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

Load RuleBasedTransliterator files from UTF8 files instead of ResourceBundles

Browse Source 
X-SVN-Rev: 3551
This commit is contained in:
Alan Liu 2001-02-03 00:57:34 +00:00
parent 189ab5836c
commit 4f7d4c5d07
34 changed files with 10 additions and 40692 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
icu4j/build.xml
View File

@ -6,8 +6,8 @@
*******************************************************************************
*
* $Source: /xsrl/Nsvn/icu/icu4j/build.xml,v $
* $Date: 2001/01/11 21:06:07 $
* $Revision: 1.25 $
* $Date: 2001/02/03 00:57:34 $
* $Revision: 1.26 $
*
*******************************************************************************
* This is the ant build file for ICU4J. See readme.html for more information.
@ -39,7 +39,7 @@
<target name="all" depends="core,tests,tools,demos,jar,ucharacterjar,docs"/>
<target name="core" depends="init,ucharacterData">
<target name="core" depends="init,ucharacterData,translitData">
<mkdir dir="${build.dir}"/>
<copy file="${src.dir}/com/ibm/text/resources/thai_dict"
todir="${build.dir}/com/ibm/text/resources/"/>
@ -111,6 +111,13 @@
</copy>
</target>
<target name ="translitData" depends="init">
<copy todir="${build.dir}/com/ibm/text/resources">
<fileset dir="${src.dir}/com/ibm/text/resources"
includes="Transliterator_*.utf8.txt"/>
</copy>
</target>
<target name="ucharacterjar" depends="core">
<jar jarfile="${ucharacter.jar.file}"
includes="com/ibm/icu/text/*.class,com/ibm/icu/text/*.dat"

115
icu4j/src/com/ibm/text/resources/TransliterationRule_Bengali_InterIndic.java
View File

@ -1,115 +0,0 @@
/***********************************************************************
* Copyright (c) 2000, International Business Machines Corporation
* and others. All Rights Reserved.
************************************************************************
* > THIS FILE WAS MACHINE GENERATED <
* > DO NOT EDIT BY HAND <
* > RUN TOOL TO REGENERATE <
* Tool: icu4j/src/com/ibm/tools/translit/indic.pl
* Creation date: Fri Oct 6 15:55:21 2000
*/
package com.ibm.text.resources;
import java.util.ListResourceBundle;
public class TransliterationRule_Bengali_InterIndic extends ListResourceBundle {
/**
* Overrides ListResourceBundle
*/
public Object[][] getContents() {
return new Object[][] {
{ "Rule",
"\u0981>\uE001;"+ // SIGN CANDRABINDU
"\u0982>\uE002;"+ // SIGN ANUSVARA
"\u0983>\uE003;"+ // SIGN VISARGA
"\u0985>\uE005;"+ // LETTER A
"\u0986>\uE006;"+ // LETTER AA
"\u0987>\uE007;"+ // LETTER I
"\u0988>\uE008;"+ // LETTER II
"\u0989>\uE009;"+ // LETTER U
"\u098A>\uE00A;"+ // LETTER UU
"\u098B>\uE00B;"+ // LETTER VOCALIC R
"\u098C>\uE00C;"+ // LETTER VOCALIC L
"\u098F>\uE081;"+ // LETTER E
"\u0990>\uE010;"+ // LETTER AI
"\u0993>\uE082;"+ // LETTER O
"\u0994>\uE014;"+ // LETTER AU
"\u0995>\uE015;"+ // LETTER KA
"\u0996>\uE016;"+ // LETTER KHA
"\u0997>\uE017;"+ // LETTER GA
"\u0998>\uE018;"+ // LETTER GHA
"\u0999>\uE019;"+ // LETTER NGA
"\u099A>\uE01A;"+ // LETTER CA
"\u099B>\uE01B;"+ // LETTER CHA
"\u099C>\uE01C;"+ // LETTER JA
"\u099D>\uE01D;"+ // LETTER JHA
"\u099E>\uE01E;"+ // LETTER NYA
"\u099F>\uE01F;"+ // LETTER TTA
"\u09A0>\uE020;"+ // LETTER TTHA
"\u09A1>\uE021;"+ // LETTER DDA
"\u09A2>\uE022;"+ // LETTER DDHA
"\u09A3>\uE023;"+ // LETTER NNA
"\u09A4>\uE024;"+ // LETTER TA
"\u09A5>\uE025;"+ // LETTER THA
"\u09A6>\uE026;"+ // LETTER DA
"\u09A7>\uE027;"+ // LETTER DHA
"\u09A8>\uE028;"+ // LETTER NA
"\u09AA>\uE02A;"+ // LETTER PA
"\u09AB>\uE02B;"+ // LETTER PHA
"\u09AC>\uE02C;"+ // LETTER BA
"\u09AD>\uE02D;"+ // LETTER BHA
"\u09AE>\uE02E;"+ // LETTER MA
"\u09AF>\uE02F;"+ // LETTER YA
"\u09B0>\uE030;"+ // LETTER RA
"\u09B2>\uE032;"+ // LETTER LA
"\u09B6>\uE036;"+ // LETTER SHA
"\u09B7>\uE037;"+ // LETTER SSA
"\u09B8>\uE038;"+ // LETTER SA
"\u09B9>\uE039;"+ // LETTER HA
"\u09BC>\uE03C;"+ // SIGN NUKTA
"\u09BE>\uE03E;"+ // VOWEL SIGN AA
"\u09BF>\uE03F;"+ // VOWEL SIGN I
"\u09C0>\uE040;"+ // VOWEL SIGN II
"\u09C1>\uE041;"+ // VOWEL SIGN U
"\u09C2>\uE042;"+ // VOWEL SIGN UU
"\u09C3>\uE043;"+ // VOWEL SIGN VOCALIC R
"\u09C4>\uE044;"+ // VOWEL SIGN VOCALIC RR
"\u09C7>\uE084;"+ // VOWEL SIGN E
"\u09C8>\uE048;"+ // VOWEL SIGN AI
"\u09CB>\uE085;"+ // VOWEL SIGN O
"\u09CC>\uE04C;"+ // VOWEL SIGN AU
"\u09CD>\uE04D;"+ // SIGN VIRAMA
"\u09D7>\uE057;"+ // AU LENGTH MARK
"\u09DC>\uE083;"+ // LETTER RRA
"\u09DD>\uE05D;"+ // LETTER RHA
"\u09DF>\uE05F;"+ // LETTER YYA
"\u09E0>\uE060;"+ // LETTER VOCALIC RR
"\u09E1>\uE061;"+ // LETTER VOCALIC LL
"\u09E2>\uE062;"+ // VOWEL SIGN VOCALIC L
"\u09E3>\uE063;"+ // VOWEL SIGN VOCALIC LL
"\u09E6>\uE066;"+ // DIGIT ZERO
"\u09E7>\uE067;"+ // DIGIT ONE
"\u09E8>\uE068;"+ // DIGIT TWO
"\u09E9>\uE069;"+ // DIGIT THREE
"\u09EA>\uE06A;"+ // DIGIT FOUR
"\u09EB>\uE06B;"+ // DIGIT FIVE
"\u09EC>\uE06C;"+ // DIGIT SIX
"\u09ED>\uE06D;"+ // DIGIT SEVEN
"\u09EE>\uE06E;"+ // DIGIT EIGHT
"\u09EF>\uE06F;"+ // DIGIT NINE
// \u09F0>; // UNMAPPED Bengali-InterIndic: LETTER RA WITH MIDDLE DIAGONAL
// \u09F1>; // UNMAPPED Bengali-InterIndic: LETTER RA WITH LOWER DIAGONAL
// \u09F2>; // UNMAPPED Bengali-InterIndic: RUPEE MARK
// \u09F3>; // UNMAPPED Bengali-InterIndic: RUPEE SIGN
// \u09F4>; // UNMAPPED Bengali-InterIndic: CURRENCY NUMERATOR ONE
// \u09F5>; // UNMAPPED Bengali-InterIndic: CURRENCY NUMERATOR TWO
// \u09F6>; // UNMAPPED Bengali-InterIndic: CURRENCY NUMERATOR THREE
// \u09F7>; // UNMAPPED Bengali-InterIndic: CURRENCY NUMERATOR FOUR
// \u09F8>; // UNMAPPED Bengali-InterIndic: CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR
// \u09F9>; // UNMAPPED Bengali-InterIndic: CURRENCY DENOMINATOR SIXTEEN
"\u09FA>\uE080;"+ // ISSHAR
""
}
};
}
}

130
icu4j/src/com/ibm/text/resources/TransliterationRule_Devanagari_InterIndic.java
View File

@ -1,130 +0,0 @@
/***********************************************************************
* Copyright (c) 2000, International Business Machines Corporation
* and others. All Rights Reserved.
************************************************************************
* > THIS FILE WAS MACHINE GENERATED <
* > DO NOT EDIT BY HAND <
* > RUN TOOL TO REGENERATE <
* Tool: icu4j/src/com/ibm/tools/translit/indic.pl
* Creation date: Fri Oct 6 15:55:21 2000
*/
package com.ibm.text.resources;
import java.util.ListResourceBundle;
public class TransliterationRule_Devanagari_InterIndic extends ListResourceBundle {
/**
* Overrides ListResourceBundle
*/
public Object[][] getContents() {
return new Object[][] {
{ "Rule",
"\u0901>\uE001;"+ // SIGN CANDRABINDU
"\u0902>\uE002;"+ // SIGN ANUSVARA
"\u0903>\uE003;"+ // SIGN VISARGA
"\u0905>\uE005;"+ // LETTER A
"\u0906>\uE006;"+ // LETTER AA
"\u0907>\uE007;"+ // LETTER I
"\u0908>\uE008;"+ // LETTER II
"\u0909>\uE009;"+ // LETTER U
"\u090A>\uE00A;"+ // LETTER UU
"\u090B>\uE00B;"+ // LETTER VOCALIC R
"\u090C>\uE00C;"+ // LETTER VOCALIC L
// \u090D>; // UNMAPPED Devanagari-InterIndic: LETTER CANDRA E
// \u090E>; // UNMAPPED Devanagari-InterIndic: LETTER SHORT E
"\u090F>\uE081;"+ // LETTER E
"\u0910>\uE010;"+ // LETTER AI
// \u0911>; // UNMAPPED Devanagari-InterIndic: LETTER CANDRA O
// \u0912>; // UNMAPPED Devanagari-InterIndic: LETTER SHORT O
"\u0913>\uE082;"+ // LETTER O
"\u0914>\uE014;"+ // LETTER AU
"\u0915>\uE015;"+ // LETTER KA
"\u0916>\uE016;"+ // LETTER KHA
"\u0917>\uE017;"+ // LETTER GA
"\u0918>\uE018;"+ // LETTER GHA
"\u0919>\uE019;"+ // LETTER NGA
"\u091A>\uE01A;"+ // LETTER CA
"\u091B>\uE01B;"+ // LETTER CHA
"\u091C>\uE01C;"+ // LETTER JA
"\u091D>\uE01D;"+ // LETTER JHA
"\u091E>\uE01E;"+ // LETTER NYA
"\u091F>\uE01F;"+ // LETTER TTA
"\u0920>\uE020;"+ // LETTER TTHA
"\u0921>\uE021;"+ // LETTER DDA
"\u0922>\uE022;"+ // LETTER DDHA
"\u0923>\uE023;"+ // LETTER NNA
"\u0924>\uE024;"+ // LETTER TA
"\u0925>\uE025;"+ // LETTER THA
"\u0926>\uE026;"+ // LETTER DA
"\u0927>\uE027;"+ // LETTER DHA
"\u0928>\uE028;"+ // LETTER NA
"\u0929>\uE029;"+ // LETTER NNNA
"\u092A>\uE02A;"+ // LETTER PA
"\u092B>\uE02B;"+ // LETTER PHA
"\u092C>\uE02C;"+ // LETTER BA
"\u092D>\uE02D;"+ // LETTER BHA
"\u092E>\uE02E;"+ // LETTER MA
"\u092F>\uE02F;"+ // LETTER YA
"\u0930>\uE030;"+ // LETTER RA
"\u0931>\uE083;"+ // LETTER RRA
"\u0932>\uE032;"+ // LETTER LA
"\u0933>\uE033;"+ // LETTER LLA
"\u0934>\uE034;"+ // LETTER LLLA
"\u0935>\uE035;"+ // LETTER VA
"\u0936>\uE036;"+ // LETTER SHA
"\u0937>\uE037;"+ // LETTER SSA
"\u0938>\uE038;"+ // LETTER SA
"\u0939>\uE039;"+ // LETTER HA
"\u093C>\uE03C;"+ // SIGN NUKTA
"\u093D>\uE03D;"+ // SIGN AVAGRAHA
"\u093E>\uE03E;"+ // VOWEL SIGN AA
"\u093F>\uE03F;"+ // VOWEL SIGN I
"\u0940>\uE040;"+ // VOWEL SIGN II
"\u0941>\uE041;"+ // VOWEL SIGN U
"\u0942>\uE042;"+ // VOWEL SIGN UU
"\u0943>\uE043;"+ // VOWEL SIGN VOCALIC R
"\u0944>\uE044;"+ // VOWEL SIGN VOCALIC RR
"\u0945>\uE045;"+ // VOWEL SIGN CANDRA E
// \u0946>; // UNMAPPED Devanagari-InterIndic: VOWEL SIGN SHORT E
"\u0947>\uE084;"+ // VOWEL SIGN E
"\u0948>\uE048;"+ // VOWEL SIGN AI
"\u0949>\uE049;"+ // VOWEL SIGN CANDRA O
// \u094A>; // UNMAPPED Devanagari-InterIndic: VOWEL SIGN SHORT O
"\u094B>\uE085;"+ // VOWEL SIGN O
"\u094C>\uE04C;"+ // VOWEL SIGN AU
"\u094D>\uE04D;"+ // SIGN VIRAMA
"\u0950>\uE050;"+ // OM
// \u0951>; // UNMAPPED Devanagari-InterIndic: STRESS SIGN UDATTA
// \u0952>; // UNMAPPED Devanagari-InterIndic: STRESS SIGN ANUDATTA
// \u0953>; // UNMAPPED Devanagari-InterIndic: GRAVE ACCENT
// \u0954>; // UNMAPPED Devanagari-InterIndic: ACUTE ACCENT
// \u0958>; // UNMAPPED Devanagari-InterIndic: LETTER QA
"\u0959>\uE059;"+ // LETTER KHHA
"\u095A>\uE05A;"+ // LETTER GHHA
"\u095B>\uE05B;"+ // LETTER ZA
// \u095C>; // UNMAPPED Devanagari-InterIndic: LETTER DDDHA
"\u095D>\uE05D;"+ // LETTER RHA
"\u095E>\uE05E;"+ // LETTER FA
"\u095F>\uE05F;"+ // LETTER YYA
"\u0960>\uE060;"+ // LETTER VOCALIC RR
"\u0961>\uE061;"+ // LETTER VOCALIC LL
"\u0962>\uE062;"+ // VOWEL SIGN VOCALIC L
"\u0963>\uE063;"+ // VOWEL SIGN VOCALIC LL
// \u0964>; // UNMAPPED Devanagari-InterIndic: DANDA
// \u0965>; // UNMAPPED Devanagari-InterIndic: DOUBLE DANDA
"\u0966>\uE066;"+ // DIGIT ZERO
"\u0967>\uE067;"+ // DIGIT ONE
"\u0968>\uE068;"+ // DIGIT TWO
"\u0969>\uE069;"+ // DIGIT THREE
"\u096A>\uE06A;"+ // DIGIT FOUR
"\u096B>\uE06B;"+ // DIGIT FIVE
"\u096C>\uE06C;"+ // DIGIT SIX
"\u096D>\uE06D;"+ // DIGIT SEVEN
"\u096E>\uE06E;"+ // DIGIT EIGHT
"\u096F>\uE06F;"+ // DIGIT NINE
// \u0970>; // UNMAPPED Devanagari-InterIndic: ABBREVIATION SIGN
""
}
};
}
}

287
icu4j/src/com/ibm/text/resources/TransliterationRule_Fullwidth_Halfwidth.java
View File

@ -1,287 +0,0 @@
/*
*******************************************************************************
* Copyright (C) 1996-2000, International Business Machines Corporation and *
* others. All Rights Reserved. *
*******************************************************************************
*
* $Source: /xsrl/Nsvn/icu/icu4j/src/com/ibm/text/resources/Attic/TransliterationRule_Fullwidth_Halfwidth.java,v $
* $Date: 2000/05/23 16:47:48 $
* $Revision: 1.3 $
*
*****************************************************************************************
*/
package com.ibm.text.resources;
import java.util.ListResourceBundle;
public class TransliterationRule_Fullwidth_Halfwidth extends ListResourceBundle {
/**
* Overrides ListResourceBundle
*/
public Object[][] getContents() {
return new Object[][] {
{ "Rule", ""
// Mechanically generated from Unicode Character Database
// multicharacter
+ "\u30AC<>\uFF76\uFF9E;" // to KATAKANA LETTER GA
+ "\u30AE<>\uFF77\uFF9E;" // to KATAKANA LETTER GI
+ "\u30B0<>\uFF78\uFF9E;" // to KATAKANA LETTER GU
+ "\u30B2<>\uFF79\uFF9E;" // to KATAKANA LETTER GE
+ "\u30B4<>\uFF7A\uFF9E;" // to KATAKANA LETTER GO
+ "\u30B6<>\uFF7B\uFF9E;" // to KATAKANA LETTER ZA
+ "\u30B8<>\uFF7C\uFF9E;" // to KATAKANA LETTER ZI
+ "\u30BA<>\uFF7D\uFF9E;" // to KATAKANA LETTER ZU
+ "\u30BC<>\uFF7E\uFF9E;" // to KATAKANA LETTER ZE
+ "\u30BE<>\uFF7F\uFF9E;" // to KATAKANA LETTER ZO
+ "\u30C0<>\uFF80\uFF9E;" // to KATAKANA LETTER DA
+ "\u30C2<>\uFF81\uFF9E;" // to KATAKANA LETTER DI
+ "\u30C5<>\uFF82\uFF9E;" // to KATAKANA LETTER DU
+ "\u30C7<>\uFF83\uFF9E;" // to KATAKANA LETTER DE
+ "\u30C9<>\uFF84\uFF9E;" // to KATAKANA LETTER DO
+ "\u30D0<>\uFF8A\uFF9E;" // to KATAKANA LETTER BA
+ "\u30D1<>\uFF8A\uFF9F;" // to KATAKANA LETTER PA
+ "\u30D3<>\uFF8B\uFF9E;" // to KATAKANA LETTER BI
+ "\u30D4<>\uFF8B\uFF9F;" // to KATAKANA LETTER PI
+ "\u30D6<>\uFF8C\uFF9E;" // to KATAKANA LETTER BU
+ "\u30D7<>\uFF8C\uFF9F;" // to KATAKANA LETTER PU
+ "\u30D9<>\uFF8D\uFF9E;" // to KATAKANA LETTER BE
+ "\u30DA<>\uFF8D\uFF9F;" // to KATAKANA LETTER PE
+ "\u30DC<>\uFF8E\uFF9E;" // to KATAKANA LETTER BO
+ "\u30DD<>\uFF8E\uFF9F;" // to KATAKANA LETTER PO
+ "\u30F4<>\uFF73\uFF9E;" // to KATAKANA LETTER VU
+ "\u30F7<>\uFF9C\uFF9E;" // to KATAKANA LETTER VA
+ "\u30FA<>\uFF66\uFF9E;" // to KATAKANA LETTER VO
// single character
+ "\uFF01<>'!';" // from FULLWIDTH EXCLAMATION MARK
+ "\uFF02<>'\"';" // from FULLWIDTH QUOTATION MARK
+ "\uFF03<>'#';" // from FULLWIDTH NUMBER SIGN
+ "\uFF04<>'$';" // from FULLWIDTH DOLLAR SIGN
+ "\uFF05<>'%';" // from FULLWIDTH PERCENT SIGN
+ "\uFF06<>'&';" // from FULLWIDTH AMPERSAND
+ "\uFF07<>'';" // from FULLWIDTH APOSTROPHE
+ "\uFF08<>'(';" // from FULLWIDTH LEFT PARENTHESIS
+ "\uFF09<>')';" // from FULLWIDTH RIGHT PARENTHESIS
+ "\uFF0A<>'*';" // from FULLWIDTH ASTERISK
+ "\uFF0B<>'+';" // from FULLWIDTH PLUS SIGN
+ "\uFF0C<>',';" // from FULLWIDTH COMMA
+ "\uFF0D<>'-';" // from FULLWIDTH HYPHEN-MINUS
+ "\uFF0E<>'.';" // from FULLWIDTH FULL STOP
+ "\uFF0F<>'/';" // from FULLWIDTH SOLIDUS
+ "\uFF10<>'0';" // from FULLWIDTH DIGIT ZERO
+ "\uFF11<>'1';" // from FULLWIDTH DIGIT ONE
+ "\uFF12<>'2';" // from FULLWIDTH DIGIT TWO
+ "\uFF13<>'3';" // from FULLWIDTH DIGIT THREE
+ "\uFF14<>'4';" // from FULLWIDTH DIGIT FOUR
+ "\uFF15<>'5';" // from FULLWIDTH DIGIT FIVE
+ "\uFF16<>'6';" // from FULLWIDTH DIGIT SIX
+ "\uFF17<>'7';" // from FULLWIDTH DIGIT SEVEN
+ "\uFF18<>'8';" // from FULLWIDTH DIGIT EIGHT
+ "\uFF19<>'9';" // from FULLWIDTH DIGIT NINE
+ "\uFF1A<>':';" // from FULLWIDTH COLON
+ "\uFF1B<>';';" // from FULLWIDTH SEMICOLON
+ "\uFF1C<>'<';" // from FULLWIDTH LESS-THAN SIGN
+ "\uFF1D<>'=';" // from FULLWIDTH EQUALS SIGN
+ "\uFF1E<>'>';" // from FULLWIDTH GREATER-THAN SIGN
+ "\uFF1F<>'?';" // from FULLWIDTH QUESTION MARK
+ "\uFF20<>'@';" // from FULLWIDTH COMMERCIAL AT
+ "\uFF21<>A;" // from FULLWIDTH LATIN CAPITAL LETTER A
+ "\uFF22<>B;" // from FULLWIDTH LATIN CAPITAL LETTER B
+ "\uFF23<>C;" // from FULLWIDTH LATIN CAPITAL LETTER C
+ "\uFF24<>D;" // from FULLWIDTH LATIN CAPITAL LETTER D
+ "\uFF25<>E;" // from FULLWIDTH LATIN CAPITAL LETTER E
+ "\uFF26<>F;" // from FULLWIDTH LATIN CAPITAL LETTER F
+ "\uFF27<>G;" // from FULLWIDTH LATIN CAPITAL LETTER G
+ "\uFF28<>H;" // from FULLWIDTH LATIN CAPITAL LETTER H
+ "\uFF29<>I;" // from FULLWIDTH LATIN CAPITAL LETTER I
+ "\uFF2A<>J;" // from FULLWIDTH LATIN CAPITAL LETTER J
+ "\uFF2B<>K;" // from FULLWIDTH LATIN CAPITAL LETTER K
+ "\uFF2C<>L;" // from FULLWIDTH LATIN CAPITAL LETTER L
+ "\uFF2D<>M;" // from FULLWIDTH LATIN CAPITAL LETTER M
+ "\uFF2E<>N;" // from FULLWIDTH LATIN CAPITAL LETTER N
+ "\uFF2F<>O;" // from FULLWIDTH LATIN CAPITAL LETTER O
+ "\uFF30<>P;" // from FULLWIDTH LATIN CAPITAL LETTER P
+ "\uFF31<>Q;" // from FULLWIDTH LATIN CAPITAL LETTER Q
+ "\uFF32<>R;" // from FULLWIDTH LATIN CAPITAL LETTER R
+ "\uFF33<>S;" // from FULLWIDTH LATIN CAPITAL LETTER S
+ "\uFF34<>T;" // from FULLWIDTH LATIN CAPITAL LETTER T
+ "\uFF35<>U;" // from FULLWIDTH LATIN CAPITAL LETTER U
+ "\uFF36<>V;" // from FULLWIDTH LATIN CAPITAL LETTER V
+ "\uFF37<>W;" // from FULLWIDTH LATIN CAPITAL LETTER W
+ "\uFF38<>X;" // from FULLWIDTH LATIN CAPITAL LETTER X
+ "\uFF39<>Y;" // from FULLWIDTH LATIN CAPITAL LETTER Y
+ "\uFF3A<>Z;" // from FULLWIDTH LATIN CAPITAL LETTER Z
+ "\uFF3B<>'[';" // from FULLWIDTH LEFT SQUARE BRACKET
+ "\uFF3C<>'\\';" // from FULLWIDTH REVERSE SOLIDUS {double escape - aliu}
+ "\uFF3D<>']';" // from FULLWIDTH RIGHT SQUARE BRACKET
+ "\uFF3E<>'^';" // from FULLWIDTH CIRCUMFLEX ACCENT
+ "\uFF3F<>'_';" // from FULLWIDTH LOW LINE
+ "\uFF40<>'`';" // from FULLWIDTH GRAVE ACCENT
+ "\uFF41<>a;" // from FULLWIDTH LATIN SMALL LETTER A
+ "\uFF42<>b;" // from FULLWIDTH LATIN SMALL LETTER B
+ "\uFF43<>c;" // from FULLWIDTH LATIN SMALL LETTER C
+ "\uFF44<>d;" // from FULLWIDTH LATIN SMALL LETTER D
+ "\uFF45<>e;" // from FULLWIDTH LATIN SMALL LETTER E
+ "\uFF46<>f;" // from FULLWIDTH LATIN SMALL LETTER F
+ "\uFF47<>g;" // from FULLWIDTH LATIN SMALL LETTER G
+ "\uFF48<>h;" // from FULLWIDTH LATIN SMALL LETTER H
+ "\uFF49<>i;" // from FULLWIDTH LATIN SMALL LETTER I
+ "\uFF4A<>j;" // from FULLWIDTH LATIN SMALL LETTER J
+ "\uFF4B<>k;" // from FULLWIDTH LATIN SMALL LETTER K
+ "\uFF4C<>l;" // from FULLWIDTH LATIN SMALL LETTER L
+ "\uFF4D<>m;" // from FULLWIDTH LATIN SMALL LETTER M
+ "\uFF4E<>n;" // from FULLWIDTH LATIN SMALL LETTER N
+ "\uFF4F<>o;" // from FULLWIDTH LATIN SMALL LETTER O
+ "\uFF50<>p;" // from FULLWIDTH LATIN SMALL LETTER P
+ "\uFF51<>q;" // from FULLWIDTH LATIN SMALL LETTER Q
+ "\uFF52<>r;" // from FULLWIDTH LATIN SMALL LETTER R
+ "\uFF53<>s;" // from FULLWIDTH LATIN SMALL LETTER S
+ "\uFF54<>t;" // from FULLWIDTH LATIN SMALL LETTER T
+ "\uFF55<>u;" // from FULLWIDTH LATIN SMALL LETTER U
+ "\uFF56<>v;" // from FULLWIDTH LATIN SMALL LETTER V
+ "\uFF57<>w;" // from FULLWIDTH LATIN SMALL LETTER W
+ "\uFF58<>x;" // from FULLWIDTH LATIN SMALL LETTER X
+ "\uFF59<>y;" // from FULLWIDTH LATIN SMALL LETTER Y
+ "\uFF5A<>z;" // from FULLWIDTH LATIN SMALL LETTER Z
+ "\uFF5B<>'{';" // from FULLWIDTH LEFT CURLY BRACKET
+ "\uFF5C<>'|';" // from FULLWIDTH VERTICAL LINE
+ "\uFF5D<>'}';" // from FULLWIDTH RIGHT CURLY BRACKET
+ "\uFF5E<>'~';" // from FULLWIDTH TILDE
+ "\u3002<>\uFF61;" // to HALFWIDTH IDEOGRAPHIC FULL STOP
+ "\u300C<>\uFF62;" // to HALFWIDTH LEFT CORNER BRACKET
+ "\u300D<>\uFF63;" // to HALFWIDTH RIGHT CORNER BRACKET
+ "\u3001<>\uFF64;" // to HALFWIDTH IDEOGRAPHIC COMMA
+ "\u30FB<>\uFF65;" // to HALFWIDTH KATAKANA MIDDLE DOT
+ "\u30F2<>\uFF66;" // to HALFWIDTH KATAKANA LETTER WO
+ "\u30A1<>\uFF67;" // to HALFWIDTH KATAKANA LETTER SMALL A
+ "\u30A3<>\uFF68;" // to HALFWIDTH KATAKANA LETTER SMALL I
+ "\u30A5<>\uFF69;" // to HALFWIDTH KATAKANA LETTER SMALL U
+ "\u30A7<>\uFF6A;" // to HALFWIDTH KATAKANA LETTER SMALL E
+ "\u30A9<>\uFF6B;" // to HALFWIDTH KATAKANA LETTER SMALL O
+ "\u30E3<>\uFF6C;" // to HALFWIDTH KATAKANA LETTER SMALL YA
+ "\u30E5<>\uFF6D;" // to HALFWIDTH KATAKANA LETTER SMALL YU
+ "\u30E7<>\uFF6E;" // to HALFWIDTH KATAKANA LETTER SMALL YO
+ "\u30C3<>\uFF6F;" // to HALFWIDTH KATAKANA LETTER SMALL TU
+ "\u30FC<>\uFF70;" // to HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK
+ "\u30A2<>\uFF71;" // to HALFWIDTH KATAKANA LETTER A
+ "\u30A4<>\uFF72;" // to HALFWIDTH KATAKANA LETTER I
+ "\u30A6<>\uFF73;" // to HALFWIDTH KATAKANA LETTER U
+ "\u30A8<>\uFF74;" // to HALFWIDTH KATAKANA LETTER E
+ "\u30AA<>\uFF75;" // to HALFWIDTH KATAKANA LETTER O
+ "\u30AB<>\uFF76;" // to HALFWIDTH KATAKANA LETTER KA
+ "\u30AD<>\uFF77;" // to HALFWIDTH KATAKANA LETTER KI
+ "\u30AF<>\uFF78;" // to HALFWIDTH KATAKANA LETTER KU
+ "\u30B1<>\uFF79;" // to HALFWIDTH KATAKANA LETTER KE
+ "\u30B3<>\uFF7A;" // to HALFWIDTH KATAKANA LETTER KO
+ "\u30B5<>\uFF7B;" // to HALFWIDTH KATAKANA LETTER SA
+ "\u30B7<>\uFF7C;" // to HALFWIDTH KATAKANA LETTER SI
+ "\u30B9<>\uFF7D;" // to HALFWIDTH KATAKANA LETTER SU
+ "\u30BB<>\uFF7E;" // to HALFWIDTH KATAKANA LETTER SE
+ "\u30BD<>\uFF7F;" // to HALFWIDTH KATAKANA LETTER SO
+ "\u30BF<>\uFF80;" // to HALFWIDTH KATAKANA LETTER TA
+ "\u30C1<>\uFF81;" // to HALFWIDTH KATAKANA LETTER TI
+ "\u30C4<>\uFF82;" // to HALFWIDTH KATAKANA LETTER TU
+ "\u30C6<>\uFF83;" // to HALFWIDTH KATAKANA LETTER TE
+ "\u30C8<>\uFF84;" // to HALFWIDTH KATAKANA LETTER TO
+ "\u30CA<>\uFF85;" // to HALFWIDTH KATAKANA LETTER NA
+ "\u30CB<>\uFF86;" // to HALFWIDTH KATAKANA LETTER NI
+ "\u30CC<>\uFF87;" // to HALFWIDTH KATAKANA LETTER NU
+ "\u30CD<>\uFF88;" // to HALFWIDTH KATAKANA LETTER NE
+ "\u30CE<>\uFF89;" // to HALFWIDTH KATAKANA LETTER NO
+ "\u30CF<>\uFF8A;" // to HALFWIDTH KATAKANA LETTER HA
+ "\u30D2<>\uFF8B;" // to HALFWIDTH KATAKANA LETTER HI
+ "\u30D5<>\uFF8C;" // to HALFWIDTH KATAKANA LETTER HU
+ "\u30D8<>\uFF8D;" // to HALFWIDTH KATAKANA LETTER HE
+ "\u30DB<>\uFF8E;" // to HALFWIDTH KATAKANA LETTER HO
+ "\u30DE<>\uFF8F;" // to HALFWIDTH KATAKANA LETTER MA
+ "\u30DF<>\uFF90;" // to HALFWIDTH KATAKANA LETTER MI
+ "\u30E0<>\uFF91;" // to HALFWIDTH KATAKANA LETTER MU
+ "\u30E1<>\uFF92;" // to HALFWIDTH KATAKANA LETTER ME
+ "\u30E2<>\uFF93;" // to HALFWIDTH KATAKANA LETTER MO
+ "\u30E4<>\uFF94;" // to HALFWIDTH KATAKANA LETTER YA
+ "\u30E6<>\uFF95;" // to HALFWIDTH KATAKANA LETTER YU
+ "\u30E8<>\uFF96;" // to HALFWIDTH KATAKANA LETTER YO
+ "\u30E9<>\uFF97;" // to HALFWIDTH KATAKANA LETTER RA
+ "\u30EA<>\uFF98;" // to HALFWIDTH KATAKANA LETTER RI
+ "\u30EB<>\uFF99;" // to HALFWIDTH KATAKANA LETTER RU
+ "\u30EC<>\uFF9A;" // to HALFWIDTH KATAKANA LETTER RE
+ "\u30ED<>\uFF9B;" // to HALFWIDTH KATAKANA LETTER RO
+ "\u30EF<>\uFF9C;" // to HALFWIDTH KATAKANA LETTER WA
+ "\u30F3<>\uFF9D;" // to HALFWIDTH KATAKANA LETTER N
+ "\u3099<>\uFF9E;" // to HALFWIDTH KATAKANA VOICED SOUND MARK
+ "\u309A<>\uFF9F;" // to HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK
+ "\u1160<>\uFFA0;" // to HALFWIDTH HANGUL FILLER
+ "\u1100<>\uFFA1;" // to HALFWIDTH HANGUL LETTER KIYEOK
+ "\u1101<>\uFFA2;" // to HALFWIDTH HANGUL LETTER SSANGKIYEOK
+ "\u11AA<>\uFFA3;" // to HALFWIDTH HANGUL LETTER KIYEOK-SIOS
+ "\u1102<>\uFFA4;" // to HALFWIDTH HANGUL LETTER NIEUN
+ "\u11AC<>\uFFA5;" // to HALFWIDTH HANGUL LETTER NIEUN-CIEUC
+ "\u11AD<>\uFFA6;" // to HALFWIDTH HANGUL LETTER NIEUN-HIEUH
+ "\u1103<>\uFFA7;" // to HALFWIDTH HANGUL LETTER TIKEUT
+ "\u1104<>\uFFA8;" // to HALFWIDTH HANGUL LETTER SSANGTIKEUT
+ "\u1105<>\uFFA9;" // to HALFWIDTH HANGUL LETTER RIEUL
+ "\u11B0<>\uFFAA;" // to HALFWIDTH HANGUL LETTER RIEUL-KIYEOK
+ "\u11B1<>\uFFAB;" // to HALFWIDTH HANGUL LETTER RIEUL-MIEUM
+ "\u11B2<>\uFFAC;" // to HALFWIDTH HANGUL LETTER RIEUL-PIEUP
+ "\u11B3<>\uFFAD;" // to HALFWIDTH HANGUL LETTER RIEUL-SIOS
+ "\u11B4<>\uFFAE;" // to HALFWIDTH HANGUL LETTER RIEUL-THIEUTH
+ "\u11B5<>\uFFAF;" // to HALFWIDTH HANGUL LETTER RIEUL-PHIEUPH
+ "\u111A<>\uFFB0;" // to HALFWIDTH HANGUL LETTER RIEUL-HIEUH
+ "\u1106<>\uFFB1;" // to HALFWIDTH HANGUL LETTER MIEUM
+ "\u1107<>\uFFB2;" // to HALFWIDTH HANGUL LETTER PIEUP
+ "\u1108<>\uFFB3;" // to HALFWIDTH HANGUL LETTER SSANGPIEUP
+ "\u1121<>\uFFB4;" // to HALFWIDTH HANGUL LETTER PIEUP-SIOS
+ "\u1109<>\uFFB5;" // to HALFWIDTH HANGUL LETTER SIOS
+ "\u110A<>\uFFB6;" // to HALFWIDTH HANGUL LETTER SSANGSIOS
+ "\u110B<>\uFFB7;" // to HALFWIDTH HANGUL LETTER IEUNG
+ "\u110C<>\uFFB8;" // to HALFWIDTH HANGUL LETTER CIEUC
+ "\u110D<>\uFFB9;" // to HALFWIDTH HANGUL LETTER SSANGCIEUC
+ "\u110E<>\uFFBA;" // to HALFWIDTH HANGUL LETTER CHIEUCH
+ "\u110F<>\uFFBB;" // to HALFWIDTH HANGUL LETTER KHIEUKH
+ "\u1110<>\uFFBC;" // to HALFWIDTH HANGUL LETTER THIEUTH
+ "\u1111<>\uFFBD;" // to HALFWIDTH HANGUL LETTER PHIEUPH
+ "\u1112<>\uFFBE;" // to HALFWIDTH HANGUL LETTER HIEUH
+ "\u1161<>\uFFC2;" // to HALFWIDTH HANGUL LETTER A
+ "\u1162<>\uFFC3;" // to HALFWIDTH HANGUL LETTER AE
+ "\u1163<>\uFFC4;" // to HALFWIDTH HANGUL LETTER YA
+ "\u1164<>\uFFC5;" // to HALFWIDTH HANGUL LETTER YAE
+ "\u1165<>\uFFC6;" // to HALFWIDTH HANGUL LETTER EO
+ "\u1166<>\uFFC7;" // to HALFWIDTH HANGUL LETTER E
+ "\u1167<>\uFFCA;" // to HALFWIDTH HANGUL LETTER YEO
+ "\u1168<>\uFFCB;" // to HALFWIDTH HANGUL LETTER YE
+ "\u1169<>\uFFCC;" // to HALFWIDTH HANGUL LETTER O
+ "\u116A<>\uFFCD;" // to HALFWIDTH HANGUL LETTER WA
+ "\u116B<>\uFFCE;" // to HALFWIDTH HANGUL LETTER WAE
+ "\u116C<>\uFFCF;" // to HALFWIDTH HANGUL LETTER OE
+ "\u116D<>\uFFD2;" // to HALFWIDTH HANGUL LETTER YO
+ "\u116E<>\uFFD3;" // to HALFWIDTH HANGUL LETTER U
+ "\u116F<>\uFFD4;" // to HALFWIDTH HANGUL LETTER WEO
+ "\u1170<>\uFFD5;" // to HALFWIDTH HANGUL LETTER WE
+ "\u1171<>\uFFD6;" // to HALFWIDTH HANGUL LETTER WI
+ "\u1172<>\uFFD7;" // to HALFWIDTH HANGUL LETTER YU
+ "\u1173<>\uFFDA;" // to HALFWIDTH HANGUL LETTER EU
+ "\u1174<>\uFFDB;" // to HALFWIDTH HANGUL LETTER YI
+ "\u1175<>\uFFDC;" // to HALFWIDTH HANGUL LETTER I
+ "\uFFE0<>'\u00a2';" // from FULLWIDTH CENT SIGN
+ "\uFFE1<>'\u00a3';" // from FULLWIDTH POUND SIGN
+ "\uFFE2<>'\u00ac';" // from FULLWIDTH NOT SIGN
+ "\uFFE3<>' '\u0304;" // from FULLWIDTH MACRON
+ "\uFFE4<>'\u00a6';" // from FULLWIDTH BROKEN BAR
+ "\uFFE5<>'\u00a5';" // from FULLWIDTH YEN SIGN
+ "\uFFE6<>\u20A9;" // from FULLWIDTH WON SIGN
+ "\u2502<>\uFFE8;" // to HALFWIDTH FORMS LIGHT VERTICAL
+ "\u2190<>\uFFE9;" // to HALFWIDTH LEFTWARDS ARROW
+ "\u2191<>\uFFEA;" // to HALFWIDTH UPWARDS ARROW
+ "\u2192<>\uFFEB;" // to HALFWIDTH RIGHTWARDS ARROW
+ "\u2193<>\uFFEC;" // to HALFWIDTH DOWNWARDS ARROW
+ "\u25A0<>\uFFED;" // to HALFWIDTH BLACK SQUARE
+ "\u25CB<>\uFFEE;" // to HALFWIDTH WHITE CIRCLE
}
};
}
}

