organicmaps/icu
13
Fork 0
mirror of https://github.com/unicode-org/icu.git synced 2025-04-13 08:53:20 +00:00
Code Issues1 Projects Releases Wiki Activity Actions3

Update to Mark's latest rules

Browse source 
X-SVN-Rev: 490
This commit is contained in:
Alan Liu 2000-01-06 03:00:51 +00:00
parent abfccede27
commit a55e26abb1
12 changed files with 28902 additions and 440 deletions

276
icu4j/src/com/ibm/text/resources/TransliterationRule$Fullwidth$Halfwidth.java Executable file
View file

@ -0,0 +1,276 @@
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 {';' doesn't work yet - aliu}
+ "\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
}
};
}
}

20351
icu4j/src/com/ibm/text/resources/TransliterationRule$Han$Pinyin.java Executable file
View file

File diff suppressed because it is too large Load diff

6362
icu4j/src/com/ibm/text/resources/TransliterationRule$Kanji$English.java Executable file
View file

File diff suppressed because it is too large Load diff

5
icu4j/src/com/ibm/text/resources/TransliterationRule$KeyboardEscape$Latin1.java
View file

@ -8,9 +8,6 @@ public class TransliterationRule$KeyboardEscape$Latin1 extends ListResourceBundl
*/
public Object[][] getContents() {
return new Object[][] {
{ "Description",
"Keyboard transliterator for Latin-1 block" },
{ "Rule",
"esc='';"
+ "grave=`;"
@ -125,7 +122,7 @@ public class TransliterationRule$KeyboardEscape$Latin1 extends ListResourceBundl
+ "y{acute}{esc}>\u00FD;"
+ "y{esc}>\u00A5;" // yen sign
+ "th{esc}>\u00FE;"
// + "ss{esc}>\u00FF;" // masked
//masked: + "ss{esc}>\u00FF;"
}
};
}

2
icu4j/src/com/ibm/text/resources/TransliterationRule$Latin$Arabic.java
View file

@ -8,8 +8,6 @@ public class TransliterationRule$Latin$Arabic extends ListResourceBundle {
*/
public Object[][] getContents() {
return new Object[][] {
{ "HasInverse", "1" },
{ "Rule",
// To Do: finish adding shadda, add sokoon

62
icu4j/src/com/ibm/text/resources/TransliterationRule$Latin$Cyrillic.java
View file

