X-Git-Url: https://git.saurik.com/apple/icu.git/blobdiff_plain/374ca955a76ecab1204ca8bfa63ff9238d998416..e4f10fab0c078f399c9deef476d9c9b73b47dff8:/icuSources/test/intltest/transrt.cpp diff --git a/icuSources/test/intltest/transrt.cpp b/icuSources/test/intltest/transrt.cpp index f8803212..eab4c90a 100644 --- a/icuSources/test/intltest/transrt.cpp +++ b/icuSources/test/intltest/transrt.cpp @@ -1,6 +1,6 @@ /* ********************************************************************** -* Copyright (C) 2000-2004, International Business Machines +* Copyright (C) 2000-2011, International Business Machines * Corporation and others. All Rights Reserved. ********************************************************************** * Date Name Description @@ -26,6 +26,7 @@ #include "unicode/locid.h" #include "unicode/ulocdata.h" #include "unicode/utf8.h" +#include "unicode/utf16.h" #include "putilimp.h" #include "cmemory.h" #include "transrt.h" @@ -79,19 +80,6 @@ TransliteratorRoundTripTest::runIndexedTest(int32_t index, UBool exec, } } -//-------------------------------------------------------------------- -// Time bomb - allows temporary behavior that expires at a given -// release -//-------------------------------------------------------------------- -/* -static const UVersionInfo ICU_30 = {3,0,0,0}; - -static UBool isICUVersionAtLeast(const UVersionInfo x) { - UVersionInfo v; - u_getVersion(v); - return (uprv_memcmp(v, x, U_MAX_VERSION_LENGTH) >= 0); -} -*/ //-------------------------------------------------------------------- // TransliteratorPointer @@ -272,6 +260,10 @@ UBool LegalGreek::isRho(UChar c) { } // AbbreviatedUnicodeSetIterator Interface --------------------------------------------- +// +// Iterate over a UnicodeSet, only returning a sampling of the contained code points. +// density is the approximate total number of code points to returned for the entire set. +// class AbbreviatedUnicodeSetIterator : public UnicodeSetIterator { public : @@ -281,18 +273,18 @@ public : void reset(UnicodeSet& set, UBool abb = FALSE, int32_t density = 100); /** - * ICU "poor man's RTTI", returns a UClassID for the actual class. + * ICU "poor man's RTTI", returns a UClassID for this class. */ - virtual inline UClassID getDynamicClassID() const { return getStaticClassID(); } + static inline UClassID getStaticClassID() { return (UClassID)&fgClassID; } /** - * ICU "poor man's RTTI", returns a UClassID for this class. + * ICU "poor man's RTTI", returns a UClassID for the actual class. */ - static inline UClassID getStaticClassID() { return (UClassID)&fgClassID; } + virtual inline UClassID getDynamicClassID() const { return getStaticClassID(); } private : UBool abbreviated; - int32_t perRange; + int32_t perRange; // The maximum number of code points to be returned from each range virtual void loadRange(int32_t range); /** @@ -448,7 +440,7 @@ UBool RTTest::isCamel(const UnicodeString& a) { // see if string is of the form aB; e.g. lower, then upper or title UChar32 cp; UBool haveLower = FALSE; - for (int32_t i = 0; i < a.length(); i += UTF_CHAR_LENGTH(cp)) { + for (int32_t i = 0; i < a.length(); i += U16_LENGTH(cp)) { cp = a.char32At(i); int8_t t = u_charType(cp); switch (t) { @@ -483,7 +475,7 @@ void RTTest::test(const UnicodeString& sourceRangeVal, UnicodeSet okAnyway("[^[:Letter:]]", status); if (U_FAILURE(status)) { - parent->errln("FAIL: Initializing UnicodeSet with [:Other:] or [^[:Letter:]]"); + parent->dataerrln("FAIL: Initializing UnicodeSet with [:Other:] or [^[:Letter:]] - Error: %s", u_errorName(status)); return; } @@ -525,7 +517,7 @@ void RTTest::test(const UnicodeString& sourceRangeVal, this->roundtripExclusionsSet.clear(); if (roundtripExclusions != NULL && strlen(roundtripExclusions) > 0) { - this->roundtripExclusionsSet.applyPattern(roundtripExclusions, status); + this->roundtripExclusionsSet.applyPattern(UnicodeString(roundtripExclusions, -1, US_INV), status); if (U_FAILURE(status)) { parent->errln("FAIL: UnicodeSet::applyPattern(%s)", roundtripExclusions); return; @@ -575,7 +567,7 @@ void RTTest::test2(UBool quickRt, int32_t density) { Transliterator::createInstance(transliteratorID, UTRANS_FORWARD, parseError, status)); if ((Transliterator *)sourceToTarget == NULL) { - parent->errln("FAIL: createInstance(" + transliteratorID + + parent->dataerrln("FAIL: createInstance(" + transliteratorID + ") returned NULL. Error: " + u_errorName(status) + "\n\tpreContext : " + prettify(parseError.preContext) + "\n\tpostContext : " + prettify(parseError.postContext)); @@ -964,12 +956,15 @@ void RTTest::logRoundTripFailure(const UnicodeString& from, 30FF ; 3.2 # KATAKANA DIGRAPH KOTO 31F0..31FF ; 3.2 # [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO + Unicode 5.2 added another Hiragana character: +1F200 ; 5.2 # SQUARE HIRAGANA HOKA + We will not add them to the rules until they are more supported (e.g. in fonts on Windows) A bug has been filed to remind us to do this: #1979. */ - -static const char KATAKANA[] = "[[[:katakana:][\\u30A1-\\u30FA\\u30FC]]-[\\u30FF\\u31F0-\\u31FF]]"; -static const char HIRAGANA[] = "[[[:hiragana:][\\u3040-\\u3094]]-[\\u3095-\\u3096\\u309F-\\u30A0]]"; + +static const char KATAKANA[] = "[[[:katakana:][\\u30A1-\\u30FA\\u30FC]]-[\\u30FF\\u31F0-\\u31FF]-[:^age=5.2:]]"; +static const char HIRAGANA[] = "[[[:hiragana:][\\u3040-\\u3094]]-[\\u3095-\\u3096\\u309F-\\u30A0\\U0001F200-\\U0001F2FF]-[:^age=5.2:]]"; static const char LENGTH[] = "[\\u30FC]"; static const char HALFWIDTH_KATAKANA[] = "[\\uFF65-\\uFF9D]"; static const char KATAKANA_ITERATION[] = "[\\u30FD\\u30FE]"; @@ -994,7 +989,7 @@ void TransliteratorRoundTripTest::TestHiragana() { RTTest test("Latin-Hiragana"); Legal *legal = new Legal(); test.test(UnicodeString("[a-zA-Z]", ""), - HIRAGANA, + UnicodeString(HIRAGANA, -1, US_INV), HIRAGANA_ITERATION, this, quick, legal); delete legal; } @@ -1008,7 +1003,7 @@ void TransliteratorRoundTripTest::TestKatakana() { strcat(temp, HALFWIDTH_KATAKANA); strcat(temp, "]"); test.test(UnicodeString("[a-zA-Z]", ""), - KATAKANA, + UnicodeString(KATAKANA, -1, US_INV), temp, this, quick, legal); delete legal; @@ -1036,7 +1031,7 @@ void TransliteratorRoundTripTest::TestHangul() { #define ASSERT_SUCCESS(status) {if (U_FAILURE(status)) { \ - errln("error at file %s, line %d, status = %s", __FILE__, __LINE__, \ + errcheckln(status, "error at file %s, line %d, status = %s", __FILE__, __LINE__, \ u_errorName(status)); \ return;}} @@ -1048,7 +1043,7 @@ static void writeStringInU8(FILE *out, const UnicodeString &s) { uint8_t bufForOneChar[10]; UBool isError = FALSE; int32_t destIdx = 0; - U8_APPEND(bufForOneChar, destIdx, sizeof(bufForOneChar), c, isError); + U8_APPEND(bufForOneChar, destIdx, (int32_t)sizeof(bufForOneChar), c, isError); fwrite(bufForOneChar, 1, destIdx, out); } } @@ -1058,24 +1053,16 @@ static void writeStringInU8(FILE *out, const UnicodeString &s) { void TransliteratorRoundTripTest::TestHan() { UErrorCode status = U_ZERO_ERROR; - - // TODO: getExemplars() exists only as a C API, taking a USet. - // The set API we need to use exists only on UnicodeSet, not on USet. - // Do a hacky cast, knowing that a USet is really a UnicodeSet in - // the implementation. Once USet gets the missing API, switch back - // to using that. - USet *USetExemplars = NULL; - USetExemplars = uset_open(0, 0); - USetExemplars = ulocdata_getExemplarSet(USetExemplars, "zh", 0, &status); + LocalULocaleDataPointer uld(ulocdata_open("zh",&status)); + LocalUSetPointer USetExemplars(ulocdata_getExemplarSet(uld.getAlias(), uset_openEmpty(), 0, ULOCDATA_ES_STANDARD, &status)); ASSERT_SUCCESS(status); - UnicodeSet *exemplars = (UnicodeSet *)USetExemplars; UnicodeString source; UChar32 c; int i; for (i=0; ;i++) { // Add all of the Chinese exemplar chars to the string "source". - c = exemplars->charAt(i); + c = uset_charAt(USetExemplars.getAlias(), i); if (c == (UChar32)-1) { break; } @@ -1102,19 +1089,19 @@ void TransliteratorRoundTripTest::TestHan() { pn->transliterate(target2); // verify that there are no marks - Transliterator *nfc = Transliterator::createInstance("nfc", UTRANS_FORWARD, status); + Transliterator *nfd = Transliterator::createInstance("nfd", UTRANS_FORWARD, status); ASSERT_SUCCESS(status); - UnicodeString nfced = target2; - nfc->transliterate(nfced); - UnicodeSet allMarks("[:mark:]", status); + UnicodeString nfded = target2; + nfd->transliterate(nfded); + UnicodeSet allMarks(UNICODE_STRING_SIMPLE("[\\u0304\\u0301\\u030C\\u0300\\u0306]"), status); // look only for Pinyin tone marks, not all marks (there are some others in there) ASSERT_SUCCESS(status); - assertFalse("NumericPinyin must contain no marks", allMarks.containsSome(nfced)); + assertFalse("NumericPinyin must contain no marks", allMarks.containsSome(nfded)); // verify roundtrip Transliterator *np = pn->createInverse(status); ASSERT_SUCCESS(status); - UnicodeString target3 = target; + UnicodeString target3 = target2; np->transliterate(target3); UBool roundtripOK = (target3.compare(target) == 0); assertTrue("NumericPinyin must roundtrip", roundtripOK); @@ -1126,30 +1113,33 @@ void TransliteratorRoundTripTest::TestHan() { writeStringInU8(out, target); fprintf(out, "\nPinyin-Numeric-Pinyin: "); writeStringInU8(out, target2); + fprintf(out, "\nNumeric-Pinyin-Pinyin: "); + writeStringInU8(out, target3); fprintf(out, "\n"); fclose(out); } delete hanTL; delete pn; - delete nfc; + delete nfd; delete np; - uset_close(USetExemplars); } void TransliteratorRoundTripTest::TestGreek() { - // weiv removed the test and the fiter - /* - if (isICUVersionAtLeast(ICU_30)) { - // We temporarily filter against Unicode 3.2, but we only do this - // before version 3.0. - errln("FAIL: TestGreek needs to be updated to remove Unicode 