AuroraMiddleware/scuffed-code
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

ICU-483 add inter-Indic transliterators

Browse Source 
X-SVN-Rev: 3886
This commit is contained in:
Alan Liu 2001-03-03 00:49:45 +00:00
parent 7dc78c8188
commit 83377886c0
26 changed files with 2636 additions and 161 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

117
icu4c/data/Bengali_InterIndic.txt Normal file
View File

@ -0,0 +1,117 @@
 // -*- Coding: utf-8; -*-
//--------------------------------------------------------------------
// Copyright (c) 1999-2001, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// THIS IS A MACHINE-GENERATED FILE
// Tool: dumpICUrules.bat
// Source: \icu4j\src\com\ibm\text\resources/Transliterator_Bengali_InterIndic.utf8.txt
// Date: Thu Mar 1 20:03:54 2001
//--------------------------------------------------------------------
// Bengali_InterIndic
Bengali_InterIndic {
Rule {
//--------------------------------------------------------------------
// Copyright (c) 1999-2001, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// Date: Tue Jan 23 12:41:57 2001
//--------------------------------------------------------------------
// Bengali-InterIndic
"ঁ>\uE001;" // SIGN CANDRABINDU
"ং>\uE002;" // SIGN ANUSVARA
"ঃ>\uE003;" // SIGN VISARGA
"অ>\uE005;" // LETTER A
"আ>\uE006;" // LETTER AA
"ই>\uE007;" // LETTER I
"ঈ>\uE008;" // LETTER II
"উ>\uE009;" // LETTER U
"ঊ>\uE00A;" // LETTER UU
"ঋ>\uE00B;" // LETTER VOCALIC R
"ঌ>\uE00C;" // LETTER VOCALIC L
"এ>\uE081;" // LETTER E
"ঐ>\uE010;" // LETTER AI
"ও>\uE082;" // LETTER O
"ঔ>\uE014;" // LETTER AU
"ক>\uE015;" // LETTER KA
"খ>\uE016;" // LETTER KHA
"গ>\uE017;" // LETTER GA
"ঘ>\uE018;" // LETTER GHA
"ঙ>\uE019;" // LETTER NGA
"চ>\uE01A;" // LETTER CA
"ছ>\uE01B;" // LETTER CHA
"জ>\uE01C;" // LETTER JA
"ঝ>\uE01D;" // LETTER JHA
"ঞ>\uE01E;" // LETTER NYA
"ট>\uE01F;" // LETTER TTA
"ঠ>\uE020;" // LETTER TTHA
"ড>\uE021;" // LETTER DDA
"ঢ>\uE022;" // LETTER DDHA
"ণ>\uE023;" // LETTER NNA
"ত>\uE024;" // LETTER TA
"থ>\uE025;" // LETTER THA
"দ>\uE026;" // LETTER DA
"ধ>\uE027;" // LETTER DHA
"ন>\uE028;" // LETTER NA
"প>\uE02A;" // LETTER PA
"ফ>\uE02B;" // LETTER PHA
"ব>\uE02C;" // LETTER BA
"ভ>\uE02D;" // LETTER BHA
"ম>\uE02E;" // LETTER MA
"য>\uE02F;" // LETTER YA
"র>\uE030;" // LETTER RA
"ল>\uE032;" // LETTER LA
"শ>\uE036;" // LETTER SHA
"ষ>\uE037;" // LETTER SSA
"স>\uE038;" // LETTER SA
"হ>\uE039;" // LETTER HA
"়>\uE03C;" // SIGN NUKTA
"া>\uE03E;" // VOWEL SIGN AA
"ি>\uE03F;" // VOWEL SIGN I
"ী>\uE040;" // VOWEL SIGN II
"ু>\uE041;" // VOWEL SIGN U
"ূ>\uE042;" // VOWEL SIGN UU
"ৃ>\uE043;" // VOWEL SIGN VOCALIC R
"ৄ>\uE044;" // VOWEL SIGN VOCALIC RR
"ে>\uE084;" // VOWEL SIGN E
"ৈ>\uE048;" // VOWEL SIGN AI
"ো>\uE085;" // VOWEL SIGN O
"ৌ>\uE04C;" // VOWEL SIGN AU
"্>\uE04D;" // SIGN VIRAMA
"ৗ>\uE057;" // AU LENGTH MARK
"ড়>\uE083;" // LETTER RRA
"ঢ়>\uE05D;" // LETTER RHA
"য়>\uE05F;" // LETTER YYA
"ৠ>\uE060;" // LETTER VOCALIC RR
"ৡ>\uE061;" // LETTER VOCALIC LL
"ৢ>\uE062;" // VOWEL SIGN VOCALIC L
"ৣ>\uE063;" // VOWEL SIGN VOCALIC LL
"০>\uE066;" // DIGIT ZERO
"১>\uE067;" // DIGIT ONE
"২>\uE068;" // DIGIT TWO
"৩>\uE069;" // DIGIT THREE
"৪>\uE06A;" // DIGIT FOUR
"৫>\uE06B;" // DIGIT FIVE
"৬>\uE06C;" // DIGIT SIX
"৭>\uE06D;" // DIGIT SEVEN
"৮>\uE06E;" // DIGIT EIGHT
"৯>\uE06F;" // DIGIT NINE
// ৰ>; // UNMAPPED Bengali-InterIndic: LETTER RA WITH MIDDLE DIAGONAL
// ৱ>; // UNMAPPED Bengali-InterIndic: LETTER RA WITH LOWER DIAGONAL
// ৲>; // UNMAPPED Bengali-InterIndic: RUPEE MARK
// ৳>; // UNMAPPED Bengali-InterIndic: RUPEE SIGN
// ৴>; // UNMAPPED Bengali-InterIndic: CURRENCY NUMERATOR ONE
// ৵>; // UNMAPPED Bengali-InterIndic: CURRENCY NUMERATOR TWO
// ৶>; // UNMAPPED Bengali-InterIndic: CURRENCY NUMERATOR THREE
// ৷>; // UNMAPPED Bengali-InterIndic: CURRENCY NUMERATOR FOUR
// ৸>; // UNMAPPED Bengali-InterIndic: CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR
// ৹>; // UNMAPPED Bengali-InterIndic: CURRENCY DENOMINATOR SIXTEEN
"৺>\uE080;" // ISSHAR
// eof
}
}

132
icu4c/data/Devanagari_InterIndic.txt Normal file
View File

@ -0,0 +1,132 @@
 // -*- Coding: utf-8; -*-
//--------------------------------------------------------------------
// Copyright (c) 1999-2001, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// THIS IS A MACHINE-GENERATED FILE
// Tool: dumpICUrules.bat
// Source: \icu4j\src\com\ibm\text\resources/Transliterator_Devanagari_InterIndic.utf8.txt
// Date: Thu Mar 1 20:03:54 2001
//--------------------------------------------------------------------
// Devanagari_InterIndic
Devanagari_InterIndic {
Rule {
//--------------------------------------------------------------------
// Copyright (c) 1999-2001, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// Date: Tue Jan 23 12:41:57 2001
//--------------------------------------------------------------------
// Devanagari-InterIndic
"ँ>\uE001;" // SIGN CANDRABINDU
"ं>\uE002;" // SIGN ANUSVARA
"ः>\uE003;" // SIGN VISARGA
"अ>\uE005;" // LETTER A
"आ>\uE006;" // LETTER AA
"इ>\uE007;" // LETTER I
"ई>\uE008;" // LETTER II
"उ>\uE009;" // LETTER U
"ऊ>\uE00A;" // LETTER UU
"ऋ>\uE00B;" // LETTER VOCALIC R
"ऌ>\uE00C;" // LETTER VOCALIC L
// ऍ>; // UNMAPPED Devanagari-InterIndic: LETTER CANDRA E
// ऎ>; // UNMAPPED Devanagari-InterIndic: LETTER SHORT E
"ए>\uE081;" // LETTER E
"ऐ>\uE010;" // LETTER AI
// ऑ>; // UNMAPPED Devanagari-InterIndic: LETTER CANDRA O
// ऒ>; // UNMAPPED Devanagari-InterIndic: LETTER SHORT O
"ओ>\uE082;" // LETTER O
"औ>\uE014;" // LETTER AU
"क>\uE015;" // LETTER KA
"ख>\uE016;" // LETTER KHA
"ग>\uE017;" // LETTER GA
"घ>\uE018;" // LETTER GHA
"ङ>\uE019;" // LETTER NGA
"च>\uE01A;" // LETTER CA
"छ>\uE01B;" // LETTER CHA
"ज>\uE01C;" // LETTER JA
"झ>\uE01D;" // LETTER JHA
"ञ>\uE01E;" // LETTER NYA
"ट>\uE01F;" // LETTER TTA
"ठ>\uE020;" // LETTER TTHA
"ड>\uE021;" // LETTER DDA
"ढ>\uE022;" // LETTER DDHA
"ण>\uE023;" // LETTER NNA
"त>\uE024;" // LETTER TA
"थ>\uE025;" // LETTER THA
"द>\uE026;" // LETTER DA
"ध>\uE027;" // LETTER DHA
"न>\uE028;" // LETTER NA
"ऩ>\uE029;" // LETTER NNNA
"प>\uE02A;" // LETTER PA
"फ>\uE02B;" // LETTER PHA
"ब>\uE02C;" // LETTER BA
"भ>\uE02D;" // LETTER BHA
"म>\uE02E;" // LETTER MA
"य>\uE02F;" // LETTER YA
"र>\uE030;" // LETTER RA
"ऱ>\uE083;" // LETTER RRA
"ल>\uE032;" // LETTER LA
"ळ>\uE033;" // LETTER LLA
"ऴ>\uE034;" // LETTER LLLA
"व>\uE035;" // LETTER VA
"श>\uE036;" // LETTER SHA
"ष>\uE037;" // LETTER SSA
"स>\uE038;" // LETTER SA
"ह>\uE039;" // LETTER HA
"़>\uE03C;" // SIGN NUKTA
"ऽ>\uE03D;" // SIGN AVAGRAHA
"ा>\uE03E;" // VOWEL SIGN AA
"ि>\uE03F;" // VOWEL SIGN I
"ी>\uE040;" // VOWEL SIGN II
"ु>\uE041;" // VOWEL SIGN U
"ू>\uE042;" // VOWEL SIGN UU
"ृ>\uE043;" // VOWEL SIGN VOCALIC R
"ॄ>\uE044;" // VOWEL SIGN VOCALIC RR
"ॅ>\uE045;" // VOWEL SIGN CANDRA E
// ॆ>; // UNMAPPED Devanagari-InterIndic: VOWEL SIGN SHORT E
"े>\uE084;" // VOWEL SIGN E
"ै>\uE048;" // VOWEL SIGN AI
"ॉ>\uE049;" // VOWEL SIGN CANDRA O
// ॊ>; // UNMAPPED Devanagari-InterIndic: VOWEL SIGN SHORT O
"ो>\uE085;" // VOWEL SIGN O
"ौ>\uE04C;" // VOWEL SIGN AU
"्>\uE04D;" // SIGN VIRAMA
"ॐ>\uE050;" // OM
// ॑>; // UNMAPPED Devanagari-InterIndic: STRESS SIGN UDATTA
// ॒>; // UNMAPPED Devanagari-InterIndic: STRESS SIGN ANUDATTA
// ॓>; // UNMAPPED Devanagari-InterIndic: GRAVE ACCENT
// ॔>; // UNMAPPED Devanagari-InterIndic: ACUTE ACCENT
// क़>; // UNMAPPED Devanagari-InterIndic: LETTER QA
"ख़>\uE059;" // LETTER KHHA
"ग़>\uE05A;" // LETTER GHHA
"ज़>\uE05B;" // LETTER ZA
// ड़>; // UNMAPPED Devanagari-InterIndic: LETTER DDDHA
"ढ़>\uE05D;" // LETTER RHA
"फ़>\uE05E;" // LETTER FA
"य़>\uE05F;" // LETTER YYA
"ॠ>\uE060;" // LETTER VOCALIC RR
"ॡ>\uE061;" // LETTER VOCALIC LL
"ॢ>\uE062;" // VOWEL SIGN VOCALIC L
"ॣ>\uE063;" // VOWEL SIGN VOCALIC LL
// ।>; // UNMAPPED Devanagari-InterIndic: DANDA
// ॥>; // UNMAPPED Devanagari-InterIndic: DOUBLE DANDA
"०>\uE066;" // DIGIT ZERO
"१>\uE067;" // DIGIT ONE
"२>\uE068;" // DIGIT TWO
"३>\uE069;" // DIGIT THREE
"४>\uE06A;" // DIGIT FOUR
"५>\uE06B;" // DIGIT FIVE
"६>\uE06C;" // DIGIT SIX
"७>\uE06D;" // DIGIT SEVEN
"८>\uE06E;" // DIGIT EIGHT
"९>\uE06F;" // DIGIT NINE
// ॰>; // UNMAPPED Devanagari-InterIndic: ABBREVIATION SIGN
// eof
}
}

106
icu4c/data/Gujarati_InterIndic.txt Normal file
View File

@ -0,0 +1,106 @@
 // -*- Coding: utf-8; -*-
//--------------------------------------------------------------------
// Copyright (c) 1999-2001, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// THIS IS A MACHINE-GENERATED FILE
// Tool: dumpICUrules.bat
// Source: \icu4j\src\com\ibm\text\resources/Transliterator_Gujarati_InterIndic.utf8.txt
// Date: Thu Mar 1 20:03:54 2001
//--------------------------------------------------------------------
// Gujarati_InterIndic
Gujarati_InterIndic {
Rule {
//--------------------------------------------------------------------
// Copyright (c) 1999-2001, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// Date: Tue Jan 23 12:41:58 2001
//--------------------------------------------------------------------
// Gujarati-InterIndic
"ઁ>\uE001;" // SIGN CANDRABINDU
"ં>\uE002;" // SIGN ANUSVARA
"ઃ>\uE003;" // SIGN VISARGA
"અ>\uE005;" // LETTER A
"આ>\uE006;" // LETTER AA
"ઇ>\uE007;" // LETTER I
"ઈ>\uE008;" // LETTER II
"ઉ>\uE009;" // LETTER U
"ઊ>\uE00A;" // LETTER UU
"ઋ>\uE00B;" // LETTER VOCALIC R
// ઍ>; // UNMAPPED Gujarati-InterIndic: VOWEL CANDRA E
"એ>\uE081;" // LETTER E
"ઐ>\uE010;" // LETTER AI
// ઑ>; // UNMAPPED Gujarati-InterIndic: VOWEL CANDRA O
"ઓ>\uE082;" // LETTER O
"ઔ>\uE014;" // LETTER AU
"ક>\uE015;" // LETTER KA
"ખ>\uE016;" // LETTER KHA
"ગ>\uE017;" // LETTER GA
"ઘ>\uE018;" // LETTER GHA
"ઙ>\uE019;" // LETTER NGA
"ચ>\uE01A;" // LETTER CA
"છ>\uE01B;" // LETTER CHA
"જ>\uE01C;" // LETTER JA
"ઝ>\uE01D;" // LETTER JHA
"ઞ>\uE01E;" // LETTER NYA
"ટ>\uE01F;" // LETTER TTA
"ઠ>\uE020;" // LETTER TTHA
"ડ>\uE021;" // LETTER DDA
"ઢ>\uE022;" // LETTER DDHA
"ણ>\uE023;" // LETTER NNA
"ત>\uE024;" // LETTER TA
"થ>\uE025;" // LETTER THA
"દ>\uE026;" // LETTER DA
"ધ>\uE027;" // LETTER DHA
"ન>\uE028;" // LETTER NA
"પ>\uE02A;" // LETTER PA
"ફ>\uE02B;" // LETTER PHA
"બ>\uE02C;" // LETTER BA
"ભ>\uE02D;" // LETTER BHA
"મ>\uE02E;" // LETTER MA
"ય>\uE02F;" // LETTER YA
"ર>\uE030;" // LETTER RA
"લ>\uE032;" // LETTER LA
"ળ>\uE033;" // LETTER LLA
"વ>\uE035;" // LETTER VA
"શ>\uE036;" // LETTER SHA
"ષ>\uE037;" // LETTER SSA
"સ>\uE038;" // LETTER SA
"હ>\uE039;" // LETTER HA
"઼>\uE03C;" // SIGN NUKTA
"ઽ>\uE03D;" // SIGN AVAGRAHA
"ા>\uE03E;" // VOWEL SIGN AA
"િ>\uE03F;" // VOWEL SIGN I
"ી>\uE040;" // VOWEL SIGN II
"ુ>\uE041;" // VOWEL SIGN U
"ૂ>\uE042;" // VOWEL SIGN UU
"ૃ>\uE043;" // VOWEL SIGN VOCALIC R
"ૄ>\uE044;" // VOWEL SIGN VOCALIC RR
"ૅ>\uE045;" // VOWEL SIGN CANDRA E
"ે>\uE084;" // VOWEL SIGN E
"ૈ>\uE048;" // VOWEL SIGN AI
"ૉ>\uE049;" // VOWEL SIGN CANDRA O
"ો>\uE085;" // VOWEL SIGN O
"ૌ>\uE04C;" // VOWEL SIGN AU
"્>\uE04D;" // SIGN VIRAMA
"ૐ>\uE050;" // OM
"ૠ>\uE060;" // LETTER VOCALIC RR
"૦>\uE066;" // DIGIT ZERO
"૧>\uE067;" // DIGIT ONE
"૨>\uE068;" // DIGIT TWO
"૩>\uE069;" // DIGIT THREE
"૪>\uE06A;" // DIGIT FOUR
"૫>\uE06B;" // DIGIT FIVE
"૬>\uE06C;" // DIGIT SIX
"૭>\uE06D;" // DIGIT SEVEN
"૮>\uE06E;" // DIGIT EIGHT
"૯>\uE06F;" // DIGIT NINE
// eof
}
}

