2 *******************************************************************************
3 * Copyright (C) 2010-2011, International Business Machines
4 * Corporation and others. All Rights Reserved.
5 *******************************************************************************
6 * file name: uts46test.cpp
8 * tab size: 8 (not used)
11 * created on: 2010may05
12 * created by: Markus W. Scherer
15 #include "unicode/utypes.h"
20 #include "unicode/bytestream.h"
21 #include "unicode/idna.h"
22 #include "unicode/localpointer.h"
23 #include "unicode/std_string.h"
24 #include "unicode/stringpiece.h"
25 #include "unicode/uidna.h"
26 #include "unicode/unistr.h"
29 #define LENGTHOF(array) (int32_t)(sizeof(array)/sizeof((array)[0]))
31 class UTS46Test
: public IntlTest
{
33 UTS46Test() : trans(NULL
), nontrans(NULL
) {}
36 void runIndexedTest(int32_t index
, UBool exec
, const char *&name
, char *par
=NULL
);
41 IDNA
*trans
, *nontrans
;
44 extern IntlTest
*createUTS46Test() {
45 return new UTS46Test();
48 UTS46Test::~UTS46Test() {
53 void UTS46Test::runIndexedTest(int32_t index
, UBool exec
, const char *&name
, char * /*par*/) {
55 logln("TestSuite UTS46Test: ");
57 IcuTestErrorCode
errorCode(*this, "init/createUTS46Instance()");
58 uint32_t commonOptions
=
59 UIDNA_USE_STD3_RULES
|UIDNA_CHECK_BIDI
|
60 UIDNA_CHECK_CONTEXTJ
|UIDNA_CHECK_CONTEXTO
;
61 trans
=IDNA::createUTS46Instance(commonOptions
, errorCode
);
62 nontrans
=IDNA::createUTS46Instance(
64 UIDNA_NONTRANSITIONAL_TO_ASCII
|UIDNA_NONTRANSITIONAL_TO_UNICODE
,
66 if(errorCode
.logDataIfFailureAndReset("createUTS46Instance()")) {
73 TESTCASE_AUTO(TestAPI
);
74 TESTCASE_AUTO(TestNotSTD3
);
75 TESTCASE_AUTO(TestSomeCases
);
79 const uint32_t severeErrors
=
80 UIDNA_ERROR_LEADING_COMBINING_MARK
|
81 UIDNA_ERROR_DISALLOWED
|
83 UIDNA_ERROR_LABEL_HAS_DOT
|
84 UIDNA_ERROR_INVALID_ACE_LABEL
;
86 static UBool
isASCII(const UnicodeString
&str
) {
87 const UChar
*s
=str
.getBuffer();
88 int32_t length
=str
.length();
89 for(int32_t i
=0; i
<length
; ++i
) {
97 class TestCheckedArrayByteSink
: public CheckedArrayByteSink
{
99 TestCheckedArrayByteSink(char* outbuf
, int32_t capacity
)
100 : CheckedArrayByteSink(outbuf
, capacity
), calledFlush(FALSE
) {}
101 virtual CheckedArrayByteSink
& Reset() {
102 CheckedArrayByteSink::Reset();
106 virtual void Flush() { calledFlush
= TRUE
; }
110 void UTS46Test::TestAPI() {
111 UErrorCode errorCode
=U_ZERO_ERROR
;
112 UnicodeString result
;
114 UnicodeString input
=UNICODE_STRING_SIMPLE("www.eXample.cOm");
115 UnicodeString expected
=UNICODE_STRING_SIMPLE("www.example.com");
116 trans
->nameToASCII(input
, result
, info
, errorCode
);
117 if(U_FAILURE(errorCode
) || info
.hasErrors() || result
!=expected
) {
118 errln("T.nameToASCII(www.example.com) info.errors=%04lx result matches=%d %s",
119 (long)info
.getErrors(), result
==expected
, u_errorName(errorCode
));
121 errorCode
=U_USELESS_COLLATOR_ERROR
;
122 trans
->nameToUnicode(input
, result
, info
, errorCode
);
123 if(errorCode
!=U_USELESS_COLLATOR_ERROR
|| !result
.isBogus()) {
124 errln("T.nameToUnicode(U_FAILURE) did not preserve the errorCode "
125 "or not result.setToBogus() - %s",
126 u_errorName(errorCode
));
128 errorCode
=U_ZERO_ERROR
;
130 result
=UNICODE_STRING_SIMPLE("quatsch");
131 nontrans
->labelToASCII(input
, result
, info
, errorCode
);
132 if(errorCode
!=U_ILLEGAL_ARGUMENT_ERROR
|| !result
.isBogus()) {
133 errln("N.labelToASCII(bogus) did not set illegal-argument-error "
134 "or not result.setToBogus() - %s",
135 u_errorName(errorCode
));
137 errorCode
=U_ZERO_ERROR
;
138 input
=UNICODE_STRING_SIMPLE("xn--bcher.de-65a");
139 expected
=UNICODE_STRING_SIMPLE("xn--bcher\\uFFFDde-65a").unescape();
140 nontrans
->labelToASCII(input
, result
, info
, errorCode
);
141 if( U_FAILURE(errorCode
) ||
142 info
.getErrors()!=(UIDNA_ERROR_LABEL_HAS_DOT
|UIDNA_ERROR_INVALID_ACE_LABEL
) ||
145 errln("N.labelToASCII(label-with-dot) failed with errors %04lx - %s",
146 info
.getErrors(), u_errorName(errorCode
));
150 TestCheckedArrayByteSink
sink(buffer
, LENGTHOF(buffer
));
151 errorCode
=U_ZERO_ERROR
;
152 nontrans
->labelToUnicodeUTF8(StringPiece(NULL
, 5), sink
, info
, errorCode
);
153 if(errorCode
!=U_ILLEGAL_ARGUMENT_ERROR
|| sink
.NumberOfBytesWritten()!=0) {
154 errln("N.labelToUnicodeUTF8(StringPiece(NULL, 5)) did not set illegal-argument-error ",
155 "or did output something - %s",
156 u_errorName(errorCode
));
160 errorCode
=U_ZERO_ERROR
;
161 nontrans
->nameToASCII_UTF8(StringPiece(), sink
, info
, errorCode
);
162 if(U_FAILURE(errorCode
) || sink
.NumberOfBytesWritten()!=0 || !sink
.calledFlush
) {
163 errln("N.nameToASCII_UTF8(empty) failed - %s",
164 u_errorName(errorCode
));
167 static const char s
[]={ 0x61, (char)0xc3, (char)0x9f };
169 errorCode
=U_USELESS_COLLATOR_ERROR
;
170 nontrans
->nameToUnicodeUTF8(StringPiece(s
, 3), sink
, info
, errorCode
);
171 if(errorCode
!=U_USELESS_COLLATOR_ERROR
|| sink
.NumberOfBytesWritten()!=0) {
172 errln("N.nameToUnicode_UTF8(U_FAILURE) did not preserve the errorCode "
