icuSources/test/testdata/DataDrivenCollationTest.txt

   1 // Copyright (c) 2001-2004 International Business Machines
   2 // Corporation and others. All Rights Reserved.
   3 DataDrivenCollationTest {
   4     Info {
   5         Headers { "sequence" }
   6         Description { "These are the data driven tests" }
   7         LongDescription {     "The following entries are separate tests containing test data for various locales."
   8                       "Each entry has the following fields: "
   9                       "Info/Description - short descrioption of the test"
  10                       "Settings - settings for the test."
  11                       "Settings/TestLocale - locale for the collator OR"
  12                       "Settings/Rules - rules for the collator (can't have both)"
  13                       "Settings/Arguments - arguments to be passed to the collator before testing. Use rule syntax."
  14                       "Cases - set of test cases, which are sequences of strings that will be parsed"
  15                       "Sequences must not change the sign of relation, i.e. we can only have < and = or"
  16                       "> and = in single sequence. Cannot mix < and > in the same sequence. Whitespace is"
  17                       "is ignored unless quoted."
  18                      }
  19     }
  20     TestData {
  21         TestLithuanian {
  22             Info {
  23                 Description { "Lithuanian sort order." }
  24             }
  25             Settings {
  26                 {
  27                     TestLocale { "lt" }
  28                 }
  29             }
  30             Cases { "cz<č<d<iz<y<j<sz<š<t<zz<ž" }
  31         }
  32         TestLatvian {
  33             Info {
  34                 Description { "Latvian sort order." }
  35             }
  36             Settings {
  37                 {
  38                     TestLocale { "lv" }
  39                 }
  40             }
  41             Cases { "cz<č<d<gz<ģ<h<iz<y<j<kz<ķ<l<lz<ļ<m<nz<ņ<o<rz<ŗ<s<sz<š<t<zz<ž" }
  42         }
  43         TestEstonian {
  44             Info {
  45                 Description { "Estonian sort order." }
  46             }
  47             Settings {
  48                 {
  49                     TestLocale { "et" }
  50                 }
  51             }
  52             Cases { "sy<š<šy<z<zy<ž<v<w<va<õ<õy<ä<äy<ö<öy<ü<üy<x" }
  53         }
  54         TestAlbanian {
  55             Info {
  56                 Description { "Albanian sort order." }
  57             }
  58             Settings {
  59                 {
  60                     TestLocale { "sq" }
  61                 }
  62             }
  63             Cases { "cz<ç<d<dz<dh<e<ez<ë<f<gz<gj<h<lz<ll<m<nz<nj<o<rz<rr<s<sz<sh<t<tz<th<u<xz<xh<y<zz<zh" }
  64          }
  65
  66          TestSimplifiedChineseOrder {
  67             Info {
  68                 Description { "Sorted file has different order." }
  69             }
  70             Settings {
  71                 {
  72                     TestLocale { "root" }
  73                     Arguments { "[normalization on]" }
  74                 }
  75             }
  76
  77             Cases { "\u5F20<\u5F20\u4E00\u8E3F"  }
  78         }
  79
  80         TestTibetanNormalizedIterativeCrash {
  81             Info {
  82                 Description { "This pretty much crashes." }
  83             }
  84             Settings {
  85                 {
  86                     TestLocale { "root" }
  87                 }
  88             }
  89
  90             Cases { "\u0f71\u0f72\u0f80\u0f71\u0f72"
  91                     "<\u0f80"
  92             }
  93         }
  94         TestThaiPartialSortKeyProblems {
  95             Info {
  96                 Description { "These are examples of strings that caused trouble in partial sort key testing." }
  97             }
  98             Settings {
  99                 {
 100                     TestLocale { "th_TH" }
 101                 }
 102             }
 103             // TODO: the tests that are commented out should be enabled when j2720 is fixed
 104             Cases { "\u0E01\u0E01\u0E38\u0E18\u0E20\u0E31\u0E13\u0E11\u0E4C"
 105                     "<\u0E01\u0E01\u0E38\u0E2A\u0E31\u0E19\u0E42\u0E18",
 106                     "\u0E01\u0E07\u0E01\u0E32\u0E23"
 107                     "<\u0E01\u0E07\u0E42\u0E01\u0E49",
 108                     "\u0E01\u0E23\u0E19\u0E17\u0E32"
 109                     "<\u0E01\u0E23\u0E19\u0E19\u0E40\u0E0A\u0E49\u0E32",
 110                     "\u0E01\u0E23\u0E30\u0E40\u0E08\u0E35\u0E22\u0E27"
 111                     "<\u0E01\u0E23\u0E30\u0E40\u0E08\u0E35\u0E4A\u0E22\u0E27",
 112                     "\u0E01\u0E23\u0E23\u0E40\u0E0A\u0E2D"
 113                     "<\u0E01\u0E23\u0E23\u0E40\u0E0A\u0E49\u0E32"
 114           }
 115         }
 116         TestJavaStyleRule {
 117             Info {
 118                 Description { "java.text allows rules to start as '<<<x<<<y...' "
 119                               "we emulate this by assuming a &[first tertiary ignorable] "
 120                               "in this case."