3.2 filter"); - return; - } else { - logln("Warning: TestGreek needs to be updated to remove Unicode 3.2 filter"); - } - */ + + // CLDR bug #1911: This test should be moved into CLDR. + // It is left in its current state as a regression test. + +// if (isICUVersionAtLeast(ICU_39)) { +// // We temporarily filter against Unicode 4.1, but we only do this +// // before version 3.4. +// errln("FAIL: TestGreek needs to be updated to remove delete the [:Age=4.0:] filter "); +// return; +// } else { +// logln("Warning: TestGreek needs to be updated to remove delete the section marked [:Age=4.0:] filter"); +// } + RTTest test("Latin-Greek"); LegalGreek *legal = new LegalGreek(TRUE); @@ -1159,7 +1149,7 @@ void TransliteratorRoundTripTest::TestGreek() { "\\u1D5D-\\u1D61" // Lm [5] MODIFIER LETTER SMALL BETA..MODIFIER LETTER SMALL CHI "\\u1D66-\\u1D6A" // L& [5] GREEK SUBSCRIPT SMALL LETTER BETA..GREEK SUBSCRIPT SMALL LETTER CHI "\\u03D7-\\u03EF" // \N{GREEK KAI SYMBOL}..\N{COPTIC SMALL LETTER DEI} - "]]", + "] & [:Age=4.0:]]", //UnicodeString("[[\\u003B\\u00B7[:Greek:]-[\\u0374\\u0385\\u1fcd\\u1fce\\u1fdd\\u1fde\\u1fed-\\u1fef\\u1ffd\\u03D7-\\u03EF]]&[:Age=3.2:]]", ""), @@ -1172,17 +1162,19 @@ void TransliteratorRoundTripTest::TestGreek() { void TransliteratorRoundTripTest::TestGreekUNGEGN() { - // weiv removed the test and the fiter - /* - if (isICUVersionAtLeast(ICU_30)) { - // We temporarily filter against Unicode 3.2, but we only do this - // before version 3.0. - errln("FAIL: TestGreekUNGEGN needs to be updated to remove Unicode 3.2 filter"); - return; - } else { - logln("Warning: TestGreekUNGEGN needs to be updated to remove Unicode 3.2 filter"); - } - */ + + // CLDR bug #1911: This test should be moved into CLDR. + // It is left in its current state as a regression test. + +// if (isICUVersionAtLeast(ICU_39)) { +// // We temporarily filter against Unicode 4.1, but we only do this +// // before version 3.4. +// errln("FAIL: TestGreek needs to be updated to remove delete the [:Age=4.0:] filter "); +// return; +// } else { +// logln("Warning: TestGreek needs to be updated to remove delete the section marked [:Age=4.0:] filter"); +// } + RTTest test("Latin-Greek/UNGEGN"); LegalGreek *legal = new LegalGreek(FALSE); @@ -1192,7 +1184,7 @@ void TransliteratorRoundTripTest::TestGreekUNGEGN() { "\\u1D5D-\\u1D61" // Lm [5] MODIFIER LETTER SMALL BETA..MODIFIER LETTER SMALL CHI "\\u1D66-\\u1D6A" // L& [5] GREEK SUBSCRIPT SMALL LETTER BETA..GREEK SUBSCRIPT SMALL LETTER CHI "\\u03D7-\\u03EF" // \N{GREEK KAI SYMBOL}..\N{COPTIC SMALL LETTER DEI} - "]]", + "] & [:Age=4.0:]]", //UnicodeString("[[\\u003B\\u00B7[:Greek:]-[\\u0374\\u0385\\u1fce\\u1fde\\u03D7-\\u03EF]]&[:Age=3.2:]]", ""), "[\\u0385\\u00B5\\u037A\\u03D0-\\uFFFF {\\u039C\\u03C0}]", /* roundtrip exclusions */ @@ -1202,17 +1194,19 @@ void TransliteratorRoundTripTest::TestGreekUNGEGN() { } void TransliteratorRoundTripTest::Testel() { - // weiv removed the test and the fiter - /* - if (isICUVersionAtLeast(ICU_30)) { - // We temporarily filter against Unicode 3.2, but we only do this - // before version 3.0. - errln("FAIL: Testel needs to be updated to remove Unicode 3.2 filter"); - return; - } else { - logln("Warning: Testel needs to be updated to remove Unicode 3.2 filter"); - } - */ + + // CLDR bug #1911: This test should be moved into CLDR. + // It is left in its current state as a regression test. + +// if (isICUVersionAtLeast(ICU_39)) { +// // We temporarily filter against Unicode 4.1, but we only do this +// // before version 3.4. +// errln("FAIL: TestGreek needs to be updated to remove delete the [:Age=4.0:] filter "); +// return; +// } else { +// logln("Warning: TestGreek needs to be updated to remove delete the section marked [:Age=4.0:] filter"); +// } + RTTest test("Latin-el"); LegalGreek *legal = new LegalGreek(FALSE); @@ -1222,7 +1216,7 @@ void TransliteratorRoundTripTest::Testel() { "\\u1D5D-\\u1D61" // Lm [5] MODIFIER LETTER SMALL BETA..MODIFIER LETTER SMALL CHI "\\u1D66-\\u1D6A" // L& [5] GREEK SUBSCRIPT SMALL LETTER BETA..GREEK SUBSCRIPT SMALL LETTER CHI "\\u03D7-\\u03EF" // \N{GREEK KAI SYMBOL}..\N{COPTIC SMALL LETTER DEI} - "]]", + "] & [:Age=4.0:]]", //UnicodeString("[[\\u003B\\u00B7[:Greek:]-[\\u0374\\u0385\\u1fce\\u1fde\\u03D7-\\u03EF]]&[:Age=3.2:]]", ""), "[\\u00B5\\u037A\\u03D0-\\uFFFF {\\u039C\\u03C0}]", /* exclusions */ @@ -1234,10 +1228,10 @@ void TransliteratorRoundTripTest::Testel() { void TransliteratorRoundTripTest::TestArabic() { - UnicodeString ARABIC("[\\u060C\\u061B\\u061F\\u0621\\u0627-\\u063A\\u0641-\\u0655\\u0660-\\u066C\\u067E\\u0686\\u0698\\u06A4\\u06AD\\u06AF\\u06CB-\\u06CC\\u06F0-\\u06F9]"); + UnicodeString ARABIC("[\\u060C\\u061B\\u061F\\u0621\\u0627-\\u063A\\u0641-\\u0655\\u0660-\\u066C\\u067E\\u0686\\u0698\\u06A4\\u06AD\\u06AF\\u06CB-\\u06CC\\u06F0-\\u06F9]", -1, US_INV); Legal *legal = new