173 "or did output something - %s",
174 u_errorName(errorCode
));
178 errorCode
=U_ZERO_ERROR
;
179 trans
->labelToUnicodeUTF8(StringPiece(s
, 3), sink
, info
, errorCode
);
180 if( U_FAILURE(errorCode
) || sink
.NumberOfBytesWritten()!=3 ||
181 buffer
[0]!=0x61 || buffer
[1]!=0x73 || buffer
[2]!=0x73 ||
184 errln("T.labelToUnicodeUTF8(a sharp-s) failed - %s",
185 u_errorName(errorCode
));
189 errorCode
=U_ZERO_ERROR
;
191 static const char eX
[]={ 0x65, 0x58, 0x61, 0x6d, 0x70, 0x4c, 0x65, 0x2e, 0x63, 0x4f, 0x6d, 0 };
193 static const char ex
[]={ 0x65, 0x78, 0x61, 0x6d, 0x70, 0x6c, 0x65, 0x2e, 0x63, 0x6f, 0x6d };
194 trans
->nameToUnicodeUTF8(eX
, sink
, info
, errorCode
);
195 if( U_FAILURE(errorCode
) || sink
.NumberOfBytesWritten()!=11 ||
196 0!=memcmp(ex
, buffer
, 11) || !sink
.calledFlush
198 errln("T.nameToUnicodeUTF8(eXampLe.cOm) failed - %s",
199 u_errorName(errorCode
));
203 void UTS46Test::TestNotSTD3() {
204 IcuTestErrorCode
errorCode(*this, "TestNotSTD3()");
206 LocalPointer
<IDNA
> not3(IDNA::createUTS46Instance(UIDNA_CHECK_BIDI
, errorCode
));
207 if(errorCode
.isFailure()) {
210 UnicodeString input
=UNICODE_STRING_SIMPLE("\\u0000A_2+2=4\\u000A.e\\u00DFen.net").unescape();
211 UnicodeString result
;
213 if( not3
->nameToUnicode(input
, result
, info
, errorCode
)!=
214 UNICODE_STRING_SIMPLE("\\u0000a_2+2=4\\u000A.essen.net").unescape() ||
217 prettify(result
).extract(0, 0x7fffffff, buffer
, LENGTHOF(buffer
));
218 errln("notSTD3.nameToUnicode(non-LDH ASCII) unexpected errors %04lx string %s",
219 (long)info
.getErrors(), buffer
);
221 // A space (BiDi class WS) is not allowed in a BiDi domain name.
222 input
=UNICODE_STRING_SIMPLE("a z.xn--4db.edu");
223 not3
->nameToASCII(input
, result
, info
, errorCode
);
224 if(result
!=input
|| info
.getErrors()!=UIDNA_ERROR_BIDI
) {
225 errln("notSTD3.nameToASCII(ASCII-with-space.alef.edu) failed");
227 // Characters that are canonically equivalent to sequences with non-LDH ASCII.
228 input
=UNICODE_STRING_SIMPLE("a\\u2260b\\u226Ec\\u226Fd").unescape();
229 not3
->nameToUnicode(input
, result
, info
, errorCode
);
230 if(result
!=input
|| info
.hasErrors()) {
231 prettify(result
).extract(0, 0x7fffffff, buffer
, LENGTHOF(buffer
));
232 errln("notSTD3.nameToUnicode(equiv to non-LDH ASCII) unexpected errors %04lx string %s",
233 (long)info
.getErrors(), buffer
);
238 // Input string and options string (Nontransitional/Transitional/Both).
240 // Expected Unicode result string.
245 static const TestCase testCases
[]={
246 { "www.eXample.cOm", "B", // all ASCII
247 "www.example.com", 0 },
248 { "B\\u00FCcher.de", "B", // u-umlaut
249 "b\\u00FCcher.de", 0 },
250 { "\\u00D6BB", "B", // O-umlaut
252 { "fa\\u00DF.de", "N", // sharp s
254 { "fa\\u00DF.de", "T", // sharp s
256 { "XN--fA-hia.dE", "B", // sharp s in Punycode
258 { "\\u03B2\\u03CC\\u03BB\\u03BF\\u03C2.com", "N", // Greek with final sigma
259 "\\u03B2\\u03CC\\u03BB\\u03BF\\u03C2.com", 0 },
260 { "\\u03B2\\u03CC\\u03BB\\u03BF\\u03C2.com", "T", // Greek with final sigma
261 "\\u03B2\\u03CC\\u03BB\\u03BF\\u03C3.com", 0 },
262 { "xn--nxasmm1c", "B", // Greek with final sigma in Punycode
263 "\\u03B2\\u03CC\\u03BB\\u03BF\\u03C2", 0 },
264 { "www.\\u0DC1\\u0DCA\\u200D\\u0DBB\\u0DD3.com", "N", // "Sri" in "Sri Lanka" has a ZWJ
265 "www.\\u0DC1\\u0DCA\\u200D\\u0DBB\\u0DD3.com", 0 },
266 { "www.\\u0DC1\\u0DCA\\u200D\\u0DBB\\u0DD3.com", "T", // "Sri" in "Sri Lanka" has a ZWJ
267 "www.\\u0DC1\\u0DCA\\u0DBB\\u0DD3.com", 0 },
268 { "www.xn--10cl1a0b660p.com", "B", // "Sri" in Punycode
269 "www.\\u0DC1\\u0DCA\\u200D\\u0DBB\\u0DD3.com", 0 },
270 { "\\u0646\\u0627\\u0645\\u0647\\u200C\\u0627\\u06CC", "N", // ZWNJ
271 "\\u0646\\u0627\\u0645\\u0647\\u200C\\u0627\\u06CC", 0 },
272 { "\\u0646\\u0627\\u0645\\u0647\\u200C\\u0627\\u06CC", "T", // ZWNJ
273 "\\u0646\\u0627\\u0645\\u0647\\u0627\\u06CC", 0 },
274 { "xn--mgba3gch31f060k.com", "B", // ZWNJ in Punycode
275 "\\u0646\\u0627\\u0645\\u0647\\u200C\\u0627\\u06CC.com", 0 },
276 { "a.b\\uFF0Ec\\u3002d\\uFF61", "B",
278 { "U\\u0308.xn--tda", "B", // U+umlaut.u-umlaut
279 "\\u00FC.\\u00FC", 0 },
280 { "xn--u-ccb", "B", // u+umlaut in Punycode
281 "xn--u-ccb\\uFFFD", UIDNA_ERROR_INVALID_ACE_LABEL
},
282 { "a\\u2488com", "B", // contains 1-dot
283 "a\\uFFFDcom", UIDNA_ERROR_DISALLOWED
},
284 { "xn--a-ecp.ru", "B", // contains 1-dot in Punycode
285 "xn--a-ecp\\uFFFD.ru", UIDNA_ERROR_INVALID_ACE_LABEL
},
286 { "xn--0.pt", "B", // invalid Punycode
287 "xn--0\\uFFFD.pt", UIDNA_ERROR_PUNYCODE
},
288 { "xn--a.pt", "B", // U+0080
289 "xn--a\\uFFFD.pt", UIDNA_ERROR_INVALID_ACE_LABEL
},
290 { "xn--a-\\u00C4.pt", "B", // invalid Punycode
291 "xn--a-\\u00E4.pt", UIDNA_ERROR_PUNYCODE
},
292 { "\\u65E5\\u672C\\u8A9E\\u3002\\uFF2A\\uFF30", "B", // Japanese with fullwidth ".jp"
293 "\\u65E5\\u672C\\u8A9E.jp", 0 },
294 { "\\u2615", "B", "\\u2615", 0 }, // Unicode 4.0 HOT BEVERAGE
295 // some characters are disallowed because they are canonically equivalent
296 // to sequences with non-LDH ASCII
297 { "a\\u2260b\\u226Ec\\u226Fd", "B",