@ -8,7 +8,17 @@ public class TransliterationRule$Latin$Cyrillic extends ListResourceBundle {
*/
public Object[][] getContents() {
return new Object[][] {
{ "Rule", "" // Russian Letters
{ "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;"
@ -104,24 +114,10 @@ public class TransliterationRule$Latin$Cyrillic extends ListResourceBundle {
+ "letter=[[:Lu:][:Ll:]];"
+ "lower=[[:Ll:]];"
+ "Agrave=\u00C0;"
+ "Egrave=\u00C8;"
+ "Igrave=\u00CC;"
+ "Ograve=\u00D2;"
+ "Ugrave=\u00D9;"
+ "Ydiaeresis=\u009F;" // Non-standard?
+ "agrave=\u00E0;"
+ "egrave=\u00E8;"
+ "igrave=\u00EC;"
+ "ograve=\u00F2;"
+ "ugrave=\u00F9;"
+ "ydiaeresis=\u00FF;"
/*
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 \u009A instead of digraphs
It does not, although it could, use characters like \u0161 instead of digraphs
like sh.
*/
@ -177,7 +173,7 @@ public class TransliterationRule$Latin$Cyrillic extends ListResourceBundle {
+ "E<>{E};"
+ "F<>{F};"
+ "G<>{G};"
+ "{Igrave}<>{YI};"
+ "\u00cc<>{YI};"
+ "I<>{I};"
+ "KH<>{KH};"
+ "K<>{K};"
@ -188,27 +184,28 @@ public class TransliterationRule$Latin$Cyrillic extends ListResourceBundle {
+ "P<>{P};"
+ "R<>{R};"
+ "SHCH<>{SHCH};"
+ "SH<>{SH};"
+ "SH>{SH};" //+ "SH<{SH};"
+ "{S-hacek}<>{SH};"
+ "S<>{S};"
+ "TS<>{TS};"
+ "T<>{T};"
+ "U<>{U};"
+ "V<>{V};"
//AEOU + grave
//\u00cc\u00c0\u00c8\u00d2\u00d9
+ "YE>{YE};" //+ "YE<{YE};"
+ "{Egrave}<>{YE};"
+ "\u00c8<>{YE};"
+ "YO>{YO};" //+ "YO<{YO};"
+ "{Ograve}<>{YO};"
+ "\u00d2<>{YO};"
+ "YU>{YU};" //+ "YU<{YU};"
+ "{Ugrave}<>{YU};"
+ "\u00d9<>{YU};"
+ "YA>{YA};" //+ "YA<{YA};"
+ "{Agrave}<>{YA};"
+ "\u00c0<>{YA};"
+ "Y<>{Y};"
+ "ZH<>{ZH};"
+ "Z<>{Z};"
+ "H<>{HARD};"
+ "{Ydiaeresis}<>{SOFT};"
+ "\u0178<>{SOFT};"
// Non-russian
@ -255,7 +252,7 @@ public class TransliterationRule$Latin$Cyrillic extends ListResourceBundle {
+ "e<>{e};"
+ "f<>{f};"
+ "g<>{g};"
+ "{igrave}<>{yi};"
+ "\u00ec<>{yi};"
+ "i<>{i};"
+ "kh<>{kh};"
+ "k<>{k};"
@ -266,27 +263,28 @@ public class TransliterationRule$Latin$Cyrillic extends ListResourceBundle {
+ "p<>{p};"
+ "r<>{r};"
+ "shch<>{shch};"
+ "sh<>{sh};"
+ "sh>{sh};" //+ "sh<{sh};"
+ "{s-hacek}<>{sh};"
+ "s<>{s};"
+ "ts<>{ts};"
+ "t<>{t};"
+ "u<>{u};"
+ "v<>{v};"
//aeou + grave
//\u00ec\u00e0\u00e8\u00f2\u00f9
+ "ye>{ye};" //+ "ye<{ye};"
+ "{egrave}<>{ye};"
+ "\u00e8<>{ye};"
+ "yo>{yo};" //+ "yo<{yo};"
+ "{ograve}<>{yo};"
+ "\u00f2<>{yo};"
+ "yu>{yu};" //+ "yu<{yu};"
+ "{ugrave}<>{yu};"
+ "\u00f9<>{yu};"
+ "ya>{ya};" //+ "ya<{ya};"
+ "{agrave}<>{ya};"
+ "\u00e0<>{ya};"
+ "y<>{y};"
+ "zh<>{zh};"
+ "z<>{z};"
+ "h<>{hard};"
+ "{ydiaeresis}<>{soft};"
+ "\u00ff<>{soft};"
// non-russian

3
icu4j/src/com/ibm/text/resources/TransliterationRule$Latin$Devanagari.java
View file

@ -8,9 +8,6 @@ public class TransliterationRule$Latin$Devanagari extends ListResourceBundle {
*/
public Object[][] getContents() {
return new Object[][] {
{ "Description",
"Latin to Devanagari" },
{ "Rule",
//#####################################################################
// Keyboard Transliteration Table

685
icu4j/src/com/ibm/text/resources/TransliterationRule$Latin$Greek.java
View file

