[sword-svn] r2412 - trunk/icu
chrislit at crosswire.org
chrislit at crosswire.org
Thu May 14 12:46:39 MST 2009
Author: chrislit
Date: 2009-05-14 12:46:39 -0700 (Thu, 14 May 2009)
New Revision: 2412
Removed:
trunk/icu/translit_Latin_Arabic.txt
trunk/icu/translit_Latin_Armenian.txt
trunk/icu/translit_Latin_Ethiopic.txt
trunk/icu/translit_Latin_Georgian.txt
trunk/icu/translit_Latin_Hebrew.txt
trunk/icu/translit_Latin_Syriac.txt
trunk/icu/translit_Latin_Thai.txt
Modified:
trunk/icu/Makefile.am
trunk/icu/translit_swordindex.txt
Log:
started to update old ICU stuff in sword repo by removing transliterators now part of stock ICU
Modified: trunk/icu/Makefile.am
===================================================================
--- trunk/icu/Makefile.am 2009-05-14 07:42:28 UTC (rev 2411)
+++ trunk/icu/Makefile.am 2009-05-14 19:46:39 UTC (rev 2412)
@@ -4,25 +4,13 @@
swicuSOURCES += translit_BGreek_Greek.txt
swicuSOURCES += translit_CCAT_Hebrew.txt
swicuSOURCES += translit_CCAT_Syriac.txt
-swicuSOURCES += translit_Latin_Armenian.txt
swicuSOURCES += translit_Latin_Coptic.txt
-swicuSOURCES += translit_Latin_Ethiopic.txt
-swicuSOURCES += translit_Latin_Georgian.txt
swicuSOURCES += translit_Latin_Gothic.txt
-swicuSOURCES += translit_Latin_Syriac.txt
-swicuSOURCES += translit_Latin_Thai.txt
swicuSOURCES += translit_Latin_Ugaritic.txt
swicuSOURCES += translit_Any_Latin1.txt
swicuSOURCES += translit_Any_Latex.txt
-#swicuSOURCES += translit_HTMLEnt_Unicode.txt
-#swicuSOURCES += translit_Han_Pinyin.txt
-#swicuSOURCES += translit_Kanji_English.txt
-#swicuSOURCES += translit_Kanji_OnRomaji.txt
-swicuSOURCES += translit_Latin_Arabic.txt
-swicuSOURCES += translit_Latin_Hebrew.txt
swicuSOURCES += translit_swordindex.txt
-
if ICU
swicu_DATA = $(swicuSOURCES:.txt=.res)
else
Deleted: trunk/icu/translit_Latin_Arabic.txt
===================================================================
--- trunk/icu/translit_Latin_Arabic.txt 2009-05-14 07:42:28 UTC (rev 2411)
+++ trunk/icu/translit_Latin_Arabic.txt 2009-05-14 19:46:39 UTC (rev 2412)
@@ -1,198 +0,0 @@
-//--------------------------------------------------------------------
-// Copyright (c) 1999-2000, International Business Machines
-// Corporation and others. All Rights Reserved.
-//--------------------------------------------------------------------
-// THIS IS A MACHINE-GENERATED FILE
-// Tool: src\com\ibm\tools\translit\dumpICUrules.bat
-// Source: src\com\ibm\text\resources/TransliterationRule_Latin_Arabic.java
-// Date: Wed Jul 5 16:11:18 2000
-//--------------------------------------------------------------------
-
-// Latin-Arabic
-
-translit_Latin_Arabic {
- Rule {
- ":: NFD (NFC) ;"
-
- // To Do: finish adding shadda, add sokoon
- // [Is this done? Can someone finish this?]
-
- "$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
-
- ":: NFC (NFD) ;"
- }
-}
Deleted: trunk/icu/translit_Latin_Armenian.txt
===================================================================
--- trunk/icu/translit_Latin_Armenian.txt 2009-05-14 07:42:28 UTC (rev 2411)
+++ trunk/icu/translit_Latin_Armenian.txt 2009-05-14 19:46:39 UTC (rev 2412)
@@ -1,151 +0,0 @@
-//--------------------------------------------------------------------
-// Copyright 2001, CrossWire Bible Society (http://www.crosswire.org)
-// Use freely.