104
icu4j/src/com/ibm/text/resources/TransliterationRule_Gujarati_InterIndic.java
View File

@ -1,104 +0,0 @@
/***********************************************************************
* Copyright (c) 2000, International Business Machines Corporation
* and others. All Rights Reserved.
************************************************************************
* > THIS FILE WAS MACHINE GENERATED <
* > DO NOT EDIT BY HAND <
* > RUN TOOL TO REGENERATE <
* Tool: icu4j/src/com/ibm/tools/translit/indic.pl
* Creation date: Fri Oct 6 15:55:21 2000
*/
package com.ibm.text.resources;
import java.util.ListResourceBundle;
public class TransliterationRule_Gujarati_InterIndic extends ListResourceBundle {
/**
* Overrides ListResourceBundle
*/
public Object[][] getContents() {
return new Object[][] {
{ "Rule",
"\u0A81>\uE001;"+ // SIGN CANDRABINDU
"\u0A82>\uE002;"+ // SIGN ANUSVARA
"\u0A83>\uE003;"+ // SIGN VISARGA
"\u0A85>\uE005;"+ // LETTER A
"\u0A86>\uE006;"+ // LETTER AA
"\u0A87>\uE007;"+ // LETTER I
"\u0A88>\uE008;"+ // LETTER II
"\u0A89>\uE009;"+ // LETTER U
"\u0A8A>\uE00A;"+ // LETTER UU
"\u0A8B>\uE00B;"+ // LETTER VOCALIC R
// \u0A8D>; // UNMAPPED Gujarati-InterIndic: VOWEL CANDRA E
"\u0A8F>\uE081;"+ // LETTER E
"\u0A90>\uE010;"+ // LETTER AI
// \u0A91>; // UNMAPPED Gujarati-InterIndic: VOWEL CANDRA O
"\u0A93>\uE082;"+ // LETTER O
"\u0A94>\uE014;"+ // LETTER AU
"\u0A95>\uE015;"+ // LETTER KA
"\u0A96>\uE016;"+ // LETTER KHA
"\u0A97>\uE017;"+ // LETTER GA
"\u0A98>\uE018;"+ // LETTER GHA
"\u0A99>\uE019;"+ // LETTER NGA
"\u0A9A>\uE01A;"+ // LETTER CA
"\u0A9B>\uE01B;"+ // LETTER CHA
"\u0A9C>\uE01C;"+ // LETTER JA
"\u0A9D>\uE01D;"+ // LETTER JHA
"\u0A9E>\uE01E;"+ // LETTER NYA
"\u0A9F>\uE01F;"+ // LETTER TTA
"\u0AA0>\uE020;"+ // LETTER TTHA
"\u0AA1>\uE021;"+ // LETTER DDA
"\u0AA2>\uE022;"+ // LETTER DDHA
"\u0AA3>\uE023;"+ // LETTER NNA
"\u0AA4>\uE024;"+ // LETTER TA
"\u0AA5>\uE025;"+ // LETTER THA
"\u0AA6>\uE026;"+ // LETTER DA
"\u0AA7>\uE027;"+ // LETTER DHA
"\u0AA8>\uE028;"+ // LETTER NA
"\u0AAA>\uE02A;"+ // LETTER PA
"\u0AAB>\uE02B;"+ // LETTER PHA
"\u0AAC>\uE02C;"+ // LETTER BA
"\u0AAD>\uE02D;"+ // LETTER BHA
"\u0AAE>\uE02E;"+ // LETTER MA
"\u0AAF>\uE02F;"+ // LETTER YA
"\u0AB0>\uE030;"+ // LETTER RA
"\u0AB2>\uE032;"+ // LETTER LA
"\u0AB3>\uE033;"+ // LETTER LLA
"\u0AB5>\uE035;"+ // LETTER VA
"\u0AB6>\uE036;"+ // LETTER SHA
"\u0AB7>\uE037;"+ // LETTER SSA
"\u0AB8>\uE038;"+ // LETTER SA
"\u0AB9>\uE039;"+ // LETTER HA
"\u0ABC>\uE03C;"+ // SIGN NUKTA
"\u0ABD>\uE03D;"+ // SIGN AVAGRAHA
"\u0ABE>\uE03E;"+ // VOWEL SIGN AA
"\u0ABF>\uE03F;"+ // VOWEL SIGN I
"\u0AC0>\uE040;"+ // VOWEL SIGN II
"\u0AC1>\uE041;"+ // VOWEL SIGN U
"\u0AC2>\uE042;"+ // VOWEL SIGN UU
"\u0AC3>\uE043;"+ // VOWEL SIGN VOCALIC R
"\u0AC4>\uE044;"+ // VOWEL SIGN VOCALIC RR
"\u0AC5>\uE045;"+ // VOWEL SIGN CANDRA E
"\u0AC7>\uE084;"+ // VOWEL SIGN E
"\u0AC8>\uE048;"+ // VOWEL SIGN AI
"\u0AC9>\uE049;"+ // VOWEL SIGN CANDRA O
"\u0ACB>\uE085;"+ // VOWEL SIGN O
"\u0ACC>\uE04C;"+ // VOWEL SIGN AU
"\u0ACD>\uE04D;"+ // SIGN VIRAMA
"\u0AD0>\uE050;"+ // OM
"\u0AE0>\uE060;"+ // LETTER VOCALIC RR
"\u0AE6>\uE066;"+ // DIGIT ZERO
"\u0AE7>\uE067;"+ // DIGIT ONE
"\u0AE8>\uE068;"+ // DIGIT TWO
"\u0AE9>\uE069;"+ // DIGIT THREE
"\u0AEA>\uE06A;"+ // DIGIT FOUR
"\u0AEB>\uE06B;"+ // DIGIT FIVE
"\u0AEC>\uE06C;"+ // DIGIT SIX
"\u0AED>\uE06D;"+ // DIGIT SEVEN
"\u0AEE>\uE06E;"+ // DIGIT EIGHT
"\u0AEF>\uE06F;"+ // DIGIT NINE
""
}
};
}
}

101
icu4j/src/com/ibm/text/resources/TransliterationRule_Gurmukhi_InterIndic.java
View File

@ -1,101 +0,0 @@
/***********************************************************************
* Copyright (c) 2000, International Business Machines Corporation
* and others. All Rights Reserved.
************************************************************************
* > THIS FILE WAS MACHINE GENERATED <
* > DO NOT EDIT BY HAND <
* > RUN TOOL TO REGENERATE <
* Tool: icu4j/src/com/ibm/tools/translit/indic.pl
* Creation date: Fri Oct 6 15:55:21 2000
*/
package com.ibm.text.resources;
import java.util.ListResourceBundle;
public class TransliterationRule_Gurmukhi_InterIndic extends ListResourceBundle {
/**
* Overrides ListResourceBundle
*/
public Object[][] getContents() {
return new Object[][] {
{ "Rule",
"\u0A02>\uE001;"+ // REMAP (indicExceptions.txt): \u0A01>\u0A02 = SIGN CANDRABINDU>SIGN BINDI
"\u0A05>\uE005;"+ // LETTER A
"\u0A06>\uE006;"+ // LETTER AA
"\u0A07>\uE007;"+ // LETTER I
"\u0A08>\uE008;"+ // LETTER II
"\u0A09>\uE009;"+ // LETTER U
"\u0A0A>\uE00A;"+ // LETTER UU
"\u0A0F>\uE00F;"+ // LETTER EE
"\u0A10>\uE010;"+ // LETTER AI
"\u0A13>\uE013;"+ // LETTER OO
"\u0A14>\uE014;"+ // LETTER AU
"\u0A15>\uE015;"+ // LETTER KA
"\u0A16>\uE016;"+ // LETTER KHA
"\u0A17>\uE017;"+ // LETTER GA
"\u0A18>\uE018;"+ // LETTER GHA
"\u0A19>\uE019;"+ // LETTER NGA
"\u0A1A>\uE01A;"+ // LETTER CA
"\u0A1B>\uE01B;"+ // LETTER CHA
"\u0A1C>\uE01C;"+ // LETTER JA
"\u0A1D>\uE01D;"+ // LETTER JHA
"\u0A1E>\uE01E;"+ // LETTER NYA
"\u0A1F>\uE01F;"+ // LETTER TTA
"\u0A20>\uE020;"+ // LETTER TTHA
"\u0A21>\uE021;"+ // LETTER DDA
"\u0A22>\uE022;"+ // LETTER DDHA
"\u0A23>\uE023;"+ // LETTER NNA
"\u0A24>\uE024;"+ // LETTER TA
"\u0A25>\uE025;"+ // LETTER THA
"\u0A26>\uE026;"+ // LETTER DA
"\u0A27>\uE027;"+ // LETTER DHA
"\u0A28>\uE028;"+ // LETTER NA
"\u0A2A>\uE02A;"+ // LETTER PA
"\u0A2B>\uE02B;"+ // LETTER PHA
"\u0A2C>\uE02C;"+ // LETTER BA
"\u0A2D>\uE02D;"+ // LETTER BHA
"\u0A2E>\uE02E;"+ // LETTER MA
"\u0A2F>\uE02F;"+ // LETTER YA
"\u0A30>\uE030;"+ // LETTER RA
"\u0A32>\uE032;"+ // LETTER LA
"\u0A33>\uE033;"+ // LETTER LLA
"\u0A35>\uE035;"+ // LETTER VA
"\u0A36>\uE036;"+ // LETTER SHA
"\u0A38>\uE038;"+ // LETTER SA
"\u0A39>\uE039;"+ // LETTER HA
"\u0A3C>\uE03C;"+ // SIGN NUKTA
"\u0A3E>\uE03E;"+ // VOWEL SIGN AA
"\u0A3F>\uE03F;"+ // VOWEL SIGN I
"\u0A40>\uE040;"+ // VOWEL SIGN II
"\u0A41>\uE041;"+ // VOWEL SIGN U
"\u0A42>\uE042;"+ // VOWEL SIGN UU
"\u0A47>\uE047;"+ // VOWEL SIGN EE
"\u0A48>\uE048;"+ // VOWEL SIGN AI
"\u0A4B>\uE04B;"+ // VOWEL SIGN OO
"\u0A4C>\uE04C;"+ // VOWEL SIGN AU
"\u0A4D>\uE04D;"+ // SIGN VIRAMA
"\u0A59>\uE059;"+ // LETTER KHHA
"\u0A5A>\uE05A;"+ // LETTER GHHA
"\u0A5B>\uE05B;"+ // LETTER ZA
"\u0A5C>\uE083;"+ // LETTER RRA
"\u0A5E>\uE05E;"+ // LETTER FA
"\u0A66>\uE066;"+ // DIGIT ZERO
"\u0A67>\uE067;"+ // DIGIT ONE
"\u0A68>\uE068;"+ // DIGIT TWO
"\u0A69>\uE069;"+ // DIGIT THREE
"\u0A6A>\uE06A;"+ // DIGIT FOUR
"\u0A6B>\uE06B;"+ // DIGIT FIVE
"\u0A6C>\uE06C;"+ // DIGIT SIX
"\u0A6D>\uE06D;"+ // DIGIT SEVEN
"\u0A6E>\uE06E;"+ // DIGIT EIGHT
"\u0A6F>\uE06F;"+ // DIGIT NINE
// \u0A70>; // UNMAPPED Gurmukhi-InterIndic: TIPPI
// \u0A71>; // UNMAPPED Gurmukhi-InterIndic: ADDAK
// \u0A72>; // UNMAPPED Gurmukhi-InterIndic: IRI
// \u0A73>; // UNMAPPED Gurmukhi-InterIndic: URA
// \u0A74>; // UNMAPPED Gurmukhi-InterIndic: EK ONKAR
""
}
};
}
}

20427
icu4j/src/com/ibm/text/resources/TransliterationRule_Han_Pinyin.java
View File

File diff suppressed because it is too large Load Diff

221
icu4j/src/com/ibm/text/resources/TransliterationRule_Hiragana_Katakana.java
View File

@ -1,221 +0,0 @@
/*******************************************************************************
* Copyright (C) 1997-2000, International Business Machines
* Corporation and others. All Rights Reserved.
*******************************************************************************
* $Source: /xsrl/Nsvn/icu/icu4j/src/com/ibm/text/resources/Attic/TransliterationRule_Hiragana_Katakana.java,v $
* $Date: 2000/06/30 00:00:09 $
* $Revision: 1.1 $
*******************************************************************************
* Date Name Description
* 06/29/00 aliu Creation.
*******************************************************************************
*/
package com.ibm.text.resources;
import java.util.ListResourceBundle;
public class TransliterationRule_Hiragana_Katakana extends ListResourceBundle {
/**
* Overrides ListResourceBundle
*/
public Object[][] getContents() {
return new Object[][] {
{ "Rule", "" +
// Hiragana-Katana
// This is largely a one-to-one mapping, but it has a
// few kinks:
// 1. The Katakana va/vi/ve/vo (30F7-30FA) have no
// Hiragana equivalents. We use Hiragana wa/wi/we/wo
// (308F-3092) with a voicing mark (3099), which is
// semantically equivalent. However, this is a non-
// roundtripping transformation.
// 2. The Katakana small ka/ke (30F5,30F6) have no
// Hiragana equiavlents. We convert them to normal
// Hiragana ka/ke (304B,3051). This is a one-way
// information-losing transformation and precludes
// round-tripping of 30F5 and 30F6.
// 3. The combining marks 3099-309C are in the Hiragana
// block, but they apply to Katakana as well, so we
// leave the untouched.
// 4. The Katakana prolonged sound mark 30FC doubles the
// preceding vowel. This is a one-way information-
// losing transformation from Katakana to Hiragana.
// 5. The Katakana middle dot separates words in foreign
// expressions; we leave this unmodified.
// The above points preclude successful round-trip
// transformations of arbitrary input text. However,
// they provide naturalistic results that should conform
// to natural language expectations.
// Combining equivalents
"\u308F\u3099 <> \u30F7;" +
"\u3090\u3099 <> \u30F8;" +
"\u3091\u3099 <> \u30F9;" +
"\u3092\u3099 <> \u30FA;" +
// One-to-one mappings, main block
// 3041:3094 <> 30A1:30F4
// 309D,E <> 30FD,E
"\u3041 <> \u30A1;" +
"\u3042 <> \u30A2;" +
"\u3043 <> \u30A3;" +
"\u3044 <> \u30A4;" +
"\u3045 <> \u30A5;" +
"\u3046 <> \u30A6;" +
"\u3047 <> \u30A7;" +
"\u3048 <> \u30A8;" +
"\u3049 <> \u30A9;" +
"\u304A <> \u30AA;" +
"\u304B <> \u30AB;" +
"\u304C <> \u30AC;" +
"\u304D <> \u30AD;" +
"\u304E <> \u30AE;" +
"\u304F <> \u30AF;" +
"\u3050 <> \u30B0;" +
"\u3051 <> \u30B1;" +
"\u3052 <> \u30B2;" +
"\u3053 <> \u30B3;" +
"\u3054 <> \u30B4;" +
"\u3055 <> \u30B5;" +
"\u3056 <> \u30B6;" +
"\u3057 <> \u30B7;" +
"\u3058 <> \u30B8;" +
"\u3059 <> \u30B9;" +
"\u305A <> \u30BA;" +
"\u305B <> \u30BB;" +
"\u305C <> \u30BC;" +
"\u305D <> \u30BD;" +
"\u305E <> \u30BE;" +
"\u305F <> \u30BF;" +
"\u3060 <> \u30C0;" +
"\u3061 <> \u30C1;" +
"\u3062 <> \u30C2;" +
"\u3063 <> \u30C3;" +
"\u3064 <> \u30C4;" +
"\u3065 <> \u30C5;" +
"\u3066 <> \u30C6;" +
"\u3067 <> \u30C7;" +
"\u3068 <> \u30C8;" +
"\u3069 <> \u30C9;" +
"\u306A <> \u30CA;" +
"\u306B <> \u30CB;" +
"\u306C <> \u30CC;" +
"\u306D <> \u30CD;" +
"\u306E <> \u30CE;" +
"\u306F <> \u30CF;" +
"\u3070 <> \u30D0;" +
"\u3071 <> \u30D1;" +
"\u3072 <> \u30D2;" +
"\u3073 <> \u30D3;" +
"\u3074 <> \u30D4;" +
"\u3075 <> \u30D5;" +
"\u3076 <> \u30D6;" +
"\u3077 <> \u30D7;" +
"\u3078 <> \u30D8;" +
"\u3079 <> \u30D9;" +
"\u307A <> \u30DA;" +
"\u307B <> \u30DB;" +
"\u307C <> \u30DC;" +
"\u307D <> \u30DD;" +
"\u307E <> \u30DE;" +
"\u307F <> \u30DF;" +
"\u3080 <> \u30E0;" +
"\u3081 <> \u30E1;" +
"\u3082 <> \u30E2;" +
"\u3083 <> \u30E3;" +
"\u3084 <> \u30E4;" +
"\u3085 <> \u30E5;" +
"\u3086 <> \u30E6;" +
"\u3087 <> \u30E7;" +
"\u3088 <> \u30E8;" +
"\u3089 <> \u30E9;" +
"\u308A <> \u30EA;" +
"\u308B <> \u30EB;" +
"\u308C <> \u30EC;" +
"\u308D <> \u30ED;" +
"\u308E <> \u30EE;" +
"\u308F <> \u30EF;" +
"\u3090 <> \u30F0;" +
"\u3091 <> \u30F1;" +
"\u3092 <> \u30F2;" +
"\u3093 <> \u30F3;" +
"\u3094 <> \u30F4;" +
"\u309D <> \u30FD;" +
"\u309E <> \u30FE;" +
// Fallback; this is a one-way Katakana-Hiragana xform.
"\u304B < \u30F5;" +
"\u3051 < \u30F6;" +
// Anything followed by a prolonged sound mark 30FC has
// its final vowel doubled. This is a Katakana-Hiragana
// one-way information-losing transformation. We
// include the small Katakana (e.g., small A 3041) and
// do not distinguish them from their large
// counterparts. It doesn't make sense to double a
// small counterpart vowel as a small Hiragana vowel, so
// we don't do so. In natural text this should never
// occur anyway. If a 30FC is seen without a preceding
// vowel sound (e.g., after n 30F3) we do not change it.
"$long = \u30FC;" +
// The following categories are Hiragana, not Katakana
// as might be expected, since by the time we get to the
// 30FC, the preceding character will have already been
// transformed to Hiragana.
// {The following mechanically generated from the
// Unicode 3.0 data:}
"$xa = [" +
"\u3041 \u3042 \u304B \u304C \u3055 \u3056" +
"\u305F \u3060 \u306A \u306F \u3070 \u3071" +
"\u307E \u3083 \u3084 \u3089 \u308E \u308F" +
"];" +
"$xi = [" +
"\u3043 \u3044 \u304D \u304E \u3057 \u3058" +
"\u3061 \u3062 \u306B \u3072 \u3073 \u3074" +
"\u307F \u308A \u3090" +
"];" +
"$xu = [" +
"\u3045 \u3046 \u304F \u3050 \u3059 \u305A" +
"\u3063 \u3064 \u3065 \u306C \u3075 \u3076" +
"\u3077 \u3080 \u3085 \u3086 \u308B \u3094" +
"];" +
"$xe = [" +
"\u3047 \u3048 \u3051 \u3052 \u305B \u305C" +
"\u3066 \u3067 \u306D \u3078 \u3079 \u307A" +
"\u3081 \u308C \u3091" +
"];" +
"$xo = [" +
"\u3049 \u304A \u3053 \u3054 \u305D \u305E" +
"\u3068 \u3069 \u306E \u307B \u307C \u307D" +
"\u3082 \u3087 \u3088 \u308D \u3092" +
"];" +
"\u3042 < $xa {$long};" +
"\u3044 < $xi {$long};" +
"\u3046 < $xu {$long};" +
"\u3048 < $xe {$long};" +
"\u304A < $xo {$long};" +
""
}
};
}
}

123
icu4j/src/com/ibm/text/resources/TransliterationRule_InterIndic_Bengali.java
View File

@ -1,123 +0,0 @@
/***********************************************************************
* Copyright (c) 2000, International Business Machines Corporation
* and others. All Rights Reserved.
************************************************************************
* > THIS FILE WAS MACHINE GENERATED <
* > DO NOT EDIT BY HAND <
* > RUN TOOL TO REGENERATE <
* Tool: icu4j/src/com/ibm/tools/translit/indic.pl
* Creation date: Fri Oct 6 15:55:21 2000
*/
package com.ibm.text.resources;
import java.util.ListResourceBundle;
public class TransliterationRule_InterIndic_Bengali extends ListResourceBundle {
/**
* Overrides ListResourceBundle
*/
public Object[][] getContents() {
return new Object[][] {
{ "Rule",
"\uE001>\u0981;"+ // SIGN CANDRABINDU
"\uE002>\u0982;"+ // SIGN ANUSVARA
"\uE003>\u0983;"+ // SIGN VISARGA
"\uE005>\u0985;"+ // LETTER A
"\uE006>\u0986;"+ // LETTER AA
"\uE007>\u0987;"+ // LETTER I
"\uE008>\u0988;"+ // LETTER II
"\uE009>\u0989;"+ // LETTER U
"\uE00A>\u098A;"+ // LETTER UU
"\uE00B>\u098B;"+ // LETTER VOCALIC R
"\uE00C>\u098C;"+ // LETTER VOCALIC L
// \uE00F>; // UNMAPPED InterIndic-Bengali: LETTER EE (\u098F = LETTER E)
"\uE010>\u0990;"+ // LETTER AI
// \uE013>; // UNMAPPED InterIndic-Bengali: LETTER OO (\u0993 = LETTER O)
"\uE014>\u0994;"+ // LETTER AU
"\uE015>\u0995;"+ // LETTER KA
"\uE016>\u0996;"+ // LETTER KHA
"\uE017>\u0997;"+ // LETTER GA
"\uE018>\u0998;"+ // LETTER GHA
"\uE019>\u0999;"+ // LETTER NGA
"\uE01A>\u099A;"+ // LETTER CA
"\uE01B>\u099B;"+ // LETTER CHA
"\uE01C>\u099C;"+ // LETTER JA
"\uE01D>\u099D;"+ // LETTER JHA
"\uE01E>\u099E;"+ // LETTER NYA
"\uE01F>\u099F;"+ // LETTER TTA
"\uE020>\u09A0;"+ // LETTER TTHA
"\uE021>\u09A1;"+ // LETTER DDA
"\uE022>\u09A2;"+ // LETTER DDHA
"\uE023>\u09A3;"+ // LETTER NNA
"\uE024>\u09A4;"+ // LETTER TA
"\uE025>\u09A5;"+ // LETTER THA
"\uE026>\u09A6;"+ // LETTER DA
"\uE027>\u09A7;"+ // LETTER DHA
"\uE028>\u09A8;"+ // LETTER NA
"\uE029>\u09A8;"+ // REMAP (indicExceptions.txt): \u09A9>\u09A8 = LETTER NNNA>LETTER NA
"\uE02A>\u09AA;"+ // LETTER PA
"\uE02B>\u09AB;"+ // LETTER PHA
"\uE02C>\u09AC;"+ // LETTER BA
"\uE02D>\u09AD;"+ // LETTER BHA
"\uE02E>\u09AE;"+ // LETTER MA
"\uE02F>\u09AF;"+ // LETTER YA
"\uE030>\u09B0;"+ // LETTER RA
"\uE032>\u09B2;"+ // LETTER LA
"\uE033>\u09B2;"+ // REMAP (indicExceptions.txt): \u09B3>\u09B2 = LETTER LLA>LETTER LA
"\uE034>\u09B2;"+ // REMAP (indicExceptions.txt): \u09B4>\u09B2 = LETTER LLLA>LETTER LA
"\uE035>\u09AC;"+ // REMAP (indicExceptions.txt): \u09B5>\u09AC = LETTER VA>LETTER BA
"\uE036>\u09B6;"+ // LETTER SHA
"\uE037>\u09B7;"+ // LETTER SSA
"\uE038>\u09B8;"+ // LETTER SA
"\uE039>\u09B9;"+ // LETTER HA
"\uE03C>\u09BC;"+ // SIGN NUKTA
// \uE03D>; // UNMAPPED InterIndic-Bengali: SIGN AVAGRAHA
"\uE03E>\u09BE;"+ // VOWEL SIGN AA
"\uE03F>\u09BF;"+ // VOWEL SIGN I
"\uE040>\u09C0;"+ // VOWEL SIGN II
"\uE041>\u09C1;"+ // VOWEL SIGN U
"\uE042>\u09C2;"+ // VOWEL SIGN UU
"\uE043>\u09C3;"+ // VOWEL SIGN VOCALIC R
"\uE044>\u09C4;"+ // VOWEL SIGN VOCALIC RR
"\uE045>\u09C7;"+ // REMAP (indicExceptions.txt): \u09C5>\u09C7 = VOWEL SIGN CANDRA E>VOWEL SIGN E
// \uE047>; // UNMAPPED InterIndic-Bengali: VOWEL SIGN EE (\u09C7 = VOWEL SIGN E)
"\uE048>\u09C8;"+ // VOWEL SIGN AI
"\uE049>\u09CB;"+ // REMAP (indicExceptions.txt): \u09C9>\u09CB = VOWEL SIGN CANDRA O>VOWEL SIGN O
// \uE04B>; // UNMAPPED InterIndic-Bengali: VOWEL SIGN OO (\u09CB = VOWEL SIGN O)
"\uE04C>\u09CC;"+ // VOWEL SIGN AU
"\uE04D>\u09CD;"+ // SIGN VIRAMA
// \uE050>; // UNMAPPED InterIndic-Bengali: OM
// \uE055>; // UNMAPPED InterIndic-Bengali: LENGTH MARK
"\uE056>\u09C8;"+ // REMAP (indicExceptions.txt): \u09D6>\u09C8 = AI LENGTH MARK>VOWEL SIGN AI
"\uE057>\u09D7;"+ // AU LENGTH MARK
"\uE059>\u0996;"+ // REMAP (indicExceptions.txt): \u09D9>\u0996 = LETTER KHHA>LETTER KHA
"\uE05A>\u0997;"+ // REMAP (indicExceptions.txt): \u09DA>\u0997 = LETTER GHHA>LETTER GA
"\uE05B>\u099C;"+ // REMAP (indicExceptions.txt): \u09DB>\u099C = LETTER ZA>LETTER JA
"\uE05D>\u09DD;"+ // LETTER RHA
"\uE05E>\u09AB;"+ // REMAP (indicExceptions.txt): \u09DE>\u09AB = LETTER FA>LETTER PHA
"\uE05F>\u09DF;"+ // LETTER YYA
"\uE060>\u09E0;"+ // LETTER VOCALIC RR
"\uE061>\u09E1;"+ // LETTER VOCALIC LL
"\uE062>\u09E2;"+ // VOWEL SIGN VOCALIC L
"\uE063>\u09E3;"+ // VOWEL SIGN VOCALIC LL
"\uE066>\u09E6;"+ // DIGIT ZERO
"\uE067>\u09E7;"+ // DIGIT ONE
"\uE068>\u09E8;"+ // DIGIT TWO
"\uE069>\u09E9;"+ // DIGIT THREE
"\uE06A>\u09EA;"+ // DIGIT FOUR
"\uE06B>\u09EB;"+ // DIGIT FIVE
"\uE06C>\u09EC;"+ // DIGIT SIX
"\uE06D>\u09ED;"+ // DIGIT SEVEN
"\uE06E>\u09EE;"+ // DIGIT EIGHT
"\uE06F>\u09EF;"+ // DIGIT NINE
"\uE080>\u09FA;"+ // ISSHAR
"\uE081>\u098F;"+ // LETTER E
"\uE082>\u0993;"+ // LETTER O
"\uE083>\u09DC;"+ // LETTER RRA
"\uE084>\u09C7;"+ // VOWEL SIGN E
"\uE085>\u09CB;"+ // VOWEL SIGN O
""
}
};
}
}

123
icu4j/src/com/ibm/text/resources/TransliterationRule_InterIndic_Devanagari.java
View File

@ -1,123 +0,0 @@
/***********************************************************************
* Copyright (c) 2000, International Business Machines Corporation
* and others. All Rights Reserved.
************************************************************************
* > THIS FILE WAS MACHINE GENERATED <
* > DO NOT EDIT BY HAND <
* > RUN TOOL TO REGENERATE <
* Tool: icu4j/src/com/ibm/tools/translit/indic.pl
* Creation date: Fri Oct 6 15:55:21 2000
*/
package com.ibm.text.resources;
import java.util.ListResourceBundle;
public class TransliterationRule_InterIndic_Devanagari extends ListResourceBundle {
/**
* Overrides ListResourceBundle
*/
public Object[][] getContents() {
return new Object[][] {
{ "Rule",
"\uE001>\u0901;"+ // SIGN CANDRABINDU
"\uE002>\u0902;"+ // SIGN ANUSVARA
"\uE003>\u0903;"+ // SIGN VISARGA
"\uE005>\u0905;"+ // LETTER A
"\uE006>\u0906;"+ // LETTER AA
"\uE007>\u0907;"+ // LETTER I
"\uE008>\u0908;"+ // LETTER II
"\uE009>\u0909;"+ // LETTER U
"\uE00A>\u090A;"+ // LETTER UU
"\uE00B>\u090B;"+ // LETTER VOCALIC R
"\uE00C>\u090C;"+ // LETTER VOCALIC L
// \uE00F>; // UNMAPPED InterIndic-Devanagari: LETTER EE (\u090F = LETTER E)
"\uE010>\u0910;"+ // LETTER AI
// \uE013>; // UNMAPPED InterIndic-Devanagari: LETTER OO (\u0913 = LETTER O)
"\uE014>\u0914;"+ // LETTER AU
"\uE015>\u0915;"+ // LETTER KA
"\uE016>\u0916;"+ // LETTER KHA
"\uE017>\u0917;"+ // LETTER GA
"\uE018>\u0918;"+ // LETTER GHA
"\uE019>\u0919;"+ // LETTER NGA
"\uE01A>\u091A;"+ // LETTER CA
"\uE01B>\u091B;"+ // LETTER CHA
"\uE01C>\u091C;"+ // LETTER JA
"\uE01D>\u091D;"+ // LETTER JHA
"\uE01E>\u091E;"+ // LETTER NYA
"\uE01F>\u091F;"+ // LETTER TTA
"\uE020>\u0920;"+ // LETTER TTHA
"\uE021>\u0921;"+ // LETTER DDA
"\uE022>\u0922;"+ // LETTER DDHA
"\uE023>\u0923;"+ // LETTER NNA
"\uE024>\u0924;"+ // LETTER TA
"\uE025>\u0925;"+ // LETTER THA
"\uE026>\u0926;"+ // LETTER DA
"\uE027>\u0927;"+ // LETTER DHA
"\uE028>\u0928;"+ // LETTER NA
"\uE029>\u0929;"+ // LETTER NNNA
"\uE02A>\u092A;"+ // LETTER PA
"\uE02B>\u092B;"+ // LETTER PHA
"\uE02C>\u092C;"+ // LETTER BA
"\uE02D>\u092D;"+ // LETTER BHA
"\uE02E>\u092E;"+ // LETTER MA
"\uE02F>\u092F;"+ // LETTER YA
"\uE030>\u0930;"+ // LETTER RA
"\uE032>\u0932;"+ // LETTER LA
"\uE033>\u0933;"+ // LETTER LLA
"\uE034>\u0934;"+ // LETTER LLLA
"\uE035>\u0935;"+ // LETTER VA
"\uE036>\u0936;"+ // LETTER SHA
"\uE037>\u0937;"+ // LETTER SSA
"\uE038>\u0938;"+ // LETTER SA
"\uE039>\u0939;"+ // LETTER HA
"\uE03C>\u093C;"+ // SIGN NUKTA
"\uE03D>\u093D;"+ // SIGN AVAGRAHA
"\uE03E>\u093E;"+ // VOWEL SIGN AA
"\uE03F>\u093F;"+ // VOWEL SIGN I
"\uE040>\u0940;"+ // VOWEL SIGN II
"\uE041>\u0941;"+ // VOWEL SIGN U
"\uE042>\u0942;"+ // VOWEL SIGN UU
"\uE043>\u0943;"+ // VOWEL SIGN VOCALIC R
"\uE044>\u0944;"+ // VOWEL SIGN VOCALIC RR
"\uE045>\u0945;"+ // VOWEL SIGN CANDRA E
// \uE047>; // UNMAPPED InterIndic-Devanagari: VOWEL SIGN EE (\u0947 = VOWEL SIGN E)
"\uE048>\u0948;"+ // VOWEL SIGN AI
"\uE049>\u0949;"+ // VOWEL SIGN CANDRA O
// \uE04B>; // UNMAPPED InterIndic-Devanagari: VOWEL SIGN OO (\u094B = VOWEL SIGN O)
"\uE04C>\u094C;"+ // VOWEL SIGN AU
"\uE04D>\u094D;"+ // SIGN VIRAMA
"\uE050>\u0950;"+ // OM
// \uE055>; // UNMAPPED InterIndic-Devanagari: LENGTH MARK
"\uE056>\u0948;"+ // REMAP (indicExceptions.txt): \u0956>\u0948 = AI LENGTH MARK>VOWEL SIGN AI
"\uE057>\u094C;"+ // REMAP (indicExceptions.txt): \u0957>\u094C = AU LENGTH MARK>VOWEL SIGN AU
"\uE059>\u0959;"+ // LETTER KHHA
"\uE05A>\u095A;"+ // LETTER GHHA
"\uE05B>\u095B;"+ // LETTER ZA
"\uE05D>\u095D;"+ // LETTER RHA
"\uE05E>\u095E;"+ // LETTER FA
"\uE05F>\u095F;"+ // LETTER YYA
"\uE060>\u0960;"+ // LETTER VOCALIC RR
"\uE061>\u0961;"+ // LETTER VOCALIC LL
"\uE062>\u0962;"+ // VOWEL SIGN VOCALIC L
"\uE063>\u0963;"+ // VOWEL SIGN VOCALIC LL
"\uE066>\u0966;"+ // DIGIT ZERO
"\uE067>\u0967;"+ // DIGIT ONE
"\uE068>\u0968;"+ // DIGIT TWO
"\uE069>\u0969;"+ // DIGIT THREE
"\uE06A>\u096A;"+ // DIGIT FOUR
"\uE06B>\u096B;"+ // DIGIT FIVE
"\uE06C>\u096C;"+ // DIGIT SIX
"\uE06D>\u096D;"+ // DIGIT SEVEN
"\uE06E>\u096E;"+ // DIGIT EIGHT
"\uE06F>\u096F;"+ // DIGIT NINE
// \uE080>; // UNMAPPED InterIndic-Devanagari: ISSHAR
"\uE081>\u090F;"+ // LETTER E
"\uE082>\u0913;"+ // LETTER O
"\uE083>\u0931;"+ // LETTER RRA
"\uE084>\u0947;"+ // VOWEL SIGN E
"\uE085>\u094B;"+ // VOWEL SIGN O
""
}
};
}
}

