);
|
||||
temp2.append("& [:Age=3.2:]]");
|
||||
test.test( interIndicArray[i*INTER_INDIC_ARRAY_WIDTH + 1],
|
||||
interIndicArray[i*INTER_INDIC_ARRAY_WIDTH + 2],
|
||||
interIndicArray[i*INTER_INDIC_ARRAY_WIDTH + 3], // roundtrip exclusions
|
||||
this, quick, legal, 50);
|
||||
|
||||
test.test(temp1,
|
||||
temp2,
|
||||
interIndicArray[i*INTER_INDIC_ARRAY_WIDTH + 3], // roundtrip exclusions
|
||||
this, quick, legal, 50);
|
||||
} else {
|
||||
logln("Warning: TestDevanagariLatin needs to be updated to remove Unicode 3.2 filter");
|
||||
}
|
||||
delete legal;
|
||||
}
|
||||
|
||||
|
|
|
@ -37,6 +37,8 @@ class TransliteratorRoundTripTest : public IntlTest {
|
|||
void TestCyrillic(void);
|
||||
void TestDevanagariLatin(void);
|
||||
void TestInterIndic(void);
|
||||
void TestHebrew(void);
|
||||
void TestArabic(void);
|
||||
void TestDebug(const char* name,const char fromSet[],
|
||||
const char* toSet,const char* exclusions);
|
||||
};
|
||||
|
|
Loading…
Add table
Reference in a new issue