298 "a\\uFFFDb\\uFFFDc\\uFFFDd", UIDNA_ERROR_DISALLOWED
},
299 // many deviation characters, test the special mapping code
300 { "1.a\\u00DF\\u200C\\u200Db\\u200C\\u200Dc\\u00DF\\u00DF\\u00DF\\u00DFd"
301 "\\u03C2\\u03C3\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DFe"
302 "\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DFx"
303 "\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DFy"
304 "\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u0302\\u00DFz", "N",
305 "1.a\\u00DF\\u200C\\u200Db\\u200C\\u200Dc\\u00DF\\u00DF\\u00DF\\u00DFd"
306 "\\u03C2\\u03C3\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DFe"
307 "\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DFx"
308 "\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DFy"
309 "\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u0302\\u00DFz",
310 UIDNA_ERROR_LABEL_TOO_LONG
|UIDNA_ERROR_CONTEXTJ
},
311 { "1.a\\u00DF\\u200C\\u200Db\\u200C\\u200Dc\\u00DF\\u00DF\\u00DF\\u00DFd"
312 "\\u03C2\\u03C3\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DFe"
313 "\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DFx"
314 "\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DFy"
315 "\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u0302\\u00DFz", "T",
317 "\\u03C3\\u03C3sssssssssssssssse"
318 "ssssssssssssssssssssx"
319 "ssssssssssssssssssssy"
320 "sssssssssssssss\\u015Dssz", UIDNA_ERROR_LABEL_TOO_LONG
},
321 // "xn--bss" with deviation characters
322 { "\\u200Cx\\u200Dn\\u200C-\\u200D-b\\u00DF", "N",
323 "\\u200Cx\\u200Dn\\u200C-\\u200D-b\\u00DF", UIDNA_ERROR_CONTEXTJ
},
324 { "\\u200Cx\\u200Dn\\u200C-\\u200D-b\\u00DF", "T",
326 // "xn--bssffl" written as:
327 // 02E3 MODIFIER LETTER SMALL X
328 // 034F COMBINING GRAPHEME JOINER (ignored)
329 // 2115 DOUBLE-STRUCK CAPITAL N
330 // 200B ZERO WIDTH SPACE (ignored)
331 // FE63 SMALL HYPHEN-MINUS
332 // 00AD SOFT HYPHEN (ignored)
333 // FF0D FULLWIDTH HYPHEN-MINUS
334 // 180C MONGOLIAN FREE VARIATION SELECTOR TWO (ignored)
335 // 212C SCRIPT CAPITAL B
336 // FE00 VARIATION SELECTOR-1 (ignored)
337 // 017F LATIN SMALL LETTER LONG S
338 // 2064 INVISIBLE PLUS (ignored)
339 // 1D530 MATHEMATICAL FRAKTUR SMALL S
340 // E01EF VARIATION SELECTOR-256 (ignored)
341 // FB04 LATIN SMALL LIGATURE FFL
342 { "\\u02E3\\u034F\\u2115\\u200B\\uFE63\\u00AD\\uFF0D\\u180C"
343 "\\u212C\\uFE00\\u017F\\u2064\\U0001D530\\U000E01EF\\uFB04", "B",
344 "\\u5921\\u591E\\u591C\\u5919", 0 },
345 { "123456789012345678901234567890123456789012345678901234567890123."
346 "123456789012345678901234567890123456789012345678901234567890123."
347 "123456789012345678901234567890123456789012345678901234567890123."
348 "1234567890123456789012345678901234567890123456789012345678901", "B",
349 "123456789012345678901234567890123456789012345678901234567890123."
350 "123456789012345678901234567890123456789012345678901234567890123."
351 "123456789012345678901234567890123456789012345678901234567890123."
352 "1234567890123456789012345678901234567890123456789012345678901", 0 },
353 { "123456789012345678901234567890123456789012345678901234567890123."
354 "123456789012345678901234567890123456789012345678901234567890123."
355 "123456789012345678901234567890123456789012345678901234567890123."
356 "1234567890123456789012345678901234567890123456789012345678901.", "B",
357 "123456789012345678901234567890123456789012345678901234567890123."
358 "123456789012345678901234567890123456789012345678901234567890123."
359 "123456789012345678901234567890123456789012345678901234567890123."
360 "1234567890123456789012345678901234567890123456789012345678901.", 0 },
361 // Domain name >256 characters, forces slow path in UTF-8 processing.
362 { "123456789012345678901234567890123456789012345678901234567890123."
363 "123456789012345678901234567890123456789012345678901234567890123."
364 "123456789012345678901234567890123456789012345678901234567890123."
365 "123456789012345678901234567890123456789012345678901234567890123."
366 "12345678901234567890123456789012345678901234567890123456789012", "B",
367 "123456789012345678901234567890123456789012345678901234567890123."
368 "123456789012345678901234567890123456789012345678901234567890123."
369 "123456789012345678901234567890123456789012345678901234567890123."
370 "123456789012345678901234567890123456789012345678901234567890123."
371 "12345678901234567890123456789012345678901234567890123456789012",
372 UIDNA_ERROR_DOMAIN_NAME_TOO_LONG
},
373 { "123456789012345678901234567890123456789012345678901234567890123."
374 "123456789012345678901234567890123456789012345678901234567890123."
375 "123456789012345678901234567890123456789012345678901234567890123."
376 "123456789012345678901234567890123456789012345678901234567890123."
377 "1234567890123456789012345678901234567890123456789\\u05D0", "B",
378 "123456789012345678901234567890123456789012345678901234567890123."
379 "123456789012345678901234567890123456789012345678901234567890123."
380 "123456789012345678901234567890123456789012345678901234567890123."
381 "123456789012345678901234567890123456789012345678901234567890123."