123
icu4j/src/com/ibm/text/resources/TransliterationRule_InterIndic_Gujarati.java
View File

@ -1,123 +0,0 @@
/***********************************************************************
* Copyright (c) 2000, International Business Machines Corporation
* and others. All Rights Reserved.
************************************************************************
* > THIS FILE WAS MACHINE GENERATED <
* > DO NOT EDIT BY HAND <
* > RUN TOOL TO REGENERATE <
* Tool: icu4j/src/com/ibm/tools/translit/indic.pl
* Creation date: Fri Oct 6 15:55:21 2000
*/
package com.ibm.text.resources;
import java.util.ListResourceBundle;
public class TransliterationRule_InterIndic_Gujarati extends ListResourceBundle {
/**
* Overrides ListResourceBundle
*/
public Object[][] getContents() {
return new Object[][] {
{ "Rule",
"\uE001>\u0A81;"+ // SIGN CANDRABINDU
"\uE002>\u0A82;"+ // SIGN ANUSVARA
"\uE003>\u0A83;"+ // SIGN VISARGA
"\uE005>\u0A85;"+ // LETTER A
"\uE006>\u0A86;"+ // LETTER AA
"\uE007>\u0A87;"+ // LETTER I
"\uE008>\u0A88;"+ // LETTER II
"\uE009>\u0A89;"+ // LETTER U
"\uE00A>\u0A8A;"+ // LETTER UU
"\uE00B>\u0A8B;"+ // LETTER VOCALIC R
"\uE00C>\u0AB2\u0AC3;"+ // REMAP (indicExceptions.txt): \u0A8C>\u0AB2\u0AC3 = LETTER VOCALIC L>LETTER LA.VOWEL SIGN VOCALIC R
// \uE00F>; // UNMAPPED InterIndic-Gujarati: LETTER EE (\u0A8F = LETTER E)
"\uE010>\u0A90;"+ // LETTER AI
// \uE013>; // UNMAPPED InterIndic-Gujarati: LETTER OO (\u0A93 = LETTER O)
"\uE014>\u0A94;"+ // LETTER AU
"\uE015>\u0A95;"+ // LETTER KA
"\uE016>\u0A96;"+ // LETTER KHA
"\uE017>\u0A97;"+ // LETTER GA
"\uE018>\u0A98;"+ // LETTER GHA
"\uE019>\u0A99;"+ // LETTER NGA
"\uE01A>\u0A9A;"+ // LETTER CA
"\uE01B>\u0A9B;"+ // LETTER CHA
"\uE01C>\u0A9C;"+ // LETTER JA
"\uE01D>\u0A9D;"+ // LETTER JHA
"\uE01E>\u0A9E;"+ // LETTER NYA
"\uE01F>\u0A9F;"+ // LETTER TTA
"\uE020>\u0AA0;"+ // LETTER TTHA
"\uE021>\u0AA1;"+ // LETTER DDA
"\uE022>\u0AA2;"+ // LETTER DDHA
"\uE023>\u0AA3;"+ // LETTER NNA
"\uE024>\u0AA4;"+ // LETTER TA
"\uE025>\u0AA5;"+ // LETTER THA
"\uE026>\u0AA6;"+ // LETTER DA
"\uE027>\u0AA7;"+ // LETTER DHA
"\uE028>\u0AA8;"+ // LETTER NA
"\uE029>\u0AA8;"+ // REMAP (indicExceptions.txt): \u0AA9>\u0AA8 = LETTER NNNA>LETTER NA
"\uE02A>\u0AAA;"+ // LETTER PA
"\uE02B>\u0AAB;"+ // LETTER PHA
"\uE02C>\u0AAC;"+ // LETTER BA
"\uE02D>\u0AAD;"+ // LETTER BHA
"\uE02E>\u0AAE;"+ // LETTER MA
"\uE02F>\u0AAF;"+ // LETTER YA
"\uE030>\u0AB0;"+ // LETTER RA
"\uE032>\u0AB2;"+ // LETTER LA
"\uE033>\u0AB3;"+ // LETTER LLA
"\uE034>\u0AB3;"+ // REMAP (indicExceptions.txt): \u0AB4>\u0AB3 = LETTER LLLA>LETTER LLA
"\uE035>\u0AB5;"+ // LETTER VA
"\uE036>\u0AB6;"+ // LETTER SHA
"\uE037>\u0AB7;"+ // LETTER SSA
"\uE038>\u0AB8;"+ // LETTER SA
"\uE039>\u0AB9;"+ // LETTER HA
"\uE03C>\u0ABC;"+ // SIGN NUKTA
"\uE03D>\u0ABD;"+ // SIGN AVAGRAHA
"\uE03E>\u0ABE;"+ // VOWEL SIGN AA
"\uE03F>\u0ABF;"+ // VOWEL SIGN I
"\uE040>\u0AC0;"+ // VOWEL SIGN II
"\uE041>\u0AC1;"+ // VOWEL SIGN U
"\uE042>\u0AC2;"+ // VOWEL SIGN UU
"\uE043>\u0AC3;"+ // VOWEL SIGN VOCALIC R
"\uE044>\u0AC4;"+ // VOWEL SIGN VOCALIC RR
"\uE045>\u0AC5;"+ // VOWEL SIGN CANDRA E
// \uE047>; // UNMAPPED InterIndic-Gujarati: VOWEL SIGN EE (\u0AC7 = VOWEL SIGN E)
"\uE048>\u0AC8;"+ // VOWEL SIGN AI
"\uE049>\u0AC9;"+ // VOWEL SIGN CANDRA O
// \uE04B>; // UNMAPPED InterIndic-Gujarati: VOWEL SIGN OO (\u0ACB = VOWEL SIGN O)
"\uE04C>\u0ACC;"+ // VOWEL SIGN AU
"\uE04D>\u0ACD;"+ // SIGN VIRAMA
"\uE050>\u0AD0;"+ // OM
// \uE055>; // UNMAPPED InterIndic-Gujarati: LENGTH MARK
"\uE056>\u0AC8;"+ // REMAP (indicExceptions.txt): \u0AD6>\u0AC8 = AI LENGTH MARK>VOWEL SIGN AI
"\uE057>\u0ACC;"+ // REMAP (indicExceptions.txt): \u0AD7>\u0ACC = AU LENGTH MARK>VOWEL SIGN AU
"\uE059>\u0A96\u0ABC;"+ // REMAP (indicExceptions.txt): \u0AD9>\u0A96\u0ABC = LETTER KHHA>LETTER KHA.SIGN NUKTA
"\uE05A>\u0A97\u0ABC;"+ // REMAP (indicExceptions.txt): \u0ADA>\u0A97\u0ABC = LETTER GHHA>LETTER GA.SIGN NUKTA
"\uE05B>\u0A9C\u0ABC;"+ // REMAP (indicExceptions.txt): \u0ADB>\u0A9C\u0ABC = LETTER ZA>LETTER JA.SIGN NUKTA
"\uE05D>\u0AA2\u0ABC;"+ // REMAP (indicExceptions.txt): \u0ADD>\u0AA2\u0ABC = LETTER RHA>LETTER DDHA.SIGN NUKTA
"\uE05E>\u0AAB\u0ABC;"+ // REMAP (indicExceptions.txt): \u0ADE>\u0AAB\u0ABC = LETTER FA>LETTER PHA.SIGN NUKTA
"\uE05F>\u0AAF\u0ABC;"+ // REMAP (indicExceptions.txt): \u0ADF>\u0AAF\u0ABC = LETTER YYA>LETTER YA.SIGN NUKTA
"\uE060>\u0AE0;"+ // LETTER VOCALIC RR
"\uE061>\u0AB2\u0AC3;"+ // REMAP (indicExceptions.txt): \u0AE1>\u0AB2\u0AC3 = LETTER VOCALIC LL>LETTER LA.VOWEL SIGN VOCALIC R
"\uE062>\u0ABF\u0ABC;"+ // REMAP (indicExceptions.txt): \u0AE2>\u0ABF\u0ABC = VOWEL SIGN VOCALIC L>VOWEL SIGN I.SIGN NUKTA
"\uE063>\u0AC0\u0ABC;"+ // REMAP (indicExceptions.txt): \u0AE3>\u0AC0\u0ABC = VOWEL SIGN VOCALIC LL>VOWEL SIGN II.SIGN NUKTA
"\uE066>\u0AE6;"+ // DIGIT ZERO
"\uE067>\u0AE7;"+ // DIGIT ONE
"\uE068>\u0AE8;"+ // DIGIT TWO
"\uE069>\u0AE9;"+ // DIGIT THREE
"\uE06A>\u0AEA;"+ // DIGIT FOUR
"\uE06B>\u0AEB;"+ // DIGIT FIVE
"\uE06C>\u0AEC;"+ // DIGIT SIX
"\uE06D>\u0AED;"+ // DIGIT SEVEN
"\uE06E>\u0AEE;"+ // DIGIT EIGHT
"\uE06F>\u0AEF;"+ // DIGIT NINE
// \uE080>; // UNMAPPED InterIndic-Gujarati: ISSHAR
"\uE081>\u0A8F;"+ // LETTER E
"\uE082>\u0A93;"+ // LETTER O
// \uE083>; // UNMAPPED InterIndic-Gujarati: LETTER RRA (\u0A83 = SIGN VISARGA)
"\uE084>\u0AC7;"+ // VOWEL SIGN E
"\uE085>\u0ACB;"+ // VOWEL SIGN O
""
}
};
}
}

123
icu4j/src/com/ibm/text/resources/TransliterationRule_InterIndic_Gurmukhi.java
View File

@ -1,123 +0,0 @@
/***********************************************************************
* Copyright (c) 2000, International Business Machines Corporation
* and others. All Rights Reserved.
************************************************************************
* > THIS FILE WAS MACHINE GENERATED <
* > DO NOT EDIT BY HAND <
* > RUN TOOL TO REGENERATE <
* Tool: icu4j/src/com/ibm/tools/translit/indic.pl
* Creation date: Fri Oct 6 15:55:21 2000
*/
package com.ibm.text.resources;
import java.util.ListResourceBundle;
public class TransliterationRule_InterIndic_Gurmukhi extends ListResourceBundle {
/**
* Overrides ListResourceBundle
*/
public Object[][] getContents() {
return new Object[][] {
{ "Rule",
"\uE001>\u0A02;"+ // REMAP (indicExceptions.txt): \u0A01>\u0A02 = SIGN CANDRABINDU>SIGN BINDI
// \uE002>; // UNMAPPED InterIndic-Gurmukhi: SIGN ANUSVARA (\u0A02 = SIGN BINDI)
// \uE003>; // UNMAPPED InterIndic-Gurmukhi: SIGN VISARGA
"\uE005>\u0A05;"+ // LETTER A
"\uE006>\u0A06;"+ // LETTER AA
"\uE007>\u0A07;"+ // LETTER I
"\uE008>\u0A08;"+ // LETTER II
"\uE009>\u0A09;"+ // LETTER U
"\uE00A>\u0A0A;"+ // LETTER UU
"\uE00B>\u0A30\u0A3F;"+ // REMAP (indicExceptions.txt): \u0A0B>\u0A30\u0A3F = LETTER VOCALIC R>LETTER RA.VOWEL SIGN I
"\uE00C>\u0A07;"+ // REMAP (indicExceptions.txt): \u0A0C>\u0A07 = LETTER VOCALIC L>LETTER I
"\uE00F>\u0A0F;"+ // LETTER EE
"\uE010>\u0A10;"+ // LETTER AI
"\uE013>\u0A13;"+ // LETTER OO
"\uE014>\u0A14;"+ // LETTER AU
"\uE015>\u0A15;"+ // LETTER KA
"\uE016>\u0A16;"+ // LETTER KHA
"\uE017>\u0A17;"+ // LETTER GA
"\uE018>\u0A18;"+ // LETTER GHA
"\uE019>\u0A19;"+ // LETTER NGA
"\uE01A>\u0A1A;"+ // LETTER CA
"\uE01B>\u0A1B;"+ // LETTER CHA
"\uE01C>\u0A1C;"+ // LETTER JA
"\uE01D>\u0A1D;"+ // LETTER JHA
"\uE01E>\u0A1E;"+ // LETTER NYA
"\uE01F>\u0A1F;"+ // LETTER TTA
"\uE020>\u0A20;"+ // LETTER TTHA
"\uE021>\u0A21;"+ // LETTER DDA
"\uE022>\u0A22;"+ // LETTER DDHA
"\uE023>\u0A23;"+ // LETTER NNA
"\uE024>\u0A24;"+ // LETTER TA
"\uE025>\u0A25;"+ // LETTER THA
"\uE026>\u0A26;"+ // LETTER DA
"\uE027>\u0A27;"+ // LETTER DHA
"\uE028>\u0A28;"+ // LETTER NA
"\uE029>\u0A28;"+ // REMAP (indicExceptions.txt): \u0A29>\u0A28 = LETTER NNNA>LETTER NA
"\uE02A>\u0A2A;"+ // LETTER PA
"\uE02B>\u0A2B;"+ // LETTER PHA
"\uE02C>\u0A2C;"+ // LETTER BA
"\uE02D>\u0A2D;"+ // LETTER BHA
"\uE02E>\u0A2E;"+ // LETTER MA
"\uE02F>\u0A2F;"+ // LETTER YA
"\uE030>\u0A30;"+ // LETTER RA
"\uE032>\u0A32;"+ // LETTER LA
"\uE033>\u0A33;"+ // LETTER LLA
"\uE034>\u0A33;"+ // REMAP (indicExceptions.txt): \u0A34>\u0A33 = LETTER LLLA>LETTER LLA
"\uE035>\u0A35;"+ // LETTER VA
"\uE036>\u0A36;"+ // LETTER SHA
"\uE037>\u0A36;"+ // REMAP (indicExceptions.txt): \u0A37>\u0A36 = LETTER SSA>LETTER SHA
"\uE038>\u0A38;"+ // LETTER SA
"\uE039>\u0A39;"+ // LETTER HA
"\uE03C>\u0A3C;"+ // SIGN NUKTA
// \uE03D>; // UNMAPPED InterIndic-Gurmukhi: SIGN AVAGRAHA
"\uE03E>\u0A3E;"+ // VOWEL SIGN AA
"\uE03F>\u0A3F;"+ // VOWEL SIGN I
"\uE040>\u0A40;"+ // VOWEL SIGN II
"\uE041>\u0A41;"+ // VOWEL SIGN U
"\uE042>\u0A42;"+ // VOWEL SIGN UU
// \uE043>; // UNMAPPED InterIndic-Gurmukhi: VOWEL SIGN VOCALIC R
// \uE044>; // UNMAPPED InterIndic-Gurmukhi: VOWEL SIGN VOCALIC RR
"\uE045>\u0A48;"+ // REMAP (indicExceptions.txt): \u0A45>\u0A48 = VOWEL SIGN CANDRA E>VOWEL SIGN AI
"\uE047>\u0A47;"+ // VOWEL SIGN EE
"\uE048>\u0A48;"+ // VOWEL SIGN AI
"\uE049>\u0A4C;"+ // REMAP (indicExceptions.txt): \u0A49>\u0A4C = VOWEL SIGN CANDRA O>VOWEL SIGN AU
"\uE04B>\u0A4B;"+ // VOWEL SIGN OO
"\uE04C>\u0A4C;"+ // VOWEL SIGN AU
"\uE04D>\u0A4D;"+ // SIGN VIRAMA
// \uE050>; // UNMAPPED InterIndic-Gurmukhi: OM
// \uE055>; // UNMAPPED InterIndic-Gurmukhi: LENGTH MARK
"\uE056>\u0A48;"+ // REMAP (indicExceptions.txt): \u0A56>\u0A48 = AI LENGTH MARK>VOWEL SIGN AI
"\uE057>\u0A4C;"+ // REMAP (indicExceptions.txt): \u0A57>\u0A4C = AU LENGTH MARK>VOWEL SIGN AU
"\uE059>\u0A59;"+ // LETTER KHHA
"\uE05A>\u0A5A;"+ // LETTER GHHA
"\uE05B>\u0A5B;"+ // LETTER ZA
"\uE05D>\u0A22\u0A3C;"+ // REMAP (indicExceptions.txt): \u0A5D>\u0A22\u0A3C = LETTER RHA>LETTER DDHA.SIGN NUKTA
"\uE05E>\u0A5E;"+ // LETTER FA
"\uE05F>\u0A2F;"+ // REMAP (indicExceptions.txt): \u0A5F>\u0A2F = LETTER YYA>LETTER YA
"\uE060>\u0A30\u0A3F;"+ // REMAP (indicExceptions.txt): \u0A60>\u0A30\u0A3F = LETTER VOCALIC RR>LETTER RA.VOWEL SIGN I
"\uE061>\u0A08\u0A3C;"+ // REMAP (indicExceptions.txt): \u0A61>\u0A08\u0A3C = LETTER VOCALIC LL>LETTER II.SIGN NUKTA
"\uE062>\u0A3F\u0A3C;"+ // REMAP (indicExceptions.txt): \u0A62>\u0A3F\u0A3C = VOWEL SIGN VOCALIC L>VOWEL SIGN I.SIGN NUKTA
"\uE063>\u0A40\u0A3C;"+ // REMAP (indicExceptions.txt): \u0A63>\u0A40\u0A3C = VOWEL SIGN VOCALIC LL>VOWEL SIGN II.SIGN NUKTA
"\uE066>\u0A66;"+ // DIGIT ZERO
"\uE067>\u0A67;"+ // DIGIT ONE
"\uE068>\u0A68;"+ // DIGIT TWO
"\uE069>\u0A69;"+ // DIGIT THREE
"\uE06A>\u0A6A;"+ // DIGIT FOUR
"\uE06B>\u0A6B;"+ // DIGIT FIVE
"\uE06C>\u0A6C;"+ // DIGIT SIX
"\uE06D>\u0A6D;"+ // DIGIT SEVEN
"\uE06E>\u0A6E;"+ // DIGIT EIGHT
"\uE06F>\u0A6F;"+ // DIGIT NINE
// \uE080>; // UNMAPPED InterIndic-Gurmukhi: ISSHAR
// \uE081>; // UNMAPPED InterIndic-Gurmukhi: LETTER E
// \uE082>; // UNMAPPED InterIndic-Gurmukhi: LETTER O (\u0A02 = SIGN BINDI)
"\uE083>\u0A5C;"+ // LETTER RRA
// \uE084>; // UNMAPPED InterIndic-Gurmukhi: VOWEL SIGN E
// \uE085>; // UNMAPPED InterIndic-Gurmukhi: VOWEL SIGN O (\u0A05 = LETTER A)
""
}
};
}
}

123
icu4j/src/com/ibm/text/resources/TransliterationRule_InterIndic_Kannada.java
View File

@ -1,123 +0,0 @@
/***********************************************************************
* Copyright (c) 2000, International Business Machines Corporation
* and others. All Rights Reserved.
************************************************************************
* > THIS FILE WAS MACHINE GENERATED <
* > DO NOT EDIT BY HAND <
* > RUN TOOL TO REGENERATE <
* Tool: icu4j/src/com/ibm/tools/translit/indic.pl
* Creation date: Fri Oct 6 15:55:21 2000
*/
package com.ibm.text.resources;
import java.util.ListResourceBundle;
public class TransliterationRule_InterIndic_Kannada extends ListResourceBundle {
/**
* Overrides ListResourceBundle
*/
public Object[][] getContents() {
return new Object[][] {
{ "Rule",
"\uE001>\u0C82;"+ // REMAP (indicExceptions.txt): \u0C81>\u0C82 = SIGN CANDRABINDU>SIGN ANUSVARA
"\uE002>\u0C82;"+ // SIGN ANUSVARA
"\uE003>\u0C83;"+ // SIGN VISARGA
"\uE005>\u0C85;"+ // LETTER A
"\uE006>\u0C86;"+ // LETTER AA
"\uE007>\u0C87;"+ // LETTER I
"\uE008>\u0C88;"+ // LETTER II
"\uE009>\u0C89;"+ // LETTER U
"\uE00A>\u0C8A;"+ // LETTER UU
"\uE00B>\u0C8B;"+ // LETTER VOCALIC R
"\uE00C>\u0C8C;"+ // LETTER VOCALIC L
"\uE00F>\u0C8F;"+ // LETTER EE
"\uE010>\u0C90;"+ // LETTER AI
"\uE013>\u0C93;"+ // LETTER OO
"\uE014>\u0C94;"+ // LETTER AU
"\uE015>\u0C95;"+ // LETTER KA
"\uE016>\u0C96;"+ // LETTER KHA
"\uE017>\u0C97;"+ // LETTER GA
"\uE018>\u0C98;"+ // LETTER GHA
"\uE019>\u0C99;"+ // LETTER NGA
"\uE01A>\u0C9A;"+ // LETTER CA
"\uE01B>\u0C9B;"+ // LETTER CHA
"\uE01C>\u0C9C;"+ // LETTER JA
"\uE01D>\u0C9D;"+ // LETTER JHA
"\uE01E>\u0C9E;"+ // LETTER NYA
"\uE01F>\u0C9F;"+ // LETTER TTA
"\uE020>\u0CA0;"+ // LETTER TTHA
"\uE021>\u0CA1;"+ // LETTER DDA
"\uE022>\u0CA2;"+ // LETTER DDHA
"\uE023>\u0CA3;"+ // LETTER NNA
"\uE024>\u0CA4;"+ // LETTER TA
"\uE025>\u0CA5;"+ // LETTER THA
"\uE026>\u0CA6;"+ // LETTER DA
"\uE027>\u0CA7;"+ // LETTER DHA
"\uE028>\u0CA8;"+ // LETTER NA
"\uE029>\u0CA8;"+ // REMAP (indicExceptions.txt): \u0CA9>\u0CA8 = LETTER NNNA>LETTER NA
"\uE02A>\u0CAA;"+ // LETTER PA
"\uE02B>\u0CAB;"+ // LETTER PHA
"\uE02C>\u0CAC;"+ // LETTER BA
"\uE02D>\u0CAD;"+ // LETTER BHA
"\uE02E>\u0CAE;"+ // LETTER MA
"\uE02F>\u0CAF;"+ // LETTER YA
"\uE030>\u0CB0;"+ // LETTER RA
"\uE032>\u0CB2;"+ // LETTER LA
"\uE033>\u0CB3;"+ // LETTER LLA
"\uE034>\u0CB3;"+ // REMAP (indicExceptions.txt): \u0CB4>\u0CB3 = LETTER LLLA>LETTER LLA
"\uE035>\u0CB5;"+ // LETTER VA
"\uE036>\u0CB6;"+ // LETTER SHA
"\uE037>\u0CB7;"+ // LETTER SSA
"\uE038>\u0CB8;"+ // LETTER SA
"\uE039>\u0CB9;"+ // LETTER HA
// \uE03C>; // UNMAPPED InterIndic-Kannada: SIGN NUKTA
// \uE03D>; // UNMAPPED InterIndic-Kannada: SIGN AVAGRAHA
"\uE03E>\u0CBE;"+ // VOWEL SIGN AA
"\uE03F>\u0CBF;"+ // VOWEL SIGN I
"\uE040>\u0CC0;"+ // VOWEL SIGN II
"\uE041>\u0CC1;"+ // VOWEL SIGN U
"\uE042>\u0CC2;"+ // VOWEL SIGN UU
"\uE043>\u0CC3;"+ // VOWEL SIGN VOCALIC R
"\uE044>\u0CC4;"+ // VOWEL SIGN VOCALIC RR
"\uE045>\u0CC6;"+ // REMAP (indicExceptions.txt): \u0CC5>\u0CC6 = VOWEL SIGN CANDRA E>VOWEL SIGN E
"\uE047>\u0CC7;"+ // VOWEL SIGN EE
"\uE048>\u0CC8;"+ // VOWEL SIGN AI
"\uE049>\u0CCA;"+ // REMAP (indicExceptions.txt): \u0CC9>\u0CCA = VOWEL SIGN CANDRA O>VOWEL SIGN O
"\uE04B>\u0CCB;"+ // VOWEL SIGN OO
"\uE04C>\u0CCC;"+ // VOWEL SIGN AU
"\uE04D>\u0CCD;"+ // SIGN VIRAMA
"\uE050>\u0C93\u0C82;"+ // REMAP (indicExceptions.txt): \u0CD0>\u0C93\u0C82 = OM>LETTER OO.SIGN ANUSVARA
"\uE055>\u0CD5;"+ // LENGTH MARK
"\uE056>\u0CD6;"+ // AI LENGTH MARK
"\uE057>\u0CCC;"+ // REMAP (indicExceptions.txt): \u0CD7>\u0CCC = AU LENGTH MARK>VOWEL SIGN AU
"\uE059>\u0C96;"+ // REMAP (indicExceptions.txt): \u0CD9>\u0C96 = LETTER KHHA>LETTER KHA
"\uE05A>\u0C97;"+ // REMAP (indicExceptions.txt): \u0CDA>\u0C97 = LETTER GHHA>LETTER GA
"\uE05B>\u0C9C;"+ // REMAP (indicExceptions.txt): \u0CDB>\u0C9C = LETTER ZA>LETTER JA
"\uE05D>\u0CA2;"+ // REMAP (indicExceptions.txt): \u0CDD>\u0CA2 = LETTER RHA>LETTER DDHA
"\uE05E>\u0CDE;"+ // LETTER FA
"\uE05F>\u0CAF;"+ // REMAP (indicExceptions.txt): \u0CDF>\u0CAF = LETTER YYA>LETTER YA
"\uE060>\u0CE0;"+ // LETTER VOCALIC RR
"\uE061>\u0CE1;"+ // LETTER VOCALIC LL
"\uE062>\u0CBF;"+ // REMAP (indicExceptions.txt): \u0CE2>\u0CBF = VOWEL SIGN VOCALIC L>VOWEL SIGN I
"\uE063>\u0CC0;"+ // REMAP (indicExceptions.txt): \u0CE3>\u0CC0 = VOWEL SIGN VOCALIC LL>VOWEL SIGN II
"\uE066>\u0CE6;"+ // DIGIT ZERO
"\uE067>\u0CE7;"+ // DIGIT ONE
"\uE068>\u0CE8;"+ // DIGIT TWO
"\uE069>\u0CE9;"+ // DIGIT THREE
"\uE06A>\u0CEA;"+ // DIGIT FOUR
"\uE06B>\u0CEB;"+ // DIGIT FIVE
"\uE06C>\u0CEC;"+ // DIGIT SIX
"\uE06D>\u0CED;"+ // DIGIT SEVEN
"\uE06E>\u0CEE;"+ // DIGIT EIGHT
"\uE06F>\u0CEF;"+ // DIGIT NINE
// \uE080>; // UNMAPPED InterIndic-Kannada: ISSHAR
"\uE081>\u0C8E;"+ // LETTER E
"\uE082>\u0C92;"+ // LETTER O
"\uE083>\u0CB1;"+ // LETTER RRA
"\uE084>\u0CC6;"+ // VOWEL SIGN E
"\uE085>\u0CCA;"+ // VOWEL SIGN O
""
}
};
}
}

123
icu4j/src/com/ibm/text/resources/TransliterationRule_InterIndic_Malayalam.java
View File

@ -1,123 +0,0 @@
/***********************************************************************
* Copyright (c) 2000, International Business Machines Corporation
* and others. All Rights Reserved.
************************************************************************
* > THIS FILE WAS MACHINE GENERATED <
* > DO NOT EDIT BY HAND <
* > RUN TOOL TO REGENERATE <
* Tool: icu4j/src/com/ibm/tools/translit/indic.pl
* Creation date: Fri Oct 6 15:55:21 2000
*/
package com.ibm.text.resources;
import java.util.ListResourceBundle;
public class TransliterationRule_InterIndic_Malayalam extends ListResourceBundle {
/**
* Overrides ListResourceBundle
*/
public Object[][] getContents() {
return new Object[][] {
{ "Rule",
"\uE001>\u0D02;"+ // REMAP (indicExceptions.txt): \u0D01>\u0D02 = SIGN CANDRABINDU>SIGN ANUSVARA
"\uE002>\u0D02;"+ // SIGN ANUSVARA
"\uE003>\u0D03;"+ // SIGN VISARGA
"\uE005>\u0D05;"+ // LETTER A
"\uE006>\u0D06;"+ // LETTER AA
"\uE007>\u0D07;"+ // LETTER I
"\uE008>\u0D08;"+ // LETTER II
"\uE009>\u0D09;"+ // LETTER U
"\uE00A>\u0D0A;"+ // LETTER UU
"\uE00B>\u0D0B;"+ // LETTER VOCALIC R
"\uE00C>\u0D0C;"+ // LETTER VOCALIC L
"\uE00F>\u0D0F;"+ // LETTER EE
"\uE010>\u0D10;"+ // LETTER AI
"\uE013>\u0D13;"+ // LETTER OO
"\uE014>\u0D14;"+ // LETTER AU
"\uE015>\u0D15;"+ // LETTER KA
"\uE016>\u0D16;"+ // LETTER KHA
"\uE017>\u0D17;"+ // LETTER GA
"\uE018>\u0D18;"+ // LETTER GHA
"\uE019>\u0D19;"+ // LETTER NGA
"\uE01A>\u0D1A;"+ // LETTER CA
"\uE01B>\u0D1B;"+ // LETTER CHA
"\uE01C>\u0D1C;"+ // LETTER JA
"\uE01D>\u0D1D;"+ // LETTER JHA
"\uE01E>\u0D1E;"+ // LETTER NYA
"\uE01F>\u0D1F;"+ // LETTER TTA
"\uE020>\u0D20;"+ // LETTER TTHA
"\uE021>\u0D21;"+ // LETTER DDA
"\uE022>\u0D22;"+ // LETTER DDHA
"\uE023>\u0D23;"+ // LETTER NNA
"\uE024>\u0D24;"+ // LETTER TA
"\uE025>\u0D25;"+ // LETTER THA
"\uE026>\u0D26;"+ // LETTER DA
"\uE027>\u0D27;"+ // LETTER DHA
"\uE028>\u0D28;"+ // LETTER NA
"\uE029>\u0D28;"+ // REMAP (indicExceptions.txt): \u0D29>\u0D28 = LETTER NNNA>LETTER NA
"\uE02A>\u0D2A;"+ // LETTER PA
"\uE02B>\u0D2B;"+ // LETTER PHA
"\uE02C>\u0D2C;"+ // LETTER BA
"\uE02D>\u0D2D;"+ // LETTER BHA
"\uE02E>\u0D2E;"+ // LETTER MA
"\uE02F>\u0D2F;"+ // LETTER YA
"\uE030>\u0D30;"+ // LETTER RA
"\uE032>\u0D32;"+ // LETTER LA
"\uE033>\u0D33;"+ // LETTER LLA
"\uE034>\u0D34;"+ // LETTER LLLA
"\uE035>\u0D35;"+ // LETTER VA
"\uE036>\u0D36;"+ // LETTER SHA
"\uE037>\u0D37;"+ // LETTER SSA
"\uE038>\u0D38;"+ // LETTER SA
"\uE039>\u0D39;"+ // LETTER HA
// \uE03C>; // UNMAPPED InterIndic-Malayalam: SIGN NUKTA
// \uE03D>; // UNMAPPED InterIndic-Malayalam: SIGN AVAGRAHA
"\uE03E>\u0D3E;"+ // VOWEL SIGN AA
"\uE03F>\u0D3F;"+ // VOWEL SIGN I
"\uE040>\u0D40;"+ // VOWEL SIGN II
"\uE041>\u0D41;"+ // VOWEL SIGN U
"\uE042>\u0D42;"+ // VOWEL SIGN UU
"\uE043>\u0D43;"+ // VOWEL SIGN VOCALIC R
// \uE044>; // UNMAPPED InterIndic-Malayalam: VOWEL SIGN VOCALIC RR
"\uE045>\u0D3E;"+ // REMAP (indicExceptions.txt): \u0D45>\u0D3E = VOWEL SIGN CANDRA E>VOWEL SIGN AA
"\uE047>\u0D47;"+ // VOWEL SIGN EE
"\uE048>\u0D48;"+ // VOWEL SIGN AI
"\uE049>\u0D4B;"+ // REMAP (indicExceptions.txt): \u0D49>\u0D4B = VOWEL SIGN CANDRA O>VOWEL SIGN OO
"\uE04B>\u0D4B;"+ // VOWEL SIGN OO
"\uE04C>\u0D4C;"+ // VOWEL SIGN AU
"\uE04D>\u0D4D;"+ // SIGN VIRAMA
// \uE050>; // UNMAPPED InterIndic-Malayalam: OM
// \uE055>; // UNMAPPED InterIndic-Malayalam: LENGTH MARK
"\uE056>\u0D48;"+ // REMAP (indicExceptions.txt): \u0D56>\u0D48 = AI LENGTH MARK>VOWEL SIGN AI
"\uE057>\u0D57;"+ // AU LENGTH MARK
"\uE059>\u0D16;"+ // REMAP (indicExceptions.txt): \u0D59>\u0D16 = LETTER KHHA>LETTER KHA
"\uE05A>\u0D17;"+ // REMAP (indicExceptions.txt): \u0D5A>\u0D17 = LETTER GHHA>LETTER GA
"\uE05B>\u0D1C;"+ // REMAP (indicExceptions.txt): \u0D5B>\u0D1C = LETTER ZA>LETTER JA
"\uE05D>\u0D22;"+ // REMAP (indicExceptions.txt): \u0D5D>\u0D22 = LETTER RHA>LETTER DDHA
"\uE05E>\u0D2B;"+ // REMAP (indicExceptions.txt): \u0D5E>\u0D2B = LETTER FA>LETTER PHA
"\uE05F>\u0D2F;"+ // REMAP (indicExceptions.txt): \u0D5F>\u0D2F = LETTER YYA>LETTER YA
"\uE060>\u0D60;"+ // LETTER VOCALIC RR
"\uE061>\u0D61;"+ // LETTER VOCALIC LL
// \uE062>; // UNMAPPED InterIndic-Malayalam: VOWEL SIGN VOCALIC L
// \uE063>; // UNMAPPED InterIndic-Malayalam: VOWEL SIGN VOCALIC LL
"\uE066>\u0D66;"+ // DIGIT ZERO
"\uE067>\u0D67;"+ // DIGIT ONE
"\uE068>\u0D68;"+ // DIGIT TWO
"\uE069>\u0D69;"+ // DIGIT THREE
"\uE06A>\u0D6A;"+ // DIGIT FOUR
"\uE06B>\u0D6B;"+ // DIGIT FIVE
"\uE06C>\u0D6C;"+ // DIGIT SIX
"\uE06D>\u0D6D;"+ // DIGIT SEVEN
"\uE06E>\u0D6E;"+ // DIGIT EIGHT
"\uE06F>\u0D6F;"+ // DIGIT NINE
// \uE080>; // UNMAPPED InterIndic-Malayalam: ISSHAR
"\uE081>\u0D0E;"+ // LETTER E
"\uE082>\u0D12;"+ // LETTER O
"\uE083>\u0D31;"+ // LETTER RRA
"\uE084>\u0D46;"+ // VOWEL SIGN E
"\uE085>\u0D4A;"+ // VOWEL SIGN O
""
}
};
}
}

123
icu4j/src/com/ibm/text/resources/TransliterationRule_InterIndic_Oriya.java
View File

