| OLD | NEW |
|---|
| (Empty) | |
| 1 /* |
| 2 ******************************************************************************* |
| 3 * Copyright (C) 2010, International Business Machines |
| 4 * Corporation and others. All Rights Reserved. |
| 5 ******************************************************************************* |
| 6 * file name: uts46test.cpp |
| 7 * encoding: US-ASCII |
| 8 * tab size: 8 (not used) |
| 9 * indentation:4 |
| 10 * |
| 11 * created on: 2010may05 |
| 12 * created by: Markus W. Scherer |
| 13 */ |
| 14 |
| 15 #include "unicode/utypes.h" |
| 16 |
| 17 #if !UCONFIG_NO_IDNA |
| 18 |
| 19 #include <string.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" |
| 27 #include "intltest.h" |
| 28 |
| 29 #define LENGTHOF(array) (int32_t)(sizeof(array)/sizeof((array)[0])) |
| 30 |
| 31 class UTS46Test : public IntlTest { |
| 32 public: |
| 33 UTS46Test() : trans(NULL), nontrans(NULL) {} |
| 34 virtual ~UTS46Test(); |
| 35 |
| 36 void runIndexedTest(int32_t index, UBool exec, const char *&name, char *par=
NULL); |
| 37 void TestAPI(); |
| 38 void TestNotSTD3(); |
| 39 void TestSomeCases(); |
| 40 private: |
| 41 IDNA *trans, *nontrans; |
| 42 }; |
| 43 |
| 44 extern IntlTest *createUTS46Test() { |
| 45 return new UTS46Test(); |
| 46 } |
| 47 |
| 48 UTS46Test::~UTS46Test() { |
| 49 delete trans; |
| 50 delete nontrans; |
| 51 } |
| 52 |
| 53 void UTS46Test::runIndexedTest(int32_t index, UBool exec, const char *&name, cha
r * /*par*/) { |
| 54 if(exec) { |
| 55 logln("TestSuite UTS46Test: "); |
| 56 if(trans==NULL) { |
| 57 IcuTestErrorCode errorCode(*this, "init/createUTS46Instance()"); |
| 58 trans=IDNA::createUTS46Instance( |
| 59 UIDNA_USE_STD3_RULES|UIDNA_CHECK_BIDI|UIDNA_CHECK_CONTEXTJ, |
| 60 errorCode); |
| 61 nontrans=IDNA::createUTS46Instance( |
| 62 UIDNA_USE_STD3_RULES|UIDNA_CHECK_BIDI|UIDNA_CHECK_CONTEXTJ| |
| 63 UIDNA_NONTRANSITIONAL_TO_ASCII|UIDNA_NONTRANSITIONAL_TO_UNICODE, |
| 64 errorCode); |
| 65 if(errorCode.logDataIfFailureAndReset("createUTS46Instance()")) { |
| 66 name=""; |
| 67 return; |
| 68 } |
| 69 } |
| 70 } |
| 71 TESTCASE_AUTO_BEGIN; |
| 72 TESTCASE_AUTO(TestAPI); |
| 73 TESTCASE_AUTO(TestNotSTD3); |
| 74 TESTCASE_AUTO(TestSomeCases); |
| 75 TESTCASE_AUTO_END; |
| 76 } |
| 77 |
| 78 const uint32_t severeErrors= |
| 79 UIDNA_ERROR_LEADING_COMBINING_MARK| |
| 80 UIDNA_ERROR_DISALLOWED| |
| 81 UIDNA_ERROR_PUNYCODE| |
| 82 UIDNA_ERROR_LABEL_HAS_DOT| |
| 83 UIDNA_ERROR_INVALID_ACE_LABEL; |
| 84 |
| 85 static UBool isASCII(const UnicodeString &str) { |
| 86 const UChar *s=str.getBuffer(); |
| 87 int32_t length=str.length(); |
| 88 for(int32_t i=0; i<length; ++i) { |
| 89 if(s[i]>=0x80) { |
| 90 return FALSE; |
| 91 } |
| 92 } |
| 93 return TRUE; |
| 94 } |
| 95 |
| 96 class TestCheckedArrayByteSink : public CheckedArrayByteSink { |
| 97 public: |
| 98 TestCheckedArrayByteSink(char* outbuf, int32_t capacity) |
| 99 : CheckedArrayByteSink(outbuf, capacity), calledFlush(FALSE) {} |
| 100 virtual CheckedArrayByteSink& Reset() { |
| 101 CheckedArrayByteSink::Reset(); |
| 102 calledFlush = FALSE; |
| 103 return *this; |
| 104 } |
| 105 virtual void Flush() { calledFlush = TRUE; } |
| 106 UBool calledFlush; |
| 107 }; |
| 108 |
| 109 void UTS46Test::TestAPI() { |
| 110 UErrorCode errorCode=U_ZERO_ERROR; |
| 111 UnicodeString result; |
| 112 IDNAInfo info; |
| 113 UnicodeString input=UNICODE_STRING_SIMPLE("www.eXample.cOm"); |
| 114 UnicodeString expected=UNICODE_STRING_SIMPLE("www.example.com"); |
| 115 trans->nameToASCII(input, result, info, errorCode); |
| 116 if(U_FAILURE(errorCode) || info.hasErrors() || result!=expected) { |
| 117 errln("T.nameToASCII(www.example.com) info.errors=%04lx result matches=%
d %s", |
| 118 (long)info.getErrors(), result==expected, u_errorName(errorCode)); |
| 119 } |
| 120 errorCode=U_USELESS_COLLATOR_ERROR; |
| 121 trans->nameToUnicode(input, result, info, errorCode); |
| 122 if(errorCode!=U_USELESS_COLLATOR_ERROR || !result.isBogus()) { |
| 123 errln("T.nameToUnicode(U_FAILURE) did not preserve the errorCode " |
| 124 "or not result.setToBogus() - %s", |
| 125 u_errorName(errorCode)); |
| 126 } |
| 127 errorCode=U_ZERO_ERROR; |
| 128 input.setToBogus(); |
| 129 result=UNICODE_STRING_SIMPLE("quatsch"); |
| 130 nontrans->labelToASCII(input, result, info, errorCode); |
| 131 if(errorCode!=U_ILLEGAL_ARGUMENT_ERROR || !result.isBogus()) { |
| 132 errln("N.labelToASCII(bogus) did not set illegal-argument-error " |
| 133 "or not result.setToBogus() - %s", |
| 134 u_errorName(errorCode)); |
| 135 } |
| 136 errorCode=U_ZERO_ERROR; |
| 137 input=UNICODE_STRING_SIMPLE("xn--bcher.de-65a"); |
| 138 expected=UNICODE_STRING_SIMPLE("xn--bcher\\uFFFDde-65a").unescape(); |
| 139 nontrans->labelToASCII(input, result, info, errorCode); |
| 140 if( U_FAILURE(errorCode) || |
| 141 info.getErrors()!=(UIDNA_ERROR_LABEL_HAS_DOT|UIDNA_ERROR_INVALID_ACE_LAB
EL) || |
| 142 result!=expected |
| 143 ) { |
| 144 errln("N.labelToASCII(label-with-dot) failed with errors %04lx - %s", |
| 145 info.getErrors(), u_errorName(errorCode)); |
| 146 } |
| 147 // UTF-8 |
| 148 char buffer[100]; |
| 149 TestCheckedArrayByteSink sink(buffer, LENGTHOF(buffer)); |
| 150 errorCode=U_ZERO_ERROR; |
| 151 nontrans->labelToUnicodeUTF8(StringPiece(NULL, 5), sink, info, errorCode); |
| 152 if(errorCode!=U_ILLEGAL_ARGUMENT_ERROR || sink.NumberOfBytesWritten()!=0) { |