-//--------------------------------------------------------------------
-// Based upon UNGEGN recommendations from
-// http://www.eki.ee/wgrs/rom2_hy.pdf
-//--------------------------------------------------------------------
-
-// Latin-Armenian
-
-translit_Latin_Armenian {
- Rule {
- ":: NFD (NFC) ;"
-
- "$armenian = [[:ARMENIAN:] & [:L:]];"
- "$armenian_vowels = [\u0531\u0535\u0537\u053B\u0548\u0552\u0555\u0561\u0565\u0567\u056B\u0578\u0582\u0585];"
-
- "Ye<[:^L:]{\u0535}[:Ll:];"
- "Ye<[$armenian_vowels]{\u0535}[:Ll:];"
- "YE<[:^L:]{\u0535;"
- "YE<[$armenian_vowels]{\u0535;"
-
- "OV<[:^L:]{\u0548\u054E}[:^L:];"
- "Ov<[:^L:]{\u0548\u057E}[:^L:];"
- "Vo<[:^L:]{\u0548}[:Ll:];"
- "VO<[:^L:]{\u0548;"
-
- "Ts''<>\u0551}[:Ll:];"
- "Ch''<>\u0549}[:Ll:];"
-
- "Gh<>\u0542}[:Ll:];"
- "Dz<>\u0541}[:Ll:];"
- "Zh<>\u053A}[:Ll:];"
- "Kh<>\u053D}[:Ll:];"
- "Ts<>\u053E}[:Ll:];"
- "Ch<>\u0543}[:Ll:];"
- "Sh<>\u0547}[:Ll:];"
- "Rr<>\u054C}[:Ll:];"
-
- "TS''<>\u0551;"
- "CH''<>\u0549;"
-
- "GH<>\u0542;"
- "DZ<>\u0541;"
- "T''<>\u0539;"
- "ZH<>\u053A;"
- "KH<>\u053D;"
- "TS<>\u053E;"
- "CH<>\u0543;"
- "SH<>\u0547;"
- "RR<>\u054C;"
- "P''<>\u0553;"
- "K''<>\u0554;"
-
- "A<>\u0531;"
- "B<>\u0532;"
- "G<>\u0533;"
- "D<>\u0534;"
- "E<>\u0535;"
- "Z<>\u0536;"
- "E<\u0537;"
- "Y<>\u0538;"
- "I<>\u053B;"
- "L<>\u053C;"
- "K<>\u053F;"
- "H<>\u0540;"
- "M<>\u0544;"
- "Y<\u0545;"
- "N<>\u0546;"
- "O<\u0548;"
- "P<>\u054A;"
- "J<>\u054B;"
- "S<>\u054D;"
- "V<>\u054E;"
- "T<>\u054F;"
- "R<>\u0550;"
- "U<>\u0552;"
- "O<>\u0555;"
- "F<>\u0556;"
-
- "\u02BF<>\u0559;"
- "\u02BE<>\u055A;"
- "\u02CA<>\u055B;"
- "'!'<>\u055C;"
- "','<>\u055D;"
- "'?'<>\u055E;"
- "\u2026<\u055F;"
-
- "yev<>[:^L:]{\u0587;"
- "yev<[$armenian_vowels]{\u0587;"
- "ye<[:^L:]{\u0565;"
- "ye<[$armenian_vowels]{\u0565;"
-
- "ov<>[:^L:]{\u0578\u057E}[:^L:];"
- "vo<>[:^L:]{\u0578;"
-
- "ts''<>\u0581;"
- "ch''<>\u0579;"
-
- "gh<>\u0572;"
- "dz<>\u0571;"
- "ev<>\u0587;"
- "t''<>\u0569;"
- "zh<>\u056A;"
- "kh<>\u056D;"
- "ts<>\u056E;"
- "k''<>\u0584;"
- "ch<>\u0573;"
- "p''<>\u0583;"
- "rr<>\u057C;"
- "sh<>\u0577;"
-
- "a<>\u0561;"
- "b<>\u0562;"
- "g<>\u0563;"
- "d<>\u0564;"
- "e<>\u0565;"
- "z<>\u0566;"
- "e<\u0567;"
- "y<>\u0568;"
- "i<>\u056B;"
- "l<>\u056C;"
- "k<>\u056F;"
- "h<>\u0570;"
- "m<>\u0574;"
- "y<\u0575;"
- "n<>\u0576;"
- "o<\u0578;"
- "p<>\u057A;"
- "j<>\u057B;"
- "s<>\u057D;"
- "v<>\u057E;"
- "t<>\u057F;"
- "r<>\u0580;"
- "u<>\u0582;"
- "o<>\u0585;"
- "f<>\u0586;"
-
- "'.'<>\u0589;"
- "'-'<>\u058A;"
-
- //remove untransliterated
- "<[:ARMENIAN:];"
- "[:LATIN:]>;"
-
- ":: NFC (NFD) ;"
- }
-}
-
-
-
Deleted: trunk/icu/translit_Latin_Ethiopic.txt
===================================================================
--- trunk/icu/translit_Latin_Ethiopic.txt 2009-05-14 07:42:28 UTC (rev 2411)
+++ trunk/icu/translit_Latin_Ethiopic.txt 2009-05-14 19:46:39 UTC (rev 2412)
@@ -1,407 +0,0 @@
-//--------------------------------------------------------------------
-// Copyright 2001, CrossWire Bible Society (http://www.crosswire.org)
-// Use freely.
-//--------------------------------------------------------------------
-// Based upon UNGEGN recommendations for Amharic/Ethiopic from
-// http://www.eki.ee/wgrs/rom1_am.pdf
-//--------------------------------------------------------------------
-// Latin-Ethiopic
-
-translit_Latin_Ethiopic {
- Rule {
- ":: NFD (NFC) ;"
-
- ":: [:LATIN:] lower();"
-
- "$macron = \u0331;"
