organicmaps/icu
13
Fork 0
mirror of https://github.com/unicode-org/icu.git synced 2025-04-09 07:22:11 +00:00
Code Issues 1 Projects Releases Wiki Activity Actions 1

Update rules to new rule syntax (parens delimit context)

Browse source 
X-SVN-Rev: 518
This commit is contained in:
Alan Liu 2000-01-11 02:24:15 +00:00
parent 471a29ebeb
commit de9589cdcb
11 changed files with 11499 additions and 11499 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
icu4j/src/com/ibm/text/resources/TransliterationRule$Fullwidth$Halfwidth.java
View file

@ -72,7 +72,7 @@ public class TransliterationRule$Fullwidth$Halfwidth extends ListResourceBundle
+ "\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}
+ "\uFF1B<>';';" // from FULLWIDTH SEMICOLON
+ "\uFF1C<>'<';" // from FULLWIDTH LESS-THAN SIGN
+ "\uFF1D<>'=';" // from FULLWIDTH EQUALS SIGN
+ "\uFF1E<>'>';" // from FULLWIDTH GREATER-THAN SIGN

9600
icu4j/src/com/ibm/text/resources/TransliterationRule$Han$Pinyin.java
View file

File diff suppressed because it is too large Load diff

12694
icu4j/src/com/ibm/text/resources/TransliterationRule$Kanji$English.java
View file

File diff suppressed because it is too large Load diff

2
icu4j/src/com/ibm/text/resources/TransliterationRule$KeyboardEscape$Latin1.java
View file

@ -32,7 +32,7 @@ public class TransliterationRule$KeyboardEscape$Latin1 extends ListResourceBundl
+ "mul{esc}>\u00D7;"
+ "div{esc}>\u00F7;"
+ " {esc}>\u00A0;" // non-breaking space
+ "\\ {esc}>\u00A0;" // non-breaking space
+ "!{esc}>\u00A1;" // inverted exclamation
+ "c/{esc}>\u00A2;" // cent sign
+ "lb{esc}>\u00A3;" // pound sign

90
icu4j/src/com/ibm/text/resources/TransliterationRule$Latin$Arabic.java
View file

@ -60,11 +60,11 @@ public class TransliterationRule$Latin$Arabic extends ListResourceBundle {
// convert English to Arabic
"Arabic>"+
"\u062a\u062a\u0645\u062a\u0639\u0020"+
"\u0627\u0644\u0644\u063a\u0629\u0020"+
"\u0627\u0644\u0639\u0631\u0628\u0628\u064a\u0629\u0020"+
"\u0628\u0628\u0646\u0638\u0645\u0020"+
"\u0643\u062a\u0627\u0628\u0628\u064a\u0629\u0020"+
"\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;"+
"ai>{alefmadda};"+
@ -75,11 +75,11 @@ public class TransliterationRule$Latin$Arabic extends ListResourceBundle {
"a>{fatha};"+
"b>{beh};"+
"c>{kaf};"+
"{dhal}]dh>{shadda};"+
"{dhal})dh>{shadda};"+
"dh>{dhal};"+
"{dad}]dd>{shadda};"+
"{dad})dd>{shadda};"+
"dd>{dad};"+
"{dal}]d>{shadda};"+
"{dal})d>{shadda};"+
"d>{dal};"+
"e>{ein};"+
"f>{feh};"+
@ -153,88 +153,88 @@ public class TransliterationRule$Latin$Arabic extends ListResourceBundle {
// now Arabic to English
"''ai<a]{alefmadda};"+
"''ai<a){alefmadda};"+
"ai<{alefmadda};"+
"''ae<a]{alefuhamza};"+
"''ae<a){alefuhamza};"+
"ae<{alefuhamza};"+
"''ao<a]{alefhamza};"+
"''ao<a){alefhamza};"+
"ao<{alefhamza};"+
"''aa<a]{alef};"+
"''aa<a){alef};"+
"aa<{alef};"+
"''an<a]{fathatein};"+
"''an<a){fathatein};"+
"an<{fathatein};"+
"''a<a]{fatha};"+
"''a<a){fatha};"+
"a<{fatha};"+
"b<{beh};"+
"''dh<d]{dhal};"+
"''dh<d){dhal};"+
"dh<{dhal};"+
"''dd<d]{dad};"+
"''dd<d){dad};"+
"dd<{dad};"+
"''d<d]{dal};"+
"''d<d){dal};"+
"d<{dal};"+
"''e<a]{ein};"+
"''e<w]{ein};"+
"''e<y]{ein};"+
"''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<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<d){heh};"+
"''h<t){heh};"+
"''h<k){heh};"+
"''h<s){heh};"+
"h<{heh};"+
"''ii<i]{kasratein};"+
"''ii<i){kasratein};"+
"ii<{kasratein};"+
"''i<i]{kasra};"+
"''i<i){kasra};"+
"i<{kasra};"+
"j<{geem};"+
"kh<{kha};"+
"x<{kaf}{shadda}{seen};"+
"k<{kaf};"+
"l<{lam};"+
"''m<y]{meem};"+
"''m<t]{meem};"+
"''m<y){meem};"+
"''m<t){meem};"+
"m<{meem};"+
"n<{noon};"+
"''o<a]{hamza};"+
"''o<a){hamza};"+
"o<{hamza};"+
"p<{peh};"+
"q<{qaaf};"+
"r<{reh};"+
"sh<{sheen};"+
"''ss<s]{sad};"+
"''ss<s){sad};"+
"ss<{sad};"+
"''s<s]{seen};"+
"''s<s){seen};"+
"s<{seen};"+
"th<{theh};"+
"tm<{tehmarbuta};"+
"''tt<t]{tah};"+
"''tt<t){tah};"+
"tt<{tah};"+
"''t<t]{teh};"+
"''t<t){teh};"+
"t<{teh};"+
"''uu<u]{dammatein};"+
"''uu<u){dammatein};"+
"uu<{dammatein};"+
"''u<u]{damma};"+
"''u<u){damma};"+
"u<{damma};"+
"we<{wauuhamza};"+
"w<{wau};"+
"ye<{yehuhamza};"+
"ym<{yehmaqsura};"+
"''y<y]{yeh};"+
"''y<y){yeh};"+
"y<{yeh};"+
"''zz<z]{zah};"+
"''zz<z){zah};"+
"zz<{zah};"+
"''z<z]{zain};"+
"''z<z){zain};"+
"z<{zain};"+
"dh<dh]{shadda};"+
"dd<dd]{shadda};"+
"''d<d]{shadda};"
"dh<dh){shadda};"+
"dd<dd){shadda};"+
"''d<d){shadda};"
}
};
}

