organicmaps/icu
13
Fork 0
mirror of https://github.com/unicode-org/icu.git synced 2025-04-13 08:53:20 +00:00
Code Issues 1 Projects Releases Wiki Activity Actions 3

Quote all special characters.

Browse source 
X-SVN-Rev: 1216
This commit is contained in:
Alan Liu 2000-04-22 00:04:39 +00:00
parent be940edb7b
commit 0460815e8c
10 changed files with 1773 additions and 1776 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

38
icu4j/src/com/ibm/icu/dev/test/translit/TransliteratorTest.java
View file

@ -5,8 +5,8 @@
*******************************************************************************
*
* $Source: /xsrl/Nsvn/icu/icu4j/src/com/ibm/icu/dev/test/translit/TransliteratorTest.java,v $
* $Date: 2000/04/19 16:37:38 $
* $Revision: 1.15 $
* $Date: 2000/04/22 00:04:39 $
* $Revision: 1.16 $
*
*****************************************************************************************
*/
@ -103,13 +103,13 @@ public class TransliteratorTest extends TestFmwk {
/* Test categories
*/
Transliterator t = new RuleBasedTransliterator("<ID>",
"dummy=\uE100;" +
"vowel=[aeiouAEIOU];" +
"lu=[:Lu:];" +
"{vowel} ({lu}) > !;" +
"{vowel} > &;" +
"(!) {lu} > ^;" +
"{lu} > *;" +
"$dummy=\uE100;" +
"$vowel=[aeiouAEIOU];" +
"$lu=[:Lu:];" +
"$vowel } $lu > '!';" +
"$vowel > '&';" +
"'!' { $lu > '^';" +
"$lu > '*';" +
"a>ERROR");
expect(t, "abcdefgABCDEFGU", "&bcd&fg!^**!^*&");
}
@ -118,7 +118,7 @@ public class TransliteratorTest extends TestFmwk {
* Test undefined variable.
*/
public void TestUndefinedVariable() {
String rule = "({initial}) a <> \u1161;";
String rule = "$initial } a <> \u1161;";
try {
Transliterator t = new RuleBasedTransliterator("<ID>", rule);
} catch (IllegalArgumentException e) {
@ -133,22 +133,22 @@ public class TransliteratorTest extends TestFmwk {
* Test empty context.
*/
public void TestEmptyContext() {
expect("() a () > b;", "xay a ", "xby b ");
expect(" { a } > b;", "xay a ", "xby b ");
}
/**
* Test inline set syntax and set variable syntax.
*/
public void TestInlineSet() {
expect("[:Ll:] (x) > y; [:Ll:] > z;", "aAbxq", "zAyzz");
expect("{ [:Ll:] } x > y; [:Ll:] > z;", "aAbxq", "zAyzz");
expect("a[0-9]b > qrs", "1a7b9", "1qrs9");
expect("digit = [0-9];" +
"alpha = [a-zA-Z];" +
"alphanumeric = [{digit}{alpha}];" + // ***
"special = [^{alphanumeric}];" + // ***
"{alphanumeric} > -;" +
"{special} > *;",
expect("$digit = [0-9];" +
"$alpha = [a-zA-Z];" +
"$alphanumeric = [$digit $alpha];" + // ***
"$special = [^$alphanumeric];" + // ***
"$alphanumeric > '-';" +
"$special > '*';",
"thx-1138", "---*----");
}
@ -419,7 +419,7 @@ public class TransliteratorTest extends TestFmwk {
// Array of 3n items
// Each item is <rules>, <input>, <expected output>
String[] DATA = {
"$([a-z]$) . $([0-9]$) > $2-$1",
"([a-z]) '.' ([0-9]) > $2 '-' $1",
"abc.123.xyz.456",
"ab1-c23.xy4-z56",
};

38
icu4j/src/com/ibm/test/translit/TransliteratorTest.java
View file

@ -5,8 +5,8 @@
*******************************************************************************
*
* $Source: /xsrl/Nsvn/icu/icu4j/src/com/ibm/test/translit/Attic/TransliteratorTest.java,v $
* $Date: 2000/04/19 16:37:38 $
* $Revision: 1.15 $
* $Date: 2000/04/22 00:04:39 $
* $Revision: 1.16 $
*
*****************************************************************************************
*/
@ -103,13 +103,13 @@ public class TransliteratorTest extends TestFmwk {
/* Test categories
*/
Transliterator t = new RuleBasedTransliterator("<ID>",
"dummy=\uE100;" +
"vowel=[aeiouAEIOU];" +
"lu=[:Lu:];" +
"{vowel} ({lu}) > !;" +
"{vowel} > &;" +
"(!) {lu} > ^;" +
"{lu} > *;" +
"$dummy=\uE100;" +
"$vowel=[aeiouAEIOU];" +
"$lu=[:Lu:];" +
"$vowel } $lu > '!';" +
"$vowel > '&';" +
"'!' { $lu > '^';" +
"$lu > '*';" +
"a>ERROR");
expect(t, "abcdefgABCDEFGU", "&bcd&fg!^**!^*&");
}
@ -118,7 +118,7 @@ public class TransliteratorTest extends TestFmwk {
* Test undefined variable.
*/
public void TestUndefinedVariable() {
String rule = "({initial}) a <> \u1161;";
String rule = "$initial } a <> \u1161;";
try {
Transliterator t = new RuleBasedTransliterator("<ID>", rule);
} catch (IllegalArgumentException e) {
@ -133,22 +133,22 @@ public class TransliteratorTest extends TestFmwk {
* Test empty context.
*/
public void TestEmptyContext() {
expect("() a () > b;", "xay a ", "xby b ");
expect(" { a } > b;", "xay a ", "xby b ");
}
/**
* Test inline set syntax and set variable syntax.
*/
public void TestInlineSet() {
expect("[:Ll:] (x) > y; [:Ll:] > z;", "aAbxq", "zAyzz");
expect("{ [:Ll:] } x > y; [:Ll:] > z;", "aAbxq", "zAyzz");
expect("a[0-9]b > qrs", "1a7b9", "1qrs9");
expect("digit = [0-9];" +
"alpha = [a-zA-Z];" +
"alphanumeric = [{digit}{alpha}];" + // ***
"special = [^{alphanumeric}];" + // ***
"{alphanumeric} > -;" +
"{special} > *;",
expect("$digit = [0-9];" +
"$alpha = [a-zA-Z];" +
"$alphanumeric = [$digit $alpha];" + // ***
"$special = [^$alphanumeric];" + // ***
"$alphanumeric > '-';" +
"$special > '*';",
"thx-1138", "---*----");
}
@ -419,7 +419,7 @@ public class TransliteratorTest extends TestFmwk {
// Array of 3n items
// Each item is <rules>, <input>, <expected output>
String[] DATA = {
"$([a-z]$) . $([0-9]$) > $2-$1",
"([a-z]) '.' ([0-9]) > $2 '-' $1",
"abc.123.xyz.456",
"ab1-c23.xy4-z56",
};

