| 1 | |
| 2 | require 5; |
| 3 | package I18N::LangTags::List; |
| 4 | # Time-stamp: "2002-02-02 20:13:58 MST" |
| 5 | use strict; |
| 6 | use vars qw(%Name $Debug $VERSION); |
| 7 | $VERSION = '0.25'; |
| 8 | # POD at the end. |
| 9 | |
| 10 | #---------------------------------------------------------------------- |
| 11 | { |
| 12 | # read the table out of our own POD! |
| 13 | my $seeking = 1; |
| 14 | my $count = 0; |
| 15 | my($tag,$name); |
| 16 | while(<I18N::LangTags::List::DATA>) { |
| 17 | if($seeking) { |
| 18 | $seeking = 0 if m/=for woohah/; |
| 19 | } else { |
| 20 | next unless ($tag, $name) = |
| 21 | m/\{([-0-9a-zA-Z]+)\}(?:\s*:)?\s*([^\[\]]+)/; |
| 22 | $name =~ s/\s*[;\.]*\s*$//g; |
| 23 | next unless $name; |
| 24 | ++$count; |
| 25 | print "<$tag> <$name>\n" if $Debug; |
| 26 | $Name{$tag} = $name; |
| 27 | } |
| 28 | } |
| 29 | die "No tags read??" unless $count; |
| 30 | } |
| 31 | #---------------------------------------------------------------------- |
| 32 | |
| 33 | sub name { |
| 34 | my $tag = lc($_[0] || return); |
| 35 | $tag =~ s/^\s+//s; |
| 36 | $tag =~ s/\s+$//s; |
| 37 | |
| 38 | my $alt; |
| 39 | if($tag =~ m/^x-(.+)/) { |
| 40 | $alt = "i-$1"; |
| 41 | } elsif($tag =~ m/^i-(.+)/) { |
| 42 | $alt = "x-$1"; |
| 43 | } else { |
| 44 | $alt = ''; |
| 45 | } |
| 46 | |
| 47 | my $subform = ''; |
| 48 | my $name = ''; |
| 49 | print "Input: {$tag}\n" if $Debug; |
| 50 | while(length $tag) { |
| 51 | last if $name = $Name{$tag}; |
| 52 | last if $name = $Name{$alt}; |
| 53 | if($tag =~ s/(-[a-z0-9]+)$//s) { |
| 54 | print "Shaving off: $1 leaving $tag\n" if $Debug; |
| 55 | $subform = "$1$subform"; |
| 56 | # and loop around again |
| 57 | |
| 58 | $alt =~ s/(-[a-z0-9]+)$//s && $Debug && print " alt -> $alt\n"; |
| 59 | } else { |
| 60 | # we're trying to pull a subform off a primary tag. TILT! |
| 61 | print "Aborting on: {$name}{$subform}\n" if $Debug; |
| 62 | last; |
| 63 | } |
| 64 | } |
| 65 | print "Output: {$name}{$subform}\n" if $Debug; |
| 66 | |
| 67 | return unless $name; # Failure |
| 68 | return $name unless $subform; # Exact match |
| 69 | $subform =~ s/^-//s; |
| 70 | $subform =~ s/-$//s; |
| 71 | return "$name (Subform \"$subform\")"; |
| 72 | } |
| 73 | |
| 74 | 1; |
| 75 | |
| 76 | __DATA__ |
| 77 | |
| 78 | =head1 NAME |
| 79 | |
| 80 | I18N::LangTags::List -- tags and names for human languages |
| 81 | |
| 82 | =head1 SYNOPSIS |
| 83 | |
| 84 | use I18N::LangTags::List; |
| 85 | print "Parlez-vous... ", join(', ', |
| 86 | I18N::LangTags::List::name('elx') || 'unknown_language', |
| 87 | I18N::LangTags::List::name('ar-Kw') || 'unknown_language', |
| 88 | I18N::LangTags::List::name('en') || 'unknown_language', |
| 89 | I18N::LangTags::List::name('en-CA') || 'unknown_language', |
| 90 | ), "?\n"; |
| 91 | |
| 92 | prints: |
| 93 | |
| 94 | Parlez-vous... Elamite, Kuwait Arabic, English, Canadian English? |
| 95 | |
| 96 | =head1 DESCRIPTION |
| 97 | |
| 98 | This module provides a function |
| 99 | C<I18N::LangTags::List::name( I<langtag> ) > that takes |
| 100 | a language tag (see L<I18N::LangTags|I18N::LangTags>) |
| 101 | and returns the best attempt at an English name for it, or |
| 102 | undef if it can't make sense of the tag. |
| 103 | |
| 104 | The function I18N::LangTags::List::name(...) is not exported. |