@ -8,376 +8,349 @@ public class TransliterationRule$Latin$Greek extends ListResourceBundle {
*/
public Object[][] getContents() {
return new Object[][] {
{ "Description",
"Latin to Greek" },
{ "Rule",
{ "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.
// ==============================================
// 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
"grAl=\u0391;"
+ "grBe=\u0392;"
+ "grGa=\u0393;"
+ "grDe=\u0394;"
+ "grEp=\u0395;"
+ "grZe=\u0396;"
+ "grEt=\u0397;"
+ "grTh=\u0398;"
+ "grIo=\u0399;"
+ "grKa=\u039A;"
+ "grLa=\u039B;"
+ "grMu=\u039C;"
+ "grNu=\u039D;"
+ "grKs=\u039E;"
+ "grOm=\u039F;"
+ "grPi=\u03A0;"
+ "grRh=\u03A1;"
+ "grSi=\u03A3;"
+ "grTa=\u03A4;"
+ "grUp=\u03A5;"
+ "grPh=\u03A6;"
+ "grKh=\u03A7;"
+ "grPs=\u03A8;"
+ "grOme=\u03A9;"
+ "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;"
+ "gral=\u03B1;"
+ "grbe=\u03B2;"
+ "grga=\u03B3;"
+ "grde=\u03B4;"
+ "grep=\u03B5;"
+ "grze=\u03B6;"
+ "gret=\u03B7;"
+ "grth=\u03B8;"
+ "grio=\u03B9;"
+ "grka=\u03BA;"
+ "grla=\u03BB;"
+ "grmu=\u03BC;"
+ "grnu=\u03BD;"
+ "grks=\u03BE;"
+ "grom=\u03BF;"
+ "grpi=\u03C0;"
+ "grrh=\u03C1;"
+ "grsi=\u03C3;"
+ "grta=\u03C4;"
+ "grup=\u03C5;"
+ "grph=\u03C6;"
+ "grkh=\u03C7;"
+ "grps=\u03C8;"
+ "grome=\u03C9;"
+ "ALPHA+=\u0386;"
+ "EPSILON+=\u0388;"
+ "ETA+=\u0389;"
+ "IOTA+=\u038A;"
+ "OMICRON+=\u038C;"
+ "YPSILON+=\u038E;"
+ "OMEGA+=\u038F;"
+ "IOTA\u00a8=\u03AA;"
+ "YPSILON\u00a8=\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
+ "grfinal=\u03C2;"
+ "grAcAl=\u0386;"
+ "grAcEp=\u0388;"
+ "grAcEt=\u0389;"
+ "grAcIo=\u038A;"
+ "grAcOm=\u038C;"
+ "grAcUp=\u038E;"
+ "grAcOme=\u038F;"
+ "grDiIo=\u03AA;"
+ "grDiUp=\u03AB;"
+ "alpha+=\u03AC;"
+ "epsilon+=\u03AD;"
+ "eta+=\u03AE;"
+ "iota+=\u03AF;"
+ "omicron+=\u03CC;"
+ "ypsilon+=\u03CD;"
+ "omega+=\u03CE;"
+ "iota\u00a8=\u03CA;"
+ "ypsilon\u00a8=\u03CB;"
+ "iota\u00a8+=\u0390;"
+ "ypsilon\u00a8+=\u03B0;"
+ "sigma+=\u03C2;"
+ "gracal=\u03AC;"
+ "gracep=\u03AD;"
+ "gracet=\u03AE;"
+ "gracio=\u03AF;"
+ "gracom=\u03CC;"
+ "gracup=\u03CD;"
+ "gracome=\u03CE;"
+ "grdiio=\u03CA;"
+ "grdiup=\u03CB;"
//gracdiio=\u00FD
//gracdiup=\u00FE
// Variables for conditional mappings
// Use lowercase for all variable names, to allow cut/paste below.
+ "letter=[[:Lu:][:Ll:]];"
+ "lower=[[:Ll:]];"
+ "vowel=[aeiouAEIOU"
