+// © 2016 and later: Unicode, Inc. and others.
+// License & terms of use: http://www.unicode.org/copyright.html
/*
**********************************************************************
-* Copyright (C) 1999-2008, International Business Machines
+* Copyright (C) 1999-2016, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
* Date Name Description
#include "unicode/ustring.h"
#include "unicode/usetiter.h"
#include "unicode/uscript.h"
+#include "unicode/utf16.h"
#include "cpdtrans.h"
#include "nultrans.h"
#include "rbt.h"
TESTCASE(62,TestAnchorMasking);
TESTCASE(63,TestDisplayName);
TESTCASE(64,TestSpecialCases);
+#if !UCONFIG_NO_FILE_IO
TESTCASE(65,TestIncrementalProgress);
+#endif
TESTCASE(66,TestSurrogateCasing);
TESTCASE(67,TestFunction);
TESTCASE(68,TestInvalidBackRef);
TESTCASE(71,TestAnyX);
TESTCASE(72,TestSourceTargetSet);
TESTCASE(73,TestGurmukhiDevanagari);
- TESTCASE(74,TestRuleWhitespace);
+ TESTCASE(74,TestPatternWhiteSpace);
TESTCASE(75,TestAllCodepoints);
TESTCASE(76,TestBoilerplate);
TESTCASE(77,TestAlternateSyntax);
TESTCASE(81,TestRuleStripping);
TESTCASE(82,TestHalfwidthFullwidth);
TESTCASE(83,TestThai);
+ TESTCASE(84,TestAny);
default: name = ""; break;
}
}
-static const UVersionInfo ICU_39 = {3,9,4,0};
/**
* Make sure every system transliterator can be instantiated.
*
name.truncate(0);
Transliterator::getDisplayName(id, name);
if (t == 0) {
- errln(UnicodeString("FAIL: Couldn't create ") + id +
- /*", parse error " + parseError.code +*/
- ", line " + parseError.line +
- ", offset " + parseError.offset +
- ", pre-context " + prettify(parseError.preContext, TRUE) +
- ", post-context " +prettify(parseError.postContext,TRUE) +
- ", Error: " + u_errorName(status));
- // When createInstance fails, it deletes the failing
- // entry from the available ID list. We detect this
- // here by looking for a change in countAvailableIDs.
+#if UCONFIG_NO_BREAK_ITERATION
+ // If UCONFIG_NO_BREAK_ITERATION is on, then only Thai should fail.
+ if (id.compare((UnicodeString)"Thai-Latn") != 0 &&
+ id.compare((UnicodeString)"Thai-Latin") != 0)
+#endif
+ dataerrln(UnicodeString("FAIL: Couldn't create ") + id +
+ /*", parse error " + parseError.code +*/
+ ", line " + parseError.line +
+ ", offset " + parseError.offset +
+ ", pre-context " + prettify(parseError.preContext, TRUE) +
+ ", post-context " +prettify(parseError.postContext,TRUE) +
+ ", Error: " + u_errorName(status));
+ // When createInstance fails, it deletes the failing
+ // entry from the available ID list. We detect this
+ // here by looking for a change in countAvailableIDs.
int32_t nn = Transliterator::countAvailableIDs();
if (nn == (n - 1)) {
n = nn;
UTRANS_FORWARD, parseError,
status);
if (U_FAILURE(status)) {
- errln("FAIL: RBT constructor failed");
+ dataerrln("FAIL: RBT constructor failed - %s", u_errorName(status));
return;
}
expect(*t, "abcdefgABCDEFGU", "&bcd&fg!^**!^*&");
"caccb", "xyzzy",
};
- int32_t DATA_length = (int32_t)(sizeof(DATA) / sizeof(DATA[0]));
+ int32_t DATA_length = UPRV_LENGTHOF(DATA);
UErrorCode status = U_ZERO_ERROR;
UParseError parseError;
0, "AycAY", // null means finishKeyboardTransliteration
};
- keyboardAux(*t, DATA, (int32_t)(sizeof(DATA)/sizeof(DATA[0])));
+ keyboardAux(*t, DATA, UPRV_LENGTHOF(DATA));
delete t;
}
0, "AycAY", // null means finishKeyboardTransliteration
};
- keyboardAux(*t, DATA, (int32_t)(sizeof(DATA)/sizeof(DATA[0])));
+ keyboardAux(*t, DATA, UPRV_LENGTHOF(DATA));
delete t;
}
errln("FAIL: RBT constructor failed");
return;
}
- keyboardAux(*t, DATA, (int32_t)(sizeof(DATA)/sizeof(DATA[0])));
+ keyboardAux(*t, DATA, UPRV_LENGTHOF(DATA));
delete t;
}
UErrorCode status = U_ZERO_ERROR;
Transliterator* t = Transliterator::createInstance("Latin-Hiragana;Hiragana-Latin", UTRANS_FORWARD, parseError, status);