103
icu4c/data/Gurmukhi_InterIndic.txt Normal file
View File

@ -0,0 +1,103 @@
 // -*- Coding: utf-8; -*-
//--------------------------------------------------------------------
// Copyright (c) 1999-2001, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// THIS IS A MACHINE-GENERATED FILE
// Tool: dumpICUrules.bat
// Source: \icu4j\src\com\ibm\text\resources/Transliterator_Gurmukhi_InterIndic.utf8.txt
// Date: Thu Mar 1 20:03:54 2001
//--------------------------------------------------------------------
// Gurmukhi_InterIndic
Gurmukhi_InterIndic {
Rule {
//--------------------------------------------------------------------
// Copyright (c) 1999-2001, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// Date: Tue Jan 23 12:41:58 2001
//--------------------------------------------------------------------
// Gurmukhi-InterIndic
"ਂ>\uE001;" // REMAP (indicExceptions.txt): ਁ>ਂ = SIGN CANDRABINDU>SIGN BINDI
"ਅ>\uE005;" // LETTER A
"ਆ>\uE006;" // LETTER AA
"ਇ>\uE007;" // LETTER I
"ਈ>\uE008;" // LETTER II
"ਉ>\uE009;" // LETTER U
"ਊ>\uE00A;" // LETTER UU
"ਏ>\uE00F;" // LETTER EE
"ਐ>\uE010;" // LETTER AI
"ਓ>\uE013;" // LETTER OO
"ਔ>\uE014;" // LETTER AU
"ਕ>\uE015;" // LETTER KA
"ਖ>\uE016;" // LETTER KHA
"ਗ>\uE017;" // LETTER GA
"ਘ>\uE018;" // LETTER GHA
"ਙ>\uE019;" // LETTER NGA
"ਚ>\uE01A;" // LETTER CA
"ਛ>\uE01B;" // LETTER CHA
"ਜ>\uE01C;" // LETTER JA
"ਝ>\uE01D;" // LETTER JHA
"ਞ>\uE01E;" // LETTER NYA
"ਟ>\uE01F;" // LETTER TTA
"ਠ>\uE020;" // LETTER TTHA
"ਡ>\uE021;" // LETTER DDA
"ਢ>\uE022;" // LETTER DDHA
"ਣ>\uE023;" // LETTER NNA
"ਤ>\uE024;" // LETTER TA
"ਥ>\uE025;" // LETTER THA
"ਦ>\uE026;" // LETTER DA
"ਧ>\uE027;" // LETTER DHA
"ਨ>\uE028;" // LETTER NA
"ਪ>\uE02A;" // LETTER PA
"ਫ>\uE02B;" // LETTER PHA
"ਬ>\uE02C;" // LETTER BA
"ਭ>\uE02D;" // LETTER BHA
"ਮ>\uE02E;" // LETTER MA
"ਯ>\uE02F;" // LETTER YA
"ਰ>\uE030;" // LETTER RA
"ਲ>\uE032;" // LETTER LA
"ਲ਼>\uE033;" // LETTER LLA
"ਵ>\uE035;" // LETTER VA
"ਸ਼>\uE036;" // LETTER SHA
"ਸ>\uE038;" // LETTER SA
"ਹ>\uE039;" // LETTER HA
"਼>\uE03C;" // SIGN NUKTA
"ਾ>\uE03E;" // VOWEL SIGN AA
"ਿ>\uE03F;" // VOWEL SIGN I
"ੀ>\uE040;" // VOWEL SIGN II
"ੁ>\uE041;" // VOWEL SIGN U
"ੂ>\uE042;" // VOWEL SIGN UU
"ੇ>\uE047;" // VOWEL SIGN EE
"ੈ>\uE048;" // VOWEL SIGN AI
"ੋ>\uE04B;" // VOWEL SIGN OO
"ੌ>\uE04C;" // VOWEL SIGN AU
"੍>\uE04D;" // SIGN VIRAMA
"ਖ਼>\uE059;" // LETTER KHHA
"ਗ਼>\uE05A;" // LETTER GHHA
"ਜ਼>\uE05B;" // LETTER ZA
"ੜ>\uE083;" // LETTER RRA
"ਫ਼>\uE05E;" // LETTER FA
"੦>\uE066;" // DIGIT ZERO
"੧>\uE067;" // DIGIT ONE
"੨>\uE068;" // DIGIT TWO
"੩>\uE069;" // DIGIT THREE
"੪>\uE06A;" // DIGIT FOUR
"੫>\uE06B;" // DIGIT FIVE
"੬>\uE06C;" // DIGIT SIX
"੭>\uE06D;" // DIGIT SEVEN
"੮>\uE06E;" // DIGIT EIGHT
"੯>\uE06F;" // DIGIT NINE
// ੰ>; // UNMAPPED Gurmukhi-InterIndic: TIPPI
// ੱ>; // UNMAPPED Gurmukhi-InterIndic: ADDAK
// ੲ>; // UNMAPPED Gurmukhi-InterIndic: IRI
// ੳ>; // UNMAPPED Gurmukhi-InterIndic: URA
// ੴ>; // UNMAPPED Gurmukhi-InterIndic: EK ONKAR
// eof
}
}

125
icu4c/data/InterIndic_Bengali.txt Normal file
View File

@ -0,0 +1,125 @@
 // -*- Coding: utf-8; -*-
//--------------------------------------------------------------------
// Copyright (c) 1999-2001, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// THIS IS A MACHINE-GENERATED FILE
// Tool: dumpICUrules.bat
// Source: \icu4j\src\com\ibm\text\resources/Transliterator_InterIndic_Bengali.utf8.txt
// Date: Thu Mar 1 20:03:55 2001
//--------------------------------------------------------------------
// InterIndic_Bengali
InterIndic_Bengali {
Rule {
//--------------------------------------------------------------------
// Copyright (c) 1999-2001, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// Date: Tue Jan 23 12:41:59 2001
//--------------------------------------------------------------------
// InterIndic-Bengali
"\uE001>ঁ;" // SIGN CANDRABINDU
"\uE002>ং;" // SIGN ANUSVARA
"\uE003>ঃ;" // SIGN VISARGA
"\uE005>অ;" // LETTER A
"\uE006>আ;" // LETTER AA
"\uE007>ই;" // LETTER I
"\uE008>ঈ;" // LETTER II
"\uE009>উ;" // LETTER U
"\uE00A>ঊ;" // LETTER UU
"\uE00B>ঋ;" // LETTER VOCALIC R
"\uE00C>ঌ;" // LETTER VOCALIC L
// \uE00F>; // UNMAPPED InterIndic-Bengali: LETTER EE (এ = LETTER E)
"\uE010>ঐ;" // LETTER AI
// \uE013>; // UNMAPPED InterIndic-Bengali: LETTER OO (ও = LETTER O)
"\uE014>ঔ;" // LETTER AU
"\uE015>ক;" // LETTER KA
"\uE016>খ;" // LETTER KHA
"\uE017>গ;" // LETTER GA
"\uE018>ঘ;" // LETTER GHA
"\uE019>ঙ;" // LETTER NGA
"\uE01A>চ;" // LETTER CA
"\uE01B>ছ;" // LETTER CHA
"\uE01C>জ;" // LETTER JA
"\uE01D>ঝ;" // LETTER JHA
"\uE01E>ঞ;" // LETTER NYA
"\uE01F>ট;" // LETTER TTA
"\uE020>ঠ;" // LETTER TTHA
"\uE021>ড;" // LETTER DDA
"\uE022>ঢ;" // LETTER DDHA
"\uE023>ণ;" // LETTER NNA
"\uE024>ত;" // LETTER TA
"\uE025>থ;" // LETTER THA
"\uE026>দ;" // LETTER DA
"\uE027>ধ;" // LETTER DHA
"\uE028>ন;" // LETTER NA
"\uE029>ন;" // REMAP (indicExceptions.txt): ঩>ন = LETTER NNNA>LETTER NA
"\uE02A>প;" // LETTER PA
"\uE02B>ফ;" // LETTER PHA
"\uE02C>ব;" // LETTER BA
"\uE02D>ভ;" // LETTER BHA
"\uE02E>ম;" // LETTER MA
"\uE02F>য;" // LETTER YA
"\uE030>র;" // LETTER RA
"\uE032>ল;" // LETTER LA
"\uE033>ল;" // REMAP (indicExceptions.txt): ঳>ল = LETTER LLA>LETTER LA
"\uE034>ল;" // REMAP (indicExceptions.txt): ঴>ল = LETTER LLLA>LETTER LA
"\uE035>ব;" // REMAP (indicExceptions.txt): ঵>ব = LETTER VA>LETTER BA
"\uE036>শ;" // LETTER SHA
"\uE037>ষ;" // LETTER SSA
"\uE038>স;" // LETTER SA
"\uE039>হ;" // LETTER HA
"\uE03C>়;" // SIGN NUKTA
// \uE03D>; // UNMAPPED InterIndic-Bengali: SIGN AVAGRAHA
"\uE03E>া;" // VOWEL SIGN AA
"\uE03F>ি;" // VOWEL SIGN I
"\uE040>ী;" // VOWEL SIGN II
"\uE041>ু;" // VOWEL SIGN U
"\uE042>ূ;" // VOWEL SIGN UU
"\uE043>ৃ;" // VOWEL SIGN VOCALIC R
"\uE044>ৄ;" // VOWEL SIGN VOCALIC RR
"\uE045>ে;" // REMAP (indicExceptions.txt): ৅>ে = VOWEL SIGN CANDRA E>VOWEL SIGN E
// \uE047>; // UNMAPPED InterIndic-Bengali: VOWEL SIGN EE (ে = VOWEL SIGN E)
"\uE048>ৈ;" // VOWEL SIGN AI
"\uE049>ো;" // REMAP (indicExceptions.txt): ৉>ো = VOWEL SIGN CANDRA O>VOWEL SIGN O
// \uE04B>; // UNMAPPED InterIndic-Bengali: VOWEL SIGN OO (ো = VOWEL SIGN O)
"\uE04C>ৌ;" // VOWEL SIGN AU
"\uE04D>্;" // SIGN VIRAMA
// \uE050>; // UNMAPPED InterIndic-Bengali: OM
// \uE055>; // UNMAPPED InterIndic-Bengali: LENGTH MARK
"\uE056>ৈ;" // REMAP (indicExceptions.txt): ৖>ৈ = AI LENGTH MARK>VOWEL SIGN AI
"\uE057>ৗ;" // AU LENGTH MARK
"\uE059>খ;" // REMAP (indicExceptions.txt): ৙>খ = LETTER KHHA>LETTER KHA
"\uE05A>গ;" // REMAP (indicExceptions.txt): ৚>গ = LETTER GHHA>LETTER GA
"\uE05B>জ;" // REMAP (indicExceptions.txt): ৛>জ = LETTER ZA>LETTER JA
"\uE05D>ঢ়;" // LETTER RHA
"\uE05E>ফ;" // REMAP (indicExceptions.txt): ৞>ফ = LETTER FA>LETTER PHA
"\uE05F>য়;" // LETTER YYA
"\uE060>ৠ;" // LETTER VOCALIC RR
"\uE061>ৡ;" // LETTER VOCALIC LL
"\uE062>ৢ;" // VOWEL SIGN VOCALIC L
"\uE063>ৣ;" // VOWEL SIGN VOCALIC LL
"\uE066>০;" // DIGIT ZERO
"\uE067>১;" // DIGIT ONE
"\uE068>২;" // DIGIT TWO
"\uE069>৩;" // DIGIT THREE
"\uE06A>৪;" // DIGIT FOUR
"\uE06B>৫;" // DIGIT FIVE
"\uE06C>৬;" // DIGIT SIX
"\uE06D>৭;" // DIGIT SEVEN
"\uE06E>৮;" // DIGIT EIGHT
"\uE06F>৯;" // DIGIT NINE
"\uE080>৺;" // ISSHAR
"\uE081>এ;" // LETTER E
"\uE082>ও;" // LETTER O
"\uE083>ড়;" // LETTER RRA
"\uE084>ে;" // VOWEL SIGN E
"\uE085>ো;" // VOWEL SIGN O
// eof
}
}

125
icu4c/data/InterIndic_Devanagari.txt Normal file
View File

@ -0,0 +1,125 @@
 // -*- Coding: utf-8; -*-
//--------------------------------------------------------------------
// Copyright (c) 1999-2001, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// THIS IS A MACHINE-GENERATED FILE
// Tool: dumpICUrules.bat
// Source: \icu4j\src\com\ibm\text\resources/Transliterator_InterIndic_Devanagari.utf8.txt
// Date: Thu Mar 1 20:03:55 2001
//--------------------------------------------------------------------
// InterIndic_Devanagari
InterIndic_Devanagari {
Rule {
//--------------------------------------------------------------------
// Copyright (c) 1999-2001, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// Date: Tue Jan 23 12:41:59 2001
//--------------------------------------------------------------------
// InterIndic-Devanagari
"\uE001>ँ;" // SIGN CANDRABINDU
"\uE002>ं;" // SIGN ANUSVARA
"\uE003>ः;" // SIGN VISARGA
"\uE005>अ;" // LETTER A
"\uE006>आ;" // LETTER AA
"\uE007>इ;" // LETTER I
"\uE008>ई;" // LETTER II
"\uE009>उ;" // LETTER U
"\uE00A>ऊ;" // LETTER UU
"\uE00B>ऋ;" // LETTER VOCALIC R
"\uE00C>ऌ;" // LETTER VOCALIC L
// \uE00F>; // UNMAPPED InterIndic-Devanagari: LETTER EE (ए = LETTER E)
"\uE010>ऐ;" // LETTER AI
// \uE013>; // UNMAPPED InterIndic-Devanagari: LETTER OO (ओ = LETTER O)
"\uE014>औ;" // LETTER AU
"\uE015>क;" // LETTER KA
"\uE016>ख;" // LETTER KHA
"\uE017>ग;" // LETTER GA
"\uE018>घ;" // LETTER GHA
"\uE019>ङ;" // LETTER NGA
"\uE01A>च;" // LETTER CA
"\uE01B>छ;" // LETTER CHA
"\uE01C>ज;" // LETTER JA
"\uE01D>झ;" // LETTER JHA
"\uE01E>ञ;" // LETTER NYA
"\uE01F>ट;" // LETTER TTA
"\uE020>ठ;" // LETTER TTHA
"\uE021>ड;" // LETTER DDA
"\uE022>ढ;" // LETTER DDHA
"\uE023>ण;" // LETTER NNA
"\uE024>त;" // LETTER TA
"\uE025>थ;" // LETTER THA
"\uE026>द;" // LETTER DA
"\uE027>ध;" // LETTER DHA
"\uE028>न;" // LETTER NA
"\uE029>ऩ;" // LETTER NNNA
"\uE02A>प;" // LETTER PA
"\uE02B>फ;" // LETTER PHA
"\uE02C>ब;" // LETTER BA
"\uE02D>भ;" // LETTER BHA
"\uE02E>म;" // LETTER MA
"\uE02F>य;" // LETTER YA
"\uE030>र;" // LETTER RA
"\uE032>ल;" // LETTER LA
"\uE033>ळ;" // LETTER LLA
"\uE034>ऴ;" // LETTER LLLA
"\uE035>व;" // LETTER VA
"\uE036>श;" // LETTER SHA
"\uE037>ष;" // LETTER SSA
"\uE038>स;" // LETTER SA
"\uE039>ह;" // LETTER HA
"\uE03C>़;" // SIGN NUKTA
"\uE03D>ऽ;" // SIGN AVAGRAHA
"\uE03E>ा;" // VOWEL SIGN AA
"\uE03F>ि;" // VOWEL SIGN I
"\uE040>ी;" // VOWEL SIGN II
"\uE041>ु;" // VOWEL SIGN U
"\uE042>ू;" // VOWEL SIGN UU
"\uE043>ृ;" // VOWEL SIGN VOCALIC R
"\uE044>ॄ;" // VOWEL SIGN VOCALIC RR
"\uE045>ॅ;" // VOWEL SIGN CANDRA E
// \uE047>; // UNMAPPED InterIndic-Devanagari: VOWEL SIGN EE (े = VOWEL SIGN E)
"\uE048>ै;" // VOWEL SIGN AI
"\uE049>ॉ;" // VOWEL SIGN CANDRA O
// \uE04B>; // UNMAPPED InterIndic-Devanagari: VOWEL SIGN OO (ो = VOWEL SIGN O)
"\uE04C>ौ;" // VOWEL SIGN AU
"\uE04D>्;" // SIGN VIRAMA
"\uE050>ॐ;" // OM
// \uE055>; // UNMAPPED InterIndic-Devanagari: LENGTH MARK
"\uE056>ै;" // REMAP (indicExceptions.txt): ॖ>ै = AI LENGTH MARK>VOWEL SIGN AI
"\uE057>ौ;" // REMAP (indicExceptions.txt): ॗ>ौ = AU LENGTH MARK>VOWEL SIGN AU
"\uE059>ख़;" // LETTER KHHA
"\uE05A>ग़;" // LETTER GHHA
"\uE05B>ज़;" // LETTER ZA
"\uE05D>ढ़;" // LETTER RHA
"\uE05E>फ़;" // LETTER FA
"\uE05F>य़;" // LETTER YYA
"\uE060>ॠ;" // LETTER VOCALIC RR
"\uE061>ॡ;" // LETTER VOCALIC LL
"\uE062>ॢ;" // VOWEL SIGN VOCALIC L
"\uE063>ॣ;" // VOWEL SIGN VOCALIC LL
"\uE066>०;" // DIGIT ZERO
"\uE067>१;" // DIGIT ONE
"\uE068>२;" // DIGIT TWO
"\uE069>३;" // DIGIT THREE
"\uE06A>४;" // DIGIT FOUR
"\uE06B>५;" // DIGIT FIVE
"\uE06C>६;" // DIGIT SIX
"\uE06D>७;" // DIGIT SEVEN
"\uE06E>८;" // DIGIT EIGHT
"\uE06F>९;" // DIGIT NINE
// \uE080>; // UNMAPPED InterIndic-Devanagari: ISSHAR
"\uE081>ए;" // LETTER E
"\uE082>ओ;" // LETTER O
"\uE083>ऱ;" // LETTER RRA
"\uE084>े;" // VOWEL SIGN E
"\uE085>ो;" // VOWEL SIGN O
// eof
}
}