@ -1,123 +0,0 @@
/***********************************************************************
* Copyright (c) 2000, International Business Machines Corporation
* and others. All Rights Reserved.
************************************************************************
* > THIS FILE WAS MACHINE GENERATED <
* > DO NOT EDIT BY HAND <
* > RUN TOOL TO REGENERATE <
* Tool: icu4j/src/com/ibm/tools/translit/indic.pl
* Creation date: Fri Oct 6 15:55:21 2000
*/
package com.ibm.text.resources;
import java.util.ListResourceBundle;
public class TransliterationRule_InterIndic_Oriya extends ListResourceBundle {
/**
* Overrides ListResourceBundle
*/
public Object[][] getContents() {
return new Object[][] {
{ "Rule",
"\uE001>\u0B01;"+ // SIGN CANDRABINDU
"\uE002>\u0B02;"+ // SIGN ANUSVARA
"\uE003>\u0B03;"+ // SIGN VISARGA
"\uE005>\u0B05;"+ // LETTER A
"\uE006>\u0B06;"+ // LETTER AA
"\uE007>\u0B07;"+ // LETTER I
"\uE008>\u0B08;"+ // LETTER II
"\uE009>\u0B09;"+ // LETTER U
"\uE00A>\u0B0A;"+ // LETTER UU
"\uE00B>\u0B0B;"+ // LETTER VOCALIC R
"\uE00C>\u0B0C;"+ // LETTER VOCALIC L
// \uE00F>; // UNMAPPED InterIndic-Oriya: LETTER EE (\u0B0F = LETTER E)
"\uE010>\u0B10;"+ // LETTER AI
// \uE013>; // UNMAPPED InterIndic-Oriya: LETTER OO (\u0B13 = LETTER O)
"\uE014>\u0B14;"+ // LETTER AU
"\uE015>\u0B15;"+ // LETTER KA
"\uE016>\u0B16;"+ // LETTER KHA
"\uE017>\u0B17;"+ // LETTER GA
"\uE018>\u0B18;"+ // LETTER GHA
"\uE019>\u0B19;"+ // LETTER NGA
"\uE01A>\u0B1A;"+ // LETTER CA
"\uE01B>\u0B1B;"+ // LETTER CHA
"\uE01C>\u0B1C;"+ // LETTER JA
"\uE01D>\u0B1D;"+ // LETTER JHA
"\uE01E>\u0B1E;"+ // LETTER NYA
"\uE01F>\u0B1F;"+ // LETTER TTA
"\uE020>\u0B20;"+ // LETTER TTHA
"\uE021>\u0B21;"+ // LETTER DDA
"\uE022>\u0B22;"+ // LETTER DDHA
"\uE023>\u0B23;"+ // LETTER NNA
"\uE024>\u0B24;"+ // LETTER TA
"\uE025>\u0B25;"+ // LETTER THA
"\uE026>\u0B26;"+ // LETTER DA
"\uE027>\u0B27;"+ // LETTER DHA
"\uE028>\u0B28;"+ // LETTER NA
"\uE029>\u0B28;"+ // REMAP (indicExceptions.txt): \u0B29>\u0B28 = LETTER NNNA>LETTER NA
"\uE02A>\u0B2A;"+ // LETTER PA
"\uE02B>\u0B2B;"+ // LETTER PHA
"\uE02C>\u0B2C;"+ // LETTER BA
"\uE02D>\u0B2D;"+ // LETTER BHA
"\uE02E>\u0B2E;"+ // LETTER MA
"\uE02F>\u0B2F;"+ // LETTER YA
"\uE030>\u0B30;"+ // LETTER RA
"\uE032>\u0B32;"+ // LETTER LA
"\uE033>\u0B33;"+ // LETTER LLA
"\uE034>\u0B33;"+ // REMAP (indicExceptions.txt): \u0B34>\u0B33 = LETTER LLLA>LETTER LLA
"\uE035>\u0B2C;"+ // REMAP (indicExceptions.txt): \u0B35>\u0B2C = LETTER VA>LETTER BA
"\uE036>\u0B36;"+ // LETTER SHA
"\uE037>\u0B37;"+ // LETTER SSA
"\uE038>\u0B38;"+ // LETTER SA
"\uE039>\u0B39;"+ // LETTER HA
"\uE03C>\u0B3C;"+ // SIGN NUKTA
"\uE03D>\u0B3D;"+ // SIGN AVAGRAHA
"\uE03E>\u0B3E;"+ // VOWEL SIGN AA
"\uE03F>\u0B3F;"+ // VOWEL SIGN I
"\uE040>\u0B40;"+ // VOWEL SIGN II
"\uE041>\u0B41;"+ // VOWEL SIGN U
"\uE042>\u0B42;"+ // VOWEL SIGN UU
"\uE043>\u0B43;"+ // VOWEL SIGN VOCALIC R
"\uE044>\u0B43\u0B3C;"+ // REMAP (indicExceptions.txt): \u0B44>\u0B43\u0B3C = VOWEL SIGN VOCALIC RR>VOWEL SIGN VOCALIC R.SIGN NUKTA
"\uE045>\u0B47;"+ // REMAP (indicExceptions.txt): \u0B45>\u0B47 = VOWEL SIGN CANDRA E>VOWEL SIGN E
// \uE047>; // UNMAPPED InterIndic-Oriya: VOWEL SIGN EE (\u0B47 = VOWEL SIGN E)
"\uE048>\u0B48;"+ // VOWEL SIGN AI
"\uE049>\u0B4B;"+ // REMAP (indicExceptions.txt): \u0B49>\u0B4B = VOWEL SIGN CANDRA O>VOWEL SIGN O
// \uE04B>; // UNMAPPED InterIndic-Oriya: VOWEL SIGN OO (\u0B4B = VOWEL SIGN O)
"\uE04C>\u0B4C;"+ // VOWEL SIGN AU
"\uE04D>\u0B4D;"+ // SIGN VIRAMA
"\uE050>\u0B13\u0B01;"+ // REMAP (indicExceptions.txt): \u0B50>\u0B13\u0B01 = OM>LETTER O.SIGN CANDRABINDU
// \uE055>; // UNMAPPED InterIndic-Oriya: LENGTH MARK
"\uE056>\u0B56;"+ // AI LENGTH MARK
"\uE057>\u0B57;"+ // AU LENGTH MARK
"\uE059>\u0B16\u0B3C;"+ // REMAP (indicExceptions.txt): \u0B59>\u0B16\u0B3C = LETTER KHHA>LETTER KHA.SIGN NUKTA
"\uE05A>\u0B17\u0B3C;"+ // REMAP (indicExceptions.txt): \u0B5A>\u0B17\u0B3C = LETTER GHHA>LETTER GA.SIGN NUKTA
"\uE05B>\u0B1C\u0B3C;"+ // REMAP (indicExceptions.txt): \u0B5B>\u0B1C\u0B3C = LETTER ZA>LETTER JA.SIGN NUKTA
"\uE05D>\u0B5D;"+ // LETTER RHA
"\uE05E>\u0B2B\u0B3C;"+ // REMAP (indicExceptions.txt): \u0B5E>\u0B2B\u0B3C = LETTER FA>LETTER PHA.SIGN NUKTA
"\uE05F>\u0B5F;"+ // LETTER YYA
"\uE060>\u0B60;"+ // LETTER VOCALIC RR
"\uE061>\u0B61;"+ // LETTER VOCALIC LL
"\uE062>\u0B56\u0B3C;"+ // REMAP (indicExceptions.txt): \u0B62>\u0B56\u0B3C = VOWEL SIGN VOCALIC L>AI LENGTH MARK.SIGN NUKTA
"\uE063>\u0B57\u0B3C;"+ // REMAP (indicExceptions.txt): \u0B63>\u0B57\u0B3C = VOWEL SIGN VOCALIC LL>AU LENGTH MARK.SIGN NUKTA
"\uE066>\u0B66;"+ // DIGIT ZERO
"\uE067>\u0B67;"+ // DIGIT ONE
"\uE068>\u0B68;"+ // DIGIT TWO
"\uE069>\u0B69;"+ // DIGIT THREE
"\uE06A>\u0B6A;"+ // DIGIT FOUR
"\uE06B>\u0B6B;"+ // DIGIT FIVE
"\uE06C>\u0B6C;"+ // DIGIT SIX
"\uE06D>\u0B6D;"+ // DIGIT SEVEN
"\uE06E>\u0B6E;"+ // DIGIT EIGHT
"\uE06F>\u0B6F;"+ // DIGIT NINE
"\uE080>\u0B70;"+ // ISSHAR
"\uE081>\u0B0F;"+ // LETTER E
"\uE082>\u0B13;"+ // LETTER O
"\uE083>\u0B5C;"+ // LETTER RRA
"\uE084>\u0B47;"+ // VOWEL SIGN E
"\uE085>\u0B4B;"+ // VOWEL SIGN O
""
}
};
}
}

123
icu4j/src/com/ibm/text/resources/TransliterationRule_InterIndic_Tamil.java
View File

@ -1,123 +0,0 @@
/***********************************************************************
* Copyright (c) 2000, International Business Machines Corporation
* and others. All Rights Reserved.
************************************************************************
* > THIS FILE WAS MACHINE GENERATED <
* > DO NOT EDIT BY HAND <
* > RUN TOOL TO REGENERATE <
* Tool: icu4j/src/com/ibm/tools/translit/indic.pl
* Creation date: Fri Oct 6 15:55:21 2000
*/
package com.ibm.text.resources;
import java.util.ListResourceBundle;
public class TransliterationRule_InterIndic_Tamil extends ListResourceBundle {
/**
* Overrides ListResourceBundle
*/
public Object[][] getContents() {
return new Object[][] {
{ "Rule",
// \uE001>; // UNMAPPED InterIndic-Tamil: SIGN CANDRABINDU
"\uE002>\u0B82;"+ // SIGN ANUSVARA
"\uE003>\u0B83;"+ // SIGN VISARGA
"\uE005>\u0B85;"+ // LETTER A
"\uE006>\u0B86;"+ // LETTER AA
"\uE007>\u0B87;"+ // LETTER I
"\uE008>\u0B88;"+ // LETTER II
"\uE009>\u0B89;"+ // LETTER U
"\uE00A>\u0B8A;"+ // LETTER UU
"\uE00B>\u0BB0\u0BBF;"+ // REMAP (indicExceptions.txt): \u0B8B>\u0BB0\u0BBF = LETTER VOCALIC R>LETTER RA.VOWEL SIGN I
"\uE00C>\u0B87;"+ // REMAP (indicExceptions.txt): \u0B8C>\u0B87 = LETTER VOCALIC L>LETTER I
"\uE00F>\u0B8F;"+ // LETTER EE
"\uE010>\u0B90;"+ // LETTER AI
"\uE013>\u0B93;"+ // LETTER OO
"\uE014>\u0B94;"+ // LETTER AU
"\uE015>\u0B95;"+ // LETTER KA
"\uE016>\u0B95;"+ // REMAP (indicExceptions.txt): \u0B96>\u0B95 = LETTER KHA>LETTER KA
"\uE017>\u0B95;"+ // REMAP (indicExceptions.txt): \u0B97>\u0B95 = LETTER GA>LETTER KA
"\uE018>\u0B95;"+ // REMAP (indicExceptions.txt): \u0B98>\u0B95 = LETTER GHA>LETTER KA
"\uE019>\u0B99;"+ // LETTER NGA
"\uE01A>\u0B9A;"+ // LETTER CA
"\uE01B>\u0B9A;"+ // REMAP (indicExceptions.txt): \u0B9B>\u0B9A = LETTER CHA>LETTER CA
"\uE01C>\u0B9C;"+ // LETTER JA
"\uE01D>\u0B9A;"+ // REMAP (indicExceptions.txt): \u0B9D>\u0B9A = LETTER JHA>LETTER CA
"\uE01E>\u0B9E;"+ // LETTER NYA
"\uE01F>\u0B9F;"+ // LETTER TTA
"\uE020>\u0B9F;"+ // REMAP (indicExceptions.txt): \u0BA0>\u0B9F = LETTER TTHA>LETTER TTA
"\uE021>\u0B9F;"+ // REMAP (indicExceptions.txt): \u0BA1>\u0B9F = LETTER DDA>LETTER TTA
"\uE022>\u0B9F;"+ // REMAP (indicExceptions.txt): \u0BA2>\u0B9F = LETTER DDHA>LETTER TTA
"\uE023>\u0BA3;"+ // LETTER NNA
"\uE024>\u0BA4;"+ // LETTER TA
"\uE025>\u0BA4;"+ // REMAP (indicExceptions.txt): \u0BA5>\u0BA4 = LETTER THA>LETTER TA
"\uE026>\u0BA4;"+ // REMAP (indicExceptions.txt): \u0BA6>\u0BA4 = LETTER DA>LETTER TA
"\uE027>\u0BA4;"+ // REMAP (indicExceptions.txt): \u0BA7>\u0BA4 = LETTER DHA>LETTER TA
"\uE028>\u0BA8;"+ // LETTER NA
"\uE029>\u0BA9;"+ // LETTER NNNA
"\uE02A>\u0BAA;"+ // LETTER PA
"\uE02B>\u0BAA;"+ // REMAP (indicExceptions.txt): \u0BAB>\u0BAA = LETTER PHA>LETTER PA
"\uE02C>\u0BAA;"+ // REMAP (indicExceptions.txt): \u0BAC>\u0BAA = LETTER BA>LETTER PA
"\uE02D>\u0BAA;"+ // REMAP (indicExceptions.txt): \u0BAD>\u0BAA = LETTER BHA>LETTER PA
"\uE02E>\u0BAE;"+ // LETTER MA
"\uE02F>\u0BAF;"+ // LETTER YA
"\uE030>\u0BB0;"+ // LETTER RA
"\uE032>\u0BB2;"+ // LETTER LA
"\uE033>\u0BB3;"+ // LETTER LLA
"\uE034>\u0BB4;"+ // LETTER LLLA
"\uE035>\u0BB5;"+ // LETTER VA
"\uE036>\u0BB7;"+ // REMAP (indicExceptions.txt): \u0BB6>\u0BB7 = LETTER SHA>LETTER SSA
"\uE037>\u0BB7;"+ // LETTER SSA
"\uE038>\u0BB8;"+ // LETTER SA
"\uE039>\u0BB9;"+ // LETTER HA
// \uE03C>; // UNMAPPED InterIndic-Tamil: SIGN NUKTA
// \uE03D>; // UNMAPPED InterIndic-Tamil: SIGN AVAGRAHA
"\uE03E>\u0BBE;"+ // VOWEL SIGN AA
"\uE03F>\u0BBF;"+ // VOWEL SIGN I
"\uE040>\u0BC0;"+ // VOWEL SIGN II
"\uE041>\u0BC1;"+ // VOWEL SIGN U
"\uE042>\u0BC2;"+ // VOWEL SIGN UU
"\uE043>\u0BCD\u0BB0\u0BBF;"+ // REMAP (indicExceptions.txt): \u0BC3>\u0BCD\u0BB0\u0BBF = VOWEL SIGN VOCALIC R>SIGN VIRAMA.LETTER RA.VOWEL SIGN I
"\uE044>\u0BCD\u0BB0\u0BBF;"+ // REMAP (indicExceptions.txt): \u0BC4>\u0BCD\u0BB0\u0BBF = VOWEL SIGN VOCALIC RR>SIGN VIRAMA.LETTER RA.VOWEL SIGN I
"\uE045>\u0BBE;"+ // REMAP (indicExceptions.txt): \u0BC5>\u0BBE = VOWEL SIGN CANDRA E>VOWEL SIGN AA
"\uE047>\u0BC7;"+ // VOWEL SIGN EE
"\uE048>\u0BC8;"+ // VOWEL SIGN AI
"\uE049>\u0BBE;"+ // REMAP (indicExceptions.txt): \u0BC9>\u0BBE = VOWEL SIGN CANDRA O>VOWEL SIGN AA
"\uE04B>\u0BCB;"+ // VOWEL SIGN OO
"\uE04C>\u0BCC;"+ // VOWEL SIGN AU
"\uE04D>\u0BCD;"+ // SIGN VIRAMA
"\uE050>\u0B93\u0BAE\u0BCD;"+ // REMAP (indicExceptions.txt): \u0BD0>\u0B93\u0BAE\u0BCD = OM>LETTER OO.LETTER MA.SIGN VIRAMA
// \uE055>; // UNMAPPED InterIndic-Tamil: LENGTH MARK
"\uE056>\u0BC8;"+ // REMAP (indicExceptions.txt): \u0BD6>\u0BC8 = AI LENGTH MARK>VOWEL SIGN AI
"\uE057>\u0BD7;"+ // AU LENGTH MARK
"\uE059>\u0B95;"+ // REMAP (indicExceptions.txt): \u0BD9>\u0B95 = LETTER KHHA>LETTER KA
"\uE05A>\u0B95;"+ // REMAP (indicExceptions.txt): \u0BDA>\u0B95 = LETTER GHHA>LETTER KA
"\uE05B>\u0B9C;"+ // REMAP (indicExceptions.txt): \u0BDB>\u0B9C = LETTER ZA>LETTER JA
"\uE05D>\u0B9F;"+ // REMAP (indicExceptions.txt): \u0BDD>\u0B9F = LETTER RHA>LETTER TTA
"\uE05E>\u0BAA;"+ // REMAP (indicExceptions.txt): \u0BDE>\u0BAA = LETTER FA>LETTER PA
"\uE05F>\u0BAF;"+ // REMAP (indicExceptions.txt): \u0BDF>\u0BAF = LETTER YYA>LETTER YA
"\uE060>\u0BB0\u0BBF;"+ // REMAP (indicExceptions.txt): \u0BE0>\u0BB0\u0BBF = LETTER VOCALIC RR>LETTER RA.VOWEL SIGN I
"\uE061>\u0B88;"+ // REMAP (indicExceptions.txt): \u0BE1>\u0B88 = LETTER VOCALIC LL>LETTER II
// \uE062>; // UNMAPPED InterIndic-Tamil: VOWEL SIGN VOCALIC L
// \uE063>; // UNMAPPED InterIndic-Tamil: VOWEL SIGN VOCALIC LL
// \uE066>; // UNMAPPED InterIndic-Tamil: DIGIT ZERO
"\uE067>\u0BE7;"+ // DIGIT ONE
"\uE068>\u0BE8;"+ // DIGIT TWO
"\uE069>\u0BE9;"+ // DIGIT THREE
"\uE06A>\u0BEA;"+ // DIGIT FOUR
"\uE06B>\u0BEB;"+ // DIGIT FIVE
"\uE06C>\u0BEC;"+ // DIGIT SIX
"\uE06D>\u0BED;"+ // DIGIT SEVEN
"\uE06E>\u0BEE;"+ // DIGIT EIGHT
"\uE06F>\u0BEF;"+ // DIGIT NINE
// \uE080>; // UNMAPPED InterIndic-Tamil: ISSHAR
"\uE081>\u0B8E;"+ // LETTER E
"\uE082>\u0B92;"+ // LETTER O
"\uE083>\u0BB1;"+ // LETTER RRA
"\uE084>\u0BC6;"+ // VOWEL SIGN E
"\uE085>\u0BCA;"+ // VOWEL SIGN O
""
}
};
}
}

123
icu4j/src/com/ibm/text/resources/TransliterationRule_InterIndic_Telugu.java
View File

@ -1,123 +0,0 @@
/***********************************************************************
* Copyright (c) 2000, International Business Machines Corporation
* and others. All Rights Reserved.
************************************************************************
* > THIS FILE WAS MACHINE GENERATED <
* > DO NOT EDIT BY HAND <
* > RUN TOOL TO REGENERATE <
* Tool: icu4j/src/com/ibm/tools/translit/indic.pl
* Creation date: Fri Oct 6 15:55:22 2000
*/
package com.ibm.text.resources;
import java.util.ListResourceBundle;
public class TransliterationRule_InterIndic_Telugu extends ListResourceBundle {
/**
* Overrides ListResourceBundle
*/
public Object[][] getContents() {
return new Object[][] {
{ "Rule",
"\uE001>\u0C01;"+ // SIGN CANDRABINDU
"\uE002>\u0C02;"+ // SIGN ANUSVARA
"\uE003>\u0C03;"+ // SIGN VISARGA
"\uE005>\u0C05;"+ // LETTER A
"\uE006>\u0C06;"+ // LETTER AA
"\uE007>\u0C07;"+ // LETTER I
"\uE008>\u0C08;"+ // LETTER II
"\uE009>\u0C09;"+ // LETTER U
"\uE00A>\u0C0A;"+ // LETTER UU
"\uE00B>\u0C0B;"+ // LETTER VOCALIC R
"\uE00C>\u0C0C;"+ // LETTER VOCALIC L
"\uE00F>\u0C0F;"+ // LETTER EE
"\uE010>\u0C10;"+ // LETTER AI
"\uE013>\u0C13;"+ // LETTER OO
"\uE014>\u0C14;"+ // LETTER AU
"\uE015>\u0C15;"+ // LETTER KA
"\uE016>\u0C16;"+ // LETTER KHA
"\uE017>\u0C17;"+ // LETTER GA
"\uE018>\u0C18;"+ // LETTER GHA
"\uE019>\u0C19;"+ // LETTER NGA
"\uE01A>\u0C1A;"+ // LETTER CA
"\uE01B>\u0C1B;"+ // LETTER CHA
"\uE01C>\u0C1C;"+ // LETTER JA
"\uE01D>\u0C1D;"+ // LETTER JHA
"\uE01E>\u0C1E;"+ // LETTER NYA
"\uE01F>\u0C1F;"+ // LETTER TTA
"\uE020>\u0C20;"+ // LETTER TTHA
"\uE021>\u0C21;"+ // LETTER DDA
"\uE022>\u0C22;"+ // LETTER DDHA
"\uE023>\u0C23;"+ // LETTER NNA
"\uE024>\u0C24;"+ // LETTER TA
"\uE025>\u0C25;"+ // LETTER THA
"\uE026>\u0C26;"+ // LETTER DA
"\uE027>\u0C27;"+ // LETTER DHA
"\uE028>\u0C28;"+ // LETTER NA
"\uE029>\u0C28;"+ // REMAP (indicExceptions.txt): \u0C29>\u0C28 = LETTER NNNA>LETTER NA
"\uE02A>\u0C2A;"+ // LETTER PA
"\uE02B>\u0C2B;"+ // LETTER PHA
"\uE02C>\u0C2C;"+ // LETTER BA
"\uE02D>\u0C2D;"+ // LETTER BHA
"\uE02E>\u0C2E;"+ // LETTER MA
"\uE02F>\u0C2F;"+ // LETTER YA
"\uE030>\u0C30;"+ // LETTER RA
"\uE032>\u0C32;"+ // LETTER LA
"\uE033>\u0C33;"+ // LETTER LLA
"\uE034>\u0C33;"+ // REMAP (indicExceptions.txt): \u0C34>\u0C33 = LETTER LLLA>LETTER LLA
"\uE035>\u0C35;"+ // LETTER VA
"\uE036>\u0C36;"+ // LETTER SHA
"\uE037>\u0C37;"+ // LETTER SSA
"\uE038>\u0C38;"+ // LETTER SA
"\uE039>\u0C39;"+ // LETTER HA
// \uE03C>; // UNMAPPED InterIndic-Telugu: SIGN NUKTA
// \uE03D>; // UNMAPPED InterIndic-Telugu: SIGN AVAGRAHA
"\uE03E>\u0C3E;"+ // VOWEL SIGN AA
"\uE03F>\u0C3F;"+ // VOWEL SIGN I
"\uE040>\u0C40;"+ // VOWEL SIGN II
"\uE041>\u0C41;"+ // VOWEL SIGN U
"\uE042>\u0C42;"+ // VOWEL SIGN UU
"\uE043>\u0C43;"+ // VOWEL SIGN VOCALIC R
"\uE044>\u0C44;"+ // VOWEL SIGN VOCALIC RR
"\uE045>\u0C46;"+ // REMAP (indicExceptions.txt): \u0C45>\u0C46 = VOWEL SIGN CANDRA E>VOWEL SIGN E
"\uE047>\u0C47;"+ // VOWEL SIGN EE
"\uE048>\u0C48;"+ // VOWEL SIGN AI
"\uE049>\u0C4A;"+ // REMAP (indicExceptions.txt): \u0C49>\u0C4A = VOWEL SIGN CANDRA O>VOWEL SIGN O
"\uE04B>\u0C4B;"+ // VOWEL SIGN OO
"\uE04C>\u0C4C;"+ // VOWEL SIGN AU
"\uE04D>\u0C4D;"+ // SIGN VIRAMA
"\uE050>\u0C13\u0C02;"+ // REMAP (indicExceptions.txt): \u0C50>\u0C13\u0C02 = OM>LETTER OO.SIGN ANUSVARA
"\uE055>\u0C55;"+ // LENGTH MARK
"\uE056>\u0C56;"+ // AI LENGTH MARK
"\uE057>\u0C4C;"+ // REMAP (indicExceptions.txt): \u0C57>\u0C4C = AU LENGTH MARK>VOWEL SIGN AU
"\uE059>\u0C16;"+ // REMAP (indicExceptions.txt): \u0C59>\u0C16 = LETTER KHHA>LETTER KHA
"\uE05A>\u0C17;"+ // REMAP (indicExceptions.txt): \u0C5A>\u0C17 = LETTER GHHA>LETTER GA
"\uE05B>\u0C1C;"+ // REMAP (indicExceptions.txt): \u0C5B>\u0C1C = LETTER ZA>LETTER JA
"\uE05D>\u0C22;"+ // REMAP (indicExceptions.txt): \u0C5D>\u0C22 = LETTER RHA>LETTER DDHA
"\uE05E>\u0C2B;"+ // REMAP (indicExceptions.txt): \u0C5E>\u0C2B = LETTER FA>LETTER PHA
"\uE05F>\u0C2F;"+ // REMAP (indicExceptions.txt): \u0C5F>\u0C2F = LETTER YYA>LETTER YA
"\uE060>\u0C60;"+ // LETTER VOCALIC RR
"\uE061>\u0C61;"+ // LETTER VOCALIC LL
"\uE062>\u0C3F;"+ // REMAP (indicExceptions.txt): \u0C62>\u0C3F = VOWEL SIGN VOCALIC L>VOWEL SIGN I
"\uE063>\u0C40;"+ // REMAP (indicExceptions.txt): \u0C63>\u0C40 = VOWEL SIGN VOCALIC LL>VOWEL SIGN II
"\uE066>\u0C66;"+ // DIGIT ZERO
"\uE067>\u0C67;"+ // DIGIT ONE
"\uE068>\u0C68;"+ // DIGIT TWO
"\uE069>\u0C69;"+ // DIGIT THREE
"\uE06A>\u0C6A;"+ // DIGIT FOUR
"\uE06B>\u0C6B;"+ // DIGIT FIVE
"\uE06C>\u0C6C;"+ // DIGIT SIX
"\uE06D>\u0C6D;"+ // DIGIT SEVEN
"\uE06E>\u0C6E;"+ // DIGIT EIGHT
"\uE06F>\u0C6F;"+ // DIGIT NINE
// \uE080>; // UNMAPPED InterIndic-Telugu: ISSHAR
"\uE081>\u0C0E;"+ // LETTER E
"\uE082>\u0C12;"+ // LETTER O
"\uE083>\u0C31;"+ // LETTER RRA
"\uE084>\u0C46;"+ // VOWEL SIGN E
"\uE085>\u0C4A;"+ // VOWEL SIGN O
""
}
};
}
}

6374
icu4j/src/com/ibm/text/resources/TransliterationRule_Kanji_English.java
View File

File diff suppressed because it is too large Load Diff

6225
icu4j/src/com/ibm/text/resources/TransliterationRule_Kanji_OnRomaji.java
View File

File diff suppressed because it is too large Load Diff

106
icu4j/src/com/ibm/text/resources/TransliterationRule_Kannada_InterIndic.java
View File

@ -1,106 +0,0 @@
/***********************************************************************
* Copyright (c) 2000, International Business Machines Corporation
* and others. All Rights Reserved.
************************************************************************
* > THIS FILE WAS MACHINE GENERATED <
* > DO NOT EDIT BY HAND <
* > RUN TOOL TO REGENERATE <
* Tool: icu4j/src/com/ibm/tools/translit/indic.pl
* Creation date: Fri Oct 6 15:55:21 2000
*/
package com.ibm.text.resources;
import java.util.ListResourceBundle;
public class TransliterationRule_Kannada_InterIndic extends ListResourceBundle {
/**
* Overrides ListResourceBundle
*/
public Object[][] getContents() {
return new Object[][] {
{ "Rule",
"\u0C82>\uE002;"+ // SIGN ANUSVARA
"\u0C83>\uE003;"+ // SIGN VISARGA
"\u0C85>\uE005;"+ // LETTER A
"\u0C86>\uE006;"+ // LETTER AA
"\u0C87>\uE007;"+ // LETTER I
"\u0C88>\uE008;"+ // LETTER II
"\u0C89>\uE009;"+ // LETTER U
"\u0C8A>\uE00A;"+ // LETTER UU
"\u0C8B>\uE00B;"+ // LETTER VOCALIC R
"\u0C8C>\uE00C;"+ // LETTER VOCALIC L
"\u0C8E>\uE081;"+ // LETTER E
"\u0C8F>\uE00F;"+ // LETTER EE
"\u0C90>\uE010;"+ // LETTER AI
"\u0C92>\uE082;"+ // LETTER O
"\u0C93>\uE013;"+ // LETTER OO
"\u0C94>\uE014;"+ // LETTER AU
"\u0C95>\uE015;"+ // LETTER KA
"\u0C96>\uE016;"+ // LETTER KHA
"\u0C97>\uE017;"+ // LETTER GA
"\u0C98>\uE018;"+ // LETTER GHA
"\u0C99>\uE019;"+ // LETTER NGA
"\u0C9A>\uE01A;"+ // LETTER CA
"\u0C9B>\uE01B;"+ // LETTER CHA
"\u0C9C>\uE01C;"+ // LETTER JA
"\u0C9D>\uE01D;"+ // LETTER JHA
"\u0C9E>\uE01E;"+ // LETTER NYA
"\u0C9F>\uE01F;"+ // LETTER TTA
"\u0CA0>\uE020;"+ // LETTER TTHA
"\u0CA1>\uE021;"+ // LETTER DDA
"\u0CA2>\uE022;"+ // LETTER DDHA
"\u0CA3>\uE023;"+ // LETTER NNA
"\u0CA4>\uE024;"+ // LETTER TA
"\u0CA5>\uE025;"+ // LETTER THA
"\u0CA6>\uE026;"+ // LETTER DA
"\u0CA7>\uE027;"+ // LETTER DHA
"\u0CA8>\uE028;"+ // LETTER NA
"\u0CAA>\uE02A;"+ // LETTER PA
"\u0CAB>\uE02B;"+ // LETTER PHA
"\u0CAC>\uE02C;"+ // LETTER BA
"\u0CAD>\uE02D;"+ // LETTER BHA
"\u0CAE>\uE02E;"+ // LETTER MA
"\u0CAF>\uE02F;"+ // LETTER YA
"\u0CB0>\uE030;"+ // LETTER RA
"\u0CB1>\uE083;"+ // LETTER RRA
"\u0CB2>\uE032;"+ // LETTER LA
"\u0CB3>\uE033;"+ // LETTER LLA
"\u0CB5>\uE035;"+ // LETTER VA
"\u0CB6>\uE036;"+ // LETTER SHA
"\u0CB7>\uE037;"+ // LETTER SSA
"\u0CB8>\uE038;"+ // LETTER SA
"\u0CB9>\uE039;"+ // LETTER HA
"\u0CBE>\uE03E;"+ // VOWEL SIGN AA
"\u0CBF>\uE03F;"+ // VOWEL SIGN I
"\u0CC0>\uE040;"+ // VOWEL SIGN II
"\u0CC1>\uE041;"+ // VOWEL SIGN U
"\u0CC2>\uE042;"+ // VOWEL SIGN UU
"\u0CC3>\uE043;"+ // VOWEL SIGN VOCALIC R
"\u0CC4>\uE044;"+ // VOWEL SIGN VOCALIC RR
"\u0CC6>\uE084;"+ // VOWEL SIGN E
"\u0CC7>\uE047;"+ // VOWEL SIGN EE
"\u0CC8>\uE048;"+ // VOWEL SIGN AI
"\u0CCA>\uE085;"+ // VOWEL SIGN O
"\u0CCB>\uE04B;"+ // VOWEL SIGN OO
"\u0CCC>\uE04C;"+ // VOWEL SIGN AU
"\u0CCD>\uE04D;"+ // SIGN VIRAMA
"\u0CD5>\uE055;"+ // LENGTH MARK
"\u0CD6>\uE056;"+ // AI LENGTH MARK
"\u0CDE>\uE05E;"+ // LETTER FA
"\u0CE0>\uE060;"+ // LETTER VOCALIC RR
"\u0CE1>\uE061;"+ // LETTER VOCALIC LL
"\u0CE6>\uE066;"+ // DIGIT ZERO
"\u0CE7>\uE067;"+ // DIGIT ONE
"\u0CE8>\uE068;"+ // DIGIT TWO
"\u0CE9>\uE069;"+ // DIGIT THREE
"\u0CEA>\uE06A;"+ // DIGIT FOUR
"\u0CEB>\uE06B;"+ // DIGIT FIVE
"\u0CEC>\uE06C;"+ // DIGIT SIX
"\u0CED>\uE06D;"+ // DIGIT SEVEN
"\u0CEE>\uE06E;"+ // DIGIT EIGHT
"\u0CEF>\uE06F;"+ // DIGIT NINE
""
}
};
}
}

141
icu4j/src/com/ibm/text/resources/TransliterationRule_KeyboardEscape_Latin1.java
View File

@ -1,141 +0,0 @@
/*
*******************************************************************************
* Copyright (C) 1996-2000, International Business Machines Corporation and *
* others. All Rights Reserved. *
*******************************************************************************
*
* $Source: /xsrl/Nsvn/icu/icu4j/src/com/ibm/text/resources/Attic/TransliterationRule_KeyboardEscape_Latin1.java,v $
* $Date: 2000/04/22 00:04:25 $
* $Revision: 1.4 $
*
*****************************************************************************************
*/
package com.ibm.text.resources;
import java.util.ListResourceBundle;
public class TransliterationRule_KeyboardEscape_Latin1 extends ListResourceBundle {
/**
* Overrides ListResourceBundle
*/
public Object[][] getContents() {
return new Object[][] {
{ "Rule",
"$esc='';"
+ "$grave='`';"
+ "$acute='';"
+ "$hat='^';"
+ "$tilde='~';"
+ "$umlaut=':';"
+ "$ring='.';"
+ "$cedilla=',';"
+ "$slash='/';"
+ "$super='^';"
// Make keyboard entry of {esc} possible
// and of backslash
+ "'\\'$esc>$esc;"
+ "'\\\\'>'\\';"
// Long keys
+ "cur$esc>\u00A4;"
+ "sec$esc>\u00A7;"
+ "not$esc>\u00AC;"
+ "mul$esc>\u00D7;"
+ "div$esc>\u00F7;"
+ "\\ $esc>\u00A0;" // non-breaking space
+ "'!'$esc>\u00A1;" // inverted exclamation
+ "c'/'$esc>\u00A2;" // cent sign
+ "lb$esc>\u00A3;" // pound sign
+ "'|'$esc>\u00A6;" // broken vertical bar
+ "':'$esc>\u00A8;" // umlaut
+ "$super a$esc>\u00AA;" // feminine ordinal
+ "'<<'$esc>\u00AB;"
+ "r$esc>\u00AE;"
+ "'--'$esc>\u00AF;"
+ "'-'$esc>\u00AD;"
+ "'+-'$esc>\u00B1;"
+ "$super 2$esc>\u00B2;"
+ "$super 3$esc>\u00B3;"
+ "$acute$esc>\u00B4;"
+ "m$esc>\u00B5;"
+ "para$esc>\u00B6;"
+ "dot$esc>\u00B7;"
+ "$cedilla$esc>\u00B8;"
+ "$super 1$esc>\u00B9;"
+ "$super o$esc>\u00BA;" // masculine ordinal
+ "'>>'$esc>\u00BB;"
+ "'1/4'$esc>\u00BC;"
+ "'1/2'$esc>\u00BD;"
+ "'3/4'$esc>\u00BE;"
+ "'?'$esc>\u00BF;"
+ "A$grave$esc>\u00C0;"
+ "A$acute$esc>\u00C1;"
+ "A$hat$esc>\u00C2;"
+ "A$tilde$esc>\u00C3;"
+ "A$umlaut$esc>\u00C4;"
+ "A$ring$esc>\u00C5;"
+ "AE$esc>\u00C6;"
+ "C$cedilla$esc>\u00C7;"
+ "E$grave$esc>\u00C8;"
+ "E$acute$esc>\u00C9;"
+ "E$hat$esc>\u00CA;"
+ "E$umlaut$esc>\u00CB;"
+ "I$grave$esc>\u00CC;"
+ "I$acute$esc>\u00CD;"
+ "I$hat$esc>\u00CE;"
+ "I$umlaut$esc>\u00CF;"
+ "'D-'$esc>\u00D0;"
+ "N$tilde$esc>\u00D1;"
+ "O$grave$esc>\u00D2;"
+ "O$acute$esc>\u00D3;"
+ "O$hat$esc>\u00D4;"
+ "O$tilde$esc>\u00D5;"
+ "O$umlaut$esc>\u00D6;"
+ "O$slash$esc>\u00D8;"
+ "U$grave$esc>\u00D9;"
+ "U$acute$esc>\u00DA;"
+ "U$hat$esc>\u00DB;"
+ "U$umlaut$esc>\u00DC;"
+ "Y$acute$esc>\u00DD;"
+ "TH$esc>\u00DE;"
+ "ss$esc>\u00DF;"
+ "a$grave$esc>\u00E0;"
+ "a$acute$esc>\u00E1;"
+ "a$hat$esc>\u00E2;"
+ "a$tilde$esc>\u00E3;"
+ "a$umlaut$esc>\u00E4;"
+ "a$ring$esc>\u00E5;"
+ "ae$esc>\u00E6;"
+ "c$cedilla$esc>\u00E7;"
+ "c$esc>\u00A9;" // copyright - after c{cedilla}
+ "e$grave$esc>\u00E8;"
+ "e$acute$esc>\u00E9;"
+ "e$hat$esc>\u00EA;"
+ "e$umlaut$esc>\u00EB;"
+ "i$grave$esc>\u00EC;"
+ "i$acute$esc>\u00ED;"
+ "i$hat$esc>\u00EE;"
+ "i$umlaut$esc>\u00EF;"
+ "'d-'$esc>\u00F0;"
+ "n$tilde$esc>\u00F1;"
+ "o$grave$esc>\u00F2;"
+ "o$acute$esc>\u00F3;"
+ "o$hat$esc>\u00F4;"
+ "o$tilde$esc>\u00F5;"
+ "o$umlaut$esc>\u00F6;"
+ "o$slash$esc>\u00F8;"
+ "o$esc>\u00B0;"
+ "u$grave$esc>\u00F9;"
+ "u$acute$esc>\u00FA;"
+ "u$hat$esc>\u00FB;"
+ "u$umlaut$esc>\u00FC;"
+ "y$acute$esc>\u00FD;"
+ "y$esc>\u00A5;" // yen sign
+ "th$esc>\u00FE;"
//masked: + "ss$esc>\u00FF;"
}
};
}
}