-
- "li$macron<>\u120D;"
- "le$macron<>\u1208;"
- "lu<>\u1209;"
- "li<>\u120A;"
- "la<>\u120B;"
- "le<>\u120C;"
- "lo<>\u120E;"
- "lwa<>\u120F;"
-
- "mi$macron<>\u121D;"
- "me$macron<>\u1218;"
- "mu<>\u1219;"
- "mi<>\u121A;"
- "ma<>\u121B;"
- "me<>\u121C;"
- "mo<>\u121E;"
- "mwa<>\u121F;"
-
- "si$macron<>\u1225;"
- "se$macron<>\u1220;"
- "su<>\u1221;"
- "si<>\u1222;"
- "sa<>\u1223;"
- "se<>\u1224;"
- "so<>\u1226;"
- "swa<>\u1227;"
-
- "ri$macron<>\u122D;"
- "re$macron<>\u1228;"
- "ru<>\u1229;"
- "ri<>\u122A;"
- "ra<>\u122B;"
- "re<>\u122C;"
- "ro<>\u122E;"
- "rwa<>\u122F;"
-
- "si$macron<\u1235;"
- "se$macron<\u1230;"
- "su<\u1231;"
- "si<\u1232;"
- "sa<\u1233;"
- "se<\u1234;"
- "so<\u1236;"
- "swa<\u1237;"
-
- "shi$macron<>\u123D;"
- "she$macron<>\u1238;"
- "shu<>\u1239;"
- "shi<>\u123A;"
- "sha<>\u123B;"
- "she<>\u123C;"
- "sho<>\u123E;"
- "shwa<>\u123F;"
-
- "k''i$macron<>\u1245;"
- "k''e$macron<>\u1240;"
- "k''u<>\u1241;"
- "k''i<>\u1242;"
- "k''a<>\u1243;"
- "k''e<>\u1244;"
- "k''o<>\u1246;"
- "k''wi$macron<>\u124D;"
- "k''we$macron<>\u1248;"
- "k''wi<>\u124A;"
- "k''wa<>\u124B;"
- "k''we<>\u124C;"
-
- "khi$macron<>\u1255;"
- "khe$macron<>\u1250;"
- "khu<>\u1251;"
- "khi<>\u1252;"
- "kha<>\u1253;"
- "khe<>\u1254;"
- "kho<>\u1256;"
- "khwi$macron<>\u125D;"
- "khwe$macron<>\u1258;"
- "khwi<>\u125A;"
- "khwa<>\u125B;"
- "khwe<>\u125C;"
-
- "bi$macron<>\u1265;"
- "be$macron<>\u1260;"
- "bu<>\u1261;"
- "bi<>\u1262;"
- "ba<>\u1263;"
- "be<>\u1264;"
- "bo<>\u1266;"
- "bwa<>\u1267;"
-
- "vi$macron<>\u126D;"
- "ve$macron<>\u1268;"
- "vu<>\u1269;"
- "vi<>\u126A;"
- "va<>\u126B;"
- "ve<>\u126C;"
- "vo<>\u126E;"
- "vwa<>\u126F;"
-
- "ti$macron<>\u1275;"
- "te$macron<>\u1270;"
- "tu<>\u1271;"
- "ti<>\u1272;"
- "ta<>\u1273;"
- "te<>\u1274;"
- "to<>\u1276;"
- "twa<>\u1277;"
-
- "chi$macron<>\u127D;"
- "che$macron<>\u1278;"
- "chu<>\u1279;"
- "chi<>\u127A;"
- "cha<>\u127B;"
- "che<>\u127C;"
- "cho<>\u127E;"
- "chwa<>\u127F;"
-
- "ni$macron<>\u1295;"
- "ne$macron<>\u1290;"
- "nu<>\u1291;"
- "ni<>\u1292;"
- "na<>\u1293;"
- "ne<>\u1294;"
- "no<>\u1296;"
- "nwa<>\u1297;"
-
- "nyi$macron<>\u129D;"
- "nye$macron<>\u1298;"
- "nyu<>\u1299;"
- "nyi<>\u129A;"
- "nya<>\u129B;"
- "nye<>\u129C;"
- "nyo<>\u129E;"
- "nywa<>\u129F;"
-
- "ki$macron<>\u12AD;"
- "ke$macron<>\u12A8;"
- "ku<>\u12A9;"
- "ki<>\u12AA;"
- "ka<>\u12AB;"
- "ke<>\u12AC;"
- "ko<>\u12AE;"
- "kwi$macron<>\u12B5;"
- "kwe$macron<>\u12B0;"
- "kwi<>\u12B2;"
- "kwa<>\u12B3;"
- "kwe<>\u12B4;"
-
- "wi$macron<>\u12CD;"
- "we$macron<>\u12C8;"
- "wu<>\u12C9;"
- "wi<>\u12CA;"
- "wa<>\u12CB;"
- "we<>\u12CC;"
- "wo<>\u12CE;"
-
- "zi$macron<>\u12DD;"
- "ze$macron<>\u12D8;"
- "zu<>\u12D9;"
- "zi<>\u12DA;"
- "za<>\u12DB;"
- "ze<>\u12DC;"
- "zo<>\u12DE;"
- "zwa<>\u12DF;"
-
- "zhi$macron<>\u12E5;"
- "zhe$macron<>\u12E0;"
- "zhu<>\u12E1;"
- "zhi<>\u12E2;"
- "zha<>\u12E3;"
- "zhe<>\u12E4;"
- "zho<>\u12E6;"
- "zhwa<>\u12E7;"
-
- "yi$macron<>\u12ED;"
- "ye$macron<>\u12E8;"
- "yu<>\u12E9;"
- "yi<>\u12EA;"
- "ya<>\u12EB;"
- "ye<>\u12EC;"
- "yo<>\u12EE;"
-
- "ddi$macron<>\u12FD;"
- "dde$macron<>\u12F8;"
- "ddu<>\u12F9;"
- "ddi<>\u12FA;"
- "dda<>\u12FB;"
- "dde<>\u12FC;"
- "ddo<>\u12FE;"
- "ddwa<>\u12FF;"
-
- "di$macron<>\u12F5;"
- "de$macron<>\u12F0;"
- "du<>\u12F1;"
- "di<>\u12F2;"
- "da<>\u12F3;"
- "de<>\u12F4;"
- "do<>\u12F6;"
- "dwa<>\u12F7;"
-
- "ji$macron<>\u1305;"
- "je$macron<>\u1300;"
- "ju<>\u1301;"
- "ji<>\u1302;"
- "ja<>\u1303;"