125
icu4c/data/InterIndic_Gujarati.txt Normal file
View File

@ -0,0 +1,125 @@
 // -*- Coding: utf-8; -*-
//--------------------------------------------------------------------
// Copyright (c) 1999-2001, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// THIS IS A MACHINE-GENERATED FILE
// Tool: dumpICUrules.bat
// Source: \icu4j\src\com\ibm\text\resources/Transliterator_InterIndic_Gujarati.utf8.txt
// Date: Thu Mar 1 20:03:55 2001
//--------------------------------------------------------------------
// InterIndic_Gujarati
InterIndic_Gujarati {
Rule {
//--------------------------------------------------------------------
// Copyright (c) 1999-2001, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// Date: Tue Jan 23 12:41:59 2001
//--------------------------------------------------------------------
// InterIndic-Gujarati
"\uE001>ઁ;" // SIGN CANDRABINDU
"\uE002>ં;" // SIGN ANUSVARA
"\uE003>ઃ;" // SIGN VISARGA
"\uE005>અ;" // LETTER A
"\uE006>આ;" // LETTER AA
"\uE007>ઇ;" // LETTER I
"\uE008>ઈ;" // LETTER II
"\uE009>ઉ;" // LETTER U
"\uE00A>ઊ;" // LETTER UU
"\uE00B>ઋ;" // LETTER VOCALIC R
"\uE00C>લૃ;" // REMAP (indicExceptions.txt): ઌ>લૃ = LETTER VOCALIC L>LETTER LA.VOWEL SIGN VOCALIC R
// \uE00F>; // UNMAPPED InterIndic-Gujarati: LETTER EE (એ = LETTER E)
"\uE010>ઐ;" // LETTER AI
// \uE013>; // UNMAPPED InterIndic-Gujarati: LETTER OO (ઓ = LETTER O)
"\uE014>ઔ;" // LETTER AU
"\uE015>ક;" // LETTER KA
"\uE016>ખ;" // LETTER KHA
"\uE017>ગ;" // LETTER GA
"\uE018>ઘ;" // LETTER GHA
"\uE019>ઙ;" // LETTER NGA
"\uE01A>ચ;" // LETTER CA
"\uE01B>છ;" // LETTER CHA
"\uE01C>જ;" // LETTER JA
"\uE01D>ઝ;" // LETTER JHA
"\uE01E>ઞ;" // LETTER NYA
"\uE01F>ટ;" // LETTER TTA
"\uE020>ઠ;" // LETTER TTHA
"\uE021>ડ;" // LETTER DDA
"\uE022>ઢ;" // LETTER DDHA
"\uE023>ણ;" // LETTER NNA
"\uE024>ત;" // LETTER TA
"\uE025>થ;" // LETTER THA
"\uE026>દ;" // LETTER DA
"\uE027>ધ;" // LETTER DHA
"\uE028>ન;" // LETTER NA
"\uE029>ન;" // REMAP (indicExceptions.txt): ઩>ન = LETTER NNNA>LETTER NA
"\uE02A>પ;" // LETTER PA
"\uE02B>ફ;" // LETTER PHA
"\uE02C>બ;" // LETTER BA
"\uE02D>ભ;" // LETTER BHA
"\uE02E>મ;" // LETTER MA
"\uE02F>ય;" // LETTER YA
"\uE030>ર;" // LETTER RA
"\uE032>લ;" // LETTER LA
"\uE033>ળ;" // LETTER LLA
"\uE034>ળ;" // REMAP (indicExceptions.txt): ઴>ળ = LETTER LLLA>LETTER LLA
"\uE035>વ;" // LETTER VA
"\uE036>શ;" // LETTER SHA
"\uE037>ષ;" // LETTER SSA
"\uE038>સ;" // LETTER SA
"\uE039>હ;" // LETTER HA
"\uE03C>઼;" // SIGN NUKTA
"\uE03D>ઽ;" // SIGN AVAGRAHA
"\uE03E>ા;" // VOWEL SIGN AA
"\uE03F>િ;" // VOWEL SIGN I
"\uE040>ી;" // VOWEL SIGN II
"\uE041>ુ;" // VOWEL SIGN U
"\uE042>ૂ;" // VOWEL SIGN UU
"\uE043>ૃ;" // VOWEL SIGN VOCALIC R
"\uE044>ૄ;" // VOWEL SIGN VOCALIC RR
"\uE045>ૅ;" // VOWEL SIGN CANDRA E
// \uE047>; // UNMAPPED InterIndic-Gujarati: VOWEL SIGN EE (ે = VOWEL SIGN E)
"\uE048>ૈ;" // VOWEL SIGN AI
"\uE049>ૉ;" // VOWEL SIGN CANDRA O
// \uE04B>; // UNMAPPED InterIndic-Gujarati: VOWEL SIGN OO (ો = VOWEL SIGN O)
"\uE04C>ૌ;" // VOWEL SIGN AU
"\uE04D>્;" // SIGN VIRAMA
"\uE050>ૐ;" // OM
// \uE055>; // UNMAPPED InterIndic-Gujarati: LENGTH MARK
"\uE056>ૈ;" // REMAP (indicExceptions.txt): ૖>ૈ = AI LENGTH MARK>VOWEL SIGN AI
"\uE057>ૌ;" // REMAP (indicExceptions.txt): ૗>ૌ = AU LENGTH MARK>VOWEL SIGN AU
"\uE059>ખ઼;" // REMAP (indicExceptions.txt): ૙>ખ઼ = LETTER KHHA>LETTER KHA.SIGN NUKTA
"\uE05A>ગ઼;" // REMAP (indicExceptions.txt): ૚>ગ઼ = LETTER GHHA>LETTER GA.SIGN NUKTA
"\uE05B>જ઼;" // REMAP (indicExceptions.txt): ૛>જ઼ = LETTER ZA>LETTER JA.SIGN NUKTA
"\uE05D>ઢ઼;" // REMAP (indicExceptions.txt): ૝>ઢ઼ = LETTER RHA>LETTER DDHA.SIGN NUKTA
"\uE05E>ફ઼;" // REMAP (indicExceptions.txt): ૞>ફ઼ = LETTER FA>LETTER PHA.SIGN NUKTA
"\uE05F>ય઼;" // REMAP (indicExceptions.txt): ૟>ય઼ = LETTER YYA>LETTER YA.SIGN NUKTA
"\uE060>ૠ;" // LETTER VOCALIC RR
"\uE061>લૃ;" // REMAP (indicExceptions.txt): ૡ>લૃ = LETTER VOCALIC LL>LETTER LA.VOWEL SIGN VOCALIC R
"\uE062>િ઼;" // REMAP (indicExceptions.txt): ૢ>િ઼ = VOWEL SIGN VOCALIC L>VOWEL SIGN I.SIGN NUKTA
"\uE063>ી઼;" // REMAP (indicExceptions.txt): ૣ>ી઼ = VOWEL SIGN VOCALIC LL>VOWEL SIGN II.SIGN NUKTA
"\uE066>૦;" // DIGIT ZERO
"\uE067>૧;" // DIGIT ONE
"\uE068>૨;" // DIGIT TWO
"\uE069>૩;" // DIGIT THREE
"\uE06A>૪;" // DIGIT FOUR
"\uE06B>૫;" // DIGIT FIVE
"\uE06C>૬;" // DIGIT SIX
"\uE06D>૭;" // DIGIT SEVEN
"\uE06E>૮;" // DIGIT EIGHT
"\uE06F>૯;" // DIGIT NINE
// \uE080>; // UNMAPPED InterIndic-Gujarati: ISSHAR
"\uE081>એ;" // LETTER E
"\uE082>ઓ;" // LETTER O
// \uE083>; // UNMAPPED InterIndic-Gujarati: LETTER RRA (ઃ = SIGN VISARGA)
"\uE084>ે;" // VOWEL SIGN E
"\uE085>ો;" // VOWEL SIGN O
// eof
}
}

125
icu4c/data/InterIndic_Gurmukhi.txt Normal file
View File

@ -0,0 +1,125 @@
 // -*- Coding: utf-8; -*-
//--------------------------------------------------------------------
// Copyright (c) 1999-2001, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// THIS IS A MACHINE-GENERATED FILE
// Tool: dumpICUrules.bat
// Source: \icu4j\src\com\ibm\text\resources/Transliterator_InterIndic_Gurmukhi.utf8.txt
// Date: Thu Mar 1 20:03:55 2001
//--------------------------------------------------------------------
// InterIndic_Gurmukhi
InterIndic_Gurmukhi {
Rule {
//--------------------------------------------------------------------
// Copyright (c) 1999-2001, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// Date: Tue Jan 23 12:42:00 2001
//--------------------------------------------------------------------
// InterIndic-Gurmukhi
"\uE001>ਂ;" // REMAP (indicExceptions.txt): ਁ>ਂ = SIGN CANDRABINDU>SIGN BINDI
// \uE002>; // UNMAPPED InterIndic-Gurmukhi: SIGN ANUSVARA (ਂ = SIGN BINDI)
// \uE003>; // UNMAPPED InterIndic-Gurmukhi: SIGN VISARGA
"\uE005>ਅ;" // LETTER A
"\uE006>ਆ;" // LETTER AA
"\uE007>ਇ;" // LETTER I
"\uE008>ਈ;" // LETTER II
"\uE009>ਉ;" // LETTER U
"\uE00A>ਊ;" // LETTER UU
"\uE00B>ਰਿ;" // REMAP (indicExceptions.txt): ਋>ਰਿ = LETTER VOCALIC R>LETTER RA.VOWEL SIGN I
"\uE00C>ਇ;" // REMAP (indicExceptions.txt): ਌>ਇ = LETTER VOCALIC L>LETTER I
"\uE00F>ਏ;" // LETTER EE
"\uE010>ਐ;" // LETTER AI
"\uE013>ਓ;" // LETTER OO
"\uE014>ਔ;" // LETTER AU
"\uE015>ਕ;" // LETTER KA
"\uE016>ਖ;" // LETTER KHA
"\uE017>ਗ;" // LETTER GA
"\uE018>ਘ;" // LETTER GHA
"\uE019>ਙ;" // LETTER NGA
"\uE01A>ਚ;" // LETTER CA
"\uE01B>ਛ;" // LETTER CHA
"\uE01C>ਜ;" // LETTER JA
"\uE01D>ਝ;" // LETTER JHA
"\uE01E>ਞ;" // LETTER NYA
"\uE01F>ਟ;" // LETTER TTA
"\uE020>ਠ;" // LETTER TTHA
"\uE021>ਡ;" // LETTER DDA
"\uE022>ਢ;" // LETTER DDHA
"\uE023>ਣ;" // LETTER NNA
"\uE024>ਤ;" // LETTER TA
"\uE025>ਥ;" // LETTER THA
"\uE026>ਦ;" // LETTER DA
"\uE027>ਧ;" // LETTER DHA
"\uE028>ਨ;" // LETTER NA
"\uE029>ਨ;" // REMAP (indicExceptions.txt): ਩>ਨ = LETTER NNNA>LETTER NA
"\uE02A>ਪ;" // LETTER PA
"\uE02B>ਫ;" // LETTER PHA
"\uE02C>ਬ;" // LETTER BA
"\uE02D>ਭ;" // LETTER BHA
"\uE02E>ਮ;" // LETTER MA
"\uE02F>ਯ;" // LETTER YA
"\uE030>ਰ;" // LETTER RA
"\uE032>ਲ;" // LETTER LA
"\uE033>ਲ਼;" // LETTER LLA
"\uE034>ਲ਼;" // REMAP (indicExceptions.txt): ਴>ਲ਼ = LETTER LLLA>LETTER LLA
"\uE035>ਵ;" // LETTER VA
"\uE036>ਸ਼;" // LETTER SHA
"\uE037>ਸ਼;" // REMAP (indicExceptions.txt): ਷>ਸ਼ = LETTER SSA>LETTER SHA
"\uE038>ਸ;" // LETTER SA
"\uE039>ਹ;" // LETTER HA
"\uE03C>਼;" // SIGN NUKTA
// \uE03D>; // UNMAPPED InterIndic-Gurmukhi: SIGN AVAGRAHA
"\uE03E>ਾ;" // VOWEL SIGN AA
"\uE03F>ਿ;" // VOWEL SIGN I
"\uE040>ੀ;" // VOWEL SIGN II
"\uE041>ੁ;" // VOWEL SIGN U
"\uE042>ੂ;" // VOWEL SIGN UU
// \uE043>; // UNMAPPED InterIndic-Gurmukhi: VOWEL SIGN VOCALIC R
// \uE044>; // UNMAPPED InterIndic-Gurmukhi: VOWEL SIGN VOCALIC RR
"\uE045>ੈ;" // REMAP (indicExceptions.txt): ੅>ੈ = VOWEL SIGN CANDRA E>VOWEL SIGN AI
"\uE047>ੇ;" // VOWEL SIGN EE
"\uE048>ੈ;" // VOWEL SIGN AI
"\uE049>ੌ;" // REMAP (indicExceptions.txt): ੉>ੌ = VOWEL SIGN CANDRA O>VOWEL SIGN AU
"\uE04B>ੋ;" // VOWEL SIGN OO
"\uE04C>ੌ;" // VOWEL SIGN AU
"\uE04D>੍;" // SIGN VIRAMA
// \uE050>; // UNMAPPED InterIndic-Gurmukhi: OM
// \uE055>; // UNMAPPED InterIndic-Gurmukhi: LENGTH MARK
"\uE056>ੈ;" // REMAP (indicExceptions.txt): ੖>ੈ = AI LENGTH MARK>VOWEL SIGN AI
"\uE057>ੌ;" // REMAP (indicExceptions.txt): ੗>ੌ = AU LENGTH MARK>VOWEL SIGN AU
"\uE059>ਖ਼;" // LETTER KHHA
"\uE05A>ਗ਼;" // LETTER GHHA
"\uE05B>ਜ਼;" // LETTER ZA
"\uE05D>ਢ਼;" // REMAP (indicExceptions.txt): ੝>ਢ਼ = LETTER RHA>LETTER DDHA.SIGN NUKTA
"\uE05E>ਫ਼;" // LETTER FA
"\uE05F>ਯ;" // REMAP (indicExceptions.txt): ੟>ਯ = LETTER YYA>LETTER YA
"\uE060>ਰਿ;" // REMAP (indicExceptions.txt): ੠>ਰਿ = LETTER VOCALIC RR>LETTER RA.VOWEL SIGN I
"\uE061>ਈ਼;" // REMAP (indicExceptions.txt): ੡>ਈ਼ = LETTER VOCALIC LL>LETTER II.SIGN NUKTA
"\uE062>ਿ਼;" // REMAP (indicExceptions.txt): ੢>ਿ਼ = VOWEL SIGN VOCALIC L>VOWEL SIGN I.SIGN NUKTA
"\uE063>ੀ਼;" // REMAP (indicExceptions.txt): ੣>ੀ਼ = VOWEL SIGN VOCALIC LL>VOWEL SIGN II.SIGN NUKTA
"\uE066>੦;" // DIGIT ZERO
"\uE067>੧;" // DIGIT ONE
"\uE068>੨;" // DIGIT TWO
"\uE069>੩;" // DIGIT THREE
"\uE06A>੪;" // DIGIT FOUR
"\uE06B>੫;" // DIGIT FIVE
"\uE06C>੬;" // DIGIT SIX
"\uE06D>੭;" // DIGIT SEVEN
"\uE06E>੮;" // DIGIT EIGHT
"\uE06F>੯;" // DIGIT NINE
// \uE080>; // UNMAPPED InterIndic-Gurmukhi: ISSHAR
// \uE081>; // UNMAPPED InterIndic-Gurmukhi: LETTER E
// \uE082>; // UNMAPPED InterIndic-Gurmukhi: LETTER O (ਂ = SIGN BINDI)
"\uE083>ੜ;" // LETTER RRA
// \uE084>; // UNMAPPED InterIndic-Gurmukhi: VOWEL SIGN E
// \uE085>; // UNMAPPED InterIndic-Gurmukhi: VOWEL SIGN O (ਅ = LETTER A)
// eof
}
}

125
icu4c/data/InterIndic_Kannada.txt Normal file
View File

@ -0,0 +1,125 @@
 // -*- Coding: utf-8; -*-
//--------------------------------------------------------------------
// Copyright (c) 1999-2001, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// THIS IS A MACHINE-GENERATED FILE
// Tool: dumpICUrules.bat
// Source: \icu4j\src\com\ibm\text\resources/Transliterator_InterIndic_Kannada.utf8.txt
// Date: Thu Mar 1 20:03:55 2001
//--------------------------------------------------------------------
// InterIndic_Kannada
InterIndic_Kannada {
Rule {
//--------------------------------------------------------------------
// Copyright (c) 1999-2001, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// Date: Tue Jan 23 12:42:00 2001
//--------------------------------------------------------------------
// InterIndic-Kannada
"\uE001>ಂ;" // REMAP (indicExceptions.txt): ಁ>ಂ = SIGN CANDRABINDU>SIGN ANUSVARA
"\uE002>ಂ;" // SIGN ANUSVARA
"\uE003>ಃ;" // SIGN VISARGA
"\uE005>ಅ;" // LETTER A
"\uE006>ಆ;" // LETTER AA
"\uE007>ಇ;" // LETTER I
"\uE008>ಈ;" // LETTER II
"\uE009>ಉ;" // LETTER U
"\uE00A>ಊ;" // LETTER UU
"\uE00B>ಋ;" // LETTER VOCALIC R
"\uE00C>ಌ;" // LETTER VOCALIC L
"\uE00F>ಏ;" // LETTER EE
"\uE010>ಐ;" // LETTER AI
"\uE013>ಓ;" // LETTER OO
"\uE014>ಔ;" // LETTER AU
"\uE015>ಕ;" // LETTER KA
"\uE016>ಖ;" // LETTER KHA
"\uE017>ಗ;" // LETTER GA
"\uE018>ಘ;" // LETTER GHA
"\uE019>ಙ;" // LETTER NGA
"\uE01A>ಚ;" // LETTER CA
"\uE01B>ಛ;" // LETTER CHA
"\uE01C>ಜ;" // LETTER JA
"\uE01D>ಝ;" // LETTER JHA
"\uE01E>ಞ;" // LETTER NYA
"\uE01F>ಟ;" // LETTER TTA
"\uE020>ಠ;" // LETTER TTHA
"\uE021>ಡ;" // LETTER DDA
"\uE022>ಢ;" // LETTER DDHA
"\uE023>ಣ;" // LETTER NNA
"\uE024>ತ;" // LETTER TA
"\uE025>ಥ;" // LETTER THA
"\uE026>ದ;" // LETTER DA
"\uE027>ಧ;" // LETTER DHA
"\uE028>ನ;" // LETTER NA
"\uE029>ನ;" // REMAP (indicExceptions.txt): ಩>ನ = LETTER NNNA>LETTER NA
"\uE02A>ಪ;" // LETTER PA
"\uE02B>ಫ;" // LETTER PHA
"\uE02C>ಬ;" // LETTER BA
"\uE02D>ಭ;" // LETTER BHA
"\uE02E>ಮ;" // LETTER MA
"\uE02F>ಯ;" // LETTER YA
"\uE030>ರ;" // LETTER RA
"\uE032>ಲ;" // LETTER LA
"\uE033>ಳ;" // LETTER LLA
"\uE034>ಳ;" // REMAP (indicExceptions.txt): ಴>ಳ = LETTER LLLA>LETTER LLA
"\uE035>ವ;" // LETTER VA
"\uE036>ಶ;" // LETTER SHA
"\uE037>ಷ;" // LETTER SSA
"\uE038>ಸ;" // LETTER SA
"\uE039>ಹ;" // LETTER HA
// \uE03C>; // UNMAPPED InterIndic-Kannada: SIGN NUKTA
// \uE03D>; // UNMAPPED InterIndic-Kannada: SIGN AVAGRAHA
"\uE03E>ಾ;" // VOWEL SIGN AA
"\uE03F>ಿ;" // VOWEL SIGN I
"\uE040>ೀ;" // VOWEL SIGN II
"\uE041>ು;" // VOWEL SIGN U
"\uE042>ೂ;" // VOWEL SIGN UU
"\uE043>ೃ;" // VOWEL SIGN VOCALIC R
"\uE044>ೄ;" // VOWEL SIGN VOCALIC RR
"\uE045>ೆ;" // REMAP (indicExceptions.txt): ೅>ೆ = VOWEL SIGN CANDRA E>VOWEL SIGN E
"\uE047>ೇ;" // VOWEL SIGN EE
"\uE048>ೈ;" // VOWEL SIGN AI
"\uE049>ೊ;" // REMAP (indicExceptions.txt): ೉>ೊ = VOWEL SIGN CANDRA O>VOWEL SIGN O
"\uE04B>ೋ;" // VOWEL SIGN OO
"\uE04C>ೌ;" // VOWEL SIGN AU
"\uE04D>್;" // SIGN VIRAMA
"\uE050>ಓಂ;" // REMAP (indicExceptions.txt): ೐>ಓಂ = OM>LETTER OO.SIGN ANUSVARA
"\uE055>ೕ;" // LENGTH MARK
"\uE056>ೖ;" // AI LENGTH MARK
"\uE057>ೌ;" // REMAP (indicExceptions.txt): ೗>ೌ = AU LENGTH MARK>VOWEL SIGN AU
"\uE059>ಖ;" // REMAP (indicExceptions.txt): ೙>ಖ = LETTER KHHA>LETTER KHA
"\uE05A>ಗ;" // REMAP (indicExceptions.txt): ೚>ಗ = LETTER GHHA>LETTER GA
"\uE05B>ಜ;" // REMAP (indicExceptions.txt): ೛>ಜ = LETTER ZA>LETTER JA
"\uE05D>ಢ;" // REMAP (indicExceptions.txt): ೝ>ಢ = LETTER RHA>LETTER DDHA
"\uE05E>ೞ;" // LETTER FA
"\uE05F>ಯ;" // REMAP (indicExceptions.txt): ೟>ಯ = LETTER YYA>LETTER YA
"\uE060>ೠ;" // LETTER VOCALIC RR
"\uE061>ೡ;" // LETTER VOCALIC LL
"\uE062>ಿ;" // REMAP (indicExceptions.txt): ೢ>ಿ = VOWEL SIGN VOCALIC L>VOWEL SIGN I
"\uE063>ೀ;" // REMAP (indicExceptions.txt): ೣ>ೀ = VOWEL SIGN VOCALIC LL>VOWEL SIGN II
"\uE066>೦;" // DIGIT ZERO
"\uE067>೧;" // DIGIT ONE
"\uE068>೨;" // DIGIT TWO
"\uE069>೩;" // DIGIT THREE
"\uE06A>೪;" // DIGIT FOUR
"\uE06B>೫;" // DIGIT FIVE
"\uE06C>೬;" // DIGIT SIX
"\uE06D>೭;" // DIGIT SEVEN
"\uE06E>೮;" // DIGIT EIGHT
"\uE06F>೯;" // DIGIT NINE
// \uE080>; // UNMAPPED InterIndic-Kannada: ISSHAR
"\uE081>ಎ;" // LETTER E
"\uE082>ಒ;" // LETTER O
"\uE083>ಱ;" // LETTER RRA
"\uE084>ೆ;" // VOWEL SIGN E
"\uE085>ೊ;" // VOWEL SIGN O
// eof
}
}