+ "{ALPHA}{EPSILON}{ETA}{IOTA}{OMICRON}{YPSILON}{OMEGA}"
+ "{ALPHA+}{EPSILON+}{ETA+}{IOTA+}{OMICRON+}{YPSILON+}{OMEGA+}"
+ "{IOTA\u00a8}{YPSILON\u00a8}"
+ "{alpha}{epsilon}{eta}{iota}{omicron}{ypsilon}{omega}"
+ "{alpha+}{epsilon+}{eta+}{iota+}{omicron+}{ypsilon+}{omega+}"
+ "{iota\u00a8}{ypsilon\u00a8}"
+ "{iota\u00a8+}{ypsilon\u00a8+}"
+ "];"
+ "n-gamma=[GKXCgkxc];"
+ "gamma-n=[{GAMMA}{KAPPA}{CHI}{XI}{gamma}{kappa}{chi}{xi}];"
+ "pp=[Pp];"
// convert Roman to Native
+ "Greek>\u039c\u0397\u039d\u0399\u039d\u0020\u0391\u0395\u0399\u0394\u0395\u002c\u0020\u0398\u0395\u0391\u002c\u0020--\u0397\u039b\u0397\u0399\u0391\u0394\u0395\u03a9\u0020\u0391\u03a7\u0399\u039b\u0397\u039f\u03a3;"
// ==============================================
// 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.
// 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
+ "''S<{pp}]{SIGMA};" // for PS
+ "''s<{pp}]{sigma};" // for ps
+ "''s<{pp}]{sigma+};" // for ps
+ "S[{letter}>{SIGMA};" + "S<{SIGMA};"
+ "s[{letter}>{sigma};" + "s<{sigma};"
+ "s<>{sigma+};"
// because there are no uppercase forms, had to move these up too.
+ "i\"`>{iota\u00a8+};"
+ "y\"`>{ypsilon\u00a8+};"
+ "{\u00ef-acute}<>{iota\u00a8+};"
+ "{vowel}]{\u00fc-acute}>{ypsilon\u00a8+};" + "{\u00fc-acute}<{vowel}]{ypsilon\u00a8+};"
+ "{y-umlaut-acute}<>{ypsilon\u00a8+};"
// ==============================================
// Uppercase Forms.
// To make lowercase forms, just copy and lowercase below
// ==============================================
// Typing variants, in case the keyboard doesn't have accents
+ "A`>{ALPHA+};"
+ "E`>{EPSILON+};"
+ "EE`>{ETA+};"
+ "EE>{ETA};"
+ "I`>{IOTA+};"
+ "O`>{OMICRON+};"
+ "OO`>{OMEGA+};"
+ "OO>{OMEGA};"
+ "I\">{IOTA\u00a8};"
+ "Y\">{YPSILON\u00a8};"
// Basic Letters
+ "A<>{ALPHA};"
+ "\u00c1<>{ALPHA+};"
+ "B<>{BETA};"
+ "N]{n-gamma}>{GAMMA};" + "N<{GAMMA}[{gamma-n};"
+ "G<>{GAMMA};"
+ "D<>{DELTA};"
+ "E<>{EPSILON};"
+ "\u00c9<>{EPSILON+};"
+ "Z<>{ZETA};"
+ "{E-MACRON-ACUTE}<>{ETA+};"
+ "{E-MACRON}<>{ETA};"
+ "TH<>{THETA};"
+ "I<>{IOTA};"
+ "\u00cd<>{IOTA+};"
+ "\u00cf<>{IOTA\u00a8};"
+ "K<>{KAPPA};"
+ "L<>{LAMBDA};"
+ "M<>{MU};"
+ "N<>{NU};"
+ "X<>{XI};"
+ "O<>{OMICRON};"
+ "\u00d3>{OMICRON+};" + "\u00d3<{OMEGA+};"
+ "PH<>{PHI};" // needs ordering before P
+ "PS<>{PSI};" // needs ordering before P
+ "P<>{PI};"
+ "R<>{RHO};"