- "je<>\u1304;"
- "jo<>\u1306;"
- "jwa<>\u1307;"
-
- "ggi$macron<>\u131D;"
- "gge$macron<>\u1318;"
- "ggu<>\u1319;"
- "ggi<>\u131A;"
- "gga<>\u131B;"
- "gge<>\u131C;"
- "ggo<>\u131E;"
- "ggwa<>\u131F;"
-
- "gi$macron<>\u130D;"
- "ge$macron<>\u1308;"
- "gu<>\u1309;"
- "gi<>\u130A;"
- "ga<>\u130B;"
- "ge<>\u130C;"
- "go<>\u130E;"
- "gwi$macron<>\u1315;"
- "gwe$macron<>\u1310;"
- "gwi<>\u1312;"
- "gwa<>\u1313;"
- "gwe<>\u1314;"
-
- "t''i$macron<>\u1325;"
- "t''e$macron<>\u1320;"
- "t''u<>\u1321;"
- "t''i<>\u1322;"
- "t''a<>\u1323;"
- "t''e<>\u1324;"
- "t''o<>\u1326;"
- "t''wa<>\u1327;"
-
- "ch''i$macron<>\u132D;"
- "ch''e$macron<>\u1328;"
- "ch''u<>\u1329;"
- "ch''i<>\u132A;"
- "ch''a<>\u132B;"
- "ch''e<>\u132C;"
- "ch''o<>\u132E;"
- "ch''wa<>\u132F;"
-
- "p''i$macron<>\u1335;"
- "p''e$macron<>\u1330;"
- "p''u<>\u1331;"
- "p''i<>\u1332;"
- "p''a<>\u1333;"
- "p''e<>\u1334;"
- "p''o<>\u1336;"
- "p''wa<>\u1337;"
-
- "ts''i$macron<>\u133D;"
- "ts''e$macron<>\u1338;"
- "ts''u<>\u1339;"
- "ts''i<>\u133A;"
- "ts''a<>\u133B;"
- "ts''e<>\u133C;"
- "ts''o<>\u133E;"
- "ts''wa<>\u133F;"
-
- "ts''i$macron<\u1345;"
- "ts''e$macron<\u1340;"
- "ts''u<\u1341;"
- "ts''i<\u1342;"
- "ts''a<\u1343;"
- "ts''e<\u1344;"
- "ts''o<\u1346;"
-
- "fi$macron<>\u134D;"
- "fe$macron<>\u1348;"
- "fu<>\u1349;"
- "fi<>\u134A;"
- "fa<>\u134B;"
- "fe<>\u134C;"
- "fo<>\u134E;"
- "fwa<>\u134F;"
-
- "pi$macron<>\u1355;"
- "pe$macron<>\u1350;"
- "pu<>\u1351;"
- "pi<>\u1352;"
- "pa<>\u1353;"
- "pe<>\u1354;"
- "po<>\u1356;"
- "pwa<>\u1357;"
-
- "rya<>\u1358;"
- "mya<>\u1359;"
- "fya<>\u135A;"
-
- "hi$macron<>\u1205;"
- "ha<>\u1200;"
- "hu<>\u1201;"
- "hi<>\u1202;"
- "ha<\u1203;"
- "he<>\u1204;"
- "ho<>\u1206;"
-
- "hi$macron<\u1215;"
- "ha<\u1210;"
- "hu<\u1211;"
- "hi<\u1212;"
- "ha<\u1213;"
- "he<\u1214;"
- "ho<\u1216;"
- "hwa<>\u1217;"
-
- "hi$macron<\u1285;"
- "ha<\u1280;"
- "hu<\u1281;"
- "hi<\u1282;"
- "ha<\u1283;"
- "he<\u1284;"
- "ho<\u1286;"
- "hwi$macron<>\u128D;"
- "hwe$macron<>\u1288;"
- "hwi<>\u128A;"
- "hwa<\u128B;"
- "hwe<>\u128C;"
-
- "hi$macron<\u12BD;"
- "he$macron<\u12B8;"
- "hu<\u12B9;"
- "hi<\u12BA;"
- "ha<\u12BB;"
- "he<\u12BC;"
- "ho<\u12BE;"
- "hwa<\u12BF;"
- "hwi$macron<\u12C5;"
- "hwe$macron<\u12C0;"
- "hwi<\u12C2;"
- "hwa<\u12C3;"
- "hwe<\u12C4;"
-
- "i$macron<>\u12A5;"
- "a<>\u12A0;"
- "u<>\u12A1;"
- "i<>\u12A2;"
- "a<\u12A3;"
- "e<>\u12A4;"
- "o<>\u12A6;"
-
- "i$macron<\u12D5;"
- "a<\u12D0;"
- "u<\u12D1;"
- "i<\u12D2;"
- "a<\u12D3;"
- "e<\u12D4;"
- "o<\u12D6;"
-
- "' '<>\u1361;"
- "'.'<>\u1362;"
- "','<>\u1363;"
- "';'<>\u1364;"
- "':'<>\u1365;"
- "':'<\u1366;"
- "'?'<>\u1367;"
- "\u00B6<>\u1368;"
-
- "1<>\u1369;"
- "2<>\u136A;"
- "3<>\u136B;"
- "4<>\u136C;"
- "5<>\u136D;"
- "6<>\u136E;"
- "7<>\u136F;"
- "8<>\u1370;"
- "9<>\u1371;"
-
- "10<\u1372;"
- "20<\u1373;"
- "30<\u1374;"
- "40<\u1375;"
- "50<\u1376;"
- "60<\u1377;"
- "70<\u1378;"
- "80<\u1379;"
- "90<\u137A;"
- "100<\u137B;"
- "10000<\u137C;"
-
- ":: NFC (NFD) ;"
- }
-}
Deleted: trunk/icu/translit_Latin_Georgian.txt
===================================================================
--- trunk/icu/translit_Latin_Georgian.txt 2009-05-14 07:42:28 UTC (rev 2411)
+++ trunk/icu/translit_Latin_Georgian.txt 2009-05-14 19:46:39 UTC (rev 2412)
@@ -1,137 +0,0 @@
-//--------------------------------------------------------------------
-// Copyright 2001, CrossWire Bible Society (http://www.crosswire.org)
-// Use freely.