22
icu4j/src/com/ibm/text/resources/TransliterationRule_Kanji_English.java
View file

@ -5,8 +5,8 @@
*******************************************************************************
*
* $Source: /xsrl/Nsvn/icu/icu4j/src/com/ibm/text/resources/Attic/TransliterationRule_Kanji_English.java,v $
* $Date: 2000/03/10 04:07:30 $
* $Revision: 1.2 $
* $Date: 2000/04/22 00:04:25 $
* $Revision: 1.3 $
*
*****************************************************************************************
*/
@ -148,7 +148,7 @@ public class TransliterationRule_Kanji_English extends ListResourceBundle {
"\u4F38>'[extend]'",
"\u4F3A>'[serve]'",
"\u4F3C>'[resemble]'",
"\u4F3D>'[transcription of sanskrit gha in buddhist texts ('\u00ebm\u00e2\u00e6 \"samgha\"')]'",
"\u4F3D>'[transcription of sanskrit gha in buddhist texts ('\u00ebm\u00e2\u00e6' \"samgha\")]'",
"\u4F43>'[tenant farmer]'",
"\u4F46>'[only]'",
"\u4F47>'[wait]'",
@ -631,7 +631,7 @@ public class TransliterationRule_Kanji_English extends ListResourceBundle {
"\u53F7>'[mark]'",
"\u53F8>'[take charge of]'",
//"\u53F9>'[sigh]'",
"\u5401>'['interjection \"Alas!\"']'",
"\u5401>'[interjection \"Alas!\"]'",
"\u5403>'[eat]'",
"\u5404>'[each]'",
"\u5408>'[combine]'",
@ -659,7 +659,7 @@ public class TransliterationRule_Kanji_English extends ListResourceBundle {
"\u5439>'[blow]'",
"\u543B>'[kiss]'",
"\u543C>'[roar]'",
"\u543D>'['\"OM\"']'",
"\u543D>'[\"OM\"]'",
"\u543E>'[i]'",
"\u5440>'[particle used express surprise]'",
"\u5442>'[surname]'",
@ -1262,7 +1262,7 @@ public class TransliterationRule_Kanji_English extends ListResourceBundle {
"\u5C31>'[just]'",
"\u5C38>'[corpse]'",
"\u5C39>'[govern]'",
"\u5C3A>'['chinese measure approx. \"foot\"']'",
"\u5C3A>'[chinese measure approx. \"foot\"]'",
"\u5C3B>'[end of spine]'",
"\u5C3C>'[buddhist nun]'",
"\u5C3D>'[exhaust]'",
@ -2250,7 +2250,7 @@ public class TransliterationRule_Kanji_English extends ListResourceBundle {
"\u670D>'[clothes]'",
"\u670F>'[light of crescent moon]'",
"\u6714>'[first day of lunar month]'",
"\u6715>'['pronoun \"i\"']'",
"\u6715>'[pronoun \"i\"]'",
"\u6716>'[clear]'",
"\u6717>'[clear]'",
"\u671B>'[look at or forward]'",
@ -4651,7 +4651,7 @@ public class TransliterationRule_Kanji_English extends ListResourceBundle {
"\u85A4>'[allium bakeri]'",
"\u85A6>'[offer]'",
"\u85A8>'[death of prince]'",
"\u85A9>'['transliteration of\"sat\" of boddhisattva etc.']'",
"\u85A9>'[transliteration of \"sat\" of boddhisattva etc.]'",
"\u85AA>'[fuel]'",
"\u85AB>'[a medicinal herb]'",
"\u85AC>'[drugs]'",
@ -4854,7 +4854,7 @@ public class TransliterationRule_Kanji_English extends ListResourceBundle {
"\u889E>'[ceremonial dress worn by emperor]'",
"\u88A2>'[robe]'",
"\u88A4>'[longitude]'",
"\u88AB>'['passive indicator \"by\"']'",
"\u88AB>'[passive indicator \"by\"]'",
//"\u88AE>'[................................]'",
//"\u88B0>'[................................]'",
"\u88B1>'[piece of cloth used wrap bundles]'",
@ -5779,7 +5779,7 @@ public class TransliterationRule_Kanji_English extends ListResourceBundle {
//"\u9665>'[submerge]'",
"\u966A>'[accompany]'",
"\u966C>'[corner]'",
"\u9670>'['\"female\" principle']'",
"\u9670>'[\"female\" principle]'",
"\u9672>'[frontier]'",
"\u9673>'[exhibit]'",
"\u9675>'[hill]'",
@ -5787,7 +5787,7 @@ public class TransliterationRule_Kanji_English extends ListResourceBundle {
"\u9677>'[submerge]'",
"\u9678>'[land]'",
"\u967A>'[narrow pass]'",
"\u967D>'['\"male\" principle']'",
"\u967D>'[\"male\" principle]'",
"\u9685>'[corner]'",
"\u9686>'[prosperous]'",
"\u9688>'[cove]'",