+ "T<>{TAU};"
+ "{vowel}]U>{YPSILON};" + "U<{vowel}]{YPSILON};"
+ "{vowel}]\u00da>{YPSILON+};" + "\u00da<{vowel}]{YPSILON+};"
+ "{vowel}]\u00dc>{YPSILON\u00a8};" + "\u00dc<{vowel}]{YPSILON\u00a8};"
+ "Y<>{YPSILON};"
+ "\u00dd<>{YPSILON+};"
+ "{Y-UMLAUT}<>{YPSILON\u00a8};"
+ "CH<>{CHI};"
+ "{O-MACRON-ACUTE}>{OMEGA+};" + "{O-MACRON-ACUTE}<{OMICRON+};"
+ "{O-MACRON}<>{OMEGA};"
+ "AV`>{grAl}{grAcUp};"
+ "EV`>{grEp}{grAcUp};"
+ "AV>{grAl}{grUp};"
+ "EV>{grEp}{grUp};"
+ "NG>{grGa}{grGa};"
+ "NK>{grGa}{grKa};"
+ "NX>{grGa}{grKs};"
+ "NCH>{grGa}{grKh};"
// Extra English Letters. Mapped for completeness
+ "C[I>{SIGMA};"
+ "C[E>{SIGMA};"
+ "C[Y>{SIGMA};"
+ "C>{KAPPA};"
+ "F>{PHI};"
+ "H>{CHI};"
+ "J>{IOTA};"
+ "Q>{KAPPA};"
+ "V>{YPSILON};"
+ "W>{YPSILON};"
// ==============================================
// Lowercase Forms. Just copy above and lowercase
// ==============================================
//+ "final = [ .;];" // Syntax error, unused anyway - Liu
// typing variants, in case the keyboard doesn't have accents
+ "a`>{alpha+};"
+ "e`>{epsilon+};"
+ "ee`>{eta+};"
+ "ee>{eta};"
+ "i`>{iota+};"
+ "o`>{omicron+};"
+ "oo`>{omega+};"
+ "oo>{omega};"
+ "i\">{iota\u00a8};"
+ "y\">{ypsilon\u00a8};"
// basic letters
+ "a<>{alpha};"
+ "\u00e1<>{alpha+};"
+ "b<>{beta};"
+ "n]{n-gamma}>{gamma};" + "n<{gamma}[{gamma-n};"
+ "g<>{gamma};"
+ "d<>{delta};"
+ "e<>{epsilon};"
+ "\u00e9<>{epsilon+};"
+ "z<>{zeta};"
+ "{e-macron-acute}<>{eta+};"
+ "{e-macron}<>{eta};"
+ "th<>{theta};"
+ "i<>{iota};"
+ "\u00ed<>{iota+};"
+ "\u00ef<>{iota\u00a8};"
+ "k<>{kappa};"
+ "l<>{lambda};"
+ "m<>{mu};"
+ "n<>{nu};"
+ "x<>{xi};"
+ "o<>{omicron};"
+ "\u00f3>{omicron+};" + "\u00f3<{omega+};"
+ "ph<>{phi};" // needs ordering before p
+ "ps<>{psi};" // needs ordering before p
+ "p<>{pi};"
+ "r<>{rho};"
+ "t<>{tau};"
+ "{vowel}]u>{ypsilon};" + "u<{vowel}]{ypsilon};"
+ "{vowel}]\u00fa>{ypsilon+};" + "\u00fa<{vowel}]{ypsilon+};"
+ "{vowel}]\u00fc>{ypsilon\u00a8};" + "\u00fc<{vowel}]{ypsilon\u00a8};"
+ "y<>{ypsilon};"
+ "\u00fd<>{ypsilon+};"
+ "{y-umlaut}<>{ypsilon\u00a8};"
+ "ch<>{chi};"
+ "{o-macron-acute}>{omega+};" + "{o-macron-acute}<{omicron+};"
+ "{o-macron}<>{omega};"
+ "A`>{grAcAl};"
+ "EE`>{grAcEt};"
+ "E`>{grAcEp};"
+ "I`>{grAcIo};"
+ "U`>{grAcUp};"
+ "OO`>{grAcOme};"
+ "O`>{grAcOm};"
+ "''I>{grDiIo};"
+ "''U>{grDiUp};"