207
icu4j/src/com/ibm/text/resources/TransliterationRule_Latin_Arabic.java
View File

@ -1,207 +0,0 @@
/*
*******************************************************************************
* Copyright (C) 1996-2000, International Business Machines Corporation and *
* others. All Rights Reserved. *
*******************************************************************************
*
* $Source: /xsrl/Nsvn/icu/icu4j/src/com/ibm/text/resources/Attic/TransliterationRule_Latin_Arabic.java,v $
* $Date: 2000/07/05 23:43:32 $
* $Revision: 1.7 $
*
*****************************************************************************************
*/
package com.ibm.text.resources;
import java.util.ListResourceBundle;
public class TransliterationRule_Latin_Arabic extends ListResourceBundle {
/**
* Overrides ListResourceBundle
*/
public Object[][] getContents() {
return new Object[][] {
{ "Rule",
// To Do: finish adding shadda, add sokoon
// [Is this done? Can someone finish this?]
"$alefmadda=\u0622;"+
"$alefuhamza=\u0623;"+
"$wauuhamza=\u0624;"+
"$alefhamza=\u0625;"+
"$yehuhamza=\u0626;"+
"$alef=\u0627;"+
"$beh=\u0628;"+
"$tehmarbuta=\u0629;"+
"$teh=\u062A;"+
"$theh=\u062B;"+
"$geem=\u062C;"+
"$hah=\u062D;"+
"$kha=\u062E;"+
"$dal=\u062F;"+
"$dhal=\u0630;"+
"$reh=\u0631;"+
"$zain=\u0632;"+
"$seen=\u0633;"+
"$sheen=\u0634;"+
"$sad=\u0635;"+
"$dad=\u0636;"+
"$tah=\u0637;"+
"$zah=\u0638;"+
"$ein=\u0639;"+
"$ghein=\u063A;"+
"$feh=\u0641;"+
"$qaaf=\u0642;"+
"$kaf=\u0643;"+
"$lam=\u0644;"+
"$meem=\u0645;"+
"$noon=\u0646;"+
"$heh=\u0647;"+
"$wau=\u0648;"+
"$yehmaqsura=\u0649;"+
"$yeh=\u064A;"+
"$peh=\u06A4;"+
"$hamza=\u0621;"+
"$fathatein=\u064B;"+
"$dammatein=\u064C;"+
"$kasratein=\u064D;"+
"$fatha=\u064E;"+
"$damma=\u064F;"+
"$kasra=\u0650;"+
"$shadda=\u0651;"+
"$sokoon=\u0652;"+
// Doubles - liu
"t'' < {$teh} [$teh$theh$tehmarbuta$tah];" +
"h'' < {$heh} [$heh$hah];"+
"s'' < {$seen} $sheen;"+
// A few pathological special cases to make round
// trip work. - liu
"d'~'d <> $dal $dal;"+
"dh'~'dh <> $dhal $dhal;"+
"dd'~'dd <> $dad $dad;"+
// Shadda: Map x $shadda to x x, where x is dh, dd, or
// d (that is, $dhal, $dad, or $dal). If x is d, d'd is
// output. Net effect is to map s.th. like $dad $shadda
// to dd'dd. - liu
"$dhal {dh} <> dh {$shadda};"+
"$dad {dd} <> dd {$shadda};"+
"$dal {''d} [^dh] <> d {$shadda};"+ // Avoid d'dd or d'dh
// [This should be removed, but it's good for demos]
"Arabic>"+
"\u062a\u062a\u0645\u062a\u0639' '"+
"\u0627\u0644\u0644\u063a\u0629' '"+
"\u0627\u0644\u0639\u0631\u0628\u0628\u064a\u0629' '"+
"\u0628\u0628\u0646\u0638\u0645' '"+
"\u0643\u062a\u0627\u0628\u0628\u064a\u0629' '"+
"\u062c\u0645\u064a\u0644\u0629;"+
// Main rules
"''ai<a{$alefmadda;"+
"ai<>$alefmadda;"+
"''ae<a{$alefuhamza;"+
"ae<>$alefuhamza;"+
"''ao<a{$alefhamza;"+
"ao<>$alefhamza;"+
"''aa<a{$alef;"+
"aa<>$alef;"+
"''an<a{$fathatein;"+
"an<>$fathatein;"+
"''a<a{$fatha;"+
"a<>$fatha;"+
"b<>$beh;"+
"''dh<d{$dhal;"+
"dh<>$dhal;"+
"''dd<d{$dad;"+
"dd<>$dad;"+
"''d<d{$dal;"+
"d<>$dal;"+
"''e<a{$ein;"+
"''e<w{$ein;"+
"''e<y{$ein;"+
"e<>$ein;"+
"f<>$feh;"+
"gh<>$ghein;"+
"''hh<d{$hah;"+
"''hh<t{$hah;"+
"''hh<k{$hah;"+
"''hh<s{$hah;"+
"hh<>$hah;"+
"''h<d{$heh;"+
"''h<t{$heh;"+
"''h<k{$heh;"+
"''h<s{$heh;"+
"h<>$heh;"+
"''ii<i{$kasratein;"+
"ii<>$kasratein;"+
"''i<i{$kasra;"+
"i<>$kasra;"+
"j<>$geem;"+
"kh<>$kha;"+
"k<>$kaf;"+
"l<>$lam;"+
"''m<y{$meem;"+
"''m<t{$meem;"+
"m<>$meem;"+
"n<>$noon;"+
"''o<a{$hamza;"+
"o<>$hamza;"+
"p<>$peh;"+
"q<>$qaaf;"+
"r<>$reh;"+
"sh<>$sheen;"+
"''ss<s{$sad;"+
"ss<>$sad;"+
"''s<s{$seen;"+
"s<>$seen;"+
"th<>$theh;"+
"tm<>$tehmarbuta;"+
"''tt<t{$tah;"+
"tt<>$tah;"+
"''t<t{$teh;"+
"t<>$teh;"+
"''uu<u{$dammatein;"+
"uu<>$dammatein;"+
"''u<u{$damma;"+
"u<>$damma;"+
"we<>$wauuhamza;"+
"w<>$wau;"+
"ye<>$yehuhamza;"+
"ym<>$yehmaqsura;"+
"''y<y{$yeh;"+
"y<>$yeh;"+
"''zz<z{$zah;"+
"zz<>$zah;"+
"''z<z{$zain;"+
"z<>$zain;"+
// One-way Latin-Arabic compatability rules
"c>$kaf;"+
"g>$geem;"+
"x>$kaf$shadda$seen;"+
"v>$beh;"+
// Digits
"0<>\u0660;"+ // Arabic digit 0
"1<>\u0661;"+ // Arabic digit 1
"2<>\u0662;"+ // Arabic digit 2
"3<>\u0663;"+ // Arabic digit 3
"4<>\u0664;"+ // Arabic digit 4
"5<>\u0665;"+ // Arabic digit 5
"6<>\u0666;"+ // Arabic digit 6
"7<>\u0667;"+ // Arabic digit 7
"8<>\u0668;"+ // Arabic digit 8
"9<>\u0669;"+ // Arabic digit 9
"'%'<>\u066A;"+ // Arabic %
"'.'<>\u066B;"+ // Arabic decimal separator
"','<>\u066C;"+ // Arabic thousands separator
"'*'<>\u066D;"+ // Arabic five-pointed star
"''>;"
}
};
}
}

323
icu4j/src/com/ibm/text/resources/TransliterationRule_Latin_Cyrillic.java
View File

@ -1,323 +0,0 @@
/*
*******************************************************************************
* Copyright (C) 1996-2000, International Business Machines Corporation and *
* others. All Rights Reserved. *
*******************************************************************************
*
* $Source: /xsrl/Nsvn/icu/icu4j/src/com/ibm/text/resources/Attic/TransliterationRule_Latin_Cyrillic.java,v $
* $Date: 2000/07/05 23:07:58 $
* $Revision: 1.6 $
*
*****************************************************************************************
*/
package com.ibm.text.resources;
import java.util.ListResourceBundle;
public class TransliterationRule_Latin_Cyrillic extends ListResourceBundle {
/**
* Overrides ListResourceBundle
*/
public Object[][] getContents() {
return new Object[][] {
{ "Rule", ""
// This class is designed to be a general Latin-Cyrillic
// transliteration. The standard Russian transliterations
// are generally used for the letters from Russian,
// with additional Cyrillic characters given consistent
// mappings.
+ "$S_hacek=\u0160;"
+ "$s_hacek=\u0161;"
+ "$YO=\u0401;"
+ "$J=\u0408;"
+ "$A=\u0410;"
+ "$B=\u0411;"
+ "$V=\u0412;"
+ "$G=\u0413;"
+ "$D=\u0414;"
+ "$YE=\u0415;"
+ "$ZH=\u0416;"
+ "$Z=\u0417;"
+ "$YI=\u0418;"
+ "$Y=\u0419;"
+ "$K=\u041A;"
+ "$L=\u041B;"
+ "$M=\u041C;"
+ "$N=\u041D;"
+ "$O=\u041E;"
+ "$P=\u041F;"
+ "$R=\u0420;"
+ "$S=\u0421;"
+ "$T=\u0422;"
+ "$U=\u0423;"
+ "$F=\u0424;"
+ "$KH=\u0425;"
+ "$TS=\u0426;"
+ "$CH=\u0427;"
+ "$SH=\u0428;"
+ "$SHCH=\u0429;"
+ "$HARD=\u042A;"
+ "$I=\u042B;"
+ "$SOFT=\u042C;"
+ "$E=\u042D;"
+ "$YU=\u042E;"
+ "$YA=\u042F;"
// Lowercase
+ "$a=\u0430;"
+ "$b=\u0431;"
+ "$v=\u0432;"
+ "$g=\u0433;"
+ "$d=\u0434;"
+ "$ye=\u0435;"
+ "$zh=\u0436;"
+ "$z=\u0437;"
+ "$yi=\u0438;"
+ "$y=\u0439;"
+ "$k=\u043a;"
+ "$l=\u043b;"
+ "$m=\u043c;"
+ "$n=\u043d;"
+ "$o=\u043e;"
+ "$p=\u043f;"
+ "$r=\u0440;"
+ "$s=\u0441;"
+ "$t=\u0442;"
+ "$u=\u0443;"
+ "$f=\u0444;"
+ "$kh=\u0445;"
+ "$ts=\u0446;"
+ "$ch=\u0447;"
+ "$sh=\u0448;"
+ "$shch=\u0449;"
+ "$hard=\u044a;"
+ "$i=\u044b;"
+ "$soft=\u044c;"
+ "$e=\u044d;"
+ "$yu=\u044e;"
+ "$ya=\u044f;"
+ "$yo=\u0451;"
+ "$j=\u0458;"
// variables
// some are duplicated so lowercasing works
+ "$csoft=[eiyEIY];"
+ "$CSOFT=[eiyEIY];"
+ "$BECOMES_H=[$HARD$hard];"
+ "$becomes_h=[$HARD$hard];"
+ "$BECOMES_S=[$S$s];"
+ "$becomes_s=[$S$s];"
+ "$BECOMES_C=[$CH$ch];"
+ "$becomes_c=[$CH$ch];"
+ "$BECOMES_VOWEL=[$A$E$I$O$U$a$e$i$o$u];"
+ "$becomes_vowel=[$A$E$I$O$U$a$e$i$o$u];"
+ "$letter=[[:Lu:][:Ll:]];"
+ "$lower=[[:Ll:]];"
// Modified to combine display transliterator and typing transliterator.
// The display mapping uses accents for the "soft" vowels.
// It does not, although it could, use characters like \u0161 instead of digraphs
// like sh.
// #############################################
// Special titlecase forms, not duplicated
// #############################################
+ "Sh''ch<>$SH$ch;" // LIU Distinguish $SH$ch from $SHCH
+ "Ch <> {$CH} $lower;"
+ "Kh <> {$KH} $lower;"
+ "Shch <> {$SHCH}$lower;"
+ "Sh <> {$SH} $lower;"
+ "Ts <> {$TS} $lower;"
+ "Zh <> {$ZH} $lower;"
+ "Yi>$YI;"
+ "Ye>$YE;"
+ "Yo>$YO;"
+ "Yu>$YU;"
+ "Ya>$YA;"
// #############################################
// Rules to Duplicate
// To get the lowercase versions, copy these and lowercase
// #############################################
// variant spellings in English
+ "SHTCH>$SHCH;"
+ "TCH>$CH;"
+ "TH>$Z;"
+ "Q>$K;"
+ "WH>$V;"
+ "W>$V;"
+ "X>$K$S;" //+ "X<$K$S;"
// Separate letters that would otherwise join
+ "SH''<$SH}$BECOMES_C;"
+ "T''<$T}$BECOMES_S;"
+ "T''<$T}[$CH$SHCH$shch];" // LIU add special cases
+ "K''<$K}$BECOMES_H;"
+ "S''<$S}$BECOMES_H;"
+ "T''<$T}$BECOMES_H;"
+ "Z''<$Z}$BECOMES_H;"
+ "Y''<$Y}$BECOMES_VOWEL;"
// Main letters
+ "A<>$A;"
+ "B<>$B;"
+ "CH<>$CH;"
+ "D<>$D;"
+ "E<>$E;"
+ "F<>$F;"
+ "G<>$G;"
+ "\u00cc<>$YI;"
+ "I<>$I;"
+ "KH<>$KH;"
+ "K<>$K;"
+ "L<>$L;"
+ "M<>$M;"
+ "N<>$N;"
+ "O<>$O;"
+ "P<>$P;"
+ "R<>$R;"
+ "SHCH<>$SHCH;"
+ "SH>$SH;" //+ "SH<$SH;"
+ "$S_hacek<>$SH;"
+ "S<>$S;"
+ "TS<>$TS;"
+ "T<>$T;"
+ "U<>$U;"
+ "V<>$V;"
//\u00cc\u00c0\u00c8\u00d2\u00d9
+ "YE>$YE;" //+ "YE<$YE;"
+ "\u00c8<>$YE;"
+ "YO>$YO;" //+ "YO<$YO;"
+ "\u00d2<>$YO;"
+ "YU>$YU;" //+ "YU<$YU;"
+ "\u00d9<>$YU;"
+ "YA>$YA;" //+ "YA<$YA;"
+ "\u00c0<>$YA;"
+ "Y<>$Y;"
+ "ZH<>$ZH;"
+ "Z<>$Z;"
+ "H<>$HARD;"
+ "\u0178<>$SOFT;"
// Non-russian
+ "J<>$J;"
// variant spellings in English
+ "C}$csoft>$S;"
+ "C>$K;"
// #############################################
// Duplicated Rules
// Copy and lowercase the above rules
// #############################################
// variant spellings in english
+ "shtch>$shch;"
+ "tch>$ch;"
+ "th>$z;"
+ "q>$k;"
+ "wh>$v;"
+ "w>$v;"
+ "x>$k$s;" //+ "x<$k$s;"
// separate letters that would otherwise join
+ "sh''<$sh}$becomes_c;"
+ "t''<$t}$becomes_s;"
+ "t''<$t}[$ch$shch];" // LIU add special cases
+ "k''<$k}$becomes_h;"
+ "s''<$s}$becomes_h;"
+ "t''<$t}$becomes_h;"
+ "z''<$z}$becomes_h;"
+ "y''<$y}$becomes_vowel;"
// main letters
+ "a<>$a;"
+ "b<>$b;"
+ "ch<>$ch;"
+ "d<>$d;"
+ "e<>$e;"
+ "f<>$f;"
+ "g<>$g;"
+ "\u00ec<>$yi;"
+ "i<>$i;"
+ "kh<>$kh;"
+ "k<>$k;"
+ "l<>$l;"
+ "m<>$m;"
+ "n<>$n;"
+ "o<>$o;"
+ "p<>$p;"
+ "r<>$r;"
+ "shch<>$shch;"
+ "sh>$sh;" //+ "sh<$sh;"
+ "$s_hacek<>$sh;"
+ "s<>$s;"
+ "ts<>$ts;"
+ "t<>$t;"
+ "u<>$u;"
+ "v<>$v;"
//\u00ec\u00e0\u00e8\u00f2\u00f9
+ "ye>$ye;" //+ "ye<$ye;"
+ "\u00e8<>$ye;"
+ "yo>$yo;" //+ "yo<$yo;"
+ "\u00f2<>$yo;"
+ "yu>$yu;" //+ "yu<$yu;"
+ "\u00f9<>$yu;"
+ "ya>$ya;" //+ "ya<$ya;"
+ "\u00e0<>$ya;"
+ "y<>$y;"
+ "zh<>$zh;"
+ "z<>$z;"
+ "h<>$hard;"
+ "\u00ff<>$soft;"
// non-russian
+ "j<>$j;"
// variant spellings in english
+ "c}$csoft>$s;"
+ "c>$k;"
// #############################################
// End of Duplicated Rules
// #############################################
//generally the last rule
+ "''>;"
//the end
}
};
}
}

422
icu4j/src/com/ibm/text/resources/TransliterationRule_Latin_Devanagari.java
View File

@ -1,422 +0,0 @@
/*
*******************************************************************************
* Copyright (C) 1996-2000, International Business Machines Corporation and *
* others. All Rights Reserved. *
*******************************************************************************
*
* $Source: /xsrl/Nsvn/icu/icu4j/src/com/ibm/text/resources/Attic/TransliterationRule_Latin_Devanagari.java,v $
* $Date: 2000/04/22 00:04:25 $
* $Revision: 1.4 $
*
*****************************************************************************************
*/
package com.ibm.text.resources;
import java.util.ListResourceBundle;
public class TransliterationRule_Latin_Devanagari extends ListResourceBundle {
/**
* Overrides ListResourceBundle
*/
public Object[][] getContents() {
return new Object[][] {
{ "Rule",
//#####################################################################
// Keyboard Transliteration Table
//#####################################################################
// Conversions should be:
// 1. complete
// * convert every sequence of Latin letters (a to z plus apostrophe)
// to a sequence of Native letters
// * convert every sequence of Native letters to Latin letters
// 2. reversable
// * any string of Native converted to Latin and back should be the same
// * this is not true for English converted to Native & back, e.g.:
// k -> {kaf} -> k
// c -> {kaf} -> k
//#####################################################################
// Sequences of Latin letters may convert to a single Native letter.
// When this is the case, an apostrophe can be used to indicate separate
// letters.$
// E.g. sh -> {shin}
// s'h -> {sin}{heh}
// ss -> {sad}
// s's -> {sin}{shadda}
//#####################################################################
// To Do:
// finish adding shadda, add sokoon, fix uppercase
// make two transliteration tables: one with vowels, one without
//#####################################################################
// Modifications
// Devanagari Transliterator: broken up with consonsants/vowels
//#####################################################################
// Unicode character name definitions
//#####################################################################
//consonants
"$candrabindu=\u0901;"
+ "$bindu=\u0902;"
+ "$visarga=\u0903;"
// w<vowel> represents the stand-alone form
+ "$wa=\u0905;"
+ "$waa=\u0906;"
+ "$wi=\u0907;"
+ "$wii=\u0908;"
+ "$wu=\u0909;"
+ "$wuu=\u090A;"
+ "$wr=\u090B;"
+ "$wl=\u090C;"
+ "$we=\u090F;"
+ "$wai=\u0910;"
+ "$wo=\u0913;"
+ "$wau=\u0914;"
+ "$ka=\u0915;"
+ "$kha=\u0916;"
+ "$ga=\u0917;"
+ "$gha=\u0918;"
+ "$nga=\u0919;"
+ "$ca=\u091A;"
+ "$cha=\u091B;"
+ "$ja=\u091C;"
+ "$jha=\u091D;"
+ "$nya=\u091E;"
+ "$tta=\u091F;"
+ "$ttha=\u0920;"
+ "$dda=\u0921;"
+ "$ddha=\u0922;"
+ "$nna=\u0923;"
+ "$ta=\u0924;"
+ "$tha=\u0925;"
+ "$da=\u0926;"
+ "$dha=\u0927;"
+ "$na=\u0928;"
+ "$pa=\u092A;"
+ "$pha=\u092B;"
+ "$ba=\u092C;"
+ "$bha=\u092D;"
+ "$ma=\u092E;"
+ "$ya=\u092F;"
+ "$ra=\u0930;"
+ "$rra=\u0931;"
+ "$la=\u0933;"
+ "$va=\u0935;"
+ "$sha=\u0936;"
+ "$ssa=\u0937;"
+ "$sa=\u0938;"
+ "$ha=\u0939;"
// <vowel> represents the dependent form
+ "$aa=\u093E;"
+ "$i=\u093F;"
+ "$ii=\u0940;"
+ "$u=\u0941;"
+ "$uu=\u0942;"
+ "$rh=\u0943;"
+ "$lh=\u0944;"
+ "$e=\u0947;"
+ "$ai=\u0948;"
+ "$o=\u094B;"
+ "$au=\u094C;"
+ "$virama=\u094D;"
+ "$wrr=\u0960;"
+ "$rrh=\u0962;"
+ "$danda=\u0964;"
+ "$doubleDanda=\u0965;"
+ "$depVowelAbove=[\u093E-\u0940\u0945-\u094C];"
+ "$depVowelBelow=[\u0941-\u0944];"
+ "$endThing=[$danda$doubleDanda \u0000-\u08FF\u0980-\uFFFF];"
// $x was originally called '&'; $z was '%'
+ "$x=[$virama$aa$ai$au$ii$i$uu$u$rrh$rh$lh$e$o];"
+ "$z=[bcdfghjklmnpqrstvwxyz];"
//#####################################################################
// convert from Latin letters to Native letters
//#####################################################################
//Hindi>\u092d\u093e\u0930\u0924--\u0020\u0926\u0947\u0936\u0020\u092c\u0928\u094d\u0927\u0941\u002e
// special forms with no good conversion
+ "mm>$bindu;"
+ "x>$visarga;"
// convert to independent forms at start of word or syllable:
// e.g. keai -> {ka}{e}{wai}; k'ai -> {ka}{wai}; (ai) -> ({wai})
// Moved up [LIU]
+ "aa>$waa;"
+ "ai>$wai;"
+ "au>$wau;"
+ "ii>$wii;"
+ "i>$wi;"
+ "uu>$wuu;"
+ "u>$wu;"
+ "rrh>$wrr;"
+ "rh>$wr;"
+ "lh>$wl;"
+ "e>$we;"
+ "o>$wo;"
+ "a>$wa;"
// normal consonants
+ "kh>$kha|$virama;"
+ "k>$ka|$virama;"
+ "q>$ka|$virama;"
+ "gh>$gha|$virama;"
+ "g>$ga|$virama;"
+ "ng>$nga|$virama;"
+ "ch>$cha|$virama;"
+ "c>$ca|$virama;"
+ "jh>$jha|$virama;"
+ "j>$ja|$virama;"
+ "ny>$nya|$virama;"
+ "tth>$ttha|$virama;"
+ "tt>$tta|$virama;"
+ "ddh>$ddha|$virama;"
+ "dd>$dda|$virama;"
+ "nn>$nna|$virama;"
+ "th>$tha|$virama;"
+ "t>$ta|$virama;"
+ "dh>$dha|$virama;"
+ "d>$da|$virama;"
+ "n>$na|$virama;"
+ "ph>$pha|$virama;"
+ "p>$pa|$virama;"
+ "bh>$bha|$virama;"
+ "b>$ba|$virama;"
+ "m>$ma|$virama;"
+ "y>$ya|$virama;"
+ "r>$ra|$virama;"
+ "l>$la|$virama;"
+ "v>$va|$virama;"
+ "f>$va|$virama;"
+ "w>$va|$virama;"
+ "sh>$sha|$virama;"
+ "ss>$ssa|$virama;"
+ "s>$sa|$virama;"
+ "z>$sa|$virama;"
+ "h>$ha|$virama;"
+ "'.'>$danda;"
+ "$danda'.'>$doubleDanda;"
+ "$depVowelAbove{'~'>$bindu;"
+ "$depVowelBelow{'~'>$candrabindu;"
// convert to dependent forms after consonant with no vowel:
// e.g. kai -> {ka}{virama}ai -> {ka}{ai}
+ "$virama aa>$aa;"
+ "$virama ai>$ai;"
+ "$virama au>$au;"
+ "$virama ii>$ii;"
+ "$virama i>$i;"
+ "$virama uu>$uu;"
+ "$virama u>$u;"
+ "$virama rrh>$rrh;"
+ "$virama rh>$rh;"
+ "$virama lh>$lh;"
+ "$virama e>$e;"
+ "$virama o>$o;"
+ "$virama a>;"
// otherwise convert independent forms when separated by ': k'ai -> {ka}{virama}{wai}
+ "$virama''aa>$waa;"
+ "$virama''ai>$wai;"
+ "$virama''au>$wau;"
+ "$virama''ii>$wii;"
+ "$virama''i>$wi;"
+ "$virama''uu>$wuu;"
+ "$virama''u>$wu;"
+ "$virama''rrh>$wrr;"
+ "$virama''rh>$wr;"
+ "$virama''lh>$wl;"
+ "$virama''e>$we;"
+ "$virama''o>$wo;"
+ "$virama''a>$wa;"
+ "$virama}$endThing>;"
// convert any left-over apostrophes used for separation
+ "''>;"
//#####################################################################
// convert from Native letters to Latin letters
//#####################################################################
// special forms with no good conversion
+ "mm<$bindu;"
+ "x<$visarga;"
// normal consonants
+ "kh<$kha}$x;"
+ "kha<$kha;"
+ "k''<$ka$virama}$ha;"
+ "k<$ka}$x;"
+ "ka<$ka;"
+ "gh<$gha}$x;"
+ "gha<$gha;"
+ "g''<$ga$virama}$ha;"
+ "g<$ga}$x;"
+ "ga<$ga;"
+ "ng<$nga}$x;"
+ "nga<$nga;"
+ "ch<$cha}$x;"
+ "cha<$cha;"
+ "c''<$ca$virama}$ha;"
+ "c<$ca}$x;"
+ "ca<$ca;"
+ "jh<$jha}$x;"
+ "jha<$jha;"
+ "j''<$ja$virama}$ha;"
+ "j<$ja}$x;"
+ "ja<$ja;"
+ "ny<$nya}$x;"
+ "nya<$nya;"
+ "tth<$ttha}$x;"
+ "ttha<$ttha;"
+ "tt''<$tta$virama}$ha;"
+ "tt<$tta}$x;"
+ "tta<$tta;"
+ "ddh<$ddha}$x;"
+ "ddha<$ddha;"
+ "dd''<$dda}$x$ha;"
+ "dd<$dda}$x;"
+ "dda<$dda;"
+ "dh<$dha}$x;"
+ "dha<$dha;"
+ "d''<$da$virama}$ha;"
+ "d''<$da$virama}$ddha;"
+ "d''<$da$virama}$dda;"
+ "d''<$da$virama}$dha;"
+ "d''<$da$virama}$da;"
+ "d<$da}$x;"
+ "da<$da;"
+ "th<$tha}$x;"
+ "tha<$tha;"
+ "t''<$ta$virama}$ha;"
+ "t''<$ta$virama}$ttha;"
+ "t''<$ta$virama}$tta;"
+ "t''<$ta$virama}$tha;"
+ "t''<$ta$virama}$ta;"
+ "t<$ta}$x;"
+ "ta<$ta;"
+ "n''<$na$virama}$ga;"
+ "n''<$na$virama}$ya;"
+ "n<$na}$x;"
+ "na<$na;"
+ "ph<$pha}$x;"
+ "pha<$pha;"
+ "p''<$pa$virama}$ha;"
+ "p<$pa}$x;"
+ "pa<$pa;"
+ "bh<$bha}$x;"
+ "bha<$bha;"
+ "b''<$ba$virama}$ha;"
+ "b<$ba}$x;"
+ "ba<$ba;"
+ "m''<$ma$virama}$ma;"
+ "m''<$ma$virama}$bindu;"
+ "m<$ma}$x;"
+ "ma<$ma;"
+ "y<$ya}$x;"
+ "ya<$ya;"
+ "r''<$ra$virama}$ha;"
+ "r<$ra}$x;"
+ "ra<$ra;"
+ "l''<$la$virama}$ha;"
+ "l<$la}$x;"
+ "la<$la;"
+ "v<$va}$x;"
+ "va<$va;"
+ "sh<$sha}$x;"
+ "sha<$sha;"
+ "ss<$ssa}$x;"
+ "ssa<$ssa;"
+ "s''<$sa$virama}$ha;"
+ "s''<$sa$virama}$sha;"
+ "s''<$sa$virama}$ssa;"
+ "s''<$sa$virama}$sa;"
+ "s<$sa}$x;"
+ "sa<$sa;"
+ "h<$ha}$x;"
+ "ha<$ha;"
// dependent vowels (should never occur except following consonants)
+ "aa<$aa;"
+ "ai<$ai;"
+ "au<$au;"
+ "ii<$ii;"
+ "i<$i;"
+ "uu<$uu;"
+ "u<$u;"
+ "rrh<$rrh;"
+ "rh<$rh;"
+ "lh<$lh;"
+ "e<$e;"
+ "o<$o;"
// independent vowels (when following consonants)
+ "''aa<a{$waa;"
+ "''aa<$z{$waa;"
+ "''ai<a{$wai;"
+ "''ai<$z{$wai;"
+ "''au<a{$wau;"
+ "''au<$z{$wau;"
+ "''ii<a{$wii;"
+ "''ii<$z{$wii;"
+ "''i<a{$wi;"
+ "''i<$z{$wi;"
+ "''uu<a{$wuu;"
+ "''uu<$z{$wuu;"
+ "''u<a{$wu;"
+ "''u<$z{$wu;"
+ "''rrh<$z{$wrr;"
+ "''rh<$z{$wr;"
+ "''lh<$z{$wl;"
+ "''e<$z{$we;"
+ "''o<$z{$wo;"
+ "''a<a{$wa;"
+ "''a<$z{$wa;"
// independent vowels (otherwise)
+ "aa<$waa;"
+ "ai<$wai;"
+ "au<$wau;"
+ "ii<$wii;"
+ "i<$wi;"
+ "uu<$wuu;"
+ "u<$wu;"
+ "rrh<$wrr;"
+ "rh<$wr;"
+ "lh<$wl;"
+ "e<$we;"
+ "o<$wo;"
+ "a<$wa;"
// blow away any remaining viramas
+ "<$virama;"
}
};
}
}

391
icu4j/src/com/ibm/text/resources/TransliterationRule_Latin_Greek.java
View File

