ICU-7865 Wiring up IndexCharacters class with CLDR data; part of this is merged from the branch umesh/index-characters-100730
X-SVN-Rev: 28409
This commit is contained in:
Umesh Nair
parent
75b55210bd
commit
f519d51352
@ -15,6 +15,7 @@ import java.util.LinkedHashMap;
|
||||
import java.util.LinkedHashSet;
|
||||
import java.util.List;
|
||||
import java.util.Map;
|
||||
import java.util.MissingResourceException;
|
||||
import java.util.Set;
|
||||
import java.util.TreeSet;
|
||||
|
||||
@ -84,7 +85,7 @@ public class IndexCharacters {
|
||||
* @provisional This API might change or be removed in a future release.
|
||||
*/
|
||||
public IndexCharacters(ULocale locale) {
|
||||
this(locale, LocaleData.getExemplarSet(locale, LocaleData.ES_STANDARD), Collator.getInstance(locale));
|
||||
this(locale, Collator.getInstance(locale));
|
||||
}
|
||||
|
||||
/**
|
||||
@ -92,7 +93,7 @@ public class IndexCharacters {
|
||||
* @deprecated This API is ICU internal only.
|
||||
*/
|
||||
@SuppressWarnings("unchecked")
|
||||
public IndexCharacters(ULocale locale, UnicodeSet exemplarSet, Collator collator) {
|
||||
public IndexCharacters(ULocale locale, Collator collator) {
|
||||
this.locale = locale;
|
||||
try {
|
||||
comparator = (Collator) collator.clone();
|
||||
@ -101,24 +102,33 @@ public class IndexCharacters {
|
||||
}
|
||||
comparator.setStrength(Collator.PRIMARY);
|
||||
|
||||
// get the exemplars, and handle special cases
|
||||
boolean gotFromLocale = true;
|
||||
UnicodeSet exemplars = LocaleData.getExemplarSet(locale, 0, LocaleData.ES_INDEX);
|
||||
|
||||
UnicodeSet exemplars = exemplarSet.cloneAsThawed();
|
||||
// question: should we add auxiliary exemplars?
|
||||
if (exemplars.containsSome(CORE_LATIN)) {
|
||||
exemplars.addAll(CORE_LATIN);
|
||||
}
|
||||
if (exemplars.containsSome(HANGUL)) {
|
||||
// cut down to small list
|
||||
exemplars.removeAll(new UnicodeSet("[:block=hangul_syllables:]")).addAll(HANGUL);
|
||||
}
|
||||
if (exemplars.containsSome(ETHIOPIC)) {
|
||||
// cut down to small list
|
||||
// make use of the fact that Ethiopic is allocated in 8's, where
|
||||
// the base is 0 mod 8.
|
||||
for (UnicodeSetIterator it = new UnicodeSetIterator(ETHIOPIC); it.next();) {
|
||||
if ((it.codepoint & 0x7) != 0) {
|
||||
exemplars.remove(it.codepoint);
|
||||
if (exemplars == null) {
|
||||
gotFromLocale = false;
|
||||
// manufacture a set
|
||||
exemplars = LocaleData.getExemplarSet(locale, 0, LocaleData.ES_STANDARD);
|
||||
|
||||
// get the exemplars, and handle special cases
|
||||
|
||||
exemplars = exemplars.cloneAsThawed();
|
||||
// question: should we add auxiliary exemplars?
|
||||
if (exemplars.containsSome(CORE_LATIN)) {
|
||||
exemplars.addAll(CORE_LATIN);
|
||||
}
|
||||
if (exemplars.containsSome(HANGUL)) {
|
||||
// cut down to small list
|
||||
exemplars.removeAll(new UnicodeSet("[:block=hangul_syllables:]")).addAll(HANGUL);
|
||||
}
|
||||
if (exemplars.containsSome(ETHIOPIC)) {
|
||||
// cut down to small list
|
||||
// make use of the fact that Ethiopic is allocated in 8's, where
|
||||
// the base is 0 mod 8.