+ "A>{grAl};"
+ "B>{grBe};"
+ "C[I>{grSi};"
+ "C[E>{grSi};"
+ "C[Y>{grSi};"
+ "CH>{grKh};"
+ "C>{grKa};"
+ "D>{grDe};"
+ "EE>{grEt};"
+ "E>{grEp};"
+ "F>{grPh};"
+ "G>{grGa};"
+ "H>{grKh};"
+ "I>{grIo};"
+ "J>{grIo};"
+ "KS>{grKs};"
+ "KH>{grKh};"
+ "K>{grKa};"
+ "L>{grLa};"
+ "M>{grMu};"
+ "N>{grNu};"
+ "OO>{grOme};"
+ "O>{grOm};"
+ "PS>{grPs};"
+ "PH>{grPh};"
+ "P>{grPi};"
+ "Q>{grKa};"
+ "R>{grRh};"
+ "S>{grSi};"
+ "TH>{grTh};"
+ "T>{grTa};"
+ "W>{grUp}{grUp};"
+ "U>{grUp};"
+ "V>{grUp};"
+ "X>{grKs};"
+ "Y>{grUp};"
+ "Z>{grZe};"
//now Native to Roman
+ "AV<{grAl}{grUp};"
+ "EV<{grEp}{grUp};"
+ "AV`<{grAl}{grAcUp};"
+ "EV`<{grEp}{grAcUp};"
+ "N''<{grNu}[{grGa};"
+ "NG<{grGa}{grGa};"
+ "N''<{grNu}[{grKa};"
+ "NK<{grGa}{grKa};"
+ "N''<{grNu}[{grKs};"
+ "NX<{grGa}{grKs};"
+ "N''<{grNu}[{grKh};"
+ "NCH<{grGa}{grKh};"
+ "A<{grAl};"
+ "B<{grBe};"
+ "G<{grGa};"
+ "D<{grDe};"
+ "E''<{grEp}[{grEp};"
+ "E''<{grEp}[{grEt};"
+ "E''<{grEp}[{grAcEp};"
+ "E''<{grEp}[{grAcEt};"
+ "E<{grEp};"
+ "Z<{grZe};"
+ "EE<{grEt};"
+ "TH<{grTh};"
+ "I<{grIo};"
+ "K<{grKa};"
+ "L<{grLa};"
+ "M<{grMu};"
+ "N<{grNu};"
+ "X<{grKs};"
+ "O''<{grOm}[{grOm};"
+ "O''<{grOm}[{grOme};"
+ "O''<{grOm}[{grAcOm};"
+ "O''<{grOm}[{grAcOme};"
+ "O<{grOm};"
+ "P''<{grPi}[{grSi};"
+ "P''<{grPi}[{grfinal};"
+ "P<{grPi};"
+ "R<{grRh};"
+ "S<{grSi};"
+ "T<{grTa};"
+ "W<{grUp}{grUp};"
+ "V<{grUp}[{grAcAl};"
+ "V<{grUp}[{grAcEp};"
+ "V<{grUp}[{grAcEt};"
+ "V<{grUp}[{grAcIo};"
+ "V<{grUp}[{grAcOm};"
+ "V<{grUp}[{grAcUp};"
+ "V<{grUp}[{grAcOme};"
+ "V<{grUp}[{grAl};"
+ "V<{grUp}[{grEp};"
+ "V<{grUp}[{grEt};"
+ "V<{grUp}[{grIo};"
+ "V<{grUp}[{grOm};"
//{grUp}[{grUp}<V
+ "V<{grUp}[{grOme};"
+ "U<{grUp};"
+ "PH<{grPh};"
+ "CH<{grKh};"
+ "PS<{grPs};"
+ "OO<{grOme};"
//forms
+ "A`<{grAcAl};"
+ "E`<{grAcEp};"
+ "EE`<{grAcEt};"
+ "I`<{grAcIo};"
+ "O`<{grAcOm};"
+ "U`<{grAcUp};"
+ "OO`<{grAcOme};"
+ "''I<{grDiIo};"
+ "''U<{grDiUp};"
//{gracdiio}<XX
//{gracdiup}<XX
//{grfinal}<XX
+ "av`>{gral}{gracup};"
+ "ev`>{grep}{gracup};"
+ "av>{gral}{grup};"
+ "ev>{grep}{grup};"
+ "ng>{grga}{grga};"
+ "nk>{grga}{grka};"
+ "nx>{grga}{grks};"
+ "nch>{grga}{grkh};"
+ "a`>{gracal};"
+ "ee`>{gracet};"
+ "e`>{gracep};"
+ "i`>{gracio};"
+ "u`>{gracup};"
+ "oo`>{gracome};"
+ "o`>{gracom};"
+ "''i>{grdiio};"
+ "''u>{grdiup};"
+ "a>{gral};"
+ "b>{grbe};"