54
icu4j/src/com/ibm/text/resources/TransliterationRule$Latin$Cyrillic.java
View file

@ -125,17 +125,17 @@ public class TransliterationRule$Latin$Cyrillic extends ListResourceBundle {
// Special titlecase forms, not duplicated
// #############################################
+ "Ch>{CH};" + "Ch<{CH}[{lower};"
+ "Kh>{KH};" + "Kh<{KH}[{lower};"
+ "Shch>{SHCH};" + "Shch<{SHCH}[{lower};"
+ "Sh>{SH};" + "Sh<{SH}[{lower};"
+ "Ts>{TS};" + "Ts<{TS}[{lower};"
+ "Zh>{ZH};" + "Zh<{ZH}[{lower};"
+ "Yi>{YI};" //+ "Yi<{YI}[{lower};"
+ "Ye>{YE};" //+ "Ye<{YE}[{lower};"
+ "Yo>{YO};" //+ "Yo<{YO}[{lower};"
+ "Yu>{YU};" //+ "Yu<{YU}[{lower};"
+ "Ya>{YA};" //+ "Ya<{YA}[{lower};"
+ "Ch>{CH};" + "Ch<{CH}({lower};"
+ "Kh>{KH};" + "Kh<{KH}({lower};"
+ "Shch>{SHCH};" + "Shch<{SHCH}({lower};"
+ "Sh>{SH};" + "Sh<{SH}({lower};"
+ "Ts>{TS};" + "Ts<{TS}({lower};"
+ "Zh>{ZH};" + "Zh<{ZH}({lower};"
+ "Yi>{YI};" //+ "Yi<{YI}({lower};"
+ "Ye>{YE};" //+ "Ye<{YE}({lower};"
+ "Yo>{YO};" //+ "Yo<{YO}({lower};"
+ "Yu>{YU};" //+ "Yu<{YU}({lower};"
+ "Ya>{YA};" //+ "Ya<{YA}({lower};"
// #############################################
// Rules to Duplicate
@ -154,15 +154,15 @@ public class TransliterationRule$Latin$Cyrillic extends ListResourceBundle {
// Separate letters that would otherwise join
+ "SH''<{SH}[{BECOMES_C};"
+ "T''<{T}[{BECOMES_S};"
+ "SH''<{SH}({BECOMES_C};"
+ "T''<{T}({BECOMES_S};"
+ "K''<{K}[{BECOMES_H};"
+ "S''<{S}[{BECOMES_H};"
+ "T''<{T}[{BECOMES_H};"
+ "Z''<{Z}[{BECOMES_H};"
+ "K''<{K}({BECOMES_H};"
+ "S''<{S}({BECOMES_H};"
+ "T''<{T}({BECOMES_H};"
+ "Z''<{Z}({BECOMES_H};"
+ "Y''<{Y}[{BECOMES_VOWEL};"
+ "Y''<{Y}({BECOMES_VOWEL};"
// Main letters
@ -213,7 +213,7 @@ public class TransliterationRule$Latin$Cyrillic extends ListResourceBundle {
// variant spellings in English
+ "C[{csoft}>{S};"
+ "C({csoft}>{S};"
+ "C>{K};"
// #############################################
@ -233,15 +233,15 @@ public class TransliterationRule$Latin$Cyrillic extends ListResourceBundle {
// separate letters that would otherwise join
+ "sh''<{sh}[{becomes_c};"
+ "t''<{t}[{becomes_s};"
+ "sh''<{sh}({becomes_c};"
+ "t''<{t}({becomes_s};"
+ "k''<{k}[{becomes_h};"
+ "s''<{s}[{becomes_h};"
+ "t''<{t}[{becomes_h};"
+ "z''<{z}[{becomes_h};"
+ "k''<{k}({becomes_h};"
+ "s''<{s}({becomes_h};"
+ "t''<{t}({becomes_h};"
+ "z''<{z}({becomes_h};"
+ "y''<{y}[{becomes_vowel};"
+ "y''<{y}({becomes_vowel};"
// main letters
@ -292,7 +292,7 @@ public class TransliterationRule$Latin$Cyrillic extends ListResourceBundle {
// variant spellings in english
+ "c[{csoft}>{s};"
+ "c({csoft}>{s};"
+ "c>{k};"