 121                 }
 122             }
 123             Settings {
 124                 {
 125                     Rules { "=equal<<<z<<x<<<w<y &[first tertiary ignorable]=a &[first primary ignorable]=b" }
 126                 }
 127             }
 128             Cases { "a = equal < z < x < w < b < y" }
 129         }
 130         TestShiftedIgnorable {
 131             Info {
 132                 Description { "New UCA states that primary ignorables should be completely "
 133                               "ignorable when following a shifted code point."
 134                             }
 135             }
 136             Settings {
 137                 {
 138                     TestLocale { "root" }
 139                     Arguments { "[alternate shifted][strength 4]" }
 140                 }
 141             }
 142             Cases {
 143                 "a' 'b="
 144                 "a' '\u0300b="
 145                 "a' '\u0301b<"
 146                 "a_b="
 147                 "a_\u0300b="
 148                 "a_\u0301b<"
 149                 "A' 'b="
 150                 "A' '\u0300b="
 151                 "A' '\u0301b<"
 152                 "A_b="
 153                 "A_\u0300b="
 154                 "A_\u0301b<"
 155                 "a\u0301b<"
 156                 "A\u0301b<"
 157                 "a\u0300b<"
 158                 "A\u0300b"
 159
 160             }
 161         }
 162
 163         TestNShiftedIgnorable {
 164             Info {
 165                 Description { "New UCA states that primary ignorables should be completely "
 166                               "ignorable when following a shifted code point."
 167                             }
 168             }
 169             Settings {
 170                 {
 171                     TestLocale { "root" }
 172                     Arguments { "[alternate non-ignorable][strength 3]" }
 173                 }
 174             }
 175             Cases {
 176                 "a' 'b<"
 177                 "A' 'b<"
 178                 "a' '\u0301b<"
 179                 "A' '\u0301b<"
 180                 "a' '\u0300b<"
 181                 "A' '\u0300b<"
 182                 "a_b<"
 183                 "A_b<"
 184                 "a_\u0301b<"
 185                 "A_\u0301b<"
 186                 "a_\u0300b<"
 187                 "A_\u0300b<"
 188                 "a\u0301b<"
 189                 "A\u0301b<"
 190                 "a\u0300b<"
 191                 "A\u0300b<"
 192             }
 193         }
 194
 195         TestSafeSurrogates {
 196             Info {
 197                 Description { "It turned out that surrogates were not skipped properly "
 198                               "when iterating backwards if they were in the middle of a "
 199                               "contraction. This test assures that this is fixed."
 200                             }
 201             }
 202             Settings {
 203                 {
 204                     Rules {
 205                                 "&a < x\ud800\udc00b"
 206                     }
 207                 }
 208             }
 209             Cases {
 210                 "a<x\ud800\udc00b"
 211             }
 212         }
 213
 214         TestCIgnorableContraction {
 215             Info {
 216                 Description { "Checks whether completely ignorable code points are "
 217                               "skipped in contractions."
 218                               }
 219             }
 220             Settings {
 221                 {
 222                     TestLocale { "sh" }
 223                 }
 224                 {
 225                     Rules {
 226                                 "& L < lj, Lj <<< LJ"
 227                                 "& N < nj, Nj <<< NJ "
 228                     }
 229                 }
 230             }
 231             Cases {
 232                 "njiva=n\ud834\udd65jiva=n\uD834\uDD79jiva=n\u0000\u0000\u0000jiva=n\u0000jiva=n\ud800jiva=n\ufffejiva",
 233                 "ljubav=l\u0000jubav=l\uD834\uDD79jubav=l\u0000\u0000\u0000jubav=l\ud800jubav=l\ufffejubav",
 234                 "Ljubav=L\u0000jubav=L\uD834\uDD79jubav=L\u0000\u0000\u0000jubav=L\ud800jubav=L\ufffejubav",
 235             }
 236         }
 237
 238
 239         TestCIgnorablePrefix {
 240             Info {
 241                 Description { "Checks whether completely ignorable code points are "
 242                               "skipped in prefix processing."