125
icu4c/data/InterIndic_Malayalam.txt Normal file
View File

@ -0,0 +1,125 @@
 // -*- Coding: utf-8; -*-
//--------------------------------------------------------------------
// Copyright (c) 1999-2001, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// THIS IS A MACHINE-GENERATED FILE
// Tool: dumpICUrules.bat
// Source: \icu4j\src\com\ibm\text\resources/Transliterator_InterIndic_Malayalam.utf8.txt
// Date: Thu Mar 1 20:03:55 2001
//--------------------------------------------------------------------
// InterIndic_Malayalam
InterIndic_Malayalam {
Rule {
//--------------------------------------------------------------------
// Copyright (c) 1999-2001, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// Date: Tue Jan 23 12:42:00 2001
//--------------------------------------------------------------------
// InterIndic-Malayalam
"\uE001>ം;" // REMAP (indicExceptions.txt): ഁ>ം = SIGN CANDRABINDU>SIGN ANUSVARA
"\uE002>ം;" // SIGN ANUSVARA
"\uE003>ഃ;" // SIGN VISARGA
"\uE005>അ;" // LETTER A
"\uE006>ആ;" // LETTER AA
"\uE007>ഇ;" // LETTER I
"\uE008>ഈ;" // LETTER II
"\uE009>ഉ;" // LETTER U
"\uE00A>ഊ;" // LETTER UU
"\uE00B>ഋ;" // LETTER VOCALIC R
"\uE00C>ഌ;" // LETTER VOCALIC L
"\uE00F>ഏ;" // LETTER EE
"\uE010>ഐ;" // LETTER AI
"\uE013>ഓ;" // LETTER OO
"\uE014>ഔ;" // LETTER AU
"\uE015>ക;" // LETTER KA
"\uE016>ഖ;" // LETTER KHA
"\uE017>ഗ;" // LETTER GA
"\uE018>ഘ;" // LETTER GHA
"\uE019>ങ;" // LETTER NGA
"\uE01A>ച;" // LETTER CA
"\uE01B>ഛ;" // LETTER CHA
"\uE01C>ജ;" // LETTER JA
"\uE01D>ഝ;" // LETTER JHA
"\uE01E>ഞ;" // LETTER NYA
"\uE01F>ട;" // LETTER TTA
"\uE020>ഠ;" // LETTER TTHA
"\uE021>ഡ;" // LETTER DDA
"\uE022>ഢ;" // LETTER DDHA
"\uE023>ണ;" // LETTER NNA
"\uE024>ത;" // LETTER TA
"\uE025>ഥ;" // LETTER THA
"\uE026>ദ;" // LETTER DA
"\uE027>ധ;" // LETTER DHA
"\uE028>ന;" // LETTER NA
"\uE029>ന;" // REMAP (indicExceptions.txt): ഩ>ന = LETTER NNNA>LETTER NA
"\uE02A>പ;" // LETTER PA
"\uE02B>ഫ;" // LETTER PHA
"\uE02C>ബ;" // LETTER BA
"\uE02D>ഭ;" // LETTER BHA
"\uE02E>മ;" // LETTER MA
"\uE02F>യ;" // LETTER YA
"\uE030>ര;" // LETTER RA
"\uE032>ല;" // LETTER LA
"\uE033>ള;" // LETTER LLA
"\uE034>ഴ;" // LETTER LLLA
"\uE035>വ;" // LETTER VA
"\uE036>ശ;" // LETTER SHA
"\uE037>ഷ;" // LETTER SSA
"\uE038>സ;" // LETTER SA
"\uE039>ഹ;" // LETTER HA
// \uE03C>; // UNMAPPED InterIndic-Malayalam: SIGN NUKTA
// \uE03D>; // UNMAPPED InterIndic-Malayalam: SIGN AVAGRAHA
"\uE03E>ാ;" // VOWEL SIGN AA
"\uE03F>ി;" // VOWEL SIGN I
"\uE040>ീ;" // VOWEL SIGN II
"\uE041>ു;" // VOWEL SIGN U
"\uE042>ൂ;" // VOWEL SIGN UU
"\uE043>ൃ;" // VOWEL SIGN VOCALIC R
// \uE044>; // UNMAPPED InterIndic-Malayalam: VOWEL SIGN VOCALIC RR
"\uE045>ാ;" // REMAP (indicExceptions.txt): ൅>ാ = VOWEL SIGN CANDRA E>VOWEL SIGN AA
"\uE047>േ;" // VOWEL SIGN EE
"\uE048>ൈ;" // VOWEL SIGN AI
"\uE049>ോ;" // REMAP (indicExceptions.txt): ൉>ോ = VOWEL SIGN CANDRA O>VOWEL SIGN OO
"\uE04B>ോ;" // VOWEL SIGN OO
"\uE04C>ൌ;" // VOWEL SIGN AU
"\uE04D>്;" // SIGN VIRAMA
// \uE050>; // UNMAPPED InterIndic-Malayalam: OM
// \uE055>; // UNMAPPED InterIndic-Malayalam: LENGTH MARK
"\uE056>ൈ;" // REMAP (indicExceptions.txt): ൖ>ൈ = AI LENGTH MARK>VOWEL SIGN AI
"\uE057>ൗ;" // AU LENGTH MARK
"\uE059>ഖ;" // REMAP (indicExceptions.txt): ൙>ഖ = LETTER KHHA>LETTER KHA
"\uE05A>ഗ;" // REMAP (indicExceptions.txt): ൚>ഗ = LETTER GHHA>LETTER GA
"\uE05B>ജ;" // REMAP (indicExceptions.txt): ൛>ജ = LETTER ZA>LETTER JA
"\uE05D>ഢ;" // REMAP (indicExceptions.txt): ൝>ഢ = LETTER RHA>LETTER DDHA
"\uE05E>ഫ;" // REMAP (indicExceptions.txt): ൞>ഫ = LETTER FA>LETTER PHA
"\uE05F>യ;" // REMAP (indicExceptions.txt): ൟ>യ = LETTER YYA>LETTER YA
"\uE060>ൠ;" // LETTER VOCALIC RR
"\uE061>ൡ;" // LETTER VOCALIC LL
// \uE062>; // UNMAPPED InterIndic-Malayalam: VOWEL SIGN VOCALIC L
// \uE063>; // UNMAPPED InterIndic-Malayalam: VOWEL SIGN VOCALIC LL
"\uE066>൦;" // DIGIT ZERO
"\uE067>൧;" // DIGIT ONE
"\uE068>൨;" // DIGIT TWO
"\uE069>൩;" // DIGIT THREE
"\uE06A>൪;" // DIGIT FOUR
"\uE06B>൫;" // DIGIT FIVE
"\uE06C>൬;" // DIGIT SIX
"\uE06D>൭;" // DIGIT SEVEN
"\uE06E>൮;" // DIGIT EIGHT
"\uE06F>൯;" // DIGIT NINE
// \uE080>; // UNMAPPED InterIndic-Malayalam: ISSHAR
"\uE081>എ;" // LETTER E
"\uE082>ഒ;" // LETTER O
"\uE083>റ;" // LETTER RRA
"\uE084>െ;" // VOWEL SIGN E
"\uE085>ൊ;" // VOWEL SIGN O
// eof
}
}

125
icu4c/data/InterIndic_Oriya.txt Normal file
View File

@ -0,0 +1,125 @@
 // -*- Coding: utf-8; -*-
//--------------------------------------------------------------------
// Copyright (c) 1999-2001, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// THIS IS A MACHINE-GENERATED FILE
// Tool: dumpICUrules.bat
// Source: \icu4j\src\com\ibm\text\resources/Transliterator_InterIndic_Oriya.utf8.txt
// Date: Thu Mar 1 20:03:55 2001
//--------------------------------------------------------------------
// InterIndic_Oriya
InterIndic_Oriya {
Rule {
//--------------------------------------------------------------------
// Copyright (c) 1999-2001, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// Date: Tue Jan 23 12:42:01 2001
//--------------------------------------------------------------------
// InterIndic-Oriya
"\uE001>ଁ;" // SIGN CANDRABINDU
"\uE002>ଂ;" // SIGN ANUSVARA
"\uE003>ଃ;" // SIGN VISARGA
"\uE005>ଅ;" // LETTER A
"\uE006>ଆ;" // LETTER AA
"\uE007>ଇ;" // LETTER I
"\uE008>ଈ;" // LETTER II
"\uE009>ଉ;" // LETTER U
"\uE00A>ଊ;" // LETTER UU
"\uE00B>ଋ;" // LETTER VOCALIC R
"\uE00C>ଌ;" // LETTER VOCALIC L
// \uE00F>; // UNMAPPED InterIndic-Oriya: LETTER EE (ଏ = LETTER E)
"\uE010>ଐ;" // LETTER AI
// \uE013>; // UNMAPPED InterIndic-Oriya: LETTER OO (ଓ = LETTER O)
"\uE014>ଔ;" // LETTER AU
"\uE015>କ;" // LETTER KA
"\uE016>ଖ;" // LETTER KHA
"\uE017>ଗ;" // LETTER GA
"\uE018>ଘ;" // LETTER GHA
"\uE019>ଙ;" // LETTER NGA
"\uE01A>ଚ;" // LETTER CA
"\uE01B>ଛ;" // LETTER CHA
"\uE01C>ଜ;" // LETTER JA
"\uE01D>ଝ;" // LETTER JHA
"\uE01E>ଞ;" // LETTER NYA
"\uE01F>ଟ;" // LETTER TTA
"\uE020>ଠ;" // LETTER TTHA
"\uE021>ଡ;" // LETTER DDA
"\uE022>ଢ;" // LETTER DDHA
"\uE023>ଣ;" // LETTER NNA
"\uE024>ତ;" // LETTER TA
"\uE025>ଥ;" // LETTER THA
"\uE026>ଦ;" // LETTER DA
"\uE027>ଧ;" // LETTER DHA
"\uE028>ନ;" // LETTER NA
"\uE029>ନ;" // REMAP (indicExceptions.txt): ଩>ନ = LETTER NNNA>LETTER NA
"\uE02A>ପ;" // LETTER PA
"\uE02B>ଫ;" // LETTER PHA
"\uE02C>ବ;" // LETTER BA
"\uE02D>ଭ;" // LETTER BHA
"\uE02E>ମ;" // LETTER MA
"\uE02F>ଯ;" // LETTER YA
"\uE030>ର;" // LETTER RA
"\uE032>ଲ;" // LETTER LA
"\uE033>ଳ;" // LETTER LLA
"\uE034>ଳ;" // REMAP (indicExceptions.txt): ଴>ଳ = LETTER LLLA>LETTER LLA
"\uE035>ବ;" // REMAP (indicExceptions.txt): ଵ>ବ = LETTER VA>LETTER BA
"\uE036>ଶ;" // LETTER SHA
"\uE037>ଷ;" // LETTER SSA
"\uE038>ସ;" // LETTER SA
"\uE039>ହ;" // LETTER HA
"\uE03C>଼;" // SIGN NUKTA
"\uE03D>ଽ;" // SIGN AVAGRAHA
"\uE03E>ା;" // VOWEL SIGN AA
"\uE03F>ି;" // VOWEL SIGN I
"\uE040>ୀ;" // VOWEL SIGN II
"\uE041>ୁ;" // VOWEL SIGN U
"\uE042>ୂ;" // VOWEL SIGN UU
"\uE043>ୃ;" // VOWEL SIGN VOCALIC R
"\uE044>ୃ଼;" // REMAP (indicExceptions.txt): ୄ>ୃ଼ = VOWEL SIGN VOCALIC RR>VOWEL SIGN VOCALIC R.SIGN NUKTA
"\uE045>େ;" // REMAP (indicExceptions.txt): ୅>େ = VOWEL SIGN CANDRA E>VOWEL SIGN E
// \uE047>; // UNMAPPED InterIndic-Oriya: VOWEL SIGN EE (େ = VOWEL SIGN E)
"\uE048>ୈ;" // VOWEL SIGN AI
"\uE049>ୋ;" // REMAP (indicExceptions.txt): ୉>ୋ = VOWEL SIGN CANDRA O>VOWEL SIGN O
// \uE04B>; // UNMAPPED InterIndic-Oriya: VOWEL SIGN OO (ୋ = VOWEL SIGN O)
"\uE04C>ୌ;" // VOWEL SIGN AU
"\uE04D>୍;" // SIGN VIRAMA
"\uE050>ଓଁ;" // REMAP (indicExceptions.txt): ୐>ଓଁ = OM>LETTER O.SIGN CANDRABINDU
// \uE055>; // UNMAPPED InterIndic-Oriya: LENGTH MARK
"\uE056>ୖ;" // AI LENGTH MARK
"\uE057>ୗ;" // AU LENGTH MARK
"\uE059>ଖ଼;" // REMAP (indicExceptions.txt): ୙>ଖ଼ = LETTER KHHA>LETTER KHA.SIGN NUKTA
"\uE05A>ଗ଼;" // REMAP (indicExceptions.txt): ୚>ଗ଼ = LETTER GHHA>LETTER GA.SIGN NUKTA
"\uE05B>ଜ଼;" // REMAP (indicExceptions.txt): ୛>ଜ଼ = LETTER ZA>LETTER JA.SIGN NUKTA
"\uE05D>ଢ଼;" // LETTER RHA
"\uE05E>ଫ଼;" // REMAP (indicExceptions.txt): ୞>ଫ଼ = LETTER FA>LETTER PHA.SIGN NUKTA
"\uE05F>ୟ;" // LETTER YYA
"\uE060>ୠ;" // LETTER VOCALIC RR
"\uE061>ୡ;" // LETTER VOCALIC LL
"\uE062>ୖ଼;" // REMAP (indicExceptions.txt): ୢ>ୖ଼ = VOWEL SIGN VOCALIC L>AI LENGTH MARK.SIGN NUKTA
"\uE063>ୗ଼;" // REMAP (indicExceptions.txt): ୣ>ୗ଼ = VOWEL SIGN VOCALIC LL>AU LENGTH MARK.SIGN NUKTA
"\uE066>୦;" // DIGIT ZERO
"\uE067>୧;" // DIGIT ONE
"\uE068>୨;" // DIGIT TWO
"\uE069>୩;" // DIGIT THREE
"\uE06A>୪;" // DIGIT FOUR
"\uE06B>୫;" // DIGIT FIVE
"\uE06C>୬;" // DIGIT SIX
"\uE06D>୭;" // DIGIT SEVEN
"\uE06E>୮;" // DIGIT EIGHT
"\uE06F>୯;" // DIGIT NINE
"\uE080>୰;" // ISSHAR
"\uE081>ଏ;" // LETTER E
"\uE082>ଓ;" // LETTER O
"\uE083>ଡ଼;" // LETTER RRA
"\uE084>େ;" // VOWEL SIGN E
"\uE085>ୋ;" // VOWEL SIGN O
// eof
}
}

125
icu4c/data/InterIndic_Tamil.txt Normal file
View File

@ -0,0 +1,125 @@
 // -*- Coding: utf-8; -*-
//--------------------------------------------------------------------
// Copyright (c) 1999-2001, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// THIS IS A MACHINE-GENERATED FILE
// Tool: dumpICUrules.bat
// Source: \icu4j\src\com\ibm\text\resources/Transliterator_InterIndic_Tamil.utf8.txt
// Date: Thu Mar 1 20:03:55 2001
//--------------------------------------------------------------------
// InterIndic_Tamil
InterIndic_Tamil {
Rule {
//--------------------------------------------------------------------
// Copyright (c) 1999-2001, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// Date: Tue Jan 23 12:42:01 2001
//--------------------------------------------------------------------
// InterIndic-Tamil
// \uE001>; // UNMAPPED InterIndic-Tamil: SIGN CANDRABINDU
"\uE002>ஂ;" // SIGN ANUSVARA
"\uE003>ஃ;" // SIGN VISARGA
"\uE005>அ;" // LETTER A
"\uE006>ஆ;" // LETTER AA
"\uE007>இ;" // LETTER I
"\uE008>ஈ;" // LETTER II
"\uE009>உ;" // LETTER U
"\uE00A>ஊ;" // LETTER UU
"\uE00B>ரி;" // REMAP (indicExceptions.txt): ஋>ரி = LETTER VOCALIC R>LETTER RA.VOWEL SIGN I
"\uE00C>இ;" // REMAP (indicExceptions.txt): ஌>இ = LETTER VOCALIC L>LETTER I
"\uE00F>ஏ;" // LETTER EE
"\uE010>ஐ;" // LETTER AI
"\uE013>ஓ;" // LETTER OO
"\uE014>ஔ;" // LETTER AU
"\uE015>க;" // LETTER KA
"\uE016>க;" // REMAP (indicExceptions.txt): ஖>க = LETTER KHA>LETTER KA
"\uE017>க;" // REMAP (indicExceptions.txt): ஗>க = LETTER GA>LETTER KA
"\uE018>க;" // REMAP (indicExceptions.txt): ஘>க = LETTER GHA>LETTER KA
"\uE019>ங;" // LETTER NGA
"\uE01A>ச;" // LETTER CA
"\uE01B>ச;" // REMAP (indicExceptions.txt): ஛>ச = LETTER CHA>LETTER CA
"\uE01C>ஜ;" // LETTER JA
"\uE01D>ச;" // REMAP (indicExceptions.txt): ஝>ச = LETTER JHA>LETTER CA
"\uE01E>ஞ;" // LETTER NYA
"\uE01F>ட;" // LETTER TTA
"\uE020>ட;" // REMAP (indicExceptions.txt): ஠>ட = LETTER TTHA>LETTER TTA
"\uE021>ட;" // REMAP (indicExceptions.txt): ஡>ட = LETTER DDA>LETTER TTA
"\uE022>ட;" // REMAP (indicExceptions.txt): ஢>ட = LETTER DDHA>LETTER TTA
"\uE023>ண;" // LETTER NNA
"\uE024>த;" // LETTER TA
"\uE025>த;" // REMAP (indicExceptions.txt): ஥>த = LETTER THA>LETTER TA
"\uE026>த;" // REMAP (indicExceptions.txt): ஦>த = LETTER DA>LETTER TA
"\uE027>த;" // REMAP (indicExceptions.txt): ஧>த = LETTER DHA>LETTER TA
"\uE028>ந;" // LETTER NA
"\uE029>ன;" // LETTER NNNA
"\uE02A>ப;" // LETTER PA
"\uE02B>ப;" // REMAP (indicExceptions.txt): ஫>ப = LETTER PHA>LETTER PA
"\uE02C>ப;" // REMAP (indicExceptions.txt): ஬>ப = LETTER BA>LETTER PA
"\uE02D>ப;" // REMAP (indicExceptions.txt): ஭>ப = LETTER BHA>LETTER PA
"\uE02E>ம;" // LETTER MA
"\uE02F>ய;" // LETTER YA
"\uE030>ர;" // LETTER RA
"\uE032>ல;" // LETTER LA
"\uE033>ள;" // LETTER LLA
"\uE034>ழ;" // LETTER LLLA
"\uE035>வ;" // LETTER VA
"\uE036>ஷ;" // REMAP (indicExceptions.txt): ஶ>ஷ = LETTER SHA>LETTER SSA
"\uE037>ஷ;" // LETTER SSA
"\uE038>ஸ;" // LETTER SA
"\uE039>ஹ;" // LETTER HA
// \uE03C>; // UNMAPPED InterIndic-Tamil: SIGN NUKTA
// \uE03D>; // UNMAPPED InterIndic-Tamil: SIGN AVAGRAHA
"\uE03E>ா;" // VOWEL SIGN AA
"\uE03F>ி;" // VOWEL SIGN I
"\uE040>ீ;" // VOWEL SIGN II
"\uE041>ு;" // VOWEL SIGN U
"\uE042>ூ;" // VOWEL SIGN UU
"\uE043>்ரி;" // REMAP (indicExceptions.txt): ௃>்ரி = VOWEL SIGN VOCALIC R>SIGN VIRAMA.LETTER RA.VOWEL SIGN I
"\uE044>்ரி;" // REMAP (indicExceptions.txt): ௄>்ரி = VOWEL SIGN VOCALIC RR>SIGN VIRAMA.LETTER RA.VOWEL SIGN I
"\uE045>ா;" // REMAP (indicExceptions.txt): ௅>ா = VOWEL SIGN CANDRA E>VOWEL SIGN AA
"\uE047>ே;" // VOWEL SIGN EE
"\uE048>ை;" // VOWEL SIGN AI
"\uE049>ா;" // REMAP (indicExceptions.txt): ௉>ா = VOWEL SIGN CANDRA O>VOWEL SIGN AA
"\uE04B>ோ;" // VOWEL SIGN OO
"\uE04C>ௌ;" // VOWEL SIGN AU
"\uE04D>்;" // SIGN VIRAMA
"\uE050>ஓம்;" // REMAP (indicExceptions.txt): ௐ>ஓம் = OM>LETTER OO.LETTER MA.SIGN VIRAMA
// \uE055>; // UNMAPPED InterIndic-Tamil: LENGTH MARK
"\uE056>ை;" // REMAP (indicExceptions.txt): ௖>ை = AI LENGTH MARK>VOWEL SIGN AI
"\uE057>ௗ;" // AU LENGTH MARK
"\uE059>க;" // REMAP (indicExceptions.txt): ௙>க = LETTER KHHA>LETTER KA
"\uE05A>க;" // REMAP (indicExceptions.txt): ௚>க = LETTER GHHA>LETTER KA
"\uE05B>ஜ;" // REMAP (indicExceptions.txt): ௛>ஜ = LETTER ZA>LETTER JA
"\uE05D>ட;" // REMAP (indicExceptions.txt): ௝>ட = LETTER RHA>LETTER TTA
"\uE05E>ப;" // REMAP (indicExceptions.txt): ௞>ப = LETTER FA>LETTER PA
"\uE05F>ய;" // REMAP (indicExceptions.txt): ௟>ய = LETTER YYA>LETTER YA
"\uE060>ரி;" // REMAP (indicExceptions.txt): ௠>ரி = LETTER VOCALIC RR>LETTER RA.VOWEL SIGN I
"\uE061>ஈ;" // REMAP (indicExceptions.txt): ௡>ஈ = LETTER VOCALIC LL>LETTER II
// \uE062>; // UNMAPPED InterIndic-Tamil: VOWEL SIGN VOCALIC L
// \uE063>; // UNMAPPED InterIndic-Tamil: VOWEL SIGN VOCALIC LL
// \uE066>; // UNMAPPED InterIndic-Tamil: DIGIT ZERO
"\uE067>௧;" // DIGIT ONE
"\uE068>௨;" // DIGIT TWO
"\uE069>௩;" // DIGIT THREE
"\uE06A>௪;" // DIGIT FOUR
"\uE06B>௫;" // DIGIT FIVE
"\uE06C>௬;" // DIGIT SIX
"\uE06D>௭;" // DIGIT SEVEN
"\uE06E>௮;" // DIGIT EIGHT
"\uE06F>௯;" // DIGIT NINE
// \uE080>; // UNMAPPED InterIndic-Tamil: ISSHAR
"\uE081>எ;" // LETTER E
"\uE082>ஒ;" // LETTER O
"\uE083>ற;" // LETTER RRA
"\uE084>ெ;" // VOWEL SIGN E
"\uE085>ொ;" // VOWEL SIGN O
// eof
}
}

