+// © 2016 and later: Unicode, Inc. and others.
+// License & terms of use: http://www.unicode.org/copyright.html
/*
**********************************************************************
-* Copyright (C) 1999-2010, 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(71,TestAnyX);
TESTCASE(72,TestSourceTargetSet);
TESTCASE(73,TestGurmukhiDevanagari);
- TESTCASE(74,TestRuleWhitespace);
+ TESTCASE(74,TestPatternWhiteSpace);
TESTCASE(75,TestAllCodepoints);
TESTCASE(76,TestBoilerplate);
TESTCASE(77,TestAlternateSyntax);
}
}
-static const UVersionInfo ICU_39 = {3,9,4,0};
/**
* Make sure every system transliterator can be instantiated.
*
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;
}
{ 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], "");
// 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* 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;
"([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) {
"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];
"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");
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");
_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;
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?
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;
}
/**
Transliterator* anyLatin =
Transliterator::createInstance("Any-Latin", UTRANS_FORWARD, parseError, status);
if (U_FAILURE(status)) {
- errln("Failure: file %s, line %d, status = %s", __FILE__, __LINE__, u_errorName(status));
+ dataerrln("Failure: file %s, line %d, status = %s", __FILE__, __LINE__, u_errorName(status));
return;
}
}
/**
- * 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) {
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;
}
"::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
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]);
projects / apple / icu.git / blobdiff