1 // Copyright (C) 2016 and later: Unicode, Inc. and others.
2 // License & terms of use: http://www.unicode.org/copyright.html
4 *******************************************************************************
5 * Copyright (C) 2010-2014, International Business Machines
6 * Corporation and others. All Rights Reserved.
7 *******************************************************************************
8 * file name: uts46test.cpp
10 * tab size: 8 (not used)
13 * created on: 2010may05
14 * created by: Markus W. Scherer
17 #include "unicode/utypes.h"
22 #include "unicode/bytestream.h"
23 #include "unicode/idna.h"
24 #include "unicode/localpointer.h"
25 #include "unicode/std_string.h"
26 #include "unicode/stringpiece.h"
27 #include "unicode/uidna.h"
28 #include "unicode/unistr.h"
32 class UTS46Test : public IntlTest {
34 UTS46Test() : trans(NULL), nontrans(NULL) {}
37 void runIndexedTest(int32_t index, UBool exec, const char *&name, char *par=NULL);
42 IDNA *trans, *nontrans;
45 extern IntlTest *createUTS46Test() {
46 return new UTS46Test();
49 UTS46Test::~UTS46Test() {
54 void UTS46Test::runIndexedTest(int32_t index, UBool exec, const char *&name, char * /*par*/) {
56 logln("TestSuite UTS46Test: ");
58 IcuTestErrorCode errorCode(*this, "init/createUTS46Instance()");
59 uint32_t commonOptions=
60 UIDNA_USE_STD3_RULES|UIDNA_CHECK_BIDI|
61 UIDNA_CHECK_CONTEXTJ|UIDNA_CHECK_CONTEXTO;
62 trans=IDNA::createUTS46Instance(commonOptions, errorCode);
63 nontrans=IDNA::createUTS46Instance(
65 UIDNA_NONTRANSITIONAL_TO_ASCII|UIDNA_NONTRANSITIONAL_TO_UNICODE,
67 if(errorCode.logDataIfFailureAndReset("createUTS46Instance()")) {
74 TESTCASE_AUTO(TestAPI);
75 TESTCASE_AUTO(TestNotSTD3);
76 TESTCASE_AUTO(TestSomeCases);
80 const uint32_t severeErrors=
81 UIDNA_ERROR_LEADING_COMBINING_MARK|
82 UIDNA_ERROR_DISALLOWED|
84 UIDNA_ERROR_LABEL_HAS_DOT|
85 UIDNA_ERROR_INVALID_ACE_LABEL;
87 static UBool isASCII(const UnicodeString &str) {
88 const UChar *s=str.getBuffer();
89 int32_t length=str.length();
90 for(int32_t i=0; i<length; ++i) {
98 class TestCheckedArrayByteSink : public CheckedArrayByteSink {
100 TestCheckedArrayByteSink(char* outbuf, int32_t capacity)
101 : CheckedArrayByteSink(outbuf, capacity), calledFlush(FALSE) {}
102 virtual CheckedArrayByteSink& Reset() {
103 CheckedArrayByteSink::Reset();
107 virtual void Flush() { calledFlush = TRUE; }
111 void UTS46Test::TestAPI() {
112 UErrorCode errorCode=U_ZERO_ERROR;
113 UnicodeString result;
115 UnicodeString input=UNICODE_STRING_SIMPLE("www.eXample.cOm");
116 UnicodeString expected=UNICODE_STRING_SIMPLE("www.example.com");
117 trans->nameToASCII(input, result, info, errorCode);
118 if(U_FAILURE(errorCode) || info.hasErrors() || result!=expected) {
119 errln("T.nameToASCII(www.example.com) info.errors=%04lx result matches=%d %s",
120 (long)info.getErrors(), result==expected, u_errorName(errorCode));
122 errorCode=U_USELESS_COLLATOR_ERROR;
123 trans->nameToUnicode(input, result, info, errorCode);
124 if(errorCode!=U_USELESS_COLLATOR_ERROR || !result.isBogus()) {
125 errln("T.nameToUnicode(U_FAILURE) did not preserve the errorCode "
126 "or not result.setToBogus() - %s",
127 u_errorName(errorCode));
129 errorCode=U_ZERO_ERROR;
131 result=UNICODE_STRING_SIMPLE("quatsch");
132 nontrans->labelToASCII(input, result, info, errorCode);
133 if(errorCode!=U_ILLEGAL_ARGUMENT_ERROR || !result.isBogus()) {
134 errln("N.labelToASCII(bogus) did not set illegal-argument-error "
135 "or not result.setToBogus() - %s",
136 u_errorName(errorCode));
138 errorCode=U_ZERO_ERROR;
139 input=UNICODE_STRING_SIMPLE("xn--bcher.de-65a");
140 expected=UNICODE_STRING_SIMPLE("xn--bcher\\uFFFDde-65a").unescape();
141 nontrans->labelToASCII(input, result, info, errorCode);
142 if( U_FAILURE(errorCode) ||
143 info.getErrors()!=(UIDNA_ERROR_LABEL_HAS_DOT|UIDNA_ERROR_INVALID_ACE_LABEL) ||
146 errln("N.labelToASCII(label-with-dot) failed with errors %04lx - %s",
147 info.getErrors(), u_errorName(errorCode));
151 TestCheckedArrayByteSink sink(buffer, UPRV_LENGTHOF(buffer));
152 errorCode=U_ZERO_ERROR;
153 nontrans->labelToUnicodeUTF8(StringPiece(NULL, 5), sink, info, errorCode);
154 if(errorCode!=U_ILLEGAL_ARGUMENT_ERROR || sink.NumberOfBytesWritten()!=0) {
155 errln("N.labelToUnicodeUTF8(StringPiece(NULL, 5)) did not set illegal-argument-error ",
156 "or did output something - %s",
157 u_errorName(errorCode));
161 errorCode=U_ZERO_ERROR;
162 nontrans->nameToASCII_UTF8(StringPiece(), sink, info, errorCode);
163 if(U_FAILURE(errorCode) || sink.NumberOfBytesWritten()!=0 || !sink.calledFlush) {
164 errln("N.nameToASCII_UTF8(empty) failed - %s",
165 u_errorName(errorCode));
168 static const char s[]={ 0x61, (char)0xc3, (char)0x9f };
170 errorCode=U_USELESS_COLLATOR_ERROR;
171 nontrans->nameToUnicodeUTF8(StringPiece(s, 3), sink, info, errorCode);
172 if(errorCode!=U_USELESS_COLLATOR_ERROR || sink.NumberOfBytesWritten()!=0) {
173 errln("N.nameToUnicode_UTF8(U_FAILURE) did not preserve the errorCode "
174 "or did output something - %s",