|
||||
for (UnicodeSetIterator it = new UnicodeSetIterator(ETHIOPIC); it.next();) {
|
||||
if ((it.codepoint & 0x7) != 0) {
|
||||
exemplars.remove(it.codepoint);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@ -142,7 +152,9 @@ public class IndexCharacters {
|
||||
// So we make a pass through, filtering out those cases.
|
||||
|
||||
for (String item : preferenceSorting) {
|
||||
item = UCharacter.toUpperCase(locale, item);
|
||||
if (!gotFromLocale) {
|
||||
item = UCharacter.toUpperCase(locale, item);
|
||||
}
|
||||
if (indexCharacters.contains(item)) {
|
||||
for (String itemAlreadyIn : indexCharacters) {
|
||||
if (comparator.compare(item, itemAlreadyIn) == 0) {
|
||||
@ -222,6 +234,10 @@ public class IndexCharacters {
|
||||
return locale;
|
||||
}
|
||||
|
||||
public Collator getCollator() {
|
||||
return comparator;
|
||||
}
|
||||
|
||||
/**
|
||||
* As the index is built, items may be discarded from the exemplars.
|
||||
* This contains some of the discards, and is intended for debugging.
|
||||
|
||||
@ -40,11 +40,23 @@ public final class LocaleData {
|
||||
*/
|
||||
public static final int ES_AUXILIARY = 1;
|
||||
|
||||
/**
|
||||
* EXType for {@link #getExemplarSet(int, int)}.
|
||||
* @stable ICU 3.4
|
||||
*/
|
||||
public static final int ES_INDEX = 2;
|
||||
|
||||
/**
|
||||
* EXType for {@link #getExemplarSet(int, int)}.
|
||||
* @stable ICU 3.4
|
||||
*/
|
||||
public static final int ES_CURRENCY = 3;
|
||||
|
||||
/**
|
||||
* Count of EXTypes for {@link #getExemplarSet(int, int)}.
|
||||
* @stable ICU 3.4
|
||||
*/
|
||||
public static final int ES_COUNT = 2;
|
||||
public static final int ES_COUNT = 4;
|
||||
|
||||
/**
|
||||
* Delimiter type for {@link #getDelimiter(int)}.
|
||||
@ -98,10 +110,29 @@ public final class LocaleData {
|
||||
* @stable ICU 3.0
|
||||
*/
|
||||
public static UnicodeSet getExemplarSet(ULocale locale, int options) {
|
||||
ICUResourceBundle bundle = (ICUResourceBundle)UResourceBundle.getBundleInstance(ICUResourceBundle.ICU_BASE_NAME, locale);
|
||||
String pattern = bundle.getString(EXEMPLAR_CHARS);
|
||||
return new UnicodeSet(pattern, UnicodeSet.IGNORE_SPACE | options);
|
||||
}
|
||||
return LocaleData.getInstance(locale).getExemplarSet(options, ES_STANDARD);
|
||||
}
|
||||
|
||||
/**
|
||||
* Returns the set of exemplar characters for a locale.
|
||||
*
|
||||
* @param locale Locale for which the exemplar character set
|
||||
* is to be retrieved.
|
||||
* @param options Bitmask for options to apply to the exemplar pattern.
|
||||
* Specify zero to retrieve the exemplar set as it is
|
||||
* defined in the locale data. Specify
|
||||
* UnicodeSet.CASE to retrieve a case-folded exemplar
|
||||
* set. See {@link UnicodeSet#applyPattern(String,
|
||||
* int)} for a complete list of valid options. The
|
||||
* IGNORE_SPACE bit is always set, regardless of the
|
||||
* value of 'options'.
|
||||
* @param extype The type of exemplar character set to retrieve.
|
||||
* @return The set of exemplar characters for the given locale.
|
||||
* @stable ICU 3.0
|
||||
*/
|
||||
public static UnicodeSet getExemplarSet(ULocale locale, int options, int extype) {
|
||||
return LocaleData.getInstance(locale).getExemplarSet(options, extype);
|
||||
}
|
||||
|
||||
/**
|
||||
* Returns the set of exemplar characters for a locale.