-//--------------------------------------------------------------------
-// Based upon UNGEGN recommendations from
-// http://www.eki.ee/wgrs/rom2_ka.pdf
-//--------------------------------------------------------------------
-
-// Latin-Georgian
-
-translit_Latin_Georgian {
- Rule {
- ":: NFD (NFC) ;"
-
- ":: [:LATIN:] lower();"
-
- //titlecase digraphs
- "Ch\'<\u10B9}[:LowercaseLetter:];"
- "Ts\'<\u10BA}[:LowercaseLetter:];"
-
- "Zh<\u10AF}[:LowercaseLetter:];"
- "Gh<\u10B6}[:LowercaseLetter:];"
- "Sh<\u10B8}[:LowercaseLetter:];"
- "Dz<\u10BB}[:LowercaseLetter:];"
- "Ts<\u10BC}[:LowercaseLetter:];"
- "Ch<\u10BD}[:LowercaseLetter:];"
- "Kh<\u10BE}[:LowercaseLetter:];"
-
- //non-UNGEGN
- "Ey<\u10C1}[:Ll:];"
- "Ow<\u10C5}[:Ll:];"
-
- //uppercase digraphs
- "CH\'<\u10B9;"
- "TS\'<\u10BA;"
-
- "T\'<\u10A7;"
- "ZH<\u10AF;"
- "P\'<\u10B4;"
- "K\'<\u10B5;"
- "GH<\u10B6;"
- "SH<\u10B8;"
- "DZ<\u10BB;"
- "TS<\u10BC;"
- "CH<\u10BD;"
- "KH<\u10BE;"
-
- //non-UNGEGN
- "EY<\u10C1;"
- "Q\'<\u10C4;"
- "OW<\u10C5;"
-
- "A<\u10A0;"
- "B<\u10A1;"
- "G<\u10A2;"
- "D<\u10A3;"
- "E<\u10A4;"
- "V<\u10A5;"
- "Z<\u10A6;"
- "I<\u10A8;"
- "K<\u10A9;"
- "L<\u10AA;"
- "M<\u10AB;"
- "N<\u10AC;"
- "O<\u10AD;"
- "P<\u10AE;"
- "R<\u10B0;"
- "S<\u10B1;"
- "T<\u10B2;"
- "U<\u10B3;"
- "Q<\u10B7;"
- "J<\u10BF;"
- "H<\u10C0;"
- "Y<\u10C2;"
- "W<\u10C3;"
-
- //lowercase digraphs
- "ch\'<>\u10E9;"
- "ts\'<>\u10EA;"
-
- "t\'<>\u10D7;"
- "zh<>\u10DF;"
- "p\'<>\u10E4;"
- "k\'<>\u10E5;"
- "gh<>\u10E6;"
- "sh<>\u10E8;"
- "dz<>\u10EB;"
- "ts<>\u10EC;"
- "ch<>\u10ED;"
- "kh<>\u10EE;"
-
- //non-UNGEGN
- "ey<>\u10F1;"
- "q\'<>\u10F4;"
- "ow<>\u10F5;"
-
- "a<>\u10D0;"
- "b<>\u10D1;"
- "g<>\u10D2;"
- "d<>\u10D3;"
- "e<>\u10D4;"
- "v<>\u10D5;"
- "z<>\u10D6;"
- "i<>\u10D8;"
- "k<>\u10D9;"
- "l<>\u10DA;"
- "m<>\u10DB;"
- "n<>\u10DC;"
- "o<>\u10DD;"
- "p<>\u10DE;"
- "r<>\u10E0;"
- "s<>\u10E1;"
- "t<>\u10E2;"
- "u<>\u10E3;"
- "q<>\u10E7;"
- "j<>\u10EF;"
- "h<>\u10F0;"
-
- //non-UNGEGN
- "y<>\u10F2;"
- "w<>\u10F3;"
- "f<>\u10F6;"
-
- //paragraph
- "\u00B6<>\u10FB;"
-
- //completeness mappings for latin
- "c>\u10D9;"
- "x>\u10EE;"
-
- //remove untransliterated
- "<[:GEORGIAN:];"
- "[:LATIN:]>;"
-
- ":: NFC (NFD) ;"
- }
-}
Deleted: trunk/icu/translit_Latin_Hebrew.txt
===================================================================
--- trunk/icu/translit_Latin_Hebrew.txt 2009-05-14 07:42:28 UTC (rev 2411)
+++ trunk/icu/translit_Latin_Hebrew.txt 2009-05-14 19:46:39 UTC (rev 2412)
@@ -1,223 +0,0 @@
-//--------------------------------------------------------------------
-// Copyright (c) 1999-2000, International Business Machines
-// Corporation and others. All Rights Reserved.
-//--------------------------------------------------------------------
-// THIS IS A MACHINE-GENERATED FILE
-// Tool: src\com\ibm\tools\translit\dumpICUrules.bat
-// Source: src\com\ibm\text\resources/TransliterationRule_Latin_Hebrew.java
-// Date: Wed Jul 5 16:11:18 2000
-//--------------------------------------------------------------------
-
-// Latin-Hebrew
-
-translit_Latin_Hebrew {
- Rule {
- ":: NFD (NFC) ;"
-
- // 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>$ZAYIN;"
-
- //Delete any Syriac we didn't recognize
- "<$hebrew;"
-
- ":: NFC (NFD) ;"
- }
-}
Deleted: trunk/icu/translit_Latin_Syriac.txt
===================================================================
--- trunk/icu/translit_Latin_Syriac.txt 2009-05-14 07:42:28 UTC (rev 2411)
+++ trunk/icu/translit_Latin_Syriac.txt 2009-05-14 19:46:39 UTC (rev 2412)
@@ -1,169 +0,0 @@
-// Latin-Syriac
-
-translit_Latin_Syriac {
- Rule {
- ":: NFD (NFC) ;"
-
- // Variable names, derived from the Unicode names.