44
icu4j/src/com/ibm/text/resources/TransliterationRule_KeyboardEscape_Latin1.java
View file

@ -5,8 +5,8 @@
*******************************************************************************
*
* $Source: /xsrl/Nsvn/icu/icu4j/src/com/ibm/text/resources/Attic/TransliterationRule_KeyboardEscape_Latin1.java,v $
* $Date: 2000/04/21 21:17:08 $
* $Revision: 1.3 $
* $Date: 2000/04/22 00:04:25 $
* $Revision: 1.4 $
*
*****************************************************************************************
*/
@ -22,15 +22,15 @@ public class TransliterationRule_KeyboardEscape_Latin1 extends ListResourceBundl
return new Object[][] {
{ "Rule",
"$esc='';"
+ "$grave=`;"
+ "$grave='`';"
+ "$acute='';"
+ "$hat=^;"
+ "$tilde=~;"
+ "$umlaut=:;"
+ "$ring=.;"
+ "$cedilla=,;"
+ "$slash=/;"
+ "$super=^;"
+ "$hat='^';"
+ "$tilde='~';"
+ "$umlaut=':';"
+ "$ring='.';"
+ "$cedilla=',';"
+ "$slash='/';"
+ "$super='^';"
// Make keyboard entry of {esc} possible
// and of backslash
@ -45,17 +45,17 @@ public class TransliterationRule_KeyboardEscape_Latin1 extends ListResourceBundl
+ "div$esc>\u00F7;"
+ "\\ $esc>\u00A0;" // non-breaking space
+ "!$esc>\u00A1;" // inverted exclamation
+ "c/$esc>\u00A2;" // cent sign
+ "'!'$esc>\u00A1;" // inverted exclamation
+ "c'/'$esc>\u00A2;" // cent sign
+ "lb$esc>\u00A3;" // pound sign
+ "'|'$esc>\u00A6;" // broken vertical bar
+ ":$esc>\u00A8;" // umlaut
+ "':'$esc>\u00A8;" // umlaut
+ "$super a$esc>\u00AA;" // feminine ordinal
+ "'<<'$esc>\u00AB;"
+ "r$esc>\u00AE;"
+ "--$esc>\u00AF;"
+ "-$esc>\u00AD;"
+ "+-$esc>\u00B1;"
+ "'--'$esc>\u00AF;"
+ "'-'$esc>\u00AD;"
+ "'+-'$esc>\u00B1;"
+ "$super 2$esc>\u00B2;"
+ "$super 3$esc>\u00B3;"
+ "$acute$esc>\u00B4;"
@ -66,10 +66,10 @@ public class TransliterationRule_KeyboardEscape_Latin1 extends ListResourceBundl
+ "$super 1$esc>\u00B9;"
+ "$super o$esc>\u00BA;" // masculine ordinal
+ "'>>'$esc>\u00BB;"
+ "1/4$esc>\u00BC;"
+ "1/2$esc>\u00BD;"
+ "3/4$esc>\u00BE;"
+ "?$esc>\u00BF;"
+ "'1/4'$esc>\u00BC;"
+ "'1/2'$esc>\u00BD;"
+ "'3/4'$esc>\u00BE;"
+ "'?'$esc>\u00BF;"
+ "A$grave$esc>\u00C0;"
+ "A$acute$esc>\u00C1;"
+ "A$hat$esc>\u00C2;"
@ -86,7 +86,7 @@ public class TransliterationRule_KeyboardEscape_Latin1 extends ListResourceBundl
+ "I$acute$esc>\u00CD;"
+ "I$hat$esc>\u00CE;"
+ "I$umlaut$esc>\u00CF;"
+ "D-$esc>\u00D0;"
+ "'D-'$esc>\u00D0;"
+ "N$tilde$esc>\u00D1;"
+ "O$grave$esc>\u00D2;"
+ "O$acute$esc>\u00D3;"
@ -118,7 +118,7 @@ public class TransliterationRule_KeyboardEscape_Latin1 extends ListResourceBundl
+ "i$acute$esc>\u00ED;"
+ "i$hat$esc>\u00EE;"
+ "i$umlaut$esc>\u00EF;"
+ "d-$esc>\u00F0;"
+ "'d-'$esc>\u00F0;"
+ "n$tilde$esc>\u00F1;"
+ "o$grave$esc>\u00F2;"
+ "o$acute$esc>\u00F3;"

42
icu4j/src/com/ibm/text/resources/TransliterationRule_Latin_Arabic.java
View file