168
icu4j/src/com/ibm/text/resources/TransliterationRule$Latin$Devanagari.java
View file

@ -198,8 +198,8 @@ public class TransliterationRule$Latin$Devanagari extends ListResourceBundle {
+ ".>{danda};"
+ "{danda}.>{doubleDanda};"
+ "{depVowelAbove}]~>{bindu};"
+ "{depVowelBelow}]~>{candrabindu};"
+ "{depVowelAbove})~>{bindu};"
+ "{depVowelBelow})~>{candrabindu};"
// convert to dependent forms after consonant with no vowel:
// e.g. kai -> {ka}{virama}ai -> {ka}{ai}
@ -234,7 +234,7 @@ public class TransliterationRule$Latin$Devanagari extends ListResourceBundle {
+ "{virama}''o>{wo};"
+ "{virama}''a>{wa};"
+ "{virama}[{endThing}>;"
+ "{virama}({endThing}>;"
// convert any left-over apostrophes used for separation
@ -251,97 +251,97 @@ public class TransliterationRule$Latin$Devanagari extends ListResourceBundle {
// normal consonants
+ "kh<{kha}[&;"
+ "kh<{kha}(&;"
+ "kha<{kha};"
+ "k''<{ka}{virama}[{ha};"
+ "k<{ka}[&;"
+ "k''<{ka}{virama}({ha};"
+ "k<{ka}(&;"
+ "ka<{ka};"
+ "gh<{gha}[&;"
+ "gh<{gha}(&;"
+ "gha<{gha};"
+ "g''<{ga}{virama}[{ha};"
+ "g<{ga}[&;"
+ "g''<{ga}{virama}({ha};"
+ "g<{ga}(&;"
+ "ga<{ga};"
+ "ng<{nga}[&;"
+ "ng<{nga}(&;"
+ "nga<{nga};"
+ "ch<{cha}[&;"
+ "ch<{cha}(&;"
+ "cha<{cha};"
+ "c''<{ca}{virama}[{ha};"
+ "c<{ca}[&;"
+ "c''<{ca}{virama}({ha};"
+ "c<{ca}(&;"
+ "ca<{ca};"
+ "jh<{jha}[&;"
+ "jh<{jha}(&;"
+ "jha<{jha};"
+ "j''<{ja}{virama}[{ha};"
+ "j<{ja}[&;"
+ "j''<{ja}{virama}({ha};"
+ "j<{ja}(&;"
+ "ja<{ja};"
+ "ny<{nya}[&;"
+ "ny<{nya}(&;"
+ "nya<{nya};"
+ "tth<{ttha}[&;"
+ "tth<{ttha}(&;"
+ "ttha<{ttha};"
+ "tt''<{tta}{virama}[{ha};"
+ "tt<{tta}[&;"
+ "tt''<{tta}{virama}({ha};"
+ "tt<{tta}(&;"
+ "tta<{tta};"
+ "ddh<{ddha}[&;"
+ "ddh<{ddha}(&;"
+ "ddha<{ddha};"
+ "dd''<{dda}[&{ha};"
+ "dd<{dda}[&;"
+ "dd''<{dda}(&{ha};"
+ "dd<{dda}(&;"
+ "dda<{dda};"
+ "dh<{dha}[&;"
+ "dh<{dha}(&;"
+ "dha<{dha};"
+ "d''<{da}{virama}[{ha};"
+ "d''<{da}{virama}[{ddha};"
+ "d''<{da}{virama}[{dda};"
+ "d''<{da}{virama}[{dha};"
+ "d''<{da}{virama}[{da};"
+ "d<{da}[&;"
+ "d''<{da}{virama}({ha};"
+ "d''<{da}{virama}({ddha};"
+ "d''<{da}{virama}({dda};"
+ "d''<{da}{virama}({dha};"
+ "d''<{da}{virama}({da};"
+ "d<{da}(&;"
+ "da<{da};"
+ "th<{tha}[&;"
+ "th<{tha}(&;"
+ "tha<{tha};"
+ "t''<{ta}{virama}[{ha};"
+ "t''<{ta}{virama}[{ttha};"
+ "t''<{ta}{virama}[{tta};"
+ "t''<{ta}{virama}[{tha};"
+ "t''<{ta}{virama}[{ta};"
+ "t<{ta}[&;"