if (t == 0) {
- errln("FAIL: construction of Latin-Hiragana;Hiragana-Latin failed");
+ dataerrln("FAIL: construction of Latin-Hiragana;Hiragana-Latin failed - %s", u_errorName(status));
} else {
expect(*t, "aaaaa", "aaaaa");
delete t;
UParseError parseError;
Transliterator *gl = Transliterator::createInstance("Greek-Latin; NFD; [:M:]Remove; NFC", UTRANS_FORWARD, parseError, status);
if (gl == NULL) {
- errln("FAIL: createInstance(Greek-Latin) returned NULL");
+ dataerrln("FAIL: createInstance(Greek-Latin) returned NULL - %s", u_errorName(status));
return;
}
{ FALSE, "a > b; c > d" },
{ TRUE, "a > b; no operator; c > d" },
};
- int32_t DATA_length = (int32_t)(sizeof(DATA) / sizeof(DATA[0]));
+ int32_t DATA_length = UPRV_LENGTHOF(DATA);
for (int32_t i=0; i<DATA_length; ++i) {
UErrorCode status = U_ZERO_ERROR;
"a1 b2",
"a1.a.1 b2.b.2",
};
- int32_t DATA_length = (int32_t)(sizeof(DATA)/sizeof(*DATA));
+ int32_t DATA_length = UPRV_LENGTHOF(DATA);
for (int32_t i=0; i<DATA_length; i+=3) {
logln("Pattern: " + prettify(DATA[i]));
"prbetaxyz preBETApost",
};
- int32_t DATA_length = (int32_t)(sizeof(DATA)/sizeof(*DATA));
+ int32_t DATA_length = UPRV_LENGTHOF(DATA);
for (int32_t i=0; i<DATA_length; i+=3) {
logln("Pattern: " + prettify(DATA[i]));
"ab xYzxyz stY78",
"ABE ENDEND 1129",
};
- int32_t DATA_length = (int32_t)(sizeof(DATA)/sizeof(*DATA));
+ int32_t DATA_length = UPRV_LENGTHOF(DATA);
for (int32_t i=0; i<DATA_length; i+=3) {
logln("Pattern: " + prettify(DATA[i]));
3, 8, 3, 8,
};
- int32_t n = (int32_t)(sizeof(DATA) / sizeof(DATA[0])) / 3;
+ int32_t n = UPRV_LENGTHOF(DATA) / 3;
for (int32_t i=0; i<n; i++) {
UErrorCode status = U_ZERO_ERROR;
UParseError parseError;
Transliterator* hk = Transliterator::createInstance("Hiragana-Katakana", UTRANS_FORWARD, parseError, status);
Transliterator* kh = Transliterator::createInstance("Katakana-Hiragana", UTRANS_FORWARD, parseError, status);
if (hk == 0 || kh == 0) {
- errln("FAIL: createInstance failed");
+ dataerrln("FAIL: createInstance failed - %s", u_errorName(status));
delete hk;
delete kh;
return;
"\\u307C\\u3051\\u3060\\u3042\\u3093\\u30FC",
"\\u30DC\\u30F6\\u30C0\\u30FC\\u30F3\\u30FC",
};
- int32_t DATA_length = (int32_t)(sizeof(DATA) / sizeof(DATA[0]));
+ int32_t DATA_length = UPRV_LENGTHOF(DATA);
for (int32_t i=0; i<DATA_length; i+=3) {
UnicodeString h = CharsToUnicodeString(DATA[i+1]);
UParseError parseError;
Transliterator* dg = Transliterator::createInstance(ID, UTRANS_FORWARD, parseError, status);
if (dg == 0) {
- errln("FAIL: createInstance(" + ID + ") returned NULL");
+ dataerrln("FAIL: createInstance(" + ID + ") returned NULL - " + u_errorName(status));
return;
}
UnicodeString id = dg->getID();
"xyz",
"xyz",
};
- enum { DATA_length = sizeof(DATA) / sizeof(DATA[0]) };
+ enum { DATA_length = UPRV_LENGTHOF(DATA) };
for (int i=0; i<DATA_length; i+=4) {
UnicodeString ID(DATA[i], "");
// Careful: CharsToUS will convert "\\N" => "N"; use "\\\\N" for \N
expect(*uni2name, CharsToUnicodeString("\\u00A0abc\\u4E01\\u00B5\\u0A81\\uFFFD\\u0004\\u0009\\u0081\\uFFFF"),
- CharsToUnicodeString("\\\\N{NO-BREAK SPACE}abc\\\\N{CJK UNIFIED IDEOGRAPH-4E01}\\\\N{MICRO SIGN}\\\\N{GUJARATI SIGN CANDRABINDU}\\\\N{REPLACEMENT CHARACTER}\\\\N{END OF TRANSMISSION}\\\\N{CHARACTER TABULATION}\\\\N{<control-0081>}\\\\N{<noncharacter-FFFF>}"));
- expect(*name2uni, UNICODE_STRING_SIMPLE("{\\N { NO-BREAK SPACE}abc\\N{ CJK UNIFIED IDEOGRAPH-4E01 }\\N{x\\N{MICRO SIGN}\\N{GUJARATI SIGN CANDRABINDU}\\N{REPLACEMENT CHARACTER}\\N{END OF TRANSMISSION}\\N{CHARACTER TABULATION}\\N{<control-0081>}\\N{<noncharacter-FFFF>}\\N{<control-0004>}\\N{"),
+ CharsToUnicodeString("\\\\N{NO-BREAK SPACE}abc\\\\N{CJK UNIFIED IDEOGRAPH-4E01}\\\\N{MICRO SIGN}\\\\N{GUJARATI SIGN CANDRABINDU}\\\\N{REPLACEMENT CHARACTER}\\\\N{<control-0004>}\\\\N{<control-0009>}\\\\N{<control-0081>}\\\\N{<noncharacter-FFFF>}"));