| 105 | |
| 106 | The map of tags-to-names that it uses is accessable as |
| 107 | %I18N::LangTags::List::Name, and it's the same as the list |
| 108 | that follows in this documentation, which should be useful |
| 109 | to you even if you don't use this module. |
| 110 | |
| 111 | =head1 ABOUT LANGUAGE TAGS |
| 112 | |
| 113 | Internet language tags, as defined in RFC 3066, are a formalism |
| 114 | for denoting human languages. The two-letter ISO 639-1 language |
| 115 | codes are well known (as "en" for English), as are their forms |
| 116 | when qualified by a country code ("en-US"). Less well-known are the |
| 117 | arbitrary-length non-ISO codes (like "i-mingo"), and the |
| 118 | recently (in 2001) introduced three-letter ISO-639-2 codes. |
| 119 | |
| 120 | Remember these important facts: |
| 121 | |
| 122 | =over |
| 123 | |
| 124 | =item * |
| 125 | |
| 126 | Language tags are not locale IDs. A locale ID is written with a "_" |
| 127 | instead of a "-", (almost?) always matches C<m/^\w\w_\w\w\b/>, and |
| 128 | I<means> something different than a language tag. A language tag |
| 129 | denotes a language. A locale ID denotes a language I<as used in> |
| 130 | a particular place, in combination with non-linguistic |
| 131 | location-specific information such as what currency is used |
| 132 | there. Locales I<also> often denote character set information, |
| 133 | as in "en_US.ISO8859-1". |
| 134 | |
| 135 | =item * |
| 136 | |
| 137 | Language tags are not for computer languages. |
| 138 | |
| 139 | =item * |
| 140 | |
| 141 | "Dialect" is not a useful term, since there is no objective |
| 142 | criterion for establishing when two language-forms are |
| 143 | dialects of eachother, or are separate languages. |
| 144 | |
| 145 | =item * |
| 146 | |
| 147 | Language tags are not case-sensitive. en-US, en-us, En-Us, etc., |
| 148 | are all the same tag, and denote the same language. |
| 149 | |
| 150 | =item * |
| 151 | |
| 152 | Not every language tag really refers to a single language. Some |
| 153 | language tags refer to conditions: i-default (system-message text |
| 154 | in English plus maybe other languages), und (undetermined |
| 155 | language). Others (notably lots of the three-letter codes) are |
| 156 | bibliographic tags that classify whole groups of languages, as |
| 157 | with cus "Cushitic (Other)" (i.e., a |
| 158 | language that has been classed as Cushtic, but which has no more |
| 159 | specific code) or the even less linguistically coherent |
| 160 | sai for "South American Indian (Other)". Though useful in |
| 161 | bibliography, B<SUCH TAGS ARE NOT |
| 162 | FOR GENERAL USE>. For further guidance, email me. |
| 163 | |
| 164 | =item * |
| 165 | |
| 166 | Language tags are not country codes. In fact, they are often |
| 167 | distinct codes, as with language tag ja for Japanese, and |
| 168 | ISO 3166 country code C<.jp> for Japan. |
| 169 | |
| 170 | =back |
| 171 | |
| 172 | =head1 LIST OF LANGUAGES |
| 173 | |
| 174 | The first part of each item is the language tag, between |
| 175 | {...}. It |
| 176 | is followed by an English name for the language or language-group. |
| 177 | Language tags that I judge to be not for general use, are bracketed. |
| 178 | |
| 179 | This list is in alphabetical order by English name of the language. |