+ "t''<{ta}{virama}({ha};"
+ "t''<{ta}{virama}({ttha};"
+ "t''<{ta}{virama}({tta};"
+ "t''<{ta}{virama}({tha};"
+ "t''<{ta}{virama}({ta};"
+ "t<{ta}(&;"
+ "ta<{ta};"
+ "n''<{na}{virama}[{ga};"
+ "n''<{na}{virama}[{ya};"
+ "n<{na}[&;"
+ "n''<{na}{virama}({ga};"
+ "n''<{na}{virama}({ya};"
+ "n<{na}(&;"
+ "na<{na};"
+ "ph<{pha}[&;"
+ "ph<{pha}(&;"
+ "pha<{pha};"
+ "p''<{pa}{virama}[{ha};"
+ "p<{pa}[&;"
+ "p''<{pa}{virama}({ha};"
+ "p<{pa}(&;"
+ "pa<{pa};"
+ "bh<{bha}[&;"
+ "bh<{bha}(&;"
+ "bha<{bha};"
+ "b''<{ba}{virama}[{ha};"
+ "b<{ba}[&;"
+ "b''<{ba}{virama}({ha};"
+ "b<{ba}(&;"
+ "ba<{ba};"
+ "m''<{ma}{virama}[{ma};"
+ "m''<{ma}{virama}[{bindu};"
+ "m<{ma}[&;"
+ "m''<{ma}{virama}({ma};"
+ "m''<{ma}{virama}({bindu};"
+ "m<{ma}(&;"
+ "ma<{ma};"
+ "y<{ya}[&;"
+ "y<{ya}(&;"
+ "ya<{ya};"
+ "r''<{ra}{virama}[{ha};"
+ "r<{ra}[&;"
+ "r''<{ra}{virama}({ha};"
+ "r<{ra}(&;"
+ "ra<{ra};"
+ "l''<{la}{virama}[{ha};"
+ "l<{la}[&;"
+ "l''<{la}{virama}({ha};"
+ "l<{la}(&;"
+ "la<{la};"
+ "v<{va}[&;"
+ "v<{va}(&;"
+ "va<{va};"
+ "sh<{sha}[&;"
+ "sh<{sha}(&;"
+ "sha<{sha};"
+ "ss<{ssa}[&;"
+ "ss<{ssa}(&;"
+ "ssa<{ssa};"
+ "s''<{sa}{virama}[{ha};"
+ "s''<{sa}{virama}[{sha};"
+ "s''<{sa}{virama}[{ssa};"
+ "s''<{sa}{virama}[{sa};"
+ "s<{sa}[&;"
+ "s''<{sa}{virama}({ha};"
+ "s''<{sa}{virama}({sha};"
+ "s''<{sa}{virama}({ssa};"
+ "s''<{sa}{virama}({sa};"
+ "s<{sa}(&;"
+ "sa<{sa};"
+ "h<{ha}[&;"
+ "h<{ha}(&;"
+ "ha<{ha};"
// dependent vowels (should never occur except following consonants)
@ -361,27 +361,27 @@ public class TransliterationRule$Latin$Devanagari extends ListResourceBundle {
// independent vowels (when following consonants)
+ "''aa<a]{waa};"
+ "''aa<%]{waa};"
+ "''ai<a]{wai};"
+ "''ai<%]{wai};"
+ "''au<a]{wau};"
+ "''au<%]{wau};"
+ "''ii<a]{wii};"
+ "''ii<%]{wii};"
+ "''i<a]{wi};"
+ "''i<%]{wi};"
+ "''uu<a]{wuu};"
+ "''uu<%]{wuu};"
+ "''u<a]{wu};"
+ "''u<%]{wu};"
+ "''rrh<%]{wrr};"
+ "''rh<%]{wr};"
+ "''lh<%]{wl};"
+ "''e<%]{we};"
+ "''o<%]{wo};"
+ "''a<a]{wa};"
+ "''a<%]{wa};"
+ "''aa<a){waa};"
+ "''aa<%){waa};"
+ "''ai<a){wai};"
+ "''ai<%){wai};"
+ "''au<a){wau};"
+ "''au<%){wau};"
+ "''ii<a){wii};"
+ "''ii<%){wii};"
+ "''i<a){wi};"
+ "''i<%){wi};"
+ "''uu<a){wuu};"
+ "''uu<%){wuu};"
+ "''u<a){wu};"
+ "''u<%){wu};"
+ "''rrh<%){wrr};"
+ "''rh<%){wr};"
+ "''lh<%){wl};"
+ "''e<%){we};"
+ "''o<%){wo};"
+ "''a<a){wa};"
+ "''a<%){wa};"
// independent vowels (otherwise)