|
||||
@ -114,13 +145,17 @@ public final class LocaleData {
|
||||
* int)} for a complete list of valid options. The
|
||||
* IGNORE_SPACE bit is always set, regardless of the
|
||||
* value of 'options'.
|
||||
* @param extype The type of exemplar set to be retrieved,
|
||||
* ES_STANDARD or ES_AUXILIARY
|
||||
* @param extype The type of exemplar set to be retrieved,
|
||||
* ES_STANDARD, ES_INDEX, ES_CURRENCY, or ES_AUXILIARY
|
||||
* @return The set of exemplar characters for the given locale.
|
||||
* @stable ICU 3.4
|
||||
*/
|
||||
public UnicodeSet getExemplarSet(int options, int extype) {
|
||||
String [] exemplarSetTypes = { "ExemplarCharacters", "AuxExemplarCharacters" };
|
||||
String [] exemplarSetTypes = {
|
||||
"ExemplarCharacters", "AuxExemplarCharacters",
|
||||
"ExemplarCharactersIndex", "ExemplarCharactersCurrency"
|
||||
};
|
||||
|
||||
try{
|
||||
ICUResourceBundle stringBundle = (ICUResourceBundle) bundle.get(exemplarSetTypes[extype]);
|
||||
|
||||
@ -131,6 +166,8 @@ public final class LocaleData {
|
||||
}catch(MissingResourceException ex){
|
||||
if(extype==LocaleData.ES_AUXILIARY){
|
||||
return new UnicodeSet();
|
||||
} else if (extype==LocaleData.ES_INDEX){
|
||||
return null;
|
||||
}
|
||||
throw ex;
|
||||
}
|
||||
|
||||
@ -1,10 +1,11 @@
|
||||
/*
|
||||
*******************************************************************************
|
||||
* Copyright (C) 2008-2009, International Business Machines Corporation and *
|
||||
* Copyright (C) 2008-2010, International Business Machines Corporation and *
|
||||
* others. All Rights Reserved. *
|
||||
*******************************************************************************
|
||||
*/
|
||||
package com.ibm.icu.dev.test.collator;
|
||||
import com.ibm.icu.text.IndexCharacters;
|
||||
|
||||
import java.util.ArrayList;
|
||||
import java.util.Collection;
|
||||
@ -26,6 +27,136 @@ public class IndexCharactersTest extends TestFmwk {
|
||||
new IndexCharactersTest().run(args);
|
||||
}
|
||||
|
||||
public void TestIndexCharactersList() {
|
||||
String[][] localeAndIndexCharactersList = new String[][] {
|
||||
{"af", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z"},
|
||||
{"ak", "A:B:C:D:E:\u0190:F:G:H:I:J:K:L:M:N:O:\u0186:P:Q:R:S:T:U:V:W:X:Y:Z"},
|
||||
{"ar", "\u0627:\u0628:\u062A:\u062B:\u062C:\u062D:\u062E:\u062F:\u0630:\u0631:\u0632:\u0633:\u0634:\u0635:\u0636:\u0637:\u0638:\u0639:\u063A:\u0641:\u0642:\u0643:\u0644:\u0645:\u0646:\u0647:\u0648:\u064A"},
|
||||
{"asa", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:R:S:T:U:V:W:Y:Z"},
|
||||
{"az", "A:B:C:\u00C7:D:E:\u018F:F:G:\u011E:H:X:I:\u0130:J:K:Q:L:M:N:O:\u00D6:P:R:S:\u015E:T:U:\u00DC:V:W:Y:Z"},
|
||||
{"be", "\u0410:\u0411:\u0412:\u0413:\u0414:\u0415:\u0416:\u0417:\u0406:\u0419:\u041A:\u041B:\u041C:\u041D:\u041E:\u041F:\u0420:\u0421:\u0422:\u0423:\u0424:\u0425:\u0426:\u0427:\u0428:\u042B:\u042D:\u042E:\u042F"},