175 u_errorName(errorCode));
179 errorCode=U_ZERO_ERROR;
180 trans->labelToUnicodeUTF8(StringPiece(s, 3), sink, info, errorCode);
181 if( U_FAILURE(errorCode) || sink.NumberOfBytesWritten()!=3 ||
182 buffer[0]!=0x61 || buffer[1]!=0x73 || buffer[2]!=0x73 ||
185 errln("T.labelToUnicodeUTF8(a sharp-s) failed - %s",
186 u_errorName(errorCode));
190 errorCode=U_ZERO_ERROR;
192 static const char eX[]={ 0x65, 0x58, 0x61, 0x6d, 0x70, 0x4c, 0x65, 0x2e, 0x63, 0x4f, 0x6d, 0 };
194 static const char ex[]={ 0x65, 0x78, 0x61, 0x6d, 0x70, 0x6c, 0x65, 0x2e, 0x63, 0x6f, 0x6d };
195 trans->nameToUnicodeUTF8(eX, sink, info, errorCode);
196 if( U_FAILURE(errorCode) || sink.NumberOfBytesWritten()!=11 ||
197 0!=memcmp(ex, buffer, 11) || !sink.calledFlush
199 errln("T.nameToUnicodeUTF8(eXampLe.cOm) failed - %s",
200 u_errorName(errorCode));
204 void UTS46Test::TestNotSTD3() {
205 IcuTestErrorCode errorCode(*this, "TestNotSTD3()");
207 LocalPointer<IDNA> not3(IDNA::createUTS46Instance(UIDNA_CHECK_BIDI, errorCode));
208 if(errorCode.isFailure()) {
211 UnicodeString input=UNICODE_STRING_SIMPLE("\\u0000A_2+2=4\\u000A.e\\u00DFen.net").unescape();
212 UnicodeString result;
214 if( not3->nameToUnicode(input, result, info, errorCode)!=
215 UNICODE_STRING_SIMPLE("\\u0000a_2+2=4\\u000A.essen.net").unescape() ||
218 prettify(result).extract(0, 0x7fffffff, buffer, UPRV_LENGTHOF(buffer));
219 errln("notSTD3.nameToUnicode(non-LDH ASCII) unexpected errors %04lx string %s",
220 (long)info.getErrors(), buffer);
222 // A space (BiDi class WS) is not allowed in a BiDi domain name.
223 input=UNICODE_STRING_SIMPLE("a z.xn--4db.edu");
224 not3->nameToASCII(input, result, info, errorCode);
225 if(result!=input || info.getErrors()!=UIDNA_ERROR_BIDI) {
226 errln("notSTD3.nameToASCII(ASCII-with-space.alef.edu) failed");
228 // Characters that are canonically equivalent to sequences with non-LDH ASCII.
229 input=UNICODE_STRING_SIMPLE("a\\u2260b\\u226Ec\\u226Fd").unescape();
230 not3->nameToUnicode(input, result, info, errorCode);
231 if(result!=input || info.hasErrors()) {
232 prettify(result).extract(0, 0x7fffffff, buffer, UPRV_LENGTHOF(buffer));
233 errln("notSTD3.nameToUnicode(equiv to non-LDH ASCII) unexpected errors %04lx string %s",
234 (long)info.getErrors(), buffer);
239 // Input string and options string (Nontransitional/Transitional/Both).
241 // Expected Unicode result string.
246 static const TestCase testCases[]={
247 { "www.eXample.cOm", "B", // all ASCII
248 "www.example.com", 0 },
249 { "B\\u00FCcher.de", "B", // u-umlaut
250 "b\\u00FCcher.de", 0 },
251 { "\\u00D6BB", "B", // O-umlaut
253 { "fa\\u00DF.de", "N", // sharp s
255 { "fa\\u00DF.de", "T", // sharp s
257 { "XN--fA-hia.dE", "B", // sharp s in Punycode
259 { "\\u03B2\\u03CC\\u03BB\\u03BF\\u03C2.com", "N", // Greek with final sigma
260 "\\u03B2\\u03CC\\u03BB\\u03BF\\u03C2.com", 0 },
261 { "\\u03B2\\u03CC\\u03BB\\u03BF\\u03C2.com", "T", // Greek with final sigma
262 "\\u03B2\\u03CC\\u03BB\\u03BF\\u03C3.com", 0 },
263 { "xn--nxasmm1c", "B", // Greek with final sigma in Punycode
264 "\\u03B2\\u03CC\\u03BB\\u03BF\\u03C2", 0 },
265 { "www.\\u0DC1\\u0DCA\\u200D\\u0DBB\\u0DD3.com", "N", // "Sri" in "Sri Lanka" has a ZWJ
266 "www.\\u0DC1\\u0DCA\\u200D\\u0DBB\\u0DD3.com", 0 },
267 { "www.\\u0DC1\\u0DCA\\u200D\\u0DBB\\u0DD3.com", "T", // "Sri" in "Sri Lanka" has a ZWJ
268 "www.\\u0DC1\\u0DCA\\u0DBB\\u0DD3.com", 0 },
269 { "www.xn--10cl1a0b660p.com", "B", // "Sri" in Punycode
270 "www.\\u0DC1\\u0DCA\\u200D\\u0DBB\\u0DD3.com", 0 },
271 { "\\u0646\\u0627\\u0645\\u0647\\u200C\\u0627\\u06CC", "N", // ZWNJ
272 "\\u0646\\u0627\\u0645\\u0647\\u200C\\u0627\\u06CC", 0 },
273 { "\\u0646\\u0627\\u0645\\u0647\\u200C\\u0627\\u06CC", "T", // ZWNJ
274 "\\u0646\\u0627\\u0645\\u0647\\u0627\\u06CC", 0 },
275 { "xn--mgba3gch31f060k.com", "B", // ZWNJ in Punycode
276 "\\u0646\\u0627\\u0645\\u0647\\u200C\\u0627\\u06CC.com", 0 },
277 { "a.b\\uFF0Ec\\u3002d\\uFF61", "B",
279 { "U\\u0308.xn--tda", "B", // U+umlaut.u-umlaut
280 "\\u00FC.\\u00FC", 0 },
281 { "xn--u-ccb", "B", // u+umlaut in Punycode
282 "xn--u-ccb\\uFFFD", UIDNA_ERROR_INVALID_ACE_LABEL },
283 { "a\\u2488com", "B", // contains 1-dot
284 "a\\uFFFDcom", UIDNA_ERROR_DISALLOWED },
285 { "xn--a-ecp.ru", "B", // contains 1-dot in Punycode
286 "xn--a-ecp\\uFFFD.ru", UIDNA_ERROR_INVALID_ACE_LABEL },
287 { "xn--0.pt", "B", // invalid Punycode
288 "xn--0\\uFFFD.pt", UIDNA_ERROR_PUNYCODE },
289 { "xn--a.pt", "B", // U+0080
290 "xn--a\\uFFFD.pt", UIDNA_ERROR_INVALID_ACE_LABEL },
291 { "xn--a-\\u00C4.pt", "B", // invalid Punycode
292 "xn--a-\\u00E4.pt", UIDNA_ERROR_PUNYCODE },
293 { "\\u65E5\\u672C\\u8A9E\\u3002\\uFF2A\\uFF30", "B", // Japanese with fullwidth ".jp"
294 "\\u65E5\\u672C\\u8A9E.jp", 0 },
295 { "\\u2615", "B", "\\u2615", 0 }, // Unicode 4.0 HOT BEVERAGE
296 // some characters are disallowed because they are canonically equivalent
297 // to sequences with non-LDH ASCII
298 { "a\\u2260b\\u226Ec\\u226Fd", "B",
299 "a\\uFFFDb\\uFFFDc\\uFFFDd", UIDNA_ERROR_DISALLOWED },