- "$ALEF=\u0710;"
- "$ALEF_SUPERSCRIPT=\u0711;"
- "$BET=\u0712;"
- "$GIMEL=\u0713;"
- "$GIMEL_GARSHUNI=\u0714;"
- "$DALET=\u0715;"
- "$DALET_DOTLESS=\u0716;"
- "$HE=\u0717;"
- "$VAV=\u0718;"
- "$ZAYIN=\u0719;"
- "$HET=\u071A;"
- "$TET=\u071B;"
- "$TET_GARSHUNI=\u071C;"
- "$YOD=\u071D;"
- "$YOD_HE=\u071E;"
- "$KAF=\u071F;"
- "$LAMED=\u0720;"
- "$MEM=\u0721;"
- "$NUN=\u0722;"
- "$SAMEKH=\u0723;"
- "$FINAL_SAMEKH=\u0724;"
- "$AYIN=\u0725;"
- "$PE=\u0726;"
- "$PE_REVERSED=\u0727;"
- "$TSADI=\u0728;"
- "$QOF=\u0729;"
- "$RESH=\u072A;"
- "$SHIN=\u072B;"
- "$TAV=\u072C;"
-
- "$PARAGRAPH=\u0700;"
-
- "$letter=[a-zA-Z];"
- "$softvowel=[eiyEIY];"
- "$vowellike=[$ALEF $AYIN $YOD $VAV $ALEF_SUPERSCRIPT];"
-
- // [Why is this a special case? -liu]
- "k''h <> $KAF $HE ;"
-
- // Mark non-final forms in final position as x~ -liu
- "s < $SAMEKH } [[:SYRIAC:]&[:LETTER:]] ;"
- "s'~' <> $SAMEKH ;"
-
- // Mark final forms in non-final position as x^ -liu
- "s < $FINAL_SAMEKH;"
-
- // Main rules
- "a<>$ALEF;"
- "A>$ALEF;"
- "a<$ALEF_SUPERSCRIPT;"
-
- "b<>$BET;"
- "B>$BET;"
-
- "c}$softvowel>$SAMEKH;"
- "C}$softvowel>$SAMEKH;"
- "c>$KAF;"
- "C>$KAF;"
-
- "d<>$DALET;"
- "D>$DALET;"
- "d<$DALET_DOTLESS;"
-
- "e<>$AYIN;"
- "E>$AYIN;"
-
- "f>$PE;"
- "F>$PE;"
-
- "g<>$GIMEL;"
- "G>$GIMEL;"
- "g<$GIMEL_GARSHUNI;"
-
- "h<>$HE;"
- "H>$HE;"
-
- "i>$YOD;"
- "I>$YOD;"
- "ih<$YOD_HE;"
-
- "j>$DALET$SHIN;"
- "J>$DALET$SHIN;"
-
- "kh<>$HET;"
- "kH>$HET;"
- "Kh>$HET;"
- "KH>$HET;"
- "k<>$KAF;"
- "K>$KAF;"
-
- "l<>$LAMED;"
- "L>$LAMED;"
-
- "m<>$MEM;"
- "M>$MEM;"
-
- "n<>$NUN;"
- "N>$NUN;"
-
- "o>$VAV;"
- "O>$VAV;"
-
- "p<>$PE;"
- "P>$PE;"
- "p<$PE_REVERSED;"
-
- "q<>$QOF;"
- "Q>$QOF;"
-
- "r<>$RESH;"
- "R>$RESH;"
-
- "sh<>$SHIN;"
- "sH>$SHIN;"
- "Sh>$SHIN;"
- "SH>$SHIN;"
-
- "th<>$TAV;"
- "tH>$TAV;"
- "Th>$TAV;"
- "TH>$TAV;"
- "tS>$TSADI;"
- "ts<>$TSADI;"
- "Ts>$TSADI;"
- "TS>$TSADI;"
- "t''<$TET}[$HE $SAMEKH $SHIN];"
- "t<>$TET;"
- "T>$TET;"
- "t<$TET_GARSHUNI;"
-
- "s}$letter>$SAMEKH;"
- "s>$FINAL_SAMEKH;"
- "S}$letter>$SAMEKH;"
- "S>$FINAL_SAMEKH;"
-
- "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;"
-
- "\u00B6<>$PARAGRAPH;"
-
- //Delete any Syriac we didn't recognize
- "<[:SYRIAC:];"
-
- ":: NFC (NFD) ;"
- }
-}
Deleted: trunk/icu/translit_Latin_Thai.txt
===================================================================
--- trunk/icu/translit_Latin_Thai.txt 2009-05-14 07:42:28 UTC (rev 2411)
+++ trunk/icu/translit_Latin_Thai.txt 2009-05-14 19:46:39 UTC (rev 2412)
@@ -1,162 +0,0 @@
-//--------------------------------------------------------------------
-// Copyright 2001, CrossWire Bible Society (http://www.crosswire.org)
-// Use freely.