 243                               }
 244             }
 245             Settings {
 246                 {
 247                     TestLocale { "ja" }
 248                 }
 249             }
 250             Cases {
 251                "\u30A1\u30FC"
 252                "= \u30A1\uDB40\uDC30\u30FC"
 253                "= \u30A1\uD800\u30FC"
 254                "= \u30A1\uFFFE\u30FC"
 255                "= \u30A1\uD834\uDD79\u30FC"
 256                "= \u30A1\u0000\u0000\u0000\u30FC"
 257                "= \u30A1\u0000\u30FC"
 258                "= \u30A1\u30FC"
 259                "= \u30A1\u0000\u059a\u30FC"
 260                "= \u30A1\u30FC"
 261             }
 262         }
 263         da_TestPrimary {
 264             Info {
 265                 Description { "This test goes through primary strength cases" }
 266             }
 267             Settings {
 268                 {
 269                     TestLocale { "da" }
 270                     Arguments { "[strength 1]" }
 271                 }
 272             }
 273             Cases {
 274                 "Lvi<Lwi",
 275                 "L\u00e4vi<L\u00f6wi",
 276                 "L\u00fcbeck=Lybeck",
 277             }
 278         }
 279         da_TestTertiary {
 280             Info {
 281                 Description { "This test goes through tertiary strength cases" }
 282             }
 283             Settings {
 284                 {
 285                     TestLocale { "da" }
 286                     Arguments { "[strength 3]" }
 287                 }
 288             }
 289             Cases {
 290                 "Luc<luck",
 291                 "luck<L\u00fcbeck",
 292                 "L\u00fcbeck>lybeck",
 293                 "L\u00e4vi<L\u00f6we",
 294                 "L\u00f6ww<mast",
 295                 // constUCharCollationDanishTest::testBugs[][CollationDanishTest::MAX_TOKEN_LEN]="
 296                 "A/S<"
 297                 "ANDRE<"
 298                 "ANDR\u00c9<"
 299                 "ANDREAS<"
 300                 "AS<"
 301                 "CA<"
 302                 "\u00c7A<"
 303                 "CB<"
 304                 "\u00c7C<"
 305                 "D.S.B.<"
 306                 "DA<"
 307                 "\u00d0A<"
 308                 "DB<"
 309                 "\u00d0C<"
 310                 "DSB<"
 311                 "DSC<"
 312                 "EKSTRA_ARBEJDE<"
 313                 "EKSTRABUD0<"
 314                 "H\u00d8ST<"
 315                 "HAAG<"
 316                 "H\u00c5NDBOG<"
 317                 "HAANDV\u00c6RKSBANKEN<"
 318                 "Karl<"
 319                 "karl<"
 320                 "'NIELS J\u00d8RGEN'<"
 321                 "NIELS-J\u00d8RGEN<"
 322                 "NIELSEN<"
 323                 "'R\u00c9E, A'<"
 324                 "'REE, B'<"
 325                 "'R\u00c9E, L'<"
 326                 "'REE, V'<"
 327                 "'SCHYTT, B'<"
 328                 "'SCHYTT, H'<"
 329                 "'SCH\u00dcTT, H'<"
 330                 "'SCHYTT, L'<"
 331                 "'SCH\u00dcTT, M'<"
 332                 "SS<"
 333                 "\u00df<"
 334                 "SSA<"
 335                 "'STORE VILDMOSE'<"
 336                 "STOREK\u00c6R0<"