@ -1,391 +0,0 @@
/*
*******************************************************************************
* Copyright (C) 1996-2000, International Business Machines Corporation and *
* others. All Rights Reserved. *
*******************************************************************************
*
* $Source: /xsrl/Nsvn/icu/icu4j/src/com/ibm/text/resources/Attic/TransliterationRule_Latin_Greek.java,v $
* $Date: 2000/04/22 00:04:25 $
* $Revision: 1.4 $
*
*****************************************************************************************
*/
package com.ibm.text.resources;
import java.util.ListResourceBundle;
public class TransliterationRule_Latin_Greek extends ListResourceBundle {
/**
* Overrides ListResourceBundle
*/
public Object[][] getContents() {
return new Object[][] {
{ "Rule", ""
// ==============================================
// Modern Greek Transliteration Rules
//
// This transliterates modern Greek characters, but using rules
// that are traditional for Ancient Greek, and
// thus more resemble Greek words that have become part
// of English. It differs from the official Greek
// transliteration, which is more phonetic (since
// most modern Greek vowels, for example, have
// degenerated simply to sound like "ee").
//
// There are only a few tricky parts.
// 1. eta and omega don't map directly to Latin vowels,
// so we use a macron on e and o, and some
// other combinations if they are accented.
// 2. The accented, diaeresis i and y are substituted too.
// 3. Some letters use digraphs, like "ph". While typical,
// they need some special handling.
// 4. A gamma before a gamma or a few other letters is
// transliterated as an "n", as in "Anglo"
// 5. An ypsilon after a vowel is a "u", as in
// "Mouseio". Otherwise it is a "y" as in "Physikon"
// 6. The construction of the rules is made simpler by making sure
// that most rules for lowercase letters exactly correspond to the
// rules for uppercase letters, *except* for the case of the letters
// in the rule itself. That way, after modifying the uppercase rules,
// you can just copy, paste, and "set to lowercase" to get
// the rules for lowercase letters!
// ==============================================
// ==============================================
// Variables, used to make the rules more comprehensible
// and for conditionals.
// ==============================================
+ "$quote='\"';"
// Latin Letters
+ "$E_MACRON=\u0112;"
+ "$e_macron=\u0113;"
+ "$O_MACRON=\u014C;"
+ "$o_macron=\u014D;"
+ "$Y_UMLAUT=\u0178;"
+ "$y_umlaut=\u00FF;"
//! // with real accents.
//! + "$E_MACRON_ACUTE=\u0112\u0301;"
//! + "$e_macron_acute=\u0113\u0301;"
//! + "$O_MACRON_ACUTE=\u014C\u0301;"
//! + "$o_macron_acute=\u014D\u0301;"
//! + "$y_umlaut_acute=\u00FF\u0301;"
//! + "$u00ef_acute=\u00ef\u0301;"
//! + "$u00fc_acute=\u00fc\u0301;"
//! //
// single letter equivalents
+ "$E_MACRON_ACUTE=\u00CA;"
+ "$e_macron_acute=\u00EA;"
+ "$O_MACRON_ACUTE=\u00D4;"
+ "$o_macron_acute=\u00F4;"
+ "$y_umlaut_acute=\u0177;"
+ "$u00ef_acute=\u00EE;"
+ "$u00fc_acute=\u00FB;"
// Greek Letters
+ "$ALPHA=\u0391;"
+ "$BETA=\u0392;"
+ "$GAMMA=\u0393;"
+ "$DELTA=\u0394;"
+ "$EPSILON=\u0395;"
+ "$ZETA=\u0396;"
+ "$ETA=\u0397;"
+ "$THETA=\u0398;"
+ "$IOTA=\u0399;"
+ "$KAPPA=\u039A;"
+ "$LAMBDA=\u039B;"
+ "$MU=\u039C;"
+ "$NU=\u039D;"
+ "$XI=\u039E;"
+ "$OMICRON=\u039F;"
+ "$PI=\u03A0;"
+ "$RHO=\u03A1;"
+ "$SIGMA=\u03A3;"
+ "$TAU=\u03A4;"
+ "$YPSILON=\u03A5;"
+ "$PHI=\u03A6;"
+ "$CHI=\u03A7;"
+ "$PSI=\u03A8;"
+ "$OMEGA=\u03A9;"
+ "$ALPHA2=\u0386;"
+ "$EPSILON2=\u0388;"
+ "$ETA2=\u0389;"
+ "$IOTA2=\u038A;"
+ "$OMICRON2=\u038C;"
+ "$YPSILON2=\u038E;"
+ "$OMEGA2=\u038F;"
+ "$IOTA_DIAERESIS=\u03AA;"
+ "$YPSILON_DIAERESIS=\u03AB;"
+ "$alpha=\u03B1;"
+ "$beta=\u03B2;"
+ "$gamma=\u03B3;"
+ "$delta=\u03B4;"
+ "$epsilon=\u03B5;"
+ "$zeta=\u03B6;"
+ "$eta=\u03B7;"
+ "$theta=\u03B8;"
+ "$iota=\u03B9;"
+ "$kappa=\u03BA;"
+ "$lambda=\u03BB;"
+ "$mu=\u03BC;"
+ "$nu=\u03BD;"
+ "$xi=\u03BE;"
+ "$omicron=\u03BF;"
+ "$pi=\u03C0;"
+ "$rho=\u03C1;"
+ "$sigma=\u03C3;"
+ "$tau=\u03C4;"
+ "$ypsilon=\u03C5;"
+ "$phi=\u03C6;"
+ "$chi=\u03C7;"
+ "$psi=\u03C8;"
+ "$omega=\u03C9;"
//forms
+ "$alpha2=\u03AC;"
+ "$epsilon2=\u03AD;"
+ "$eta2=\u03AE;"
+ "$iota2=\u03AF;"
+ "$omicron2=\u03CC;"
+ "$ypsilon2=\u03CD;"
+ "$omega2=\u03CE;"
+ "$iota_diaeresis=\u03CA;"
+ "$ypsilon_diaeresis=\u03CB;"
+ "$iota_diaeresis2=\u0390;"
+ "$ypsilon_diaeresis2=\u03B0;"
+ "$sigma2=\u03C2;"
// Variables for conditional mappings
// Use lowercase for all variable names, to allow cut/paste below.
+ "$letter=[~[:Lu:][:Ll:]];"
+ "$lower=[[:Ll:]];"
+ "$softener=[eiyEIY];"
+ "$vowel=[aeiouAEIOU"
+ "$ALPHA$EPSILON$ETA$IOTA$OMICRON$YPSILON$OMEGA"
+ "$ALPHA2$EPSILON2$ETA2$IOTA2$OMICRON2$YPSILON2$OMEGA2"
+ "$IOTA_DIAERESIS$YPSILON_DIAERESIS"
+ "$alpha$epsilon$eta$iota$omicron$ypsilon$omega"
+ "$alpha2$epsilon2$eta2$iota2$omicron2$ypsilon2$omega2"
+ "$iota_diaeresis$ypsilon_diaeresis"
+ "$iota_diaeresis2$ypsilon_diaeresis2"
+ "];"
+ "$n_gamma=[GKXCgkxc];"
+ "$gamma_n=[$GAMMA$KAPPA$CHI$XI$gamma$kappa$chi$xi];"
+ "$pp=[Pp];"
// ==============================================
// Rules
// ==============================================
// The following are special titlecases, and should
// not be copied when duplicating the lowercase
// ==============================================
+ "Th <> $THETA}$lower;"
+ "Ph <> $PHI}$lower;"
+ "Ch <> $CHI}$lower;"
//masked: + "Ps<$PHI}$lower;"
// Because there is no uppercase forms for final sigma,
// we had to move all the sigma rules up here.
// Remember to insert ' to preserve round trip, for double letters
// don't need to do this for the digraphs with h,
// since it is not created when mapping back from greek
// use special form for s
+ "''S <> $pp{$SIGMA;" // handle PS
+ "S <> $SIGMA;"
// The following are a bit tricky. 's' takes two forms in greek
// final or non final.
// We use ~s to represent the abnormal form: final before letter
// or non-final before non-letter.
// We use 's to separate p and s (otherwise ps is one letter)
// so, we break out the following forms:
+ "''s < $pp{$sigma}$letter;"
+ "s < $sigma}$letter;"
+ "'~'s < $sigma;"
+ "'~'s < $sigma2}$letter;"
+ "''s < $pp{$sigma2;"
+ "s < $sigma2;"
+ "'~'s }$letter>$sigma2;"
+ "'~'s > $sigma;"
+ "''s }$letter>$sigma;"
+ "''s > $sigma2;"
+ "s }$letter>$sigma;"
+ "s > $sigma2;"
// because there are no uppercase forms, had to move these up too.
+ "i$quote'`'>$iota_diaeresis2;"
+ "y$quote'`'>$ypsilon_diaeresis2;"
+ "$u00ef_acute<>$iota_diaeresis2;"
+ "$u00fc_acute<>$vowel{$ypsilon_diaeresis2;"
+ "$y_umlaut_acute<>$ypsilon_diaeresis2;"
// ==============================================
// Uppercase Forms.
// To make lowercase forms, just copy and lowercase below
// ==============================================
// Typing variants, in case the keyboard doesn't have accents
+ "'A`'>$ALPHA2;"
+ "'E`'>$EPSILON2;"
+ "'EE`'>$ETA2;"
+ "EE>$ETA;"
+ "'I`'>$IOTA2;"
+ "'O`'>$OMICRON2;"
+ "'OO`'>$OMEGA2;"
+ "OO>$OMEGA;"
+ "I$quote>$IOTA_DIAERESIS;"
+ "Y$quote>$YPSILON_DIAERESIS;"
// Basic Letters
+ "A<>$ALPHA;"
+ "\u00c1<>$ALPHA2;"
+ "B<>$BETA;"
+ "N }$n_gamma<>$GAMMA}$gamma_n;"
+ "G<>$GAMMA;"
+ "D<>$DELTA;"
+ "''E <> [Ee]{$EPSILON;" // handle EE
+ "E<>$EPSILON;"
+ "\u00c9<>$EPSILON2;"
+ "Z<>$ZETA;"
+ "$E_MACRON_ACUTE<>$ETA2;"
+ "$E_MACRON<>$ETA;"
+ "TH<>$THETA;"
+ "I<>$IOTA;"
+ "\u00cd<>$IOTA2;"
+ "\u00cf<>$IOTA_DIAERESIS;"
+ "K<>$KAPPA;"
+ "L<>$LAMBDA;"
+ "M<>$MU;"
+ "N'' <> $NU}$gamma_n;"
+ "N<>$NU;"
+ "X<>$XI;"
+ "''O <> [Oo]{ $OMICRON;" // handle OO
+ "O<>$OMICRON;"
+ "\u00d3<>$OMICRON2;"
+ "PH<>$PHI;" // needs ordering before P
+ "PS<>$PSI;" // needs ordering before P
+ "P<>$PI;"
+ "R<>$RHO;"
+ "T<>$TAU;"
+ "U <> $vowel{$YPSILON;"
+ "\u00da <> $vowel{$YPSILON2;"
+ "\u00dc <> $vowel{$YPSILON_DIAERESIS;"
+ "Y<>$YPSILON;"
+ "\u00dd<>$YPSILON2;"
+ "$Y_UMLAUT<>$YPSILON_DIAERESIS;"
+ "CH<>$CHI;"
+ "$O_MACRON_ACUTE<>$OMEGA2;"
+ "$O_MACRON<>$OMEGA;"
// Extra English Letters. Mapped for completeness
+ "C}$softener>|S;"
+ "C>|K;"
+ "F>|PH;"
+ "H>|CH;"
+ "J>|I;"
+ "Q>|K;"
+ "V>|U;"
+ "W>|U;"
// ==============================================
// Lowercase Forms. Just copy above and lowercase
// ==============================================
// typing variants, in case the keyboard doesn't have accents
+ "'a`'>$alpha2;"
+ "'e`'>$epsilon2;"
+ "'ee`'>$eta2;"
+ "ee>$eta;"
+ "'i`'>$iota2;"
+ "'o`'>$omicron2;"
+ "'oo`'>$omega2;"
+ "oo>$omega;"
+ "i$quote>$iota_diaeresis;"
+ "y$quote>$ypsilon_diaeresis;"
// basic letters
+ "a<>$alpha;"
+ "\u00e1<>$alpha2;"
+ "b<>$beta;"
+ "n }$n_gamma<>$gamma}$gamma_n;"
+ "g<>$gamma;"
+ "d<>$delta;"
+ "''e <> [Ee]{$epsilon;" // handle EE
+ "e<>$epsilon;"
+ "\u00e9<>$epsilon2;"
+ "z<>$zeta;"
+ "$e_macron_acute<>$eta2;"
+ "$e_macron<>$eta;"
+ "th<>$theta;"
+ "i<>$iota;"
+ "\u00ed<>$iota2;"
+ "\u00ef<>$iota_diaeresis;"
+ "k<>$kappa;"
+ "l<>$lambda;"
+ "m<>$mu;"
+ "n'' <> $nu}$gamma_n;"
+ "n<>$nu;"
+ "x<>$xi;"
+ "''o <> [Oo]{ $omicron;" // handle OO
+ "o<>$omicron;"
+ "\u00f3<>$omicron2;"
+ "ph<>$phi;" // needs ordering before p
+ "ps<>$psi;" // needs ordering before p
+ "p<>$pi;"
+ "r<>$rho;"
+ "t<>$tau;"
+ "u <> $vowel{$ypsilon;"
+ "\u00fa <> $vowel{$ypsilon2;"
+ "\u00fc <> $vowel{$ypsilon_diaeresis;"
+ "y<>$ypsilon;"
+ "\u00fd<>$ypsilon2;"
+ "$y_umlaut<>$ypsilon_diaeresis;"
+ "ch<>$chi;"
+ "$o_macron_acute<>$omega2;"
+ "$o_macron<>$omega;"
// extra english letters. mapped for completeness
+ "c}$softener>|s;"
+ "c>|k;"
+ "f>|ph;"
+ "h>|ch;"
+ "j>|i;"
+ "q>|k;"
+ "v>|u;"
+ "w>|u;"
// ====================================
// Normal final rule: remove '
// ====================================
//+ "''>;"
}
};
}
}

232
icu4j/src/com/ibm/text/resources/TransliterationRule_Latin_Hebrew.java
View File

@ -1,232 +0,0 @@
/*
*******************************************************************************
* Copyright (C) 1996-2000, International Business Machines Corporation and *
* others. All Rights Reserved. *
*******************************************************************************
*
* $Source: /xsrl/Nsvn/icu/icu4j/src/com/ibm/text/resources/Attic/TransliterationRule_Latin_Hebrew.java,v $
* $Date: 2000/07/05 23:07:58 $
* $Revision: 1.5 $
*
*****************************************************************************************
*/
package com.ibm.text.resources;
import java.util.ListResourceBundle;
public class TransliterationRule_Latin_Hebrew extends ListResourceBundle {
/**
* Overrides ListResourceBundle
*/
public Object[][] getContents() {
return new Object[][] {
{ "Rule", ""
// Variable names, derived from the Unicode names.
+ "$POINT_SHEVA=\u05B0;"
+ "$POINT_HATAF_SEGOL=\u05B1;"
+ "$POINT_HATAF_PATAH=\u05B2;"
+ "$POINT_HATAF_QAMATS=\u05B3;"
+ "$POINT_HIRIQ=\u05B4;"
+ "$POINT_TSERE=\u05B5;"
+ "$POINT_SEGOL=\u05B6;"
+ "$POINT_PATAH=\u05B7;"
+ "$POINT_QAMATS=\u05B8;"
+ "$POINT_HOLAM=\u05B9;"
+ "$POINT_QUBUTS=\u05BB;"
+ "$POINT_DAGESH_OR_MAPIQ=\u05BC;"
+ "$POINT_METEG=\u05BD;"
+ "$PUNCTUATION_MAQAF=\u05BE;"
+ "$POINT_RAFE=\u05BF;"
+ "$PUNCTUATION_PASEQ=\u05C0;"
+ "$POINT_SHIN_DOT=\u05C1;"
+ "$POINT_SIN_DOT=\u05C2;"
+ "$PUNCTUATION_SOF_PASUQ=\u05C3;"
+ "$ALEF=\u05D0;"
+ "$BET=\u05D1;"
+ "$GIMEL=\u05D2;"
+ "$DALET=\u05D3;"
+ "$HE=\u05D4;"
+ "$VAV=\u05D5;"
+ "$ZAYIN=\u05D6;"
+ "$HET=\u05D7;"
+ "$TET=\u05D8;"
+ "$YOD=\u05D9;"
+ "$FINAL_KAF=\u05DA;"
+ "$KAF=\u05DB;"
+ "$LAMED=\u05DC;"
+ "$FINAL_MEM=\u05DD;"
+ "$MEM=\u05DE;"
+ "$FINAL_NUN=\u05DF;"
+ "$NUN=\u05E0;"
+ "$SAMEKH=\u05E1;"
+ "$AYIN=\u05E2;"
+ "$FINAL_PE=\u05E3;"
+ "$PE=\u05E4;"
+ "$FINAL_TSADI=\u05E5;"
+ "$TSADI=\u05E6;"
+ "$QOF=\u05E7;"
+ "$RESH=\u05E8;"
+ "$SHIN=\u05E9;"
+ "$TAV=\u05EA;"
+ "$YIDDISH_DOUBLE_VAV=\u05F0;"
+ "$YIDDISH_VAV_YOD=\u05F1;"
+ "$YIDDISH_DOUBLE_YOD=\u05F2;"
+ "$PUNCTUATION_GERESH=\u05F3;"
+ "$PUNCTUATION_GERSHAYIM=\u05F4;"
+ "$letter=[a-zA-Z];"
+ "$softvowel=[eiyEIY];"
+ "$vowellike=[$ALEF$AYIN$YOD$VAV];"
+ "$hebrew=[\u0590-\u05FF];" // the whole block -liu
// [Why is this a special case? -liu]
+ "k''h <> $KAF $HE ;"
// Mark non-final forms in final position as x~ -liu
+ "k < $KAF } $hebrew ;"
+ "m < $MEM } $hebrew ;"
+ "n < $NUN } $hebrew ;"
+ "p < $PE } $hebrew ;"
+ "ts < $TSADI } $hebrew ;"
+ "k'~' <> $KAF ;"
+ "m'~' <> $MEM ;"
+ "n'~' <> $NUN ;"
+ "p'~' <> $PE ;"
+ "ts'~'<> $TSADI ;"
// Mark final forms in non-final position as x^ -liu
+ "k'^' <> $FINAL_KAF } $hebrew ;"
+ "m'^' <> $FINAL_MEM } $hebrew ;"
+ "n'^' <> $FINAL_NUN } $hebrew ;"
+ "p'^' <> $FINAL_PE } $hebrew ;"
+ "ts'^'<> $FINAL_TSADI } $hebrew ;"
+ "k < $FINAL_KAF;"
+ "m < $FINAL_MEM;"
+ "n < $FINAL_NUN;"
+ "p < $FINAL_PE;"
+ "ts < $FINAL_TSADI;"
// Main rules
+ "a<>$ALEF;"
+ "A>$ALEF;"
+ "b<>$BET;"
+ "B>$BET;"
+ "c}$softvowel>$SAMEKH;"
+ "C}$softvowel>$SAMEKH;"
+ "c}$letter>$KAF;"
+ "C}$letter>$KAF;"
+ "c>$FINAL_KAF;"
+ "C>$FINAL_KAF;"
+ "d<>$DALET;"
+ "D>$DALET;"
+ "e<>$AYIN;"
+ "E>$AYIN;"
+ "f}$letter>$PE;"
+ "f>$FINAL_PE;"
+ "F}$letter>$PE;"
+ "F>$FINAL_PE;"
+ "g<>$GIMEL;"
+ "G>$GIMEL;"
+ "h<>$HE;"
+ "H>$HE;"
+ "i>$YOD;"
+ "I>$YOD;"
+ "j>$DALET$SHIN;"
+ "J>$DALET$SHIN;"
+ "kh<>$HET;"
+ "kH>$HET;"
+ "Kh>$HET;"
+ "KH>$HET;"
+ "k}$letter>$KAF;"
+ "K}$letter>$KAF;"
+ "k>$FINAL_KAF;"
+ "K>$FINAL_KAF;"
+ "l<>$LAMED;"
+ "L>$LAMED;"
+ "m}$letter>$MEM;"
+ "m>$FINAL_MEM;"
+ "M}$letter>$MEM;"
+ "M>$FINAL_MEM;"
+ "n}$letter>$NUN;"
+ "n>$FINAL_NUN;"
+ "N}$letter>$NUN;"
+ "N>$FINAL_NUN;"
+ "o>$VAV;"
+ "O>$VAV;"
+ "p}$letter>$PE;"
+ "p>$FINAL_PE;"
+ "P}$letter>$PE;"
+ "P>$FINAL_PE;"
+ "q<>$QOF;"
+ "Q>$QOF;"
+ "r<>$RESH;"
+ "R>$RESH;"
+ "sh<>$SHIN;"
+ "sH>$SHIN;"
+ "Sh>$SHIN;"
+ "SH>$SHIN;"
+ "s''<$SAMEKH}$HE;"
+ "s<>$SAMEKH;"
+ "S>$SAMEKH;"
+ "th<>$TAV;"
+ "tH>$TAV;"
+ "Th>$TAV;"
+ "TH>$TAV;"
+ "tS}$letter>$TSADI;"
+ "ts}$letter>$TSADI;"
+ "Ts}$letter>$TSADI;"
+ "TS}$letter>$TSADI;"
+ "tS>$FINAL_TSADI;"
+ "ts>$FINAL_TSADI;"
+ "Ts>$FINAL_TSADI;"
+ "TS>$FINAL_TSADI;"
+ "t''<$TET}[$HE $SAMEKH $SHIN];"
+ "t<>$TET;"
+ "T>$TET;"
+ "v<$VAV}$vowellike;"
+ "u<>$VAV;"
+ "U>$VAV;"
+ "v>$VAV;"
+ "V>$VAV;"
+ "w>$VAV;"
+ "W>$VAV;"
+ "x>$KAF$SAMEKH;"
+ "X>$KAF$SAMEKH;"
+ "y<>$YOD;"
+ "Y>$YOD;"
+ "z<>$ZAYIN;"
+ "Z>$ZAYIN;"
// Delete stray apostrophes
+ "''>;"
+ "<'';"
}
};
}
}

757
icu4j/src/com/ibm/text/resources/TransliterationRule_Latin_Jamo.java
View File

@ -1,757 +0,0 @@
/*
*******************************************************************************
* Copyright (C) 1996-2000, International Business Machines Corporation and *
* others. All Rights Reserved. *
*******************************************************************************
*
* $Source: /xsrl/Nsvn/icu/icu4j/src/com/ibm/text/resources/Attic/TransliterationRule_Latin_Jamo.java,v $
* $Date: 2000/05/01 20:56:34 $
* $Revision: 1.7 $
*
*****************************************************************************************
*/
package com.ibm.text.resources;
import java.util.ListResourceBundle;
public class TransliterationRule_Latin_Jamo extends ListResourceBundle {
/**
* Overrides ListResourceBundle
*/
public Object[][] getContents() {
return new Object[][] {
{ "Rule", ""
// VARIABLES
+ "$initial=[\u1100-\u115F];"
+ "$INITIAL=[bcdghjklmnpst];"
+ "$medial=[\u1160-\u11A7];"
+ "$MEDIAL=[aeiou];" // as a left context
+ "$comp_med=[\u1160\u1176-\u11A7];" // compound medials and filler
+ "$final=[\u11A8-\u11F9];" // added - aliu
+ "$vowel=[aeiouwy$medial];"
// following line used to read "..$medial$final]"
// assume this was a typo - liu
+ "$consonant=[bcdfghjklmnpqrstvxz$initial$final];"
+ "$ye_=[yeYE];"
+ "$ywe_=[yweYWE];"
+ "$yw_=[ywYW];"
+ "$nl_=[nlNL];"
+ "$gnl_=[gnlGNL];"
+ "$lsgb_=[lsgbLSGB];"
+ "$ywao_=[ywaoYWAO];"
+ "$bl_=[blBL];"
+ "$ieung = \u110b;"
// RULES
// Hangul structure is IMF or IM
// So you can have, because of adjacent sequences
// IM, but not II or IF
// MF or MI, but not MM
// FI, but not FF or FM
// For English, we just have C or V.
// To generate valid Hangul:
// Vowels:
// We insert IEUNG between VV, and otherwise map V to M
// We also insert IEUNG if there is no
// Consonants:
// We don't break doubles
// Cases like lmgg, we have to break at lm
// So to guess whether a consonant is I or F
// we map all C's to F, except when followed by a vowel, e.g.
// X[{vowel}>CHOSEONG (initial)
// X>JONGSEONG (final)
// Below, insert an empty consonant in front of a vowel, if there is no Initial in front.
// General strategy.
//
// 1. We support both the normal Jamo block, 1100 - 117F, and the
// compatibility block, 3130 - 318F. The former uses lowercase latin;
// the latter uses uppercase. See notes below for details of the
// compatibility block. Remaining items in this list pertain to the
// normal Jamo block.
//
// 2. Canonical syllables should transliterate without special
// characters. Canonical syllables are either IMF or IM.
//
// 3. We want to support round-trip integrity from jamo to latin and back
// to Jamo. To do this we have to mark the jamo with special characters
// when they occur in non-canonical positions.
//
// 4. When initial jamo occur in a non-canonical position, they are
// marked with a leading '['.
//
// 5. When final jamo occur in a non-canonical position, they are marked
// with a trailing ']'.
//
// 6. When medial jamo occur in a non-canonical position, they are marked
// with a leading '~'.
//
// 7. Compound jamo characters are handled by enclosing them in
// parentheses. Initials are '((x)', medials are '(x)', and finals are
// '(x))'.
//
// 8. Disambiguation of 'g' + 'g' vs. 'gg' is accomplished by inserting a
// '' character between them.
//
// 9. IEUNG is used to mark medials not occuring after initials.
// Isolated IEUNG is transliterated as a back tick.
//
// 10. Some old special case and completeness rules have been commented
// out. These can be reintroduced (and the existing rules modified as
// needed) so long as round-trip integrity is maintained.
// We use the uppercase latin letters for the compatibility Jamo
// U+3130 - U+318F. The following rules are generated
// programmatically by a perl script that analyzes the Unicode
// database. These rules are much simpler because there are no
// separate code points for initial vs. final consonants, so no
// contextual rules are needed. The one wrinkle is, as usual, the
// need to distinguish doubles from two singles, that is, GG vs G G.
// The perl script finds these special cases by exhaustive search and
// adds only the minimal rules needed to resolve these cases. The one
// modification that is made by hand is to replace '' with '/' so as
// not to conflict with the normal IEUNG in the standard Jamo range. -
// liu
+ "A '' <> {\u314F} [\u3153\u3161\u3154];"
+ "B '' <> {\u3142} [\u3142\u3143];"
+ "D '' <> {\u3137} [\u3137\u3138];"
+ "E '' <> {\u3154} [\u315A\u3157\u315C];"
+ "G '' <> {\u3131} [\u3132\u3133\u3131\u3146\u3145];"
+ "J '' <> {\u3148} [\u3149\u3148];"
+ "L '' <> {\u3139} [\u3132\u3133\u3131\u3141\u3142\u3143\u3146\u3145\u314C\u314D];"
+ "N '' <> {\u3134} [\u3149\u3148\u314E];"
+ "O '' <> {\u3157} [\u3153\u3161\u3154];"
+ "S '' <> {\u3145} [\u3146\u3145];"
+ "WA '' <> {\u3158} [\u3153\u3161\u3154];"
+ "WE '' <> {\u315E} [\u315A\u3157];"
+ "YA '' <> {\u3151} [\u3153\u3161\u3154];"
+ "YE '' <> {\u3156} [\u315A\u3157];"
+ "YU <> \u3160;"
+ "YO <> \u315B;"
+ "YI <> \u3162;"
+ "YEO <> \u3155;"
+ "YE <> \u3156;"
+ "YAE <> \u3152;"
+ "YA <> \u3151;"
+ "WI <> \u315F;"
+ "WEO <> \u315D;"
+ "WE <> \u315E;"
+ "WAE <> \u3159;"
+ "WA <> \u3158;"
+ "U <> \u315C;"
+ "T <> \u314C;"
+ "S S <> \u3146;"
+ "S <> \u3145;"
+ "P <> \u314D;"
+ "OE <> \u315A;"
+ "O <> \u3157;"
+ "N J <> \u3135;"
+ "N H <> \u3136;"
+ "N <> \u3134;"
+ "M <> \u3141;"
+ "L T <> \u313E;"
+ "L S <> \u313D;"
+ "L P <> \u313F;"
+ "L M <> \u313B;"
+ "L G <> \u313A;"
+ "L B <> \u313C;"
+ "L <> \u3139;"
+ "K <> \u314B;"
+ "J J <> \u3149;"
+ "J <> \u3148;"
+ "I <> \u3163;"
+ "H <> \u314E;"
+ "G S <> \u3133;"
+ "G G <> \u3132;"
+ "G <> \u3131;"
+ "EU <> \u3161;"
+ "EO <> \u3153;"
+ "E <> \u3154;"
+ "D D <> \u3138;"
+ "D <> \u3137;"
+ "C <> \u314A;"
+ "B B <> \u3143;"
+ "B <> \u3142;"
+ "AE <> \u3150;"
+ "A <> \u314F;"
+ "'/' <> \u3147;"
+ "'(' YU YEO ')' <> \u318A;"
+ "'(' YU YE ')' <> \u318B;"
+ "'(' YU I ')' <> \u318C;"
+ "'(' YR ')' <> \u3186;"
+ "'(' YO YAE ')' <> \u3188;"
+ "'(' YO YA ')' <> \u3187;"
+ "'(' YO I ')' <> \u3189;"
+ "'(' YES S ')' <> \u3182;"
+ "'(' YES PAN ')' <> \u3183;"
+ "'(' YES ')' <> \u3181;"
+ "'(' S N ')' <> \u317B;"
+ "'(' S J ')' <> \u317E;"
+ "'(' S G ')' <> \u317A;"
+ "'(' S D ')' <> \u317C;"
+ "'(' S B ')' <> \u317D;"
+ "'(' PAN ')' <> \u317F;"
+ "'(' P '' ')' <> \u3184;"
+ "'(' N S ')' <> \u3167;"
+ "'(' N PAN ')' <> \u3168;"
+ "'(' N N ')' <> \u3165;"
+ "'(' N D ')' <> \u3166;"
+ "'(' M S ')' <> \u316F;"
+ "'(' M PAN ')' <> \u3170;"
+ "'(' M B ')' <> \u316E;"
+ "'(' M '' ')' <> \u3171;"
+ "'(' L YR ')' <> \u316D;"
+ "'(' L PAN ')' <> \u316C;"
+ "'(' L H ')' <> \u3140;"
+ "'(' L G S ')' <> \u3169;"
+ "'(' L D ')' <> \u316A;"
+ "'(' L B S ')' <> \u316B;"
+ "'(' HJF ')' <> \u3164;"
+ "'(' H H ')' <> \u3185;"
+ "'(' B T ')' <> \u3177;"
+ "'(' B S G ')' <> \u3174;"
+ "'(' B S D ')' <> \u3175;"
+ "'(' B S ')' <> \u3144;"
+ "'(' B J ')' <> \u3176;"
+ "'(' B G ')' <> \u3172;"
+ "'(' B D ')' <> \u3173;"
+ "'(' B B '' ')' <> \u3179;"
+ "'(' B '' ')' <> \u3178;"
+ "'(' AR I ')' <> \u318E;"
+ "'(' AR ')' <> \u318D;"
+ "'(' '' '' ')' <> \u3180;"
// APOSTROPHE
// As always, an apostrophe is used to separate digraphs into
// singles. That is, if you really wanted [KAN][GGAN], instead
// of [KANG][GAN] you would write "kan'ggan".
// Rules for inserting ' when mapping separated digraphs back
// from Hangul to Latin. Catch every letter that can be the
// LAST of a digraph (or multigraph) AND first of an initial
// special insertion for funny sequences of vowels, and for empty consonant
// + "'' < l{ }\u11c0;" // hangul jongseong thieuth
// + "'' < $lsgb_{}\u11ba;" // hangul jongseong sios
// + "'' < l{ }\u11c1;" // hangul jongseong phieuph
// + "'' < l{ }\u11b7;" // hangul jongseong mieum
// + "'' < n{ }\u11bd;" // hangul jongseong cieuc
// + "'' < $nl_{}\u11c2;" // hangul jongseong hieuh
// + "'' < $gnl_{}\u11a9;" // hangul jongseong ssangkiyeok
// + "'' < $bl_{}\u11b8;" // hangul jongseong pieup
// + "'' < d{ }\u11ae;" // hangul jongseong tikeut
//
// + "'' < $ye_{}\u116e;" // hangul jungseong u
// + "'' < $ywe_{}\u1169;" // hangul jungseong o
// + "'' < $yw_{}\u1175;" // hangul jungseong i
// + "'' < $ywao_{}\u1166;" // hangul jungseong e
// + "'' < $yw_{}\u1161;" // hangul jungseong a
//
// + "'' < l{ }\u1110;" // hangul choseong thieuth
// + "'' < $lsgb_{}\u110a;" // hangul choseong ssangsios
// + "'' < $lsgb_{}\u1109;" // hangul choseong sios
// + "'' < l{ }\u1111;" // hangul choseong phieuph
// + "'' < l{ }\u1106;" // hangul choseong mieum
// + "'' < n{ }\u110c;" // hangul choseong cieuc
// + "'' < n{ }\u110d;"
// + "'' < $nl_{}\u1112;" // hangul choseong hieuh
// + "'' < $gnl_{}\u1101;" // hangul choseong ssangkiyeok
// + "'' < $gnl_{}\u1100;" // hangul choseong kiyeok
// + "'' < d{ }\u1103;" // hangul choseong tikeut
// + "'' < d{ }\u1104;"
// + "'' < $bl_{}\u1107;" // hangul choseong pieup
// + "'' < $bl_{}\u1108;"
// We transliterate the compound Jamo code points using ((x) for
// initials, (x) for medials, and (x)) for finals. - liu
+ " '((' n g ')' <> \u1113;"
+ " '((' n n ')' <> \u1114;"
+ " '((' n d ')' <> \u1115;"
+ " '((' n b ')' <> \u1116;"
+ " '((' d g ')' <> \u1117;"
+ " '((' l n ')' <> \u1118;"
+ " '((' l l ')' <> \u1119;"
+ " '((' l h ')' <> \u111A;"
+ " '((' l '' ')' <> \u111B;"
+ " '((' m b ')' <> \u111C;"
+ " '((' m '' ')' <> \u111D;"
+ " '((' b g ')' <> \u111E;"
+ " '((' b n ')' <> \u111F;"
+ " '((' b d ')' <> \u1120;"
+ " '((' b s ')' <> \u1121;"
+ " '((' b s g ')' <> \u1122;"
+ " '((' b s d ')' <> \u1123;"
+ " '((' b s b ')' <> \u1124;"
+ " '((' b s s ')' <> \u1125;"
+ " '((' b s j ')' <> \u1126;"
+ " '((' b j ')' <> \u1127;"
+ " '((' b c ')' <> \u1128;"
+ " '((' b t ')' <> \u1129;"
+ " '((' b p ')' <> \u112A;"
+ " '((' b '' ')' <> \u112B;"
+ " '((' b b '' ')' <> \u112C;"
+ " '((' s g ')' <> \u112D;"
+ " '((' s n ')' <> \u112E;"
+ " '((' s d ')' <> \u112F;"
+ " '((' s l ')' <> \u1130;"
+ " '((' s m ')' <> \u1131;"
+ " '((' s b ')' <> \u1132;"
+ " '((' s b g ')' <> \u1133;"
+ " '((' s s s ')' <> \u1134;"
+ " '((' s '' ')' <> \u1135;"
+ " '((' s j ')' <> \u1136;"
+ " '((' s c ')' <> \u1137;"
+ " '((' s k ')' <> \u1138;"
+ " '((' s t ')' <> \u1139;"
+ " '((' s p ')' <> \u113A;"
+ " '((' s h ')' <> \u113B;"
+ " '((' chs ')' <> \u113C;"
+ " '((' chs chs ')' <> \u113D;"
+ " '((' ces ')' <> \u113E;"
+ " '((' ces ces ')' <> \u113F;"
+ " '((' pan ')' <> \u1140;"
+ " '((' '' g ')' <> \u1141;"
+ " '((' '' d ')' <> \u1142;"
+ " '((' '' m ')' <> \u1143;"
+ " '((' '' b ')' <> \u1144;"
+ " '((' '' s ')' <> \u1145;"
+ " '((' '' pan ')' <> \u1146;"
+ " '((' '' '' ')' <> \u1147;"
+ " '((' '' j ')' <> \u1148;"
+ " '((' '' c ')' <> \u1149;"
+ " '((' '' t ')' <> \u114A;"
+ " '((' '' p ')' <> \u114B;"
+ " '((' yes ')' <> \u114C;"
+ " '((' j '' ')' <> \u114D;"
+ " '((' chc ')' <> \u114E;"
+ " '((' chc chc ')' <> \u114F;"
+ " '((' cec ')' <> \u1150;"
+ " '((' cec cec ')' <> \u1151;"
+ " '((' c k ')' <> \u1152;"
+ " '((' c h ')' <> \u1153;"
+ " '((' cch ')' <> \u1154;"
+ " '((' ceh ')' <> \u1155;"
+ " '((' p b ')' <> \u1156;"
+ " '((' p '' ')' <> \u1157;"
+ " '((' h h ')' <> \u1158;"
+ " '((' yr ')' <> \u1159;"
+ " '((' hcf ')' <> \u115F;"
+ " '(' ahjf ')' <> \u1160;" // must start with vowel, hence 'a' + hjf
+ " '(' a o ')' <> \u1176;"
+ " '(' a u ')' <> \u1177;"
+ " '(' ya o ')' <> \u1178;"
+ " '(' ya yo ')' <> \u1179;"
+ " '(' eo o ')' <> \u117A;"
+ " '(' eo u ')' <> \u117B;"
+ " '(' eo eu ')' <> \u117C;"
+ " '(' yeo o ')' <> \u117D;"
+ " '(' yeo u ')' <> \u117E;"
+ " '(' o eo ')' <> \u117F;"
+ " '(' o e ')' <> \u1180;"
+ " '(' o ye ')' <> \u1181;"
+ " '(' o o ')' <> \u1182;"
+ " '(' o u ')' <> \u1183;"
+ " '(' yo ya ')' <> \u1184;"
+ " '(' yo yae ')' <> \u1185;"
+ " '(' yo yeo ')' <> \u1186;"
+ " '(' yo o ')' <> \u1187;"
+ " '(' yo i ')' <> \u1188;"
+ " '(' u a ')' <> \u1189;"
+ " '(' u ae ')' <> \u118A;"
+ " '(' u eo eu ')' <> \u118B;"
+ " '(' u ye ')' <> \u118C;"
+ " '(' u u ')' <> \u118D;"
+ " '(' yu a ')' <> \u118E;"
+ " '(' yu eo ')' <> \u118F;"
+ " '(' yu e ')' <> \u1190;"
+ " '(' yu yeo ')' <> \u1191;"
+ " '(' yu ye ')' <> \u1192;"
+ " '(' yu u ')' <> \u1193;"
+ " '(' yu i ')' <> \u1194;"
+ " '(' eu u ')' <> \u1195;"
+ " '(' eu eu ')' <> \u1196;"
+ " '(' yi u ')' <> \u1197;"
+ " '(' i a ')' <> \u1198;"
+ " '(' i ya ')' <> \u1199;"
+ " '(' i o ')' <> \u119A;"
+ " '(' i u ')' <> \u119B;"
+ " '(' i eu ')' <> \u119C;"
+ " '(' i ar ')' <> \u119D;"
+ " '(' ar ')' <> \u119E;"
+ " '(' ar eo ')' <> \u119F;"
+ " '(' ar u ')' <> \u11A0;"
+ " '(' ar i ')' <> \u11A1;"
+ " '(' ar ar ')' <> \u11A2;"
+ " '(' g l '))' <> \u11C3;"
+ " '(' g s g '))' <> \u11C4;"
+ " '(' n g '))' <> \u11C5;"
+ " '(' n d '))' <> \u11C6;"
+ " '(' n s '))' <> \u11C7;"
+ " '(' n pan '))' <> \u11C8;"
+ " '(' n t '))' <> \u11C9;"
+ " '(' d g '))' <> \u11CA;"
+ " '(' d l '))' <> \u11CB;"
+ " '(' l g s '))' <> \u11CC;"
+ " '(' l n '))' <> \u11CD;"
+ " '(' l d '))' <> \u11CE;"
+ " '(' l d h '))' <> \u11CF;"
+ " '(' l l '))' <> \u11D0;"
+ " '(' l m g '))' <> \u11D1;"
+ " '(' l m s '))' <> \u11D2;"
+ " '(' l b s '))' <> \u11D3;"
+ " '(' l b h '))' <> \u11D4;"
+ " '(' l b ng '))' <> \u11D5;"
+ " '(' l s s '))' <> \u11D6;"
+ " '(' l pan '))' <> \u11D7;"
+ " '(' l k '))' <> \u11D8;"
+ " '(' l yr '))' <> \u11D9;"
+ " '(' m g '))' <> \u11DA;"
+ " '(' m l '))' <> \u11DB;"
+ " '(' m b '))' <> \u11DC;"
+ " '(' m s '))' <> \u11DD;"
+ " '(' m s s '))' <> \u11DE;"
+ " '(' m pan '))' <> \u11DF;"
+ " '(' m c '))' <> \u11E0;"
+ " '(' m h '))' <> \u11E1;"
+ " '(' m ng '))' <> \u11E2;"
+ " '(' b l '))' <> \u11E3;"
+ " '(' b p '))' <> \u11E4;"
+ " '(' b h '))' <> \u11E5;"
+ " '(' b ng '))' <> \u11E6;"
+ " '(' s g '))' <> \u11E7;"
+ " '(' s d '))' <> \u11E8;"
+ " '(' s l '))' <> \u11E9;"
+ " '(' s b '))' <> \u11EA;"
+ " '(' pan '))' <> \u11EB;"
+ " '(' ng g '))' <> \u11EC;"
+ " '(' ng g g '))' <> \u11ED;"
+ " '(' ng ng '))' <> \u11EE;"
+ " '(' ng k '))' <> \u11EF;"
+ " '(' yes '))' <> \u11F0;"
+ " '(' yes s '))' <> \u11F1;"
+ " '(' yes pan '))' <> \u11F2;"
+ " '(' p b '))' <> \u11F3;"
+ " '(' p ng '))' <> \u11F4;"
+ " '(' h n '))' <> \u11F5;"
+ " '(' h l '))' <> \u11F6;"
+ " '(' h m '))' <> \u11F7;"
+ " '(' h b '))' <> \u11F8;"
+ " '(' yr '))' <> \u11F9;"
// INITIALS
// Added }$vowel post context - liu
+ "bb}$vowel<>\u1108 } $vowel;"
+ "jj}$vowel<>\u110d } $vowel;"
+ "dd}$vowel<>\u1104 } $vowel;"
+ "t }$vowel<>\u1110 } $vowel;" // hangul choseong thieuth
+ "ss}$vowel<>\u110a } $vowel;" // hangul choseong ssangsios
+ "s }$vowel<>\u1109 } $vowel;" // hangul choseong sios
+ "p }$vowel<>\u1111 } $vowel;" // hangul choseong phieuph
+ "n }$vowel<>\u1102 } $vowel;" // hangul choseong nieun
+ "m }$vowel<>\u1106 } $vowel;" // hangul choseong mieum
+ "l }$vowel<>\u1105 } $vowel;" // hangul choseong rieul
+ "k }$vowel<>\u110f } $vowel;" // hangul choseong khieukh
+ "j }$vowel<>\u110c } $vowel;" // hangul choseong cieuc
+ "h }$vowel<>\u1112 } $vowel;" // hangul choseong hieuh
+ "gg}$vowel<>\u1101 } $vowel;" // hangul choseong ssangkiyeok
+ "g }$vowel<>\u1100 } $vowel;" // hangul choseong kiyeok
+ "d }$vowel<>\u1103 } $vowel;" // hangul choseong tikeut
+ "c }$vowel<>\u110e } $vowel;" // hangul choseong chieuch
+ "b }$vowel<>\u1107 } $vowel;" // hangul choseong pieup
// Take care of initial-compound medial - '(' $vowel - liu
+ "bb} '(' $vowel <> \u1108 } $comp_med;"
+ "jj} '(' $vowel <> \u110d } $comp_med;"
+ "dd} '(' $vowel <> \u1104 } $comp_med;"
+ "t } '(' $vowel <> \u1110 } $comp_med;" // hangul choseong thieuth
+ "ss} '(' $vowel <> \u110a } $comp_med;" // hangul choseong ssangsios
+ "s } '(' $vowel <> \u1109 } $comp_med;" // hangul choseong sios
+ "p } '(' $vowel <> \u1111 } $comp_med;" // hangul choseong phieuph
+ "n } '(' $vowel <> \u1102 } $comp_med;" // hangul choseong nieun
+ "m } '(' $vowel <> \u1106 } $comp_med;" // hangul choseong mieum
+ "l } '(' $vowel <> \u1105 } $comp_med;" // hangul choseong rieul
+ "k } '(' $vowel <> \u110f } $comp_med;" // hangul choseong khieukh
+ "j } '(' $vowel <> \u110c } $comp_med;" // hangul choseong cieuc
+ "h } '(' $vowel <> \u1112 } $comp_med;" // hangul choseong hieuh
+ "gg} '(' $vowel <> \u1101 } $comp_med;" // hangul choseong ssangkiyeok
+ "g } '(' $vowel <> \u1100 } $comp_med;" // hangul choseong kiyeok
+ "d } '(' $vowel <> \u1103 } $comp_med;" // hangul choseong tikeut
+ "c } '(' $vowel <> \u110e } $comp_med;" // hangul choseong chieuch
+ "b } '(' $vowel <> \u1107 } $comp_med;" // hangul choseong pieup
// Mark non-canonical initials with '[' - liu
+ "'[' bb <> \u1108;"
+ "'[' jj <> \u110d;"
+ "'[' dd <> \u1104;"
+ "'[' t <> \u1110;" // hangul choseong thieuth
+ "'[' ss <> \u110a;" // hangul choseong ssangsios
+ "'[' s <> \u1109;" // hangul choseong sios
+ "'[' p <> \u1111;" // hangul choseong phieuph
+ "'[' n <> \u1102;" // hangul choseong nieun
+ "'[' m <> \u1106;" // hangul choseong mieum
+ "'[' l <> \u1105;" // hangul choseong rieul
+ "'[' k <> \u110f;" // hangul choseong khieukh
+ "'[' j <> \u110c;" // hangul choseong cieuc
+ "'[' h <> \u1112;" // hangul choseong hieuh
+ "'[' gg <> \u1101;" // hangul choseong ssangkiyeok
+ "'[' g <> \u1100;" // hangul choseong kiyeok
+ "'[' d <> \u1103;" // hangul choseong tikeut
+ "'[' c <> \u110e;" // hangul choseong chieuch
+ "'[' b <> \u1107;" // hangul choseong pieup
// If we have gotten through to these rules, and we start with
// a consonant, then the remaining mappings would be to F,
// because must have CC (or C<non-letter>), not CV.
// If we have F before us, then
// we would end up with FF, which is wrong. The simplest fix is
// to still make it an initial, but also insert an "u",
// so we end up with F, I, u, and then continue with the C
// special, only initial
// + "bb > \u1108\u116e;" // bb u hangul choseong ssangpieup
// + "jj > \u110d\u116e;" // jj u hangul choseong ssangcieuc
// + "dd > \u1104\u116e;" // dd u hangul choseong ssangtikeut
// + "$final{ t > \u1110\u116e;" // hangul choseong thieuth
// + "$final{ ss> \u110a\u116e;" // hangul choseong ssangsios
// + "$final{ s > \u1109\u116e;" // hangul choseong sios
// + "$final{ p > \u1111\u116e;" // hangul choseong phieuph
// + "$final{ n > \u1102\u116e;" // hangul choseong nieun
// + "$final{ m > \u1106\u116e;" // hangul choseong mieum
// + "$final{ l > \u1105\u116e;" // hangul choseong rieul
// + "$final{ k > \u110f\u116e;" // hangul choseong khieukh
// + "$final{ j > \u110c\u116e;" // hangul choseong cieuc
// + "$final{ h > \u1112\u116e;" // hangul choseong hieuh
// + "$final{ gg> \u1101\u116e;" // hangul choseong ssangkiyeok
// + "$final{ g > \u1100\u116e;" // hangul choseong kiyeok
// + "$final{ d > \u1103\u116e;" // hangul choseong tikeut
// + "$final{ c > \u110e\u116e;" // hangul choseong chieuch
// + "$final{ b > \u1107\u116e;" // hangul choseong pieup
// MEDIALS after INITIALS
// MEDIALS (vowels) not after INITIALs
// Added left $initial context - liu
+ "$initial{ yu <> $INITIAL{ \u1172;" // hangul jungseong yu
+ "$initial{ yo <> $INITIAL{ \u116d;" // hangul jungseong yo
+ "$initial{ yi <> $INITIAL{ \u1174;" // hangul jungseong yi
+ "$initial{ yeo<> $INITIAL{ \u1167;" // hangul jungseong yeo
+ "$initial{ ye <> $INITIAL{ \u1168;" // hangul jungseong ye
+ "$initial{ yae<> $INITIAL{ \u1164;" // hangul jungseong yae
+ "$initial{ ya <> $INITIAL{ \u1163;" // hangul jungseong ya
+ "$initial{ wi <> $INITIAL{ \u1171;" // hangul jungseong wi
+ "$initial{ weo<> $INITIAL{ \u116f;" // hangul jungseong weo
+ "$initial{ we <> $INITIAL{ \u1170;" // hangul jungseong we
+ "$initial{ wae<> $INITIAL{ \u116b;" // hangul jungseong wae
+ "$initial{ wa <> $INITIAL{ \u116a;" // hangul jungseong wa
+ "$initial{ u <> $INITIAL{ \u116e;" // hangul jungseong u
+ "$initial{ oe <> $INITIAL{ \u116c;" // hangul jungseong oe
+ "$initial{ o <> $INITIAL{ \u1169;" // hangul jungseong o
+ "$initial{ i <> $INITIAL{ \u1175;" // hangul jungseong i
+ "$initial{ eu <> $INITIAL{ \u1173;" // hangul jungseong eu
+ "$initial{ eo <> $INITIAL{ \u1165;" // hangul jungseong eo
+ "$initial{ e <> $INITIAL{ \u1166;" // hangul jungseong e
+ "$initial{ ae <> $INITIAL{ \u1162;" // hangul jungseong ae
+ "$initial{ a <> $INITIAL{ \u1161;" // hangul jungseong a
// Handle non-canonical isolated jungseong - liu
+ "'~'yu <> \u1172;" // hangul jungseong yu
+ "'~'yo <> \u116d;" // hangul jungseong yo
+ "'~'yi <> \u1174;" // hangul jungseong yi
+ "'~'yeo<> \u1167;" // hangul jungseong yeo
+ "'~'ye <> \u1168;" // hangul jungseong ye
+ "'~'yae<> \u1164;" // hangul jungseong yae
+ "'~'ya <> \u1163;" // hangul jungseong ya
+ "'~'wi <> \u1171;" // hangul jungseong wi
+ "'~'weo<> \u116f;" // hangul jungseong weo
+ "'~'we <> \u1170;" // hangul jungseong we
+ "'~'wae<> \u116b;" // hangul jungseong wae
+ "'~'wa <> \u116a;" // hangul jungseong wa
+ "'~'u <> \u116e;" // hangul jungseong u
+ "'~'oe <> \u116c;" // hangul jungseong oe
+ "'~'o <> \u1169;" // hangul jungseong o
+ "'~'i <> \u1175;" // hangul jungseong i
+ "'~'eu <> \u1173;" // hangul jungseong eu
+ "'~'eo <> \u1165;" // hangul jungseong eo
+ "'~'e <> \u1166;" // hangul jungseong e
+ "'~'ae <> \u1162;" // hangul jungseong ae
+ "'~'a <> \u1161;" // hangul jungseong a
// MEDIALS (vowels) not after INITIALs
// Changed from > to <> - liu
+ "yu <> $ieung \u1172;" // hangul jungseong yu
+ "yo <> $ieung \u116d;" // hangul jungseong yo
+ "yi <> $ieung \u1174;" // hangul jungseong yi
+ "yeo<> $ieung \u1167;" // hangul jungseong yeo
+ "ye <> $ieung \u1168;" // hangul jungseong ye
+ "yae<> $ieung \u1164;" // hangul jungseong yae
+ "ya <> $ieung \u1163;" // hangul jungseong ya
+ "wi <> $ieung \u1171;" // hangul jungseong wi
+ "weo<> $ieung \u116f;" // hangul jungseong weo
+ "we <> $ieung \u1170;" // hangul jungseong we
+ "wae<> $ieung \u116b;" // hangul jungseong wae
+ "wa <> $ieung \u116a;" // hangul jungseong wa
+ "u <> $ieung \u116e;" // hangul jungseong u
+ "oe <> $ieung \u116c;" // hangul jungseong oe
+ "o <> $ieung \u1169;" // hangul jungseong o
+ "i <> $ieung \u1175;" // hangul jungseong i
+ "eu <> $ieung \u1173;" // hangul jungseong eu
+ "eo <> $ieung \u1165;" // hangul jungseong eo
+ "e <> $ieung \u1166;" // hangul jungseong e
+ "ae <> $ieung \u1162;" // hangul jungseong ae
+ "a <> $ieung \u1161;" // hangul jungseong a
+"\\` <> $ieung;"
// Moved down so as not to mask above rules - liu
// + "'' < $consonant{$ieung;" // insert a break between any consonant and the empty consonant.
// + "$medial{}$vowel<>$ieung;" // HANGUL CHOSEONG IEUNG
// FINALS
+ " '' t <> $consonant { \u11c0;" // hangul jongseong thieuth
+ " '' ss <> $consonant { \u11bb;" // hangul jongseong ssangsios
+ " '' s <> $consonant { \u11ba;" // hangul jongseong sios
+ " '' p <> $consonant { \u11c1;" // hangul jongseong phieuph
+ " '' nj <> $consonant { \u11ac;" // hangul jongseong nieun-cieuc
+ " '' nh <> $consonant { \u11ad;" // hangul jongseong nieun-hieuh
+ " '' ng <> $consonant { \u11bc;" // hangul jongseong ieung
+ " '' n <> $consonant { \u11ab;" // hangul jongseong nieun
+ " '' m <> $consonant { \u11b7;" // hangul jongseong mieum
+ " '' lt <> $consonant { \u11b4;" // hangul jongseong rieul-thieuth
+ " '' ls <> $consonant { \u11b3;" // hangul jongseong rieul-sios
+ " '' lp <> $consonant { \u11b5;" // hangul jongseong rieul-phieuph
+ " '' lm <> $consonant { \u11b1;" // hangul jongseong rieul-mieum
+ " '' lh <> $consonant { \u11b6;" // hangul jongseong rieul-hieuh
+ " '' lg <> $consonant { \u11b0;" // hangul jongseong rieul-kiyeok
+ " '' lb <> $consonant { \u11b2;" // hangul jongseong rieul-pieup
+ " '' l <> $consonant { \u11af;" // hangul jongseong rieul
+ " '' k <> $consonant { \u11bf;" // hangul jongseong khieukh
+ " '' j <> $consonant { \u11bd;" // hangul jongseong cieuc
+ " '' h <> $consonant { \u11c2;" // hangul jongseong hieuh
+ " '' gs <> $consonant { \u11aa;" // hangul jongseong kiyeok-sios
+ " '' gg <> $consonant { \u11a9;" // hangul jongseong ssangkiyeok
+ " '' g <> $consonant { \u11a8;" // hangul jongseong kiyeok
+ " '' d <> $consonant { \u11ae;" // hangul jongseong tikeut
+ " '' c <> $consonant { \u11be;" // hangul jongseong chieuch
+ " '' bs <> $consonant { \u11b9;" // hangul jongseong pieup-sios
+ " '' b <> $consonant { \u11b8;" // hangul jongseong pieup
+ "t ']'> \u11c0;" // hangul jongseong thieuth
+ "ss ']'> \u11bb;" // hangul jongseong ssangsios
+ "s ']'> \u11ba;" // hangul jongseong sios
+ "p ']'> \u11c1;" // hangul jongseong phieuph
+ "nj ']'> \u11ac;" // hangul jongseong nieun-cieuc
+ "nh ']'> \u11ad;" // hangul jongseong nieun-hieuh
+ "ng ']'> \u11bc;" // hangul jongseong ieung
+ "n ']'> \u11ab;" // hangul jongseong nieun
+ "m ']'> \u11b7;" // hangul jongseong mieum
+ "lt ']'> \u11b4;" // hangul jongseong rieul-thieuth
+ "ls ']'> \u11b3;" // hangul jongseong rieul-sios
+ "lp ']'> \u11b5;" // hangul jongseong rieul-phieuph
+ "lm ']'> \u11b1;" // hangul jongseong rieul-mieum
+ "lh ']'> \u11b6;" // hangul jongseong rieul-hieuh
+ "lg ']'> \u11b0;" // hangul jongseong rieul-kiyeok
+ "lb ']'> \u11b2;" // hangul jongseong rieul-pieup
+ "l ']'> \u11af;" // hangul jongseong rieul
+ "k ']'> \u11bf;" // hangul jongseong khieukh
+ "j ']'> \u11bd;" // hangul jongseong cieuc
+ "h ']'> \u11c2;" // hangul jongseong hieuh
+ "gs ']'> \u11aa;" // hangul jongseong kiyeok-sios
+ "gg ']'> \u11a9;" // hangul jongseong ssangkiyeok
+ "g ']'> \u11a8;" // hangul jongseong kiyeok
+ "d ']'> \u11ae;" // hangul jongseong tikeut
+ "c ']'> \u11be;" // hangul jongseong chieuch
+ "bs ']'> \u11b9;" // hangul jongseong pieup-sios
+ "b ']'> \u11b8;" // hangul jongseong pieup
+ "$medial{ t <> $MEDIAL{ \u11c0;" // hangul jongseong thieuth
+ "$medial{ ss <> $MEDIAL{ \u11bb;" // hangul jongseong ssangsios
+ "$medial{ s <> $MEDIAL{ \u11ba;" // hangul jongseong sios
+ "$medial{ p <> $MEDIAL{ \u11c1;" // hangul jongseong phieuph
+ "$medial{ nj <> $MEDIAL{ \u11ac;" // hangul jongseong nieun-cieuc
+ "$medial{ nh <> $MEDIAL{ \u11ad;" // hangul jongseong nieun-hieuh
+ "$medial{ ng <> $MEDIAL{ \u11bc;" // hangul jongseong ieung
+ "$medial{ n <> $MEDIAL{ \u11ab;" // hangul jongseong nieun
+ "$medial{ m <> $MEDIAL{ \u11b7;" // hangul jongseong mieum
+ "$medial{ lt <> $MEDIAL{ \u11b4;" // hangul jongseong rieul-thieuth
+ "$medial{ ls <> $MEDIAL{ \u11b3;" // hangul jongseong rieul-sios
+ "$medial{ lp <> $MEDIAL{ \u11b5;" // hangul jongseong rieul-phieuph
+ "$medial{ lm <> $MEDIAL{ \u11b1;" // hangul jongseong rieul-mieum
+ "$medial{ lh <> $MEDIAL{ \u11b6;" // hangul jongseong rieul-hieuh
+ "$medial{ lg <> $MEDIAL{ \u11b0;" // hangul jongseong rieul-kiyeok
+ "$medial{ lb <> $MEDIAL{ \u11b2;" // hangul jongseong rieul-pieup
+ "$medial{ l <> $MEDIAL{ \u11af;" // hangul jongseong rieul
+ "$medial{ k <> $MEDIAL{ \u11bf;" // hangul jongseong khieukh
+ "$medial{ j <> $MEDIAL{ \u11bd;" // hangul jongseong cieuc
+ "$medial{ h <> $MEDIAL{ \u11c2;" // hangul jongseong hieuh
+ "$medial{ gs <> $MEDIAL{ \u11aa;" // hangul jongseong kiyeok-sios
+ "$medial{ gg <> $MEDIAL{ \u11a9;" // hangul jongseong ssangkiyeok
+ "$medial{ g <> $MEDIAL{ \u11a8;" // hangul jongseong kiyeok
+ "$medial{ d <> $MEDIAL{ \u11ae;" // hangul jongseong tikeut
+ "$medial{ c <> $MEDIAL{ \u11be;" // hangul jongseong chieuch
+ "$medial{ bs <> $MEDIAL{ \u11b9;" // hangul jongseong pieup-sios
+ "$medial{ b <> $MEDIAL{ \u11b8;" // hangul jongseong pieup
+ "t ']'< \u11c0;" // hangul jongseong thieuth
+ "ss ']'< \u11bb;" // hangul jongseong ssangsios
+ "s ']'< \u11ba;" // hangul jongseong sios
+ "p ']'< \u11c1;" // hangul jongseong phieuph
+ "nj ']'< \u11ac;" // hangul jongseong nieun-cieuc
+ "nh ']'< \u11ad;" // hangul jongseong nieun-hieuh
+ "ng ']'< \u11bc;" // hangul jongseong ieung
+ "n ']'< \u11ab;" // hangul jongseong nieun
+ "m ']'< \u11b7;" // hangul jongseong mieum
+ "lt ']'< \u11b4;" // hangul jongseong rieul-thieuth
+ "ls ']'< \u11b3;" // hangul jongseong rieul-sios
+ "lp ']'< \u11b5;" // hangul jongseong rieul-phieuph
+ "lm ']'< \u11b1;" // hangul jongseong rieul-mieum
+ "lh ']'< \u11b6;" // hangul jongseong rieul-hieuh
+ "lg ']'< \u11b0;" // hangul jongseong rieul-kiyeok
+ "lb ']'< \u11b2;" // hangul jongseong rieul-pieup
+ "l ']'< \u11af;" // hangul jongseong rieul
+ "k ']'< \u11bf;" // hangul jongseong khieukh
+ "j ']'< \u11bd;" // hangul jongseong cieuc
+ "h ']'< \u11c2;" // hangul jongseong hieuh
+ "gs ']'< \u11aa;" // hangul jongseong kiyeok-sios
+ "gg ']'< \u11a9;" // hangul jongseong ssangkiyeok
+ "g ']'< \u11a8;" // hangul jongseong kiyeok
+ "d ']'< \u11ae;" // hangul jongseong tikeut
+ "c ']'< \u11be;" // hangul jongseong chieuch
+ "bs ']'< \u11b9;" // hangul jongseong pieup-sios
+ "b ']'< \u11b8;" // hangul jongseong pieup
// extra English letters
// + "z > |s;"
// //{ + "Z > |s;" } masked
// + "x > |ks;"
// + "X > |ks;"
// + "v > |b;"
// + "V > |b;"
// + "r > |l;"
// + "R > |l;"
// + "q > |k;"
// + "Q > |k;"
// + "f > |p;"
// + "F > |p;"
// //{ + "c > |k;" } masked
// + "C > |k;"
// + "y > \u1172;" // hangul jungseong yu
// + "w > \u1171;" // hangul jungseong wi
}
};
}
}