|
||||
{"bem", "A:B:C:E:F:G:I:J:K:L:M:N:O:P:S:T:U:W:Y"},
|
||||
{"bez", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:Y:Z"},
|
||||
{"bg", "\u0410:\u0411:\u0412:\u0413:\u0414:\u0415:\u0416:\u0417:\u0418:\u0419:\u041A:\u041B:\u041C:\u041D:\u041E:\u041F:\u0420:\u0421:\u0422:\u0423:\u0424:\u0425:\u0426:\u0427:\u0428:\u0429:\u042E:\u042F"},
|
||||
{"bm", "A:B:C:D:E:\u0190:F:G:H:I:J:K:L:M:N:\u019D:\u014A:O:\u0186:P:R:S:T:U:W:Y:Z"},
|
||||
{"bo", "\u0F40:\u0F41:\u0F42:\u0F44:\u0F45:\u0F46:\u0F47:\u0F49:\u0F4F:\u0F50:\u0F51:\u0F53:\u0F54:\u0F55:\u0F56:\u0F58:\u0F59:\u0F5A:\u0F5B:\u0F5D:\u0F5E:\u0F5F:\u0F60:\u0F61:\u0F62:\u0F63:\u0F64:\u0F66:\u0F67:\u0F68"},
|
||||
{"ca", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z"},
|
||||
{"cgg", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z"},
|
||||
{"chr", "\u13A0:\u13A6:\u13AD:\u13B3:\u13B9:\u13BE:\u13C6:\u13CC:\u13D3:\u13DC:\u13E3:\u13E9:\u13EF"},
|
||||
{"cs", "A:B:C:\u010C:D:E:F:G:H:CH:I:J:K:L:M:N:O:P:Q:R:\u0158:S:\u0160:T:U:V:W:X:Y:Z:\u017D"},
|
||||
{"cy", "A:B:C:CH:D:E:F:FF:G:H:I:J:L:LL:M:N:O:P:PH:R:RH:S:T:TH:U:W:Y"},
|
||||
{"da", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z:\u00C6:\u00D8:\u00C5"},
|
||||
{"dav", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:R:S:T:U:V:W:Y:Z"},
|
||||
{"de", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z"},
|
||||
{"ebu", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z"},
|
||||
{"ee", "A:B:C:D:\u0189:E:\u0190:F:\u0191:G:\u0194:H:I:J:K:L:M:N:\u014A:O:\u0186:P:Q:R:S:T:U:V:\u01B2:W:X:Y:Z"},
|
||||
{"el", "\u0391:\u0392:\u0393:\u0394:\u0395:\u0396:\u0397:\u0398:\u0399:\u039A:\u039B:\u039C:\u039D:\u039E:\u039F:\u03A0:\u03A1:\u03A3:\u03A4:\u03A5:\u03A6:\u03A7:\u03A8:\u03A9"},
|
||||
{"en", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z"},
|
||||
{"eo", "A:B:C:\u0108:D:E:F:G:\u011C:H:\u0124:I:J:\u0134:K:L:M:N:O:P:R:S:\u015C:T:U:\u016C:V:Z"},
|
||||
{"es", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:\u00D1:O:P:Q:R:S:T:U:V:W:X:Y:Z"},
|
||||
{"et", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:\u0160:Z:\u017D:T:U:V:\u00D5:\u00C4:\u00D6:\u00DC:X:Y"},
|
||||
{"eu", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z"},
|
||||
{"ff", "A:B:\u0181:C:D:\u018A:E:F:G:H:I:J:K:L:M:N:\u014A:O:P:R:S:T:U:W:Y:\u01B3"},
|
||||
{"fi", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z:\u00C5:\u00C4:\u00D6"},
|
||||
{"fil", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z"},
|
||||
{"fo", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z:\u00C6:\u00D8"},
|
||||
{"fr", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z"},
|
||||
{"guz", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:R:S:T:U:V:W:Y:Z"},
|
||||
{"ha", "A:B:\u0181:C:D:\u018A:E:F:G:H:I:J:K:\u0198:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z"},
|
||||