-//--------------------------------------------------------------------
-// Based upon UNGEGN recommendations from
-// http://www.eki.ee/wgrs/rom1_th.pdf
-//--------------------------------------------------------------------
-
-// Latin-Thai
-
-translit_Latin_Thai {
- Rule {
- ":: NFD (NFC) ;"
-
- ":: [[:LATIN:]-[B]] lower();"
-
- //completeness mappings
- "c}[^h]>|k;"
- "g>|ng;"
- "q>|k;"
- "v>|f;"
- "x>|kh;"
- "z>|s;"
- "j>|i;"
-
- // latin-thai
- "\u2026<>\u0E2F;"
- "\u00B7<>\u0E4F;"
-
- "B<>\u0E3F;"
-
- "|$1 a $2<([[:THAI:]&[:L:]])\u0E31([[:THAI:]&[:L:]]);"
- "|$1 a $2<([[:THAI:]&[:L:]])\u0E23\u0E23([[:THAI:]&[:L:]]);"
- "|$1 e<\u0E40([[:THAI:]&[:L:]])\u0E30;"
- "|$1 e $2<\u0E40([[:THAI:]&[:L:]])\u0E47([[:THAI:]&[:L:]]);"
- "|$1 ae<\u0E41([[:THAI:]&[:L:]])\u0E30;"
- "|$1 ae $2<\u0E41([[:THAI:]&[:L:]])\u0E47([[:THAI:]&[:L:]]);"
- "|$1 o<\u0E42([[:THAI:]&[:L:]])\u0E30;"
- "|$1 o<\u0E40([[:THAI:]&[:L:]])\u0E32\u0E30;"
- "|$1 oe<\u0E40([[:THAI:]&[:L:]])\u0E3D\u0E30;"
- "|$1 oe $2<\u0E40([[:THAI:]&[:L:]])\u0E34([[:THAI:]&[:L:]]);"
- "|$1 oe<\u0E40([[:THAI:]&[:L:]])\u0E2D;"
- "|$1 ia<\u0E40([[:THAI:]&[:L:]])\u0E35\u0E22\u0E30;"
- "|$1 ia<\u0E40([[:THAI:]&[:L:]])\u0E35\u0E22;"
- "|$1 uea<\u0E40([[:THAI:]&[:L:]])\u0E37\u0E2D\u0E30;"
- "|$1 uea<\u0E40([[:THAI:]&[:L:]])\u0E37\u0E2D;"
- "|$1 ua<([[:THAI:]&[:L:]])\u0E31\u0E27\u0E30;"
- "|$1 ua<([[:THAI:]&[:L:]])\u0E31\u0E27;"
- "|$1 ua $2<([[:THAI:]&[:L:]])\u0E27([[:THAI:]&[:L:]]);"
- "|$1 ai<([[:THAI:]&[:L:]])\u0E31\u0E22;"
- "|$1 ai<\u0E44([[:THAI:]&[:L:]])\u0E22;"
- "|$1 ai<([[:THAI:]&[:L:]])\u0E32\u0E22;"
- "|$1 ao<\u0E40([[:THAI:]&[:L:]])\u0E32;"
- "|$1 ao<([[:THAI:]&[:L:]])\u0E32\u0E27;"
- "|$1 ui<([[:THAI:]&[:L:]])\u0E38\u0E22;"
- "|$1 oi<\u0E42([[:THAI:]&[:L:]])\u0E22;"
- "|$1 oi<([[:THAI:]&[:L:]])\u0E2D\u0E22;"
- "|$1 oei<\u0E40([[:THAI:]&[:L:]])\u0E22;"
- "|$1 ueai<\u0E40([[:THAI:]&[:L:]])\u0E37\u0E2D\u0E22;"
- "|$1 uai<([[:THAI:]&[:L:]])\u0E27\u0E22;"
- "|$1 io<([[:THAI:]&[:L:]])\u0E34\u0E27;"
- "|$1 eo<\u0E40([[:THAI:]&[:L:]])\u0E47\u0E27;"
- "|$1 eo<\u0E40([[:THAI:]&[:L:]])\u0E27;"
- "|$1 aeo<\u0E41([[:THAI:]&[:L:]])\u0E47\u0E27;"
- "|$1 aeo<\u0E41([[:THAI:]&[:L:]])\u0E27;"
- "|$1 iao<\u0E40([[:THAI:]&[:L:]])\u0E35\u0E22\u0E27;"
-
- "|$1 o<([[:THAI:]&[:L:]])\u0E2D;"
- "|$1 a<([[:THAI:]&[:L:]])\u0E30;"
- "|$1 a<([[:THAI:]&[:L:]])\u0E32;"
- "|$1 an<([[:THAI:]&[:L:]])\u0E23\u0E23;"
- "|$1 am<([[:THAI:]&[:L:]])\u0E33;"
- "|$1 i<([[:THAI:]&[:L:]])\u0E34;"
- "|$1 i<([[:THAI:]&[:L:]])\u0E35;"
- "|$1 ue<([[:THAI:]&[:L:]])\u0E36;"
- "|$1 ue<([[:THAI:]&[:L:]])\u0E37;"
- "|$1 u<([[:THAI:]&[:L:]])\u0E38;"
- "|$1 u<([[:THAI:]&[:L:]])\u0E39;"
- "|$1 e<\u0E40([[:THAI:]&[:L:]]);"
- "|$1 ae<\u0E41([[:THAI:]&[:L:]]);"
- "|$1 o<\u0E42([[:THAI:]&[:L:]]);"
- "|$1 ai<\u0E43([[:THAI:]&[:L:]]);"
- "|$1 ai<\u0E44([[:THAI:]&[:L:]]);"
-
- "0<>\u0E50;"
- "1<>\u0E51;"
- "2<>\u0E52;"
- "3<>\u0E53;"
- "4<>\u0E54;"
- "5<>\u0E55;"
- "6<>\u0E56;"
- "7<>\u0E57;"
- "8<>\u0E58;"
- "9<>\u0E59;"
-
- // this doesn't work; don't know why
- // "| $1 o < ([[:THAI:]&[:L:]]);"
-
- "kh<>\u0E02;"
- "kh<\u0E03;"
- "kh<\u0E04;"
- "kh<\u0E05;"
- "kh<\u0E06;"
- "k<>\u0E01;"
- "ng<>\u0E07;"
- "ch<>\u0E08;"
- "ch<\u0E09;"
- "ch<\u0E0A;"
- "s<>\u0E0B;"
- "ch<\u0E0C;"
- "y<>\u0E0D;"
- "d<>\u0E0E;"
- "s<\u0E17\u0E23;"
- "th<>\u0E10;"
- "th<\u0E11;"
- "th<\u0E12;"
- "th<\u0E16;"
- "th<\u0E17;"
- "th<\u0E18;"