+ expect(*name2uni, UNICODE_STRING_SIMPLE("{\\N { NO-BREAK SPACE}abc\\N{ CJK UNIFIED IDEOGRAPH-4E01 }\\N{x\\N{MICRO SIGN}\\N{GUJARATI SIGN CANDRABINDU}\\N{REPLACEMENT CHARACTER}\\N{<control-0004>}\\N{<control-0009>}\\N{<control-0081>}\\N{<noncharacter-FFFF>}\\N{<control-0004>}\\N{"),
CharsToUnicodeString("{\\u00A0abc\\u4E01\\\\N{x\\u00B5\\u0A81\\uFFFD\\u0004\\u0009\\u0081\\uFFFF\\u0004\\\\N{"));
delete uni2name;
" Latin[a-z]-Greek ", "[a-z]Latin-Greek", "inline filter",
" null ; latin-greek ", NULL /*"Null;Latin-Greek"*/, "compound whitespace",
};
- const int32_t DATA_length = sizeof(DATA)/sizeof(DATA[0]);
+ const int32_t DATA_length = UPRV_LENGTHOF(DATA);
UParseError parseError;
UErrorCode status= U_ZERO_ERROR;
for (int32_t i=0; i<DATA_length; i+=3) {
Transliterator *t = Transliterator::createInstance(DATA[i], UTRANS_FORWARD, parseError, status);
if (t == 0) {
- errln(UnicodeString("FAIL: ") + DATA[i+2] +
- " cannot create ID \"" + DATA[i] + "\"");
+ dataerrln(UnicodeString("FAIL: ") + DATA[i+2] +
+ " cannot create ID \"" + DATA[i] + "\" - " + u_errorName(status));
} else {
UnicodeString exp;
if (DATA[i+1]) {
logln((UnicodeString)"Ok: createInstance(" +
id + "," + DATA[i+1] + ") => " + newID);
} else {
- errln((UnicodeString)"FAIL: createInstance(" +
+ dataerrln((UnicodeString)"FAIL: createInstance(" +
id + "," + DATA[i+1] + ") => " + newID +
", expected " + expID);
}
Transliterator* NFD = Transliterator::createInstance("NFD", UTRANS_FORWARD, parseError, status);
Transliterator* NFC = Transliterator::createInstance("NFC", UTRANS_FORWARD, parseError, status);
if (!NFD || !NFC) {
- errln("FAIL: createInstance failed");
+ dataerrln("FAIL: createInstance failed: %s", u_errorName(status));
delete NFD;
delete NFC;
return;
Transliterator* NFKD = Transliterator::createInstance("NFKD", UTRANS_FORWARD, parseError, status);
Transliterator* NFKC = Transliterator::createInstance("NFKC", UTRANS_FORWARD, parseError, status);
if (!NFKD || !NFKC) {
- errln("FAIL: createInstance failed");
+ dataerrln("FAIL: createInstance failed");
delete NFKD;
delete NFKC;
return;
// Now test toRules
t = Transliterator::createInstance("Greek-Latin; Latin-Cyrillic", UTRANS_FORWARD, parseError, status);
if (t == 0) {
- errln("FAIL: createInstance failed");
+ dataerrln("FAIL: createInstance failed - %s", u_errorName(status));
return;
}
UnicodeString exp("::Greek-Latin;\n::Latin-Cyrillic;");
Transliterator *t = Transliterator::createInstance
("Greek-Latin; Latin-Greek; Lower", UTRANS_FORWARD, parseError, status);
if (t == 0) {
- errln("FAIL: createInstance failed");
+ dataerrln("FAIL: createInstance failed - %s", u_errorName(status));
return;
}
t->adoptFilter(new UnicodeSet("[^A]", status));
"([AEIOUYaeiouy]\\u0304[[:M:]-[\\u0304\\u0345]]*)i > | $1 \\u0345;",
"([AEIOUYaeiouy]\\u0304[[:M:]-[\\u0304\\u0345]]*)i > | $1 \\u0345;",
};
- static const int32_t DATA_length = (int32_t)(sizeof(DATA) / sizeof(DATA[0]));
+ static const int32_t DATA_length = UPRV_LENGTHOF(DATA);
for (int32_t d=0; d < DATA_length; d+=3) {
if (DATA[d] == RBT) {
Transliterator *t = Transliterator::createFromRules("ID",
UnicodeString(DATA[d+1], -1, US_INV), UTRANS_FORWARD, parseError, status);
if (t == 0) {
- errln("FAIL: createFromRules failed");
+ dataerrln("FAIL: createFromRules failed - %s", u_errorName(status));
return;
}
UnicodeString rules, escapedRules;
Transliterator *t = Transliterator::createInstance
("Greek-Latin; Title()", UTRANS_REVERSE,parseError, status);
if (t == 0) {
- errln("FAIL: createInstance");
+ dataerrln("FAIL: createInstance - %s", u_errorName(status));
return;
}
UnicodeString exp("(Title);Latin-Greek");
"TEST", "::NFD; aa > Q; a > q;",
UTRANS_FORWARD, pe, ec);