{"he", "\u05D0:\u05D1:\u05D2:\u05D3:\u05D4:\u05D5:\u05D6:\u05D7:\u05D8:\u05D9:\u05DB:\u05DC:\u05DE:\u05E0:\u05E1:\u05E2:\u05E4:\u05E6:\u05E7:\u05E8:\u05E9:\u05EA"},
|
||||
{"ig", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z"},
|
||||
{"is", "A:\u00C1:B:C:D:\u00D0:E:\u00C9:F:G:H:I:\u00CD:J:K:L:M:N:O:\u00D3:P:Q:R:S:T:U:\u00DA:V:W:X:Y:\u00DD:Z:\u00DE:\u00C6:\u00D6"},
|
||||
{"it", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z"},
|
||||
{"ja", "\u3042:\u304B:\u3055:\u305F:\u306A:\u306F:\u307E:\u3084:\u3089:\u308F"},
|
||||
{"jmc", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:R:S:T:U:V:W:Y:Z"},
|
||||
{"kab", "A:B:C:D:E:\u0190:F:G:\u0194:H:I:J:K:L:M:N:P:Q:R:S:T:U:W:X:Y:Z"},
|
||||
{"kam", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z"},
|
||||
{"kde", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z"},
|
||||
{"kea", "A:B:D:E:F:G:H:I:J:K:L:M:N:O:P:R:S:T:U:V:X:Z"},
|
||||
{"khq", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:\u019D:\u014A:O:P:Q:R:S:T:U:W:X:Y:Z"},
|
||||
{"ki", "A:B:C:D:E:G:H:I:J:K:M:N:O:R:T:U:W:Y"},
|
||||
{"kln", "A:B:C:D:E:G:H:I:J:K:L:M:N:O:P:R:S:T:U:W:Y"},
|
||||
{"ko", "\u1100:\u1102:\u1103:\u1105:\u1106:\u1107:\u1109:\u110B:\u110C:\u110E:\u110F:\u1110:\u1111:\u1112"},
|
||||
{"lag", "A:B:C:D:E:F:G:H:I:\u0197:J:K:L:M:N:O:P:Q:R:S:T:U:\u0244:V:W:X:Y:Z"},
|
||||
{"lg", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z"},
|
||||
{"lt", "A:B:C:\u010C:D:E:F:G:H:I:J:K:L:M:N:O:P:R:S:\u0160:T:U:V:Z:\u017D"},
|
||||
{"luo", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:R:S:T:U:V:W:Y"},
|
||||
{"luy", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z"},
|
||||
// This should be the correct data. Commented till it is fixed in CLDR collation data.
|
||||
// {"lv", "A:B:C:\u010C:D:E:F:G:\u0122:H:I:Y:J:K:\u0136:L:\u013B:M:N:\u0145:O:P:Q:R:S:\u0160:T:U:V:W:X:Z:\u017D"},
|
||||
{"lv", "A:B:C:\u010C:D:E:F:G:\u0122:H:I:J:K:\u0136:L:\u013B:M:N:\u0145:O:P:Q:R:S:\u0160:T:U:V:W:X:Y:Z:\u017D"},
|
||||
{"mas", "A:B:C:D:E:\u0190:G:H:I:\u0197:J:K:L:M:N:\u014A:O:\u0186:P:R:S:T:U:\u0244:W:Y"},
|
||||
{"mer", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z"},
|
||||
{"mfe", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:R:S:T:U:V:W:X:Y:Z"},
|
||||
{"mg", "A:B:D:E:F:G:H:I:J:K:L:M:N:O:P:R:S:T:V:Y:Z"},
|
||||
// This should be the correct data. Commented till it is fixed in CLDR collation data.
|
||||
// {"mk", "\u0410:\u0411:\u0412:\u0413:\u0403:\u0414:\u0415:\u0416:\u0417:\u0405:\u0418:\u0408:\u041A:\u040C:\u041B:\u0409:\u041C:\u041D:\u040A:\u041E:\u041F:\u0420:\u0421:\u0422:\u0423:\u0424:\u0425:\u0426:\u0427:\u040F:\u0428"},
|
||||
{"mk", "\u0410:\u0411:\u0412:\u0413:\u0414:\u0403:\u0415:\u0416:\u0417:\u0405:\u0418:\u0408:\u041A:\u041B:\u0409:\u041C:\u041D:\u040A:\u041E:\u041F:\u0420:\u0421:\u0422:\u040C:\u0423:\u0424:\u0425:\u0426:\u0427:\u040F:\u0428"},
|
||||
// This should be the correct data. Commented till it is fixed in CLDR collation data.