- "t<>\u0E0F;"
- "n<>\u0E13;"
- "d<\u0E14;"
- "t<\u0E15;"
- "n<\u0E19;"
- "b<>\u0E1A;"
- "ph<>\u0E1C;"
- "ph<\u0E1E;"
- "ph<\u0E20;"
- "p<>\u0E1B;"
- "f<>\u0E1D;"
- "f<\u0E1F;"
- "m<>\u0E21;"
- "y<\u0E22;"
- "rue<>\u0E24\u0E32;"
- "ri<>\u0E24;"
- "r<>\u0E23;"
- "lue<\u0E26\u0E32;"
- "lue<>\u0E26;"
- "l<>\u0E25;"
- "w<>\u0E27;"
- "s<\u0E28;"
- "s<\u0E29;"
- "s<\u0E2A;"
- "h<>\u0E2B;"
- "l<\u0E2C;"
- "o<\u0E2D;"
- "h<\u0E2E;"
-
- //vowels
- "a>\u0E30;"
- "([:LATIN:])e>|\u0E40 $1;"
- "i>\u0E34;"
- "([:^L:])o>|$1 \u0E2D;"
- "u>\u0E38;"
-
- //remove untransliterated
- "<[:THAI:];"
- "[:LATIN:]>;"
-
- ":: NFC (NFD) ;"
- }
-}
Modified: trunk/icu/translit_swordindex.txt
===================================================================
--- trunk/icu/translit_swordindex.txt 2009-05-14 07:42:28 UTC (rev 2411)
+++ trunk/icu/translit_swordindex.txt 2009-05-14 19:46:39 UTC (rev 2412)
@@ -58,19 +58,6 @@
// Transliterator.getInstance(). The returned Transliterator object
// then has its ID changed to <id> and is returned.
-// ICU < 2.0 additions
-{ "Latin-Hebrew", "file", "translit_Latin_Hebrew", "FORWARD" },
-{ "Hebrew-Latin", "file", "translit_Latin_Hebrew", "REVERSE" },
-{ "Latin-Arabic", "file", "translit_Latin_Arabic", "FORWARD" },
-{ "Arabic-Latin", "file", "translit_Latin_Arabic", "REVERSE" },
-
-// xtradata additions
-//{ "Han-Pinyin", "file", "translit_Han_Pinyin", "FORWARD" },
-//{ "Kanji-English", "file", "translit_Kanji_English", "FORWARD" },
-//{ "Kanji-OnRomaji", "file", "translit_Kanji_OnRomaji", "FORWARD" },
-//{ "HTMLEntities-Unicode", "file", "translit_HTMLEnt_Unicode", "FORWARD" },
-//{ "Unicode-HTMLEntities", "file", "translit_HTMLEnt_Unicode", "REVERSE" },
-
// SWORD additions for academic Biblical transliteration schemes
{ "BGreek-Greek", "file", "translit_BGreek_Greek", "FORWARD" },
{ "Greek-BGreek", "file", "translit_BGreek_Greek", "REVERSE" },
@@ -80,24 +67,12 @@
{ "Hebrew-CCAT", "file", "translit_CCAT_Hebrew", "REVERSE" }
{ "CCAT-Syriac", "file", "translit_CCAT_Syriac", "FORWARD" },
{ "Syriac-CCAT", "file", "translit_CCAT_Syriac", "REVERSE" },
-//{ "Syriac-Hebrew", "alias", "Syriac-CCAT;CCAT-Hebrew", "" },
-//{ "Hebrew-Syriac", "alias", "Hebrew-CCAT;CCAT-Syriac", "" },
-{ "Latin-Syriac", "file", "translit_Latin_Syriac", "FORWARD" },
-{ "Syriac-Latin", "file", "translit_Latin_Syriac", "REVERSE" },
// SWORD additions for other languages
-{ "Latin-Thai", "file", "translit_Latin_Thai", "FORWARD" },
-{ "Thai-Latin", "file", "translit_Latin_Thai", "REVERSE" },
-{ "Latin-Georgian", "file", "translit_Latin_Georgian", "FORWARD" },
-{ "Georgian-Latin", "file", "translit_Latin_Georgian", "REVERSE" },
-{ "Latin-Armenian", "file", "translit_Latin_Armenian", "FORWARD" },
-{ "Armenian-Latin", "file", "translit_Latin_Armenian", "REVERSE" },
{ "Latin-Coptic", "file", "translit_Latin_Coptic", "FORWARD" },
{ "Coptic-Latin", "file", "translit_Latin_Coptic", "REVERSE" },
{ "Latin-Gothic", "file", "translit_Latin_Gothic", "FORWARD" },
{ "Gothic-Latin", "file", "translit_Latin_Gothic", "REVERSE" },
-{ "Latin-Ethiopic", "file", "translit_Latin_Ethiopic", "FORWARD" },
-{ "Ethiopic-Latin", "file", "translit_Latin_Ethiopic", "REVERSE" },
{ "Latin-Ugaritic", "file", "translit_Latin_Ugaritic", "FORWARD" },
{ "Ugaritic-Latin", "file", "translit_Latin_Ugaritic", "REVERSE" },
More information about the sword-cvs
mailing list