Legal(); RTTest test("Latin-Arabic"); - test.test("[a-zA-Z\\u02BE\\u02BF\\u207F]", ARABIC, "[a-zA-Z\\u02BE\\u02BF\\u207F]",this, quick, legal); // + test.test(UNICODE_STRING_SIMPLE("[a-zA-Z\\u02BE\\u02BF\\u207F]"), ARABIC, "[a-zA-Z\\u02BE\\u02BF\\u207F]",this, quick, legal); // delete legal; } class LegalHebrew : public Legal { @@ -1252,8 +1246,8 @@ public: }; LegalHebrew::LegalHebrew(UErrorCode& error){ - FINAL.applyPattern("[\\u05DA\\u05DD\\u05DF\\u05E3\\u05E5]", error); - NON_FINAL.applyPattern("[\\u05DB\\u05DE\\u05E0\\u05E4\\u05E6]", error); + FINAL.applyPattern(UNICODE_STRING_SIMPLE("[\\u05DA\\u05DD\\u05DF\\u05E3\\u05E5]"), error); + NON_FINAL.applyPattern(UNICODE_STRING_SIMPLE("[\\u05DB\\u05DE\\u05E0\\u05E4\\u05E6]"), error); LETTER.applyPattern("[:letter:]", error); } UBool LegalHebrew::is(const UnicodeString& sourceString)const{ @@ -1272,15 +1266,26 @@ UBool LegalHebrew::is(const UnicodeString& sourceString)const{ return TRUE; } void TransliteratorRoundTripTest::TestHebrew() { + // CLDR bug #1911: This test should be moved into CLDR. + // It is left in its current state as a regression test. +// if (isICUVersionAtLeast(ICU_39)) { +// // We temporarily filter against Unicode 4.1, but we only do this +// // before version 3.4. +// errln("FAIL: TestHebrew needs to be updated to remove delete the [:Age=4.0:] filter "); +// return; +// } else { +// logln("Warning: TestHebrew needs to be updated to remove delete the section marked [:Age=4.0:] filter"); +// } //long start = System.currentTimeMillis(); UErrorCode error = U_ZERO_ERROR; LegalHebrew* legal = new LegalHebrew(error); if(U_FAILURE(error)){ - errln("Could not construct LegalHebrew object. Error: %s", u_errorName(error)); + dataerrln("Could not construct LegalHebrew object. Error: %s", u_errorName(error)); return; } RTTest test("Latin-Hebrew"); - test.test("[a-zA-Z\\u02BC\\u02BB]", "[[:hebrew:]-[\\u05BD\\uFB00-\\uFBFF]]", "[\\u05F0\\u05F1\\u05F2]", this, quick, legal); + test.test(UNICODE_STRING_SIMPLE("[a-zA-Z\\u02BC\\u02BB]"), UNICODE_STRING_SIMPLE("[[[:hebrew:]-[\\u05BD\\uFB00-\\uFBFF]]&[:Age=4.0:]]"), "[\\u05F0\\u05F1\\u05F2]", this, quick, legal); + //showElapsed(start, "TestHebrew"); delete legal; } @@ -1305,26 +1310,8 @@ class LegalIndic :public Legal{ UnicodeSet sanskritStressSigns; UnicodeSet chandrabindu; -public: - LegalIndic(){ - UErrorCode status = U_ZERO_ERROR; - vowelSignSet.addAll( UnicodeSet("[\\u0902\\u0903\\u0904\\u093e-\\u094c\\u0962\\u0963]",status));/* Devanagari */ - vowelSignSet.addAll( UnicodeSet("[\\u0982\\u0983\\u09be-\\u09cc\\u09e2\\u09e3\\u09D7]",status));/* Bengali */ - vowelSignSet.addAll( UnicodeSet("[\\u0a02\\u0a03\\u0a3e-\\u0a4c\\u0a62\\u0a63\\u0a70\\u0a71]",status));/* Gurmukhi */ - vowelSignSet.addAll( UnicodeSet("[\\u0a82\\u0a83\\u0abe-\\u0acc\\u0ae2\\u0ae3]",status));/* Gujarati */ - vowelSignSet.addAll( UnicodeSet("[\\u0b02\\u0b03\\u0b3e-\\u0b4c\\u0b62\\u0b63\\u0b56\\u0b57]",status));/* Oriya */ - vowelSignSet.addAll( UnicodeSet("[\\u0b82\\u0b83\\u0bbe-\\u0bcc\\u0be2\\u0be3\\u0bd7]",status));/* Tamil */ - vowelSignSet.addAll( UnicodeSet("[\\u0c02\\u0c03\\u0c3e-\\u0c4c\\u0c62\\u0c63\\u0c55\\u0c56]",status));/* Telugu */ - vowelSignSet.addAll( UnicodeSet("[\\u0c82\\u0c83\\u0cbe-\\u0ccc\\u0ce2\\u0ce3\\u0cd5\\u0cd6]",status));/* Kannada */ - vowelSignSet.addAll( UnicodeSet("[\\u0d02\\u0d03\\u0d3e-\\u0d4c\\u0d62\\u0d63\\u0d57]",status));/* Malayalam */ - - avagraha.addAll(UnicodeSet("[\\u093d\\u09bd\\u0abd\\u0b3d\\u0cbd]",status)); - nukta.addAll(UnicodeSet("[\\u093c\\u09bc\\u0a3c\\u0abc\\u0b3c\\u0cbc]",status)); - virama.addAll(UnicodeSet("[\\u094d\\u09cd\\u0a4d\\u0acd\\u0b4d\\u0bcd\\u0c4d\\u0ccd\\u0d4d]",status)); - sanskritStressSigns.addAll(UnicodeSet("[\\u0951\\u0952\\u0953\\u0954]",status)); - chandrabindu.addAll(UnicodeSet("[\\u0901\\u0981\\u0A81\\u0b01\\u0c01]",status)); - - } +public: + LegalIndic(); virtual UBool is(const UnicodeString& sourceString) const; virtual ~LegalIndic() {}; }; @@ -1349,13 +1336,32 @@ UBool LegalIndic::is(const UnicodeString& sourceString) const{ } return TRUE; } +LegalIndic::LegalIndic(){ + UErrorCode status = U_ZERO_ERROR; + vowelSignSet.addAll( UnicodeSet("[\\u0902\\u0903\\u0904\\u093e-\\u094c\\u0962\\u0963]",status));/* Devanagari */ + vowelSignSet.addAll( UnicodeSet("[\\u0982\\u0983\\u09be-\\u09cc\\u09e2\\u09e3\\u09D7]",status));/* Bengali */ + vowelSignSet.addAll( UnicodeSet("[\\u0a02\\u0a03\\u0a3e-\\u0a4c\\u0a62\\u0a63\\u0a70\\u0a71]",status));/* Gurmukhi */ + vowelSignSet.addAll( UnicodeSet("[\\u0a82\\u0a83\\u0abe-\\u0acc\\u0ae2\\u0ae3]",status));/* Gujarati */ + vowelSignSet.addAll( UnicodeSet("[\\u0b02\\u0b03\\u0b3e-\\u0b4c\\u0b62\\u0b63\\u0b56\\u0b57]",status));/* Oriya */ + vowelSignSet.addAll( UnicodeSet("[\\u0b82\\u0b83\\u0bbe-\\u0bcc\\u0be2\\u0be3\\u0bd7]",status));/* Tamil */ + vowelSignSet.addAll( UnicodeSet("[\\u0c02\\u0c03\\u0c3e-\\u0c4c\\u0c62\\u0c63\\u0c55\\u0c56]",status));/* Telugu */ + vowelSignSet.addAll( UnicodeSet("[\\u0c82\\u0c83\\u0cbe-\\u0ccc\\u0ce2\\u0ce3\\u0cd5\\u0cd6]",status));/* Kannada */ + vowelSignSet.addAll( UnicodeSet("[\\u0d02\\u0d03\\u0d3e-\\u0d4c\\u0d62\\u0d63\\u0d57]",status));/* Malayalam */ + + avagraha.addAll(UnicodeSet("[\\u093d\\u09bd\\u0abd\\u0b3d\\u0cbd]",status)); + nukta.addAll(UnicodeSet("[\\u093c\\u09bc\\u0a3c\\u0abc\\u0b3c\\u0cbc]",status)); + virama.addAll(UnicodeSet("[\\u094d\\u09cd\\u0a4d\\u0acd\\u0b4d\\u0bcd\\u0c4d\\u0ccd\\u0d4d]",status)); + sanskritStressSigns.addAll(UnicodeSet("[\\u0951\\u0952\\u0953\\u0954\\u097d]",status)); + chandrabindu.addAll(UnicodeSet("[\\u0901\\u0981\\u0A81\\u0b01\\u0c01]",status)); + + } static const char latinForIndic[] = "[['.0-9A-Za-z~\\u00C0-\\u00C5\\u00C7-\\u00CF\\u00D1-\\u00D6\\u00D9-\\u00DD" "\\u00E0-\\u00E5\\u00E7-\\u00EF\\u00F1-\\u00F6\\u00F9-\\u00FD\\u00FF-\\u010F" "\\u0112-\\u0125\\u0128-\\u0130\\u0134-\\u0137\\u0139-\\u013E\\u0143-\\u0148" "\\u014C-\\u0151\\u0154-\\u0165\\u0168-\\u017E\\u01A0-\\u01A1\\u01AF-\\u01B0" "\\u01CD-\\u01DC\\u01DE-\\u01E3\\u01E6-\\u01ED\\u01F0\\u01F4-\\u01F5\\u01F8-\\u01FB" - "\\u0200-\\u021B\\u021E-\\u021F\\u0226-\\u0233\\u0303-\\u0304\\u0306\\u0314-\\u0315" + "\\u0200-\\u021B\\u021E-\\u021F\\u0226-\\u0233\\u0294\\u0303-\\u0304\\u0306\\u0314-\\u0315" "\\u0325\\u040E\\u0419\\u0439\\u045E\\u04C1-\\u04C2\\u04D0-\\u04D1\\u04D6-\\u04D7" "\\u04E2-\\u04E3\\u04EE-\\u04EF\\u1E00-\\u1E99\\u1EA0-\\u1EF9\\u1F01\\u1F03\\u1F05" "\\u1F07\\u1F09\\u1F0B\\u1F0D\\u1F0F\\u1F11\\u1F13\\u1F15\\u1F19\\u1F1B\\u1F1D\\u1F21" @@ -1379,15 +1385,24 @@ void TransliteratorRoundTripTest::TestDevanagariLatin() { errln("FAIL: could not create the Inverse:-( \n"); } }else { - errln("FAIL: could not create the transliterator. Error: %s\n", u_errorName(status)); + dataerrln("FAIL: could not create the transliterator. Error: %s\n", u_errorName(status)); } } RTTest test("Latin-Devanagari"); Legal *legal = new LegalIndic(); - + // CLDR bug #1911: This test should be moved into CLDR. + // It is left in its current state as a regression test. +// if (isICUVersionAtLeast(ICU_39)) { +// // We temporarily filter against Unicode 4.1, but we only do this +// // before version 3.4. +// errln("FAIL: TestDevanagariLatin needs to be updated to remove delete the [:Age=4.1:] filter "); +// return; +// } else { +// logln("Warning: TestDevanagariLatin needs to be updated to remove delete the section marked [:Age=4.1:] filter"); +// } test.test(UnicodeString(latinForIndic, ""), - UnicodeString("[[:Devanagari:][\\u094d][\\u0964\\u0965]]", ""), "[\\u0965\\u0904]", this, quick, + UnicodeString("[[[:Devanagari:][\\u094d][\\u0964\\u0965]]&[:Age=4.1:]-[\\u0970]]", ""), "[\\u0965\\u0904]", this, quick, legal, 50); delete legal; @@ -1396,96 +1411,97 @@ void TransliteratorRoundTripTest::TestDevanagariLatin() { /* Defined this way for HP/UX11CC :-( */ static const int32_t INTER_INDIC_ARRAY_WIDTH = 4; static const char * const interIndicArray[] = { - "BENGALI-DEVANAGARI", "[:BENGALI:]", "[:Devanagari:]", - "[\\u0904\\u0951-\\u0954\\u0943-\\u0949\\u094a\\u0962\\u0963\\u090D\\u090e\\u0911\\u0912\\u0929\\u0933\\u0934\\u0935\\u093d\\u0950\\u0958\\u0959\\u095a\\u095b\\u095e\\u09f0\\u09f1\\u09f2-\\u09fa]", /*roundtrip exclusions*/ - "DEVANAGARI-BENGALI", "[:Devanagari:]", "[:BENGALI:]", - "[\\u0951-\\u0954\\u0951-\\u0954\\u09D7\\u090D\\u090e\\u0911\\u0912\\u0929\\u0933\\u0934\\u0935\\u093d\\u0950\\u0958\\u0959\\u095a\\u095b\\u095e\\u09f0\\u09f1\\u09f2-\\u09fa]", /*roundtrip exclusions*/ + "BENGALI-DEVANAGARI", "[:BENGALI:]", "[[:Devanagari:]-[\\u0970]]", + "[\\u0904\\u0951-\\u0954\\u0943-\\u0949\\u094a\\u0962\\u0963\\u090D\\u090e\\u0911\\u0912\\u0929\\u0933\\u0934\\u0935\\u093d\\u0950\\u0958\\u0959\\u095a\\u095b\\u095e\\u097d]", /*roundtrip exclusions*/ - "GURMUKHI-DEVANAGARI", "[:GURMUKHI:]", "[:Devanagari:]", - "[\\u0904\\u0901\\u0902\\u0936\\u0933\\u0951-\\u0954\\u0902\\u0903\\u0943-\\u0949\\u094a\\u0962\\u0963\\u090B\\u090C\\u090D\\u090e\\u0911\\u0912\\u0934\\u0937\\u093D\\u0950\\u0960\\u0961\\u0a72\\u0a73\\u0a74]", /*roundtrip exclusions*/ + "DEVANAGARI-BENGALI", "[[:Devanagari:]-[\\u0970]]", "[:BENGALI:]", + "[\\u0951-\\u0954\\u0951-\\u0954\\u09D7\\u090D\\u090e\\u0911\\u0912\\u0929\\u0933\\u0934\\u0935\\u093d\\u0950\\u0958\\u0959\\u095a\\u095b\\u095e\\u09f0\\u09f1\\u09f2-\\u09fa\\u09ce]", /*roundtrip exclusions*/ - "DEVANAGARI-GURMUKHI", "[:Devanagari:]", "[:GURMUKHI:]", + "GURMUKHI-DEVANAGARI", "[:GURMUKHI:]", "[[:Devanagari:]-[\\u0970]]", + "[\\u0904\\u0901\\u0902\\u0936\\u0933\\u0951-\\u0954\\u0902\\u0903\\u0943-\\u0949\\u094a\\u0962\\u0963\\u090B\\u090C\\u090D\\u090e\\u0911\\u0912\\u0934\\u0937\\u093D\\u0950\\u0960\\u0961\\u097d]", /*roundtrip exclusions*/ + + "DEVANAGARI-GURMUKHI", "[[:Devanagari:]-[\\u0970]]", "[:GURMUKHI:]", "[\\u0904\\u0A02\\u0946\\u0A5C\\u0951-\\u0954\\u0A70\\u0A71\\u090B\\u090C\\u090D\\u090e\\u0911\\u0912\\u0934\\u0937\\u093D\\u0950\\u0960\\u0961\\u0a72\\u0a73\\u0a74]", /*roundtrip exclusions*/ - "GUJARATI-DEVANAGARI", "[:GUJARATI:]", "[:Devanagari:]", - "[\\u0946\\u094A\\u0962\\u0963\\u0951-\\u0954\\u0961\\u090c\\u090e\\u0912]", /*roundtrip exclusions*/ + "GUJARATI-DEVANAGARI", "[:GUJARATI:]", "[[:Devanagari:]-[\\u0970]]", + "[\\u0946\\u094A\\u0962\\u0963\\u0951-\\u0954\\u0961\\u090c\\u090e\\u0912\\u097d]", /*roundtrip exclusions*/ - "DEVANAGARI-GUJARATI", "[:Devanagari:]", "[:GUJARATI:]", + "DEVANAGARI-GUJARATI", "[[:Devanagari:]-[\\u0970]]", "[:GUJARATI:]", "[\\u0951-\\u0954\\u0961\\u090c\\u090e\\u0912]", /*roundtrip exclusions*/ - "ORIYA-DEVANAGARI", "[:ORIYA:]", "[:Devanagari:]", - "[\\u0904\\u0943-\\u094a\\u0962\\u0963\\u0951-\\u0954\\u0950\\u090D\\u090e\\u0912\\u0911\\u0931\\u0935]", /*roundtrip exclusions*/ + "ORIYA-DEVANAGARI", "[:ORIYA:]", "[[:Devanagari:]-[\\u0970]]", + "[\\u0904\\u0943-\\u094a\\u0962\\u0963\\u0951-\\u0954\\u0950\\u090D\\u090e\\u0912\\u0911\\u0931\\u0935\\u097d]", /*roundtrip exclusions*/ - "DEVANAGARI-ORIYA", "[:Devanagari:]", "[:ORIYA:]", + "DEVANAGARI-ORIYA", "[[:Devanagari:]-[\\u0970]]", "[:ORIYA:]", "[\\u0b5f\\u0b56\\u0b57\\u0b70\\u0b71\\u0950\\u090D\\u090e\\u0912\\u0911\\u0931]", /*roundtrip exclusions*/ - "Tamil-DEVANAGARI", "[:tamil:]", "[:Devanagari:]", - "[\\u0901\\u0904\\u093c\\u0943-\\u094a\\u0951-\\u0954\\u0962\\u0963\\u090B\\u090C\\u090D\\u0911\\u0916\\u0917\\u0918\\u091B\\u091D\\u0920\\u0921\\u0922\\u0925\\u0926\\u0927\\u092B\\u092C\\u092D\\u0936\\u093d\\u0950[\\u0958-\\u0961]]", /*roundtrip exclusions*/ + "Tamil-DEVANAGARI", "[:tamil:]", "[[:Devanagari:]-[\\u0970]]", + "[\\u0901\\u0904\\u093c\\u0943-\\u094a\\u0951-\\u0954\\u0962\\u0963\\u090B\\u090C\\u090D\\u0911\\u0916\\u0917\\u0918\\u091B\\u091D\\u0920\\u0921\\u0922\\u0925\\u0926\\u0927\\u092B\\u092C\\u092D\\u0936\\u093d\\u0950[\\u0958-\\u0961]\\u097d]", /*roundtrip exclusions*/ - "DEVANAGARI-Tamil", "[:Devanagari:]", "[:tamil:]", - "[\\u0bd7]", /*roundtrip exclusions*/ + "DEVANAGARI-Tamil", "[[:Devanagari:]-[\\u0970]]", "[:tamil:]", + "[\\u0bd7\\u0BF0\\u0BF1\\u0BF2]", /*roundtrip exclusions*/ - "Telugu-DEVANAGARI", "[:telugu:]", "[:Devanagari:]", - "[\\u0904\\u093c\\u0950\\u0945\\u0949\\u0951-\\u0954\\u0962\\u0963\\u090D\\u0911\\u093d\\u0929\\u0934[\\u0958-\\u095f]]", /*roundtrip exclusions*/ + "Telugu-DEVANAGARI", "[:telugu:]", "[[:Devanagari:]-[\\u0970]]", + "[\\u0904\\u093c\\u0950\\u0945\\u0949\\u0951-\\u0954\\u0962\\u0963\\u090D\\u0911\\u093d\\u0929\\u0934[\\u0958-\\u095f]\\u097d]", /*roundtrip exclusions*/ - "DEVANAGARI-TELUGU", "[:Devanagari:]", "[:TELUGU:]", + "DEVANAGARI-TELUGU", "[[:Devanagari:]-[\\u0970]]", "[:TELUGU:]", "[\\u0c55\\u0c56\\u0950\\u090D\\u0911\\u093d\\u0929\\u0934[\\u0958-\\u095f]]", /*roundtrip exclusions*/ - "KANNADA-DEVANAGARI", "[:KANNADA:]", "[:Devanagari:]", - "[\\u0901\\u0904\\u0946\\u093c\\u0950\\u0945\\u0949\\u0951-\\u0954\\u0962\\u0963\\u0950\\u090D\\u0911\\u093d\\u0929\\u0934[\\u0958-\\u095f]]", /*roundtrip exclusions*/ + "KANNADA-DEVANAGARI", "[:KANNADA:]", "[[:Devanagari:]-[\\u0970]]", + "[\\u0901\\u0904\\u0946\\u093c\\u0950\\u0945\\u0949\\u0951-\\u0954\\u0962\\u0963\\u0950\\u090D\\u0911\\u093d\\u0929\\u0934[\\u0958-\\u095f]\\u097d]", /*roundtrip exclusions*/ - "DEVANAGARI-KANNADA", "[:Devanagari:]", "[:KANNADA:]", + "DEVANAGARI-KANNADA", "[[:Devanagari:]-[\\u0970]]", "[:KANNADA:]", "[{\\u0cb0\\u0cbc}{\\u0cb3\\u0cbc}\\u0cde\\u0cd5\\u0cd6\\u0950\\u090D\\u0911\\u093d\\u0929\\u0934[\\u0958-\\u095f]]", /*roundtrip exclusions*/ - "MALAYALAM-DEVANAGARI", "[:MALAYALAM:]", "[:Devanagari:]", - "[\\u0901\\u0904\\u094a\\u094b\\u094c\\u093c\\u0950\\u0944\\u0945\\u0949\\u0951-\\u0954\\u0962\\u0963\\u090D\\u0911\\u093d\\u0929\\u0934[\\u0958-\\u095f]]", /*roundtrip exclusions*/ + "MALAYALAM-DEVANAGARI", "[:MALAYALAM:]", "[[:Devanagari:]-[\\u0970]]", + "[\\u0901\\u0904\\u094a\\u094b\\u094c\\u093c\\u0950\\u0944\\u0945\\u0949\\u0951-\\u0954\\u0962\\u0963\\u090D\\u0911\\u093d\\u0929\\u0934[\\u0958-\\u095f]\\u097d]", /*roundtrip exclusions*/ - "DEVANAGARI-MALAYALAM", "[:Devanagari:]", "[:MALAYALAM:]", + "DEVANAGARI-MALAYALAM", "[[:Devanagari:]-[\\u0970]]", "[:MALAYALAM:]", "[\\u0d4c\\u0d57\\u0950\\u090D\\u0911\\u093d\\u0929\\u0934[\\u0958-\\u095f]]", /*roundtrip exclusions*/ "GURMUKHI-BENGALI", "[:GURMUKHI:]", "[:BENGALI:]", - "[\\u0981\\u0982\\u09b6\\u09e2\\u09e3\\u09c3\\u09c4\\u09d7\\u098B\\u098C\\u09B7\\u09E0\\u09E1\\u09F0\\u09F1\\u09f2-\\u09fa]", /*roundtrip exclusions*/ + "[\\u0981\\u0982\\u09b6\\u09e2\\u09e3\\u09c3\\u09c4\\u09d7\\u098B\\u098C\\u09B7\\u09E0\\u09E1\\u09F0\\u09F1\\u09f2-\\u09fa\\u09ce]", /*roundtrip exclusions*/ "BENGALI-GURMUKHI", "[:BENGALI:]", "[:GURMUKHI:]", "[\\u0A02\\u0a5c\\u0a47\\u0a70\\u0a71\\u0A33\\u0A35\\u0A59\\u0A5A\\u0A5B\\u0A5E\\u0A72\\u0A73\\u0A74]", /*roundtrip