@ -5,8 +5,8 @@
*******************************************************************************
*
* $Source: /xsrl/Nsvn/icu/icu4j/src/com/ibm/text/resources/Attic/TransliterationRule_Latin_Arabic.java,v $
* $Date: 2000/04/21 21:17:08 $
* $Revision: 1.3 $
* $Date: 2000/04/22 00:04:25 $
* $Revision: 1.4 $
*
*****************************************************************************************
*/
@ -140,26 +140,26 @@ public class TransliterationRule_Latin_Arabic extends ListResourceBundle {
"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
"'%'>\u066A;"+ // Arabic %
"'.'>\u066B;"+ // Arabic decimal separator
"','>\u066C;"+ // Arabic thousands separator
"'*'>\u066D;"+ // Arabic five-pointed star
"`0>0;"+ // Escaped forms of the above
"`1>1;"+
"`2>2;"+
"`3>3;"+
"`4>4;"+
"`5>5;"+
"`6>6;"+
"`7>7;"+
"`8>8;"+
"`9>9;"+
"`%>%;"+
"`.>.;"+
"`,>,;"+
"`*>*;"+
"``>`;"+
"'`0'>0;"+ // Escaped forms of the above
"'`1'>1;"+
"'`2'>2;"+
"'`3'>3;"+
"'`4'>4;"+
"'`5'>5;"+
"'`6'>6;"+
"'`7'>7;"+
"'`8'>8;"+
"'`9'>9;"+
"'`%'>'%';"+
"'`.'>'.';"+
"'`,'>',';"+
"'`*'>'*';"+
"'``'>'`';"+
"''>;"+

110
icu4j/src/com/ibm/text/resources/TransliterationRule_Latin_Devanagari.java
View file

@ -5,8 +5,8 @@
*******************************************************************************
*
* $Source: /xsrl/Nsvn/icu/icu4j/src/com/ibm/text/resources/Attic/TransliterationRule_Latin_Devanagari.java,v $
* $Date: 2000/04/21 21:17:08 $
* $Revision: 1.3 $
* $Date: 2000/04/22 00:04:25 $
* $Revision: 1.4 $
*
*****************************************************************************************
*/
@ -137,9 +137,9 @@ public class TransliterationRule_Latin_Devanagari extends ListResourceBundle {
+ "$depVowelBelow=[\u0941-\u0944];"
+ "$endThing=[$danda$doubleDanda \u0000-\u08FF\u0980-\uFFFF];"
// Unused -- these variable names are illegal and need to be changed
// + "$&=[$virama$aa$ai$au$ii$i$uu$u$rrh$rh$lh$e$o];"
// + "$%=[bcdfghjklmnpqrstvwxyz];"
// $x was originally called '&'; $z was '%'
+ "$x=[$virama$aa$ai$au$ii$i$uu$u$rrh$rh$lh$e$o];"
+ "$z=[bcdfghjklmnpqrstvwxyz];"
//#####################################################################
// convert from Latin letters to Native letters
@ -209,10 +209,10 @@ public class TransliterationRule_Latin_Devanagari extends ListResourceBundle {
+ "z>$sa|$virama;"
+ "h>$ha|$virama;"
+ ".>$danda;"
+ "$danda.>$doubleDanda;"
+ "$depVowelAbove{~>$bindu;"
+ "$depVowelBelow{~>$candrabindu;"
+ "'.'>$danda;"
+ "$danda'.'>$doubleDanda;"
+ "$depVowelAbove{'~'>$bindu;"
+ "$depVowelBelow{'~'>$candrabindu;"
// convert to dependent forms after consonant with no vowel:
// e.g. kai -> {ka}{virama}ai -> {ka}{ai}
@ -264,97 +264,97 @@ public class TransliterationRule_Latin_Devanagari extends ListResourceBundle {
// normal consonants
+ "kh<$kha}&;"
+ "kh<$kha}$x;"
+ "kha<$kha;"
+ "k''<$ka$virama}$ha;"
+ "k<$ka}&;"
+ "k<$ka}$x;"
+ "ka<$ka;"
+ "gh<$gha}&;"
+ "gh<$gha}$x;"
+ "gha<$gha;"
+ "g''<$ga$virama}$ha;"
+ "g<$ga}&;"
+ "g<$ga}$x;"
+ "ga<$ga;"
+ "ng<$nga}&;"
+ "ng<$nga}$x;"
+ "nga<$nga;"
+ "ch<$cha}&;"
+ "ch<$cha}$x;"
+ "cha<$cha;"
+ "c''<$ca$virama}$ha;"
+ "c<$ca}&;"
+ "c<$ca}$x;"
+ "ca<$ca;"
+ "jh<$jha}&;"
+ "jh<$jha}$x;"
+ "jha<$jha;"
+ "j''<$ja$virama}$ha;"
+ "j<$ja}&;"
+ "j<$ja}$x;"
+ "ja<$ja;"
+ "ny<$nya}&;"
+ "ny<$nya}$x;"
+ "nya<$nya;"
+ "tth<$ttha}&;"
+ "tth<$ttha}$x;"
+ "ttha<$ttha;"
+ "tt''<$tta$virama}$ha;"
+ "tt<$tta}&;"
+ "tt<$tta}$x;"
+ "tta<$tta;"
+ "ddh<$ddha}&;"
+ "ddh<$ddha}$x;"
+ "ddha<$ddha;"
+ "dd''<$dda}&$ha;"
+ "dd<$dda}&;"
+ "dd''<$dda}$x$ha;"
+ "dd<$dda}$x;"
+ "dda<$dda;"
+ "dh<$dha}&;"
+ "dh<$dha}$x;"
+ "dha<$dha;"
+ "d''<$da$virama}$ha;"
+ "d''<$da$virama}$ddha;"
+ "d''<$da$virama}$dda;"
+ "d''<$da$virama}$dha;"
+ "d''<$da$virama}$da;"
+ "d<$da}&;"
+ "d<$da}$x;"
+ "da<$da;"
+ "th<$tha}&;"
+ "th<$tha}$x;"
+ "tha<$tha;"
+ "t''<$ta$virama}$ha;"
+ "t''<$ta$virama}$ttha;"
+ "t''<$ta$virama}$tta;"
+ "t''<$ta$virama}$tha;"
+ "t''<$ta$virama}$ta;"
+ "t<$ta}&;"
+ "t<$ta}$x;"
+ "ta<$ta;"
+ "n''<$na$virama}$ga;"
+ "n''<$na$virama}$ya;"
+ "n<$na}&;"
+ "n<$na}$x;"
+ "na<$na;"
+ "ph<$pha}&;"
+ "ph<$pha}$x;"
+ "pha<$pha;"
+ "p''<$pa$virama}$ha;"
+ "p<$pa}&;"
+ "p<$pa}$x;"
+ "pa<$pa;"
+ "bh<$bha}&;"
+ "bh<$bha}$x;"
+ "bha<$bha;"
+ "b''<$ba$virama}$ha;"
+ "b<$ba}&;"
+ "b<$ba}$x;"
+ "ba<$ba;"
+ "m''<$ma$virama}$ma;"
+ "m''<$ma$virama}$bindu;"
+ "m<$ma}&;"
+ "m<$ma}$x;"
+ "ma<$ma;"
+ "y<$ya}&;"
+ "y<$ya}$x;"
+ "ya<$ya;"
+ "r''<$ra$virama}$ha;"
+ "r<$ra}&;"
+ "r<$ra}$x;"
+ "ra<$ra;"
+ "l''<$la$virama}$ha;"
+ "l<$la}&;"
+ "l<$la}$x;"
+ "la<$la;"
+ "v<$va}&;"
+ "v<$va}$x;"
+ "va<$va;"
+ "sh<$sha}&;"
+ "sh<$sha}$x;"
+ "sha<$sha;"
+ "ss<$ssa}&;"
+ "ss<$ssa}$x;"
+ "ssa<$ssa;"
+ "s''<$sa$virama}$ha;"
+ "s''<$sa$virama}$sha;"
+ "s''<$sa$virama}$ssa;"
+ "s''<$sa$virama}$sa;"
+ "s<$sa}&;"
+ "s<$sa}$x;"
+ "sa<$sa;"
+ "h<$ha}&;"
+ "h<$ha}$x;"
+ "ha<$ha;"
// dependent vowels (should never occur except following consonants)
@ -375,26 +375,26 @@ public class TransliterationRule_Latin_Devanagari extends ListResourceBundle {
// independent vowels (when following consonants)
+ "''aa<a{$waa;"
+ "''aa<%{$waa;"
+ "''aa<$z{$waa;"
+ "''ai<a{$wai;"
+ "''ai<%{$wai;"
+ "''ai<$z{$wai;"
+ "''au<a{$wau;"
+ "''au<%{$wau;"
+ "''au<$z{$wau;"
+ "''ii<a{$wii;"
+ "''ii<%{$wii;"
+ "''ii<$z{$wii;"
+ "''i<a{$wi;"
+ "''i<%{$wi;"
+ "''i<$z{$wi;"
+ "''uu<a{$wuu;"
+ "''uu<%{$wuu;"
+ "''uu<$z{$wuu;"
+ "''u<a{$wu;"
+ "''u<%{$wu;"
+ "''rrh<%{$wrr;"
+ "''rh<%{$wr;"
+ "''lh<%{$wl;"
+ "''e<%{$we;"
+ "''o<%{$wo;"
+ "''u<$z{$wu;"
+ "''rrh<$z{$wrr;"
+ "''rh<$z{$wr;"
+ "''lh<$z{$wl;"
+ "''e<$z{$we;"
+ "''o<$z{$wo;"
+ "''a<a{$wa;"
+ "''a<%{$wa;"
+ "''a<$z{$wa;"
// independent vowels (otherwise)