125
icu4c/data/InterIndic_Telugu.txt Normal file
View File

@ -0,0 +1,125 @@
 // -*- Coding: utf-8; -*-
//--------------------------------------------------------------------
// Copyright (c) 1999-2001, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// THIS IS A MACHINE-GENERATED FILE
// Tool: dumpICUrules.bat
// Source: \icu4j\src\com\ibm\text\resources/Transliterator_InterIndic_Telugu.utf8.txt
// Date: Thu Mar 1 20:03:55 2001
//--------------------------------------------------------------------
// InterIndic_Telugu
InterIndic_Telugu {
Rule {
//--------------------------------------------------------------------
// Copyright (c) 1999-2001, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// Date: Tue Jan 23 12:42:01 2001
//--------------------------------------------------------------------
// InterIndic-Telugu
"\uE001>ఁ;" // SIGN CANDRABINDU
"\uE002>ం;" // SIGN ANUSVARA
"\uE003>ః;" // SIGN VISARGA
"\uE005>అ;" // LETTER A
"\uE006>ఆ;" // LETTER AA
"\uE007>ఇ;" // LETTER I
"\uE008>ఈ;" // LETTER II
"\uE009>ఉ;" // LETTER U
"\uE00A>ఊ;" // LETTER UU
"\uE00B>ఋ;" // LETTER VOCALIC R
"\uE00C>ఌ;" // LETTER VOCALIC L
"\uE00F>ఏ;" // LETTER EE
"\uE010>ఐ;" // LETTER AI
"\uE013>ఓ;" // LETTER OO
"\uE014>ఔ;" // LETTER AU
"\uE015>క;" // LETTER KA
"\uE016>ఖ;" // LETTER KHA
"\uE017>గ;" // LETTER GA
"\uE018>ఘ;" // LETTER GHA
"\uE019>ఙ;" // LETTER NGA
"\uE01A>చ;" // LETTER CA
"\uE01B>ఛ;" // LETTER CHA
"\uE01C>జ;" // LETTER JA
"\uE01D>ఝ;" // LETTER JHA
"\uE01E>ఞ;" // LETTER NYA
"\uE01F>ట;" // LETTER TTA
"\uE020>ఠ;" // LETTER TTHA
"\uE021>డ;" // LETTER DDA
"\uE022>ఢ;" // LETTER DDHA
"\uE023>ణ;" // LETTER NNA
"\uE024>త;" // LETTER TA
"\uE025>థ;" // LETTER THA
"\uE026>ద;" // LETTER DA
"\uE027>ధ;" // LETTER DHA
"\uE028>న;" // LETTER NA
"\uE029>న;" // REMAP (indicExceptions.txt): ఩>న = LETTER NNNA>LETTER NA
"\uE02A>ప;" // LETTER PA
"\uE02B>ఫ;" // LETTER PHA
"\uE02C>బ;" // LETTER BA
"\uE02D>భ;" // LETTER BHA
"\uE02E>మ;" // LETTER MA
"\uE02F>య;" // LETTER YA
"\uE030>ర;" // LETTER RA
"\uE032>ల;" // LETTER LA
"\uE033>ళ;" // LETTER LLA
"\uE034>ళ;" // REMAP (indicExceptions.txt): ఴ>ళ = LETTER LLLA>LETTER LLA
"\uE035>వ;" // LETTER VA
"\uE036>శ;" // LETTER SHA
"\uE037>ష;" // LETTER SSA
"\uE038>స;" // LETTER SA
"\uE039>హ;" // LETTER HA
// \uE03C>; // UNMAPPED InterIndic-Telugu: SIGN NUKTA
// \uE03D>; // UNMAPPED InterIndic-Telugu: SIGN AVAGRAHA
"\uE03E>ా;" // VOWEL SIGN AA
"\uE03F>ి;" // VOWEL SIGN I
"\uE040>ీ;" // VOWEL SIGN II
"\uE041>ు;" // VOWEL SIGN U
"\uE042>ూ;" // VOWEL SIGN UU
"\uE043>ృ;" // VOWEL SIGN VOCALIC R
"\uE044>ౄ;" // VOWEL SIGN VOCALIC RR
"\uE045>ె;" // REMAP (indicExceptions.txt): ౅>ె = VOWEL SIGN CANDRA E>VOWEL SIGN E
"\uE047>ే;" // VOWEL SIGN EE
"\uE048>ై;" // VOWEL SIGN AI
"\uE049>ొ;" // REMAP (indicExceptions.txt): ౉>ొ = VOWEL SIGN CANDRA O>VOWEL SIGN O
"\uE04B>ో;" // VOWEL SIGN OO
"\uE04C>ౌ;" // VOWEL SIGN AU
"\uE04D>్;" // SIGN VIRAMA
"\uE050>ఓం;" // REMAP (indicExceptions.txt): ౐>ఓం = OM>LETTER OO.SIGN ANUSVARA
"\uE055>ౕ;" // LENGTH MARK
"\uE056>ౖ;" // AI LENGTH MARK
"\uE057>ౌ;" // REMAP (indicExceptions.txt): ౗>ౌ = AU LENGTH MARK>VOWEL SIGN AU
"\uE059>ఖ;" // REMAP (indicExceptions.txt): ౙ>ఖ = LETTER KHHA>LETTER KHA
"\uE05A>గ;" // REMAP (indicExceptions.txt): ౚ>గ = LETTER GHHA>LETTER GA
"\uE05B>జ;" // REMAP (indicExceptions.txt): ౛>జ = LETTER ZA>LETTER JA
"\uE05D>ఢ;" // REMAP (indicExceptions.txt): ౝ>ఢ = LETTER RHA>LETTER DDHA
"\uE05E>ఫ;" // REMAP (indicExceptions.txt): ౞>ఫ = LETTER FA>LETTER PHA
"\uE05F>య;" // REMAP (indicExceptions.txt): ౟>య = LETTER YYA>LETTER YA
"\uE060>ౠ;" // LETTER VOCALIC RR
"\uE061>ౡ;" // LETTER VOCALIC LL
"\uE062>ి;" // REMAP (indicExceptions.txt): ౢ>ి = VOWEL SIGN VOCALIC L>VOWEL SIGN I
"\uE063>ీ;" // REMAP (indicExceptions.txt): ౣ>ీ = VOWEL SIGN VOCALIC LL>VOWEL SIGN II
"\uE066>౦;" // DIGIT ZERO
"\uE067>౧;" // DIGIT ONE
"\uE068>౨;" // DIGIT TWO
"\uE069>౩;" // DIGIT THREE
"\uE06A>౪;" // DIGIT FOUR
"\uE06B>౫;" // DIGIT FIVE
"\uE06C>౬;" // DIGIT SIX
"\uE06D>౭;" // DIGIT SEVEN
"\uE06E>౮;" // DIGIT EIGHT
"\uE06F>౯;" // DIGIT NINE
// \uE080>; // UNMAPPED InterIndic-Telugu: ISSHAR
"\uE081>ఎ;" // LETTER E
"\uE082>ఒ;" // LETTER O
"\uE083>ఱ;" // LETTER RRA
"\uE084>ె;" // VOWEL SIGN E
"\uE085>ొ;" // VOWEL SIGN O
// eof
}
}

108
icu4c/data/Kannada_InterIndic.txt Normal file
View File

@ -0,0 +1,108 @@
 // -*- Coding: utf-8; -*-
//--------------------------------------------------------------------
// Copyright (c) 1999-2001, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// THIS IS A MACHINE-GENERATED FILE
// Tool: dumpICUrules.bat
// Source: \icu4j\src\com\ibm\text\resources/Transliterator_Kannada_InterIndic.utf8.txt
// Date: Thu Mar 1 20:03:55 2001
//--------------------------------------------------------------------
// Kannada_InterIndic
Kannada_InterIndic {
Rule {
//--------------------------------------------------------------------
// Copyright (c) 1999-2001, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// Date: Tue Jan 23 12:42:05 2001
//--------------------------------------------------------------------
// Kannada-InterIndic
"ಂ>\uE002;" // SIGN ANUSVARA
"ಃ>\uE003;" // SIGN VISARGA
"ಅ>\uE005;" // LETTER A
"ಆ>\uE006;" // LETTER AA
"ಇ>\uE007;" // LETTER I
"ಈ>\uE008;" // LETTER II
"ಉ>\uE009;" // LETTER U
"ಊ>\uE00A;" // LETTER UU
"ಋ>\uE00B;" // LETTER VOCALIC R
"ಌ>\uE00C;" // LETTER VOCALIC L
"ಎ>\uE081;" // LETTER E
"ಏ>\uE00F;" // LETTER EE
"ಐ>\uE010;" // LETTER AI
"ಒ>\uE082;" // LETTER O
"ಓ>\uE013;" // LETTER OO
"ಔ>\uE014;" // LETTER AU
"ಕ>\uE015;" // LETTER KA
"ಖ>\uE016;" // LETTER KHA
"ಗ>\uE017;" // LETTER GA
"ಘ>\uE018;" // LETTER GHA
"ಙ>\uE019;" // LETTER NGA
"ಚ>\uE01A;" // LETTER CA
"ಛ>\uE01B;" // LETTER CHA
"ಜ>\uE01C;" // LETTER JA
"ಝ>\uE01D;" // LETTER JHA
"ಞ>\uE01E;" // LETTER NYA
"ಟ>\uE01F;" // LETTER TTA
"ಠ>\uE020;" // LETTER TTHA
"ಡ>\uE021;" // LETTER DDA
"ಢ>\uE022;" // LETTER DDHA
"ಣ>\uE023;" // LETTER NNA
"ತ>\uE024;" // LETTER TA
"ಥ>\uE025;" // LETTER THA
"ದ>\uE026;" // LETTER DA
"ಧ>\uE027;" // LETTER DHA
"ನ>\uE028;" // LETTER NA
"ಪ>\uE02A;" // LETTER PA
"ಫ>\uE02B;" // LETTER PHA
"ಬ>\uE02C;" // LETTER BA
"ಭ>\uE02D;" // LETTER BHA
"ಮ>\uE02E;" // LETTER MA
"ಯ>\uE02F;" // LETTER YA
"ರ>\uE030;" // LETTER RA
"ಱ>\uE083;" // LETTER RRA
"ಲ>\uE032;" // LETTER LA
"ಳ>\uE033;" // LETTER LLA
"ವ>\uE035;" // LETTER VA
"ಶ>\uE036;" // LETTER SHA
"ಷ>\uE037;" // LETTER SSA
"ಸ>\uE038;" // LETTER SA
"ಹ>\uE039;" // LETTER HA
"ಾ>\uE03E;" // VOWEL SIGN AA
"ಿ>\uE03F;" // VOWEL SIGN I
"ೀ>\uE040;" // VOWEL SIGN II
"ು>\uE041;" // VOWEL SIGN U
"ೂ>\uE042;" // VOWEL SIGN UU
"ೃ>\uE043;" // VOWEL SIGN VOCALIC R
"ೄ>\uE044;" // VOWEL SIGN VOCALIC RR
"ೆ>\uE084;" // VOWEL SIGN E
"ೇ>\uE047;" // VOWEL SIGN EE
"ೈ>\uE048;" // VOWEL SIGN AI
"ೊ>\uE085;" // VOWEL SIGN O
"ೋ>\uE04B;" // VOWEL SIGN OO
"ೌ>\uE04C;" // VOWEL SIGN AU
"್>\uE04D;" // SIGN VIRAMA
"ೕ>\uE055;" // LENGTH MARK
"ೖ>\uE056;" // AI LENGTH MARK
"ೞ>\uE05E;" // LETTER FA
"ೠ>\uE060;" // LETTER VOCALIC RR
"ೡ>\uE061;" // LETTER VOCALIC LL
"೦>\uE066;" // DIGIT ZERO
"೧>\uE067;" // DIGIT ONE
"೨>\uE068;" // DIGIT TWO
"೩>\uE069;" // DIGIT THREE
"೪>\uE06A;" // DIGIT FOUR
"೫>\uE06B;" // DIGIT FIVE
"೬>\uE06C;" // DIGIT SIX
"೭>\uE06D;" // DIGIT SEVEN
"೮>\uE06E;" // DIGIT EIGHT
"೯>\uE06F;" // DIGIT NINE
// eof
}
}

106
icu4c/data/Malayalam_InterIndic.txt Normal file
View File

@ -0,0 +1,106 @@
 // -*- Coding: utf-8; -*-
//--------------------------------------------------------------------
// Copyright (c) 1999-2001, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// THIS IS A MACHINE-GENERATED FILE
// Tool: dumpICUrules.bat
// Source: \icu4j\src\com\ibm\text\resources/Transliterator_Malayalam_InterIndic.utf8.txt
// Date: Thu Mar 1 20:03:55 2001
//--------------------------------------------------------------------
// Malayalam_InterIndic
Malayalam_InterIndic {
Rule {
//--------------------------------------------------------------------
// Copyright (c) 1999-2001, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// Date: Tue Jan 23 12:42:06 2001
//--------------------------------------------------------------------
// Malayalam-InterIndic
"ം>\uE002;" // SIGN ANUSVARA
"ഃ>\uE003;" // SIGN VISARGA
"അ>\uE005;" // LETTER A
"ആ>\uE006;" // LETTER AA
"ഇ>\uE007;" // LETTER I
"ഈ>\uE008;" // LETTER II
"ഉ>\uE009;" // LETTER U
"ഊ>\uE00A;" // LETTER UU
"ഋ>\uE00B;" // LETTER VOCALIC R
"ഌ>\uE00C;" // LETTER VOCALIC L
"എ>\uE081;" // LETTER E
"ഏ>\uE00F;" // LETTER EE
"ഐ>\uE010;" // LETTER AI
"ഒ>\uE082;" // LETTER O
"ഓ>\uE013;" // LETTER OO
"ഔ>\uE014;" // LETTER AU
"ക>\uE015;" // LETTER KA
"ഖ>\uE016;" // LETTER KHA
"ഗ>\uE017;" // LETTER GA
"ഘ>\uE018;" // LETTER GHA
"ങ>\uE019;" // LETTER NGA
"ച>\uE01A;" // LETTER CA
"ഛ>\uE01B;" // LETTER CHA
"ജ>\uE01C;" // LETTER JA
"ഝ>\uE01D;" // LETTER JHA
"ഞ>\uE01E;" // LETTER NYA
"ട>\uE01F;" // LETTER TTA
"ഠ>\uE020;" // LETTER TTHA
"ഡ>\uE021;" // LETTER DDA
"ഢ>\uE022;" // LETTER DDHA
"ണ>\uE023;" // LETTER NNA
"ത>\uE024;" // LETTER TA
"ഥ>\uE025;" // LETTER THA
"ദ>\uE026;" // LETTER DA
"ധ>\uE027;" // LETTER DHA
"ന>\uE028;" // LETTER NA
"പ>\uE02A;" // LETTER PA
"ഫ>\uE02B;" // LETTER PHA
"ബ>\uE02C;" // LETTER BA
"ഭ>\uE02D;" // LETTER BHA
"മ>\uE02E;" // LETTER MA
"യ>\uE02F;" // LETTER YA
"ര>\uE030;" // LETTER RA
"റ>\uE083;" // LETTER RRA
"ല>\uE032;" // LETTER LA
"ള>\uE033;" // LETTER LLA
"ഴ>\uE034;" // LETTER LLLA
"വ>\uE035;" // LETTER VA
"ശ>\uE036;" // LETTER SHA
"ഷ>\uE037;" // LETTER SSA
"സ>\uE038;" // LETTER SA
"ഹ>\uE039;" // LETTER HA
"ാ>\uE03E;" // VOWEL SIGN AA
"ി>\uE03F;" // VOWEL SIGN I
"ീ>\uE040;" // VOWEL SIGN II
"ു>\uE041;" // VOWEL SIGN U
"ൂ>\uE042;" // VOWEL SIGN UU
"ൃ>\uE043;" // VOWEL SIGN VOCALIC R
"െ>\uE084;" // VOWEL SIGN E
"േ>\uE047;" // VOWEL SIGN EE
"ൈ>\uE048;" // VOWEL SIGN AI
"ൊ>\uE085;" // VOWEL SIGN O
"ോ>\uE04B;" // VOWEL SIGN OO
"ൌ>\uE04C;" // VOWEL SIGN AU
"്>\uE04D;" // SIGN VIRAMA
"ൗ>\uE057;" // AU LENGTH MARK
"ൠ>\uE060;" // LETTER VOCALIC RR
"ൡ>\uE061;" // LETTER VOCALIC LL
"൦>\uE066;" // DIGIT ZERO
"൧>\uE067;" // DIGIT ONE
"൨>\uE068;" // DIGIT TWO
"൩>\uE069;" // DIGIT THREE
"൪>\uE06A;" // DIGIT FOUR
"൫>\uE06B;" // DIGIT FIVE
"൬>\uE06C;" // DIGIT SIX
"൭>\uE06D;" // DIGIT SEVEN
"൮>\uE06E;" // DIGIT EIGHT
"൯>\uE06F;" // DIGIT NINE
// eof
}
}