| 180 | |
| 181 | =for reminder |
| 182 | The name in the =item line MUST NOT have E<...>'s in it!! |
| 183 | |
| 184 | =for woohah START |
| 185 | |
| 186 | =over |
| 187 | |
| 188 | =item {ab} : Abkhazian |
| 189 | |
| 190 | eq Abkhaz |
| 191 | |
| 192 | =item {ace} : Achinese |
| 193 | |
| 194 | =item {ach} : Acoli |
| 195 | |
| 196 | =item {ada} : Adangme |
| 197 | |
| 198 | =item {aa} : Afar |
| 199 | |
| 200 | =item {afh} : Afrihili |
| 201 | |
| 202 | (Artificial) |
| 203 | |
| 204 | =item {af} : Afrikaans |
| 205 | |
| 206 | =item [{afa} : Afro-Asiatic (Other)] |
| 207 | |
| 208 | =item {aka} : Akan |
| 209 | |
| 210 | =item {akk} : Akkadian |
| 211 | |
| 212 | (Historical) |
| 213 | |
| 214 | =item {sq} : Albanian |
| 215 | |
| 216 | =item {ale} : Aleut |
| 217 | |
| 218 | =item [{alg} : Algonquian languages] |
| 219 | |
| 220 | NOT Algonquin! |
| 221 | |
| 222 | =item [{tut} : Altaic (Other)] |
| 223 | |
| 224 | =item {am} : Amharic |
| 225 | |
| 226 | NOT Aramaic! |
| 227 | |
| 228 | =item {i-ami} : Ami |
| 229 | |
| 230 | eq Amis. eq 'Amis. eq Pangca. |
| 231 | |
| 232 | =item [{apa} : Apache languages] |
| 233 | |
| 234 | =item {ar} : Arabic |
| 235 | |
| 236 | Many forms are mutually un-intelligible in spoken media. |
| 237 | Notable forms: |
| 238 | {ar-ae} UAE Arabic; |
| 239 | {ar-bh} Bahrain Arabic; |
| 240 | {ar-dz} Algerian Arabic; |
| 241 | {ar-eg} Egyptian Arabic; |
| 242 | {ar-iq} Iraqi Arabic; |
| 243 | {ar-jo} Jordanian Arabic; |
| 244 | {ar-kw} Kuwait Arabic; |
| 245 | {ar-lb} Lebanese Arabic; |
| 246 | {ar-ly} Libyan Arabic; |
| 247 | {ar-ma} Moroccan Arabic; |
| 248 | {ar-om} Omani Arabic; |
| 249 | {ar-qa} Qatari Arabic; |
| 250 | {ar-sa} Sauda Arabic; |
| 251 | {ar-sy} Syrian Arabic; |
| 252 | {ar-tn} Tunisian Arabic; |
| 253 | {ar-ye} Yemen Arabic. |
| 254 | |
| 255 | =item {arc} : Aramaic |
| 256 | |
| 257 | NOT Amharic! NOT Samaritan Aramaic! |
| 258 | |
| 259 | =item {arp} : Arapaho |
| 260 | |
| 261 | =item {arn} : Araucanian |
| 262 | |
| 263 | =item {arw} : Arawak |
| 264 | |
| 265 | =item {hy} : Armenian |
| 266 | |
| 267 | =item [{art} : Artificial (Other)] |
| 268 | |
| 269 | =item {as} : Assamese |
| 270 | |
| 271 | =item [{ath} : Athapascan languages] |
| 272 | |
| 273 | eq Athabaskan. eq Athapaskan. eq Athabascan. |
| 274 | |
| 275 | =item [{aus} : Australian languages] |
| 276 | |
| 277 | =item [{map} : Austronesian (Other)] |
| 278 | |
| 279 | =item {ava} : Avaric |
| 280 | |
| 281 | =item {ae} : Avestan |
| 282 | |
| 283 | eq Zend |
| 284 | |
| 285 | =item {awa} : Awadhi |
| 286 | |
| 287 | =item {ay} : Aymara |
| 288 | |
| 289 | =item {az} : Azerbaijani |
| 290 | |
| 291 | eq Azeri |
| 292 | |
| 293 | =item {ban} : Balinese |
| 294 | |
| 295 | =item [{bat} : Baltic (Other)] |
| 296 | |
| 297 | =item {bal} : Baluchi |
| 298 | |
| 299 | =item {bam} : Bambara |
| 300 | |
| 301 | =item [{bai} : Bamileke languages] |
| 302 | |
| 303 | =item {bad} : Banda |
| 304 | |
| 305 | =item [{bnt} : Bantu (Other)] |
| 306 | |
| 307 | =item {bas} : Basa |
| 308 | |
| 309 | =item {ba} : Bashkir |
| 310 | |
| 311 | =item {eu} : Basque |
| 312 | |
| 313 | =item {btk} : Batak (Indonesia) |
| 314 | |
| 315 | =item {bej} : Beja |
| 316 | |
| 317 | =item {be} : Belarusian |
| 318 | |
| 319 | eq Belarussian. eq Byelarussian. |