42
icu4j/src/com/ibm/text/resources/TransliterationRule_Latin_Greek.java
View file

@ -5,8 +5,8 @@
*******************************************************************************
*
* $Source: /xsrl/Nsvn/icu/icu4j/src/com/ibm/text/resources/Attic/TransliterationRule_Latin_Greek.java,v $
* $Date: 2000/04/21 21:17:08 $
* $Revision: 1.3 $
* $Date: 2000/04/22 00:04:25 $
* $Revision: 1.4 $
*
*****************************************************************************************
*/
@ -56,7 +56,7 @@ public class TransliterationRule_Latin_Greek extends ListResourceBundle {
// and for conditionals.
// ==============================================
+ "$quote=\";"
+ "$quote='\"';"
// Latin Letters
@ -217,14 +217,14 @@ public class TransliterationRule_Latin_Greek extends ListResourceBundle {
+ "''s < $pp{$sigma}$letter;"
+ "s < $sigma}$letter;"
+ "~s < $sigma;"
+ "'~'s < $sigma;"
+ "~s < $sigma2}$letter;"
+ "'~'s < $sigma2}$letter;"
+ "''s < $pp{$sigma2;"
+ "s < $sigma2;"
+ "~s }$letter>$sigma2;"
+ "~s > $sigma;"
+ "'~'s }$letter>$sigma2;"
+ "'~'s > $sigma;"
+ "''s }$letter>$sigma;"
+ "''s > $sigma2;"
+ "s }$letter>$sigma;"
@ -232,8 +232,8 @@ public class TransliterationRule_Latin_Greek extends ListResourceBundle {
// because there are no uppercase forms, had to move these up too.
+ "i$quote`>$iota_diaeresis2;"
+ "y$quote`>$ypsilon_diaeresis2;"
+ "i$quote'`'>$iota_diaeresis2;"
+ "y$quote'`'>$ypsilon_diaeresis2;"
+ "$u00ef_acute<>$iota_diaeresis2;"
+ "$u00fc_acute<>$vowel{$ypsilon_diaeresis2;"
@ -246,13 +246,13 @@ public class TransliterationRule_Latin_Greek extends ListResourceBundle {
// Typing variants, in case the keyboard doesn't have accents
+ "A`>$ALPHA2;"
+ "E`>$EPSILON2;"
+ "EE`>$ETA2;"
+ "'A`'>$ALPHA2;"
+ "'E`'>$EPSILON2;"
+ "'EE`'>$ETA2;"
+ "EE>$ETA;"
+ "I`>$IOTA2;"
+ "O`>$OMICRON2;"
+ "OO`>$OMEGA2;"
+ "'I`'>$IOTA2;"
+ "'O`'>$OMICRON2;"
+ "'OO`'>$OMEGA2;"
+ "OO>$OMEGA;"
+ "I$quote>$IOTA_DIAERESIS;"
+ "Y$quote>$YPSILON_DIAERESIS;"
@ -316,13 +316,13 @@ public class TransliterationRule_Latin_Greek extends ListResourceBundle {
// typing variants, in case the keyboard doesn't have accents
+ "a`>$alpha2;"
+ "e`>$epsilon2;"
+ "ee`>$eta2;"
+ "'a`'>$alpha2;"
+ "'e`'>$epsilon2;"
+ "'ee`'>$eta2;"
+ "ee>$eta;"
+ "i`>$iota2;"
+ "o`>$omicron2;"
+ "oo`>$omega2;"
+ "'i`'>$iota2;"
+ "'o`'>$omicron2;"
+ "'oo`'>$omega2;"
+ "oo>$omega;"
+ "i$quote>$iota_diaeresis;"
+ "y$quote>$ypsilon_diaeresis;"

174
icu4j/src/com/ibm/text/resources/TransliterationRule_Latin_Kana.java
View file