if (t == NULL || U_FAILURE(ec)) {
- errln("FAIL: Transliterator::createFromRules failed with %s", u_errorName(ec));
+ dataerrln("FAIL: Transliterator::createFromRules failed with %s", u_errorName(ec));
return;
}
expect(*t, "aa", "Q");
UErrorCode ec = U_ZERO_ERROR;
Transliterator *t = Transliterator::createInstance(ID, UTRANS_FORWARD, pe, ec);
if (t == 0 || U_FAILURE(ec)) {
- errln("FAIL: createInstance");
+ dataerrln("FAIL: createInstance - %s", u_errorName(ec));
return;
}
Transliterator *u = t->createInverse(ec);
UErrorCode ec = U_ZERO_ERROR;
Transliterator *t = Transliterator::createInstance(ID, UTRANS_FORWARD, pe, ec);
if (t == 0 || U_FAILURE(ec)) {
- errln("FAIL: createInstance");
+ dataerrln("FAIL: createInstance - %s", u_errorName(ec));
return;
}
Transliterator *u = t->createInverse(ec);
}
delete t;
} else {
- errln((UnicodeString)"FAIL: " + id + " => " + transID + ", " +
+ dataerrln((UnicodeString)"FAIL: " + id + " => " + transID + ", " +
u_errorName(ec));
}
}
UErrorCode ec = U_ZERO_ERROR;
Transliterator *t = Transliterator::createInstance("Latin-Hiragana", UTRANS_FORWARD, pe, ec);
if (t == 0 || U_FAILURE(ec)) {
- errln("FAIL: createInstance Latin-Hiragana");
+ dataerrln("FAIL: createInstance Latin-Hiragana - %s", u_errorName(ec));
return;
}
// Katakana should be untouched
Transliterator* latinToDev=Transliterator::createInstance("Latin-Devanagari", UTRANS_FORWARD, parseError, status);
Transliterator* devToLatin=Transliterator::createInstance("Devanagari-Latin", UTRANS_FORWARD, parseError, status);
if(U_FAILURE(status)){
- errln("FAIL: construction " + UnicodeString(" Error: ") + u_errorName(status));
- errln("PreContext: " + prettify(parseError.preContext) + " PostContext: " + prettify( parseError.postContext) );
+ dataerrln("FAIL: construction " + UnicodeString(" Error: ") + u_errorName(status));
+ dataerrln("PreContext: " + prettify(parseError.preContext) + " PostContext: " + prettify( parseError.postContext) );
return;
}
UnicodeString gotResult;
Transliterator* latinToDev=Transliterator::createInstance("Latin-Telugu", UTRANS_FORWARD, parseError, status);
Transliterator* devToLatin=Transliterator::createInstance("Telugu-Latin", UTRANS_FORWARD, parseError, status);
if(U_FAILURE(status)){
- errln("FAIL: construction " + UnicodeString(" Error: ") + u_errorName(status));
- errln("PreContext: " + prettify(parseError.preContext) + " PostContext: " + prettify( parseError.postContext) );
+ dataerrln("FAIL: construction " + UnicodeString(" Error: ") + u_errorName(status));
+ dataerrln("PreContext: " + prettify(parseError.preContext) + " PostContext: " + prettify( parseError.postContext) );
return;
}
UnicodeString gotResult;
Transliterator* latinToDev=Transliterator::createInstance("Latin-Devanagari", UTRANS_FORWARD, parseError, status);
Transliterator* devToLatin=Transliterator::createInstance("Devanagari-Latin", UTRANS_FORWARD, parseError, status);
if(U_FAILURE(status)){
- errln("FAIL: construction " + UnicodeString(" Error: ") + u_errorName(status));
- errln("PreContext: " + prettify(parseError.preContext) + " PostContext: " + prettify( parseError.postContext) );
+ dataerrln("FAIL: construction " + UnicodeString(" Error: ") + u_errorName(status));
+ dataerrln("PreContext: " + prettify(parseError.preContext) + " PostContext: " + prettify( parseError.postContext) );
return;
}
UnicodeString gotResult;
"kimakurvata",
"san\\u0304java"
};
- const int MAX_LEN = sizeof(source)/sizeof(source[0]);
+ const int MAX_LEN = UPRV_LENGTHOF(source);
const char* const expected[MAX_LEN] = {
"\\u0930\\u094D\\u092E\\u094D\\u0915\\u094D\\u0937\\u0947\\u0924\\u094D",
"\\u0936\\u094d\\u0930\\u0940\\u092e\\u0926\\u094d",
"\\u0915\\u093f\\u092e\\u0915\\u0941\\u0930\\u094d\\u0935\\u0924",
"\\u0938\\u0902\\u091c\\u0935"
};
- if(MAX_LEN != sizeof(expected)/sizeof(expected[0])) {