48
icu4j/src/com/ibm/text/resources/TransliterationRule$Latin$Greek.java
View file

@ -177,10 +177,10 @@ public class TransliterationRule$Latin$Greek extends ListResourceBundle {
// not be copied when duplicating the lowercase
// ==============================================
+ "Th<{THETA}[{lower};"
+ "Ph<{PHI}[{lower};"
+ "Ch<{CHI}[{lower};"
//masked: + "Ps<{PHI}[{lower};"
+ "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.
@ -189,12 +189,12 @@ public class TransliterationRule$Latin$Greek extends ListResourceBundle {
// 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<{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({letter}>{SIGMA};" + "S<{SIGMA};"
+ "s({letter}>{sigma};" + "s<{sigma};"
+ "s<>{sigma+};"
// because there are no uppercase forms, had to move these up too.
@ -203,7 +203,7 @@ public class TransliterationRule$Latin$Greek extends ListResourceBundle {
+ "y\"`>{ypsilon\u00a8+};"
+ "{\u00ef-acute}<>{iota\u00a8+};"
+ "{vowel}]{\u00fc-acute}>{ypsilon\u00a8+};" + "{\u00fc-acute}<{vowel}]{ypsilon\u00a8+};"
+ "{vowel}){\u00fc-acute}>{ypsilon\u00a8+};" + "{\u00fc-acute}<{vowel}){ypsilon\u00a8+};"
+ "{y-umlaut-acute}<>{ypsilon\u00a8+};"
// ==============================================
@ -229,7 +229,7 @@ public class TransliterationRule$Latin$Greek extends ListResourceBundle {
+ "A<>{ALPHA};"
+ "\u00c1<>{ALPHA+};"
+ "B<>{BETA};"
+ "N]{n-gamma}>{GAMMA};" + "N<{GAMMA}[{gamma-n};"
+ "N){n-gamma}>{GAMMA};" + "N<{GAMMA}({gamma-n};"
+ "G<>{GAMMA};"
+ "D<>{DELTA};"
+ "E<>{EPSILON};"
@ -253,9 +253,9 @@ public class TransliterationRule$Latin$Greek extends ListResourceBundle {
+ "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};"
+ "{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};"
@ -265,9 +265,9 @@ public class TransliterationRule$Latin$Greek extends ListResourceBundle {
// Extra English Letters. Mapped for completeness
+ "C[I>{SIGMA};"
+ "C[E>{SIGMA};"
+ "C[Y>{SIGMA};"
+ "C(I>{SIGMA};"
+ "C(E>{SIGMA};"
+ "C(Y>{SIGMA};"
+ "C>{KAPPA};"
+ "F>{PHI};"
+ "H>{CHI};"
@ -298,7 +298,7 @@ public class TransliterationRule$Latin$Greek extends ListResourceBundle {
+ "a<>{alpha};"
+ "\u00e1<>{alpha+};"
+ "b<>{beta};"
+ "n]{n-gamma}>{gamma};" + "n<{gamma}[{gamma-n};"
+ "n){n-gamma}>{gamma};" + "n<{gamma}({gamma-n};"
+ "g<>{gamma};"
+ "d<>{delta};"
+ "e<>{epsilon};"
@ -322,9 +322,9 @@ public class TransliterationRule$Latin$Greek extends ListResourceBundle {
+ "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};"
+ "{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};"
@ -334,9 +334,9 @@ public class TransliterationRule$Latin$Greek extends ListResourceBundle {
// extra english letters. mapped for completeness
+ "c[i>{sigma};"
+ "c[e>{sigma};"
+ "c[y>{sigma};"
+ "c(i>{sigma};"
+ "c(e>{sigma};"
+ "c(y>{sigma};"
+ "c>{kappa};"
+ "f>{phi};"
+ "h>{chi};"

48
icu4j/src/com/ibm/text/resources/TransliterationRule$Latin$Hebrew.java
View file

@ -98,10 +98,10 @@ public class TransliterationRule$Latin$Hebrew extends ListResourceBundle {
+ "b>{BET};"
+ "B>{BET};"
+ "c[{softvowel}>{SAMEKH};"
+ "C[{softvowel}>{SAMEKH};"
+ "c[{letter}>{KAF};"
+ "C[{letter}>{KAF};"
+ "c({softvowel}>{SAMEKH};"
+ "C({softvowel}>{SAMEKH};"
+ "c({letter}>{KAF};"
+ "C({letter}>{KAF};"
+ "c>{FINAL_KAF};"
+ "C>{FINAL_KAF};"
@ -111,9 +111,9 @@ public class TransliterationRule$Latin$Hebrew extends ListResourceBundle {
+ "e>{AYIN};"
+ "E>{AYIN};"
+ "f[{letter}>{PE};"
+ "f({letter}>{PE};"
+ "f>{FINAL_PE};"
+ "F[{letter}>{PE};"
+ "F({letter}>{PE};"
+ "F>{FINAL_PE};"
+ "g>{GIMEL};"
@ -132,30 +132,30 @@ public class TransliterationRule$Latin$Hebrew extends ListResourceBundle {
+ "kh>{HET};"
+ "KH>{HET};"
+ "Kh>{HET};"
+ "k[{letter}>{KAF};"
+ "K[{letter}>{KAF};"
+ "k({letter}>{KAF};"
+ "K({letter}>{KAF};"
+ "k>{FINAL_KAF};"
+ "K>{FINAL_KAF};"
+ "l>{LAMED};"
+ "L>{LAMED};"
+ "m[{letter}>{MEM};"
+ "m({letter}>{MEM};"
+ "m>{FINAL_MEM};"
+ "M[{letter}>{MEM};"
+ "M({letter}>{MEM};"
+ "M>{FINAL_MEM};"
+ "n[{letter}>{NUN};"
+ "n({letter}>{NUN};"
+ "n>{FINAL_NUN};"
+ "N[{letter}>{NUN};"
+ "N({letter}>{NUN};"
+ "N>{FINAL_NUN};"
+ "o>{VAV};"
+ "O>{VAV};"
+ "p[{letter}>{PE};"
+ "p({letter}>{PE};"
+ "p>{FINAL_PE};"
+ "P[{letter}>{PE};"
+ "P({letter}>{PE};"
+ "P>{FINAL_PE};"
+ "q>{QOF};"
@ -175,10 +175,10 @@ public class TransliterationRule$Latin$Hebrew extends ListResourceBundle {
+ "tH>{TAV};"
+ "TH>{TAV};"
+ "Th>{TAV};"
+ "tS[{letter}>{TSADI};"
+ "ts[{letter}>{TSADI};"
+ "Ts[{letter}>{TSADI};"
+ "TS[{letter}>{TSADI};"
+ "tS({letter}>{TSADI};"
+ "ts({letter}>{TSADI};"
+ "Ts({letter}>{TSADI};"
+ "TS({letter}>{TSADI};"
+ "tS>{FINAL_TSADI};"
+ "ts>{FINAL_TSADI};"
+ "Ts>{FINAL_TSADI};"
@ -244,7 +244,7 @@ public class TransliterationRule$Latin$Hebrew extends ListResourceBundle {
+ "g<{GIMEL};"
+ "kh<{HET};"
+ "h<{HE};"
+ "k''<{KAF}[{HE};"
+ "k''<{KAF}({HE};"
+ "k<{KAF};"
+ "l<{LAMED};"
+ "m<{MEM};"
@ -252,16 +252,16 @@ public class TransliterationRule$Latin$Hebrew extends ListResourceBundle {
+ "p<{PE};"
+ "q<{QOF};"
+ "r<{RESH};"
+ "s''<{SAMEKH}[{HE};"
+ "s''<{SAMEKH}({HE};"
+ "s<{SAMEKH};"
+ "sh<{SHIN};"
+ "th<{TAV};"
+ "t''<{TET}[{HE};"
+ "t''<{TET}[{SAMEKH};"
+ "t''<{TET}[{SHIN};"
+ "t''<{TET}({HE};"
+ "t''<{TET}({SAMEKH};"
+ "t''<{TET}({SHIN};"
+ "t<{TET};"
+ "ts<{TSADI};"
+ "v<{VAV}[{vowellike};"
+ "v<{VAV}({vowellike};"
+ "u<{VAV};"
+ "y<{YOD};"
+ "z<{ZAYIN};"