@ -5,8 +5,8 @@
*******************************************************************************
*
* $Source: /xsrl/Nsvn/icu/icu4j/src/com/ibm/text/resources/Attic/TransliterationRule_Latin_Kana.java,v $
* $Date: 2000/04/21 21:17:08 $
* $Revision: 1.3 $
* $Date: 2000/04/22 00:04:25 $
* $Revision: 1.4 $
*
*****************************************************************************************
*/
@ -24,7 +24,7 @@ public class TransliterationRule_Latin_Kana extends ListResourceBundle {
// Uppercase Latin to katakana
{ "Rule", ""
//# $Revision: 1.3 $
//# $Revision: 1.4 $
// Transliteration rules for Japanese Hiragana and Katakana to
// romaji
// lower case roman generates hiragana.
@ -382,10 +382,10 @@ public class TransliterationRule_Latin_Kana extends ListResourceBundle {
+ "BU>$BU;"
+ "BE>$BE;"
+ "BO>$BO;"
+ "BY>$BI|~Y;"
+ "BY>$BI|'~Y';"
+ "CHI>$TI;"
+ "CH>$TI|~Y;"
+ "CH>$TI|'~Y';"
+ "C}I>|S;"
+ "C}E>|S;"
@ -397,7 +397,7 @@ public class TransliterationRule_Latin_Kana extends ListResourceBundle {
+ "DO>$DO;"
+ "DZU>$DU;"
+ "DJI>$DI;"
+ "DJ>$DI|~Y;"
+ "DJ>$DI|'~Y';"
+ "E>$E;"
@ -408,7 +408,7 @@ public class TransliterationRule_Latin_Kana extends ListResourceBundle {
+ "GU>$GU;"
+ "GE>$GE;"
+ "GO>$GO;"
+ "GY>$GI|~Y;"
+ "GY>$GI|'~Y';"
+ "HA>$HA;"
+ "HI>$HI;"
@ -425,14 +425,14 @@ public class TransliterationRule_Latin_Kana extends ListResourceBundle {
+ "KU>$KU;"
+ "KE>$KE;"
+ "KO>$KO;"
+ "KY>$KI|~Y;"
+ "KY>$KI|'~Y';"
+ "MA>$MA;"
+ "MI>$MI;"
+ "MU>$MU;"
+ "ME>$ME;"
+ "MO>$MO;"
+ "MY>$MI|~Y;"
+ "MY>$MI|'~Y';"
+ "M}P>$N;"
+ "M}B>$N;"
@ -444,7 +444,7 @@ public class TransliterationRule_Latin_Kana extends ListResourceBundle {
+ "NU>$NU;"
+ "NE>$NE;"
+ "NO>$NO;"
+ "NY>$NI|~Y;"
+ "NY>$NI|'~Y';"
+ "O>$O;"
@ -453,14 +453,14 @@ public class TransliterationRule_Latin_Kana extends ListResourceBundle {
+ "PU>$PU;"
+ "PE>$PE;"
+ "PO>$PO;"
+ "PY>$PI|~Y;"
+ "PY>$PI|'~Y';"
+ "RA>$RA;"
+ "RI>$RI;"
+ "RU>$RU;"
+ "RE>$RE;"
+ "RO>$RO;"
+ "RY>$RI|~Y;"
+ "RY>$RI|'~Y';"
+ "SA>$SA;"
+ "SI>$SE$I2;"
@ -469,7 +469,7 @@ public class TransliterationRule_Latin_Kana extends ListResourceBundle {
+ "SO>$SO;"
+ "SHI>$SI;"
+ "SH>$SI|~Y;"
+ "SH>$SI|'~Y';"
+ "TA>$TA;"
+ "TI>$TE$I2;"
@ -478,7 +478,7 @@ public class TransliterationRule_Latin_Kana extends ListResourceBundle {
+ "TO>$TO;"
+ "TSU>$TU;"
//+ "TS>$TU|~;"
//+ "TS>$TU|'~';"
+ "U>$U;"
@ -504,20 +504,20 @@ public class TransliterationRule_Latin_Kana extends ListResourceBundle {
// SMALL FORMS
+ "~A>$A2;"
+ "~I>$I2;"
+ "~U>$U2;"
+ "~E>$E2;"
+ "~O>$O2;"
+ "~KA>$KA2;"
+ "~KE>$KE2;"
+ "~TSU>$TU2;"
+ "~WA>$WA2;"
+ "~YA>$YA2;"
+ "~YI>$YI2;"
+ "~YU>$YU2;"
+ "~YE>$YE2;"
+ "~YO>$YO2;"
+ "'~A'>$A2;"
+ "'~I'>$I2;"
+ "'~U'>$U2;"
+ "'~E'>$E2;"
+ "'~O'>$O2;"
+ "'~KA'>$KA2;"
+ "'~KE'>$KE2;"
+ "'~TSU'>$TU2;"
+ "'~WA'>$WA2;"
+ "'~YA'>$YA2;"
+ "'~YI'>$YI2;"
+ "'~YU'>$YU2;"
+ "'~YE'>$YE2;"
+ "'~YO'>$YO2;"
// DOUBLE CONSONANTS
@ -580,12 +580,12 @@ public class TransliterationRule_Latin_Kana extends ListResourceBundle {
// SIMPLE SUBSTITUTIONS USING BACKUP
+ "C>|K;"
+ "F>$HU|~;"
+ "J>$ZI|~Y;"
+ "F>$HU|'~';"
+ "J>$ZI|'~Y';"
+ "L>|R;"
+ "Q>|K;" // BACKUP AND REDO
+ "V>$VU|~;"
+ "W>$U|~;"
+ "V>$VU|'~';"
+ "W>$U|'~';"
+ "X>|KS;"
// WE HAD TO LIST THE LONGER ONES FIRST,
@ -826,18 +826,18 @@ public class TransliterationRule_Latin_Kana extends ListResourceBundle {
// SMALL FORMS
+ "~A<$A2;"
+ "~I<$I2;"
+ "~U<$U2;"
+ "~E<$E2;"
+ "~O<$O2;"
+ "~KA<$KA2;"
+ "~KE<$KE2;"
+ "~YA<$YA2;"
+ "~YU<$YU2;"
+ "~YO<$YO2;"
+ "~TSU<$TU2;"
+ "~WA<$WA2;"
+ "'~A'<$A2;"
+ "'~I'<$I2;"
+ "'~U'<$U2;"
+ "'~E'<$E2;"
+ "'~O'<$O2;"
+ "'~KA'<$KA2;"
+ "'~KE'<$KE2;"
+ "'~YA'<$YA2;"