|
||||
// {"mt", "A:B:C:\u010A:D:E:F:\u0120:G:G\u0126:H:\u0126:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:\u017B:Z"},
|
||||
{"mt", "A:B:\u010A:C:D:E:F:\u0120:G:G\u0126:H:\u0126:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:\u017B:Z"},
|
||||
{"naq", "A:B:C:D:E:F:G:H:I:K:M:N:O:P:Q:R:S:T:U:W:X:Y:Z"},
|
||||
{"nb", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z:\u00C6:\u00D8:\u00C5"},
|
||||
{"nd", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:S:T:U:V:W:X:Y:Z"},
|
||||
{"nl", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z"},
|
||||
{"nn", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z:\u00C6:\u00D8:\u00C5"},
|
||||
{"nyn", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z"},
|
||||
{"om", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z"},
|
||||
{"pl", "A:\u0104:B:C:\u0106:D:E:\u0118:F:G:H:I:J:K:L:\u0141:M:N:\u0143:O:\u00D3:P:Q:R:S:\u015A:T:U:V:W:X:Y:Z:\u0179:\u017B"},
|
||||
{"pt", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z"},
|
||||
{"rm", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z"},
|
||||
{"ro", "A:\u0102:\u00C2:B:C:D:E:F:G:H:I:\u00CE:J:K:L:M:N:O:P:Q:R:S:\u0218:T:\u021A:U:V:W:X:Y:Z"},
|
||||
{"rof", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:R:S:T:U:V:W:Y:Z"},
|
||||
{"ru", "\u0410:\u0411:\u0412:\u0413:\u0414:\u0415:\u0416:\u0417:\u0418:\u0419:\u041A:\u041B:\u041C:\u041D:\u041E:\u041F:\u0420:\u0421:\u0422:\u0423:\u0424:\u0425:\u0426:\u0427:\u0428:\u0429:\u042B:\u042D:\u042E:\u042F"},
|
||||
{"rw", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z"},
|
||||
{"rwk", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:R:S:T:U:V:W:Y:Z"},
|
||||
{"saq", "A:B:C:D:E:G:H:I:J:K:L:M:N:O:P:R:S:T:U:V:W:Y"},
|
||||
{"seh", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z"},
|
||||
{"ses", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:\u019D:\u014A:O:P:Q:R:S:T:U:W:X:Y:Z"},
|
||||
{"sg", "A:B:D:E:F:G:H:I:J:K:L:M:N:O:P:R:S:T:U:V:W:Y:Z"},
|
||||
{"shi", "A:B:C:D:E:\u0190:F:G:\u0194:H:I:J:K:L:M:N:Q:R:S:T:U:W:X:Y:Z"},
|
||||
{"shi_Tfng", "\u2D30:\u2D31:\u2D33:\u2D37:\u2D39:\u2D3B:\u2D3C:\u2D3D:\u2D40:\u2D43:\u2D44:\u2D45:\u2D47:\u2D49:\u2D4A:\u2D4D:\u2D4E:\u2D4F:\u2D53:\u2D54:\u2D55:\u2D56:\u2D59:\u2D5A:\u2D5B:\u2D5C:\u2D5F:\u2D61:\u2D62:\u2D63:\u2D65"},
|
||||
{"sk", "A:\u00C4:B:C:\u010C:D:E:F:G:H:CH:I:J:K:L:M:N:O:\u00D4:P:Q:R:S:\u0160:T:U:V:W:X:Y:Z:\u017D"},
|
||||
{"sl", "A:B:C:\u010C:\u0106:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:\u0160:T:U:V:W:X:Y:Z:\u017D"},
|
||||
{"sn", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:R:S:T:U:V:W:Y:Z"},
|
||||
{"sr", "\u0410:\u0411:\u0412:\u0413:\u0414:\u0402:\u0415:\u0416:\u0417:\u0418:\u0408:\u041A:\u041B:\u0409:\u041C:\u041D:\u040A:\u041E:\u041F:\u0420:\u0421:\u0422:\u040B:\u0423:\u0424:\u0425:\u0426:\u0427:\u040F:\u0428"},
|
||||
{"sv", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z:\u00C5:\u00C4:\u00D6"},