+ if(MAX_LEN != UPRV_LENGTHOF(expected)) {
errln("error in TestCompoundLatinRT: source[] and expected[] have different lengths!");
return;
}
Transliterator* latinToTelToLatin=Transliterator::createInstance("Latin-Telugu;Telugu-Latin", UTRANS_FORWARD, parseError, status);
if(U_FAILURE(status)){
- errln("FAIL: construction " + UnicodeString(" Error: ") + u_errorName(status));
- errln("PreContext: " + prettify(parseError.preContext) + " PostContext: " + prettify( parseError.postContext) );
+ dataerrln("FAIL: construction " + UnicodeString(" Error: ") + u_errorName(status));
+ dataerrln("PreContext: " + prettify(parseError.preContext) + " PostContext: " + prettify( parseError.postContext) );
return;
}
UnicodeString gotResult;
UnicodeSetIterator nvIter(non_vowel);
Transliterator* trans = Transliterator::createInstance("Devanagari-Gurmukhi",UTRANS_FORWARD, parseError, status);
if(U_FAILURE(status)) {
- errln("Error creating transliterator %s", u_errorName(status));
+ dataerrln("Error creating transliterator %s", u_errorName(status));
delete trans;
return;
}
UErrorCode ec = U_ZERO_ERROR;
Transliterator *t = Transliterator::createInstance("ru_RU-Latin", UTRANS_FORWARD, pe, ec);
if (U_FAILURE(ec)) {
- errln("FAIL: createInstance(ru_RU-Latin)");
+ dataerrln("FAIL: createInstance(ru_RU-Latin) - %s", u_errorName(ec));
delete t;
return;
}
"el-Latin", "\\u03B2", "v",
"Greek-Latin", "\\u03B2", "b",
};
- const int32_t DATA_length = sizeof(DATA) / sizeof(DATA[0]);
+ const int32_t DATA_length = UPRV_LENGTHOF(DATA);
for (int32_t i=0; i<DATA_length; i+=3) {
UParseError pe;
UErrorCode ec = U_ZERO_ERROR;
Transliterator *t = Transliterator::createInstance(DATA[i], UTRANS_FORWARD, pe, ec);
if (U_FAILURE(ec)) {
- errln((UnicodeString)"FAIL: createInstance(" + DATA[i] + ")");
+ dataerrln((UnicodeString)"FAIL: createInstance(" + DATA[i] + ") - " + u_errorName(ec));
delete t;
continue;
}
"-", NULL, NULL,
"/", NULL, NULL,
};
- const int32_t DATA_length = sizeof(DATA)/sizeof(DATA[0]);
+ const int32_t DATA_length = UPRV_LENGTHOF(DATA);
for (int32_t i=0; i<DATA_length; i+=3) {
const char* ID = DATA[i];
if (!expValid) {
logln((UnicodeString)"Ok: getInstance(" + ID +") => " + u_errorName(ec));
} else {
- errln((UnicodeString)"FAIL: Couldn't create " + ID);
+ dataerrln((UnicodeString)"FAIL: Couldn't create " + ID + " - " + u_errorName(ec));
}
delete t;
continue;
if (U_FAILURE(ec)) {
delete t2;
delete t3;
- errln((UnicodeString)"FAIL: createFromRules => " + u_errorName(ec));
+ dataerrln((UnicodeString)"FAIL: createFromRules => " + u_errorName(ec));
return;
}
"NFC", "Any to NFC", "Any to NFD",
};
- int32_t DATA_length = sizeof(DATA) / sizeof(DATA[0]);
+ int32_t DATA_length = UPRV_LENGTHOF(DATA);
Locale US("en", "US");
UnicodeString name;
Transliterator::getDisplayName(DATA[i], US, name);
if (name != DATA[i+1]) {
- errln((UnicodeString)"FAIL: " + DATA[i] + ".getDisplayName() => " +
+ dataerrln((UnicodeString)"FAIL: " + DATA[i] + ".getDisplayName() => " +
name + ", expected " + DATA[i+1]);
} else {
logln((UnicodeString)"Ok: " + DATA[i] + ".getDisplayName() => " + name);
Transliterator *t = Transliterator::createInstance(DATA[i], UTRANS_REVERSE, pe, ec);
if (U_FAILURE(ec)) {
delete t;
- errln("FAIL: createInstance failed");
+ dataerrln("FAIL: createInstance failed - %s", u_errorName(ec));
continue;
}
name = Transliterator::getDisplayName(t->getID(), US, name);
if (name != DATA[i+2]) {
- errln((UnicodeString)"FAIL: " + t->getID() + ".getDisplayName() => " +
+ dataerrln((UnicodeString)"FAIL: " + t->getID() + ".getDisplayName() => " +
name + ", expected " + DATA[i+2]);
} else {
logln((UnicodeString)"Ok: " + t->getID() + ".getDisplayName() => " + name);
Transliterator *t = Transliterator::createFromRules(registerRules[0+i],