300 // many deviation characters, test the special mapping code
301 { "1.a\\u00DF\\u200C\\u200Db\\u200C\\u200Dc\\u00DF\\u00DF\\u00DF\\u00DFd"
302 "\\u03C2\\u03C3\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DFe"
303 "\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DFx"
304 "\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DFy"
305 "\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u0302\\u00DFz", "N",
306 "1.a\\u00DF\\u200C\\u200Db\\u200C\\u200Dc\\u00DF\\u00DF\\u00DF\\u00DFd"
307 "\\u03C2\\u03C3\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DFe"
308 "\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DFx"
309 "\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DFy"
310 "\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u0302\\u00DFz",
311 UIDNA_ERROR_LABEL_TOO_LONG|UIDNA_ERROR_CONTEXTJ },
312 { "1.a\\u00DF\\u200C\\u200Db\\u200C\\u200Dc\\u00DF\\u00DF\\u00DF\\u00DFd"
313 "\\u03C2\\u03C3\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DFe"
314 "\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DFx"
315 "\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DFy"
316 "\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u0302\\u00DFz", "T",
318 "\\u03C3\\u03C3sssssssssssssssse"
319 "ssssssssssssssssssssx"
320 "ssssssssssssssssssssy"
321 "sssssssssssssss\\u015Dssz", UIDNA_ERROR_LABEL_TOO_LONG },
322 // "xn--bss" with deviation characters
323 { "\\u200Cx\\u200Dn\\u200C-\\u200D-b\\u00DF", "N",
324 "\\u200Cx\\u200Dn\\u200C-\\u200D-b\\u00DF", UIDNA_ERROR_CONTEXTJ },
325 { "\\u200Cx\\u200Dn\\u200C-\\u200D-b\\u00DF", "T",
327 // "xn--bssffl" written as:
328 // 02E3 MODIFIER LETTER SMALL X
329 // 034F COMBINING GRAPHEME JOINER (ignored)
330 // 2115 DOUBLE-STRUCK CAPITAL N
331 // 200B ZERO WIDTH SPACE (ignored)
332 // FE63 SMALL HYPHEN-MINUS
333 // 00AD SOFT HYPHEN (ignored)
334 // FF0D FULLWIDTH HYPHEN-MINUS
335 // 180C MONGOLIAN FREE VARIATION SELECTOR TWO (ignored)
336 // 212C SCRIPT CAPITAL B
337 // FE00 VARIATION SELECTOR-1 (ignored)
338 // 017F LATIN SMALL LETTER LONG S
339 // 2064 INVISIBLE PLUS (ignored)
340 // 1D530 MATHEMATICAL FRAKTUR SMALL S
341 // E01EF VARIATION SELECTOR-256 (ignored)
342 // FB04 LATIN SMALL LIGATURE FFL
343 { "\\u02E3\\u034F\\u2115\\u200B\\uFE63\\u00AD\\uFF0D\\u180C"
344 "\\u212C\\uFE00\\u017F\\u2064\\U0001D530\\U000E01EF\\uFB04", "B",
345 "\\u5921\\u591E\\u591C\\u5919", 0 },
346 { "123456789012345678901234567890123456789012345678901234567890123."
347 "123456789012345678901234567890123456789012345678901234567890123."
348 "123456789012345678901234567890123456789012345678901234567890123."
349 "1234567890123456789012345678901234567890123456789012345678901", "B",
350 "123456789012345678901234567890123456789012345678901234567890123."
351 "123456789012345678901234567890123456789012345678901234567890123."
352 "123456789012345678901234567890123456789012345678901234567890123."
353 "1234567890123456789012345678901234567890123456789012345678901", 0 },
354 { "123456789012345678901234567890123456789012345678901234567890123."
355 "123456789012345678901234567890123456789012345678901234567890123."
356 "123456789012345678901234567890123456789012345678901234567890123."
357 "1234567890123456789012345678901234567890123456789012345678901.", "B",
358 "123456789012345678901234567890123456789012345678901234567890123."
359 "123456789012345678901234567890123456789012345678901234567890123."
360 "123456789012345678901234567890123456789012345678901234567890123."
361 "1234567890123456789012345678901234567890123456789012345678901.", 0 },
362 // Domain name >256 characters, forces slow path in UTF-8 processing.
363 { "123456789012345678901234567890123456789012345678901234567890123."
364 "123456789012345678901234567890123456789012345678901234567890123."
365 "123456789012345678901234567890123456789012345678901234567890123."
366 "123456789012345678901234567890123456789012345678901234567890123."
367 "12345678901234567890123456789012345678901234567890123456789012", "B",
368 "123456789012345678901234567890123456789012345678901234567890123."
369 "123456789012345678901234567890123456789012345678901234567890123."
370 "123456789012345678901234567890123456789012345678901234567890123."
371 "123456789012345678901234567890123456789012345678901234567890123."
372 "12345678901234567890123456789012345678901234567890123456789012",
373 UIDNA_ERROR_DOMAIN_NAME_TOO_LONG },
374 { "123456789012345678901234567890123456789012345678901234567890123."
375 "123456789012345678901234567890123456789012345678901234567890123."
376 "123456789012345678901234567890123456789012345678901234567890123."
377 "123456789012345678901234567890123456789012345678901234567890123."
378 "1234567890123456789012345678901234567890123456789\\u05D0", "B",
379 "123456789012345678901234567890123456789012345678901234567890123."
380 "123456789012345678901234567890123456789012345678901234567890123."
381 "123456789012345678901234567890123456789012345678901234567890123."
382 "123456789012345678901234567890123456789012345678901234567890123."
