lib/Unicode/UCD.t

   1 #!perl -w
   2 BEGIN {
   3     if (ord("A") != 65) {
   4         print "1..0 # Skip: EBCDIC\n";
   5         exit 0;
   6     }
   7     chdir 't' if -d 't';
   8     @INC = '../lib';
   9     @INC = "::lib" if $^O eq 'MacOS'; # module parses @INC itself
  10     require Config; import Config;
  11     if ($Config{'extensions'} !~ /\bStorable\b/) {
  12         print "1..0 # Skip: Storable was not built; Unicode::UCD uses Storable\n";
  13         exit 0;
  14     }
  15 }
  16
  17 use strict;
  18 use Unicode::UCD;
  19 use Test::More;
  20
  21 BEGIN { plan tests => 256 };
  22
  23 use Unicode::UCD 'charinfo';
  24
  25 my $charinfo;
  26
  27 $charinfo = charinfo(0);    # Null is often problematic, so test it.
  28
  29 is($charinfo->{code},           '0000', '<control>');
  30 is($charinfo->{name},           '<control>');
  31 is($charinfo->{category},       'Cc');
  32 is($charinfo->{combining},      '0');
  33 is($charinfo->{bidi},           'BN');
  34 is($charinfo->{decomposition},  '');
  35 is($charinfo->{decimal},        '');
  36 is($charinfo->{digit},          '');
  37 is($charinfo->{numeric},        '');
  38 is($charinfo->{mirrored},       'N');
  39 is($charinfo->{unicode10},      'NULL');
  40 is($charinfo->{comment},        '');
  41 is($charinfo->{upper},          '');
  42 is($charinfo->{lower},          '');
  43 is($charinfo->{title},          '');
  44 is($charinfo->{block},          'Basic Latin');
  45 is($charinfo->{script},         'Common');
  46
  47 $charinfo = charinfo(0x41);
  48
  49 is($charinfo->{code},           '0041', 'LATIN CAPITAL LETTER A');
  50 is($charinfo->{name},           'LATIN CAPITAL LETTER A');
  51 is($charinfo->{category},       'Lu');
  52 is($charinfo->{combining},      '0');
  53 is($charinfo->{bidi},           'L');
  54 is($charinfo->{decomposition},  '');
  55 is($charinfo->{decimal},        '');
  56 is($charinfo->{digit},          '');
  57 is($charinfo->{numeric},        '');
  58 is($charinfo->{mirrored},       'N');
  59 is($charinfo->{unicode10},      '');
  60 is($charinfo->{comment},        '');
  61 is($charinfo->{upper},          '');
  62 is($charinfo->{lower},          '0061');
  63 is($charinfo->{title},          '');
  64 is($charinfo->{block},          'Basic Latin');
  65 is($charinfo->{script},         'Latin');
  66
  67 $charinfo = charinfo(0x100);
  68
  69 is($charinfo->{code},           '0100', 'LATIN CAPITAL LETTER A WITH MACRON');
  70 is($charinfo->{name},           'LATIN CAPITAL LETTER A WITH MACRON');
  71 is($charinfo->{category},       'Lu');
  72 is($charinfo->{combining},      '0');
  73 is($charinfo->{bidi},           'L');
  74 is($charinfo->{decomposition},  '0041 0304');
  75 is($charinfo->{decimal},        '');
  76 is($charinfo->{digit},          '');
  77 is($charinfo->{numeric},        '');
  78 is($charinfo->{mirrored},       'N');
  79 is($charinfo->{unicode10},      'LATIN CAPITAL LETTER A MACRON');
  80 is($charinfo->{comment},        '');
  81 is($charinfo->{upper},          '');
  82 is($charinfo->{lower},          '0101');
  83 is($charinfo->{title},          '');
  84 is($charinfo->{block},          'Latin Extended-A');
  85 is($charinfo->{script},         'Latin');
  86
  87 # 0x0590 is in the Hebrew block but unused.
  88
  89 $charinfo = charinfo(0x590);
  90
  91 is($charinfo->{code},          undef,   '0x0590 - unused Hebrew');
  92 is($charinfo->{name},          undef);
  93 is($charinfo->{category},      undef);
  94 is($charinfo->{combining},     undef);
  95 is($charinfo->{bidi},          undef);
  96 is($charinfo->{decomposition}, undef);
  97 is($charinfo->{decimal},       undef);
  98 is($charinfo->{digit},         undef);
  99 is($charinfo->{numeric},       undef);
 100 is($charinfo->{mirrored},      undef);
 101 is($charinfo->{unicode10},     undef);
 102 is($charinfo->{comment},       undef);
 103 is($charinfo->{upper},         undef);
 104 is($charinfo->{lower},         undef);
 105 is($charinfo->{title},         undef);
 106 is($charinfo->{block},         undef);
 107 is($charinfo->{script},        undef);
 108
 109 # 0x05d0 is in the Hebrew block and used.