274
icu4j/src/com/ibm/text/resources/TransliterationRule$Latin$Kana.java
View file

@ -12,7 +12,7 @@ public class TransliterationRule$Latin$Kana extends ListResourceBundle {
// Uppercase Latin to katakana
{ "Rule", ""
//# $Revision: 1.6 $
//# $Revision: 1.7 $
// Transliteration rules for Japanese Hiragana and Katakana to
// romaji
// lower case roman generates hiragana.
@ -375,8 +375,8 @@ public class TransliterationRule$Latin$Kana extends ListResourceBundle {
+ "CHI>{TI};"
+ "CH>{TI}|~Y;"
+ "C[I>|S;"
+ "C[E>|S;"
+ "C(I>|S;"
+ "C(E>|S;"
+ "DA>{DA};"
+ "DI>{DE}{~I};"
@ -422,10 +422,10 @@ public class TransliterationRule$Latin$Kana extends ListResourceBundle {
+ "MO>{MO};"
+ "MY>{MI}|~Y;"
+ "M[P>{^N};"
+ "M[B>{^N};"
+ "M[F>{^N};"
+ "M[V>{^N};"
+ "M(P>{^N};"
+ "M(B>{^N};"
+ "M(F>{^N};"
+ "M(V>{^N};"
+ "NA>{NA};"
+ "NI>{NI};"
@ -509,31 +509,31 @@ public class TransliterationRule$Latin$Kana extends ListResourceBundle {
// DOUBLE CONSONANTS
+ "B[B>{~TU};"
+ "C[K>{~TU};"
+ "C[C>{~TU};"
+ "C[Q>{~TU};"
+ "D[D>{~TU};"
+ "F[F>{~TU};"
+ "G[G>{~TU};"
+ "H[H>{~TU};"
+ "J[J>{~TU};"
+ "K[K>{~TU};"
+ "L[L>{~TU};"
+ "M[M>{~TU};"
+ "N[N>{~TU};"
+ "P[P>{~TU};"
+ "Q[Q>{~TU};"
+ "R[R>{~TU};"
+ "S[SH>{~TU};"
+ "S[S>{~TU};"
+ "T[CH>{~TU};"
+ "T[T>{~TU};"
+ "V[V>{~TU};"
+ "W[W>{~TU};"
+ "X[X>{~TU};"
+ "Y[Y>{~TU};"
+ "Z[Z>{~TU};"
+ "B(B>{~TU};"
+ "C(K>{~TU};"
+ "C(C>{~TU};"
+ "C(Q>{~TU};"
+ "D(D>{~TU};"
+ "F(F>{~TU};"
+ "G(G>{~TU};"
+ "H(H>{~TU};"
+ "J(J>{~TU};"
+ "K(K>{~TU};"
+ "L(L>{~TU};"
+ "M(M>{~TU};"
+ "N(N>{~TU};"
+ "P(P>{~TU};"
+ "Q(Q>{~TU};"
+ "R(R>{~TU};"
+ "S(SH>{~TU};"
+ "S(S>{~TU};"
+ "T(CH>{~TU};"
+ "T(T>{~TU};"
+ "V(V>{~TU};"
+ "W(W>{~TU};"
+ "X(X>{~TU};"
+ "Y(Y>{~TU};"
+ "Z(Z>{~TU};"
// ########################################
// CATCH MISSING VOWELS!
@ -772,41 +772,41 @@ public class TransliterationRule$Latin$Kana extends ListResourceBundle {
// DOUBLED LETTERS
+ "N''<{^N}[{^A};"
+ "N''<{^N}[{^I};"
+ "N''<{^N}[{^U};"
+ "N''<{^N}[{^E};"
+ "N''<{^N}[{^O};"
+ "N''<{^N}[{NA};"
+ "N''<{^N}[{NI};"
+ "N''<{^N}[{NU};"
+ "N''<{^N}[{NE};"
+ "N''<{^N}[{NO};"
+ "N''<{^N}[{YA};"
+ "N''<{^N}[{YU};"
+ "N''<{^N}[{YO};"
+ "N''<{^N}[{^N};"
+ "N''<{^N}({^A};"
+ "N''<{^N}({^I};"
+ "N''<{^N}({^U};"
+ "N''<{^N}({^E};"
+ "N''<{^N}({^O};"
+ "N''<{^N}({NA};"
+ "N''<{^N}({NI};"
+ "N''<{^N}({NU};"
+ "N''<{^N}({NE};"
+ "N''<{^N}({NO};"
+ "N''<{^N}({YA};"
+ "N''<{^N}({YU};"
+ "N''<{^N}({YO};"
+ "N''<{^N}({^N};"
+ "N<{^N};"
+ "N<{~TU}[{N-START};"
+ "M<{~TU}[{M-START};"
+ "W<{~TU}[{W-START};"
+ "Y<{~TU}[{Y-START};"
+ "G<{~TU}[{G-START};"
+ "K<{~TU}[{K-START};"
+ "Z<{~TU}[{Z-START};"
+ "J<{~TU}[{J-START};"
+ "S<{~TU}[{S-START};"
+ "D<{~TU}[{D-START};"
+ "T<{~TU}[{T-START};"
+ "B<{~TU}[{B-START};"
+ "P<{~TU}[{P-START};"
+ "H<{~TU}[{H-START};"
+ "F<{~TU}[{F-START};"
+ "R<{~TU}[{R-START};"
+ "V<{~TU}[{V-START};"
+ "N<{~TU}({N-START};"
+ "M<{~TU}({M-START};"
+ "W<{~TU}({W-START};"
+ "Y<{~TU}({Y-START};"
+ "G<{~TU}({G-START};"
+ "K<{~TU}({K-START};"
+ "Z<{~TU}({Z-START};"
+ "J<{~TU}({J-START};"
+ "S<{~TU}({S-START};"
+ "D<{~TU}({D-START};"
+ "T<{~TU}({T-START};"
+ "B<{~TU}({B-START};"
+ "P<{~TU}({P-START};"
+ "H<{~TU}({H-START};"
+ "F<{~TU}({F-START};"
+ "R<{~TU}({R-START};"
+ "V<{~TU}({V-START};"
+ "A<{^A};" // MOVED THIS BLOCK DOWN [LIU]
+ "A<{^A};" // MOVED THIS BLOCK DOWN {aliu}
+ "I<{^I};"
+ "U<{^U};"
+ "E<{^E};"
@ -829,11 +829,11 @@ public class TransliterationRule$Latin$Kana extends ListResourceBundle {
// LENGTH MARK. LATER, COULD USE CIRCUMFLEX
+ "A<A]{LONG};" // LIU
+ "E<E]{LONG};" // LIU
+ "I<I]{LONG};" // LIU
+ "O<O]{LONG};" // LIU
+ "U<U]{LONG};" // LIU