382 "1234567890123456789012345678901234567890123456789\\u05D0",
383 UIDNA_ERROR_DOMAIN_NAME_TOO_LONG
|UIDNA_ERROR_BIDI
},
384 { "123456789012345678901234567890123456789012345678901234567890123."
385 "1234567890123456789012345678901234567890123456789012345678901234."
386 "123456789012345678901234567890123456789012345678901234567890123."
387 "123456789012345678901234567890123456789012345678901234567890", "B",
388 "123456789012345678901234567890123456789012345678901234567890123."
389 "1234567890123456789012345678901234567890123456789012345678901234."
390 "123456789012345678901234567890123456789012345678901234567890123."
391 "123456789012345678901234567890123456789012345678901234567890",
392 UIDNA_ERROR_LABEL_TOO_LONG
},
393 { "123456789012345678901234567890123456789012345678901234567890123."
394 "1234567890123456789012345678901234567890123456789012345678901234."
395 "123456789012345678901234567890123456789012345678901234567890123."
396 "123456789012345678901234567890123456789012345678901234567890.", "B",
397 "123456789012345678901234567890123456789012345678901234567890123."
398 "1234567890123456789012345678901234567890123456789012345678901234."
399 "123456789012345678901234567890123456789012345678901234567890123."
400 "123456789012345678901234567890123456789012345678901234567890.",
401 UIDNA_ERROR_LABEL_TOO_LONG
},
402 { "123456789012345678901234567890123456789012345678901234567890123."
403 "1234567890123456789012345678901234567890123456789012345678901234."
404 "123456789012345678901234567890123456789012345678901234567890123."
405 "1234567890123456789012345678901234567890123456789012345678901", "B",
406 "123456789012345678901234567890123456789012345678901234567890123."
407 "1234567890123456789012345678901234567890123456789012345678901234."
408 "123456789012345678901234567890123456789012345678901234567890123."
409 "1234567890123456789012345678901234567890123456789012345678901",
410 UIDNA_ERROR_LABEL_TOO_LONG
|UIDNA_ERROR_DOMAIN_NAME_TOO_LONG
},
411 // label length 63: xn--1234567890123456789012345678901234567890123456789012345-9te
412 { "\\u00E41234567890123456789012345678901234567890123456789012345", "B",
413 "\\u00E41234567890123456789012345678901234567890123456789012345", 0 },
414 { "1234567890\\u00E41234567890123456789012345678901234567890123456", "B",
415 "1234567890\\u00E41234567890123456789012345678901234567890123456", UIDNA_ERROR_LABEL_TOO_LONG
},
416 { "123456789012345678901234567890123456789012345678901234567890123."
417 "1234567890\\u00E4123456789012345678901234567890123456789012345."
418 "123456789012345678901234567890123456789012345678901234567890123."
419 "1234567890123456789012345678901234567890123456789012345678901", "B",
420 "123456789012345678901234567890123456789012345678901234567890123."
421 "1234567890\\u00E4123456789012345678901234567890123456789012345."
422 "123456789012345678901234567890123456789012345678901234567890123."
423 "1234567890123456789012345678901234567890123456789012345678901", 0 },
424 { "123456789012345678901234567890123456789012345678901234567890123."
425 "1234567890\\u00E4123456789012345678901234567890123456789012345."
426 "123456789012345678901234567890123456789012345678901234567890123."
427 "1234567890123456789012345678901234567890123456789012345678901.", "B",
428 "123456789012345678901234567890123456789012345678901234567890123."
429 "1234567890\\u00E4123456789012345678901234567890123456789012345."
430 "123456789012345678901234567890123456789012345678901234567890123."
431 "1234567890123456789012345678901234567890123456789012345678901.", 0 },
432 { "123456789012345678901234567890123456789012345678901234567890123."
433 "1234567890\\u00E4123456789012345678901234567890123456789012345."
434 "123456789012345678901234567890123456789012345678901234567890123."
435 "12345678901234567890123456789012345678901234567890123456789012", "B",
436 "123456789012345678901234567890123456789012345678901234567890123."
437 "1234567890\\u00E4123456789012345678901234567890123456789012345."
438 "123456789012345678901234567890123456789012345678901234567890123."
439 "12345678901234567890123456789012345678901234567890123456789012",
440 UIDNA_ERROR_DOMAIN_NAME_TOO_LONG
},
441 { "123456789012345678901234567890123456789012345678901234567890123."
442 "1234567890\\u00E41234567890123456789012345678901234567890123456."
443 "123456789012345678901234567890123456789012345678901234567890123."
444 "123456789012345678901234567890123456789012345678901234567890", "B",
445 "123456789012345678901234567890123456789012345678901234567890123."
446 "1234567890\\u00E41234567890123456789012345678901234567890123456."
447 "123456789012345678901234567890123456789012345678901234567890123."
448 "123456789012345678901234567890123456789012345678901234567890",
449 UIDNA_ERROR_LABEL_TOO_LONG
},
450 { "123456789012345678901234567890123456789012345678901234567890123."
451 "1234567890\\u00E41234567890123456789012345678901234567890123456."
452 "123456789012345678901234567890123456789012345678901234567890123."
453 "123456789012345678901234567890123456789012345678901234567890.", "B",
454 "123456789012345678901234567890123456789012345678901234567890123."
455 "1234567890\\u00E41234567890123456789012345678901234567890123456."
456 "123456789012345678901234567890123456789012345678901234567890123."
457 "123456789012345678901234567890123456789012345678901234567890.",
458 UIDNA_ERROR_LABEL_TOO_LONG
},
459 { "123456789012345678901234567890123456789012345678901234567890123."
460 "1234567890\\u00E41234567890123456789012345678901234567890123456."
461 "123456789012345678901234567890123456789012345678901234567890123."
462 "1234567890123456789012345678901234567890123456789012345678901", "B",
463 "123456789012345678901234567890123456789012345678901234567890123."
464 "1234567890\\u00E41234567890123456789012345678901234567890123456."
465 "123456789012345678901234567890123456789012345678901234567890123."