986
icu4j/src/com/ibm/text/resources/TransliterationRule_Latin_Kana.java
View File

@ -1,986 +0,0 @@
/*
*******************************************************************************
* Copyright (C) 1996-2000, International Business Machines Corporation and *
* others. All Rights Reserved. *
*******************************************************************************
*
* $Source: /xsrl/Nsvn/icu/icu4j/src/com/ibm/text/resources/Attic/TransliterationRule_Latin_Kana.java,v $
* $Date: 2000/07/05 23:07:58 $
* $Revision: 1.7 $
*
*****************************************************************************************
*/
package com.ibm.text.resources;
import java.util.ListResourceBundle;
public class TransliterationRule_Latin_Kana extends ListResourceBundle {
/**
* Overrides ListResourceBundle
*/
public Object[][] getContents() {
return new Object[][] {
{ "Rule", ""
// Japanese hiragana and katakana to and from latin
// (romaji). Lower case latin corresponds to hiragana;
// upper case latin to katakana. The handling of
// Hiragana and Katakana is largely the same. The bulk
// of the transliterator consists of two identical sets
// of rules, differing only in case.
// Because of minor differences between the two blocks
// (e.g., the existence of small katakana ka and ke, but
// no corresponding hiragana), some rules exist for only
// one script.
// Uses modified Hepburn. Small changes to make
// unambiguous.
//| Kunrei-shiki: Hepburn/MHepburn
//| ------------------------------
//| si: shi
//| si ~ya: sha
//| si ~yu: shu
//| si ~yo: sho
//| zi: ji
//| zi ~ya: ja
//| zi ~yu: ju
//| zi ~yo: jo
//| ti: chi
//| ti ~ya: cha
//| ti ~yu: chu
//| ti ~yu: cho
//| tu: tsu
//| di: ji/dji
//| du: zu/dzu
//| hu: fu
//| For foreign words:
//| -----------------
//| se ~i si
//| si ~e she
//|
//| ze ~i zi
//| zi ~e je
//|
//| te ~i ti
//| ti ~e che
//| te ~u tu
//|
//| de ~i di
//| de ~u du
//| de ~i di
//|
//| he ~u: hu
//| hu ~a fa
//| hu ~i fi
//| hu ~e he
//| hu ~o ho
// Most small forms are generated, but if necessary
// explicit small forms are given with ~a, ~ya, etc.
//------------------------------------------------------
// Variables
+ "$vowel=[aeiou];"
+ "$QUOTE='';"
// Hiragana block
+ "$a2=\u3041;"
+ "$a=\u3042;"
+ "$i2=\u3043;"
+ "$i=\u3044;"
+ "$u2=\u3045;"
+ "$u=\u3046;"
+ "$e2=\u3047;"
+ "$e=\u3048;"
+ "$o2=\u3049;"
+ "$o=\u304A;"
+ "$ka=\u304B;"
+ "$ga=\u304C;"
+ "$ki=\u304D;"
+ "$gi=\u304E;"
+ "$ku=\u304F;"
+ "$gu=\u3050;"
+ "$ke=\u3051;"
+ "$ge=\u3052;"
+ "$ko=\u3053;"
+ "$go=\u3054;"
+ "$sa=\u3055;"
+ "$za=\u3056;"
+ "$si=\u3057;"
+ "$zi=\u3058;"
+ "$su=\u3059;"
+ "$zu=\u305A;"
+ "$se=\u305B;"
+ "$ze=\u305C;"
+ "$so=\u305D;"
+ "$zo=\u305E;"
+ "$ta=\u305F;"
+ "$da=\u3060;"
+ "$ti=\u3061;"
+ "$di=\u3062;"
+ "$tu2=\u3063;"
+ "$tu=\u3064;"
+ "$du=\u3065;"
+ "$te=\u3066;"
+ "$de=\u3067;"
+ "$to=\u3068;"
+ "$do=\u3069;"
+ "$na=\u306A;"
+ "$ni=\u306B;"
+ "$nu=\u306C;"
+ "$ne=\u306D;"
+ "$no=\u306E;"
+ "$ha=\u306F;"
+ "$ba=\u3070;"
+ "$pa=\u3071;"
+ "$hi=\u3072;"
+ "$bi=\u3073;"
+ "$pi=\u3074;"
+ "$hu=\u3075;"
+ "$bu=\u3076;"
+ "$pu=\u3077;"
+ "$he=\u3078;"
+ "$be=\u3079;"
+ "$pe=\u307A;"
+ "$ho=\u307B;"
+ "$bo=\u307C;"
+ "$po=\u307D;"
+ "$ma=\u307E;"
+ "$mi=\u307F;"
+ "$mu=\u3080;"
+ "$me=\u3081;"
+ "$mo=\u3082;"
+ "$ya2=\u3083;"
+ "$ya=\u3084;"
+ "$yu2=\u3085;"
+ "$yu=\u3086;"
+ "$yo2=\u3087;"
+ "$yo=\u3088;"
+ "$ra=\u3089;"
+ "$ri=\u308A;"
+ "$ru=\u308B;"
+ "$re=\u308C;"
+ "$ro=\u308D;"
+ "$wa2=\u308E;"
+ "$wa=\u308F;"
+ "$wi=\u3090;"
+ "$we=\u3091;"
+ "$wo=\u3092;"
+ "$n=\u3093;"
+ "$vu=\u3094;"
// Alternates, just to make the rules easier
+ "$yi2=\u3043;"
+ "$yi=\u3044;"
+ "$ye2=\u3047;"
+ "$ye=\u3048;"
+ "$wu=$u;"
// End alternates
// Katakana block
+ "$A2=\u30A1;"
+ "$A=\u30A2;"
+ "$I2=\u30A3;"
+ "$I=\u30A4;"
+ "$U2=\u30A5;"
+ "$U=\u30A6;"
+ "$E2=\u30A7;"
+ "$E=\u30A8;"
+ "$O2=\u30A9;"
+ "$O=\u30AA;"
+ "$KA=\u30AB;"
+ "$GA=\u30AC;"
+ "$KI=\u30AD;"
+ "$GI=\u30AE;"
+ "$KU=\u30AF;"
+ "$GU=\u30B0;"
+ "$KE=\u30B1;"
+ "$GE=\u30B2;"
+ "$KO=\u30B3;"
+ "$GO=\u30B4;"
+ "$KA2=\u30F5;" // Small Katakana KA; no Hiragana equiv.
+ "$KE2=\u30F6;" // Small Katakana KE; no Hiragana equiv.
+ "$SA=\u30B5;"
+ "$ZA=\u30B6;"
+ "$SI=\u30B7;"
+ "$ZI=\u30B8;"
+ "$SU=\u30B9;"
+ "$ZU=\u30BA;"
+ "$SE=\u30BB;"
+ "$ZE=\u30BC;"
+ "$SO=\u30BD;"
+ "$ZO=\u30BE;"
+ "$TA=\u30BF;"
+ "$DA=\u30C0;"
+ "$TI=\u30C1;"
+ "$DI=\u30C2;"
+ "$TU2=\u30C3;"
+ "$TU=\u30C4;"
+ "$DU=\u30C5;"
+ "$TE=\u30C6;"
+ "$DE=\u30C7;"
+ "$TO=\u30C8;"
+ "$DO=\u30C9;"
+ "$NA=\u30CA;"
+ "$NI=\u30CB;"
+ "$NU=\u30CC;"
+ "$NE=\u30CD;"
+ "$NO=\u30CE;"
+ "$HA=\u30CF;"
+ "$BA=\u30D0;"
+ "$PA=\u30D1;"
+ "$HI=\u30D2;"
+ "$BI=\u30D3;"
+ "$PI=\u30D4;"
+ "$HU=\u30D5;"
+ "$BU=\u30D6;"
+ "$PU=\u30D7;"
+ "$HE=\u30D8;"
+ "$BE=\u30D9;"
+ "$PE=\u30DA;"
+ "$HO=\u30DB;"
+ "$BO=\u30DC;"
+ "$PO=\u30DD;"
+ "$MA=\u30DE;"
+ "$MI=\u30DF;"
+ "$MU=\u30E0;"
+ "$ME=\u30E1;"
+ "$MO=\u30E2;"
+ "$YA2=\u30E3;"
+ "$YA=\u30E4;"
+ "$YU2=\u30E5;"
+ "$YU=\u30E6;"
+ "$YO2=\u30E7;"
+ "$YO=\u30E8;"
+ "$WA2=\u30EE;"
// Alternates, just to make the rules easier
+ "$YI2=\u30A3;"
+ "$YI=\u30A4;"
+ "$YE2=\u30A7;"
+ "$YE=\u30A8;"
+ "$WU=$U;"
// End alternates
+ "$RA=\u30E9;"
+ "$RI=\u30EA;"
+ "$RU=\u30EB;"
+ "$RE=\u30EC;"
+ "$RO=\u30ED;"
+ "$VA=\u30F7;"
+ "$VI=\u30F8;"
+ "$VU=\u30F4;"
+ "$VE=\u30F9;"
+ "$VO=\u30FA;"
+ "$WA=\u30EF;"
+ "$WI=\u30F0;"
+ "$WE=\u30F1;"
+ "$WO=\u30F2;"
+ "$N=\u30F3;"
+ "$LONG=\u30FC;"
// Variables used for doubled-consonants with tsu
+ "$K_START=[$KA$KI$KU$KE$KO$ka$ki$ku$ke$ko];"
+ "$G_START=[$GA$GI$GU$GE$GO$ga$gi$gu$ge$go];"
+ "$S_START=[$SA$SI$SU$SE$SO$sa$si$su$se$so];"
+ "$Z_START=[$ZA$ZU$ZE$ZO$za$zu$ze$zo];"
+ "$J_START=[$ZI$zi];"
+ "$T_START=[$TA$TI$TU$TE$TO$ta$ti$tu$te$to];"
+ "$D_START=[$DA$DI$DU$DE$DO$da$di$du$de$do];"
+ "$N_START=[$NA$NI$NU$NE$NO$na$ni$nu$ne$no];"
+ "$H_START=[$HA$HI$HE$HO$ha$hi$he$ho];"
+ "$F_START=[$HU$hu];"
+ "$B_START=[$BA$BI$BU$BE$BO$ba$bi$bu$be$bo];"
+ "$P_START=[$PA$PI$PU$PE$PO$pa$pi$pu$pe$po];"
+ "$M_START=[$MA$MI$MU$ME$MO$ma$mi$mu$me$mo];"
+ "$Y_START=[$YA$YU$YO$ya$yu$yo];"
+ "$R_START=[$RA$RI$RU$RE$RO$ra$ri$ru$re$ro];"
+ "$W_START=[$WA$WI$WE$WO$wa$wi$we$wo];"
+ "$V_START=[$VA$VI$VU$VE$VO$vu];"
// If $N is followed by $N_QUOTER, then it needs an
// apostrophe after its romaji form to disambiguate it.
// E.g., $N $A != $NA, so represent as "n'a", not "na".
+ "$N_QUOTER = [$A $I $U $E $O $NA $NI $NU $NE $NO"
+ " $YA $YU $YO $N];"
+ "$n_quoter = [$a $i $u $e $o $na $ni $nu $ne $no"
+ " $ya $yu $yo $n];"
// Lowercase copies for convenience in making hiragana
// rule set copy
+ "$long = $LONG;"
+ "$quote = $QUOTE;"
+ "$k_start=$K_START;"
+ "$g_start=$G_START;"
+ "$s_start=$S_START;"
+ "$z_start=$Z_START;"
+ "$j_start=$J_START;"
+ "$t_start=$T_START;"
+ "$d_start=$D_START;"
+ "$n_start=$N_START;"
+ "$h_start=$H_START;"
+ "$f_start=$F_START;"
+ "$b_start=$B_START;"
+ "$p_start=$P_START;"
+ "$m_start=$M_START;"
+ "$y_start=$Y_START;"
+ "$r_start=$R_START;"
+ "$w_start=$W_START;"
+ "$v_start=$V_START;"
//------------------------------------------------------
// Katakana rules
// The rules immediately following are not shared. That
// is, they exist only for katakana, not for hiragana.
+ "VA<>$VA;"
+ "VI<>$VI;"
+ "VE<>$VE;"
+ "VO<>$VO;"
+ "'~KA'<>$KA2;"
+ "'~KE'<>$KE2;"
// ~~~ BEGIN shared rules ~~~
// The shared rules are copied from katakana to hiragana
// and then mechanically lowercased.
+ "A<>$A;"
+ "BA<>$BA;"
+ "BYA<$BI$YA2;"
+ "BYI<$BI$I2;"
+ "BYU<$BI$YU2;"
+ "BYE<$BI$E2;"
+ "BYO<$BI$YO2;"
+ "BI<>$BI;"
+ "BU<>$BU;"
+ "BE<>$BE;"
+ "BO<>$BO;"
+ "BY>$BI|'~Y';"
+ "CHA<$TI$YA2;"
+ "CHI'~I'<$TI$I2;" // Liu
+ "CHU<$TI$YU2;"
+ "CHE<$TI$E2;"
+ "CHO<$TI$YO2;"
+ "CHI<>$TI;"
+ "CH>$TI|'~Y';"
+ "C}I>|S;"
+ "C}E>|S;"
+ "DA<>$DA;"
+ "DI<>$DE$I2;"
+ "DU<>$DE$U2;"
+ "DE<>$DE;"
+ "DO<>$DO;"
+ "DZU<>$DU;"
+ "DJA<$DI$YA2;"
+ "DJI'~I'<$DI$I2;" // Liu
+ "DJU<$DI$YU2;"
+ "DJE<$DI$E2;"
+ "DJO<$DI$YO2;"
+ "DJI<>$DI;"
+ "DJ>$DI|'~Y';"
+ "E<>$E;"
+ "FA<$HU$A2;"
+ "FI<$HU$I2;"
+ "FE<$HU$E2;"
+ "FO<$HU$O2;"
+ "FU<>$HU;"
+ "GA<>$GA;"
+ "GYA<$GI$YA2;"
+ "GYI<$GI$I2;"
+ "GYU<$GI$YU2;"
+ "GYE<$GI$E2;"
+ "GYO<$GI$YO2;"
+ "GI<>$GI;"
+ "GU<>$GU;"
+ "GE<>$GE;"
+ "GO<>$GO;"
+ "GY>$GI|'~Y';"
+ "HA<>$HA;"
+ "HI<>$HI;"
+ "HU<>$HE$U2;"
+ "HE<>$HE;"
+ "HO<>$HO;"
+ "I<>$I;"
+ "JA<$ZI$YA2;"
+ "JI'~I'<$ZI$I2;" // Liu
+ "JU<$ZI$YU2;"
+ "JE<$ZI$E2;"
+ "JO<$ZI$YO2;"
+ "JI<>$ZI;"
+ "KA<>$KA;"
+ "KYA<$KI$YA2;"
+ "KYI<$KI$I2;"
+ "KYU<$KI$YU2;"
+ "KYE<$KI$E2;"
+ "KYO<$KI$YO2;"
+ "KI<>$KI;"
+ "KU<>$KU;"
+ "KE<>$KE;"
+ "KO<>$KO;"
+ "KY>$KI|'~Y';"
+ "MA<>$MA;"
+ "MYA<$MI$YA2;"
+ "MYI<$MI$I2;"
+ "MYU<$MI$YU2;"
+ "MYE<$MI$E2;"
+ "MYO<$MI$YO2;"
+ "MI<>$MI;"
+ "MU<>$MU;"
+ "ME<>$ME;"
+ "MO<>$MO;"
+ "MY>$MI|'~Y';"
+ "M}P>$N;"
+ "M}B>$N;"
+ "M}F>$N;"
+ "M}V>$N;"
+ "NA<>$NA;"
+ "NYA<$NI$YA2;"
+ "NYI<$NI$I2;"
+ "NYU<$NI$YU2;"
+ "NYE<$NI$E2;"
+ "NYO<$NI$YO2;"
+ "NI<>$NI;"
+ "NU<>$NU;"
+ "NE<>$NE;"
+ "NO<>$NO;"
+ "NY>$NI|'~Y';"
+ "O<>$O;"
+ "PA<>$PA;"
+ "PYA<$PI$YA2;"
+ "PYI<$PI$I2;"
+ "PYU<$PI$YU2;"
+ "PYE<$PI$E2;"
+ "PYO<$PI$YO2;"
+ "PI<>$PI;"
+ "PU<>$PU;"
+ "PE<>$PE;"
+ "PO<>$PO;"
+ "PY>$PI|'~Y';"
+ "RA<>$RA;"
+ "RYA<$RI$YA2;"
+ "RYI<$RI$I2;"
+ "RYU<$RI$YU2;"
+ "RYE<$RI$E2;"
+ "RYO<$RI$YO2;"
+ "RI<>$RI;"
+ "RU<>$RU;"
+ "RE<>$RE;"
+ "RO<>$RO;"
+ "RY>$RI|'~Y';"
+ "SA<>$SA;"
+ "SI<>$SE$I2;"
+ "SU<>$SU;"
+ "SE<>$SE;"
+ "SO<>$SO;"
+ "SHA<$SI$YA2;"
+ "SHI'~I'<$SI$I2;" // Liu
+ "SHU<$SI$YU2;"
+ "SHE<$SI$E2;"
+ "SHO<$SI$YO2;"
+ "SHI<>$SI;"
+ "SH>$SI|'~Y';"
+ "TA<>$TA;"
+ "TI<>$TE$I2;"
+ "TU<>$TE$U2;"
+ "TE<>$TE;"
+ "TO<>$TO;"
// Double consonants
+ "B}B<>$TU2}$B_START;"
+ "C}K>$TU2;"
+ "C}C>$TU2;"
+ "C}Q>$TU2;"
+ "D}D<>$TU2}$D_START;"
+ "F}F<>$TU2}$F_START;"
+ "G}G<>$TU2}$G_START;"
+ "H}H<>$TU2}$H_START;"
+ "J}J<>$TU2}$J_START;"
+ "K}K<>$TU2}$K_START;"
+ "L}L>$TU2;"
+ "M}M<>$TU2}$M_START;"
+ "N}N<>$TU2}$N_START;"
+ "P}P<>$TU2}$P_START;"
+ "Q}Q>$TU2;"
+ "R}R<>$TU2}$R_START;"
+ "S}SH>$TU2;"
+ "S}S<>$TU2}$S_START;"
+ "T}CH>$TU2;"
+ "T}T<>$TU2}$T_START;"
+ "V}V<>$TU2}$V_START;"
+ "W}W<>$TU2}$W_START;"
+ "X}X>$TU2;"
+ "Y}Y<>$TU2}$Y_START;"
+ "Z}Z<>$TU2}$Z_START;"
+ "TSU<>$TU;"
+ "U<>$U;"
+ "'V~A'<$VU$A2;" // Liu
+ "'V~I'<$VU$I2;" // Liu
+ "'V~E'<$VU$E2;" // Liu
+ "'V~O'<$VU$O2;" // Liu
+ "VU<>$VU;"
+ "WA<>$WA;"
+ "WI<>$WI;"
+ "WU>$WU;"
+ "WE<>$WE;"
+ "WO<>$WO;"
+ "YA<>$YA;"
+ "YI>$YI;"
+ "YU<>$YU;"
+ "YE>$YE;"
+ "YO<>$YO;"
+ "ZA<>$ZA;"
+ "ZI<>$ZE$I2;"
+ "ZU<>$ZU;"
+ "ZE<>$ZE;"
+ "ZO<>$ZO;"
// Prolonged vowel mark. This indicates a doubling of
// the preceding vowel sound in both katakana and
// hiragana.
+ "A<A{$LONG;" // Liu
+ "E<E{$LONG;" // Liu
+ "I<I{$LONG;" // Liu
+ "O<O{$LONG;" // Liu
+ "U<U{$LONG;" // Liu
// Small forms
+ "'~A'<>$A2;"
+ "'~I'<>$I2;"
+ "'~U'<>$U2;"
+ "'~E'<>$E2;"
+ "'~O'<>$O2;"
+ "'~TSU'<>$TU2;"
+ "'~WA'<>$WA2;"
+ "'~YA'<>$YA2;"
+ "'~YI'>$YI2;"
+ "'~YU'<>$YU2;"
+ "'~YE'>$YE2;"
+ "'~YO'<>$YO2;"
// One-way latin->kana rules. These do not occur in
// well-formed romaji representing actual Japanese text.
// Their purpose is to make all romaji map to kana of
// some sort.
// The following are not really necessary, but produce
// slightly more natural results.
+ "CY>$SE$I2;"
+ "DY>$DE$I2;"
+ "HY>$HI;"
+ "SY>$SE$I2;"
+ "TY>$TE$I2;"
+ "ZY>$ZE$I2;"
// Simple substitutions using backup
+ "C>|K;"
+ "F>$HU|'~';"
+ "J>$ZI|'~Y';"
+ "L>|R;"
+ "Q>|K;"
+ "V>$VU|'~';"
+ "W>$U|'~';"
+ "X>|KS;"
// Isolated consonants listed here so as not to mask
// longer rules above.
+ "B>$BU;"
+ "D>$DE;"
+ "G>$GU;"
+ "H>$HE;"
+ "K>$KU;"
+ "M>$N;"
+ "N''<$N}$N_QUOTER;"
+ "N<>$N;"
+ "P>$PU;"
+ "R>$RU;"
+ "S>$SU;"
+ "T>$TE;"
+ "Y>$I;"
+ "Z>$ZU;"
// ~~~ END shared rules ~~~
//------------------------------------------------------
// Hiragana rules
// Currently, there are no hiragana rules other than the
// shared rules.
// ~~~ BEGIN shared rules ~~~
// The shared rules are copied from katakana to hiragana
// and then mechanically lowercased.
+ "a<>$a;"
+ "ba<>$ba;"
+ "bya<$bi$ya2;"
+ "byi<$bi$i2;"
+ "byu<$bi$yu2;"
+ "bye<$bi$e2;"
+ "byo<$bi$yo2;"
+ "bi<>$bi;"
+ "bu<>$bu;"
+ "be<>$be;"
+ "bo<>$bo;"
+ "by>$bi|'~y';"
+ "cha<$ti$ya2;"
+ "chi'~i'<$ti$i2;" // liu
+ "chu<$ti$yu2;"
+ "che<$ti$e2;"
+ "cho<$ti$yo2;"
+ "chi<>$ti;"
+ "ch>$ti|'~y';"
+ "c}i>|s;"
+ "c}e>|s;"
+ "da<>$da;"
+ "di<>$de$i2;"
+ "du<>$de$u2;"
+ "de<>$de;"
+ "do<>$do;"
+ "dzu<>$du;"
+ "dja<$di$ya2;"
+ "dji'~i'<$di$i2;" // liu
+ "dju<$di$yu2;"
+ "dje<$di$e2;"
+ "djo<$di$yo2;"
+ "dji<>$di;"
+ "dj>$di|'~y';"
+ "e<>$e;"
+ "fa<$hu$a2;"
+ "fi<$hu$i2;"
+ "fe<$hu$e2;"
+ "fo<$hu$o2;"
+ "fu<>$hu;"
+ "ga<>$ga;"
+ "gya<$gi$ya2;"
+ "gyi<$gi$i2;"
+ "gyu<$gi$yu2;"
+ "gye<$gi$e2;"
+ "gyo<$gi$yo2;"
+ "gi<>$gi;"
+ "gu<>$gu;"
+ "ge<>$ge;"
+ "go<>$go;"
+ "gy>$gi|'~y';"
+ "ha<>$ha;"
+ "hi<>$hi;"
+ "hu<>$he$u2;"
+ "he<>$he;"
+ "ho<>$ho;"
+ "i<>$i;"
+ "ja<$zi$ya2;"
+ "ji'~i'<$zi$i2;" // liu
+ "ju<$zi$yu2;"
+ "je<$zi$e2;"
+ "jo<$zi$yo2;"
+ "ji<>$zi;"
+ "ka<>$ka;"
+ "kya<$ki$ya2;"
+ "kyi<$ki$i2;"
+ "kyu<$ki$yu2;"
+ "kye<$ki$e2;"
+ "kyo<$ki$yo2;"
+ "ki<>$ki;"
+ "ku<>$ku;"
+ "ke<>$ke;"
+ "ko<>$ko;"
+ "ky>$ki|'~y';"
+ "ma<>$ma;"
+ "mya<$mi$ya2;"
+ "myi<$mi$i2;"
+ "myu<$mi$yu2;"
+ "mye<$mi$e2;"
+ "myo<$mi$yo2;"
+ "mi<>$mi;"
+ "mu<>$mu;"
+ "me<>$me;"
+ "mo<>$mo;"
+ "my>$mi|'~y';"
+ "m}p>$n;"
+ "m}b>$n;"
+ "m}f>$n;"
+ "m}v>$n;"
+ "na<>$na;"
+ "nya<$ni$ya2;"
+ "nyi<$ni$i2;"
+ "nyu<$ni$yu2;"
+ "nye<$ni$e2;"
+ "nyo<$ni$yo2;"
+ "ni<>$ni;"
+ "nu<>$nu;"
+ "ne<>$ne;"
+ "no<>$no;"
+ "ny>$ni|'~y';"
+ "o<>$o;"
+ "pa<>$pa;"
+ "pya<$pi$ya2;"
+ "pyi<$pi$i2;"
+ "pyu<$pi$yu2;"
+ "pye<$pi$e2;"
+ "pyo<$pi$yo2;"
+ "pi<>$pi;"
+ "pu<>$pu;"
+ "pe<>$pe;"
+ "po<>$po;"
+ "py>$pi|'~y';"
+ "ra<>$ra;"
+ "rya<$ri$ya2;"
+ "ryi<$ri$i2;"
+ "ryu<$ri$yu2;"
+ "rye<$ri$e2;"
+ "ryo<$ri$yo2;"
+ "ri<>$ri;"
+ "ru<>$ru;"
+ "re<>$re;"
+ "ro<>$ro;"
+ "ry>$ri|'~y';"
+ "sa<>$sa;"
+ "si<>$se$i2;"
+ "su<>$su;"
+ "se<>$se;"
+ "so<>$so;"
+ "sha<$si$ya2;"
+ "shi'~i'<$si$i2;" // liu
+ "shu<$si$yu2;"
+ "she<$si$e2;"
+ "sho<$si$yo2;"
+ "shi<>$si;"
+ "sh>$si|'~y';"
+ "ta<>$ta;"
+ "ti<>$te$i2;"
+ "tu<>$te$u2;"
+ "te<>$te;"
+ "to<>$to;"
// double consonants
+ "b}b<>$tu2}$b_start;"
+ "c}k>$tu2;"
+ "c}c>$tu2;"
+ "c}q>$tu2;"
+ "d}d<>$tu2}$d_start;"
+ "f}f<>$tu2}$f_start;"
+ "g}g<>$tu2}$g_start;"
+ "h}h<>$tu2}$h_start;"
+ "j}j<>$tu2}$j_start;"
+ "k}k<>$tu2}$k_start;"
+ "l}l>$tu2;"
+ "m}m<>$tu2}$m_start;"
+ "n}n<>$tu2}$n_start;"
+ "p}p<>$tu2}$p_start;"
+ "q}q>$tu2;"
+ "r}r<>$tu2}$r_start;"
+ "s}sh>$tu2;"
+ "s}s<>$tu2}$s_start;"
+ "t}ch>$tu2;"
+ "t}t<>$tu2}$t_start;"
+ "v}v<>$tu2}$v_start;"
+ "w}w<>$tu2}$w_start;"
+ "x}x>$tu2;"
+ "y}y<>$tu2}$y_start;"
+ "z}z<>$tu2}$z_start;"
+ "tsu<>$tu;"
+ "u<>$u;"
+ "'v~a'<$vu$a2;" // liu
+ "'v~i'<$vu$i2;" // liu
+ "'v~e'<$vu$e2;" // liu
+ "'v~o'<$vu$o2;" // liu
+ "vu<>$vu;"
+ "wa<>$wa;"
+ "wi<>$wi;"
+ "wu>$wu;"
+ "we<>$we;"
+ "wo<>$wo;"
+ "ya<>$ya;"
+ "yi>$yi;"
+ "yu<>$yu;"
+ "ye>$ye;"
+ "yo<>$yo;"
+ "za<>$za;"
+ "zi<>$ze$i2;"
+ "zu<>$zu;"
+ "ze<>$ze;"
+ "zo<>$zo;"
// prolonged vowel mark. this indicates a doubling of
// the preceding vowel sound in both katakana and
// hiragana.
+ "a<a{$long;" // liu
+ "e<e{$long;" // liu
+ "i<i{$long;" // liu
+ "o<o{$long;" // liu
+ "u<u{$long;" // liu
// small forms
+ "'~a'<>$a2;"
+ "'~i'<>$i2;"
+ "'~u'<>$u2;"
+ "'~e'<>$e2;"
+ "'~o'<>$o2;"
+ "'~tsu'<>$tu2;"
+ "'~wa'<>$wa2;"
+ "'~ya'<>$ya2;"
+ "'~yi'>$yi2;"
+ "'~yu'<>$yu2;"
+ "'~ye'>$ye2;"
+ "'~yo'<>$yo2;"
// one-way latin->kana rules. these do not occur in
// well-formed romaji representing actual japanese text.
// their purpose is to make all romaji map to kana of
// some sort.
// the following are not really necessary, but produce
// slightly more natural results.
+ "cy>$se$i2;"
+ "dy>$de$i2;"
+ "hy>$hi;"
+ "sy>$se$i2;"
+ "ty>$te$i2;"
+ "zy>$ze$i2;"
// simple substitutions using backup
+ "c>|k;"
+ "f>$hu|'~';"
+ "j>$zi|'~y';"
+ "l>|r;"
+ "q>|k;"
+ "v>$vu|'~';"
+ "w>$u|'~';"
+ "x>|ks;"
// isolated consonants listed here so as not to mask
// longer rules above.
+ "b>$bu;"
+ "d>$de;"
+ "g>$gu;"
+ "h>$he;"
+ "k>$ku;"
+ "m>$n;"
+ "n''<$n}$n_quoter;"
+ "n<>$n;"
+ "p>$pu;"
+ "r>$ru;"
+ "s>$su;"
+ "t>$te;"
+ "y>$i;"
+ "z>$zu;"
// ~~~ END shared rules ~~~
//------------------------------------------------------
// Final cleanup
+ "'~'>;" // delete stray tildes
+ "$quote>;" // delete stray quotes
+ "'-'>$long;"
}
};
}
}