exclusions*/ "GUJARATI-BENGALI", "[:GUJARATI:]", "[:BENGALI:]", - "[\\u09d7\\u09e2\\u09e3\\u098c\\u09e1\\u09f0\\u09f1\\u09f2-\\u09fa]", /*roundtrip exclusions*/ + "[\\u09d7\\u09e2\\u09e3\\u098c\\u09e1\\u09f0\\u09f1\\u09f2-\\u09fa\\u09ce]", /*roundtrip exclusions*/ "BENGALI-GUJARATI", "[:BENGALI:]", "[:GUJARATI:]", "[\\u0A82\\u0a83\\u0Ac9\\u0Ac5\\u0ac7\\u0A8D\\u0A91\\u0AB3\\u0AB5\\u0ABD\\u0AD0]", /*roundtrip exclusions*/ "ORIYA-BENGALI", "[:ORIYA:]", "[:BENGALI:]", - "[\\u09c4\\u09e2\\u09e3\\u09f0\\u09f1\\u09f2-\\u09fa]", /*roundtrip exclusions*/ + "[\\u09c4\\u09e2\\u09e3\\u09f0\\u09f1\\u09f2-\\u09fa\\u09ce]", /*roundtrip exclusions*/ "BENGALI-ORIYA", "[:BENGALI:]", "[:ORIYA:]", "[\\u0b35\\u0b71\\u0b5f\\u0b56\\u0b33\\u0b3d]", /*roundtrip exclusions*/ "Tamil-BENGALI", "[:tamil:]", "[:BENGALI:]", - "[\\u0981\\u09bc\\u09c3\\u09c4\\u09e2\\u09e3\\u09f0\\u09f1\\u098B\\u098C\\u0996\\u0997\\u0998\\u099B\\u099D\\u09A0\\u09A1\\u09A2\\u09A5\\u09A6\\u09A7\\u09AB\\u09AC\\u09AD\\u09B6\\u09DC\\u09DD\\u09DF\\u09E0\\u09E1\\u09f2-\\u09fa]", /*roundtrip exclusions*/ + "[\\u0981\\u09bc\\u09c3\\u09c4\\u09e2\\u09e3\\u09f0\\u09f1\\u098B\\u098C\\u0996\\u0997\\u0998\\u099B\\u099D\\u09A0\\u09A1\\u09A2\\u09A5\\u09A6\\u09A7\\u09AB\\u09AC\\u09AD\\u09B6\\u09DC\\u09DD\\u09DF\\u09E0\\u09E1\\u09f2-\\u09fa\\u09ce]", /*roundtrip exclusions*/ "BENGALI-Tamil", "[:BENGALI:]", "[:tamil:]", - "[\\u0bc6\\u0bc7\\u0bca\\u0B8E\\u0B92\\u0BA9\\u0BB1\\u0BB3\\u0BB4\\u0BB5]", /*roundtrip exclusions*/ + "[\\u0bc6\\u0bc7\\u0bca\\u0B8E\\u0B92\\u0BA9\\u0BB1\\u0BB3\\u0BB4\\u0BB5\\u0BF0\\u0BF1\\u0BF2]", /*roundtrip exclusions*/ "Telugu-BENGALI", "[:telugu:]", "[:BENGALI:]", - "[\\u09e2\\u09e3\\u09bc\\u09d7\\u09f0\\u09f1\\u09dc\\u09dd\\u09df\\u09f2-\\u09fa]", /*roundtrip exclusions*/ + "[\\u09e2\\u09e3\\u09bc\\u09d7\\u09f0\\u09f1\\u09dc\\u09dd\\u09df\\u09f2-\\u09fa\\u09ce]", /*roundtrip exclusions*/ "BENGALI-TELUGU", "[:BENGALI:]", "[:TELUGU:]", "[\\u0c55\\u0c56\\u0c47\\u0c46\\u0c4a\\u0C0E\\u0C12\\u0C31\\u0C33\\u0C35]", /*roundtrip exclusions*/ "KANNADA-BENGALI", "[:KANNADA:]", "[:BENGALI:]", - "[\\u0981\\u09e2\\u09e3\\u09bc\\u09d7\\u09dc\\u09dd\\u09df\\u09f0\\u09f1\\u09f2-\\u09fa]", /*roundtrip exclusions*/ + "[\\u0981\\u09e2\\u09e3\\u09bc\\u09d7\\u09dc\\u09dd\\u09df\\u09f0\\u09f1\\u09f2-\\u09fa\\u09ce]", /*roundtrip exclusions*/ "BENGALI-KANNADA", "[:BENGALI:]", "[:KANNADA:]", "[{\\u0cb0\\u0cbc}{\\u0cb3\\u0cbc}\\u0cc6\\u0cca\\u0cd5\\u0cd6\\u0cc7\\u0C8E\\u0C92\\u0CB1\\u0cb3\\u0cb5\\u0cde]", /*roundtrip exclusions*/ "MALAYALAM-BENGALI", "[:MALAYALAM:]", "[:BENGALI:]", - "[\\u0981\\u09e2\\u09e3\\u09bc\\u09c4\\u09f0\\u09f1\\u09dc\\u09dd\\u09df\\u09dc\\u09dd\\u09df\\u09f2-\\u09fa]", /*roundtrip exclusions*/ + "[\\u0981\\u09e2\\u09e3\\u09bc\\u09c4\\u09f0\\u09f1\\u09dc\\u09dd\\u09df\\u09dc\\u09dd\\u09df\\u09f2-\\u09fa\\u09ce]", /*roundtrip exclusions*/ "BENGALI-MALAYALAM", "[:BENGALI:]", "[:MALAYALAM:]", "[\\u0d46\\u0d4a\\u0d47\\u0d31-\\u0d35\\u0d0e\\u0d12]", /*roundtrip exclusions*/ - + "GUJARATI-GURMUKHI", "[:GUJARATI:]", "[:GURMUKHI:]", "[\\u0A02\\u0ab3\\u0ab6\\u0A70\\u0a71\\u0a82\\u0a83\\u0ac3\\u0ac4\\u0ac5\\u0ac9\\u0a5c\\u0a72\\u0a73\\u0a74\\u0a8b\\u0a8d\\u0a91\\u0abd]", /*roundtrip exclusions*/ @@ -1502,7 +1518,7 @@ static const char * const interIndicArray[] = { "[\\u0A01\\u0A02\\u0a33\\u0a36\\u0a3c\\u0a70\\u0a71\\u0a47\\u0A16\\u0A17\\u0A18\\u0A1B\\u0A1D\\u0A20\\u0A21\\u0A22\\u0A25\\u0A26\\u0A27\\u0A2B\\u0A2C\\u0A2D\\u0A59\\u0A5A\\u0A5B\\u0A5C\\u0A5E\\u0A72\\u0A73\\u0A74]", /*roundtrip exclusions*/ "GURMUKHI-TAMIL", "[:GURMUKHI:]", "[:TAMIL:]", - "[\\u0b82\\u0bc6\\u0bca\\u0bd7\\u0bb7\\u0bb3\\u0b83\\u0B8E\\u0B92\\u0BA9\\u0BB1\\u0BB4]", /*roundtrip exclusions*/ + "[\\u0b82\\u0bc6\\u0bca\\u0bd7\\u0bb7\\u0bb3\\u0b83\\u0B8E\\u0B92\\u0BA9\\u0BB1\\u0BB4\\u0bb6\\u0BF0\\u0BF1\\u0BF2]", /*roundtrip exclusions*/ "TELUGU-GURMUKHI", "[:TELUGU:]", "[:GURMUKHI:]", "[\\u0A02\\u0a33\\u0a36\\u0a3c\\u0a70\\u0a71\\u0A59\\u0A5A\\u0A5B\\u0A5C\\u0A5E\\u0A72\\u0A73\\u0A74]", /*roundtrip exclusions*/ @@ -1532,7 +1548,7 @@ static const char * const interIndicArray[] = { "[\\u0A81\\u0a8c\\u0abc\\u0ac3\\u0Ac4\\u0Ac5\\u0Ac9\\u0Ac7\\u0A8B\\u0A8D\\u0A91\\u0A96\\u0A97\\u0A98\\u0A9B\\u0A9D\\u0AA0\\u0AA1\\u0AA2\\u0AA5\\u0AA6\\u0AA7\\u0AAB\\u0AAC\\u0AAD\\u0AB6\\u0ABD\\u0AD0\\u0AE0\\u0AE1]", /*roundtrip exclusions*/ "GUJARATI-TAMIL", "[:GUJARATI:]", "[:TAMIL:]", - "[\\u0Bc6\\u0Bca\\u0Bd7\\u0B8E\\u0B92\\u0BA9\\u0BB1\\u0BB4]", /*roundtrip exclusions*/ + "[\\u0Bc6\\u0Bca\\u0Bd7\\u0B8E\\u0B92\\u0BA9\\u0BB1\\u0BB4\\u0BF0\\u0BF1\\u0BF2]", /*roundtrip exclusions*/ "TELUGU-GUJARATI", "[:TELUGU:]", "[:GUJARATI:]", "[\\u0abc\\u0Ac5\\u0Ac9\\u0A8D\\u0A91\\u0ABD\\u0Ad0]", /*roundtrip exclusions*/ @@ -1556,7 +1572,7 @@ static const char * const interIndicArray[] = { "[\\u0B01\\u0b3c\\u0b43\\u0b56\\u0B0B\\u0B0C\\u0B16\\u0B17\\u0B18\\u0B1B\\u0B1D\\u0B20\\u0B21\\u0B22\\u0B25\\u0B26\\u0B27\\u0B2B\\u0B2C\\u0B2D\\u0B36\\u0B3D\\u0B5C\\u0B5D\\u0B5F\\u0B60\\u0B61\\u0b70\\u0b71]", /*roundtrip