| 153 errln("N.labelToUnicodeUTF8(StringPiece(NULL, 5)) did not set illegal-ar
gument-error ", |
| 154 "or did output something - %s", |
| 155 u_errorName(errorCode)); |
| 156 } |
| 157 |
| 158 sink.Reset(); |
| 159 errorCode=U_ZERO_ERROR; |
| 160 nontrans->nameToASCII_UTF8(StringPiece(), sink, info, errorCode); |
| 161 if(U_FAILURE(errorCode) || sink.NumberOfBytesWritten()!=0 || !sink.calledFlu
sh) { |
| 162 errln("N.nameToASCII_UTF8(empty) failed - %s", |
| 163 u_errorName(errorCode)); |
| 164 } |
| 165 |
| 166 static const char s[]={ 0x61, (char)0xc3, (char)0x9f }; |
| 167 sink.Reset(); |
| 168 errorCode=U_USELESS_COLLATOR_ERROR; |
| 169 nontrans->nameToUnicodeUTF8(StringPiece(s, 3), sink, info, errorCode); |
| 170 if(errorCode!=U_USELESS_COLLATOR_ERROR || sink.NumberOfBytesWritten()!=0) { |
| 171 errln("N.nameToUnicode_UTF8(U_FAILURE) did not preserve the errorCode " |
| 172 "or did output something - %s", |
| 173 u_errorName(errorCode)); |
| 174 } |
| 175 |
| 176 sink.Reset(); |
| 177 errorCode=U_ZERO_ERROR; |
| 178 trans->labelToUnicodeUTF8(StringPiece(s, 3), sink, info, errorCode); |
| 179 if( U_FAILURE(errorCode) || sink.NumberOfBytesWritten()!=3 || |
| 180 buffer[0]!=0x61 || buffer[1]!=0x73 || buffer[2]!=0x73 || |
| 181 !sink.calledFlush |
| 182 ) { |
| 183 errln("T.labelToUnicodeUTF8(a sharp-s) failed - %s", |
| 184 u_errorName(errorCode)); |
| 185 } |
| 186 |
| 187 sink.Reset(); |
| 188 errorCode=U_ZERO_ERROR; |
| 189 // "eXampLe.cOm" |
| 190 static const char eX[]={ 0x65, 0x58, 0x61, 0x6d, 0x70, 0x4c, 0x65, 0x2e, 0x6
3, 0x4f, 0x6d, 0 }; |
| 191 // "example.com" |
| 192 static const char ex[]={ 0x65, 0x78, 0x61, 0x6d, 0x70, 0x6c, 0x65, 0x2e, 0x6
3, 0x6f, 0x6d }; |
| 193 trans->nameToUnicodeUTF8(eX, sink, info, errorCode); |
| 194 if( U_FAILURE(errorCode) || sink.NumberOfBytesWritten()!=11 || |
| 195 0!=memcmp(ex, buffer, 11) || !sink.calledFlush |
| 196 ) { |
| 197 errln("T.nameToUnicodeUTF8(eXampLe.cOm) failed - %s", |
| 198 u_errorName(errorCode)); |
| 199 } |
| 200 } |
| 201 |
| 202 void UTS46Test::TestNotSTD3() { |
| 203 IcuTestErrorCode errorCode(*this, "TestNotSTD3()"); |
| 204 char buffer[400]; |
| 205 LocalPointer<IDNA> not3(IDNA::createUTS46Instance(UIDNA_CHECK_BIDI, errorCod
e)); |
| 206 if(errorCode.isFailure()) { |
| 207 return; |
| 208 } |
| 209 UnicodeString input=UNICODE_STRING_SIMPLE("\\u0000A_2+2=4\\u000A.e\\u00DFen.
net").unescape(); |
| 210 UnicodeString result; |
| 211 IDNAInfo info; |
| 212 if( not3->nameToUnicode(input, result, info, errorCode)!= |
| 213 UNICODE_STRING_SIMPLE("\\u0000a_2+2=4\\u000A.essen.net").unescape()
|| |
| 214 info.hasErrors() |
| 215 ) { |
| 216 prettify(result).extract(0, 0x7fffffff, buffer, LENGTHOF(buffer)); |
| 217 errln("notSTD3.nameToUnicode(non-LDH ASCII) unexpected errors %04lx stri
ng %s", |
| 218 (long)info.getErrors(), buffer); |
| 219 } |
| 220 // A space (BiDi class WS) is not allowed in a BiDi domain name. |
| 221 input=UNICODE_STRING_SIMPLE("a z.xn--4db.edu"); |
| 222 not3->nameToASCII(input, result, info, errorCode); |
| 223 if(result!=input || info.getErrors()!=UIDNA_ERROR_BIDI) { |
| 224 errln("notSTD3.nameToASCII(ASCII-with-space.alef.edu) failed"); |
| 225 } |
| 226 // Characters that are canonically equivalent to sequences with non-LDH ASCI
I. |
| 227 input=UNICODE_STRING_SIMPLE("a\\u2260b\\u226Ec\\u226Fd").unescape(); |
| 228 not3->nameToUnicode(input, result, info, errorCode); |
| 229 if(result!=input || info.hasErrors()) { |
| 230 prettify(result).extract(0, 0x7fffffff, buffer, LENGTHOF(buffer)); |
| 231 errln("notSTD3.nameToUnicode(equiv to non-LDH ASCII) unexpected errors %
04lx string %s", |
| 232 (long)info.getErrors(), buffer); |
| 233 } |
| 234 } |
| 235 |
| 236 struct TestCase { |
| 237 // Input string and options string (Nontransitional/Transitional/Both). |
| 238 const char *s, *o; |
| 239 // Expected Unicode result string. |
| 240 const char *u; |
| 241 uint32_t errors; |
| 242 }; |
| 243 |
| 244 static const TestCase testCases[]={ |
| 245 { "www.eXample.cOm", "B", // all ASCII |
| 246 "www.example.com", 0 }, |
| 247 { "B\\u00FCcher.de", "B", // u-umlaut |
| 248 "b\\u00FCcher.de", 0 }, |
| 249 { "\\u00D6BB", "B", // O-umlaut |
| 250 "\\u00F6bb", 0 }, |
| 251 { "fa\\u00DF.de", "N", // sharp s |
| 252 "fa\\u00DF.de", 0 }, |
| 253 { "fa\\u00DF.de", "T", // sharp s |
| 254 "fass.de", 0 }, |
| 255 { "XN--fA-hia.dE", "B", // sharp s in Punycode |
| 256 "fa\\u00DF.de", 0 }, |
| 257 { "\\u03B2\\u03CC\\u03BB\\u03BF\\u03C2.com", "N", // Greek with final sigma |
| 258 "\\u03B2\\u03CC\\u03BB\\u03BF\\u03C2.com", 0 }, |
| 259 { "\\u03B2\\u03CC\\u03BB\\u03BF\\u03C2.com", "T", // Greek with final sigma |
| 260 "\\u03B2\\u03CC\\u03BB\\u03BF\\u03C3.com", 0 }, |
| 261 { "xn--nxasmm1c", "B", // Greek with final sigma in Punycode |
| 262 "\\u03B2\\u03CC\\u03BB\\u03BF\\u03C2", 0 }, |
| 263 { "www.\\u0DC1\\u0DCA\\u200D\\u0DBB\\u0DD3.com", "N", // "Sri" in "Sri Lank
a" has a ZWJ |
| 264 "www.\\u0DC1\\u0DCA\\u200D\\u0DBB\\u0DD3.com", 0 }, |
| 265 { "www.\\u0DC1\\u0DCA\\u200D\\u0DBB\\u0DD3.com", "T", // "Sri" in "Sri Lank
a" has a ZWJ |
| 266 "www.\\u0DC1\\u0DCA\\u0DBB\\u0DD3.com", 0 }, |
| 267 { "www.xn--10cl1a0b660p.com", "B", // "Sri" in Punycode |
| 268 "www.\\u0DC1\\u0DCA\\u200D\\u0DBB\\u0DD3.com", 0 }, |
| 269 { "\\u0646\\u0627\\u0645\\u0647\\u200C\\u0627\\u06CC", "N", // ZWNJ |
| 270 "\\u0646\\u0627\\u0645\\u0647\\u200C\\u0627\\u06CC", 0 }, |
