+// © 2016 and later: Unicode, Inc. and others.
+// License & terms of use: http://www.unicode.org/copyright.html
/*
**********************************************************************
-* Copyright (C) 1999-2014, International Business Machines
+* Copyright (C) 1999-2016, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
* Date Name Description
TESTCASE(82,TestHalfwidthFullwidth);
TESTCASE(83,TestThai);
TESTCASE(84,TestAny);
+ TESTCASE(85,TestHansHant);
default: name = ""; break;
}
}
if (t == 0) {
#if UCONFIG_NO_BREAK_ITERATION
// If UCONFIG_NO_BREAK_ITERATION is on, then only Thai should fail.
- if (id.compare((UnicodeString)"Thai-Latin") != 0)
+ 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 +*/
"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;
}
* Used by TestFiltering().
*/
class TestFilter : public UnicodeFilter {
- virtual UnicodeFunctor* clone() const {
+ virtual TestFilter* clone() const {
return new TestFilter(*this);
}
virtual UBool contains(UChar32 c) const {
{ 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;
"\\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]);
"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], "");
" 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) {
"([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) {
public:
TestTrans(const UnicodeString& id) : Transliterator(id, 0) {
}
- virtual Transliterator* clone(void) const {
+ virtual TestTrans* clone(void) const {
return new TestTrans(getID());
}
virtual void handleTransliterate(Replaceable& /*text*/, UTransPosition& offsets,
exp = CharsToUnicodeString(DATA[i+3]);
}
UBool expOk = (DATA[i+1] != NULL);
- Transliterator* t = NULL;
+ LocalPointer<Transliterator> t;
UParseError pe;
UErrorCode ec = U_ZERO_ERROR;
if (id.charAt(0) == 0x23/*#*/) {
- t = Transliterator::createFromRules("ID", id, direction, pe, ec);
+ t.adoptInstead(Transliterator::createFromRules("ID", id, direction, pe, ec));
} else {
- t = Transliterator::createInstance(id, direction, pe, ec);
+ t.adoptInstead(Transliterator::createInstance(id, direction, pe, ec));
}
- UBool ok = (t != NULL && U_SUCCESS(ec));
+ UBool ok = (t.isValid() && U_SUCCESS(ec));
UnicodeString transID;
- if (t!=0) {
+ if (t.isValid()) {
transID = t->getID();
}
else {
if (source.length() != 0) {
expect(*t, source, exp);
}
- delete t;
} else {
dataerrln((UnicodeString)"FAIL: " + id + " => " + transID + ", " +
u_errorName(ec));
"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;
}
"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;
"-", 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];
UParseError pe;
UErrorCode ec = U_ZERO_ERROR;
- Transliterator *t2 = Transliterator::createFromRules("source-target", UnicodeString(testRules, -1, US_INV), UTRANS_FORWARD, pe, ec);
- Transliterator *t3 = Transliterator::createFromRules("target-source", UnicodeString(testRules, -1, US_INV), UTRANS_REVERSE, pe, ec);
+ LocalPointer<Transliterator> t2(
+ Transliterator::createFromRules("source-target", UnicodeString(testRules, -1, US_INV), UTRANS_FORWARD, pe, ec));
+ LocalPointer<Transliterator> t3(
+ Transliterator::createFromRules("target-source", UnicodeString(testRules, -1, US_INV), UTRANS_REVERSE, pe, ec));
if (U_FAILURE(ec)) {
- delete t2;
- delete t3;
dataerrln((UnicodeString)"FAIL: createFromRules => " + u_errorName(ec));
return;
}
checkRules("Failed toRules FORWARD", *t2, UnicodeString(testRulesForward, -1, US_INV));
checkRules("Failed toRules BACKWARD", *t3, UnicodeString(testRulesBackward, -1, US_INV));
-
- delete t2;
- delete t3;
}
/**
"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");
_trans(*t, test, rev);
Transliterator *inv = t->createInverse(status);
if (U_FAILURE(status)) {
+ // 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
- // If UCONFIG_NO_BREAK_ITERATION is on, then only Thai should fail.
- if (id.compare((UnicodeString)"Latin-Thai/") != 0)
+ && id.compare((UnicodeString)"Latin-Thai/") != 0
#endif
+ )
+ {
errln((UnicodeString)"FAIL: Could not create inverse of " + id);
-
+ }
delete t;
delete inv;
continue;
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;
}
/**
}
-#define TEST_TRANSLIT_ID(id, cls) { \
+#define TEST_TRANSLIT_ID(id, cls) UPRV_BLOCK_MACRO_BEGIN { \
UErrorCode ec = U_ZERO_ERROR; \
Transliterator* t = Transliterator::createInstance(id, UTRANS_FORWARD, ec); \
if (U_FAILURE(ec)) { \
/* *t = *t; */ /*can't do this: coverage test for assignment op*/ \
} \
delete t; \
-}
+} UPRV_BLOCK_MACRO_END
-#define TEST_TRANSLIT_RULE(rule, cls) { \
+#define TEST_TRANSLIT_RULE(rule, cls) UPRV_BLOCK_MACRO_BEGIN { \
UErrorCode ec = U_ZERO_ERROR; \
UParseError pe; \
Transliterator* t = Transliterator::createFromRules("_", rule, UTRANS_FORWARD, pe, ec); \
/* *t = *t; */ /*can't do this: coverage test for assignment op*/ \
} \
delete t; \
-}
+} UPRV_BLOCK_MACRO_END
void TransliteratorTest::TestBoilerplate() {
TEST_TRANSLIT_ID("Any-Latin", AnyTransliterator);
"::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
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);
}
"\\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]);
#endif
}
+/**
+ * Test for rdar://problem/61817095 (and maybe eventually other Hans-Hant errors)
+ * Apple-only
+ * ICU4C only
+ */
+void TransliteratorTest::TestHansHant(void) {
+ UParseError parseError;
+ UErrorCode status = U_ZERO_ERROR;
+ Transliterator* tr = Transliterator::createInstance("Hans-Hant", UTRANS_FORWARD, parseError, status);
+ if (U_FAILURE(status)) {
+ errln("FAIL: createInstance failed with %s", u_errorName(status));
+ return;
+ }
+
+ const char* _sourceText = "\\u810f \\u5185\\u810f \\u810f\\u5668 \\u4e94\\u810f \\u5fc3\\u810f \\u809d\\u810f \\u813e\\u810f \\u80c3\\u810f \\u80be\\u810f \\u80f0\\u810f \\u810f\\u8151 \\u80ba\\u810f";
+ const char* _expectedResult = "\\u9ad2 \\u5167\\u81df \\u81df\\u5668 \\u4e94\\u81df \\u5fc3\\u81df \\u809d\\u81df \\u813e\\u81df \\u80c3\\u81df \\u814e\\u81df \\u80f0\\u81df \\u81df\\u8151 \\u80ba\\u81df";
+
+ UnicodeString sourceText(_sourceText);
+ UnicodeString expectedResult(_expectedResult);
+ sourceText = sourceText.unescape();
+ expectedResult = expectedResult.unescape();
+
+ expect(*tr, sourceText, expectedResult);
+ delete tr;
+}
+
//======================================================================
// Support methods
projects / apple / icu.git / blobdiff