 110
 111 $charinfo = charinfo(0x5d0);
 112
 113 is($charinfo->{code},           '05D0', '05D0 - used Hebrew');
 114 is($charinfo->{name},           'HEBREW LETTER ALEF');
 115 is($charinfo->{category},       'Lo');
 116 is($charinfo->{combining},      '0');
 117 is($charinfo->{bidi},           'R');
 118 is($charinfo->{decomposition},  '');
 119 is($charinfo->{decimal},        '');
 120 is($charinfo->{digit},          '');
 121 is($charinfo->{numeric},        '');
 122 is($charinfo->{mirrored},       'N');
 123 is($charinfo->{unicode10},      '');
 124 is($charinfo->{comment},        '');
 125 is($charinfo->{upper},          '');
 126 is($charinfo->{lower},          '');
 127 is($charinfo->{title},          '');
 128 is($charinfo->{block},          'Hebrew');
 129 is($charinfo->{script},         'Hebrew');
 130
 131 # An open syllable in Hangul.
 132
 133 $charinfo = charinfo(0xAC00);
 134
 135 is($charinfo->{code},           'AC00', 'HANGUL SYLLABLE-AC00');
 136 is($charinfo->{name},           'HANGUL SYLLABLE-AC00');
 137 is($charinfo->{category},       'Lo');
 138 is($charinfo->{combining},      '0');
 139 is($charinfo->{bidi},           'L');
 140 is($charinfo->{decomposition},  undef);
 141 is($charinfo->{decimal},        '');
 142 is($charinfo->{digit},          '');
 143 is($charinfo->{numeric},        '');
 144 is($charinfo->{mirrored},       'N');
 145 is($charinfo->{unicode10},      '');
 146 is($charinfo->{comment},        '');
 147 is($charinfo->{upper},          '');
 148 is($charinfo->{lower},          '');
 149 is($charinfo->{title},          '');
 150 is($charinfo->{block},          'Hangul Syllables');
 151 is($charinfo->{script},         'Hangul');
 152
 153 # A closed syllable in Hangul.
 154
 155 $charinfo = charinfo(0xAE00);
 156
 157 is($charinfo->{code},           'AE00', 'HANGUL SYLLABLE-AE00');
 158 is($charinfo->{name},           'HANGUL SYLLABLE-AE00');
 159 is($charinfo->{category},       'Lo');
 160 is($charinfo->{combining},      '0');
 161 is($charinfo->{bidi},           'L');
 162 is($charinfo->{decomposition},  undef);
 163 is($charinfo->{decimal},        '');
 164 is($charinfo->{digit},          '');
 165 is($charinfo->{numeric},        '');
 166 is($charinfo->{mirrored},       'N');
 167 is($charinfo->{unicode10},      '');
 168 is($charinfo->{comment},        '');
 169 is($charinfo->{upper},          '');
 170 is($charinfo->{lower},          '');
 171 is($charinfo->{title},          '');
 172 is($charinfo->{block},          'Hangul Syllables');
 173 is($charinfo->{script},         'Hangul');
 174
 175 $charinfo = charinfo(0x1D400);
 176
 177 is($charinfo->{code},           '1D400', 'MATHEMATICAL BOLD CAPITAL A');
 178 is($charinfo->{name},           'MATHEMATICAL BOLD CAPITAL A');
 179 is($charinfo->{category},       'Lu');
 180 is($charinfo->{combining},      '0');
 181 is($charinfo->{bidi},           'L');
 182 is($charinfo->{decomposition},  '<font> 0041');
 183 is($charinfo->{decimal},        '');
 184 is($charinfo->{digit},          '');
 185 is($charinfo->{numeric},        '');
 186 is($charinfo->{mirrored},       'N');
 187 is($charinfo->{unicode10},      '');
 188 is($charinfo->{comment},        '');
 189 is($charinfo->{upper},          '');
 190 is($charinfo->{lower},          '');
 191 is($charinfo->{title},          '');
 192 is($charinfo->{block},          'Mathematical Alphanumeric Symbols');
 193 is($charinfo->{script},         'Common');
 194
 195 $charinfo = charinfo(0x9FBA);   #Bug 58428
 196
 197 is($charinfo->{code},           '9FBA', 'U+9FBA');
 198 is($charinfo->{name},           'CJK UNIFIED IDEOGRAPH-9FBA');
 199 is($charinfo->{category},       'Lo');
 200 is($charinfo->{combining},      '0');
 201 is($charinfo->{bidi},           'L');
 202 is($charinfo->{decomposition},  '');
 203 is($charinfo->{decimal},        '');
 204 is($charinfo->{digit},          '');
 205 is($charinfo->{numeric},        '');
 206 is($charinfo->{mirrored},       'N');
 207 is($charinfo->{unicode10},      '');
 208 is($charinfo->{comment},        '');
 209 is($charinfo->{upper},          '');
 210 is($charinfo->{lower},          '');
 211 is($charinfo->{title},          '');
 212 is($charinfo->{block},          'CJK Unified Ideographs');
 213 is($charinfo->{script},         'Han');
 214
 215 use Unicode::UCD qw(charblock charscript);
 216
 217 # 0x0590 is in the Hebrew block but unused.