|
||||
{"teo", "A:B:C:D:E:G:H:I:J:K:L:M:N:O:P:R:S:T:U:V:W:X:Y"},
|
||||
{"to", "A:B:C:D:E:F:G:H:\u02BB:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z"},
|
||||
{"tr", "A:B:C:\u00C7:D:E:F:G:\u011E:H:I:\u0130:J:K:L:M:N:O:\u00D6:P:Q:R:S:\u015E:T:U:\u00DC:V:W:X:Y:Z"},
|
||||
{"tzm", "A:B:C:D:E:\u0190:F:G:\u0194:H:I:J:K:L:M:N:Q:R:S:T:U:W:X:Y:Z"},
|
||||
{"uk", "\u0410:\u0411:\u0412:\u0413:\u0490:\u0414:\u0415:\u0404:\u0416:\u0417:\u0418:\u0406:\u0407:\u0419:\u041A:\u041B:\u041C:\u041D:\u041E:\u041F:\u0420:\u0421:\u0422:\u0423:\u0424:\u0425:\u0426:\u0427:\u0428:\u0429:\u042E:\u042F"},
|
||||
{"uz_Latn", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z:\u02BF"},
|
||||
{"vi", "A:\u0102:\u00C2:B:C:D:\u0110:E:\u00CA:F:G:H:I:J:K:L:M:N:O:\u00D4:\u01A0:P:Q:R:S:T:U:\u01AF:V:W:X:Y:Z"},
|
||||
{"vun", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:R:S:T:U:V:W:Y:Z"},
|
||||
{"xog", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z"},
|
||||
{"yo", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z"},
|
||||
{"zh", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z"},
|
||||
{"zh_Hant", "\u4E00:\u4E01:\u4E09:\u4E11:\u4E19:\u4E1E:\u4E32:\u4E26:\u4E9F:\u4E58:\u4E7E:\u50A2:\u4E82:\u50E7:\u5104:\u5112:\u512A:\u53E2:\u56A5:\u52F8:\u5137:\u513C:\u56CC:\u56D1:\u5EF3"},
|
||||
};
|
||||
for (String[] localeAndIndexCharacters : localeAndIndexCharactersList) {
|
||||
ULocale locale = new ULocale(localeAndIndexCharacters[0]);
|
||||
String expectedIndexCharacters = localeAndIndexCharacters[1];
|
||||
Collection<String> indexCharacters = new IndexCharacters(locale).getIndexCharacters();
|
||||
|
||||
// Join the elements of the list to a string with delimiter ":"
|
||||
StringBuilder sb = new StringBuilder();
|
||||
Iterator iter = indexCharacters.iterator();
|
||||
while (iter.hasNext()) {
|
||||
sb.append(iter.next());
|
||||
if (!iter.hasNext()) {
|
||||
break;
|
||||
}
|
||||
sb.append(":");
|
||||
}
|
||||
String actualIndexCharacters = sb.toString();
|
||||
if (!expectedIndexCharacters.equals(actualIndexCharacters)) {
|
||||
errln("Test failed for locale " + localeAndIndexCharacters[0] +
|
||||
"\n Expected = |" + expectedIndexCharacters + "|\n actual = |" + actualIndexCharacters + "|");
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
public void TestBasics() {
|
||||
ULocale[] list = ULocale.getAvailableLocales();
|
||||
// get keywords combinations
|
||||
@ -37,7 +168,7 @@ public class IndexCharactersTest extends TestFmwk {
|
||||
for (int j = 0; j < collationValues.length; ++j) {
|
||||
keywords.add("@collation=" + collationValues[j]);
|
||||
}
|
||||
|
||||
|
||||
for (int i = 0; i < list.length; ++i) {
|
||||
for (Iterator it = keywords.iterator(); it.hasNext();) {
|
||||
String collationValue = (String) it.next();
|
||||
|
||||
Loading…
Reference in New Issue
Block a user