+ "c[i>{grsi};"
+ "c[e>{grsi};"
+ "c[y>{grsi};"
+ "ch>{grkh};"
+ "c>{grka};"
+ "d>{grde};"
+ "ee>{gret};"
+ "e>{grep};"
+ "f>{grph};"
+ "g>{grga};"
+ "h>{grkh};"
+ "i>{grio};"
+ "j>{grio};"
+ "ks>{grks};"
+ "kh>{grkh};"
+ "k>{grka};"
+ "l>{grla};"
+ "m>{grmu};"
+ "n>{grnu};"
+ "oo>{grome};"
+ "o>{grom};"
+ "ps>{grps};"
+ "ph>{grph};"
+ "p>{grpi};"
+ "q>{grka};"
+ "r>{grrh};"
+ "s>|{grfinal};"
+ "{grfinal}[{letter}>{grsi};"
+ "th>{grth};"
+ "t>{grta};"
+ "w>{grup}{grup};"
+ "u>{grup};"
+ "v>{grup};"
+ "x>{grks};"
+ "y>{grup};"
+ "z>{grze};"
//forms
// extra english letters. mapped for completeness
+ "c[i>{sigma};"
+ "c[e>{sigma};"
+ "c[y>{sigma};"
+ "c>{kappa};"
+ "f>{phi};"
+ "h>{chi};"
+ "j>{iota};"
+ "q>{kappa};"
+ "v>{ypsilon};"
+ "w>{ypsilon};"
// ====================================
// Normal final rule: remove '
// ====================================
+ "''>;"
//now native to roman
+ "av<{gral}{grup};"
+ "ev<{grep}{grup};"
+ "av`<{gral}{gracup};"
+ "ev`<{grep}{gracup};"
+ "n''<{grnu}[{grga};"
+ "ng<{grga}{grga};"
+ "n''<{grnu}[{grka};"
+ "nk<{grga}{grka};"
+ "n''<{grnu}[{grks};"
+ "nx<{grga}{grks};"
+ "n''<{grnu}[{grkh};"
+ "nch<{grga}{grkh};"
+ "a<{gral};"
+ "b<{grbe};"
+ "g<{grga};"
+ "d<{grde};"
+ "e''<{grep}[{grep};"
+ "e''<{grep}[{gret};"
+ "e''<{grep}[{gracep};"
+ "e''<{grep}[{gracet};"
+ "e<{grep};"
+ "z<{grze};"
+ "ee<{gret};"
+ "th<{grth};"
+ "i<{grio};"
+ "k<{grka};"
+ "l<{grla};"
+ "m<{grmu};"
+ "n<{grnu};"
+ "x<{grks};"
+ "o''<{grom}[{grom};"
+ "o''<{grom}[{grome};"
+ "o''<{grom}[{gracom};"
+ "o''<{grom}[{gracome};"
+ "o<{grom};"
+ "p''<{grpi}[{grsi};"
+ "p''<{grpi}[{grfinal};"
+ "p<{grpi};"
+ "r<{grrh};"
+ "s<{grsi};"
+ "s<{grfinal};"
+ "t<{grta};"
+ "w<{grup}{grup};"
+ "v<{grup}[{gracal};"
+ "v<{grup}[{gracep};"
+ "v<{grup}[{gracet};"
+ "v<{grup}[{gracio};"
+ "v<{grup}[{gracom};"
+ "v<{grup}[{gracup};"
+ "v<{grup}[{gracome};"
+ "v<{grup}[{gral};"
+ "v<{grup}[{grep};"
+ "v<{grup}[{gret};"
+ "v<{grup}[{grio};"
+ "v<{grup}[{grom};"
//{grup}[{grup}<v
+ "v<{grup}[{grome};"
+ "u<{grup};"
+ "ph<{grph};"
+ "ch<{grkh};"
+ "ps<{grps};"
+ "oo<{grome};"
//forms
+ "a`<{gracal};"
+ "e`<{gracep};"
+ "ee`<{gracet};"
+ "i`<{gracio};"
+ "o`<{gracom};"
+ "u`<{gracup};"
+ "oo`<{gracome};"
+ "''i<{grdiio};"
+ "''u<{grdiup};"
+ "<'';"
//{gracdiio}<xx
//{gracdiup}<xx
//{grfinal}<xx
}
};
}