383 "1234567890123456789012345678901234567890123456789\\u05D0",
384 UIDNA_ERROR_DOMAIN_NAME_TOO_LONG|UIDNA_ERROR_BIDI },
385 { "123456789012345678901234567890123456789012345678901234567890123."
386 "1234567890123456789012345678901234567890123456789012345678901234."
387 "123456789012345678901234567890123456789012345678901234567890123."
388 "123456789012345678901234567890123456789012345678901234567890", "B",
389 "123456789012345678901234567890123456789012345678901234567890123."
390 "1234567890123456789012345678901234567890123456789012345678901234."
391 "123456789012345678901234567890123456789012345678901234567890123."
392 "123456789012345678901234567890123456789012345678901234567890",
393 UIDNA_ERROR_LABEL_TOO_LONG },
394 { "123456789012345678901234567890123456789012345678901234567890123."
395 "1234567890123456789012345678901234567890123456789012345678901234."
396 "123456789012345678901234567890123456789012345678901234567890123."
397 "123456789012345678901234567890123456789012345678901234567890.", "B",
398 "123456789012345678901234567890123456789012345678901234567890123."
399 "1234567890123456789012345678901234567890123456789012345678901234."
400 "123456789012345678901234567890123456789012345678901234567890123."
401 "123456789012345678901234567890123456789012345678901234567890.",
402 UIDNA_ERROR_LABEL_TOO_LONG },
403 { "123456789012345678901234567890123456789012345678901234567890123."
404 "1234567890123456789012345678901234567890123456789012345678901234."
405 "123456789012345678901234567890123456789012345678901234567890123."
406 "1234567890123456789012345678901234567890123456789012345678901", "B",
407 "123456789012345678901234567890123456789012345678901234567890123."
408 "1234567890123456789012345678901234567890123456789012345678901234."
409 "123456789012345678901234567890123456789012345678901234567890123."
410 "1234567890123456789012345678901234567890123456789012345678901",
411 UIDNA_ERROR_LABEL_TOO_LONG|UIDNA_ERROR_DOMAIN_NAME_TOO_LONG },
412 // label length 63: xn--1234567890123456789012345678901234567890123456789012345-9te
413 { "\\u00E41234567890123456789012345678901234567890123456789012345", "B",
414 "\\u00E41234567890123456789012345678901234567890123456789012345", 0 },
415 { "1234567890\\u00E41234567890123456789012345678901234567890123456", "B",
416 "1234567890\\u00E41234567890123456789012345678901234567890123456", UIDNA_ERROR_LABEL_TOO_LONG },
417 { "123456789012345678901234567890123456789012345678901234567890123."
418 "1234567890\\u00E4123456789012345678901234567890123456789012345."
419 "123456789012345678901234567890123456789012345678901234567890123."
420 "1234567890123456789012345678901234567890123456789012345678901", "B",
421 "123456789012345678901234567890123456789012345678901234567890123."
422 "1234567890\\u00E4123456789012345678901234567890123456789012345."
423 "123456789012345678901234567890123456789012345678901234567890123."
424 "1234567890123456789012345678901234567890123456789012345678901", 0 },
425 { "123456789012345678901234567890123456789012345678901234567890123."
426 "1234567890\\u00E4123456789012345678901234567890123456789012345."
427 "123456789012345678901234567890123456789012345678901234567890123."
428 "1234567890123456789012345678901234567890123456789012345678901.", "B",
429 "123456789012345678901234567890123456789012345678901234567890123."
430 "1234567890\\u00E4123456789012345678901234567890123456789012345."
431 "123456789012345678901234567890123456789012345678901234567890123."
432 "1234567890123456789012345678901234567890123456789012345678901.", 0 },
433 { "123456789012345678901234567890123456789012345678901234567890123."
434 "1234567890\\u00E4123456789012345678901234567890123456789012345."
435 "123456789012345678901234567890123456789012345678901234567890123."
436 "12345678901234567890123456789012345678901234567890123456789012", "B",
437 "123456789012345678901234567890123456789012345678901234567890123."
438 "1234567890\\u00E4123456789012345678901234567890123456789012345."
439 "123456789012345678901234567890123456789012345678901234567890123."
440 "12345678901234567890123456789012345678901234567890123456789012",
441 UIDNA_ERROR_DOMAIN_NAME_TOO_LONG },
442 { "123456789012345678901234567890123456789012345678901234567890123."
443 "1234567890\\u00E41234567890123456789012345678901234567890123456."
444 "123456789012345678901234567890123456789012345678901234567890123."
445 "123456789012345678901234567890123456789012345678901234567890", "B",
446 "123456789012345678901234567890123456789012345678901234567890123."
447 "1234567890\\u00E41234567890123456789012345678901234567890123456."
448 "123456789012345678901234567890123456789012345678901234567890123."
449 "123456789012345678901234567890123456789012345678901234567890",
450 UIDNA_ERROR_LABEL_TOO_LONG },
451 { "123456789012345678901234567890123456789012345678901234567890123."
452 "1234567890\\u00E41234567890123456789012345678901234567890123456."
453 "123456789012345678901234567890123456789012345678901234567890123."
454 "123456789012345678901234567890123456789012345678901234567890.", "B",
455 "123456789012345678901234567890123456789012345678901234567890123."
456 "1234567890\\u00E41234567890123456789012345678901234567890123456."
457 "123456789012345678901234567890123456789012345678901234567890123."
458 "123456789012345678901234567890123456789012345678901234567890.",
459 UIDNA_ERROR_LABEL_TOO_LONG },
460 { "123456789012345678901234567890123456789012345678901234567890123."
461 "1234567890\\u00E41234567890123456789012345678901234567890123456."
462 "123456789012345678901234567890123456789012345678901234567890123."
463 "1234567890123456789012345678901234567890123456789012345678901", "B",
464 "123456789012345678901234567890123456789012345678901234567890123."
465 "1234567890\\u00E41234567890123456789012345678901234567890123456."
466 "123456789012345678901234567890123456789012345678901234567890123."
467 "1234567890123456789012345678901234567890123456789012345678901",
468 UIDNA_ERROR_LABEL_TOO_LONG|UIDNA_ERROR_DOMAIN_NAME_TOO_LONG },
469 // hyphen errors and empty-label errors
470 // Ticket #10883: ToUnicode also checks for empty labels.