+ "'~YU'<$YU2;"
+ "'~YO'<$YO2;"
+ "'~TSU'<$TU2;"
+ "'~WA'<$WA2;"
// LENGTH MARK. LATER, COULD USE CIRCUMFLEX
@ -859,10 +859,10 @@ public class TransliterationRule_Latin_Kana extends ListResourceBundle {
+ "bu>$bu;"
+ "be>$be;"
+ "bo>$bo;"
+ "by>$bi|~y;"
+ "by>$bi|'~y';"
+ "chi>$ti;"
+ "ch>$ti|~y;"
+ "ch>$ti|'~y';"
+ "c}i>|s;"
+ "c}e>|s;"
@ -874,7 +874,7 @@ public class TransliterationRule_Latin_Kana extends ListResourceBundle {
+ "do>$do;"
+ "dzu>$du;"
+ "dji>$di;"
+ "dj>$di|~y;"
+ "dj>$di|'~y';"
+ "e>$e;"
@ -885,7 +885,7 @@ public class TransliterationRule_Latin_Kana extends ListResourceBundle {
+ "gu>$gu;"
+ "ge>$ge;"
+ "go>$go;"
+ "gy>$gi|~y;"
+ "gy>$gi|'~y';"
+ "ha>$ha;"
+ "hi>$hi;"
@ -902,14 +902,14 @@ public class TransliterationRule_Latin_Kana extends ListResourceBundle {
+ "ku>$ku;"
+ "ke>$ke;"
+ "ko>$ko;"
+ "ky>$ki|~y;"
+ "ky>$ki|'~y';"
+ "ma>$ma;"
+ "mi>$mi;"
+ "mu>$mu;"
+ "me>$me;"
+ "mo>$mo;"
+ "my>$mi|~y;"
+ "my>$mi|'~y';"
+ "m}p>$n;"
+ "m}b>$n;"
@ -921,7 +921,7 @@ public class TransliterationRule_Latin_Kana extends ListResourceBundle {
+ "nu>$nu;"
+ "ne>$ne;"
+ "no>$no;"
+ "ny>$ni|~y;"
+ "ny>$ni|'~y';"
+ "o>$o;"
@ -930,14 +930,14 @@ public class TransliterationRule_Latin_Kana extends ListResourceBundle {
+ "pu>$pu;"
+ "pe>$pe;"
+ "po>$po;"
+ "py>$pi|~y;"
+ "py>$pi|'~y';"
+ "ra>$ra;"
+ "ri>$ri;"
+ "ru>$ru;"
+ "re>$re;"
+ "ro>$ro;"
+ "ry>$ri|~y;"
+ "ry>$ri|'~y';"
+ "sa>$sa;"
+ "si>$se$i2;"
@ -946,7 +946,7 @@ public class TransliterationRule_Latin_Kana extends ListResourceBundle {
+ "so>$so;"
+ "shi>$si;"
+ "sh>$si|~y;"
+ "sh>$si|'~y';"
+ "ta>$ta;"
+ "ti>$te$i2;"
@ -955,7 +955,7 @@ public class TransliterationRule_Latin_Kana extends ListResourceBundle {
+ "to>$to;"
+ "tsu>$tu;"
//+ "ts>$tu|~;"
//+ "ts>$tu|'~';"
+ "u>$u;"
@ -981,20 +981,20 @@ public class TransliterationRule_Latin_Kana extends ListResourceBundle {
// small forms
+ "~a>$a2;"
+ "~i>$i2;"
+ "~u>$u2;"
+ "~e>$e2;"
+ "~o>$o2;"
+ "~ka>$ka2;"
+ "~ke>$ke2;"
+ "~tsu>$tu2;"
+ "~wa>$wa2;"
+ "~ya>$ya2;"
+ "~yi>$yi2;"
+ "~yu>$yu2;"
+ "~ye>$ye2;"
+ "~yo>$yo2;"
+ "'~a'>$a2;"
+ "'~i'>$i2;"
+ "'~u'>$u2;"
+ "'~e'>$e2;"
+ "'~o'>$o2;"
+ "'~ka'>$ka2;"
+ "'~ke'>$ke2;"
+ "'~tsu'>$tu2;"
+ "'~wa'>$wa2;"
+ "'~ya'>$ya2;"
+ "'~yi'>$yi2;"
+ "'~yu'>$yu2;"
+ "'~ye'>$ye2;"
+ "'~yo'>$yo2;"
// Double Consonants
@ -1057,12 +1057,12 @@ public class TransliterationRule_Latin_Kana extends ListResourceBundle {
// simple substitutions using backup
+ "c>|k;"
+ "f>$hu|~;"
+ "j>$zi|~y;"
+ "f>$hu|'~';"
+ "j>$zi|'~y';"
+ "l>|r;"
+ "q>|k;" // backup and redo
+ "v>$vu|~;"
+ "w>$u|~;"
+ "v>$vu|'~';"
+ "w>$u|'~';"
+ "x>|ks;"
// We had to list the longer ones first,
@ -1303,18 +1303,18 @@ public class TransliterationRule_Latin_Kana extends ListResourceBundle {
// small forms
+ "~a<$a2;"
+ "~i<$i2;"
+ "~u<$u2;"
+ "~e<$e2;"
+ "~o<$o2;"
//masked: + "~ka<$ka2;" ({~ka} is an alias for {~KA})
//masked: + "~ke<$ke2;" ({~ke} is an alias for {~KE})
+ "~ya<$ya2;"
+ "~yu<$yu2;"
+ "~yo<$yo2;"
+ "~tsu<$tu2;"
+ "~wa<$wa2;"
+ "'~a'<$a2;"
+ "'~i'<$i2;"
+ "'~u'<$u2;"
+ "'~e'<$e2;"
+ "'~o'<$o2;"
//masked: + "'~ka'<$ka2;" ({~ka} is an alias for {~KA})
//masked: + "'~ke'<$ke2;" ({~ke} is an alias for {~KE})
+ "'~ya'<$ya2;"
+ "'~yu'<$yu2;"
+ "'~yo'<$yo2;"
+ "'~tsu'<$tu2;"
+ "'~wa'<$wa2;"
// length mark. Later, could use circumflex
@ -1327,10 +1327,10 @@ public class TransliterationRule_Latin_Kana extends ListResourceBundle {
//#######################################
// Non-shared stuff goes here
+ "~>;" // remove if not used
+ "'~'>;" // remove if not used
+ "$quote>;" // remove if not used
//+ "<$quote;"
+ "->$long;"
+ "'-'>$long;"
}
};