3
icu4j/src/com/ibm/text/resources/TransliterationRule$Latin$Hebrew.java
View file

@ -8,9 +8,6 @@ public class TransliterationRule$Latin$Hebrew extends ListResourceBundle {
*/
public Object[][] getContents() {
return new Object[][] {
{ "Description",
"Latin to Hebrew" },
{ "Rule",
//variable names, derived from the Unicode names.

64
icu4j/src/com/ibm/text/resources/TransliterationRule$Latin$Kana.java
View file

@ -2,24 +2,17 @@ package com.ibm.text.resources;
import java.util.ListResourceBundle;
/**
* Rewritten April 1999 to implement Hepburn (kebon shiki)
* transliteration. Reference: CJKV Information Processing, Lunde,
* 1999, pp. 30-35.
* @author Alan Liu
*/
public class TransliterationRule$Latin$Kana extends ListResourceBundle {
/**
* Overrides ListResourceBundle
*/
public Object[][] getContents() {
return new Object[][] {
{ "Description",
"Lowercase Latin to hiragana; "
+ "Uppercase Latin to katakana" },
// Lowercase Latin to hiragana
// Uppercase Latin to katakana
{ "Rule", ""
//# $Revision: 1.5 $
//# $Revision: 1.6 $
// Transliteration rules for Japanese Hiragana and Katakana to
// romaji
// lower case roman generates hiragana.
@ -559,15 +552,15 @@ public class TransliterationRule$Latin$Kana extends ListResourceBundle {
// THE FOLLOWING ARE NOT REALLY NECESSARY, BUT PRODUCE
// SLIGHTLY MORE NATURAL RESULTS.
// + "BY>{BI};" // masked by BY> rule above
//masked: + "BY>{BI};"
+ "CY>{SE}{~I};"
+ "DY>{DE}{~I};"
// + "GY>{GI};" // masked
//masked: + "GY>{GI};"
+ "HY>{HI};"
// + "KY>{KI};" // masked
// + "MY>{MI};" // masked
// + "PY>{PI};" // masked
// + "RY>{RI};" // masked
//masked: + "KY>{KI};"
//masked: + "MY>{MI};"
//masked: + "PY>{PI};"
//masked: + "RY>{RI};"
+ "SY>{SE}{~I};"
+ "TY>{TE}{~I};"
+ "ZY>{ZE}{~I};"
@ -588,10 +581,10 @@ public class TransliterationRule$Latin$Kana extends ListResourceBundle {
+ "B>{BU};"
+ "D>{DE};"
// + "F>{HU};" // masked
//masked: + "F>{HU};"
+ "G>{GU};"
+ "H>{HE};"
// + "J>{ZI};" // masked
//masked: + "J>{ZI};"
+ "K>{KU};"
+ "M>{^N};"
+ "N>{^N};"
@ -599,9 +592,9 @@ public class TransliterationRule$Latin$Kana extends ListResourceBundle {
+ "R>{RU};"
+ "S>{SU};"
+ "T>{TE};"
// + "V>{BU};" // masked
// + "W>{^U};" // masked
// + "X>{KU}{SU};" // masked
//masked: + "V>{BU};"
//masked: + "W>{^U};"
//masked: + "X>{KU}{SU};"
+ "Y>{^I};"
+ "Z>{ZU};"
@ -1036,15 +1029,15 @@ public class TransliterationRule$Latin$Kana extends ListResourceBundle {
// the following are not really necessary, but produce
// slightly more natural results.
// + "by>{bi};" // masked
//masked: + "by>{bi};"
+ "cy>{se}{~i};"
+ "dy>{de}{~i};"
// + "gy>{gi};" // masked
//masked: + "gy>{gi};"
+ "hy>{hi};"
// + "ky>{ki};" // masked
// + "my>{mi};" // masked
// + "py>{pi};" // masked
// + "ry>{ri};" // masked
//masked: + "ky>{ki};"
//masked: + "my>{mi};"
//masked: + "py>{pi};"
//masked: + "ry>{ri};"
+ "sy>{se}{~i};"
+ "ty>{te}{~i};"
+ "zy>{ze}{~i};"
@ -1065,10 +1058,10 @@ public class TransliterationRule$Latin$Kana extends ListResourceBundle {
+ "b>{bu};"
+ "d>{de};"
// + "f>{hu};" // masked
//masked: + "f>{hu};"
+ "g>{gu};"
+ "h>{he};"
// + "j>{zi};" // masked
//masked: + "j>{zi};"
+ "k>{ku};"
+ "m>{^n};"
+ "n>{^n};"
@ -1076,9 +1069,9 @@ public class TransliterationRule$Latin$Kana extends ListResourceBundle {
+ "r>{ru};"
+ "s>{su};"
+ "t>{te};"
// + "v>{bu};" // masked
// + "w>{^u};" // masked
// + "x>{ku}{su};" // masked
//masked: + "v>{bu};"
//masked: + "w>{^u};"
//masked: + "x>{ku}{su};"
+ "y>{^i};"
+ "z>{zu};"
@ -1303,8 +1296,8 @@ public class TransliterationRule$Latin$Kana extends ListResourceBundle {
+ "~u<{~u};"
+ "~e<{~e};"
+ "~o<{~o};"
// + "~ka<{~ka};" // masked by <{~KA} rule
// + "~ke<{~ke};" // masked by <{~KE} rule
//masked: + "~ka<{~ka};" ({~ka} is an alias for {~KA})
//masked: + "~ke<{~ke};" ({~ke} is an alias for {~KE})
+ "~ya<{~ya};"
+ "~yu<{~yu};"
+ "~yo<{~yo};"
@ -1331,6 +1324,3 @@ public class TransliterationRule$Latin$Kana extends ListResourceBundle {
};
}
}

3
icu4j/src/com/ibm/text/resources/TransliterationRule$StraightQuotes$CurlyQuotes.java
View file

@ -8,9 +8,6 @@ public class TransliterationRule$StraightQuotes$CurlyQuotes extends ListResource
*/
public Object[][] getContents() {
return new Object[][] {
{ "Description",
"Use left and right double quotes" },
{ "Rule",
// Rewritten using character codes [LIU]
"white=[[:Zs:][:Zl:][:Zp:]];"

1526
icu4j/src/com/ibm/text/resources/TransliterationRule$UnicodeName$UnicodeChar.java Executable file
View file

File diff suppressed because it is too large Load diff