471 { ".", "B", ".", UIDNA_ERROR_EMPTY_LABEL },
472 { "\\uFF0E", "B", ".", UIDNA_ERROR_EMPTY_LABEL },
473 // "xn---q----jra"=="-q--a-umlaut-"
474 { "a.b..-q--a-.e", "B", "a.b..-q--a-.e",
475 UIDNA_ERROR_EMPTY_LABEL|UIDNA_ERROR_LEADING_HYPHEN|UIDNA_ERROR_TRAILING_HYPHEN|
476 UIDNA_ERROR_HYPHEN_3_4 },
477 { "a.b..-q--\\u00E4-.e", "B", "a.b..-q--\\u00E4-.e",
478 UIDNA_ERROR_EMPTY_LABEL|UIDNA_ERROR_LEADING_HYPHEN|UIDNA_ERROR_TRAILING_HYPHEN|
479 UIDNA_ERROR_HYPHEN_3_4 },
480 { "a.b..xn---q----jra.e", "B", "a.b..-q--\\u00E4-.e",
481 UIDNA_ERROR_EMPTY_LABEL|UIDNA_ERROR_LEADING_HYPHEN|UIDNA_ERROR_TRAILING_HYPHEN|
482 UIDNA_ERROR_HYPHEN_3_4 },
483 { "a..c", "B", "a..c", UIDNA_ERROR_EMPTY_LABEL },
484 { "a.xn--.c", "B", "a..c", UIDNA_ERROR_EMPTY_LABEL },
485 { "a.-b.", "B", "a.-b.", UIDNA_ERROR_LEADING_HYPHEN },
486 { "a.b-.c", "B", "a.b-.c", UIDNA_ERROR_TRAILING_HYPHEN },
487 { "a.-.c", "B", "a.-.c", UIDNA_ERROR_LEADING_HYPHEN|UIDNA_ERROR_TRAILING_HYPHEN },
488 { "a.bc--de.f", "B", "a.bc--de.f", UIDNA_ERROR_HYPHEN_3_4 },
489 { "\\u00E4.\\u00AD.c", "B", "\\u00E4..c", UIDNA_ERROR_EMPTY_LABEL },
490 { "\\u00E4.xn--.c", "B", "\\u00E4..c", UIDNA_ERROR_EMPTY_LABEL },
491 { "\\u00E4.-b.", "B", "\\u00E4.-b.", UIDNA_ERROR_LEADING_HYPHEN },
492 { "\\u00E4.b-.c", "B", "\\u00E4.b-.c", UIDNA_ERROR_TRAILING_HYPHEN },
493 { "\\u00E4.-.c", "B", "\\u00E4.-.c", UIDNA_ERROR_LEADING_HYPHEN|UIDNA_ERROR_TRAILING_HYPHEN },
494 { "\\u00E4.bc--de.f", "B", "\\u00E4.bc--de.f", UIDNA_ERROR_HYPHEN_3_4 },
495 { "a.b.\\u0308c.d", "B", "a.b.\\uFFFDc.d", UIDNA_ERROR_LEADING_COMBINING_MARK },
496 { "a.b.xn--c-bcb.d", "B",
497 "a.b.xn--c-bcb\\uFFFD.d", UIDNA_ERROR_LEADING_COMBINING_MARK|UIDNA_ERROR_INVALID_ACE_LABEL },
499 { "A0", "B", "a0", 0 },
500 { "0A", "B", "0a", 0 }, // all-LTR is ok to start with a digit (EN)
501 { "0A.\\u05D0", "B", // ASCII label does not start with L/R/AL
502 "0a.\\u05D0", UIDNA_ERROR_BIDI },
503 { "c.xn--0-eha.xn--4db", "B", // 2nd label does not start with L/R/AL
504 "c.0\\u00FC.\\u05D0", UIDNA_ERROR_BIDI },
505 { "b-.\\u05D0", "B", // label does not end with L/EN
506 "b-.\\u05D0", UIDNA_ERROR_TRAILING_HYPHEN|UIDNA_ERROR_BIDI },
507 { "d.xn----dha.xn--4db", "B", // 2nd label does not end with L/EN
508 "d.\\u00FC-.\\u05D0", UIDNA_ERROR_TRAILING_HYPHEN|UIDNA_ERROR_BIDI },
509 { "a\\u05D0", "B", "a\\u05D0", UIDNA_ERROR_BIDI }, // first dir != last dir
510 { "\\u05D0\\u05C7", "B", "\\u05D0\\u05C7", 0 },
511 { "\\u05D09\\u05C7", "B", "\\u05D09\\u05C7", 0 },
512 { "\\u05D0a\\u05C7", "B", "\\u05D0a\\u05C7", UIDNA_ERROR_BIDI }, // first dir != last dir
513 { "\\u05D0\\u05EA", "B", "\\u05D0\\u05EA", 0 },
514 { "\\u05D0\\u05F3\\u05EA", "B", "\\u05D0\\u05F3\\u05EA", 0 },
515 { "a\\u05D0Tz", "B", "a\\u05D0tz", UIDNA_ERROR_BIDI }, // mixed dir
516 { "\\u05D0T\\u05EA", "B", "\\u05D0t\\u05EA", UIDNA_ERROR_BIDI }, // mixed dir
517 { "\\u05D07\\u05EA", "B", "\\u05D07\\u05EA", 0 },
518 { "\\u05D0\\u0667\\u05EA", "B", "\\u05D0\\u0667\\u05EA", 0 }, // Arabic 7 in the middle
519 { "a7\\u0667z", "B", "a7\\u0667z", UIDNA_ERROR_BIDI }, // AN digit in LTR
520 { "\\u05D07\\u0667\\u05EA", "B", // mixed EN/AN digits in RTL
521 "\\u05D07\\u0667\\u05EA", UIDNA_ERROR_BIDI },
523 { "\\u0BB9\\u0BCD\\u200D", "N", "\\u0BB9\\u0BCD\\u200D", 0 }, // Virama+ZWJ
524 { "\\u0BB9\\u200D", "N", "\\u0BB9\\u200D", UIDNA_ERROR_CONTEXTJ }, // no Virama
525 { "\\u200D", "N", "\\u200D", UIDNA_ERROR_CONTEXTJ }, // no Virama
527 { "\\u0BB9\\u0BCD\\u200C", "N", "\\u0BB9\\u0BCD\\u200C", 0 }, // Virama+ZWNJ
528 { "\\u0BB9\\u200C", "N", "\\u0BB9\\u200C", UIDNA_ERROR_CONTEXTJ }, // no Virama
529 { "\\u200C", "N", "\\u200C", UIDNA_ERROR_CONTEXTJ }, // no Virama
530 { "\\u0644\\u0670\\u200C\\u06ED\\u06EF", "N", // Joining types D T ZWNJ T R
531 "\\u0644\\u0670\\u200C\\u06ED\\u06EF", 0 },
532 { "\\u0644\\u0670\\u200C\\u06EF", "N", // D T ZWNJ R
533 "\\u0644\\u0670\\u200C\\u06EF", 0 },
534 { "\\u0644\\u200C\\u06ED\\u06EF", "N", // D ZWNJ T R
535 "\\u0644\\u200C\\u06ED\\u06EF", 0 },
536 { "\\u0644\\u200C\\u06EF", "N", // D ZWNJ R
537 "\\u0644\\u200C\\u06EF", 0 },
538 { "\\u0644\\u0670\\u200C\\u06ED", "N", // D T ZWNJ T
539 "\\u0644\\u0670\\u200C\\u06ED", UIDNA_ERROR_BIDI|UIDNA_ERROR_CONTEXTJ },
540 { "\\u06EF\\u200C\\u06EF", "N", // R ZWNJ R
541 "\\u06EF\\u200C\\u06EF", UIDNA_ERROR_CONTEXTJ },
542 { "\\u0644\\u200C", "N", // D ZWNJ
543 "\\u0644\\u200C", UIDNA_ERROR_BIDI|UIDNA_ERROR_CONTEXTJ },
544 { "\\u0660\\u0661", "B", // Arabic-Indic Digits alone
545 "\\u0660\\u0661", UIDNA_ERROR_BIDI },
546 { "\\u06F0\\u06F1", "B", // Extended Arabic-Indic Digits alone
547 "\\u06F0\\u06F1", 0 },
548 { "\\u0660\\u06F1", "B", // Mixed Arabic-Indic Digits
549 "\\u0660\\u06F1", UIDNA_ERROR_CONTEXTO_DIGITS|UIDNA_ERROR_BIDI },
550 // All of the CONTEXTO "Would otherwise have been DISALLOWED" characters
551 // in their correct contexts,
552 // then each in incorrect context.