466 "1234567890123456789012345678901234567890123456789012345678901",
467 UIDNA_ERROR_LABEL_TOO_LONG
|UIDNA_ERROR_DOMAIN_NAME_TOO_LONG
},
468 // hyphen errors and empty-label errors
469 // "xn---q----jra"=="-q--a-umlaut-"
470 { "a.b..-q--a-.e", "B", "a.b..-q--a-.e",
471 UIDNA_ERROR_EMPTY_LABEL
|UIDNA_ERROR_LEADING_HYPHEN
|UIDNA_ERROR_TRAILING_HYPHEN
|
472 UIDNA_ERROR_HYPHEN_3_4
},
473 { "a.b..-q--\\u00E4-.e", "B", "a.b..-q--\\u00E4-.e",
474 UIDNA_ERROR_EMPTY_LABEL
|UIDNA_ERROR_LEADING_HYPHEN
|UIDNA_ERROR_TRAILING_HYPHEN
|
475 UIDNA_ERROR_HYPHEN_3_4
},
476 { "a.b..xn---q----jra.e", "B", "a.b..-q--\\u00E4-.e",
477 UIDNA_ERROR_EMPTY_LABEL
|UIDNA_ERROR_LEADING_HYPHEN
|UIDNA_ERROR_TRAILING_HYPHEN
|
478 UIDNA_ERROR_HYPHEN_3_4
},
479 { "a..c", "B", "a..c", UIDNA_ERROR_EMPTY_LABEL
},
480 { "a.-b.", "B", "a.-b.", UIDNA_ERROR_LEADING_HYPHEN
},
481 { "a.b-.c", "B", "a.b-.c", UIDNA_ERROR_TRAILING_HYPHEN
},
482 { "a.-.c", "B", "a.-.c", UIDNA_ERROR_LEADING_HYPHEN
|UIDNA_ERROR_TRAILING_HYPHEN
},
483 { "a.bc--de.f", "B", "a.bc--de.f", UIDNA_ERROR_HYPHEN_3_4
},
484 { "\\u00E4.\\u00AD.c", "B", "\\u00E4..c", UIDNA_ERROR_EMPTY_LABEL
},
485 { "\\u00E4.-b.", "B", "\\u00E4.-b.", UIDNA_ERROR_LEADING_HYPHEN
},
486 { "\\u00E4.b-.c", "B", "\\u00E4.b-.c", UIDNA_ERROR_TRAILING_HYPHEN
},
487 { "\\u00E4.-.c", "B", "\\u00E4.-.c", UIDNA_ERROR_LEADING_HYPHEN
|UIDNA_ERROR_TRAILING_HYPHEN
},
488 { "\\u00E4.bc--de.f", "B", "\\u00E4.bc--de.f", UIDNA_ERROR_HYPHEN_3_4
},
489 { "a.b.\\u0308c.d", "B", "a.b.\\uFFFDc.d", UIDNA_ERROR_LEADING_COMBINING_MARK
},
490 { "a.b.xn--c-bcb.d", "B",
491 "a.b.xn--c-bcb\\uFFFD.d", UIDNA_ERROR_LEADING_COMBINING_MARK
|UIDNA_ERROR_INVALID_ACE_LABEL
},
493 { "A0", "B", "a0", 0 },
494 { "0A", "B", "0a", 0 }, // all-LTR is ok to start with a digit (EN)
495 { "0A.\\u05D0", "B", // ASCII label does not start with L/R/AL
496 "0a.\\u05D0", UIDNA_ERROR_BIDI
},
497 { "c.xn--0-eha.xn--4db", "B", // 2nd label does not start with L/R/AL
498 "c.0\\u00FC.\\u05D0", UIDNA_ERROR_BIDI
},
499 { "b-.\\u05D0", "B", // label does not end with L/EN
500 "b-.\\u05D0", UIDNA_ERROR_TRAILING_HYPHEN
|UIDNA_ERROR_BIDI
},
501 { "d.xn----dha.xn--4db", "B", // 2nd label does not end with L/EN
502 "d.\\u00FC-.\\u05D0", UIDNA_ERROR_TRAILING_HYPHEN
|UIDNA_ERROR_BIDI
},
503 { "a\\u05D0", "B", "a\\u05D0", UIDNA_ERROR_BIDI
}, // first dir != last dir
504 { "\\u05D0\\u05C7", "B", "\\u05D0\\u05C7", 0 },
505 { "\\u05D09\\u05C7", "B", "\\u05D09\\u05C7", 0 },
506 { "\\u05D0a\\u05C7", "B", "\\u05D0a\\u05C7", UIDNA_ERROR_BIDI
}, // first dir != last dir
507 { "\\u05D0\\u05EA", "B", "\\u05D0\\u05EA", 0 },
508 { "\\u05D0\\u05F3\\u05EA", "B", "\\u05D0\\u05F3\\u05EA", 0 },
509 { "a\\u05D0Tz", "B", "a\\u05D0tz", UIDNA_ERROR_BIDI
}, // mixed dir
510 { "\\u05D0T\\u05EA", "B", "\\u05D0t\\u05EA", UIDNA_ERROR_BIDI
}, // mixed dir
511 { "\\u05D07\\u05EA", "B", "\\u05D07\\u05EA", 0 },
512 { "\\u05D0\\u0667\\u05EA", "B", "\\u05D0\\u0667\\u05EA", 0 }, // Arabic 7 in the middle
513 { "a7\\u0667z", "B", "a7\\u0667z", UIDNA_ERROR_BIDI
}, // AN digit in LTR
514 { "\\u05D07\\u0667\\u05EA", "B", // mixed EN/AN digits in RTL
515 "\\u05D07\\u0667\\u05EA", UIDNA_ERROR_BIDI
},
517 { "\\u0BB9\\u0BCD\\u200D", "N", "\\u0BB9\\u0BCD\\u200D", 0 }, // Virama+ZWJ
518 { "\\u0BB9\\u200D", "N", "\\u0BB9\\u200D", UIDNA_ERROR_CONTEXTJ
}, // no Virama
519 { "\\u200D", "N", "\\u200D", UIDNA_ERROR_CONTEXTJ
}, // no Virama
521 { "\\u0BB9\\u0BCD\\u200C", "N", "\\u0BB9\\u0BCD\\u200C", 0 }, // Virama+ZWNJ
522 { "\\u0BB9\\u200C", "N", "\\u0BB9\\u200C", UIDNA_ERROR_CONTEXTJ
}, // no Virama
523 { "\\u200C", "N", "\\u200C", UIDNA_ERROR_CONTEXTJ
}, // no Virama
524 { "\\u0644\\u0670\\u200C\\u06ED\\u06EF", "N", // Joining types D T ZWNJ T R
525 "\\u0644\\u0670\\u200C\\u06ED\\u06EF", 0 },
526 { "\\u0644\\u0670\\u200C\\u06EF", "N", // D T ZWNJ R
527 "\\u0644\\u0670\\u200C\\u06EF", 0 },
528 { "\\u0644\\u200C\\u06ED\\u06EF", "N", // D ZWNJ T R
529 "\\u0644\\u200C\\u06ED\\u06EF", 0 },
530 { "\\u0644\\u200C\\u06EF", "N", // D ZWNJ R
531 "\\u0644\\u200C\\u06EF", 0 },
532 { "\\u0644\\u0670\\u200C\\u06ED", "N", // D T ZWNJ T
533 "\\u0644\\u0670\\u200C\\u06ED", UIDNA_ERROR_BIDI
|UIDNA_ERROR_CONTEXTJ
},
534 { "\\u06EF\\u200C\\u06EF", "N", // R ZWNJ R
535 "\\u06EF\\u200C\\u06EF", UIDNA_ERROR_CONTEXTJ
},
536 { "\\u0644\\u200C", "N", // D ZWNJ
537 "\\u0644\\u200C", UIDNA_ERROR_BIDI
|UIDNA_ERROR_CONTEXTJ
},
538 { "\\u0660\\u0661", "B", // Arabic-Indic Digits alone
539 "\\u0660\\u0661", UIDNA_ERROR_BIDI
},
540 { "\\u06F0\\u06F1", "B", // Extended Arabic-Indic Digits alone
541 "\\u06F0\\u06F1", 0 },
542 { "\\u0660\\u06F1", "B", // Mixed Arabic-Indic Digits
543 "\\u0660\\u06F1", UIDNA_ERROR_CONTEXTO_DIGITS
|UIDNA_ERROR_BIDI
},
544 // All of the CONTEXTO "Would otherwise have been DISALLOWED" characters
545 // in their correct contexts,
546 // then each in incorrect context.