registerRules[i+1], UTRANS_FORWARD, pos, status);
if (U_FAILURE(status)) {
- errln("Fails: Unable to create the transliterator from rules.");
+ dataerrln("Fails: Unable to create the transliterator from rules. - %s", u_errorName(status));
} else {
Transliterator::registerInstance(t);
}
const UnicodeString& name = testCases[i];
Transliterator *t = Transliterator::createInstance(name, UTRANS_FORWARD, pe, ec);
if (U_FAILURE(ec)) {
- errln((UnicodeString)"FAIL: Couldn't create " + name);
+ dataerrln((UnicodeString)"FAIL: Couldn't create " + name + " - " + u_errorName(ec));
delete t;
continue;
}
char buffer[20];
UChar buffer2[20];
UChar32 dee;
- UTF_GET_CHAR(DESERET_dee,0, 0, DESERET_dee.length(), dee);
+ U16_GET(DESERET_dee,0, 0, DESERET_dee.length(), dee);
UnicodeString DEE(u_totitle(dee));
if (DEE != DESERET_DEE) {
err("Fails titlecase of surrogates");
Transliterator *t = Transliterator::createInstance(id, UTRANS_FORWARD, err, status);
if (U_FAILURE(status)) {
- errln((UnicodeString)"FAIL: Could not create " + id);
+ dataerrln((UnicodeString)"FAIL: Could not create " + id);
delete t;
continue;
}
_trans(*t, test, rev);
Transliterator *inv = t->createInverse(status);
if (U_FAILURE(status)) {
- errln((UnicodeString)"FAIL: Could not create inverse of " + id);
+ // The following are forward-only, it is OK that creating an inverse will not work:
+ // 1. Devanagari-Arabic
+ // 2. Any-*/BGN
+ // 2a. Any-*/BGN_1981
+ // 3. Any-*/UNGEGN
+ // 4. Any-*/MNS
+ // If UCONFIG_NO_BREAK_ITERATION is on, Latin-Thai is also not expected to work.
+ if ( id.compare((UnicodeString)"Devanagari-Arabic/") != 0
+ && !(id.startsWith((UnicodeString)"Any-") &&
+ (id.endsWith((UnicodeString)"/BGN") || id.endsWith((UnicodeString)"/BGN_1981") || id.endsWith((UnicodeString)"/UNGEGN") || id.endsWith((UnicodeString)"/MNS"))
+ )
+#if UCONFIG_NO_BREAK_ITERATION
+ && id.compare((UnicodeString)"Latin-Thai/") != 0
+#endif
+ )
+ {
+ errln((UnicodeString)"FAIL: Could not create inverse of " + id);
+ }
delete t;
delete inv;
continue;
return;
}
UBool gotError = FALSE;
+ (void)gotError; // Suppress set but not used warning.
// we have a few special cases. Any-Remove (pos.start = 0, but also = limit) and U+XXXXX?X?
UErrorCode ec = U_ZERO_ERROR;
Transliterator *t = Transliterator::createFromRules("Test", rule, UTRANS_FORWARD, pe, ec);
if (t == NULL) {
- errln("FAIL: createFromRules failed");
+ dataerrln("FAIL: createFromRules failed - %s", u_errorName(ec));
return;
}
UNICODE_STRING_SIMPLE("'\\'u(..)(..) > '<img src=\"http://www.unicode.org/gifs/24/' $1 '/U' $1$2 '.gif\">';"),
UTRANS_FORWARD, pe, ec);
if (t == NULL || U_FAILURE(ec)) {
- errln((UnicodeString)"FAIL: createFromRules gif " + u_errorName(ec));
+ dataerrln((UnicodeString)"FAIL: createFromRules gif " + u_errorName(ec));
return;
}
_TUFReg("Any-gif", t, 0);
Transliterator* anyLatin =
Transliterator::createInstance("Any-Latin", UTRANS_FORWARD, parseError, status);
if (anyLatin==0) {
- errln("FAIL: createInstance returned NULL");
+ dataerrln("FAIL: createInstance returned NULL - %s", u_errorName(status));
delete anyLatin;
return;
}
CharsToUnicodeString("greek:abkABK hiragana:abuku cyrillic:abc"));
delete anyLatin;
+
+ status = U_ZERO_ERROR;
+ Transliterator* anyASCII =
+ Transliterator::createInstance("Any-Latin;Latin-ASCII", UTRANS_FORWARD, parseError, status);
+ if (U_FAILURE(status) || anyASCII==0) {
+ dataerrln("FAIL: createInstance returned NULL and/or set status %s", u_errorName(status));
+ delete anyASCII;
+ return;
+ }
+
+ expect(*anyASCII,
+ CharsToUnicodeString("ArabicDigits:\\u0660\\u0661\\u0664\\u0669 PersianDigits:\\u06F0\\u06F1\\u06F4\\u06F9"),
+ CharsToUnicodeString("ArabicDigits:0149 PersianDigits:0149"));
+
+ delete anyASCII;
+}
+
+/**
+ * Test Any-X transliterators with sample letters from all scripts.