107
icu4c/data/Oriya_InterIndic.txt Normal file
View File

@ -0,0 +1,107 @@
 // -*- Coding: utf-8; -*-
//--------------------------------------------------------------------
// Copyright (c) 1999-2001, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// THIS IS A MACHINE-GENERATED FILE
// Tool: dumpICUrules.bat
// Source: \icu4j\src\com\ibm\text\resources/Transliterator_Oriya_InterIndic.utf8.txt
// Date: Thu Mar 1 20:03:55 2001
//--------------------------------------------------------------------
// Oriya_InterIndic
Oriya_InterIndic {
Rule {
//--------------------------------------------------------------------
// Copyright (c) 1999-2001, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// Date: Tue Jan 23 12:42:07 2001
//--------------------------------------------------------------------
// Oriya-InterIndic
"ଁ>\uE001;" // SIGN CANDRABINDU
"ଂ>\uE002;" // SIGN ANUSVARA
"ଃ>\uE003;" // SIGN VISARGA
"ଅ>\uE005;" // LETTER A
"ଆ>\uE006;" // LETTER AA
"ଇ>\uE007;" // LETTER I
"ଈ>\uE008;" // LETTER II
"ଉ>\uE009;" // LETTER U
"ଊ>\uE00A;" // LETTER UU
"ଋ>\uE00B;" // LETTER VOCALIC R
"ଌ>\uE00C;" // LETTER VOCALIC L
"ଏ>\uE081;" // LETTER E
"ଐ>\uE010;" // LETTER AI
"ଓ>\uE082;" // LETTER O
"ଔ>\uE014;" // LETTER AU
"କ>\uE015;" // LETTER KA
"ଖ>\uE016;" // LETTER KHA
"ଗ>\uE017;" // LETTER GA
"ଘ>\uE018;" // LETTER GHA
"ଙ>\uE019;" // LETTER NGA
"ଚ>\uE01A;" // LETTER CA
"ଛ>\uE01B;" // LETTER CHA
"ଜ>\uE01C;" // LETTER JA
"ଝ>\uE01D;" // LETTER JHA
"ଞ>\uE01E;" // LETTER NYA
"ଟ>\uE01F;" // LETTER TTA
"ଠ>\uE020;" // LETTER TTHA
"ଡ>\uE021;" // LETTER DDA
"ଢ>\uE022;" // LETTER DDHA
"ଣ>\uE023;" // LETTER NNA
"ତ>\uE024;" // LETTER TA
"ଥ>\uE025;" // LETTER THA
"ଦ>\uE026;" // LETTER DA
"ଧ>\uE027;" // LETTER DHA
"ନ>\uE028;" // LETTER NA
"ପ>\uE02A;" // LETTER PA
"ଫ>\uE02B;" // LETTER PHA
"ବ>\uE02C;" // LETTER BA
"ଭ>\uE02D;" // LETTER BHA
"ମ>\uE02E;" // LETTER MA
"ଯ>\uE02F;" // LETTER YA
"ର>\uE030;" // LETTER RA
"ଲ>\uE032;" // LETTER LA
"ଳ>\uE033;" // LETTER LLA
"ଶ>\uE036;" // LETTER SHA
"ଷ>\uE037;" // LETTER SSA
"ସ>\uE038;" // LETTER SA
"ହ>\uE039;" // LETTER HA
"଼>\uE03C;" // SIGN NUKTA
"ଽ>\uE03D;" // SIGN AVAGRAHA
"ା>\uE03E;" // VOWEL SIGN AA
"ି>\uE03F;" // VOWEL SIGN I
"ୀ>\uE040;" // VOWEL SIGN II
"ୁ>\uE041;" // VOWEL SIGN U
"ୂ>\uE042;" // VOWEL SIGN UU
"ୃ>\uE043;" // VOWEL SIGN VOCALIC R
"େ>\uE084;" // VOWEL SIGN E
"ୈ>\uE048;" // VOWEL SIGN AI
"ୋ>\uE085;" // VOWEL SIGN O
"ୌ>\uE04C;" // VOWEL SIGN AU
"୍>\uE04D;" // SIGN VIRAMA
"ୖ>\uE056;" // AI LENGTH MARK
"ୗ>\uE057;" // AU LENGTH MARK
"ଡ଼>\uE083;" // LETTER RRA
"ଢ଼>\uE05D;" // LETTER RHA
"ୟ>\uE05F;" // LETTER YYA
"ୠ>\uE060;" // LETTER VOCALIC RR
"ୡ>\uE061;" // LETTER VOCALIC LL
"୦>\uE066;" // DIGIT ZERO
"୧>\uE067;" // DIGIT ONE
"୨>\uE068;" // DIGIT TWO
"୩>\uE069;" // DIGIT THREE
"୪>\uE06A;" // DIGIT FOUR
"୫>\uE06B;" // DIGIT FIVE
"୬>\uE06C;" // DIGIT SIX
"୭>\uE06D;" // DIGIT SEVEN
"୮>\uE06E;" // DIGIT EIGHT
"୯>\uE06F;" // DIGIT NINE
"୰>\uE080;" // ISSHAR
// eof
}
}

89
icu4c/data/Tamil_InterIndic.txt Normal file
View File

@ -0,0 +1,89 @@
 // -*- Coding: utf-8; -*-
//--------------------------------------------------------------------
// Copyright (c) 1999-2001, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// THIS IS A MACHINE-GENERATED FILE
// Tool: dumpICUrules.bat
// Source: \icu4j\src\com\ibm\text\resources/Transliterator_Tamil_InterIndic.utf8.txt
// Date: Thu Mar 1 20:03:55 2001
//--------------------------------------------------------------------
// Tamil_InterIndic
Tamil_InterIndic {
Rule {
//--------------------------------------------------------------------
// Copyright (c) 1999-2001, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// Date: Tue Jan 23 12:42:07 2001
//--------------------------------------------------------------------
// Tamil-InterIndic
"ஂ>\uE002;" // SIGN ANUSVARA
"ஃ>\uE003;" // SIGN VISARGA
"அ>\uE005;" // LETTER A
"ஆ>\uE006;" // LETTER AA
"இ>\uE007;" // LETTER I
"ஈ>\uE008;" // LETTER II
"உ>\uE009;" // LETTER U
"ஊ>\uE00A;" // LETTER UU
"எ>\uE081;" // LETTER E
"ஏ>\uE00F;" // LETTER EE
"ஐ>\uE010;" // LETTER AI
"ஒ>\uE082;" // LETTER O
"ஓ>\uE013;" // LETTER OO
"ஔ>\uE014;" // LETTER AU
"க>\uE015;" // LETTER KA
"ங>\uE019;" // LETTER NGA
"ச>\uE01A;" // LETTER CA
"ஜ>\uE01C;" // LETTER JA
"ஞ>\uE01E;" // LETTER NYA
"ட>\uE01F;" // LETTER TTA
"ண>\uE023;" // LETTER NNA
"த>\uE024;" // LETTER TA
"ந>\uE028;" // LETTER NA
"ன>\uE029;" // LETTER NNNA
"ப>\uE02A;" // LETTER PA
"ம>\uE02E;" // LETTER MA
"ய>\uE02F;" // LETTER YA
"ர>\uE030;" // LETTER RA
"ற>\uE083;" // LETTER RRA
"ல>\uE032;" // LETTER LA
"ள>\uE033;" // LETTER LLA
"ழ>\uE034;" // LETTER LLLA
"வ>\uE035;" // LETTER VA
"ஷ>\uE037;" // LETTER SSA
"ஸ>\uE038;" // LETTER SA
"ஹ>\uE039;" // LETTER HA
"ா>\uE03E;" // VOWEL SIGN AA
"ி>\uE03F;" // VOWEL SIGN I
"ீ>\uE040;" // VOWEL SIGN II
"ு>\uE041;" // VOWEL SIGN U
"ூ>\uE042;" // VOWEL SIGN UU
"ெ>\uE084;" // VOWEL SIGN E
"ே>\uE047;" // VOWEL SIGN EE
"ை>\uE048;" // VOWEL SIGN AI
"ொ>\uE085;" // VOWEL SIGN O
"ோ>\uE04B;" // VOWEL SIGN OO
"ௌ>\uE04C;" // VOWEL SIGN AU
"்>\uE04D;" // SIGN VIRAMA
"ௗ>\uE057;" // AU LENGTH MARK
"௧>\uE067;" // DIGIT ONE
"௨>\uE068;" // DIGIT TWO
"௩>\uE069;" // DIGIT THREE
"௪>\uE06A;" // DIGIT FOUR
"௫>\uE06B;" // DIGIT FIVE
"௬>\uE06C;" // DIGIT SIX
"௭>\uE06D;" // DIGIT SEVEN
"௮>\uE06E;" // DIGIT EIGHT
"௯>\uE06F;" // DIGIT NINE
// ௰>; // UNMAPPED Tamil-InterIndic: NUMBER TEN
// ௱>; // UNMAPPED Tamil-InterIndic: NUMBER ONE HUNDRED
// ௲>; // UNMAPPED Tamil-InterIndic: NUMBER ONE THOUSAND
// eof
}
}

108
icu4c/data/Telugu_InterIndic.txt Normal file
View File

@ -0,0 +1,108 @@
 // -*- Coding: utf-8; -*-
//--------------------------------------------------------------------
// Copyright (c) 1999-2001, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// THIS IS A MACHINE-GENERATED FILE
// Tool: dumpICUrules.bat
// Source: \icu4j\src\com\ibm\text\resources/Transliterator_Telugu_InterIndic.utf8.txt
// Date: Thu Mar 1 20:03:55 2001
//--------------------------------------------------------------------
// Telugu_InterIndic
Telugu_InterIndic {
Rule {
//--------------------------------------------------------------------
// Copyright (c) 1999-2001, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// Date: Tue Jan 23 12:42:07 2001
//--------------------------------------------------------------------
// Telugu-InterIndic
"ఁ>\uE001;" // SIGN CANDRABINDU
"ం>\uE002;" // SIGN ANUSVARA
"ః>\uE003;" // SIGN VISARGA
"అ>\uE005;" // LETTER A
"ఆ>\uE006;" // LETTER AA
"ఇ>\uE007;" // LETTER I
"ఈ>\uE008;" // LETTER II
"ఉ>\uE009;" // LETTER U
"ఊ>\uE00A;" // LETTER UU
"ఋ>\uE00B;" // LETTER VOCALIC R
"ఌ>\uE00C;" // LETTER VOCALIC L
"ఎ>\uE081;" // LETTER E
"ఏ>\uE00F;" // LETTER EE
"ఐ>\uE010;" // LETTER AI
"ఒ>\uE082;" // LETTER O
"ఓ>\uE013;" // LETTER OO
"ఔ>\uE014;" // LETTER AU
"క>\uE015;" // LETTER KA
"ఖ>\uE016;" // LETTER KHA
"గ>\uE017;" // LETTER GA
"ఘ>\uE018;" // LETTER GHA
"ఙ>\uE019;" // LETTER NGA
"చ>\uE01A;" // LETTER CA
"ఛ>\uE01B;" // LETTER CHA
"జ>\uE01C;" // LETTER JA
"ఝ>\uE01D;" // LETTER JHA
"ఞ>\uE01E;" // LETTER NYA
"ట>\uE01F;" // LETTER TTA
"ఠ>\uE020;" // LETTER TTHA
"డ>\uE021;" // LETTER DDA
"ఢ>\uE022;" // LETTER DDHA
"ణ>\uE023;" // LETTER NNA
"త>\uE024;" // LETTER TA
"థ>\uE025;" // LETTER THA
"ద>\uE026;" // LETTER DA
"ధ>\uE027;" // LETTER DHA
"న>\uE028;" // LETTER NA
"ప>\uE02A;" // LETTER PA
"ఫ>\uE02B;" // LETTER PHA
"బ>\uE02C;" // LETTER BA
"భ>\uE02D;" // LETTER BHA
"మ>\uE02E;" // LETTER MA
"య>\uE02F;" // LETTER YA
"ర>\uE030;" // LETTER RA
"ఱ>\uE083;" // LETTER RRA
"ల>\uE032;" // LETTER LA
"ళ>\uE033;" // LETTER LLA
"వ>\uE035;" // LETTER VA
"శ>\uE036;" // LETTER SHA
"ష>\uE037;" // LETTER SSA
"స>\uE038;" // LETTER SA
"హ>\uE039;" // LETTER HA
"ా>\uE03E;" // VOWEL SIGN AA
"ి>\uE03F;" // VOWEL SIGN I
"ీ>\uE040;" // VOWEL SIGN II
"ు>\uE041;" // VOWEL SIGN U
"ూ>\uE042;" // VOWEL SIGN UU
"ృ>\uE043;" // VOWEL SIGN VOCALIC R
"ౄ>\uE044;" // VOWEL SIGN VOCALIC RR
"ె>\uE084;" // VOWEL SIGN E
"ే>\uE047;" // VOWEL SIGN EE
"ై>\uE048;" // VOWEL SIGN AI
"ొ>\uE085;" // VOWEL SIGN O
"ో>\uE04B;" // VOWEL SIGN OO
"ౌ>\uE04C;" // VOWEL SIGN AU
"్>\uE04D;" // SIGN VIRAMA
"ౕ>\uE055;" // LENGTH MARK
"ౖ>\uE056;" // AI LENGTH MARK
"ౠ>\uE060;" // LETTER VOCALIC RR
"ౡ>\uE061;" // LETTER VOCALIC LL
"౦>\uE066;" // DIGIT ZERO
"౧>\uE067;" // DIGIT ONE
"౨>\uE068;" // DIGIT TWO
"౩>\uE069;" // DIGIT THREE
"౪>\uE06A;" // DIGIT FOUR
"౫>\uE06B;" // DIGIT FIVE
"౬>\uE06C;" // DIGIT SIX
"౭>\uE06D;" // DIGIT SEVEN
"౮>\uE06E;" // DIGIT EIGHT
"౯>\uE06F;" // DIGIT NINE
// eof
}
}

22
icu4c/data/resfiles.mk
View File

@ -98,7 +98,23 @@ zh.txt zh_CN.txt zh_HK.txt zh_SG.txt zh_TW.txt
TRANSLIT_SOURCE=fullhalf.txt translit_index.txt kana.txt kbdescl1.txt\
larabic.txt lcyril.txt ldevan.txt\
lgreek.txt lhebrew.txt ljamo.txt\
lkana.txt quotes.txt ucname.txt
lkana.txt quotes.txt ucname.txt\
Bengali_InterIndic.txt\
Devanagari_InterIndic.txt\
Gujarati_InterIndic.txt\
Gurmukhi_InterIndic.txt\
Kannada_InterIndic.txt\
Malayalam_InterIndic.txt\
Oriya_InterIndic.txt\
Tamil_InterIndic.txt\
Telugu_InterIndic.txt\
InterIndic_Bengali.txt\
InterIndic_Devanagari.txt\
InterIndic_Gujarati.txt\
InterIndic_Gurmukhi.txt\
InterIndic_Kannada.txt\
InterIndic_Malayalam.txt\
InterIndic_Oriya.txt\
InterIndic_Tamil.txt\
InterIndic_Telugu.txt