547 { "l\\u00B7l\\u4E00\\u0375\\u03B1\\u05D0\\u05F3\\u05F4\\u30FB", "B",
548 "l\\u00B7l\\u4E00\\u0375\\u03B1\\u05D0\\u05F3\\u05F4\\u30FB", UIDNA_ERROR_BIDI
},
550 "l\\u00B7", UIDNA_ERROR_CONTEXTO_PUNCTUATION
},
552 "\\u00B7l", UIDNA_ERROR_CONTEXTO_PUNCTUATION
},
554 "\\u0375", UIDNA_ERROR_CONTEXTO_PUNCTUATION
},
555 { "\\u03B1\\u05F3", "B",
556 "\\u03B1\\u05F3", UIDNA_ERROR_CONTEXTO_PUNCTUATION
|UIDNA_ERROR_BIDI
},
558 "\\u05F4", UIDNA_ERROR_CONTEXTO_PUNCTUATION
},
560 "l\\u30FB", UIDNA_ERROR_CONTEXTO_PUNCTUATION
},
561 // Ticket #8137: UTS #46 toUnicode() fails with non-ASCII labels that turn
562 // into 15 characters (UChars).
563 // The bug was in u_strFromPunycode() which did not write the last character
564 // if it just so fit into the end of the destination buffer.
565 // The UTS #46 code gives a default-capacity UnicodeString as the destination buffer,
566 // and the internal UnicodeString capacity is currently 15 UChars on 64-bit machines
567 // but 13 on 32-bit machines.
568 // Label with 15 UChars, for 64-bit-machine testing:
569 { "aaaaaaaaaaaaa\\u00FCa.de", "B", "aaaaaaaaaaaaa\\u00FCa.de", 0 },
570 { "xn--aaaaaaaaaaaaaa-ssb.de", "B", "aaaaaaaaaaaaa\\u00FCa.de", 0 },
571 { "abschlu\\u00DFpr\\u00FCfung.de", "N", "abschlu\\u00DFpr\\u00FCfung.de", 0 },
572 { "xn--abschluprfung-hdb15b.de", "B", "abschlu\\u00DFpr\\u00FCfung.de", 0 },
573 // Label with 13 UChars, for 32-bit-machine testing:
574 { "xn--aaaaaaaaaaaa-nlb.de", "B", "aaaaaaaaaaa\\u00FCa.de", 0 },
575 { "xn--schluprfung-z6a39a.de", "B", "schlu\\u00DFpr\\u00FCfung.de", 0 },
580 void UTS46Test::TestSomeCases() {
581 IcuTestErrorCode
errorCode(*this, "TestSomeCases");
582 char buffer
[400], buffer2
[400];
584 for(i
=0; i
<LENGTHOF(testCases
); ++i
) {
585 const TestCase
&testCase
=testCases
[i
];
586 UnicodeString
input(ctou(testCase
.s
));
587 UnicodeString
expected(ctou(testCase
.u
));
588 // ToASCII/ToUnicode, transitional/nontransitional
589 UnicodeString aT
, uT
, aN
, uN
;
590 IDNAInfo aTInfo
, uTInfo
, aNInfo
, uNInfo
;
591 trans
->nameToASCII(input
, aT
, aTInfo
, errorCode
);
592 trans
->nameToUnicode(input
, uT
, uTInfo
, errorCode
);
593 nontrans
->nameToASCII(input
, aN
, aNInfo
, errorCode
);
594 nontrans
->nameToUnicode(input
, uN
, uNInfo
, errorCode
);
595 if(errorCode
.logIfFailureAndReset("first-level processing [%d/%s] %s",
596 (int)i
, testCase
.o
, testCase
.s
)
600 // ToUnicode does not set length errors.
601 uint32_t uniErrors
=testCase
.errors
&~
602 (UIDNA_ERROR_EMPTY_LABEL
|
603 UIDNA_ERROR_LABEL_TOO_LONG
|
604 UIDNA_ERROR_DOMAIN_NAME_TOO_LONG
);
605 char mode
=testCase
.o
[0];
606 if(mode
=='B' || mode
=='N') {
607 if(uNInfo
.getErrors()!=uniErrors
) {
608 errln("N.nameToUnicode([%d] %s) unexpected errors %04lx",
609 (int)i
, testCase
.s
, (long)uNInfo
.getErrors());
613 prettify(uN
).extract(0, 0x7fffffff, buffer
, LENGTHOF(buffer
));
614 errln("N.nameToUnicode([%d] %s) unexpected string %s",
615 (int)i
, testCase
.s
, buffer
);
618 if(aNInfo
.getErrors()!=testCase
.errors
) {
619 errln("N.nameToASCII([%d] %s) unexpected errors %04lx",
620 (int)i
, testCase
.s
, (long)aNInfo
.getErrors());
624 if(mode
=='B' || mode
=='T') {
625 if(uTInfo
.getErrors()!=uniErrors
) {
626 errln("T.nameToUnicode([%d] %s) unexpected errors %04lx",
627 (int)i
, testCase
.s
, (long)uTInfo
.getErrors());
631 prettify(uT
).extract(0, 0x7fffffff, buffer
, LENGTHOF(buffer
));
632 errln("T.nameToUnicode([%d] %s) unexpected string %s",
633 (int)i
, testCase
.s
, buffer
);
636 if(aTInfo
.getErrors()!=testCase
.errors
) {
637 errln("T.nameToASCII([%d] %s) unexpected errors %04lx",
638 (int)i
, testCase
.s
, (long)aTInfo
.getErrors());
642 // ToASCII is all-ASCII if no severe errors
643 if((aNInfo
.getErrors()&severeErrors
)==0 && !isASCII(aN
)) {
644 prettify(aN
).extract(0, 0x7fffffff, buffer
, LENGTHOF(buffer
));
645 errln("N.nameToASCII([%d] %s) (errors %04lx) result is not ASCII %s",
646 (int)i
, testCase
.s
, aNInfo
.getErrors(), buffer
);
649 if((aTInfo
.getErrors()&severeErrors
)==0 && !isASCII(aT
)) {
650 prettify(aT
).extract(0, 0x7fffffff, buffer
, LENGTHOF(buffer
));
651 errln("T.nameToASCII([%d] %s) (errors %04lx) result is not ASCII %s",
652 (int)i
, testCase
.s
, aTInfo
.getErrors(), buffer
);
656 char m
= mode
=='B' ? mode
: 'N';
657 prettify(aN