553 { "l\\u00B7l\\u4E00\\u0375\\u03B1\\u05D0\\u05F3\\u05F4\\u30FB", "B",
554 "l\\u00B7l\\u4E00\\u0375\\u03B1\\u05D0\\u05F3\\u05F4\\u30FB", UIDNA_ERROR_BIDI },
556 "l\\u00B7", UIDNA_ERROR_CONTEXTO_PUNCTUATION },
558 "\\u00B7l", UIDNA_ERROR_CONTEXTO_PUNCTUATION },
560 "\\u0375", UIDNA_ERROR_CONTEXTO_PUNCTUATION },
561 { "\\u03B1\\u05F3", "B",
562 "\\u03B1\\u05F3", UIDNA_ERROR_CONTEXTO_PUNCTUATION|UIDNA_ERROR_BIDI },
564 "\\u05F4", UIDNA_ERROR_CONTEXTO_PUNCTUATION },
566 "l\\u30FB", UIDNA_ERROR_CONTEXTO_PUNCTUATION },
567 // Ticket #8137: UTS #46 toUnicode() fails with non-ASCII labels that turn
568 // into 15 characters (UChars).
569 // The bug was in u_strFromPunycode() which did not write the last character
570 // if it just so fit into the end of the destination buffer.
571 // The UTS #46 code gives a default-capacity UnicodeString as the destination buffer,
572 // and the internal UnicodeString capacity is currently 15 UChars on 64-bit machines
573 // but 13 on 32-bit machines.
574 // Label with 15 UChars, for 64-bit-machine testing:
575 { "aaaaaaaaaaaaa\\u00FCa.de", "B", "aaaaaaaaaaaaa\\u00FCa.de", 0 },
576 { "xn--aaaaaaaaaaaaaa-ssb.de", "B", "aaaaaaaaaaaaa\\u00FCa.de", 0 },
577 { "abschlu\\u00DFpr\\u00FCfung.de", "N", "abschlu\\u00DFpr\\u00FCfung.de", 0 },
578 { "xn--abschluprfung-hdb15b.de", "B", "abschlu\\u00DFpr\\u00FCfung.de", 0 },
579 // Label with 13 UChars, for 32-bit-machine testing:
580 { "xn--aaaaaaaaaaaa-nlb.de", "B", "aaaaaaaaaaa\\u00FCa.de", 0 },
581 { "xn--schluprfung-z6a39a.de", "B", "schlu\\u00DFpr\\u00FCfung.de", 0 },
586 void UTS46Test::TestSomeCases() {
587 IcuTestErrorCode errorCode(*this, "TestSomeCases");
588 char buffer[400], buffer2[400];
590 for(i=0; i<UPRV_LENGTHOF(testCases); ++i) {
591 const TestCase &testCase=testCases[i];
592 UnicodeString input(ctou(testCase.s));
593 UnicodeString expected(ctou(testCase.u));
594 // ToASCII/ToUnicode, transitional/nontransitional
595 UnicodeString aT, uT, aN, uN;
596 IDNAInfo aTInfo, uTInfo, aNInfo, uNInfo;
597 trans->nameToASCII(input, aT, aTInfo, errorCode);
598 trans->nameToUnicode(input, uT, uTInfo, errorCode);
599 nontrans->nameToASCII(input, aN, aNInfo, errorCode);
600 nontrans->nameToUnicode(input, uN, uNInfo, errorCode);
601 if(errorCode.logIfFailureAndReset("first-level processing [%d/%s] %s",
602 (int)i, testCase.o, testCase.s)
606 // ToUnicode does not set length-overflow errors.