13
icu4j/src/com/ibm/text/resources/TransliterationRule_StraightQuotes_CurlyQuotes.java
View file

@ -5,8 +5,8 @@
*******************************************************************************
*
* $Source: /xsrl/Nsvn/icu/icu4j/src/com/ibm/text/resources/Attic/TransliterationRule_StraightQuotes_CurlyQuotes.java,v $
* $Date: 2000/04/21 21:17:08 $
* $Revision: 1.3 $
* $Date: 2000/04/22 00:04:25 $
* $Revision: 1.4 $
*
*****************************************************************************************
*/
@ -25,7 +25,7 @@ public class TransliterationRule_StraightQuotes_CurlyQuotes extends ListResource
"$white=[[:Zs:][:Zl:][:Zp:]];"
+ "$black=[^$white];"
+ "$open=[:Ps:];"
+ "$dquote=\";"
+ "$dquote='\"';"
+ "$lAng=\u3008;"
+ "$ldAng=\u300A;"
@ -75,8 +75,8 @@ public class TransliterationRule_StraightQuotes_CurlyQuotes extends ListResource
// prevent double spaces
+ "\\ {\\ >;"
// join hyphens into dash
+ "-->$mdash;"
// join hyphens into dash ### BIDIRECTIONAL ###
+ "'--'<>$mdash;"
//#######################################
// Conversions back to input
@ -87,9 +87,6 @@ public class TransliterationRule_StraightQuotes_CurlyQuotes extends ListResource
+ "''<$rquote;"
+ "$dquote<$ldquote;"
+ "$dquote<$rdquote;"
//hyphens
+ "--<$mdash;"
}
};
}

3026
icu4j/src/com/ibm/text/resources/TransliterationRule_UnicodeName_UnicodeChar.java
View file

File diff suppressed because it is too large Load diff