).extract(0, 0x7fffffff, buffer
, LENGTHOF(buffer
));
658 logln("%c.nameToASCII([%d] %s) (errors %04lx) result string: %s",
659 m
, (int)i
, testCase
.s
, aNInfo
.getErrors(), buffer
);
661 prettify(aT
).extract(0, 0x7fffffff, buffer
, LENGTHOF(buffer
));
662 logln("T.nameToASCII([%d] %s) (errors %04lx) result string: %s",
663 (int)i
, testCase
.s
, aTInfo
.getErrors(), buffer
);
666 // second-level processing
667 UnicodeString aTuN
, uTaN
, aNuN
, uNaN
;
668 IDNAInfo aTuNInfo
, uTaNInfo
, aNuNInfo
, uNaNInfo
;
669 nontrans
->nameToUnicode(aT
, aTuN
, aTuNInfo
, errorCode
);
670 nontrans
->nameToASCII(uT
, uTaN
, uTaNInfo
, errorCode
);
671 nontrans
->nameToUnicode(aN
, aNuN
, aNuNInfo
, errorCode
);
672 nontrans
->nameToASCII(uN
, uNaN
, uNaNInfo
, errorCode
);
673 if(errorCode
.logIfFailureAndReset("second-level processing [%d/%s] %s",
674 (int)i
, testCase
.o
, testCase
.s
)
679 prettify(aN
).extract(0, 0x7fffffff, buffer
, LENGTHOF(buffer
));
680 prettify(uNaN
).extract(0, 0x7fffffff, buffer2
, LENGTHOF(buffer2
));
681 errln("N.nameToASCII([%d] %s)!=N.nameToUnicode().N.nameToASCII() "
682 "(errors %04lx) %s vs. %s",
683 (int)i
, testCase
.s
, aNInfo
.getErrors(), buffer
, buffer2
);
687 prettify(aT
).extract(0, 0x7fffffff, buffer
, LENGTHOF(buffer
));
688 prettify(uTaN
).extract(0, 0x7fffffff, buffer2
, LENGTHOF(buffer2
));
689 errln("T.nameToASCII([%d] %s)!=T.nameToUnicode().N.nameToASCII() "
690 "(errors %04lx) %s vs. %s",
691 (int)i
, testCase
.s
, aNInfo
.getErrors(), buffer
, buffer2
);
695 prettify(uN
).extract(0, 0x7fffffff, buffer
, LENGTHOF(buffer
));
696 prettify(aNuN
).extract(0, 0x7fffffff, buffer2
, LENGTHOF(buffer2
));
697 errln("N.nameToUnicode([%d] %s)!=N.nameToASCII().N.nameToUnicode() "
698 "(errors %04lx) %s vs. %s",
699 (int)i
, testCase
.s
, uNInfo
.getErrors(), buffer
, buffer2
);
703 prettify(uT
).extract(0, 0x7fffffff, buffer
, LENGTHOF(buffer
));
704 prettify(aTuN
).extract(0, 0x7fffffff, buffer2
, LENGTHOF(buffer2
));
705 errln("T.nameToUnicode([%d] %s)!=T.nameToASCII().N.nameToUnicode() "
706 "(errors %04lx) %s vs. %s",
707 (int)i
, testCase
.s
, uNInfo
.getErrors(), buffer
, buffer2
);
711 UnicodeString aTL
, uTL
, aNL
, uNL
;
712 IDNAInfo aTLInfo
, uTLInfo
, aNLInfo
, uNLInfo
;
713 trans
->labelToASCII(input
, aTL
, aTLInfo
, errorCode
);
714 trans
->labelToUnicode(input
, uTL
, uTLInfo
, errorCode
);
715 nontrans
->labelToASCII(input
, aNL
, aNLInfo
, errorCode
);
716 nontrans
->labelToUnicode(input
, uNL
, uNLInfo
, errorCode
);
717 if(errorCode
.logIfFailureAndReset("labelToXYZ processing [%d/%s] %s",
718 (int)i
, testCase
.o
, testCase
.s
)
722 if(aN
.indexOf((UChar
)0x2e)<0) {
723 if(aN
!=aNL
|| aNInfo
.getErrors()!=aNLInfo
.getErrors()) {
724 prettify(aN
).extract(0, 0x7fffffff, buffer
, LENGTHOF(buffer
));
725 prettify(aNL
).extract(0, 0x7fffffff, buffer2
, LENGTHOF(buffer2
));
726 errln("N.nameToASCII([%d] %s)!=N.labelToASCII() "
727 "(errors %04lx vs %04lx) %s vs. %s",
728 (int)i
, testCase
.s
, aNInfo
.getErrors(), aNLInfo
.getErrors(), buffer
, buffer2
);
732 if((aNLInfo
.getErrors()&UIDNA_ERROR_LABEL_HAS_DOT
)==0) {
733 errln("N.labelToASCII([%d] %s) errors %04lx missing UIDNA_ERROR_LABEL_HAS_DOT",
734 (int)i
, testCase
.s
, (long)aNLInfo
.getErrors());
738 if(aT
.indexOf((UChar
)0x2e)<0) {
739 if(aT
!=aTL
|| aTInfo
.getErrors()!=aTLInfo
.getErrors()) {
740 prettify(aT
).extract(0, 0x7fffffff, buffer
, LENGTHOF(buffer
));
741 prettify(aTL
).extract(0, 0x7fffffff, buffer2
, LENGTHOF(buffer2
));
742 errln("T.nameToASCII([%d] %s)!=T.labelToASCII() "
743 "(errors %04lx vs %04lx) %s vs. %s",
744 (int)i
, testCase
.s
, aTInfo
.getErrors(), aTLInfo
.getErrors(), buffer
, buffer2
);
748 if((aTLInfo
.getErrors()&UIDNA_ERROR_LABEL_HAS_DOT
)==0) {
749 errln("T.labelToASCII([%d] %s) errors %04lx missing UIDNA_ERROR_LABEL_HAS_DOT",
750 (int)i
, testCase
.s
, (long)aTLInfo
.getErrors());
754 if(uN
.indexOf((UChar
)0x2e)<0) {
755 if(uN
!=uNL
|| uNInfo
.getErrors()!=uNLInfo
.getErrors()) {
756 prettify(uN
).extract(0, 0x7fffffff, buffer
, LENGTHOF(buffer
));
757 prettify(uNL
).extract(0, 0x7fffffff, buffer2
, LENGTHOF(buffer2
));
758 errln("N.nameToUnicode([%d] %s)!=N.labelToUnicode() "
759 "(errors %04lx vs %04lx) %s vs. %s",
760 (int)i
, testCase
.s
, uNInfo
.getErrors(), uNLInfo
.getErrors(), buffer
, buffer2
);