| 271 { "\\u0646\\u0627\\u0645\\u0647\\u200C\\u0627\\u06CC", "T", // ZWNJ |
| 272 "\\u0646\\u0627\\u0645\\u0647\\u0627\\u06CC", 0 }, |
| 273 { "xn--mgba3gch31f060k.com", "B", // ZWNJ in Punycode |
| 274 "\\u0646\\u0627\\u0645\\u0647\\u200C\\u0627\\u06CC.com", 0 }, |
| 275 { "a.b\\uFF0Ec\\u3002d\\uFF61", "B", |
| 276 "a.b.c.d.", 0 }, |
| 277 { "U\\u0308.xn--tda", "B", // U+umlaut.u-umlaut |
| 278 "\\u00FC.\\u00FC", 0 }, |
| 279 { "xn--u-ccb", "B", // u+umlaut in Punycode |
| 280 "xn--u-ccb\\uFFFD", UIDNA_ERROR_INVALID_ACE_LABEL }, |
| 281 { "a\\u2488com", "B", // contains 1-dot |
| 282 "a\\uFFFDcom", UIDNA_ERROR_DISALLOWED }, |
| 283 { "xn--a-ecp.ru", "B", // contains 1-dot in Punycode |
| 284 "xn--a-ecp\\uFFFD.ru", UIDNA_ERROR_INVALID_ACE_LABEL }, |
| 285 { "xn--0.pt", "B", // invalid Punycode |
| 286 "xn--0\\uFFFD.pt", UIDNA_ERROR_PUNYCODE }, |
| 287 { "xn--a.pt", "B", // U+0080 |
| 288 "xn--a\\uFFFD.pt", UIDNA_ERROR_INVALID_ACE_LABEL }, |
| 289 { "xn--a-\\u00C4.pt", "B", // invalid Punycode |
| 290 "xn--a-\\u00E4.pt", UIDNA_ERROR_PUNYCODE }, |
| 291 { "\\u65E5\\u672C\\u8A9E\\u3002\\uFF2A\\uFF30", "B", // Japanese with fullw
idth ".jp" |
| 292 "\\u65E5\\u672C\\u8A9E.jp", 0 }, |
| 293 { "\\u2615", "B", "\\u2615", 0 }, // Unicode 4.0 HOT BEVERAGE |
| 294 // some characters are disallowed because they are canonically equivalent |
| 295 // to sequences with non-LDH ASCII |
| 296 { "a\\u2260b\\u226Ec\\u226Fd", "B", |
| 297 "a\\uFFFDb\\uFFFDc\\uFFFDd", UIDNA_ERROR_DISALLOWED }, |
| 298 // many deviation characters, test the special mapping code |
| 299 { "1.a\\u00DF\\u200C\\u200Db\\u200C\\u200Dc\\u00DF\\u00DF\\u00DF\\u00DFd" |
| 300 "\\u03C2\\u03C3\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DFe" |
| 301 "\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DFx" |
| 302 "\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DFy" |
| 303 "\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u0302\\u00DFz",
"N", |
| 304 "1.a\\u00DF\\u200C\\u200Db\\u200C\\u200Dc\\u00DF\\u00DF\\u00DF\\u00DFd" |
| 305 "\\u03C2\\u03C3\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DFe" |
| 306 "\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DFx" |
| 307 "\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DFy" |
| 308 "\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u0302\\u00DFz", |
| 309 UIDNA_ERROR_LABEL_TOO_LONG|UIDNA_ERROR_CONTEXTJ }, |
| 310 { "1.a\\u00DF\\u200C\\u200Db\\u200C\\u200Dc\\u00DF\\u00DF\\u00DF\\u00DFd" |
| 311 "\\u03C2\\u03C3\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DFe" |
| 312 "\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DFx" |
| 313 "\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DFy" |
| 314 "\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u00DF\\u0302\\u00DFz",
"T", |
| 315 "1.assbcssssssssd" |
| 316 "\\u03C3\\u03C3sssssssssssssssse" |
| 317 "ssssssssssssssssssssx" |
| 318 "ssssssssssssssssssssy" |
| 319 "sssssssssssssss\\u015Dssz", UIDNA_ERROR_LABEL_TOO_LONG }, |
| 320 // "xn--bss" with deviation characters |
| 321 { "\\u200Cx\\u200Dn\\u200C-\\u200D-b\\u00DF", "N", |
| 322 "\\u200Cx\\u200Dn\\u200C-\\u200D-b\\u00DF", UIDNA_ERROR_CONTEXTJ }, |
| 323 { "\\u200Cx\\u200Dn\\u200C-\\u200D-b\\u00DF", "T", |
| 324 "\\u5919", 0 }, |
| 325 // "xn--bssffl" written as: |
| 326 // 02E3 MODIFIER LETTER SMALL X |
| 327 // 034F COMBINING GRAPHEME JOINER (ignored) |
| 328 // 2115 DOUBLE-STRUCK CAPITAL N |
| 329 // 200B ZERO WIDTH SPACE (ignored) |
| 330 // FE63 SMALL HYPHEN-MINUS |
| 331 // 00AD SOFT HYPHEN (ignored) |
| 332 // FF0D FULLWIDTH HYPHEN-MINUS |
| 333 // 180C MONGOLIAN FREE VARIATION SELECTOR TWO (ignored) |
| 334 // 212C SCRIPT CAPITAL B |
| 335 // FE00 VARIATION SELECTOR-1 (ignored) |
| 336 // 017F LATIN SMALL LETTER LONG S |
| 337 // 2064 INVISIBLE PLUS (ignored) |
| 338 // 1D530 MATHEMATICAL FRAKTUR SMALL S |
| 339 // E01EF VARIATION SELECTOR-256 (ignored) |
| 340 // FB04 LATIN SMALL LIGATURE FFL |
| 341 { "\\u02E3\\u034F\\u2115\\u200B\\uFE63\\u00AD\\uFF0D\\u180C" |
| 342 "\\u212C\\uFE00\\u017F\\u2064\\U0001D530\\U000E01EF\\uFB04", "B", |
| 343 "\\u5921\\u591E\\u591C\\u5919", 0 }, |
| 344 { "123456789012345678901234567890123456789012345678901234567890123." |
| 345 "123456789012345678901234567890123456789012345678901234567890123." |
| 346 "123456789012345678901234567890123456789012345678901234567890123." |
| 347 "1234567890123456789012345678901234567890123456789012345678901", "B", |
| 348 "123456789012345678901234567890123456789012345678901234567890123." |
| 349 "123456789012345678901234567890123456789012345678901234567890123." |
| 350 "123456789012345678901234567890123456789012345678901234567890123." |
| 351 "1234567890123456789012345678901234567890123456789012345678901", 0 }, |
| 352 { "123456789012345678901234567890123456789012345678901234567890123." |
| 353 "123456789012345678901234567890123456789012345678901234567890123." |
| 354 "123456789012345678901234567890123456789012345678901234567890123." |
| 355 "1234567890123456789012345678901234567890123456789012345678901.", "B", |
| 356 "123456789012345678901234567890123456789012345678901234567890123." |
| 357 "123456789012345678901234567890123456789012345678901234567890123." |
| 358 "123456789012345678901234567890123456789012345678901234567890123." |
| 359 "1234567890123456789012345678901234567890123456789012345678901.", 0 }, |
| 360 // Domain name >256 characters, forces slow path in UTF-8 processing. |