 337                 "'STORM PETERSEN'<"
 338                 "STORMLY<"
 339                 "THORVALD<"
 340                 "THORVARDUR<"
 341                 "\u00feORVAR\u00d0UR<"
 342                 "THYGESEN<"
 343                 "'VESTERG\u00c5RD, A'<"
 344                 "'VESTERGAARD, A'<"
 345                 "'VESTERG\u00c5RD, B'<"
 346                 "\u00c6BLE<"
 347                 "\u00c4BLE<"
 348                 "\u00d8BERG<"
 349                 "\u00d6BERG",
 350
 351                 // constUCharCollationDanishTest::testNTList[][CollationDanishTest::MAX_TOKEN_LEN]="
 352                 "andere<"
 353                 "chaque<"
 354                 "chemin<"
 355                 "cote<"
 356                 "cot\u00e9<"
 357                 "c\u00f4te<"
 358                 "c\u00f4t\u00e9<"
 359                 "\u010du\u010d\u0113t<"
 360                 "Czech<"
 361                 "hi\u0161a<"
 362                 "irdisch<"
 363                 "lie<"
 364                 "lire<"
 365                 "llama<"
 366                 "l\u00f5ug<"
 367                 "l\u00f2za<"
 368                 "lu\u010d<"
 369                 "luck<"
 370                 "L\u00fcbeck<"
 371                 "lye<"
 372                 "l\u00e4vi<"
 373                 "L\u00f6wen<"
 374                 "m\u00e0\u0161ta<"
 375                 "m\u00eer<"
 376                 "myndig<"
 377                 "M\u00e4nner<"
 378                 "m\u00f6chten<"
 379                 "pi\u00f1a<"
 380                 "pint<"
 381                 "pylon<"
 382                 "\u0161\u00e0ran<"
 383                 "savoir<"
 384                 "\u0160erb\u016bra<"
 385                 "Sietla<"
 386                 "\u015blub<"
 387                 "subtle<"
 388                 "symbol<"
 389                 "s\u00e4mtlich<"
 390                 "verkehrt<"
 391                 "vox<"
 392                 "v\u00e4ga<"
 393                 "waffle<"
 394                 "wood<"
 395                 "yen<"
 396                 "yuan<"
 397                 "yucca<"
 398                 "\u017eal<"
 399                 "\u017eena<"
 400                 "\u017den\u0113va<"
 401                 "zoo0<"
 402                 "Zviedrija<"
 403                 "Z\u00fcrich<"
 404                 "zysk0<"
 405                 "\u00e4ndere"
 406             }
 407         }
 408         hi_TestNewRules {
 409             Info {
 410                 Description { "This test goes through new rules and tests against old rules" }
 411             }
 412             Settings {
 413                 {
 414                     TestLocale { "hi" }
 415                 }
 416             }
 417             Cases {
 418                  "ॐ<।<॥<॰<०<१<२<३"
 419                  "<४<५<६<७<८<९<अ<आ"
 420                  "<इ<ई<उ<ऊ<ऋ<ॠ<ऌ<ॡ"
 421                  "<ऍ<ऎ<ए<ऐ<ऑ<ऒ<ओ<औ"
 422                  "<क<क़=क़<कँ<कं<कः<क॑<क॒"
 423                  "<क॓<क॔<कऽ<क्<का<कि<की<कु"
 424                  "<कू<कृ<कॄ<कॢ<कॣ<कॅ<कॆ<के"
 425                  "<कै<कॉ<कॊ<को<कौ<ख<ख़ =ख़<खँ<खं<खः"
 426                  "<ख॑<ख॒<ख॓<ख॔<खऽ<ख्<खा<खि"
 427                  "<खी<खु<खू<खृ<खॄ<खॢ<खॣ<खॅ"
 428                  "<खॆ<खे<खै<खॉ<खॊ<खो<खौ<ग"
 429                  "<ग़=ग़<गँ<गं<गः<ग॑<ग॒<ग॓<ग॔"