764 if((uNLInfo
.getErrors()&UIDNA_ERROR_LABEL_HAS_DOT
)==0) {
765 errln("N.labelToUnicode([%d] %s) errors %04lx missing UIDNA_ERROR_LABEL_HAS_DOT",
766 (int)i
, testCase
.s
, (long)uNLInfo
.getErrors());
770 if(uT
.indexOf((UChar
)0x2e)<0) {
771 if(uT
!=uTL
|| uTInfo
.getErrors()!=uTLInfo
.getErrors()) {
772 prettify(uT
).extract(0, 0x7fffffff, buffer
, LENGTHOF(buffer
));
773 prettify(uTL
).extract(0, 0x7fffffff, buffer2
, LENGTHOF(buffer2
));
774 errln("T.nameToUnicode([%d] %s)!=T.labelToUnicode() "
775 "(errors %04lx vs %04lx) %s vs. %s",
776 (int)i
, testCase
.s
, uTInfo
.getErrors(), uTLInfo
.getErrors(), buffer
, buffer2
);
780 if((uTLInfo
.getErrors()&UIDNA_ERROR_LABEL_HAS_DOT
)==0) {
781 errln("T.labelToUnicode([%d] %s) errors %04lx missing UIDNA_ERROR_LABEL_HAS_DOT",
782 (int)i
, testCase
.s
, (long)uTLInfo
.getErrors());
786 // Differences between transitional and nontransitional processing
788 if( aNInfo
.isTransitionalDifferent() ||
789 aTInfo
.isTransitionalDifferent() ||
790 uNInfo
.isTransitionalDifferent() ||
791 uTInfo
.isTransitionalDifferent() ||
792 aNLInfo
.isTransitionalDifferent() ||
793 aTLInfo
.isTransitionalDifferent() ||
794 uNLInfo
.isTransitionalDifferent() ||
795 uTLInfo
.isTransitionalDifferent()
797 errln("B.process([%d] %s) isTransitionalDifferent()", (int)i
, testCase
.s
);
800 if( aN
!=aT
|| uN
!=uT
|| aNL
!=aTL
|| uNL
!=uTL
||
801 aNInfo
.getErrors()!=aTInfo
.getErrors() || uNInfo
.getErrors()!=uTInfo
.getErrors() ||
802 aNLInfo
.getErrors()!=aTLInfo
.getErrors() || uNLInfo
.getErrors()!=uTLInfo
.getErrors()
804 errln("N.process([%d] %s) vs. T.process() different errors or result strings",
809 if( !aNInfo
.isTransitionalDifferent() ||
810 !aTInfo
.isTransitionalDifferent() ||
811 !uNInfo
.isTransitionalDifferent() ||
812 !uTInfo
.isTransitionalDifferent() ||
813 !aNLInfo
.isTransitionalDifferent() ||
814 !aTLInfo
.isTransitionalDifferent() ||
815 !uNLInfo
.isTransitionalDifferent() ||
816 !uTLInfo
.isTransitionalDifferent()
818 errln("%s.process([%d] %s) !isTransitionalDifferent()",
819 testCase
.o
, (int)i
, testCase
.s
);
822 if(aN
==aT
|| uN
==uT
|| aNL
==aTL
|| uNL
==uTL
) {
823 errln("N.process([%d] %s) vs. T.process() same result strings",
828 // UTF-8 if we have std::string
829 #if U_HAVE_STD_STRING
830 std::string input8
, aT8
, uT8
, aN8
, uN8
;
831 StringByteSink
<std::string
> aT8Sink(&aT8
), uT8Sink(&uT8
), aN8Sink(&aN8
), uN8Sink(&uN8
);
832 IDNAInfo aT8Info
, uT8Info
, aN8Info
, uN8Info
;
833 input
.toUTF8String(input8
);
834 trans
->nameToASCII_UTF8(input8
, aT8Sink
, aT8Info
, errorCode
);
835 trans
->nameToUnicodeUTF8(input8
, uT8Sink
, uT8Info
, errorCode
);
836 nontrans
->nameToASCII_UTF8(input8
, aN8Sink
, aN8Info
, errorCode
);
837 nontrans
->nameToUnicodeUTF8(input8
, uN8Sink
, uN8Info
, errorCode
);
838 if(errorCode
.logIfFailureAndReset("UTF-8 processing [%d/%s] %s",
839 (int)i
, testCase
.o
, testCase
.s
)
843 UnicodeString
aT16(UnicodeString::fromUTF8(aT8
));
844 UnicodeString
uT16(UnicodeString::fromUTF8(uT8
));
845 UnicodeString
aN16(UnicodeString::fromUTF8(aN8
));
846 UnicodeString
uN16(UnicodeString::fromUTF8(uN8
));
847 if( aN8Info
.getErrors()!=aNInfo
.getErrors() ||
848 uN8Info
.getErrors()!=uNInfo
.getErrors()
850 errln("N.xyzUTF8([%d] %s) vs. UTF-16 processing different errors %04lx vs. %04lx",
852 (long)aN8Info
.getErrors(), (long)aNInfo
.getErrors());
855 if( aT8Info
.getErrors()!=aTInfo
.getErrors() ||
856 uT8Info
.getErrors()!=uTInfo
.getErrors()
858 errln("T.xyzUTF8([%d] %s) vs. UTF-16 processing different errors %04lx vs. %04lx",
860 (long)aT8Info
.getErrors(), (long)aTInfo
.getErrors());
863 if(aT16
!=aT
|| uT16
!=uT
|| aN16
!=aN
|| uN16
!=uN
) {
864 errln("%s.xyzUTF8([%d] %s) vs. UTF-16 processing different string results",
865 testCase
.o
, (int)i
, testCase
.s
, (long)aTInfo
.getErrors());
868 if( aT8Info
.isTransitionalDifferent()!=aTInfo
.isTransitionalDifferent() ||
869 uT8Info
.isTransitionalDifferent()!=uTInfo
.isTransitionalDifferent() ||
870 aN8Info
.isTransitionalDifferent()!=aNInfo
.isTransitionalDifferent() ||
871 uN8Info
.isTransitionalDifferent()!=uNInfo
.isTransitionalDifferent()
873 errln("%s.xyzUTF8([%d] %s) vs. UTF-16 processing different isTransitionalDifferent()",
874 testCase
.o
, (int)i
, testCase
.s
);
881 #endif // UCONFIG_NO_IDNA