| 361 { "123456789012345678901234567890123456789012345678901234567890123." |
| 362 "123456789012345678901234567890123456789012345678901234567890123." |
| 363 "123456789012345678901234567890123456789012345678901234567890123." |
| 364 "123456789012345678901234567890123456789012345678901234567890123." |
| 365 "12345678901234567890123456789012345678901234567890123456789012", "B", |
| 366 "123456789012345678901234567890123456789012345678901234567890123." |
| 367 "123456789012345678901234567890123456789012345678901234567890123." |
| 368 "123456789012345678901234567890123456789012345678901234567890123." |
| 369 "123456789012345678901234567890123456789012345678901234567890123." |
| 370 "12345678901234567890123456789012345678901234567890123456789012", |
| 371 UIDNA_ERROR_DOMAIN_NAME_TOO_LONG }, |
| 372 { "123456789012345678901234567890123456789012345678901234567890123." |
| 373 "123456789012345678901234567890123456789012345678901234567890123." |
| 374 "123456789012345678901234567890123456789012345678901234567890123." |
| 375 "123456789012345678901234567890123456789012345678901234567890123." |
| 376 "1234567890123456789012345678901234567890123456789\\u05D0", "B", |
| 377 "123456789012345678901234567890123456789012345678901234567890123." |
| 378 "123456789012345678901234567890123456789012345678901234567890123." |
| 379 "123456789012345678901234567890123456789012345678901234567890123." |
| 380 "123456789012345678901234567890123456789012345678901234567890123." |
| 381 "1234567890123456789012345678901234567890123456789\\u05D0", |
| 382 UIDNA_ERROR_DOMAIN_NAME_TOO_LONG|UIDNA_ERROR_BIDI }, |
| 383 { "123456789012345678901234567890123456789012345678901234567890123." |
| 384 "1234567890123456789012345678901234567890123456789012345678901234." |
| 385 "123456789012345678901234567890123456789012345678901234567890123." |
| 386 "123456789012345678901234567890123456789012345678901234567890", "B", |
| 387 "123456789012345678901234567890123456789012345678901234567890123." |
| 388 "1234567890123456789012345678901234567890123456789012345678901234." |
| 389 "123456789012345678901234567890123456789012345678901234567890123." |
| 390 "123456789012345678901234567890123456789012345678901234567890", |
| 391 UIDNA_ERROR_LABEL_TOO_LONG }, |
| 392 { "123456789012345678901234567890123456789012345678901234567890123." |
| 393 "1234567890123456789012345678901234567890123456789012345678901234." |
| 394 "123456789012345678901234567890123456789012345678901234567890123." |
| 395 "123456789012345678901234567890123456789012345678901234567890.", "B", |
| 396 "123456789012345678901234567890123456789012345678901234567890123." |
| 397 "1234567890123456789012345678901234567890123456789012345678901234." |
| 398 "123456789012345678901234567890123456789012345678901234567890123." |
| 399 "123456789012345678901234567890123456789012345678901234567890.", |
| 400 UIDNA_ERROR_LABEL_TOO_LONG }, |
| 401 { "123456789012345678901234567890123456789012345678901234567890123." |
| 402 "1234567890123456789012345678901234567890123456789012345678901234." |
| 403 "123456789012345678901234567890123456789012345678901234567890123." |
| 404 "1234567890123456789012345678901234567890123456789012345678901", "B", |
| 405 "123456789012345678901234567890123456789012345678901234567890123." |
| 406 "1234567890123456789012345678901234567890123456789012345678901234." |
| 407 "123456789012345678901234567890123456789012345678901234567890123." |
| 408 "1234567890123456789012345678901234567890123456789012345678901", |
| 409 UIDNA_ERROR_LABEL_TOO_LONG|UIDNA_ERROR_DOMAIN_NAME_TOO_LONG }, |
| 410 // label length 63: xn--1234567890123456789012345678901234567890123456789012
345-9te |
| 411 { "\\u00E41234567890123456789012345678901234567890123456789012345", "B", |
| 412 "\\u00E41234567890123456789012345678901234567890123456789012345", 0 }, |
| 413 { "1234567890\\u00E41234567890123456789012345678901234567890123456", "B", |
| 414 "1234567890\\u00E41234567890123456789012345678901234567890123456", UIDNA_E
RROR_LABEL_TOO_LONG }, |
| 415 { "123456789012345678901234567890123456789012345678901234567890123." |
| 416 "1234567890\\u00E4123456789012345678901234567890123456789012345." |
| 417 "123456789012345678901234567890123456789012345678901234567890123." |
| 418 "1234567890123456789012345678901234567890123456789012345678901", "B", |
| 419 "123456789012345678901234567890123456789012345678901234567890123." |
| 420 "1234567890\\u00E4123456789012345678901234567890123456789012345." |
| 421 "123456789012345678901234567890123456789012345678901234567890123." |
| 422 "1234567890123456789012345678901234567890123456789012345678901", 0 }, |
| 423 { "123456789012345678901234567890123456789012345678901234567890123." |
| 424 "1234567890\\u00E4123456789012345678901234567890123456789012345." |
| 425 "123456789012345678901234567890123456789012345678901234567890123." |
| 426 "1234567890123456789012345678901234567890123456789012345678901.", "B", |
| 427 "123456789012345678901234567890123456789012345678901234567890123." |
| 428 "1234567890\\u00E4123456789012345678901234567890123456789012345." |
| 429 "123456789012345678901234567890123456789012345678901234567890123." |
| 430 "1234567890123456789012345678901234567890123456789012345678901.", 0 }, |
| 431 { "123456789012345678901234567890123456789012345678901234567890123." |
| 432 "1234567890\\u00E4123456789012345678901234567890123456789012345." |