 430                  "<गऽ<ग्<गा<गि<गी<गु<गू<गृ"
 431                  "<गॄ<गॢ<गॣ<गॅ<गॆ<गे<गै<गॉ"
 432                  "<गॊ<गो<गौ<घ<ङ<च<छ<ज<ज़ =ज़<जँ<जं<जः"
 433                  "<ज॑<ज॒<ज॓<ज॔<जऽ<ज्<जा<जि"
 434                  "<जी<जु<जू<जृ<जॄ<जॢ<जॣ<जॅ"
 435                  "<जॆ<जे<जै<जॉ<जॊ<जो<जौ<झ"
 436                  "<ञ<ट<ठ<ड<ड़=ड़<डँ<डं<डः<ड॑<ड॒<ड॓<ड॔"
 437                  "<डऽ<ड्<डा<डि<डी<डु<डू<डृ"
 438                  "<डॄ<डॢ<डॣ<डॅ<डॆ<डे<डै<डॉ"
 439                  "<डॊ<डो<डौ<ढ<ढ़=ढ़<ढँ<ढं<ढः"
 440                  "<ढ॑<ढ॒<ढ॓<ढ॔<ढऽ<ढ्<ढा<ढि"
 441                  "<ढी<ढु<ढू<ढृ<ढॄ<ढॢ<ढॣ<ढॅ"
 442                  "<ढॆ<ढे<ढै<ढॉ<ढॊ<ढो<ढौ<ण"
 443                  "<त<थ<द<ध<न<ऩ =ऩ< नँ<नं< नः"
 444                  "<न॑<न॒<न॓<न॔<नऽ<न्<ना<नि"
 445                  "<नी<नु<नू<नृ<नॄ<नॢ<नॣ<नॅ"
 446                  "<नॆ<ने<नै<नॉ<नॊ<नो<नौ"
 447                  "<प<फ<फ़=फ़<फँ<फं<फः<फ॑<फ॒"
 448                  "<फ॓<फ॔<फऽ<फ्<फा<फि<फी<फु<फू<फृ"
 449                  "<फॄ<फॢ<फॣ<फॅ<फॆ<फे<फै<फॉ"
 450                  "<फॊ<फो<फौ<ब<भ<म<य<य़=य़ "
 451                  "<यँ<यं<यः<य॑<य॒<य॓<य॔"
 452                  "<यऽ<य्<या<यि<यी<यु<यू<यृ"
 453                  "<यॄ<यॢ<यॣ<यॅ<यॆ<ये<यै<यॉ"
 454                  "<यॊ<यो<यौ<र<ऱ=ऱ<रँ<रं<रः"
 455                  "<र॑<र॒<र॓<र॔<रऽ<र्<रा<रि"
 456                  "<री<रु<रू<रृ<रॄ<रॢ<रॣ<रॅ"
 457                  "<रॆ<रे<रै<रॉ<रॊ<रो<रौ"
 458                  "<ल<ळ<ऴ=ऴ<ळँ<ळं<ळः<ळ॑<ळ॒"
 459                  "<ळ॓<ळ॔<ळऽ<ळ्<ळा<ळि<ळी<ळु"
 460                  "<ळू<ळृ<ळॄ<ळॢ<ळॣ<ळॅ<ळॆ<ळे"
 461                  "<ळै<ळॉ<ळॊ<ळो<ळौ<व<श<ष<स<ह"
 462                  "<़<ँ<ं<ः<॑<॒<॓<॔<ऽ<्<ा<ि<ी"
 463                  "<ु<ू<ृ<ॄ<ॢ<ॣ<ॅ<ॆ"
 464                  "<े<ै<ॉ<ॊ<ो<ौ"
 465            }
 466         }
 467         fi_TestNewRules {
 468             Info {
 469                 Description { "This test goes through new rules and tests against old rules" }
 470             }
 471             Settings {
 472                 {
 473                     TestLocale { "fi" }
 474                 }
 475             }
 476             Cases {
 477                 "xa<xA<Xa<XA<xá<Xá<xax<xAx<xáx<xd<Xd<xð<xÐ<Xð<XÐ<xđ<xĐ<Xđ<XĐ<"
 478                 "xdx<xðx<xÐx<xđx<xĐx<xe<Xe<xex<xn<Xn<xŋ<xŊ<Xŋ<XŊ<xnx<xŋx<xŊx<"
 479                 "xo<Xo<xó<Xó<xox<xóx<xs<Xs<xß<Xß<xßx<xsx<xt<Xt<xþ<xÞ<Xþ<XÞ<xþx<"
 480                 "xÞx<xtx<xu<Xu<xú<Xú<xux<xúx<xv<Xv<xw<Xw<xvx<xwx<xy<Xy<xü<Xü<"
 481                 "xű<Xű<xyx<xüx<xűx<xz<Xz<xzx<xå<Xå<xåx<xä<Xä<xæ<xÆ<Xæ<XÆ<xäx<"
 482                 "xæx<xÆx<xö<Xö<xø<Xø<xő<Xő<xõ<Xõ<xœ<xŒ<Xœ<XŒ<xöx<xøx<xőx<xõx<xœx<xŒx"
 483             }
 484         }
 485         ro_TestNewRules {
 486             Info {
 487                 Description { "This test goes through new rules and tests against old rules" }
 488             }
 489             Settings {
 490                 {
 491                     TestLocale { "ro" }
 492                 }
 493             }
 494             Cases {
 495                 "xAx<xă<xĂ<Xă<XĂ<xăx<xĂx<xâ<xÂ<Xâ<XÂ<xâx<xÂx<xb<xIx<xî<xÎ<Xî<XÎ<xîx<xÎx<"
 496                 "xj<xSx<xș=xş<xȘ=xŞ<Xș=Xş<XȘ=XŞ<xșx=xşx<xȘx=xŞx<xT<xTx<xț=xţ<xȚ=xŢ<Xț=Xţ<XȚ"
 497                 "=XŢ<xțx=xţx<xȚx=xŢx<xU"
 498             }
 499         }
 500     }
 501 }