233
icu4c/data/translit_index.txt
View File

@ -1,47 +1,204 @@
//--------------------------------------------------------------------
// Copyright (c) 2000, International Business Machines
// Corporation and others. All Rights Reserved.
// Copyright (c) 1999-2001, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// Date Name Description
// 01/13/2000 aliu Creation.
// THIS IS A MACHINE-GENERATED FILE
// Tool: dumpICUrules.bat
// Source: Transliterator_index.txt
// Date: Fri Mar 2 12:50:49 2001
//--------------------------------------------------------------------
//--------------------------------------------------------------------
// N.B.: This file has been generated mechanically from the
// corresponding ICU4J file, which is the master file that receives
// primary updates. The colon-delimited fields have been split into
// separate strings. For 'file' and 'internal' lines, the encoding
// field has been deleted, since the encoding is processed at build
// time in ICU4C. Certain large rule sets not intended for general
// use have been commented out with the notation "Java only".
//--------------------------------------------------------------------
translit_index {
// Map transliterator names to resource file names. This
// mapping is required because transliterator names typically
// exceed the limits of 8.3 file names.
RuleBasedTransliteratorIDs {
// Copyright (c) 2001, International Business Machines Corporation and
// others. All Rights Reserved.
//
// TRANSLITERATOR INDEX FILE. This file lists the non-algorithmic
// system transliterators. It allows arbitrary mappings between
// transliterator IDs and file names, and also allows the system to
// define aliases for transliterators, so that "Latin-Hangul", for
// example, can be implemented transparently as the compound
// "Latin-Jamo;Jamo-Hangul". Internal IDs may also be defined; these
// are invisible to the user, but can be composed together by the
// system to create visible transliterators.
//
// Blank lines and lines beginning with '#' are ignored.
//
// Lines in this file have one of the following forms (text not
// enclosed by <> is literal):
//
// <id>:file:<resource>:<encoding>:<direction>
// <id>:internal:<resource>:<encoding>:<direction>
// <id>:alias:<getInstanceArg>
//
// <id> is the ID of the system transliterator being defined. These
// are public IDs enumerated by Transliterator.getAvailableIDs(),
// unless the second field is "internal".
//
// <resource> is a ResourceReader resource name. Currently these refer
// to file names under com/ibm/text/resources. This string is passed
// directly to ResourceReader, together with <encoding>.
//
// <encoding> is the character encoding to use when reading <resource>;
// passed directly to ResourceReader. E.g., "UTF8".
//
// <direction> is either "FORWARD" or "REVERSE".
//
// <getInstanceArg> is a string to be passed directly to
// Transliterator.getInstance(). The returned Transliterator object
// then has its ID changed to <id> and is returned.
RuleBasedTransliteratorIDs {
// This is an n x 3 array of strings that serves as an index
// to the system rule-based transliterator resource bundle
// data files. If RBT files are installed or removed from the
// system this table must be updated. For each of the n rows,
// the first item is the ID of the forward transliterator for
// the rule. The second item is the ID of the reverse
// transliterator for the rule. Some rule files only contain
// forward direction rules; for those, the second item is a
// zero-length string. The third item is the name of the
// resource bundle file, a string of 8 or fewer lowercase
// letters or digits. This file will be sought in the data
// directory within the subdirectory "translit". IDs must
// have the form "From-To" or "SingleName" to work properly
// with the Transliterator code.
// Basic language rules
{ "Fullwidth-Halfwidth", "Halfwidth-Fullwidth", "fullhalf" }
{ "Latin-Arabic", "Arabic-Latin", "larabic" }
{ "Latin-Cyrillic", "Cyrillic-Latin", "lcyril" }
{ "Latin-Devanagari", "Devanagari-Latin", "ldevan" }
{ "Latin-Greek", "Greek-Latin", "lgreek" }
{ "Latin-Hebrew", "Hebrew-Latin", "lhebrew" }
{ "Latin-Jamo", "Jamo-Latin", "ljamo" }
{ "Latin-Kana", "Kana-Latin", "lkana" }
{ "Hiragana-Katakana", "Katakana-Hiragana", "kana" }
// Bidirectional rule files
// Other miscellaneous rules
{ "StraightQuotes-CurlyQuotes", "CurlyQuotes-StraightQuotes",
"quotes" }
{ "KeyboardEscape-Latin1", "", "kbdescl1" }
{ "UnicodeName-UnicodeChar", "", "ucname" }
}
{ "Fullwidth-Halfwidth", "file", "fullhalf", "FORWARD" },
{ "Halfwidth-Fullwidth", "file", "fullhalf", "REVERSE" },
{ "Latin-Arabic", "file", "larabic", "FORWARD" },
{ "Arabic-Latin", "file", "larabic", "REVERSE" },
{ "Latin-Cyrillic", "file", "lcyril", "FORWARD" },
{ "Cyrillic-Latin", "file", "lcyril", "REVERSE" },
{ "Latin-Devanagari", "file", "ldevan", "FORWARD" },
{ "Devanagari-Latin", "file", "ldevan", "REVERSE" },
{ "Latin-Greek", "file", "lgreek", "FORWARD" },
{ "Greek-Latin", "file", "lgreek", "REVERSE" },
{ "Latin-Hebrew", "file", "lhebrew", "FORWARD" },
{ "Hebrew-Latin", "file", "lhebrew", "REVERSE" },
{ "Latin-Jamo", "file", "ljamo", "FORWARD" },
{ "Jamo-Latin", "file", "ljamo", "REVERSE" },
{ "Latin-Kana", "file", "lkana", "FORWARD" },
{ "Kana-Latin", "file", "lkana", "REVERSE" },
{ "Hiragana-Katakana", "file", "kana", "FORWARD" },
{ "Katakana-Hiragana", "file", "kana", "REVERSE" },
{ "StraightQuotes-CurlyQuotes", "file", "quotes", "FORWARD" },
{ "CurlyQuotes-StraightQuotes", "file", "quotes", "REVERSE" },
// One way rules (forward only)
// Java only: { "Han-Pinyin", "file", "-", "FORWARD" },
// Java only: { "Kanji-English", "file", "-", "FORWARD" },
// Java only: { "Kanji-OnRomaji", "file", "-", "FORWARD" },
{ "KeyboardEscape-Latin1", "file", "kbdescl1", "FORWARD" },
{ "UnicodeName-UnicodeChar", "file", "ucname", "FORWARD" },
// Compound rules
{ "Latin-Hangul", "alias", "Latin-Jamo;Jamo-Hangul", "" },
{ "Hangul-Latin", "alias", "Hangul-Jamo;Jamo-Latin", "" },
// Inter-Indic composed rules
{ "Devanagari-InterIndic", "internal", "Devanagari_InterIndic", "FORWARD" },
{ "Bengali-InterIndic", "internal", "Bengali_InterIndic", "FORWARD" },
{ "Gurmukhi-InterIndic", "internal", "Gurmukhi_InterIndic", "FORWARD" },
{ "Gujarati-InterIndic", "internal", "Gujarati_InterIndic", "FORWARD" },
{ "Oriya-InterIndic", "internal", "Oriya_InterIndic", "FORWARD" },
{ "Tamil-InterIndic", "internal", "Tamil_InterIndic", "FORWARD" },
{ "Telugu-InterIndic", "internal", "Telugu_InterIndic", "FORWARD" },
{ "Kannada-InterIndic", "internal", "Kannada_InterIndic", "FORWARD" },
{ "Malayalam-InterIndic", "internal", "Malayalam_InterIndic", "FORWARD" },
{ "InterIndic-Devanagari", "internal", "InterIndic_Devanagari", "FORWARD" },
{ "InterIndic-Bengali", "internal", "InterIndic_Bengali", "FORWARD" },
{ "InterIndic-Gurmukhi", "internal", "InterIndic_Gurmukhi", "FORWARD" },
{ "InterIndic-Gujarati", "internal", "InterIndic_Gujarati", "FORWARD" },
{ "InterIndic-Oriya", "internal", "InterIndic_Oriya", "FORWARD" },
{ "InterIndic-Tamil", "internal", "InterIndic_Tamil", "FORWARD" },
{ "InterIndic-Telugu", "internal", "InterIndic_Telugu", "FORWARD" },
{ "InterIndic-Kannada", "internal", "InterIndic_Kannada", "FORWARD" },
{ "InterIndic-Malayalam", "internal", "InterIndic_Malayalam", "FORWARD" },
{ "Devanagari-Bengali", "alias", "Devanagari-InterIndic;InterIndic-Bengali", "" },
{ "Devanagari-Gurmukhi", "alias", "Devanagari-InterIndic;InterIndic-Gurmukhi", "" },
{ "Devanagari-Gujarati", "alias", "Devanagari-InterIndic;InterIndic-Gujarati", "" },
{ "Devanagari-Oriya", "alias", "Devanagari-InterIndic;InterIndic-Oriya", "" },
{ "Devanagari-Tamil", "alias", "Devanagari-InterIndic;InterIndic-Tamil", "" },
{ "Devanagari-Telugu", "alias", "Devanagari-InterIndic;InterIndic-Telugu", "" },
{ "Devanagari-Kannada", "alias", "Devanagari-InterIndic;InterIndic-Kannada", "" },
{ "Devanagari-Malayalam", "alias", "Devanagari-InterIndic;InterIndic-Malayalam", "" },
{ "Bengali-Devanagari", "alias", "Bengali-InterIndic;InterIndic-Devanagari", "" },
{ "Bengali-Gurmukhi", "alias", "Bengali-InterIndic;InterIndic-Gurmukhi", "" },
{ "Bengali-Gujarati", "alias", "Bengali-InterIndic;InterIndic-Gujarati", "" },
{ "Bengali-Oriya", "alias", "Bengali-InterIndic;InterIndic-Oriya", "" },
{ "Bengali-Tamil", "alias", "Bengali-InterIndic;InterIndic-Tamil", "" },
{ "Bengali-Telugu", "alias", "Bengali-InterIndic;InterIndic-Telugu", "" },
{ "Bengali-Kannada", "alias", "Bengali-InterIndic;InterIndic-Kannada", "" },
{ "Bengali-Malayalam", "alias", "Bengali-InterIndic;InterIndic-Malayalam", "" },
{ "Gurmukhi-Devanagari", "alias", "Gurmukhi-InterIndic;InterIndic-Devanagari", "" },
{ "Gurmukhi-Bengali", "alias", "Gurmukhi-InterIndic;InterIndic-Bengali", "" },
{ "Gurmukhi-Gujarati", "alias", "Gurmukhi-InterIndic;InterIndic-Gujarati", "" },
{ "Gurmukhi-Oriya", "alias", "Gurmukhi-InterIndic;InterIndic-Oriya", "" },
{ "Gurmukhi-Tamil", "alias", "Gurmukhi-InterIndic;InterIndic-Tamil", "" },
{ "Gurmukhi-Telugu", "alias", "Gurmukhi-InterIndic;InterIndic-Telugu", "" },
{ "Gurmukhi-Kannada", "alias", "Gurmukhi-InterIndic;InterIndic-Kannada", "" },
{ "Gurmukhi-Malayalam", "alias", "Gurmukhi-InterIndic;InterIndic-Malayalam", "" },
{ "Gujarati-Devanagari", "alias", "Gujarati-InterIndic;InterIndic-Devanagari", "" },
{ "Gujarati-Bengali", "alias", "Gujarati-InterIndic;InterIndic-Bengali", "" },
{ "Gujarati-Gurmukhi", "alias", "Gujarati-InterIndic;InterIndic-Gurmukhi", "" },
{ "Gujarati-Oriya", "alias", "Gujarati-InterIndic;InterIndic-Oriya", "" },
{ "Gujarati-Tamil", "alias", "Gujarati-InterIndic;InterIndic-Tamil", "" },
{ "Gujarati-Telugu", "alias", "Gujarati-InterIndic;InterIndic-Telugu", "" },
{ "Gujarati-Kannada", "alias", "Gujarati-InterIndic;InterIndic-Kannada", "" },
{ "Gujarati-Malayalam", "alias", "Gujarati-InterIndic;InterIndic-Malayalam", "" },
{ "Oriya-Devanagari", "alias", "Oriya-InterIndic;InterIndic-Devanagari", "" },
{ "Oriya-Bengali", "alias", "Oriya-InterIndic;InterIndic-Bengali", "" },
{ "Oriya-Gurmukhi", "alias", "Oriya-InterIndic;InterIndic-Gurmukhi", "" },
{ "Oriya-Gujarati", "alias", "Oriya-InterIndic;InterIndic-Gujarati", "" },
{ "Oriya-Tamil", "alias", "Oriya-InterIndic;InterIndic-Tamil", "" },
{ "Oriya-Telugu", "alias", "Oriya-InterIndic;InterIndic-Telugu", "" },
{ "Oriya-Kannada", "alias", "Oriya-InterIndic;InterIndic-Kannada", "" },
{ "Oriya-Malayalam", "alias", "Oriya-InterIndic;InterIndic-Malayalam", "" },
{ "Tamil-Devanagari", "alias", "Tamil-InterIndic;InterIndic-Devanagari", "" },
{ "Tamil-Bengali", "alias", "Tamil-InterIndic;InterIndic-Bengali", "" },
{ "Tamil-Gurmukhi", "alias", "Tamil-InterIndic;InterIndic-Gurmukhi", "" },
{ "Tamil-Gujarati", "alias", "Tamil-InterIndic;InterIndic-Gujarati", "" },
{ "Tamil-Oriya", "alias", "Tamil-InterIndic;InterIndic-Oriya", "" },
{ "Tamil-Telugu", "alias", "Tamil-InterIndic;InterIndic-Telugu", "" },
{ "Tamil-Kannada", "alias", "Tamil-InterIndic;InterIndic-Kannada", "" },
{ "Tamil-Malayalam", "alias", "Tamil-InterIndic;InterIndic-Malayalam", "" },
{ "Telugu-Devanagari", "alias", "Telugu-InterIndic;InterIndic-Devanagari", "" },
{ "Telugu-Bengali", "alias", "Telugu-InterIndic;InterIndic-Bengali", "" },
{ "Telugu-Gurmukhi", "alias", "Telugu-InterIndic;InterIndic-Gurmukhi", "" },
{ "Telugu-Gujarati", "alias", "Telugu-InterIndic;InterIndic-Gujarati", "" },
{ "Telugu-Oriya", "alias", "Telugu-InterIndic;InterIndic-Oriya", "" },
{ "Telugu-Tamil", "alias", "Telugu-InterIndic;InterIndic-Tamil", "" },
{ "Telugu-Kannada", "alias", "Telugu-InterIndic;InterIndic-Kannada", "" },
{ "Telugu-Malayalam", "alias", "Telugu-InterIndic;InterIndic-Malayalam", "" },
{ "Kannada-Devanagari", "alias", "Kannada-InterIndic;InterIndic-Devanagari", "" },
{ "Kannada-Bengali", "alias", "Kannada-InterIndic;InterIndic-Bengali", "" },
{ "Kannada-Gurmukhi", "alias", "Kannada-InterIndic;InterIndic-Gurmukhi", "" },
{ "Kannada-Gujarati", "alias", "Kannada-InterIndic;InterIndic-Gujarati", "" },
{ "Kannada-Oriya", "alias", "Kannada-InterIndic;InterIndic-Oriya", "" },
{ "Kannada-Tamil", "alias", "Kannada-InterIndic;InterIndic-Tamil", "" },
{ "Kannada-Telugu", "alias", "Kannada-InterIndic;InterIndic-Telugu", "" },
{ "Kannada-Malayalam", "alias", "Kannada-InterIndic;InterIndic-Malayalam", "" },
{ "Malayalam-Devanagari", "alias", "Malayalam-InterIndic;InterIndic-Devanagari", "" },
{ "Malayalam-Bengali", "alias", "Malayalam-InterIndic;InterIndic-Bengali", "" },
{ "Malayalam-Gurmukhi", "alias", "Malayalam-InterIndic;InterIndic-Gurmukhi", "" },
{ "Malayalam-Gujarati", "alias", "Malayalam-InterIndic;InterIndic-Gujarati", "" },
{ "Malayalam-Oriya", "alias", "Malayalam-InterIndic;InterIndic-Oriya", "" },
{ "Malayalam-Tamil", "alias", "Malayalam-InterIndic;InterIndic-Tamil", "" },
{ "Malayalam-Telugu", "alias", "Malayalam-InterIndic;InterIndic-Telugu", "" },
{ "Malayalam-Kannada", "alias", "Malayalam-InterIndic;InterIndic-Kannada", "" },
// eof
}
}

22
icu4c/source/data/locales/resfiles.mk
View File

@ -98,7 +98,23 @@ zh.txt zh_CN.txt zh_HK.txt zh_SG.txt zh_TW.txt
TRANSLIT_SOURCE=fullhalf.txt translit_index.txt kana.txt kbdescl1.txt\
larabic.txt lcyril.txt ldevan.txt\
lgreek.txt lhebrew.txt ljamo.txt\
lkana.txt quotes.txt ucname.txt
lkana.txt quotes.txt ucname.txt\
Bengali_InterIndic.txt\
Devanagari_InterIndic.txt\
Gujarati_InterIndic.txt\
Gurmukhi_InterIndic.txt\
Kannada_InterIndic.txt\
Malayalam_InterIndic.txt\
Oriya_InterIndic.txt\
Tamil_InterIndic.txt\
Telugu_InterIndic.txt\
InterIndic_Bengali.txt\
InterIndic_Devanagari.txt\
InterIndic_Gujarati.txt\
InterIndic_Gurmukhi.txt\
InterIndic_Kannada.txt\
InterIndic_Malayalam.txt\
InterIndic_Oriya.txt\
InterIndic_Tamil.txt\
InterIndic_Telugu.txt