| 433 "123456789012345678901234567890123456789012345678901234567890123." |
| 434 "12345678901234567890123456789012345678901234567890123456789012", "B", |
| 435 "123456789012345678901234567890123456789012345678901234567890123." |
| 436 "1234567890\\u00E4123456789012345678901234567890123456789012345." |
| 437 "123456789012345678901234567890123456789012345678901234567890123." |
| 438 "12345678901234567890123456789012345678901234567890123456789012", |
| 439 UIDNA_ERROR_DOMAIN_NAME_TOO_LONG }, |
| 440 { "123456789012345678901234567890123456789012345678901234567890123." |
| 441 "1234567890\\u00E41234567890123456789012345678901234567890123456." |
| 442 "123456789012345678901234567890123456789012345678901234567890123." |
| 443 "123456789012345678901234567890123456789012345678901234567890", "B", |
| 444 "123456789012345678901234567890123456789012345678901234567890123." |
| 445 "1234567890\\u00E41234567890123456789012345678901234567890123456." |
| 446 "123456789012345678901234567890123456789012345678901234567890123." |
| 447 "123456789012345678901234567890123456789012345678901234567890", |
| 448 UIDNA_ERROR_LABEL_TOO_LONG }, |
| 449 { "123456789012345678901234567890123456789012345678901234567890123." |
| 450 "1234567890\\u00E41234567890123456789012345678901234567890123456." |
| 451 "123456789012345678901234567890123456789012345678901234567890123." |
| 452 "123456789012345678901234567890123456789012345678901234567890.", "B", |
| 453 "123456789012345678901234567890123456789012345678901234567890123." |
| 454 "1234567890\\u00E41234567890123456789012345678901234567890123456." |
| 455 "123456789012345678901234567890123456789012345678901234567890123." |
| 456 "123456789012345678901234567890123456789012345678901234567890.", |
| 457 UIDNA_ERROR_LABEL_TOO_LONG }, |
| 458 { "123456789012345678901234567890123456789012345678901234567890123." |
| 459 "1234567890\\u00E41234567890123456789012345678901234567890123456." |
| 460 "123456789012345678901234567890123456789012345678901234567890123." |
| 461 "1234567890123456789012345678901234567890123456789012345678901", "B", |
| 462 "123456789012345678901234567890123456789012345678901234567890123." |
| 463 "1234567890\\u00E41234567890123456789012345678901234567890123456." |
| 464 "123456789012345678901234567890123456789012345678901234567890123." |
| 465 "1234567890123456789012345678901234567890123456789012345678901", |
| 466 UIDNA_ERROR_LABEL_TOO_LONG|UIDNA_ERROR_DOMAIN_NAME_TOO_LONG }, |
| 467 // hyphen errors and empty-label errors |
| 468 // "xn---q----jra"=="-q--a-umlaut-" |
| 469 { "a.b..-q--a-.e", "B", "a.b..-q--a-.e", |
| 470 UIDNA_ERROR_EMPTY_LABEL|UIDNA_ERROR_LEADING_HYPHEN|UIDNA_ERROR_TRAILING_HY
PHEN| |
| 471 UIDNA_ERROR_HYPHEN_3_4 }, |
| 472 { "a.b..-q--\\u00E4-.e", "B", "a.b..-q--\\u00E4-.e", |
| 473 UIDNA_ERROR_EMPTY_LABEL|UIDNA_ERROR_LEADING_HYPHEN|UIDNA_ERROR_TRAILING_HY
PHEN| |
| 474 UIDNA_ERROR_HYPHEN_3_4 }, |
| 475 { "a.b..xn---q----jra.e", "B", "a.b..-q--\\u00E4-.e", |
| 476 UIDNA_ERROR_EMPTY_LABEL|UIDNA_ERROR_LEADING_HYPHEN|UIDNA_ERROR_TRAILING_HY
PHEN| |
| 477 UIDNA_ERROR_HYPHEN_3_4 }, |
| 478 { "a..c", "B", "a..c", UIDNA_ERROR_EMPTY_LABEL }, |
| 479 { "a.-b.", "B", "a.-b.", UIDNA_ERROR_LEADING_HYPHEN }, |
| 480 { "a.b-.c", "B", "a.b-.c", UIDNA_ERROR_TRAILING_HYPHEN }, |
| 481 { "a.-.c", "B", "a.-.c", UIDNA_ERROR_LEADING_HYPHEN|UIDNA_ERROR_TRAILING_HYP
HEN }, |
| 482 { "a.bc--de.f", "B", "a.bc--de.f", UIDNA_ERROR_HYPHEN_3_4 }, |
| 483 { "\\u00E4.\\u00AD.c", "B", "\\u00E4..c", UIDNA_ERROR_EMPTY_LABEL }, |
| 484 { "\\u00E4.-b.", "B", "\\u00E4.-b.", UIDNA_ERROR_LEADING_HYPHEN }, |
| 485 { "\\u00E4.b-.c", "B", "\\u00E4.b-.c", UIDNA_ERROR_TRAILING_HYPHEN }, |
| 486 { "\\u00E4.-.c", "B", "\\u00E4.-.c", UIDNA_ERROR_LEADING_HYPHEN|UIDNA_ERROR_
TRAILING_HYPHEN }, |
| 487 { "\\u00E4.bc--de.f", "B", "\\u00E4.bc--de.f", UIDNA_ERROR_HYPHEN_3_4 }, |
| 488 { "a.b.\\u0308c.d", "B", "a.b.\\uFFFDc.d", UIDNA_ERROR_LEADING_COMBINING_MAR
K }, |
| 489 { "a.b.xn--c-bcb.d", "B", |
| 490 "a.b.xn--c-bcb\\uFFFD.d", UIDNA_ERROR_LEADING_COMBINING_MARK|UIDNA_ERROR_I
NVALID_ACE_LABEL }, |
| 491 // BiDi |
| 492 { "A0", "B", "a0", 0 }, |
| 493 { "0A", "B", "0a", 0 }, // all-LTR is ok to start with a digit (EN) |
| 494 { "0A.\\u05D0", "B", // ASCII label does not start with L/R/AL |
| 495 "0a.\\u05D0", UIDNA_ERROR_BIDI }, |
| 496 { "c.xn--0-eha.xn--4db", "B", // 2nd label does not start with L/R/AL |
| 497 "c.0\\u00FC.\\u05D0", UIDNA_ERROR_BIDI }, |
| 498 { "b-.\\u05D0", "B", // label does not end with L/EN |
| 499 "b-.\\u05D0", UIDNA_ERROR_TRAILING_HYPHEN|UIDNA_ERROR_BIDI }, |
| 500 { "d.xn----dha.xn--4db", "B", // 2nd label does not end with L/EN |
| 501 "d.\\u00FC-.\\u05D0", UIDNA_ERROR_TRAILING_HYPHEN|UIDNA_ERROR_BIDI }, |
| 502 { "a\\u05D0", "B", "a\\u05D0", UIDNA_ERROR_BIDI }, // first dir != last dir |
| 503 { "\\u05D0\\u05C7", "B", "\\u05D0\\u05C7", 0 }, |
| 504 { "\\u05D09\\u05C7", "B", "\\u05D09\\u05C7", 0 }, |
| 505 { "\\u05D0a\\u05C7", "B", "\\u05D0a\\u05C7", UIDNA_ERROR_BIDI }, // first d
ir != last dir |
| 506 { "\\u05D0\\u05EA", "B", "\\u05D0\\u05EA", 0 }, |
| 507 { "\\u05D0\\u05F3\\u05EA", "B", "\\u05D0\\u05F3\\u05EA", 0 }, |
| 508 { "a\\u05D0Tz", "B", "a\\u05D0tz", UIDNA_ERROR_BIDI }, // mixed dir |
| 509 { "\\u05D0T\\u05EA", "B", "\\u05D0t\\u05EA", UIDNA_ERROR_BIDI }, // mixed d
ir |
| 510 { "\\u05D07\\u05EA", "B", "\\u05D07\\u05EA", 0 }, |
| 511 { "\\u05D0\\u0667\\u05EA", "B", "\\u05D0\\u0667\\u05EA", 0 }, // Arabic 7 i