+ */
+void TransliteratorTest::TestAny(void) {
+ UErrorCode status = U_ZERO_ERROR;
+ // Note: there is a lot of implict construction of UnicodeStrings from (char *) in
+ // function call parameters going on in this test.
+ UnicodeSet alphabetic("[:alphabetic:]", status);
+ if (U_FAILURE(status)) {
+ dataerrln("Failure: file %s, line %d, status = %s", __FILE__, __LINE__, u_errorName(status));
+ return;
+ }
+ alphabetic.freeze();
+
+ UnicodeString testString;
+ for (int32_t i = 0; i < USCRIPT_CODE_LIMIT; i++) {
+ const char *scriptName = uscript_getShortName((UScriptCode)i);
+ if (scriptName == NULL) {
+ errln("Failure: file %s, line %d: Script Code %d is invalid, ", __FILE__, __LINE__, i);
+ return;
+ }
+
+ UnicodeSet sample;
+ sample.applyPropertyAlias("script", scriptName, status);
+ if (U_FAILURE(status)) {
+ errln("Failure: file %s, line %d, status = %s", __FILE__, __LINE__, u_errorName(status));
+ return;
+ }
+ sample.retainAll(alphabetic);
+ for (int32_t count=0; count<5; count++) {
+ UChar32 c = sample.charAt(count);
+ if (c == -1) {
+ break;
+ }
+ testString.append(c);
+ }
+ }
+
+ UParseError parseError;
+ Transliterator* anyLatin =
+ Transliterator::createInstance("Any-Latin", UTRANS_FORWARD, parseError, status);
+ if (U_FAILURE(status)) {
+ dataerrln("Failure: file %s, line %d, status = %s", __FILE__, __LINE__, u_errorName(status));
+ return;
+ }
+
+ logln(UnicodeString("Sample set for Any-Latin: ") + testString);
+ anyLatin->transliterate(testString);
+ logln(UnicodeString("Sample result for Any-Latin: ") + testString);
+ delete anyLatin;
}
+
/**
* Test the source and target set API. These are only implemented
* for RBT and CompoundTransliterator at this time.
}
/**
- * Test handling of rule whitespace, for both RBT and UnicodeSet.
+ * Test handling of Pattern_White_Space, for both RBT and UnicodeSet.
*/
-void TransliteratorTest::TestRuleWhitespace() {
+void TransliteratorTest::TestPatternWhiteSpace() {
// Rules
const char* r = "a > \\u200E b;";
for(uint32_t i = 0; i<=0x10ffff; i++){
code = uscript_getScript(i,&status);
if(code == USCRIPT_INVALID_CODE){
- errln("uscript_getScript for codepoint \\U%08X failed.\n", i);
+ dataerrln("uscript_getScript for codepoint \\U%08X failed.", i);
}
const char* myId = uscript_getName(code);
if(!myId) {
- errln("Valid script code returned NULL name. Check your data!");
+ dataerrln("Valid script code returned NULL name. Check your data!");
return;
}
uprv_strcpy(id,myId);
if(uprv_strcmp(newId,oldId)!=0){
Transliterator* t = Transliterator::createInstance(newId,UTRANS_FORWARD,pe,status);
if(t==NULL || U_FAILURE(status)){
- errln((UnicodeString)"FAIL: Could not create " + id);
+ dataerrln((UnicodeString)"FAIL: Could not create " + id + " - " + u_errorName(status));
}
delete t;
}
if(uprv_strcmp(newAbbrId,oldAbbrId)!=0){
Transliterator* t = Transliterator::createInstance(newAbbrId,UTRANS_FORWARD,pe,status);
if(t==NULL || U_FAILURE(status)){
- errln((UnicodeString)"FAIL: Could not create " + id);
+ dataerrln((UnicodeString)"FAIL: Could not create " + id + " - " + u_errorName(status));
}
delete t;
}
UErrorCode ec = U_ZERO_ERROR; \
Transliterator* t = Transliterator::createInstance(id, UTRANS_FORWARD, ec); \
if (U_FAILURE(ec)) { \
- errln("FAIL: Couldn't create " id); \
+ dataerrln("FAIL: Couldn't create %s - %s", id, u_errorName(ec)); \
} else { \
if (t->getDynamicClassID() != cls::getStaticClassID()) { \
errln("FAIL: " #cls " dynamic and static class ID mismatch"); \
"::Upper(Lower);"
"::([XYZ]);"
};
-static const int32_t BEGIN_END_RULES_length = (int32_t)(sizeof(BEGIN_END_RULES) / sizeof(BEGIN_END_RULES[0]));
/*