607 uint32_t uniErrors=testCase.errors&~
608 (UIDNA_ERROR_LABEL_TOO_LONG|
609 UIDNA_ERROR_DOMAIN_NAME_TOO_LONG);
610 char mode=testCase.o[0];
611 if(mode=='B' || mode=='N') {
612 if(uNInfo.getErrors()!=uniErrors) {
613 errln("N.nameToUnicode([%d] %s) unexpected errors %04lx",
614 (int)i, testCase.s, (long)uNInfo.getErrors());
618 prettify(uN).extract(0, 0x7fffffff, buffer, UPRV_LENGTHOF(buffer));
619 errln("N.nameToUnicode([%d] %s) unexpected string %s",
620 (int)i, testCase.s, buffer);
623 if(aNInfo.getErrors()!=testCase.errors) {
624 errln("N.nameToASCII([%d] %s) unexpected errors %04lx",
625 (int)i, testCase.s, (long)aNInfo.getErrors());
629 if(mode=='B' || mode=='T') {
630 if(uTInfo.getErrors()!=uniErrors) {
631 errln("T.nameToUnicode([%d] %s) unexpected errors %04lx",
632 (int)i, testCase.s, (long)uTInfo.getErrors());
636 prettify(uT).extract(0, 0x7fffffff, buffer, UPRV_LENGTHOF(buffer));
637 errln("T.nameToUnicode([%d] %s) unexpected string %s",
638 (int)i, testCase.s, buffer);
641 if(aTInfo.getErrors()!=testCase.errors) {
642 errln("T.nameToASCII([%d] %s) unexpected errors %04lx",
643 (int)i, testCase.s, (long)aTInfo.getErrors());
647 // ToASCII is all-ASCII if no severe errors
648 if((aNInfo.getErrors()&severeErrors)==0 && !isASCII(aN)) {
649 prettify(aN).extract(0, 0x7fffffff, buffer, UPRV_LENGTHOF(buffer));
650 errln("N.nameToASCII([%d] %s) (errors %04lx) result is not ASCII %s",
651 (int)i, testCase.s, aNInfo.getErrors(), buffer);
654 if((aTInfo.getErrors()&severeErrors)==0 && !isASCII(aT)) {
655 prettify(aT).extract(0, 0x7fffffff, buffer, UPRV_LENGTHOF(buffer));
656 errln("T.nameToASCII([%d] %s) (errors %04lx) result is not ASCII %s",
657 (int)i, testCase.s, aTInfo.getErrors(), buffer);
661 char m= mode=='B' ? mode : 'N';
662 prettify(aN).extract(0, 0x7fffffff, buffer, UPRV_LENGTHOF(buffer));
663 logln("%c.nameToASCII([%d] %s) (errors %04lx) result string: %s",
664 m, (int)i, testCase.s, aNInfo.getErrors(), buffer);
666 prettify(aT).extract(0, 0x7fffffff, buffer, UPRV_LENGTHOF(buffer));
667 logln("T.nameToASCII([%d] %s) (errors %04lx) result string: %s",
668 (int)i, testCase.s, aTInfo.getErrors(), buffer);
671 // second-level processing
672 UnicodeString aTuN, uTaN, aNuN, uNaN;
673 IDNAInfo aTuNInfo, uTaNInfo, aNuNInfo, uNaNInfo;
674 nontrans->nameToUnicode(aT, aTuN, aTuNInfo, errorCode);
675 nontrans->nameToASCII(uT, uTaN, uTaNInfo, errorCode);
676 nontrans->nameToUnicode(aN, aNuN, aNuNInfo, errorCode);
677 nontrans->nameToASCII(uN, uNaN, uNaNInfo, errorCode);
678 if(errorCode.logIfFailureAndReset("second-level processing [%d/%s] %s",
679 (int)i, testCase.o, testCase.s)
684 prettify(aN).extract(0, 0x7fffffff, buffer, UPRV_LENGTHOF(buffer));
685 prettify(uNaN).extract(0, 0x7fffffff, buffer2, UPRV_LENGTHOF(buffer2));
686 errln("N.nameToASCII([%d] %s)!=N.nameToUnicode().N.nameToASCII() "
687 "(errors %04lx) %s vs. %s",
688 (int)i, testCase.s, aNInfo.getErrors(), buffer, buffer2);
692 prettify(aT).extract(0, 0x7fffffff, buffer, UPRV_LENGTHOF(buffer));
693 prettify(uTaN).extract(0, 0x7fffffff, buffer2, UPRV_LENGTHOF(buffer2));
694 errln("T.nameToASCII([%d] %s)!=T.nameToUnicode().N.nameToASCII() "
695 "(errors %04lx) %s vs. %s",
696 (int)i, testCase.s, aNInfo.getErrors(), buffer, buffer2);
700 prettify(uN).extract(0, 0x7fffffff, buffer, UPRV_LENGTHOF(buffer));
701 prettify(aNuN).extract(0, 0x7fffffff, buffer2, UPRV_LENGTHOF(buffer2));
702 errln("N.nameToUnicode([%d] %s)!=N.nameToASCII().N.nameToUnicode() "
703 "(errors %04lx) %s vs. %s",
704 (int)i, testCase.s, uNInfo.getErrors(), buffer, buffer2);
708 prettify(uT).extract(0, 0x7fffffff, buffer, UPRV_LENGTHOF(buffer));
709 prettify(aTuN).extract(0, 0x7fffffff, buffer2, UPRV_LENGTHOF(buffer2));
710 errln("T.nameToUnicode([%d] %s)!=T.nameToASCII().N.nameToUnicode() "
711 "(errors %04lx) %s vs. %s",
712 (int)i, testCase.s, uNInfo.getErrors(), buffer, buffer2);
716 UnicodeString aTL, uTL, aNL, uNL;
717 IDNAInfo aTLInfo, uTLInfo, aNLInfo, uNLInfo;
718 trans->labelToASCII(input, aTL, aTLInfo, errorCode);
719 trans->labelToUnicode(input, uTL, uTLInfo, errorCode);
720 nontrans->labelToASCII(input, aNL, aNLInfo, errorCode);
721 nontrans->labelToUnicode(input, uNL, uNLInfo, errorCode);
722 if(errorCode.logIfFailureAndReset("labelToXYZ processing [%d/%s] %s",
723 (int)i, testCase.o, testCase.s)
727 if(aN.indexOf((UChar)0x2e)<0) {
728 if(aN!=aNL || aNInfo.getErrors()!=aNLInfo.getErrors()) {
729 prettify(aN).extract(0, 0x7fffffff, buffer, UPRV_LENGTHOF(buffer));
730 prettify(aNL).extract(0, 0x7fffffff, buffer2, UPRV_LENGTHOF(buffer2));
731 errln("N.nameToASCII([%d] %s)!=N.labelToASCII() "
732 "(errors %04lx vs %04lx) %s vs. %s",
733 (int)i, testCase.s, aNInfo.getErrors(), aNLInfo.getErrors(), buffer, buffer2);
737 if((aNLInfo.getErrors()&UIDNA_ERROR_LABEL_HAS_DOT)==0) {
738 errln("N.labelToASCII([%d] %s) errors %04lx missing UIDNA_ERROR_LABEL_HAS_DOT",
739 (int)i, testCase.s, (long)aNLInfo.getErrors());
743 if(aT.indexOf((UChar)0x2e)<0) {
744 if(aT!=aTL || aTInfo.getErrors()!=aTLInfo.getErrors()) {
745 prettify(aT).extract(0, 0x7fffffff, buffer, UPRV_LENGTHOF(buffer));