n the middle |
| 512 { "a7\\u0667z", "B", "a7\\u0667z", UIDNA_ERROR_BIDI }, // AN digit in LTR |
| 513 { "\\u05D07\\u0667\\u05EA", "B", // mixed EN/AN digits in RTL |
| 514 "\\u05D07\\u0667\\u05EA", UIDNA_ERROR_BIDI }, |
| 515 // ZWJ |
| 516 { "\\u0BB9\\u0BCD\\u200D", "N", "\\u0BB9\\u0BCD\\u200D", 0 }, // Virama+ZWJ |
| 517 { "\\u0BB9\\u200D", "N", "\\u0BB9\\u200D", UIDNA_ERROR_CONTEXTJ }, // no Vi
rama |
| 518 { "\\u200D", "N", "\\u200D", UIDNA_ERROR_CONTEXTJ }, // no Virama |
| 519 // ZWNJ |
| 520 { "\\u0BB9\\u0BCD\\u200C", "N", "\\u0BB9\\u0BCD\\u200C", 0 }, // Virama+ZWN
J |
| 521 { "\\u0BB9\\u200C", "N", "\\u0BB9\\u200C", UIDNA_ERROR_CONTEXTJ }, // no Vi
rama |
| 522 { "\\u200C", "N", "\\u200C", UIDNA_ERROR_CONTEXTJ }, // no Virama |
| 523 { "\\u0644\\u0670\\u200C\\u06ED\\u06EF", "N", // Joining types D T ZWNJ T R |
| 524 "\\u0644\\u0670\\u200C\\u06ED\\u06EF", 0 }, |
| 525 { "\\u0644\\u0670\\u200C\\u06EF", "N", // D T ZWNJ R |
| 526 "\\u0644\\u0670\\u200C\\u06EF", 0 }, |
| 527 { "\\u0644\\u200C\\u06ED\\u06EF", "N", // D ZWNJ T R |
| 528 "\\u0644\\u200C\\u06ED\\u06EF", 0 }, |
| 529 { "\\u0644\\u200C\\u06EF", "N", // D ZWNJ R |
| 530 "\\u0644\\u200C\\u06EF", 0 }, |
| 531 { "\\u0644\\u0670\\u200C\\u06ED", "N", // D T ZWNJ T |
| 532 "\\u0644\\u0670\\u200C\\u06ED", UIDNA_ERROR_BIDI|UIDNA_ERROR_CONTEXTJ }, |
| 533 { "\\u06EF\\u200C\\u06EF", "N", // R ZWNJ R |
| 534 "\\u06EF\\u200C\\u06EF", UIDNA_ERROR_CONTEXTJ }, |
| 535 { "\\u0644\\u200C", "N", // D ZWNJ |
| 536 "\\u0644\\u200C", UIDNA_ERROR_BIDI|UIDNA_ERROR_CONTEXTJ }, |
| 537 // Ticket #8137: UTS #46 toUnicode() fails with non-ASCII labels that turn |
| 538 // into 15 characters (UChars). |
| 539 // The bug was in u_strFromPunycode() which did not write the last character |
| 540 // if it just so fit into the end of the destination buffer. |
| 541 // The UTS #46 code gives a default-capacity UnicodeString as the destinatio
n buffer, |
| 542 // and the internal UnicodeString capacity is currently 15 UChars on 64-bit
machines |
| 543 // but 13 on 32-bit machines. |
| 544 // Label with 15 UChars, for 64-bit-machine testing: |
| 545 { "aaaaaaaaaaaaa\\u00FCa.de", "B", "aaaaaaaaaaaaa\\u00FCa.de", 0 }, |
| 546 { "xn--aaaaaaaaaaaaaa-ssb.de", "B", "aaaaaaaaaaaaa\\u00FCa.de", 0 }, |
| 547 { "abschlu\\u00DFpr\\u00FCfung.de", "N", "abschlu\\u00DFpr\\u00FCfung.de", 0
}, |
| 548 { "xn--abschluprfung-hdb15b.de", "B", "abschlu\\u00DFpr\\u00FCfung.de", 0 }, |
| 549 // Label with 13 UChars, for 32-bit-machine testing: |
| 550 { "xn--aaaaaaaaaaaa-nlb.de", "B", "aaaaaaaaaaa\\u00FCa.de", 0 }, |
| 551 { "xn--schluprfung-z6a39a.de", "B", "schlu\\u00DFpr\\u00FCfung.de", 0 }, |
| 552 // { "", "B", |
| 553 // "", 0 }, |
| 554 }; |
| 555 |
| 556 void UTS46Test::TestSomeCases() { |
| 557 IcuTestErrorCode errorCode(*this, "TestSomeCases"); |
| 558 char buffer[400], buffer2[400]; |
| 559 int32_t i; |
| 560 for(i=0; i<LENGTHOF(testCases); ++i) { |
| 561 const TestCase &testCase=testCases[i]; |
| 562 UnicodeString input(ctou(testCase.s)); |
| 563 UnicodeString expected(ctou(testCase.u)); |
| 564 // ToASCII/ToUnicode, transitional/nontransitional |
| 565 UnicodeString aT, uT, aN, uN; |
| 566 IDNAInfo aTInfo, uTInfo, aNInfo, uNInfo; |
| 567 trans->nameToASCII(input, aT, aTInfo, errorCode); |
| 568 trans->nameToUnicode(input, uT, uTInfo, errorCode); |
| 569 nontrans->nameToASCII(input, aN, aNInfo, errorCode); |
| 570 nontrans->nameToUnicode(input, uN, uNInfo, errorCode); |
| 571 if(errorCode.logIfFailureAndReset("first-level processing [%d/%s] %s", |
| 572 (int)i, testCase.o, testCase.s) |
| 573 ) { |
| 574 continue; |
| 575 } |
| 576 // ToUnicode does not set length errors. |
| 577 uint32_t uniErrors=testCase.errors&~ |
| 578 (UIDNA_ERROR_EMPTY_LABEL| |
| 579 UIDNA_ERROR_LABEL_TOO_LONG| |
| 580 UIDNA_ERROR_DOMAIN_NAME_TOO_LONG); |
| 581 char mode=testCase.o[0]; |
| 582 if(mode=='B' || mode=='N') { |
| 583 if(uNInfo.getErrors()!=uniErrors) { |
| 584 errln("N.nameToUnicode([%d] %s) unexpected errors %04lx", |
| 585 (int)i, testCase.s, (long)uNInfo.getErrors()); |
| 586 continue; |
| 587 } |
| 588 if(uN!=expected) { |
| 589 prettify(uN).extract(0, 0x7fffffff, buffer, LENGTHOF(buffer)); |
| 590 errln("N.nameToUnicode([%d] %s) unexpected string %s", |
| 591 (int)i, testCase.s, buffer); |
| 592 continue; |
| 593 } |
| 594 if(aNInfo.getErrors()!=testCase.errors) { |
| 595 errln("N.nameToASCII([%d] %s) unexpected errors %04lx", |
| 596 (int)i, testCase.s, (long)aNInfo.getErrors()); |
| 597 continue; |
| 598 } |
| 599 } |
| 600 if(mode=='B' || mode=='T') { |
| 601 if(uTInfo.getErrors()!=uniErrors) { |
| 602 errln("T.nameToUnicode([%d] %s) unexpected errors %04lx", |
| 603 (int)i, testCase.s, (long)uTInfo.getErrors()); |
| 604 continue; |
| 605 } |
| 606 if(uT!=expected) { |
| 607 prettify(uT).extract(0, 0x7fffffff, buffer, LENGTHOF(buffer)); |
| 608 errln("T.nameToUnicode([%d] %s) unexpected string %s", |
| 609 (int)i, testCase.s, buffer); |
| 610 continue; |
| 611 } |
| 612 if(aTInfo.getErrors()!=testCase.errors) { |
| 613 errln("T.nameToASCII([%d] %s) unexpected errors %04lx", |
| 614 (int)i, testCase.s, (long)aTInfo.getErrors()); |
| 615 continue; |
| 616 } |
| 617 } |
| 618 // ToASCII is all-ASCII if no severe errors |
| 619 if((aNInfo.getErrors()&severeErrors)==0 && !isASCII(aN)) { |
| 620 prettify(aN).extract(0, 0x7fffffff, buffer, LENGTHOF(buffer)); |