+ "A<A){LONG};" // LIU
+ "E<E){LONG};" // LIU
+ "I<I){LONG};" // LIU
+ "O<O){LONG};" // LIU
+ "U<U){LONG};" // LIU
//#######################################
// HIRAGANA
@ -852,8 +852,8 @@ public class TransliterationRule$Latin$Kana extends ListResourceBundle {
+ "chi>{ti};"
+ "ch>{ti}|~y;"
+ "c[i>|s;"
+ "c[e>|s;"
+ "c(i>|s;"
+ "c(e>|s;"
+ "da>{da};"
+ "di>{de}{~i};"
@ -899,10 +899,10 @@ public class TransliterationRule$Latin$Kana extends ListResourceBundle {
+ "mo>{mo};"
+ "my>{mi}|~y;"
+ "m[p>{^n};"
+ "m[b>{^n};"
+ "m[f>{^n};"
+ "m[v>{^n};"
+ "m(p>{^n};"
+ "m(b>{^n};"
+ "m(f>{^n};"
+ "m(v>{^n};"
+ "na>{na};"
+ "ni>{ni};"
@ -986,31 +986,31 @@ public class TransliterationRule$Latin$Kana extends ListResourceBundle {
// Double Consonants
+ "b[b>{~tu};"
+ "c[k>{~tu};"
+ "c[c>{~tu};"
+ "c[q>{~tu};"
+ "d[d>{~tu};"
+ "f[f>{~tu};"
+ "g[g>{~tu};"
+ "h[h>{~tu};"
+ "j[j>{~tu};"
+ "k[k>{~tu};"
+ "l[l>{~tu};"
+ "m[m>{~tu};"
+ "n[n>{~tu};"
+ "p[p>{~tu};"
+ "q[q>{~tu};"
+ "r[r>{~tu};"
+ "s[sh>{~tu};"
+ "s[s>{~tu};"
+ "t[ch>{~tu};"
+ "t[t>{~tu};"
+ "v[v>{~tu};"
+ "w[w>{~tu};"
+ "x[x>{~tu};"
+ "y[y>{~tu};"
+ "z[z>{~tu};"
+ "b(b>{~tu};"
+ "c(k>{~tu};"
+ "c(c>{~tu};"
+ "c(q>{~tu};"
+ "d(d>{~tu};"
+ "f(f>{~tu};"
+ "g(g>{~tu};"
+ "h(h>{~tu};"
+ "j(j>{~tu};"
+ "k(k>{~tu};"
+ "l(l>{~tu};"
+ "m(m>{~tu};"
+ "n(n>{~tu};"
+ "p(p>{~tu};"
+ "q(q>{~tu};"
+ "r(r>{~tu};"
+ "s(sh>{~tu};"
+ "s(s>{~tu};"
+ "t(ch>{~tu};"
+ "t(t>{~tu};"
+ "v(v>{~tu};"
+ "w(w>{~tu};"
+ "x(x>{~tu};"
+ "y(y>{~tu};"
+ "z(z>{~tu};"
// ########################################
// catch missing vowels!
@ -1249,41 +1249,41 @@ public class TransliterationRule$Latin$Kana extends ListResourceBundle {
// Doubled letters
+ "n''<{^n}[{^a};"
+ "n''<{^n}[{^i};"
+ "n''<{^n}[{^u};"
+ "n''<{^n}[{^e};"
+ "n''<{^n}[{^o};"
+ "n''<{^n}[{na};"
+ "n''<{^n}[{ni};"
+ "n''<{^n}[{nu};"
+ "n''<{^n}[{ne};"
+ "n''<{^n}[{no};"
+ "n''<{^n}[{ya};"
+ "n''<{^n}[{yu};"
+ "n''<{^n}[{yo};"
+ "n''<{^n}[{^n};"
+ "n''<{^n}({^a};"
+ "n''<{^n}({^i};"
+ "n''<{^n}({^u};"
+ "n''<{^n}({^e};"
+ "n''<{^n}({^o};"
+ "n''<{^n}({na};"
+ "n''<{^n}({ni};"
+ "n''<{^n}({nu};"
+ "n''<{^n}({ne};"
+ "n''<{^n}({no};"
+ "n''<{^n}({ya};"
+ "n''<{^n}({yu};"
+ "n''<{^n}({yo};"
+ "n''<{^n}({^n};"
+ "n<{^n};"
+ "n<{~tu}[{n-start};"
+ "m<{~tu}[{m-start};"
+ "w<{~tu}[{w-start};"
+ "y<{~tu}[{y-start};"
+ "g<{~tu}[{g-start};"
+ "k<{~tu}[{k-start};"
+ "z<{~tu}[{z-start};"
+ "j<{~tu}[{j-start};"
+ "s<{~tu}[{s-start};"
+ "d<{~tu}[{d-start};"
+ "t<{~tu}[{t-start};"
+ "b<{~tu}[{b-start};"
+ "p<{~tu}[{p-start};"
+ "h<{~tu}[{h-start};"
+ "f<{~tu}[{f-start};"
+ "r<{~tu}[{r-start};"
+ "v<{~tu}[{v-start};"
+ "n<{~tu}({n-start};"
+ "m<{~tu}({m-start};"
+ "w<{~tu}({w-start};"
+ "y<{~tu}({y-start};"
+ "g<{~tu}({g-start};"
+ "k<{~tu}({k-start};"
+ "z<{~tu}({z-start};"
+ "j<{~tu}({j-start};"
+ "s<{~tu}({s-start};"
+ "d<{~tu}({d-start};"
+ "t<{~tu}({t-start};"
+ "b<{~tu}({b-start};"
+ "p<{~tu}({p-start};"
+ "h<{~tu}({h-start};"
+ "f<{~tu}({f-start};"
+ "r<{~tu}({r-start};"
+ "v<{~tu}({v-start};"
+ "a<{^a};" // Moved this block down [LIU]
+ "a<{^a};" // Moved this block down {aliu}
+ "i<{^i};"
+ "u<{^u};"
+ "e<{^e};"
@ -1306,11 +1306,11 @@ public class TransliterationRule$Latin$Kana extends ListResourceBundle {
// length mark. Later, could use circumflex
+ "a<a]{long};" // Liu
+ "e<e]{long};" // Liu
+ "i<i]{long};" // Liu
+ "o<o]{long};" // Liu
+ "u<u]{long};" // Liu
+ "a<a){long};" // Liu
+ "e<e){long};" // Liu
+ "i<i){long};" // Liu
+ "o<o){long};" // Liu
+ "u<u){long};" // Liu
//#######################################
// Non-shared stuff goes here