233
icu4c/source/data/translit/translit_index.txt
View File

@ -1,47 +1,204 @@
//--------------------------------------------------------------------
// Copyright (c) 2000, International Business Machines
// Corporation and others. All Rights Reserved.
// Copyright (c) 1999-2001, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// Date Name Description
// 01/13/2000 aliu Creation.
// THIS IS A MACHINE-GENERATED FILE
// Tool: dumpICUrules.bat
// Source: Transliterator_index.txt
// Date: Fri Mar 2 12:50:49 2001
//--------------------------------------------------------------------
//--------------------------------------------------------------------
// N.B.: This file has been generated mechanically from the
// corresponding ICU4J file, which is the master file that receives
// primary updates. The colon-delimited fields have been split into
// separate strings. For 'file' and 'internal' lines, the encoding
// field has been deleted, since the encoding is processed at build
// time in ICU4C. Certain large rule sets not intended for general
// use have been commented out with the notation "Java only".
//--------------------------------------------------------------------
translit_index {
// Map transliterator names to resource file names. This
// mapping is required because transliterator names typically
// exceed the limits of 8.3 file names.
RuleBasedTransliteratorIDs {
// Copyright (c) 2001, International Business Machines Corporation and
// others. All Rights Reserved.
//
// TRANSLITERATOR INDEX FILE. This file lists the non-algorithmic
// system transliterators. It allows arbitrary mappings between
// transliterator IDs and file names, and also allows the system to
// define aliases for transliterators, so that "Latin-Hangul", for
// example, can be implemented transparently as the compound
// "Latin-Jamo;Jamo-Hangul". Internal IDs may also be defined; these
// are invisible to the user, but can be composed together by the
// system to create visible transliterators.
//
// Blank lines and lines beginning with '#' are ignored.
//
// Lines in this file have one of the following forms (text not
// enclosed by <> is literal):
//
// <id>:file:<resource>:<encoding>:<direction>
// <id>:internal:<resource>:<encoding>:<direction>
// <id>:alias:<getInstanceArg>
//
// <id> is the ID of the system transliterator being defined. These
// are public IDs enumerated by Transliterator.getAvailableIDs(),
// unless the second field is "internal".
//
// <resource> is a ResourceReader resource name. Currently these refer
// to file names under com/ibm/text/resources. This string is passed
// directly to ResourceReader, together with <encoding>.
//
// <encoding> is the character encoding to use when reading <resource>;
// passed directly to ResourceReader. E.g., "UTF8".
//
// <direction> is either "FORWARD" or "REVERSE".
//
// <getInstanceArg> is a string to be passed directly to
// Transliterator.getInstance(). The returned Transliterator object
// then has its ID changed to <id> and is returned.
RuleBasedTransliteratorIDs {
// This is an n x 3 array of strings that serves as an index
// to the system rule-based transliterator resource bundle
// data files. If RBT files are installed or removed from the
// system this table must be updated. For each of the n rows,
// the first item is the ID of the forward transliterator for
// the rule. The second item is the ID of the reverse
// transliterator for the rule. Some rule files only contain
// forward direction rules; for those, the second item is a
// zero-length string. The third item is the name of the
// resource bundle file, a string of 8 or fewer lowercase
// letters or digits. This file will be sought in the data
// directory within the subdirectory "translit". IDs must
// have the form "From-To" or "SingleName" to work properly
// with the Transliterator code.
// Basic language rules
{ "Fullwidth-Halfwidth", "Halfwidth-Fullwidth", "fullhalf" }
{ "Latin-Arabic", "Arabic-Latin", "larabic" }
{ "Latin-Cyrillic", "Cyrillic-Latin", "lcyril" }
{ "Latin-Devanagari", "Devanagari-Latin", "ldevan" }
{ "Latin-Greek", "Greek-Latin", "lgreek" }
{ "Latin-Hebrew", "Hebrew-Latin", "lhebrew" }
{ "Latin-Jamo", "Jamo-Latin", "ljamo" }
{ "Latin-Kana", "Kana-Latin", "lkana" }
{ "Hiragana-Katakana", "Katakana-Hiragana", "kana" }
// Bidirectional rule files
// Other miscellaneous rules
{ "StraightQuotes-CurlyQuotes", "CurlyQuotes-StraightQuotes",
"quotes" }
{ "KeyboardEscape-Latin1", "", "kbdescl1" }
{ "UnicodeName-UnicodeChar", "", "ucname" }
}
{ "Fullwidth-Halfwidth", "file", "fullhalf", "FORWARD" },
{ "Halfwidth-Fullwidth", "file", "fullhalf", "REVERSE" },
{ "Latin-Arabic", "file", "larabic", "FORWARD" },
{ "Arabic-Latin", "file", "larabic", "REVERSE" },
{ "Latin-Cyrillic", "file", "lcyril", "FORWARD" },
{ "Cyrillic-Latin", "file", "lcyril", "REVERSE" },
{ "Latin-Devanagari", "file", "ldevan", "FORWARD" },
{ "Devanagari-Latin", "file", "ldevan", "REVERSE" },
{ "Latin-Greek", "file", "lgreek", "FORWARD" },
{ "Greek-Latin", "file", "lgreek", "REVERSE" },
{ "Latin-Hebrew", "file", "lhebrew", "FORWARD" },
{ "Hebrew-Latin", "file", "lhebrew", "REVERSE" },
{ "Latin-Jamo", "file", "ljamo", "FORWARD" },
{ "Jamo-Latin", "file", "ljamo", "REVERSE" },
{ "Latin-Kana", "file", "lkana", "FORWARD" },
{ "Kana-Latin", "file", "lkana", "REVERSE" },
{ "Hiragana-Katakana", "file", "kana", "FORWARD" },
{ "Katakana-Hiragana", "file", "kana", "REVERSE" },
{ "StraightQuotes-CurlyQuotes", "file", "quotes", "FORWARD" },
{ "CurlyQuotes-StraightQuotes", "file", "quotes", "REVERSE" },
// One way rules (forward only)
// Java only: { "Han-Pinyin", "file", "-", "FORWARD" },
// Java only: { "Kanji-English", "file", "-", "FORWARD" },
// Java only: { "Kanji-OnRomaji", "file", "-", "FORWARD" },
{ "KeyboardEscape-Latin1", "file", "kbdescl1", "FORWARD" },
{ "UnicodeName-UnicodeChar", "file", "ucname", "FORWARD" },
// Compound rules
{ "Latin-Hangul", "alias", "Latin-Jamo;Jamo-Hangul", "" },
{ "Hangul-Latin", "alias", "Hangul-Jamo;Jamo-Latin", "" },
// Inter-Indic composed rules
{ "Devanagari-InterIndic", "internal", "Devanagari_InterIndic", "FORWARD" },
{ "Bengali-InterIndic", "internal", "Bengali_InterIndic", "FORWARD" },
{ "Gurmukhi-InterIndic", "internal", "Gurmukhi_InterIndic", "FORWARD" },
{ "Gujarati-InterIndic", "internal", "Gujarati_InterIndic", "FORWARD" },
{ "Oriya-InterIndic", "internal", "Oriya_InterIndic", "FORWARD" },
{ "Tamil-InterIndic", "internal", "Tamil_InterIndic", "FORWARD" },
{ "Telugu-InterIndic", "internal", "Telugu_InterIndic", "FORWARD" },
{ "Kannada-InterIndic", "internal", "Kannada_InterIndic", "FORWARD" },
{ "Malayalam-InterIndic", "internal", "Malayalam_InterIndic", "FORWARD" },
{ "InterIndic-Devanagari", "internal", "InterIndic_Devanagari", "FORWARD" },
{ "InterIndic-Bengali", "internal", "InterIndic_Bengali", "FORWARD" },
{ "InterIndic-Gurmukhi", "internal", "InterIndic_Gurmukhi", "FORWARD" },
{ "InterIndic-Gujarati", "internal", "InterIndic_Gujarati", "FORWARD" },
{ "InterIndic-Oriya", "internal", "InterIndic_Oriya", "FORWARD" },
{ "InterIndic-Tamil", "internal", "InterIndic_Tamil", "FORWARD" },
{ "InterIndic-Telugu", "internal", "InterIndic_Telugu", "FORWARD" },
{ "InterIndic-Kannada", "internal", "InterIndic_Kannada", "FORWARD" },
{ "InterIndic-Malayalam", "internal", "InterIndic_Malayalam", "FORWARD" },
{ "Devanagari-Bengali", "alias", "Devanagari-InterIndic;InterIndic-Bengali", "" },
{ "Devanagari-Gurmukhi", "alias", "Devanagari-InterIndic;InterIndic-Gurmukhi", "" },
{ "Devanagari-Gujarati", "alias", "Devanagari-InterIndic;InterIndic-Gujarati", "" },
{ "Devanagari-Oriya", "alias", "Devanagari-InterIndic;InterIndic-Oriya", "" },
{ "Devanagari-Tamil", "alias", "Devanagari-InterIndic;InterIndic-Tamil", "" },
{ "Devanagari-Telugu", "alias", "Devanagari-InterIndic;InterIndic-Telugu", "" },
{ "Devanagari-Kannada", "alias", "Devanagari-InterIndic;InterIndic-Kannada", "" },
{ "Devanagari-Malayalam", "alias", "Devanagari-InterIndic;InterIndic-Malayalam", "" },
{ "Bengali-Devanagari", "alias", "Bengali-InterIndic;InterIndic-Devanagari", "" },
{ "Bengali-Gurmukhi", "alias", "Bengali-InterIndic;InterIndic-Gurmukhi", "" },
{ "Bengali-Gujarati", "alias", "Bengali-InterIndic;InterIndic-Gujarati", "" },
{ "Bengali-Oriya", "alias", "Bengali-InterIndic;InterIndic-Oriya", "" },
{ "Bengali-Tamil", "alias", "Bengali-InterIndic;InterIndic-Tamil", "" },
{ "Bengali-Telugu", "alias", "Bengali-InterIndic;InterIndic-Telugu", "" },
{ "Bengali-Kannada", "alias", "Bengali-InterIndic;InterIndic-Kannada", "" },
{ "Bengali-Malayalam", "alias", "Bengali-InterIndic;InterIndic-Malayalam", "" },
{ "Gurmukhi-Devanagari", "alias", "Gurmukhi-InterIndic;InterIndic-Devanagari", "" },
{ "Gurmukhi-Bengali", "alias", "Gurmukhi-InterIndic;InterIndic-Bengali", "" },
{ "Gurmukhi-Gujarati", "alias", "Gurmukhi-InterIndic;InterIndic-Gujarati", "" },
{ "Gurmukhi-Oriya", "alias", "Gurmukhi-InterIndic;InterIndic-Oriya", "" },
{ "Gurmukhi-Tamil", "alias", "Gurmukhi-InterIndic;InterIndic-Tamil", "" },
{ "Gurmukhi-Telugu", "alias", "Gurmukhi-InterIndic;InterIndic-Telugu", "" },
{ "Gurmukhi-Kannada", "alias", "Gurmukhi-InterIndic;InterIndic-Kannada", "" },
{ "Gurmukhi-Malayalam", "alias", "Gurmukhi-InterIndic;InterIndic-Malayalam", "" },
{ "Gujarati-Devanagari", "alias", "Gujarati-InterIndic;InterIndic-Devanagari", "" },
{ "Gujarati-Bengali", "alias", "Gujarati-InterIndic;InterIndic-Bengali", "" },
{ "Gujarati-Gurmukhi", "alias", "Gujarati-InterIndic;InterIndic-Gurmukhi", "" },
{ "Gujarati-Oriya", "alias", "Gujarati-InterIndic;InterIndic-Oriya", "" },
{ "Gujarati-Tamil", "alias", "Gujarati-InterIndic;InterIndic-Tamil", "" },
{ "Gujarati-Telugu", "alias", "Gujarati-InterIndic;InterIndic-Telugu", "" },
{ "Gujarati-Kannada", "alias", "Gujarati-InterIndic;InterIndic-Kannada", "" },
{ "Gujarati-Malayalam", "alias", "Gujarati-InterIndic;InterIndic-Malayalam", "" },
{ "Oriya-Devanagari", "alias", "Oriya-InterIndic;InterIndic-Devanagari", "" },
{ "Oriya-Bengali", "alias", "Oriya-InterIndic;InterIndic-Bengali", "" },
{ "Oriya-Gurmukhi", "alias", "Oriya-InterIndic;InterIndic-Gurmukhi", "" },
{ "Oriya-Gujarati", "alias", "Oriya-InterIndic;InterIndic-Gujarati", "" },
{ "Oriya-Tamil", "alias", "Oriya-InterIndic;InterIndic-Tamil", "" },
{ "Oriya-Telugu", "alias", "Oriya-InterIndic;InterIndic-Telugu", "" },
{ "Oriya-Kannada", "alias", "Oriya-InterIndic;InterIndic-Kannada", "" },
{ "Oriya-Malayalam", "alias", "Oriya-InterIndic;InterIndic-Malayalam", "" },
{ "Tamil-Devanagari", "alias", "Tamil-InterIndic;InterIndic-Devanagari", "" },
{ "Tamil-Bengali", "alias", "Tamil-InterIndic;InterIndic-Bengali", "" },
{ "Tamil-Gurmukhi", "alias", "Tamil-InterIndic;InterIndic-Gurmukhi", "" },
{ "Tamil-Gujarati", "alias", "Tamil-InterIndic;InterIndic-Gujarati", "" },
{ "Tamil-Oriya", "alias", "Tamil-InterIndic;InterIndic-Oriya", "" },
{ "Tamil-Telugu", "alias", "Tamil-InterIndic;InterIndic-Telugu", "" },
{ "Tamil-Kannada", "alias", "Tamil-InterIndic;InterIndic-Kannada", "" },
{ "Tamil-Malayalam", "alias", "Tamil-InterIndic;InterIndic-Malayalam", "" },
{ "Telugu-Devanagari", "alias", "Telugu-InterIndic;InterIndic-Devanagari", "" },
{ "Telugu-Bengali", "alias", "Telugu-InterIndic;InterIndic-Bengali", "" },
{ "Telugu-Gurmukhi", "alias", "Telugu-InterIndic;InterIndic-Gurmukhi", "" },
{ "Telugu-Gujarati", "alias", "Telugu-InterIndic;InterIndic-Gujarati", "" },
{ "Telugu-Oriya", "alias", "Telugu-InterIndic;InterIndic-Oriya", "" },
{ "Telugu-Tamil", "alias", "Telugu-InterIndic;InterIndic-Tamil", "" },
{ "Telugu-Kannada", "alias", "Telugu-InterIndic;InterIndic-Kannada", "" },
{ "Telugu-Malayalam", "alias", "Telugu-InterIndic;InterIndic-Malayalam", "" },
{ "Kannada-Devanagari", "alias", "Kannada-InterIndic;InterIndic-Devanagari", "" },
{ "Kannada-Bengali", "alias", "Kannada-InterIndic;InterIndic-Bengali", "" },
{ "Kannada-Gurmukhi", "alias", "Kannada-InterIndic;InterIndic-Gurmukhi", "" },
{ "Kannada-Gujarati", "alias", "Kannada-InterIndic;InterIndic-Gujarati", "" },
{ "Kannada-Oriya", "alias", "Kannada-InterIndic;InterIndic-Oriya", "" },
{ "Kannada-Tamil", "alias", "Kannada-InterIndic;InterIndic-Tamil", "" },
{ "Kannada-Telugu", "alias", "Kannada-InterIndic;InterIndic-Telugu", "" },
{ "Kannada-Malayalam", "alias", "Kannada-InterIndic;InterIndic-Malayalam", "" },
{ "Malayalam-Devanagari", "alias", "Malayalam-InterIndic;InterIndic-Devanagari", "" },
{ "Malayalam-Bengali", "alias", "Malayalam-InterIndic;InterIndic-Bengali", "" },
{ "Malayalam-Gurmukhi", "alias", "Malayalam-InterIndic;InterIndic-Gurmukhi", "" },
{ "Malayalam-Gujarati", "alias", "Malayalam-InterIndic;InterIndic-Gujarati", "" },
{ "Malayalam-Oriya", "alias", "Malayalam-InterIndic;InterIndic-Oriya", "" },
{ "Malayalam-Tamil", "alias", "Malayalam-InterIndic;InterIndic-Tamil", "" },
{ "Malayalam-Telugu", "alias", "Malayalam-InterIndic;InterIndic-Telugu", "" },
{ "Malayalam-Kannada", "alias", "Malayalam-InterIndic;InterIndic-Kannada", "" },
// eof
}
}

119
icu4c/source/i18n/translit.cpp
View File

@ -31,27 +31,20 @@ const UChar Transliterator::ID_SEP = 0x002D; /*-*/
const UChar Transliterator::ID_DELIM = 0x003B; /*;*/
static Hashtable _cache;
static Hashtable _internalCache;
/**
* Dictionary of known transliterators. Keys are <code>String</code>
* names, values are one of the following:
*
* <ul><li><code>Transliterator</code> objects
*
* <li><code>RULE_BASED_PLACEHOLDER</code>, in which case the ID
* will have its first ID_SEP removed and be appended to
* RB_RULE_BASED_PREFIX to form a resource bundle name from which
* the RB_RULE key is looked up to obtain the rule.
*
* <li><code>REVERSE_RULE_BASED_PLACEHOLDER</code>. Like
* <code>RULE_BASED_PLACEHOLDER</code>, except the entity names in
* the ID are reversed, and the argument
* RuleBasedTransliterator::REVERSE is pased to the
* RuleBasedTransliterator constructor.
* </ul>
* Cache of public system transliterators. Keys are UnicodeString
* names, values are CacheEntry objects.
*/
Hashtable* Transliterator::cache = &_cache;
/**
* Like 'cache', but IDs are not public. Internal transliterators are
* combined together and aliased to public IDs.
*/
Hashtable* Transliterator::internalCache = &_internalCache;
/**
* The mutex controlling access to the cache.
*/
@ -592,6 +585,9 @@ Transliterator* Transliterator::_createInstance(const UnicodeString& ID,
Mutex lock(&cacheMutex);
CacheEntry* entry = (CacheEntry*) cache->get(ID);
if (entry == 0) {
entry = (CacheEntry*) internalCache->get(ID);
}
TransliterationRuleData* data = 0;
@ -604,12 +600,16 @@ Transliterator* Transliterator::_createInstance(const UnicodeString& ID,
// Fall through to construct transliterator from cached Data object.
} else if (entry->entryType == CacheEntry::PROTOTYPE) {
return entry->u.prototype->clone();
} else if (entry->entryType == CacheEntry::ALIAS) {
Transliterator *t = createInstance(entry->stringArg);
if (t != 0) {
t->setID(ID);
}
return t;
} else {
// At this point entry type must be either RULE_BASED_PLACEHOLDER
// or REVERSE_RULE_BASED_PLACEHOLDER.
UBool isReverse =
(entry->entryType ==
CacheEntry::REVERSE_RULE_BASED_PLACEHOLDER);
// At this point entry type must be either RULES_FORWARD
// or RULES_REVERSE
UBool isReverse = (entry->entryType == CacheEntry::RULES_REVERSE);
// We use the file name, taken from another resource bundle
// 2-d array at static init time, as a locale language. We're
@ -617,8 +617,8 @@ Transliterator* Transliterator::_createInstance(const UnicodeString& ID,
// name; this in no way represents an actual locale.
char *ch;
ch = new char[entry->rbFile.size() + 1];
ch[entry->rbFile.extract(0, 0x7fffffff, ch, "")] = 0;
ch = new char[entry->stringArg.size() + 1];
ch[entry->stringArg.extract(0, 0x7fffffff, ch, "")] = 0;
Locale fakeLocale(ch);
delete [] ch;
@ -824,18 +824,31 @@ void Transliterator::initializeCache(void) {
// Before looking for the resource, construct our cache.
// That way if the resource is absent, we will at least
// have a valid cache object.
// cache = new Hashtable(status); // TODO: What if this call fails?
cacheIDs.setComparer(compareIDs);
/* The following code parses the index table located in
* icu/data/translit/index.txt. The index is an n x 3 table
* that looks like this:
* icu/data/translit_index.txt. The index is an n x 4 table
* that follows this format:
*
* RuleBasedTransliteratorIDs {
* { "Latin-Arabic", "Arabic-Latin", "larabic" }
* { "KeyboardEscape-Latin1", "", "keyescl1" }
* ...
* }
* <id>:file:<resource>:<direction>
* <id>:internal:<resource>:<direction>
* <id>:alias:<getInstanceArg>:
*
* <id> is the ID of the system transliterator being defined. These
* are public IDs enumerated by Transliterator.getAvailableIDs(),
* unless the second field is "internal".
*
* <resource> is a ResourceReader resource name. Currently these refer
* to file names under com/ibm/text/resources. This string is passed
* directly to ResourceReader, together with <encoding>.
*
* <direction> is either "FORWARD" or "REVERSE".
*
* <getInstanceArg> is a string to be passed directly to
* Transliterator.getInstance(). The returned Transliterator object
* then has its ID changed to <id> and is returned.
*
* The extra blank field on "alias" lines is to make the array square.
*/
Locale indexLoc("translit_index");
@ -844,34 +857,30 @@ void Transliterator::initializeCache(void) {
indexLoc, status);
int32_t rows, cols;
const UnicodeString** ruleBasedIDs =
const UnicodeString** index =
bundle.get2dArray(RB_RULE_BASED_IDS, rows, cols, status);
if (U_SUCCESS(status) && (cols == 3)) {
if (U_SUCCESS(status) && (cols == 4)) {
for (int32_t i=0; i<rows; ++i) {
const UnicodeString* row = ruleBasedIDs[i];
for (int32_t col=0; col<2; ++col) {
if (row[col].length() > 0) {
CacheEntry* entry = new CacheEntry();
entry->entryType = (col == 0) ?
CacheEntry::RULE_BASED_PLACEHOLDER :
CacheEntry::REVERSE_RULE_BASED_PLACEHOLDER;
entry->rbFile = UnicodeString(row[2]);
//uhash_putKey(cache, hash(row[col]), entry, &status);
cache->put(row[col], entry, status);
/* It's okay to take the address of the string
* from the resource bundle under the assumption
* that the RB is caching these, and that they
* stay around forever. If this changes, what we
* need to do is change the id vector so that it
* owns its strings and create a copy here.
*/
/*cacheIDs.addElement((void*) &row[col]);*/
cacheIDs.addElement((void*) new UnicodeString(row[col]));
}
const UnicodeString* row = index[i];
UChar type = row[1].charAt(0);
CacheEntry* entry = new CacheEntry();
if (type == 0x0066 || type == 0x0069) { // 'f', 'i'
// 'file' or 'internal'; row[2]=resource, row[3]=direction
UBool isReverse = (row[3].charAt(0) == 0x0052); // 'R'
entry->entryType = isReverse ?
CacheEntry::RULES_REVERSE :
CacheEntry::RULES_FORWARD;
} else { // assert(type == 0x0061 /*a*/)
// 'alias'; row[2]=createInstance argument
entry->entryType = CacheEntry::ALIAS;
}
entry->stringArg = UnicodeString(row[2]);
// Use internalCache for 'internal' entries
Hashtable* c = (type == 0x0069/*i*/) ? internalCache : cache;
c->put(row[0], entry, status);
// cacheIDs owns & should delete the following string
cacheIDs.addElement((void*) new UnicodeString(row[0]));
}
}

39
icu4c/source/i18n/unicode/translit.h
View File

@ -242,31 +242,19 @@ private:
int32_t maximumContextLength;
/**
* Dictionary of known transliterators. Keys are <code>String</code>
* names, values are one of the following:
*
* <ul><li><code>Transliterator</code> objects
*
* <li><code>Class</code> objects. Such objects must represent
* subclasses of <code>Transliterator</code>, and must satisfy the
* constraints described in <code>registerClass()</code>
*
* <li><code>RULE_BASED_PLACEHOLDER</code>, in which case the ID
* will have its first '-' removed and be appended to
* RB_RULE_BASED_PREFIX to form a resource bundle name from which
* the RB_RULE key is looked up to obtain the rule.
*
* <li><code>REVERSE_RULE_BASED_PLACEHOLDER</code>. Like
* <code>RULE_BASED_PLACEHOLDER</code>, except the entity names in
* the ID are reversed, and the argument
* RuleBasedTransliterator.REVERSE is pased to the
* RuleBasedTransliterator constructor.
* </ul>
* Cache of public system transliterators. Keys are UnicodeString
* names, values are CacheEntry objects.
*/
static Hashtable* cache;
/**
* The mutex controlling access to the cache.
* Like 'cache', but IDs are not public. Internal transliterators
* are combined together and aliased to public IDs.
*/
static Hashtable* internalCache;
/**
* The mutex controlling access to the caches.
*/
static UMTX cacheMutex;
@ -296,13 +284,16 @@ private:
*/
struct CacheEntry {
enum Type {
RULE_BASED_PLACEHOLDER,
REVERSE_RULE_BASED_PLACEHOLDER,
RULES_FORWARD,
RULES_REVERSE,
PROTOTYPE,
RBT_DATA,
ALIAS,
NONE // Only used for uninitialized entries
} entryType;
UnicodeString rbFile; // For *PLACEHOLDER
// NOTE: stringArg cannot go inside the union because
// it has a copy constructor
UnicodeString stringArg; // For RULES_*, ALIAS
union {
Transliterator* prototype; // For PROTOTYPE
TransliterationRuleData* data; // For RBT_DATA

22
icu4c/source/test/intltest/transtst.cpp
View File

@ -63,6 +63,7 @@ TransliteratorTest::runIndexedTest(int32_t index, UBool exec,
CASE(19,TestHiraganaKatakana);
CASE(20,TestCopyJ476);
CASE(21,TestAnchors);
CASE(22,TestInterIndic);
default: name = ""; break;
}
}
@ -881,6 +882,27 @@ void TransliteratorTest::TestCopyJ476(void) {
delete t2;
}
/**
* Test inter-Indic transliterators. These are composed.
* ICU4C Jitterbug 483.
*/
void TransliteratorTest::TestInterIndic(void) {
UnicodeString ID("Devanagari-Gujarati", "");
Transliterator* dg = Transliterator::createInstance(ID);
if (dg == 0) {
errln("FAIL: createInstance(" + ID + ") returned NULL");
return;
}
UnicodeString id = dg->getID();
if (id != ID) {
errln("FAIL: createInstance(" + ID + ")->getID() => " + id);
}
UnicodeString dev = CharsToUnicodeString("\\u0901\\u090B\\u0925");
UnicodeString guj = CharsToUnicodeString("\\u0A81\\u0A8B\\u0AA5");
expect(*dg, dev, guj);
delete dg;
}
//======================================================================
// Support methods
//======================================================================

6
icu4c/source/test/intltest/transtst.h
View File

@ -127,6 +127,12 @@ class TransliteratorTest : public IntlTest {
*/
void TestCopyJ476(void);
/**
* Test inter-Indic transliterators. These are composed.
* ICU4C Jitterbug 483.
*/
void TestInterIndic(void);
//======================================================================
// Support methods
//======================================================================