104
icu4j/src/com/ibm/text/resources/TransliterationRule_Malayalam_InterIndic.java
View File

@ -1,104 +0,0 @@
/***********************************************************************
* Copyright (c) 2000, International Business Machines Corporation
* and others. All Rights Reserved.
************************************************************************
* > THIS FILE WAS MACHINE GENERATED <
* > DO NOT EDIT BY HAND <
* > RUN TOOL TO REGENERATE <
* Tool: icu4j/src/com/ibm/tools/translit/indic.pl
* Creation date: Fri Oct 6 15:55:21 2000
*/
package com.ibm.text.resources;
import java.util.ListResourceBundle;
public class TransliterationRule_Malayalam_InterIndic extends ListResourceBundle {
/**
* Overrides ListResourceBundle
*/
public Object[][] getContents() {
return new Object[][] {
{ "Rule",
"\u0D02>\uE002;"+ // SIGN ANUSVARA
"\u0D03>\uE003;"+ // SIGN VISARGA
"\u0D05>\uE005;"+ // LETTER A
"\u0D06>\uE006;"+ // LETTER AA
"\u0D07>\uE007;"+ // LETTER I
"\u0D08>\uE008;"+ // LETTER II
"\u0D09>\uE009;"+ // LETTER U
"\u0D0A>\uE00A;"+ // LETTER UU
"\u0D0B>\uE00B;"+ // LETTER VOCALIC R
"\u0D0C>\uE00C;"+ // LETTER VOCALIC L
"\u0D0E>\uE081;"+ // LETTER E
"\u0D0F>\uE00F;"+ // LETTER EE
"\u0D10>\uE010;"+ // LETTER AI
"\u0D12>\uE082;"+ // LETTER O
"\u0D13>\uE013;"+ // LETTER OO
"\u0D14>\uE014;"+ // LETTER AU
"\u0D15>\uE015;"+ // LETTER KA
"\u0D16>\uE016;"+ // LETTER KHA
"\u0D17>\uE017;"+ // LETTER GA
"\u0D18>\uE018;"+ // LETTER GHA
"\u0D19>\uE019;"+ // LETTER NGA
"\u0D1A>\uE01A;"+ // LETTER CA
"\u0D1B>\uE01B;"+ // LETTER CHA
"\u0D1C>\uE01C;"+ // LETTER JA
"\u0D1D>\uE01D;"+ // LETTER JHA
"\u0D1E>\uE01E;"+ // LETTER NYA
"\u0D1F>\uE01F;"+ // LETTER TTA
"\u0D20>\uE020;"+ // LETTER TTHA
"\u0D21>\uE021;"+ // LETTER DDA
"\u0D22>\uE022;"+ // LETTER DDHA
"\u0D23>\uE023;"+ // LETTER NNA
"\u0D24>\uE024;"+ // LETTER TA
"\u0D25>\uE025;"+ // LETTER THA
"\u0D26>\uE026;"+ // LETTER DA
"\u0D27>\uE027;"+ // LETTER DHA
"\u0D28>\uE028;"+ // LETTER NA
"\u0D2A>\uE02A;"+ // LETTER PA
"\u0D2B>\uE02B;"+ // LETTER PHA
"\u0D2C>\uE02C;"+ // LETTER BA
"\u0D2D>\uE02D;"+ // LETTER BHA
"\u0D2E>\uE02E;"+ // LETTER MA
"\u0D2F>\uE02F;"+ // LETTER YA
"\u0D30>\uE030;"+ // LETTER RA
"\u0D31>\uE083;"+ // LETTER RRA
"\u0D32>\uE032;"+ // LETTER LA
"\u0D33>\uE033;"+ // LETTER LLA
"\u0D34>\uE034;"+ // LETTER LLLA
"\u0D35>\uE035;"+ // LETTER VA
"\u0D36>\uE036;"+ // LETTER SHA
"\u0D37>\uE037;"+ // LETTER SSA
"\u0D38>\uE038;"+ // LETTER SA
"\u0D39>\uE039;"+ // LETTER HA
"\u0D3E>\uE03E;"+ // VOWEL SIGN AA
"\u0D3F>\uE03F;"+ // VOWEL SIGN I
"\u0D40>\uE040;"+ // VOWEL SIGN II
"\u0D41>\uE041;"+ // VOWEL SIGN U
"\u0D42>\uE042;"+ // VOWEL SIGN UU
"\u0D43>\uE043;"+ // VOWEL SIGN VOCALIC R
"\u0D46>\uE084;"+ // VOWEL SIGN E
"\u0D47>\uE047;"+ // VOWEL SIGN EE
"\u0D48>\uE048;"+ // VOWEL SIGN AI
"\u0D4A>\uE085;"+ // VOWEL SIGN O
"\u0D4B>\uE04B;"+ // VOWEL SIGN OO
"\u0D4C>\uE04C;"+ // VOWEL SIGN AU
"\u0D4D>\uE04D;"+ // SIGN VIRAMA
"\u0D57>\uE057;"+ // AU LENGTH MARK
"\u0D60>\uE060;"+ // LETTER VOCALIC RR
"\u0D61>\uE061;"+ // LETTER VOCALIC LL
"\u0D66>\uE066;"+ // DIGIT ZERO
"\u0D67>\uE067;"+ // DIGIT ONE
"\u0D68>\uE068;"+ // DIGIT TWO
"\u0D69>\uE069;"+ // DIGIT THREE
"\u0D6A>\uE06A;"+ // DIGIT FOUR
"\u0D6B>\uE06B;"+ // DIGIT FIVE
"\u0D6C>\uE06C;"+ // DIGIT SIX
"\u0D6D>\uE06D;"+ // DIGIT SEVEN
"\u0D6E>\uE06E;"+ // DIGIT EIGHT
"\u0D6F>\uE06F;"+ // DIGIT NINE
""
}
};
}
}

105
icu4j/src/com/ibm/text/resources/TransliterationRule_Oriya_InterIndic.java
View File

@ -1,105 +0,0 @@
/***********************************************************************
* Copyright (c) 2000, International Business Machines Corporation
* and others. All Rights Reserved.
************************************************************************
* > THIS FILE WAS MACHINE GENERATED <
* > DO NOT EDIT BY HAND <
* > RUN TOOL TO REGENERATE <
* Tool: icu4j/src/com/ibm/tools/translit/indic.pl
* Creation date: Fri Oct 6 15:55:21 2000
*/
package com.ibm.text.resources;
import java.util.ListResourceBundle;
public class TransliterationRule_Oriya_InterIndic extends ListResourceBundle {
/**
* Overrides ListResourceBundle
*/
public Object[][] getContents() {
return new Object[][] {
{ "Rule",
"\u0B01>\uE001;"+ // SIGN CANDRABINDU
"\u0B02>\uE002;"+ // SIGN ANUSVARA
"\u0B03>\uE003;"+ // SIGN VISARGA
"\u0B05>\uE005;"+ // LETTER A
"\u0B06>\uE006;"+ // LETTER AA
"\u0B07>\uE007;"+ // LETTER I
"\u0B08>\uE008;"+ // LETTER II
"\u0B09>\uE009;"+ // LETTER U
"\u0B0A>\uE00A;"+ // LETTER UU
"\u0B0B>\uE00B;"+ // LETTER VOCALIC R
"\u0B0C>\uE00C;"+ // LETTER VOCALIC L
"\u0B0F>\uE081;"+ // LETTER E
"\u0B10>\uE010;"+ // LETTER AI
"\u0B13>\uE082;"+ // LETTER O
"\u0B14>\uE014;"+ // LETTER AU
"\u0B15>\uE015;"+ // LETTER KA
"\u0B16>\uE016;"+ // LETTER KHA
"\u0B17>\uE017;"+ // LETTER GA
"\u0B18>\uE018;"+ // LETTER GHA
"\u0B19>\uE019;"+ // LETTER NGA
"\u0B1A>\uE01A;"+ // LETTER CA
"\u0B1B>\uE01B;"+ // LETTER CHA
"\u0B1C>\uE01C;"+ // LETTER JA
"\u0B1D>\uE01D;"+ // LETTER JHA
"\u0B1E>\uE01E;"+ // LETTER NYA
"\u0B1F>\uE01F;"+ // LETTER TTA
"\u0B20>\uE020;"+ // LETTER TTHA
"\u0B21>\uE021;"+ // LETTER DDA
"\u0B22>\uE022;"+ // LETTER DDHA
"\u0B23>\uE023;"+ // LETTER NNA
"\u0B24>\uE024;"+ // LETTER TA
"\u0B25>\uE025;"+ // LETTER THA
"\u0B26>\uE026;"+ // LETTER DA
"\u0B27>\uE027;"+ // LETTER DHA
"\u0B28>\uE028;"+ // LETTER NA
"\u0B2A>\uE02A;"+ // LETTER PA
"\u0B2B>\uE02B;"+ // LETTER PHA
"\u0B2C>\uE02C;"+ // LETTER BA
"\u0B2D>\uE02D;"+ // LETTER BHA
"\u0B2E>\uE02E;"+ // LETTER MA
"\u0B2F>\uE02F;"+ // LETTER YA
"\u0B30>\uE030;"+ // LETTER RA
"\u0B32>\uE032;"+ // LETTER LA
"\u0B33>\uE033;"+ // LETTER LLA
"\u0B36>\uE036;"+ // LETTER SHA
"\u0B37>\uE037;"+ // LETTER SSA
"\u0B38>\uE038;"+ // LETTER SA
"\u0B39>\uE039;"+ // LETTER HA
"\u0B3C>\uE03C;"+ // SIGN NUKTA
"\u0B3D>\uE03D;"+ // SIGN AVAGRAHA
"\u0B3E>\uE03E;"+ // VOWEL SIGN AA
"\u0B3F>\uE03F;"+ // VOWEL SIGN I
"\u0B40>\uE040;"+ // VOWEL SIGN II
"\u0B41>\uE041;"+ // VOWEL SIGN U
"\u0B42>\uE042;"+ // VOWEL SIGN UU
"\u0B43>\uE043;"+ // VOWEL SIGN VOCALIC R
"\u0B47>\uE084;"+ // VOWEL SIGN E
"\u0B48>\uE048;"+ // VOWEL SIGN AI
"\u0B4B>\uE085;"+ // VOWEL SIGN O
"\u0B4C>\uE04C;"+ // VOWEL SIGN AU
"\u0B4D>\uE04D;"+ // SIGN VIRAMA
"\u0B56>\uE056;"+ // AI LENGTH MARK
"\u0B57>\uE057;"+ // AU LENGTH MARK
"\u0B5C>\uE083;"+ // LETTER RRA
"\u0B5D>\uE05D;"+ // LETTER RHA
"\u0B5F>\uE05F;"+ // LETTER YYA
"\u0B60>\uE060;"+ // LETTER VOCALIC RR
"\u0B61>\uE061;"+ // LETTER VOCALIC LL
"\u0B66>\uE066;"+ // DIGIT ZERO
"\u0B67>\uE067;"+ // DIGIT ONE
"\u0B68>\uE068;"+ // DIGIT TWO
"\u0B69>\uE069;"+ // DIGIT THREE
"\u0B6A>\uE06A;"+ // DIGIT FOUR
"\u0B6B>\uE06B;"+ // DIGIT FIVE
"\u0B6C>\uE06C;"+ // DIGIT SIX
"\u0B6D>\uE06D;"+ // DIGIT SEVEN
"\u0B6E>\uE06E;"+ // DIGIT EIGHT
"\u0B6F>\uE06F;"+ // DIGIT NINE
"\u0B70>\uE080;"+ // ISSHAR
""
}
};
}
}

93
icu4j/src/com/ibm/text/resources/TransliterationRule_StraightQuotes_CurlyQuotes.java
View File

@ -1,93 +0,0 @@
/*
*******************************************************************************
* Copyright (C) 1996-2000, International Business Machines Corporation and *
* others. All Rights Reserved. *
*******************************************************************************
*
* $Source: /xsrl/Nsvn/icu/icu4j/src/com/ibm/text/resources/Attic/TransliterationRule_StraightQuotes_CurlyQuotes.java,v $
* $Date: 2000/04/22 00:04:25 $
* $Revision: 1.4 $
*
*****************************************************************************************
*/
package com.ibm.text.resources;
import java.util.ListResourceBundle;
public class TransliterationRule_StraightQuotes_CurlyQuotes extends ListResourceBundle {
/**
* Overrides ListResourceBundle
*/
public Object[][] getContents() {
return new Object[][] {
{ "Rule",
// Rewritten using character codes [LIU]
"$white=[[:Zs:][:Zl:][:Zp:]];"
+ "$black=[^$white];"
+ "$open=[:Ps:];"
+ "$dquote='\"';"
+ "$lAng=\u3008;"
+ "$ldAng=\u300A;"
+ "$lBrk='[';"
+ "$lBrc='{';"
+ "$lquote=\u2018;"
+ "$rquote=\u2019;"
+ "$ldquote=\u201C;"
+ "$rdquote=\u201D;"
+ "$ldguill=\u00AB;"
+ "$rdguill=\u00BB;"
+ "$lguill=\u2039;"
+ "$rguill=\u203A;"
+ "$mdash=\u2014;"
//#######################################
// Conversions from input
//#######################################
// join single quotes
+ "$lquote''>$ldquote;"
+ "$lquote$lquote>$ldquote;"
+ "$rquote''>$rdquote;"
+ "$rquote$rquote>$rdquote;"
//smart single quotes
+ "$white{''>$lquote;"
+ "$open{''>$lquote;"
+ "$black{''>$rquote;"
+ "''>$lquote;"
//smart doubles
+ "$white{$dquote>$ldquote;"
+ "$open{$dquote>$ldquote;"
+ "$black{$dquote>$rdquote;"
+ "$dquote>$ldquote;"
// join single guillemets
+ "$rguill$rguill>$rdguill;"
+ "'>>'>$rdguill;"
+ "$lguill$lguill>$ldguill;"
+ "'<<'>$ldguill;"
// prevent double spaces
+ "\\ {\\ >;"
// join hyphens into dash ### BIDIRECTIONAL ###
+ "'--'<>$mdash;"
//#######################################
// Conversions back to input
//#######################################
//smart quotes
+ "''<$lquote;"
+ "''<$rquote;"
+ "$dquote<$ldquote;"
+ "$dquote<$rdquote;"
}
};
}
}

87
icu4j/src/com/ibm/text/resources/TransliterationRule_Tamil_InterIndic.java
View File

@ -1,87 +0,0 @@
/***********************************************************************
* Copyright (c) 2000, International Business Machines Corporation
* and others. All Rights Reserved.
************************************************************************
* > THIS FILE WAS MACHINE GENERATED <
* > DO NOT EDIT BY HAND <
* > RUN TOOL TO REGENERATE <
* Tool: icu4j/src/com/ibm/tools/translit/indic.pl
* Creation date: Fri Oct 6 15:55:21 2000
*/
package com.ibm.text.resources;
import java.util.ListResourceBundle;
public class TransliterationRule_Tamil_InterIndic extends ListResourceBundle {
/**
* Overrides ListResourceBundle
*/
public Object[][] getContents() {
return new Object[][] {
{ "Rule",
"\u0B82>\uE002;"+ // SIGN ANUSVARA
"\u0B83>\uE003;"+ // SIGN VISARGA
"\u0B85>\uE005;"+ // LETTER A
"\u0B86>\uE006;"+ // LETTER AA
"\u0B87>\uE007;"+ // LETTER I
"\u0B88>\uE008;"+ // LETTER II
"\u0B89>\uE009;"+ // LETTER U
"\u0B8A>\uE00A;"+ // LETTER UU
"\u0B8E>\uE081;"+ // LETTER E
"\u0B8F>\uE00F;"+ // LETTER EE
"\u0B90>\uE010;"+ // LETTER AI
"\u0B92>\uE082;"+ // LETTER O
"\u0B93>\uE013;"+ // LETTER OO
"\u0B94>\uE014;"+ // LETTER AU
"\u0B95>\uE015;"+ // LETTER KA
"\u0B99>\uE019;"+ // LETTER NGA
"\u0B9A>\uE01A;"+ // LETTER CA
"\u0B9C>\uE01C;"+ // LETTER JA
"\u0B9E>\uE01E;"+ // LETTER NYA
"\u0B9F>\uE01F;"+ // LETTER TTA
"\u0BA3>\uE023;"+ // LETTER NNA
"\u0BA4>\uE024;"+ // LETTER TA
"\u0BA8>\uE028;"+ // LETTER NA
"\u0BA9>\uE029;"+ // LETTER NNNA
"\u0BAA>\uE02A;"+ // LETTER PA
"\u0BAE>\uE02E;"+ // LETTER MA
"\u0BAF>\uE02F;"+ // LETTER YA
"\u0BB0>\uE030;"+ // LETTER RA
"\u0BB1>\uE083;"+ // LETTER RRA
"\u0BB2>\uE032;"+ // LETTER LA
"\u0BB3>\uE033;"+ // LETTER LLA
"\u0BB4>\uE034;"+ // LETTER LLLA
"\u0BB5>\uE035;"+ // LETTER VA
"\u0BB7>\uE037;"+ // LETTER SSA
"\u0BB8>\uE038;"+ // LETTER SA
"\u0BB9>\uE039;"+ // LETTER HA
"\u0BBE>\uE03E;"+ // VOWEL SIGN AA
"\u0BBF>\uE03F;"+ // VOWEL SIGN I
"\u0BC0>\uE040;"+ // VOWEL SIGN II
"\u0BC1>\uE041;"+ // VOWEL SIGN U
"\u0BC2>\uE042;"+ // VOWEL SIGN UU
"\u0BC6>\uE084;"+ // VOWEL SIGN E
"\u0BC7>\uE047;"+ // VOWEL SIGN EE
"\u0BC8>\uE048;"+ // VOWEL SIGN AI
"\u0BCA>\uE085;"+ // VOWEL SIGN O
"\u0BCB>\uE04B;"+ // VOWEL SIGN OO
"\u0BCC>\uE04C;"+ // VOWEL SIGN AU
"\u0BCD>\uE04D;"+ // SIGN VIRAMA
"\u0BD7>\uE057;"+ // AU LENGTH MARK
"\u0BE7>\uE067;"+ // DIGIT ONE
"\u0BE8>\uE068;"+ // DIGIT TWO
"\u0BE9>\uE069;"+ // DIGIT THREE
"\u0BEA>\uE06A;"+ // DIGIT FOUR
"\u0BEB>\uE06B;"+ // DIGIT FIVE
"\u0BEC>\uE06C;"+ // DIGIT SIX
"\u0BED>\uE06D;"+ // DIGIT SEVEN
"\u0BEE>\uE06E;"+ // DIGIT EIGHT
"\u0BEF>\uE06F;"+ // DIGIT NINE
// \u0BF0>; // UNMAPPED Tamil-InterIndic: NUMBER TEN
// \u0BF1>; // UNMAPPED Tamil-InterIndic: NUMBER ONE HUNDRED
// \u0BF2>; // UNMAPPED Tamil-InterIndic: NUMBER ONE THOUSAND
""
}
};
}
}

106
icu4j/src/com/ibm/text/resources/TransliterationRule_Telugu_InterIndic.java
View File

@ -1,106 +0,0 @@
/***********************************************************************
* Copyright (c) 2000, International Business Machines Corporation
* and others. All Rights Reserved.
************************************************************************
* > THIS FILE WAS MACHINE GENERATED <
* > DO NOT EDIT BY HAND <
* > RUN TOOL TO REGENERATE <
* Tool: icu4j/src/com/ibm/tools/translit/indic.pl
* Creation date: Fri Oct 6 15:55:21 2000
*/
package com.ibm.text.resources;
import java.util.ListResourceBundle;
public class TransliterationRule_Telugu_InterIndic extends ListResourceBundle {
/**
* Overrides ListResourceBundle
*/
public Object[][] getContents() {
return new Object[][] {
{ "Rule",
"\u0C01>\uE001;"+ // SIGN CANDRABINDU
"\u0C02>\uE002;"+ // SIGN ANUSVARA
"\u0C03>\uE003;"+ // SIGN VISARGA
"\u0C05>\uE005;"+ // LETTER A
"\u0C06>\uE006;"+ // LETTER AA
"\u0C07>\uE007;"+ // LETTER I
"\u0C08>\uE008;"+ // LETTER II
"\u0C09>\uE009;"+ // LETTER U
"\u0C0A>\uE00A;"+ // LETTER UU
"\u0C0B>\uE00B;"+ // LETTER VOCALIC R
"\u0C0C>\uE00C;"+ // LETTER VOCALIC L
"\u0C0E>\uE081;"+ // LETTER E
"\u0C0F>\uE00F;"+ // LETTER EE
"\u0C10>\uE010;"+ // LETTER AI
"\u0C12>\uE082;"+ // LETTER O
"\u0C13>\uE013;"+ // LETTER OO
"\u0C14>\uE014;"+ // LETTER AU
"\u0C15>\uE015;"+ // LETTER KA
"\u0C16>\uE016;"+ // LETTER KHA
"\u0C17>\uE017;"+ // LETTER GA
"\u0C18>\uE018;"+ // LETTER GHA
"\u0C19>\uE019;"+ // LETTER NGA
"\u0C1A>\uE01A;"+ // LETTER CA
"\u0C1B>\uE01B;"+ // LETTER CHA
"\u0C1C>\uE01C;"+ // LETTER JA
"\u0C1D>\uE01D;"+ // LETTER JHA
"\u0C1E>\uE01E;"+ // LETTER NYA
"\u0C1F>\uE01F;"+ // LETTER TTA
"\u0C20>\uE020;"+ // LETTER TTHA
"\u0C21>\uE021;"+ // LETTER DDA
"\u0C22>\uE022;"+ // LETTER DDHA
"\u0C23>\uE023;"+ // LETTER NNA
"\u0C24>\uE024;"+ // LETTER TA
"\u0C25>\uE025;"+ // LETTER THA
"\u0C26>\uE026;"+ // LETTER DA
"\u0C27>\uE027;"+ // LETTER DHA
"\u0C28>\uE028;"+ // LETTER NA
"\u0C2A>\uE02A;"+ // LETTER PA
"\u0C2B>\uE02B;"+ // LETTER PHA
"\u0C2C>\uE02C;"+ // LETTER BA
"\u0C2D>\uE02D;"+ // LETTER BHA
"\u0C2E>\uE02E;"+ // LETTER MA
"\u0C2F>\uE02F;"+ // LETTER YA
"\u0C30>\uE030;"+ // LETTER RA
"\u0C31>\uE083;"+ // LETTER RRA
"\u0C32>\uE032;"+ // LETTER LA
"\u0C33>\uE033;"+ // LETTER LLA
"\u0C35>\uE035;"+ // LETTER VA
"\u0C36>\uE036;"+ // LETTER SHA
"\u0C37>\uE037;"+ // LETTER SSA
"\u0C38>\uE038;"+ // LETTER SA
"\u0C39>\uE039;"+ // LETTER HA
"\u0C3E>\uE03E;"+ // VOWEL SIGN AA
"\u0C3F>\uE03F;"+ // VOWEL SIGN I
"\u0C40>\uE040;"+ // VOWEL SIGN II
"\u0C41>\uE041;"+ // VOWEL SIGN U
"\u0C42>\uE042;"+ // VOWEL SIGN UU
"\u0C43>\uE043;"+ // VOWEL SIGN VOCALIC R
"\u0C44>\uE044;"+ // VOWEL SIGN VOCALIC RR
"\u0C46>\uE084;"+ // VOWEL SIGN E
"\u0C47>\uE047;"+ // VOWEL SIGN EE
"\u0C48>\uE048;"+ // VOWEL SIGN AI
"\u0C4A>\uE085;"+ // VOWEL SIGN O
"\u0C4B>\uE04B;"+ // VOWEL SIGN OO
"\u0C4C>\uE04C;"+ // VOWEL SIGN AU
"\u0C4D>\uE04D;"+ // SIGN VIRAMA
"\u0C55>\uE055;"+ // LENGTH MARK
"\u0C56>\uE056;"+ // AI LENGTH MARK
"\u0C60>\uE060;"+ // LETTER VOCALIC RR
"\u0C61>\uE061;"+ // LETTER VOCALIC LL
"\u0C66>\uE066;"+ // DIGIT ZERO
"\u0C67>\uE067;"+ // DIGIT ONE
"\u0C68>\uE068;"+ // DIGIT TWO
"\u0C69>\uE069;"+ // DIGIT THREE
"\u0C6A>\uE06A;"+ // DIGIT FOUR
"\u0C6B>\uE06B;"+ // DIGIT FIVE
"\u0C6C>\uE06C;"+ // DIGIT SIX
"\u0C6D>\uE06D;"+ // DIGIT SEVEN
"\u0C6E>\uE06E;"+ // DIGIT EIGHT
"\u0C6F>\uE06F;"+ // DIGIT NINE
""
}
};
}
}

1538
icu4j/src/com/ibm/text/resources/TransliterationRule_UnicodeName_UnicodeChar.java
View File

File diff suppressed because it is too large Load Diff