18
icu4j/src/com/ibm/text/resources/TransliterationRule$StraightQuotes$CurlyQuotes.java
View file

@ -11,8 +11,8 @@ public class TransliterationRule$StraightQuotes$CurlyQuotes extends ListResource
{ "Rule",
// Rewritten using character codes [LIU]
"white=[[:Zs:][:Zl:][:Zp:]];"
+ "black=[^[:Zs:][:Zl:][:Zp:]];"
+ "open=[[:Ps:]];"
+ "black=[^{white}];"
+ "open=[:Ps:];"
+ "dquote=\";"
+ "lAng=\u3008;"
@ -43,15 +43,15 @@ public class TransliterationRule$StraightQuotes$CurlyQuotes extends ListResource
+ "{rquote}{rquote}>{rdquote};"
//smart single quotes
+ "{white}]''>{lquote};"
+ "{open}]''>{lquote};"
+ "{black}]''>{rquote};"
+ "{white})''>{lquote};"
+ "{open})''>{lquote};"
+ "{black})''>{rquote};"
+ "''>{lquote};"
//smart doubles
+ "{white}]{dquote}>{ldquote};"
+ "{open}]{dquote}>{ldquote};"
+ "{black}]{dquote}>{rdquote};"
+ "{white}){dquote}>{ldquote};"
+ "{open}){dquote}>{ldquote};"
+ "{black}){dquote}>{rdquote};"
+ "{dquote}>{ldquote};"
// join single guillemets
@ -61,7 +61,7 @@ public class TransliterationRule$StraightQuotes$CurlyQuotes extends ListResource
+ "'<<'>{ldguill};"
// prevent double spaces
+ " ] >;"
+ "\\ )\\ >;"
// join hyphens into dash
+ "-->{mdash};"