746 prettify(aTL).extract(0, 0x7fffffff, buffer2, UPRV_LENGTHOF(buffer2));
747 errln("T.nameToASCII([%d] %s)!=T.labelToASCII() "
748 "(errors %04lx vs %04lx) %s vs. %s",
749 (int)i, testCase.s, aTInfo.getErrors(), aTLInfo.getErrors(), buffer, buffer2);
753 if((aTLInfo.getErrors()&UIDNA_ERROR_LABEL_HAS_DOT)==0) {
754 errln("T.labelToASCII([%d] %s) errors %04lx missing UIDNA_ERROR_LABEL_HAS_DOT",
755 (int)i, testCase.s, (long)aTLInfo.getErrors());
759 if(uN.indexOf((UChar)0x2e)<0) {
760 if(uN!=uNL || uNInfo.getErrors()!=uNLInfo.getErrors()) {
761 prettify(uN).extract(0, 0x7fffffff, buffer, UPRV_LENGTHOF(buffer));
762 prettify(uNL).extract(0, 0x7fffffff, buffer2, UPRV_LENGTHOF(buffer2));
763 errln("N.nameToUnicode([%d] %s)!=N.labelToUnicode() "
764 "(errors %04lx vs %04lx) %s vs. %s",
765 (int)i, testCase.s, uNInfo.getErrors(), uNLInfo.getErrors(), buffer, buffer2);
769 if((uNLInfo.getErrors()&UIDNA_ERROR_LABEL_HAS_DOT)==0) {
770 errln("N.labelToUnicode([%d] %s) errors %04lx missing UIDNA_ERROR_LABEL_HAS_DOT",
771 (int)i, testCase.s, (long)uNLInfo.getErrors());
775 if(uT.indexOf((UChar)0x2e)<0) {
776 if(uT!=uTL || uTInfo.getErrors()!=uTLInfo.getErrors()) {
777 prettify(uT).extract(0, 0x7fffffff, buffer, UPRV_LENGTHOF(buffer));
778 prettify(uTL).extract(0, 0x7fffffff, buffer2, UPRV_LENGTHOF(buffer2));
779 errln("T.nameToUnicode([%d] %s)!=T.labelToUnicode() "
780 "(errors %04lx vs %04lx) %s vs. %s",
781 (int)i, testCase.s, uTInfo.getErrors(), uTLInfo.getErrors(), buffer, buffer2);
785 if((uTLInfo.getErrors()&UIDNA_ERROR_LABEL_HAS_DOT)==0) {
786 errln("T.labelToUnicode([%d] %s) errors %04lx missing UIDNA_ERROR_LABEL_HAS_DOT",
787 (int)i, testCase.s, (long)uTLInfo.getErrors());
791 // Differences between transitional and nontransitional processing
793 if( aNInfo.isTransitionalDifferent() ||
794 aTInfo.isTransitionalDifferent() ||
795 uNInfo.isTransitionalDifferent() ||
796 uTInfo.isTransitionalDifferent() ||
797 aNLInfo.isTransitionalDifferent() ||
798 aTLInfo.isTransitionalDifferent() ||
799 uNLInfo.isTransitionalDifferent() ||
800 uTLInfo.isTransitionalDifferent()
802 errln("B.process([%d] %s) isTransitionalDifferent()", (int)i, testCase.s);
805 if( aN!=aT || uN!=uT || aNL!=aTL || uNL!=uTL ||
806 aNInfo.getErrors()!=aTInfo.getErrors() || uNInfo.getErrors()!=uTInfo.getErrors() ||
807 aNLInfo.getErrors()!=aTLInfo.getErrors() || uNLInfo.getErrors()!=uTLInfo.getErrors()
809 errln("N.process([%d] %s) vs. T.process() different errors or result strings",
814 if( !aNInfo.isTransitionalDifferent() ||
815 !aTInfo.isTransitionalDifferent() ||
816 !uNInfo.isTransitionalDifferent() ||
817 !uTInfo.isTransitionalDifferent() ||
818 !aNLInfo.isTransitionalDifferent() ||
819 !aTLInfo.isTransitionalDifferent() ||
820 !uNLInfo.isTransitionalDifferent() ||
821 !uTLInfo.isTransitionalDifferent()
823 errln("%s.process([%d] %s) !isTransitionalDifferent()",
824 testCase.o, (int)i, testCase.s);
827 if(aN==aT || uN==uT || aNL==aTL || uNL==uTL) {
828 errln("N.process([%d] %s) vs. T.process() same result strings",
833 // UTF-8 if we have std::string
834 #if U_HAVE_STD_STRING
835 std::string input8, aT8, uT8, aN8, uN8;
836 StringByteSink<std::string> aT8Sink(&aT8), uT8Sink(&uT8), aN8Sink(&aN8), uN8Sink(&uN8);
837 IDNAInfo aT8Info, uT8Info, aN8Info, uN8Info;
838 input.toUTF8String(input8);
839 trans->nameToASCII_UTF8(input8, aT8Sink, aT8Info, errorCode);
840 trans->nameToUnicodeUTF8(input8, uT8Sink, uT8Info, errorCode);
841 nontrans->nameToASCII_UTF8(input8, aN8Sink, aN8Info, errorCode);
842 nontrans->nameToUnicodeUTF8(input8, uN8Sink, uN8Info, errorCode);
843 if(errorCode.logIfFailureAndReset("UTF-8 processing [%d/%s] %s",
844 (int)i, testCase.o, testCase.s)
848 UnicodeString aT16(UnicodeString::fromUTF8(aT8));
849 UnicodeString uT16(UnicodeString::fromUTF8(uT8));
850 UnicodeString aN16(UnicodeString::fromUTF8(aN8));
851 UnicodeString uN16(UnicodeString::fromUTF8(uN8));
852 if( aN8Info.getErrors()!=aNInfo.getErrors() ||
853 uN8Info.getErrors()!=uNInfo.getErrors()
855 errln("N.xyzUTF8([%d] %s) vs. UTF-16 processing different errors %04lx vs. %04lx",
857 (long)aN8Info.getErrors(), (long)aNInfo.getErrors());
860 if( aT8Info.getErrors()!=aTInfo.getErrors() ||
861 uT8Info.getErrors()!=uTInfo.getErrors()
863 errln("T.xyzUTF8([%d] %s) vs. UTF-16 processing different errors %04lx vs. %04lx",
865 (long)aT8Info.getErrors(), (long)aTInfo.getErrors());
868 if(aT16!=aT || uT16!=uT || aN16!=aN || uN16!=uN) {
869 errln("%s.xyzUTF8([%d] %s) vs. UTF-16 processing different string results",
870 testCase.o, (int)i, testCase.s, (long)aTInfo.getErrors());
873 if( aT8Info.isTransitionalDifferent()!=aTInfo.isTransitionalDifferent() ||
874 uT8Info.isTransitionalDifferent()!=uTInfo.isTransitionalDifferent() ||
875 aN8Info.isTransitionalDifferent()!=aNInfo.isTransitionalDifferent() ||
876 uN8Info.isTransitionalDifferent()!=uNInfo.isTransitionalDifferent()
878 errln("%s.xyzUTF8([%d] %s) vs. UTF-16 processing different isTransitionalDifferent()",
879 testCase.o, (int)i, testCase.s);
886 #endif // UCONFIG_NO_IDNA