 218
 219 is(charblock(0x590),          'Hebrew', '0x0590 - Hebrew unused charblock');
 220 is(charscript(0x590),         undef,    '0x0590 - Hebrew unused charscript');
 221
 222 $charinfo = charinfo(0xbe);
 223
 224 is($charinfo->{code},           '00BE', 'VULGAR FRACTION THREE QUARTERS');
 225 is($charinfo->{name},           'VULGAR FRACTION THREE QUARTERS');
 226 is($charinfo->{category},       'No');
 227 is($charinfo->{combining},      '0');
 228 is($charinfo->{bidi},           'ON');
 229 is($charinfo->{decomposition},  '<fraction> 0033 2044 0034');
 230 is($charinfo->{decimal},        '');
 231 is($charinfo->{digit},          '');
 232 is($charinfo->{numeric},        '3/4');
 233 is($charinfo->{mirrored},       'N');
 234 is($charinfo->{unicode10},      'FRACTION THREE QUARTERS');
 235 is($charinfo->{comment},        '');
 236 is($charinfo->{upper},          '');
 237 is($charinfo->{lower},          '');
 238 is($charinfo->{title},          '');
 239 is($charinfo->{block},          'Latin-1 Supplement');
 240 is($charinfo->{script},         'Common');
 241
 242 use Unicode::UCD qw(charblocks charscripts);
 243
 244 my $charblocks = charblocks();
 245
 246 ok(exists $charblocks->{Thai}, 'Thai charblock exists');
 247 is($charblocks->{Thai}->[0]->[0], hex('0e00'));
 248 ok(!exists $charblocks->{PigLatin}, 'PigLatin charblock does not exist');
 249
 250 my $charscripts = charscripts();
 251
 252 ok(exists $charscripts->{Armenian}, 'Armenian charscript exists');
 253 is($charscripts->{Armenian}->[0]->[0], hex('0531'));
 254 ok(!exists $charscripts->{PigLatin}, 'PigLatin charscript does not exist');
 255
 256 my $charscript;
 257
 258 $charscript = charscript("12ab");
 259 is($charscript, 'Ethiopic', 'Ethiopic charscript');
 260
 261 $charscript = charscript("0x12ab");
 262 is($charscript, 'Ethiopic');
 263
 264 $charscript = charscript("U+12ab");
 265 is($charscript, 'Ethiopic');
 266
 267 my $ranges;
 268
 269 $ranges = charscript('Ogham');
 270 is($ranges->[1]->[0], hex('1681'), 'Ogham charscript');
 271 is($ranges->[1]->[1], hex('169a'));
 272
 273 use Unicode::UCD qw(charinrange);
 274
 275 $ranges = charscript('Cherokee');
 276 ok(!charinrange($ranges, "139f"), 'Cherokee charscript');
 277 ok( charinrange($ranges, "13a0"));
 278 ok( charinrange($ranges, "13f4"));
 279 ok(!charinrange($ranges, "13f5"));
 280
 281 use Unicode::UCD qw(general_categories);
 282
 283 my $gc = general_categories();
 284
 285 ok(exists $gc->{L}, 'has L');
 286 is($gc->{L}, 'Letter', 'L is Letter');
 287 is($gc->{Lu}, 'UppercaseLetter', 'Lu is UppercaseLetter');
 288
 289 use Unicode::UCD qw(bidi_types);
 290
 291 my $bt = bidi_types();
 292
 293 ok(exists $bt->{L}, 'has L');
 294 is($bt->{L}, 'Left-to-Right', 'L is Left-to-Right');
 295 is($bt->{AL}, 'Right-to-Left Arabic', 'AL is Right-to-Left Arabic');
 296
 297 # If this fails, then maybe one should look at the Unicode changes to see
 298 # what else might need to be updated.