| 621 errln("N.nameToASCII([%d] %s) (errors %04lx) result is not ASCII %s"
, |
| 622 (int)i, testCase.s, aNInfo.getErrors(), buffer); |
| 623 continue; |
| 624 } |
| 625 if((aTInfo.getErrors()&severeErrors)==0 && !isASCII(aT)) { |
| 626 prettify(aT).extract(0, 0x7fffffff, buffer, LENGTHOF(buffer)); |
| 627 errln("T.nameToASCII([%d] %s) (errors %04lx) result is not ASCII %s"
, |
| 628 (int)i, testCase.s, aTInfo.getErrors(), buffer); |
| 629 continue; |
| 630 } |
| 631 if(verbose) { |
| 632 char m= mode=='B' ? mode : 'N'; |
| 633 prettify(aN).extract(0, 0x7fffffff, buffer, LENGTHOF(buffer)); |
| 634 logln("%c.nameToASCII([%d] %s) (errors %04lx) result string: %s", |
| 635 m, (int)i, testCase.s, aNInfo.getErrors(), buffer); |
| 636 if(mode!='B') { |
| 637 prettify(aT).extract(0, 0x7fffffff, buffer, LENGTHOF(buffer)); |
| 638 logln("T.nameToASCII([%d] %s) (errors %04lx) result string: %s", |
| 639 (int)i, testCase.s, aTInfo.getErrors(), buffer); |
| 640 } |
| 641 } |
| 642 // second-level processing |
| 643 UnicodeString aTuN, uTaN, aNuN, uNaN; |
| 644 IDNAInfo aTuNInfo, uTaNInfo, aNuNInfo, uNaNInfo; |
| 645 nontrans->nameToUnicode(aT, aTuN, aTuNInfo, errorCode); |
| 646 nontrans->nameToASCII(uT, uTaN, uTaNInfo, errorCode); |
| 647 nontrans->nameToUnicode(aN, aNuN, aNuNInfo, errorCode); |
| 648 nontrans->nameToASCII(uN, uNaN, uNaNInfo, errorCode); |
| 649 if(errorCode.logIfFailureAndReset("second-level processing [%d/%s] %s", |
| 650 (int)i, testCase.o, testCase.s) |
| 651 ) { |
| 652 continue; |
| 653 } |
| 654 if(aN!=uNaN) { |
| 655 prettify(aN).extract(0, 0x7fffffff, buffer, LENGTHOF(buffer)); |
| 656 prettify(uNaN).extract(0, 0x7fffffff, buffer2, LENGTHOF(buffer2)); |
| 657 errln("N.nameToASCII([%d] %s)!=N.nameToUnicode().N.nameToASCII() " |
| 658 "(errors %04lx) %s vs. %s", |
| 659 (int)i, testCase.s, aNInfo.getErrors(), buffer, buffer2); |
| 660 continue; |
| 661 } |
| 662 if(aT!=uTaN) { |
| 663 prettify(aT).extract(0, 0x7fffffff, buffer, LENGTHOF(buffer)); |
| 664 prettify(uTaN).extract(0, 0x7fffffff, buffer2, LENGTHOF(buffer2)); |
| 665 errln("T.nameToASCII([%d] %s)!=T.nameToUnicode().N.nameToASCII() " |
| 666 "(errors %04lx) %s vs. %s", |
| 667 (int)i, testCase.s, aNInfo.getErrors(), buffer, buffer2); |
| 668 continue; |
| 669 } |
| 670 if(uN!=aNuN) { |
| 671 prettify(uN).extract(0, 0x7fffffff, buffer, LENGTHOF(buffer)); |
| 672 prettify(aNuN).extract(0, 0x7fffffff, buffer2, LENGTHOF(buffer2)); |
| 673 errln("N.nameToUnicode([%d] %s)!=N.nameToASCII().N.nameToUnicode() " |
| 674 "(errors %04lx) %s vs. %s", |
| 675 (int)i, testCase.s, uNInfo.getErrors(), buffer, buffer2); |
| 676 continue; |
| 677 } |
| 678 if(uT!=aTuN) { |
| 679 prettify(uT).extract(0, 0x7fffffff, buffer, LENGTHOF(buffer)); |
| 680 prettify(aTuN).extract(0, 0x7fffffff, buffer2, LENGTHOF(buffer2)); |
| 681 errln("T.nameToUnicode([%d] %s)!=T.nameToASCII().N.nameToUnicode() " |
| 682 "(errors %04lx) %s vs. %s", |
| 683 (int)i, testCase.s, uNInfo.getErrors(), buffer, buffer2); |
| 684 continue; |
| 685 } |
| 686 // labelToUnicode |
| 687 UnicodeString aTL, uTL, aNL, uNL; |
| 688 IDNAInfo aTLInfo, uTLInfo, aNLInfo, uNLInfo; |
| 689 trans->labelToASCII(input, aTL, aTLInfo, errorCode); |
| 690 trans->labelToUnicode(input, uTL, uTLInfo, errorCode); |
| 691 nontrans->labelToASCII(input, aNL, aNLInfo, errorCode); |
| 692 nontrans->labelToUnicode(input, uNL, uNLInfo, errorCode); |
| 693 if(errorCode.logIfFailureAndReset("labelToXYZ processing [%d/%s] %s", |
| 694 (int)i, testCase.o, testCase.s) |
| 695 ) { |
| 696 continue; |
| 697 } |
| 698 if(aN.indexOf((UChar)0x2e)<0) { |
| 699 if(aN!=aNL || aNInfo.getErrors()!=aNLInfo.getErrors()) { |
| 700 prettify(aN).extract(0, 0x7fffffff, buffer, LENGTHOF(buffer)); |
| 701 prettify(aNL).extract(0, 0x7fffffff, buffer2, LENGTHOF(buffer2))
; |
| 702 errln("N.nameToASCII([%d] %s)!=N.labelToASCII() " |
| 703 "(errors %04lx vs %04lx) %s vs. %s", |
| 704 (int)i, testCase.s, aNInfo.getErrors(), aNLInfo.getErrors(
), buffer, buffer2); |
| 705 continue; |
| 706 } |
| 707 } else { |
| 708 if((aNLInfo.getErrors()&UIDNA_ERROR_LABEL_HAS_DOT)==0) { |
| 709 errln("N.labelToASCII([%d] %s) errors %04lx missing UIDNA_ERROR_
LABEL_HAS_DOT", |
| 710 (int)i, testCase.s, (long)aNLInfo.getErrors()); |
| 711 continue; |
| 712 } |
| 713 } |
| 714 if(aT.indexOf((UChar)0x2e)<0) { |
| 715 if(aT!=aTL || aTInfo.getErrors()!=aTLInfo.getErrors()) { |
| 716 prettify(aT).extract(0, 0x7fffffff, buffer, LENGTHOF(buffer)); |
| 717 prettify(aTL).extract(0, 0x7fffffff, buffer2, LENGTHOF(buffer2))
; |
| 718 errln("T.nameToASCII([%d] %s)!=T.labelToASCII() " |
| 719 "(errors %04lx vs %04lx) %s vs. %s", |
| 720 (int)i, testCase.s, aTInfo.getErrors(), aTLInfo.getErrors(
), buffer, buffer2); |
| 721 continue; |
| 722 } |
| 723 } else { |
| 724 if((aTLInfo.getErrors()&UIDNA_ERROR_LABEL_HAS_DOT)==0) { |
| 725 errln("T.labelToASCII([%d] %s) errors %04lx missing UIDNA_ERROR_
LABEL_HAS_DOT", |
| 726 (int)i, testCase.s, (long)aTLInfo.getErrors()); |
| 727 continue; |
| 728 } |
| 729 } |
| 730 if(uN.indexOf((UChar)0x2e)<0) { |
| 731 if(uN!=uNL || uNInfo.getErrors()!=uNLInfo.getErrors()) { |
| 732 prettify(uN).extract(0, 0x7fffffff, buffer, LENGTHOF(buffer)); |
| 733 prettify(uNL).extract(0, 0x7fffffff, buffer2, LENGTHOF(buffer2))
; |
| 734 errln("N.nameToUnicode([%d] %s)!=N.labelToUnicode() " |
| 735 "(errors %04lx vs %04lx) %s vs. %s", |
| 736 (int)i, testCase.s, uNInfo.getErrors(), uNLInfo.getErrors(