exclusions*/ "ORIYA-TAMIL", "[:ORIYA:]", "[:TAMIL:]", - "[\\u0bc6\\u0bca\\u0bc7\\u0B8E\\u0B92\\u0BA9\\u0BB1\\u0BB4\\u0BB5]", /*roundtrip exclusions*/ + "[\\u0bc6\\u0bca\\u0bc7\\u0B8E\\u0B92\\u0BA9\\u0BB1\\u0BB4\\u0BB5\\u0BF0\\u0BF1\\u0BF2]", /*roundtrip exclusions*/ "TELUGU-ORIYA", "[:TELUGU:]", "[:ORIYA:]", "[\\u0b3c\\u0b57\\u0b56\\u0B3D\\u0B5C\\u0B5D\\u0B5F\\u0b70\\u0b71]", /*roundtrip exclusions*/ @@ -1577,19 +1593,19 @@ static const char * const interIndicArray[] = { "[\\u0D47\\u0D46\\u0D4a\\u0D0E\\u0D12\\u0D31\\u0D34\\u0D35]", /*roundtrip exclusions*/ "TELUGU-TAMIL", "[:TELUGU:]", "[:TAMIL:]", - "[\\u0bd7\\u0ba9\\u0bb4]", /*roundtrip exclusions*/ + "[\\u0bd7\\u0ba9\\u0bb4\\u0BF0\\u0BF1\\u0BF2]", /*roundtrip exclusions*/ "TAMIL-TELUGU", "[:TAMIL:]", "[:TELUGU:]", "[\\u0C01\\u0c43\\u0c44\\u0c46\\u0c47\\u0c55\\u0c56\\u0c66\\u0C0B\\u0C0C\\u0C16\\u0C17\\u0C18\\u0C1B\\u0C1D\\u0C20\\u0C21\\u0C22\\u0C25\\u0C26\\u0C27\\u0C2B\\u0C2C\\u0C2D\\u0C36\\u0C60\\u0C61]", /*roundtrip exclusions*/ "KANNADA-TAMIL", "[:KANNADA:]", "[:TAMIL:]", - "[\\u0bd7\\u0bc6\\u0ba9\\u0bb4]", /*roundtrip exclusions*/ + "[\\u0bd7\\u0bc6\\u0ba9\\u0bb4\\u0BF0\\u0BF1\\u0BF2]", /*roundtrip exclusions*/ "TAMIL-KANNADA", "[:TAMIL:]", "[:KANNADA:]", "[\\u0cc3\\u0cc4\\u0cc6\\u0cc7\\u0cd5\\u0cd6\\u0C8B\\u0C8C\\u0C96\\u0C97\\u0C98\\u0C9B\\u0C9D\\u0CA0\\u0CA1\\u0CA2\\u0CA5\\u0CA6\\u0CA7\\u0CAB\\u0CAC\\u0CAD\\u0CB6\\u0cbc\\u0cbd\\u0CDE\\u0CE0\\u0CE1]", /*roundtrip exclusions*/ "MALAYALAM-TAMIL", "[:MALAYALAM:]", "[:TAMIL:]", - "[\\u0ba9]", /*roundtrip exclusions*/ + "[\\u0ba9\\u0BF0\\u0BF1\\u0BF2]", /*roundtrip exclusions*/ "TAMIL-MALAYALAM", "[:TAMIL:]", "[:MALAYALAM:]", "[\\u0d43\\u0d12\\u0D0B\\u0D0C\\u0D16\\u0D17\\u0D18\\u0D1B\\u0D1D\\u0D20\\u0D21\\u0D22\\u0D25\\u0D26\\u0D27\\u0D2B\\u0D2C\\u0D2D\\u0D36\\u0D60\\u0D61]", /*roundtrip exclusions*/ @@ -1611,31 +1627,30 @@ static const char * const interIndicArray[] = { "KANNADA-MALAYALAM", "[:KANNADA:]", "[:MALAYALAM:]", "[\\u0d4c\\u0d57\\u0d46\\u0D34]", /*roundtrip exclusions*/ - + "Latin-Bengali",latinForIndic, "[[:Bengali:][\\u0964\\u0965]]", - "[\\u0965\\u09f0-\\u09fa]" /*roundtrip exclusions*/ , - + "[\\u0965\\u09f0-\\u09fa\\u09ce]" /*roundtrip exclusions*/ , + "Latin-Gurmukhi", latinForIndic, "[[:Gurmukhi:][\\u0964\\u0965]]", "[\\u0a01\\u0965\\u0a02\\u0a72\\u0a73\\u0a74]" /*roundtrip exclusions*/, - + "Latin-Gujarati",latinForIndic, "[[:Gujarati:][\\u0964\\u0965]]", "[\\u0965]" /*roundtrip exclusions*/, - + "Latin-Oriya",latinForIndic, "[[:Oriya:][\\u0964\\u0965]]", "[\\u0965\\u0b70]" /*roundtrip exclusions*/, - + "Latin-Tamil",latinForIndic, "[:Tamil:]", - NULL /*roundtrip exclusions*/, - + "[\\u0BF0\\u0BF1\\u0BF2]" /*roundtrip exclusions*/, + "Latin-Telugu",latinForIndic, "[:Telugu:]", NULL /*roundtrip exclusions*/, - + "Latin-Kannada",latinForIndic, "[:Kannada:]", NULL /*roundtrip exclusions*/, - + "Latin-Malayalam",latinForIndic, "[:Malayalam:]", NULL /*roundtrip exclusions*/ - }; void TransliteratorRoundTripTest::TestDebug(const char* name,const char fromSet[], @@ -1653,18 +1668,42 @@ void TransliteratorRoundTripTest::TestInterIndic() { logln("Testing only 5 of %i. Skipping rest (use -e for exhaustive)",num); num = 5; } + // CLDR bug #1911: This test should be moved into CLDR. + // It is left in its current state as a regression test. +// if (isICUVersionAtLeast(ICU_39)) { +// // We temporarily filter against Unicode 4.1, but we only do this +// // before version 3.4. +// errln("FAIL: TestInterIndic needs to be updated to remove delete the [:Age=4.1:] filter "); +// return; +// } else { +// logln("Warning: TestInterIndic needs to be updated to remove delete the section marked [:Age=4.1:] filter"); +// } for(int i = 0; i < num;i++){ RTTest test(interIndicArray[i*INTER_INDIC_ARRAY_WIDTH + 0]); Legal *legal = new LegalIndic(); - + logln(UnicodeString("Stress testing ") + interIndicArray[i*INTER_INDIC_ARRAY_WIDTH + 0]); + /* Uncomment lines below when transliterator is fixed */ + /* test.test( interIndicArray[i*INTER_INDIC_ARRAY_WIDTH + 1], interIndicArray[i*INTER_INDIC_ARRAY_WIDTH + 2], interIndicArray[i*INTER_INDIC_ARRAY_WIDTH + 3], // roundtrip exclusions this, quick, legal, 50); - + */ + /* comment lines below when transliterator is fixed */ + // start + UnicodeString source("["); + source.append(interIndicArray[i*INTER_INDIC_ARRAY_WIDTH + 1]); + source.append(" & [:Age=4.1:]]"); + UnicodeString target("["); + target.append(interIndicArray[i*INTER_INDIC_ARRAY_WIDTH + 2]); + target.append(" & [:Age=4.1:]]"); + test.test( source, + target, + interIndicArray[i*INTER_INDIC_ARRAY_WIDTH + 3], // roundtrip exclusions + this, quick, legal, 50); + // end delete legal; } - } // end indic tests ----------------------------------------------------------