 299 is(Unicode::UCD::UnicodeVersion, '6.0.0', 'UnicodeVersion');
 300
 301 use Unicode::UCD qw(compexcl);
 302
 303 ok(!compexcl(0x0100), 'compexcl');
 304 ok(!compexcl(0xD801), 'compexcl of surrogate');
 305 ok(!compexcl(0x110000), 'compexcl of non-Unicode code point');
 306 ok( compexcl(0x0958));
 307
 308 use Unicode::UCD qw(casefold);
 309
 310 my $casefold;
 311
 312 $casefold = casefold(0x41);
 313
 314 is($casefold->{code}, '0041', 'casefold 0x41 code');
 315 is($casefold->{status}, 'C', 'casefold 0x41 status');
 316 is($casefold->{mapping}, '0061', 'casefold 0x41 mapping');
 317 is($casefold->{full}, '0061', 'casefold 0x41 full');
 318 is($casefold->{simple}, '0061', 'casefold 0x41 simple');
 319 is($casefold->{turkic}, "", 'casefold 0x41 turkic');
 320
 321 $casefold = casefold(0xdf);
 322
 323 is($casefold->{code}, '00DF', 'casefold 0xDF code');
 324 is($casefold->{status}, 'F', 'casefold 0xDF status');
 325 is($casefold->{mapping}, '0073 0073', 'casefold 0xDF mapping');
 326 is($casefold->{full}, '0073 0073', 'casefold 0xDF full');
 327 is($casefold->{simple}, "", 'casefold 0xDF simple');
 328 is($casefold->{turkic}, "", 'casefold 0xDF turkic');
 329
 330 # Do different tests depending on if version <= 3.1, or not.
 331 (my $version = Unicode::UCD::UnicodeVersion) =~ /^(\d+)\.(\d+)/;
 332 if (defined $1 && ($1 <= 2 || $1 == 3 && defined $2 && $2 <= 1)) {
 333         $casefold = casefold(0x130);
 334
 335         is($casefold->{code}, '0130', 'casefold 0x130 code');
 336         is($casefold->{status}, 'I' , 'casefold 0x130 status');
 337         is($casefold->{mapping}, '0069', 'casefold 0x130 mapping');
 338         is($casefold->{full}, '0069', 'casefold 0x130 full');
 339         is($casefold->{simple}, "0069", 'casefold 0x130 simple');
 340         is($casefold->{turkic}, "0069", 'casefold 0x130 turkic');
 341
 342         $casefold = casefold(0x131);
 343
 344         is($casefold->{code}, '0131', 'casefold 0x131 code');
 345         is($casefold->{status}, 'I' , 'casefold 0x131 status');
 346         is($casefold->{mapping}, '0069', 'casefold 0x131 mapping');
 347         is($casefold->{full}, '0069', 'casefold 0x131 full');
 348         is($casefold->{simple}, "0069", 'casefold 0x131 simple');
 349         is($casefold->{turkic}, "0069", 'casefold 0x131 turkic');
 350 } else {
 351         $casefold = casefold(0x49);
 352
 353         is($casefold->{code}, '0049', 'casefold 0x49 code');
 354         is($casefold->{status}, 'C' , 'casefold 0x49 status');
 355         is($casefold->{mapping}, '0069', 'casefold 0x49 mapping');
 356         is($casefold->{full}, '0069', 'casefold 0x49 full');
 357         is($casefold->{simple}, "0069", 'casefold 0x49 simple');
 358         is($casefold->{turkic}, "0131", 'casefold 0x49 turkic');
 359
 360         $casefold = casefold(0x130);
 361
 362         is($casefold->{code}, '0130', 'casefold 0x130 code');
 363         is($casefold->{status}, 'F' , 'casefold 0x130 status');
 364         is($casefold->{mapping}, '0069 0307', 'casefold 0x130 mapping');
 365         is($casefold->{full}, '0069 0307', 'casefold 0x130 full');
 366         is($casefold->{simple}, "", 'casefold 0x130 simple');