), buffer, buffer2); |
| 737 continue; |
| 738 } |
| 739 } else { |
| 740 if((uNLInfo.getErrors()&UIDNA_ERROR_LABEL_HAS_DOT)==0) { |
| 741 errln("N.labelToUnicode([%d] %s) errors %04lx missing UIDNA_ERRO
R_LABEL_HAS_DOT", |
| 742 (int)i, testCase.s, (long)uNLInfo.getErrors()); |
| 743 continue; |
| 744 } |
| 745 } |
| 746 if(uT.indexOf((UChar)0x2e)<0) { |
| 747 if(uT!=uTL || uTInfo.getErrors()!=uTLInfo.getErrors()) { |
| 748 prettify(uT).extract(0, 0x7fffffff, buffer, LENGTHOF(buffer)); |
| 749 prettify(uTL).extract(0, 0x7fffffff, buffer2, LENGTHOF(buffer2))
; |
| 750 errln("T.nameToUnicode([%d] %s)!=T.labelToUnicode() " |
| 751 "(errors %04lx vs %04lx) %s vs. %s", |
| 752 (int)i, testCase.s, uTInfo.getErrors(), uTLInfo.getErrors(
), buffer, buffer2); |
| 753 continue; |
| 754 } |
| 755 } else { |
| 756 if((uTLInfo.getErrors()&UIDNA_ERROR_LABEL_HAS_DOT)==0) { |
| 757 errln("T.labelToUnicode([%d] %s) errors %04lx missing UIDNA_ERRO
R_LABEL_HAS_DOT", |
| 758 (int)i, testCase.s, (long)uTLInfo.getErrors()); |
| 759 continue; |
| 760 } |
| 761 } |
| 762 // Differences between transitional and nontransitional processing |
| 763 if(mode=='B') { |
| 764 if( aNInfo.isTransitionalDifferent() || |
| 765 aTInfo.isTransitionalDifferent() || |
| 766 uNInfo.isTransitionalDifferent() || |
| 767 uTInfo.isTransitionalDifferent() || |
| 768 aNLInfo.isTransitionalDifferent() || |
| 769 aTLInfo.isTransitionalDifferent() || |
| 770 uNLInfo.isTransitionalDifferent() || |
| 771 uTLInfo.isTransitionalDifferent() |
| 772 ) { |
| 773 errln("B.process([%d] %s) isTransitionalDifferent()", (int)i, te
stCase.s); |
| 774 continue; |
| 775 } |
| 776 if( aN!=aT || uN!=uT || aNL!=aTL || uNL!=uTL || |
| 777 aNInfo.getErrors()!=aTInfo.getErrors() || uNInfo.getErrors()!=uT
Info.getErrors() || |
| 778 aNLInfo.getErrors()!=aTLInfo.getErrors() || uNLInfo.getErrors()!
=uTLInfo.getErrors() |
| 779 ) { |
| 780 errln("N.process([%d] %s) vs. T.process() different errors or re
sult strings", |
| 781 (int)i, testCase.s); |
| 782 continue; |
| 783 } |
| 784 } else { |
| 785 if( !aNInfo.isTransitionalDifferent() || |
| 786 !aTInfo.isTransitionalDifferent() || |
| 787 !uNInfo.isTransitionalDifferent() || |
| 788 !uTInfo.isTransitionalDifferent() || |
| 789 !aNLInfo.isTransitionalDifferent() || |
| 790 !aTLInfo.isTransitionalDifferent() || |
| 791 !uNLInfo.isTransitionalDifferent() || |
| 792 !uTLInfo.isTransitionalDifferent() |
| 793 ) { |
| 794 errln("%s.process([%d] %s) !isTransitionalDifferent()", |
| 795 testCase.o, (int)i, testCase.s); |
| 796 continue; |
| 797 } |
| 798 if(aN==aT || uN==uT || aNL==aTL || uNL==uTL) { |
| 799 errln("N.process([%d] %s) vs. T.process() same result strings", |
| 800 (int)i, testCase.s); |
| 801 continue; |
| 802 } |
| 803 } |
| 804 // UTF-8 if we have std::string |
| 805 #if U_HAVE_STD_STRING |
| 806 U_STD_NSQ string input8, aT8, uT8, aN8, uN8; |
| 807 StringByteSink<U_STD_NSQ string> aT8Sink(&aT8), uT8Sink(&uT8), aN8Sink(&
aN8), uN8Sink(&uN8); |
| 808 IDNAInfo aT8Info, uT8Info, aN8Info, uN8Info; |
| 809 input.toUTF8String(input8); |
| 810 trans->nameToASCII_UTF8(input8, aT8Sink, aT8Info, errorCode); |
| 811 trans->nameToUnicodeUTF8(input8, uT8Sink, uT8Info, errorCode); |
| 812 nontrans->nameToASCII_UTF8(input8, aN8Sink, aN8Info, errorCode); |
| 813 nontrans->nameToUnicodeUTF8(input8, uN8Sink, uN8Info, errorCode); |
| 814 if(errorCode.logIfFailureAndReset("UTF-8 processing [%d/%s] %s", |
| 815 (int)i, testCase.o, testCase.s) |
| 816 ) { |
| 817 continue; |
| 818 } |
| 819 UnicodeString aT16(UnicodeString::fromUTF8(aT8)); |
| 820 UnicodeString uT16(UnicodeString::fromUTF8(uT8)); |
| 821 UnicodeString aN16(UnicodeString::fromUTF8(aN8)); |
| 822 UnicodeString uN16(UnicodeString::fromUTF8(uN8)); |
| 823 if( aN8Info.getErrors()!=aNInfo.getErrors() || |
| 824 uN8Info.getErrors()!=uNInfo.getErrors() |
| 825 ) { |
| 826 errln("N.xyzUTF8([%d] %s) vs. UTF-16 processing different errors %04
lx vs. %04lx", |
| 827 (int)i, testCase.s, |
| 828 (long)aN8Info.getErrors(), (long)aNInfo.getErrors()); |
| 829 continue; |
| 830 } |
| 831 if( aT8Info.getErrors()!=aTInfo.getErrors() || |
| 832 uT8Info.getErrors()!=uTInfo.getErrors() |
| 833 ) { |
| 834 errln("T.xyzUTF8([%d] %s) vs. UTF-16 processing different errors %04
lx vs. %04lx", |
| 835 (int)i, testCase.s, |
| 836 (long)aT8Info.getErrors(), (long)aTInfo.getErrors()); |
| 837 continue; |
| 838 } |
| 839 if(aT16!=aT || uT16!=uT || aN16!=aN || uN16!=uN) { |
| 840 errln("%s.xyzUTF8([%d] %s) vs. UTF-16 processing different string re
sults", |
| 841 testCase.o, (int)i, testCase.s, (long)aTInfo.getErrors()); |
| 842 continue; |
| 843 } |
| 844 if( aT8Info.isTransitionalDifferent()!=aTInfo.isTransitionalDifferent()
|| |
| 845 uT8Info.isTransitionalDifferent()!=uTInfo.isTransitionalDifferent()
|| |
| 846 aN8Info.isTransitionalDifferent()!=aNInfo.isTransitionalDifferent()
|| |
| 847 uN8Info.isTransitionalDifferent()!=uNInfo.isTransitionalDifferent() |
| 848 ) { |
| 849 errln("%s.xyzUTF8([%d] %s) vs. UTF-16 processing different isTransit
ionalDifferent()", |
| 850 testCase.o, (int)i, testCase.s); |
| 851 continue; |
| 852 } |
| 853 #endif |
| 854 } |
| 855 } |
| 856 |
| 857 #endif // UCONFIG_NO_IDNA |
| OLD | NEW |
|---|
Chromium Code Reviews
Issue 5516007:
Check in the pristine copy of ICU 4.6... (Closed)
Base URL: svn://chrome-svn/chrome/trunk/deps/third_party/