(This entire test is commented out below and will need some heavy revision when we re-add
"::Upper;"
"::END;"
};
-static const int32_t BOGUS_BEGIN_END_RULES_length = (int32_t)(sizeof(BOGUS_BEGIN_END_RULES) / sizeof(BOGUS_BEGIN_END_RULES[0]));
+static const int32_t BOGUS_BEGIN_END_RULES_length = UPRV_LENGTHOF(BOGUS_BEGIN_END_RULES);
*/
static const char* BEGIN_END_TEST_CASES[] = {
// BEGIN_END_RULES[16], "abc xy ababc xyz aba", "XY xy ABXY xyz YZ",
BEGIN_END_RULES[17], "abc xy ababc xyz aba", "XY xy ABXY xyz YZ"
};
-static const int32_t BEGIN_END_TEST_CASES_length = (int32_t)(sizeof(BEGIN_END_TEST_CASES) / sizeof(BEGIN_END_TEST_CASES[0]));
+static const int32_t BEGIN_END_TEST_CASES_length = UPRV_LENGTHOF(BEGIN_END_TEST_CASES);
void TransliteratorTest::TestBeginEnd() {
// run through the list of test cases above
err = U_ZERO_ERROR;
t1 = Transliterator::createInstance(realID, UTRANS_FORWARD, err);
if (U_FAILURE(err)) {
- errln("Failed to instantiate transliterator with real ID");
+ dataerrln("Failed to instantiate transliterator with real ID - %s", u_errorName(err));
Transliterator::unregister(realID);
return;
}
static const UChar expectedRule[] = {
0xE001,0x003E,0x0C01,0x003B,0
};
- UChar result[sizeof(rule)/sizeof(rule[0])];
+ UChar result[UPRV_LENGTHOF(rule)];
UErrorCode status = U_ZERO_ERROR;
- int32_t len = utrans_stripRules(rule, (int32_t)(sizeof(rule)/sizeof(rule[0])), result, &status);
+ int32_t len = utrans_stripRules(rule, UPRV_LENGTHOF(rule), result, &status);
if (len != u_strlen(expectedRule)) {
errln("utrans_stripRules return len = %d", len);
}
Transliterator* hf = Transliterator::createInstance("Halfwidth-Fullwidth", UTRANS_FORWARD, parseError, status);
Transliterator* fh = Transliterator::createInstance("Fullwidth-Halfwidth", UTRANS_FORWARD, parseError, status);
if (hf == 0 || fh == 0) {
- errln("FAIL: createInstance failed");
+ dataerrln("FAIL: createInstance failed - %s", u_errorName(status));
delete hf;
delete fh;
return;
"\\uFFE9\\uFFEA\\uFFEB\\uFFEC\\u0061\\uFF71\\u00AF\\u0020",
"\\u2190\\u2191\\u2192\\u2193\\uFF41\\u30A2\\uFFE3\\u3000",
};
- int32_t DATA_length = (int32_t)(sizeof(DATA) / sizeof(DATA[0]));
+ int32_t DATA_length = UPRV_LENGTHOF(DATA);
for (int32_t i=0; i<DATA_length; i+=3) {
UnicodeString h = CharsToUnicodeString(DATA[i+1]);
* For now, test just confirms that C++ and Java give identical results.
*/
void TransliteratorTest::TestThai(void) {
+#if !UCONFIG_NO_BREAK_ITERATION
UParseError parseError;
UErrorCode status = U_ZERO_ERROR;
Transliterator* tr = Transliterator::createInstance("Any-Latin", UTRANS_FORWARD, parseError, status);
if (tr == 0) {
- errln("FAIL: createInstance failed");
+ dataerrln("FAIL: createInstance failed - %s", u_errorName(status));
return;
}
if (U_FAILURE(status)) {
expect(*tr, xlitText, expectedText);
delete tr;
+#endif
}
UParseError pe;
Transliterator *t = Transliterator::createInstance(id, UTRANS_FORWARD, pe, ec);
if (U_FAILURE(ec)) {
- errln((UnicodeString)"FAIL: Could not create " + id);
+ errln((UnicodeString)"FAIL: Could not create " + id + " - " + u_errorName(ec));
delete t;
return;
}
void TransliteratorTest::reportParseError(const UnicodeString& message,
const UParseError& parseError,
const UErrorCode& status) {
- errln(message +
+ dataerrln(message +
/*", parse error " + parseError.code +*/
", line " + parseError.line +
", offset " + parseError.offset +
if (pass) {
logln(UnicodeString("(")+tag+") " + prettify(summary));
} else {
- errln(UnicodeString("FAIL: (")+tag+") "
+ dataerrln(UnicodeString("FAIL: (")+tag+") "
+ prettify(summary)
+ ", expected " + prettify(expectedResult));
}
projects / apple / icu.git / blobdiff