 367         is($casefold->{turkic}, "0069", 'casefold 0x130 turkic');
 368 }
 369
 370 $casefold = casefold(0x1F88);
 371
 372 is($casefold->{code}, '1F88', 'casefold 0x1F88 code');
 373 is($casefold->{status}, 'S' , 'casefold 0x1F88 status');
 374 is($casefold->{mapping}, '1F80', 'casefold 0x1F88 mapping');
 375 is($casefold->{full}, '1F00 03B9', 'casefold 0x1F88 full');
 376 is($casefold->{simple}, '1F80', 'casefold 0x1F88 simple');
 377 is($casefold->{turkic}, "", 'casefold 0x1F88 turkic');
 378
 379 ok(!casefold(0x20));
 380
 381 use Unicode::UCD qw(casespec);
 382
 383 my $casespec;
 384
 385 ok(!casespec(0x41));
 386
 387 $casespec = casespec(0xdf);
 388
 389 ok($casespec->{code} eq '00DF' &&
 390    $casespec->{lower} eq '00DF'  &&
 391    $casespec->{title} eq '0053 0073'  &&
 392    $casespec->{upper} eq '0053 0053' &&
 393    !defined $casespec->{condition}, 'casespec 0xDF');
 394
 395 $casespec = casespec(0x307);
 396
 397 ok($casespec->{az}->{code} eq '0307' &&
 398    !defined $casespec->{az}->{lower} &&
 399    $casespec->{az}->{title} eq '0307'  &&
 400    $casespec->{az}->{upper} eq '0307' &&
 401    $casespec->{az}->{condition} eq 'az After_I',
 402    'casespec 0x307');
 403
 404 # perl #7305 UnicodeCD::compexcl is weird
 405
 406 for (1) {my $a=compexcl $_}
 407 ok(1, 'compexcl read-only $_: perl #7305');
 408 map {compexcl $_} %{{1=>2}};
 409 ok(1, 'compexcl read-only hash: perl #7305');
 410
 411 is(Unicode::UCD::_getcode('123'),     123, "_getcode(123)");
 412 is(Unicode::UCD::_getcode('0123'),  0x123, "_getcode(0123)");
 413 is(Unicode::UCD::_getcode('0x123'), 0x123, "_getcode(0x123)");
 414 is(Unicode::UCD::_getcode('0X123'), 0x123, "_getcode(0X123)");
 415 is(Unicode::UCD::_getcode('U+123'), 0x123, "_getcode(U+123)");
 416 is(Unicode::UCD::_getcode('u+123'), 0x123, "_getcode(u+123)");
 417 is(Unicode::UCD::_getcode('U+1234'),   0x1234, "_getcode(U+1234)");
 418 is(Unicode::UCD::_getcode('U+12345'), 0x12345, "_getcode(U+12345)");
 419 is(Unicode::UCD::_getcode('123x'),    undef, "_getcode(123x)");
 420 is(Unicode::UCD::_getcode('x123'),    undef, "_getcode(x123)");
 421 is(Unicode::UCD::_getcode('0x123x'),  undef, "_getcode(x123)");
 422 is(Unicode::UCD::_getcode('U+123x'),  undef, "_getcode(x123)");
 423
 424 {
 425     my $r1 = charscript('Latin');
 426     my $n1 = @$r1;
 427     is($n1, 45, "number of ranges in Latin script (Unicode 6.0.0)");
 428     shift @$r1 while @$r1;
 429     my $r2 = charscript('Latin');
 430     is(@$r2, $n1, "modifying results should not mess up internal caches");
 431 }
 432
 433 {
 434         is(charinfo(0xdeadbeef), undef, "[perl #23273] warnings in Unicode::UCD");
 435 }
 436
 437 use Unicode::UCD qw(namedseq);
 438
 439 is(namedseq("KATAKANA LETTER AINU P"), "\x{31F7}\x{309A}", "namedseq");
 440 is(namedseq("KATAKANA LETTER AINU Q"), undef);
 441 is(namedseq(), undef);
 442 is(namedseq(qw(foo bar)), undef);
 443 my @ns = namedseq("KATAKANA LETTER AINU P");
 444 is(scalar @ns, 2);
 445 is($ns[0], 0x31F7);
 446 is($ns[1], 0x309A);
 447 my %ns = namedseq();
 448 is($ns{"KATAKANA LETTER AINU P"}, "\x{31F7}\x{309A}");
 449 @ns = namedseq(42);
 450 is(@ns, 0);
 451