| 320 | eq Belorussian. eq Byelorussian. |
| 321 | eq White Russian. eq White Ruthenian. |
| 322 | NOT Ruthenian! |
| 323 | |
| 324 | =item {bem} : Bemba |
| 325 | |
| 326 | =item {bn} : Bengali |
| 327 | |
| 328 | eq Bangla. |
| 329 | |
| 330 | =item [{ber} : Berber (Other)] |
| 331 | |
| 332 | =item {bho} : Bhojpuri |
| 333 | |
| 334 | =item {bh} : Bihari |
| 335 | |
| 336 | =item {bik} : Bikol |
| 337 | |
| 338 | =item {bin} : Bini |
| 339 | |
| 340 | =item {bi} : Bislama |
| 341 | |
| 342 | eq Bichelamar. |
| 343 | |
| 344 | =item {bs} : Bosnian |
| 345 | |
| 346 | =item {bra} : Braj |
| 347 | |
| 348 | =item {br} : Breton |
| 349 | |
| 350 | =item {bug} : Buginese |
| 351 | |
| 352 | =item {bg} : Bulgarian |
| 353 | |
| 354 | =item {i-bnn} : Bunun |
| 355 | |
| 356 | =item {bua} : Buriat |
| 357 | |
| 358 | =item {my} : Burmese |
| 359 | |
| 360 | =item {cad} : Caddo |
| 361 | |
| 362 | =item {car} : Carib |
| 363 | |
| 364 | =item {ca} : Catalan |
| 365 | |
| 366 | eq CatalE<aacute>n. eq Catalonian. |
| 367 | |
| 368 | =item [{cau} : Caucasian (Other)] |
| 369 | |
| 370 | =item {ceb} : Cebuano |
| 371 | |
| 372 | =item [{cel} : Celtic (Other)] |
| 373 | |
| 374 | Notable forms: |
| 375 | {cel-gaulish} Gaulish (Historical) |
| 376 | |
| 377 | =item [{cai} : Central American Indian (Other)] |
| 378 | |
| 379 | =item {chg} : Chagatai |
| 380 | |
| 381 | (Historical?) |
| 382 | |
| 383 | =item [{cmc} : Chamic languages] |
| 384 | |
| 385 | =item {ch} : Chamorro |
| 386 | |
| 387 | =item {ce} : Chechen |
| 388 | |
| 389 | =item {chr} : Cherokee |
| 390 | |
| 391 | eq Tsalagi |
| 392 | |
| 393 | =item {chy} : Cheyenne |
| 394 | |
| 395 | =item {chb} : Chibcha |
| 396 | |
| 397 | (Historical) NOT Chibchan (which is a language family). |
| 398 | |
| 399 | =item {ny} : Chichewa |
| 400 | |
| 401 | eq Nyanja. eq Chinyanja. |
| 402 | |
| 403 | =item {zh} : Chinese |
| 404 | |
| 405 | Many forms are mutually un-intelligible in spoken media. |
| 406 | Notable subforms: |
| 407 | {zh-cn} PRC Chinese; |
| 408 | {zh-hk} Hong Kong Chinese; |
| 409 | {zh-mo} Macau Chinese; |
| 410 | {zh-sg} Singapore Chinese; |
| 411 | {zh-tw} Taiwan Chinese; |
| 412 | {zh-guoyu} Mandarin [Putonghua/Guoyu]; |
| 413 | {zh-hakka} Hakka [formerly i-hakka]; |
| 414 | {zh-min} Hokkien; |
| 415 | {zh-min-nan} Southern Hokkien; |
| 416 | {zh-wuu} Shanghaiese; |
| 417 | {zh-xiang} Hunanese; |
| 418 | {zh-gan} Gan; |
| 419 | {zh-yue} Cantonese. |
| 420 | |
| 421 | =for etc |
| 422 | {i-hakka} Hakka (old tag) |
| 423 | |
| 424 | =item {chn} : Chinook Jargon |
| 425 | |
| 426 | eq Chinook Wawa. |
| 427 | |
| 428 | =item {chp} : Chipewyan |
| 429 | |
| 430 | =item {cho} : Choctaw |
| 431 | |
| 432 | =item {cu} : Church Slavic |
| 433 | |
| 434 | eq Old Church Slavonic. |
| 435 | |
| 436 | =item {chk} : Chuukese |
| 437 | |
| 438 | eq Trukese. eq Chuuk. eq Truk. eq Ruk. |
| 439 | |
| 440 | =item {cv} : Chuvash |
| 441 | |
| 442 | =item {cop} : Coptic |
| 443 | |
| 444 | =item {kw} : Cornish |
| 445 | |
| 446 | =item {co} : Corsican |
| 447 | |
| 448 | eq Corse. |
| 449 | |
| 450 | =item {cre} : Cree |
| 451 | |
| 452 | NOT Creek! |
| 453 | |
| 454 | =item {mus} : Creek |
| 455 | |
| 456 | NOT Cree! |
| 457 | |
| 458 | =item [{cpe} : English-based Creoles and pidgins (Other)] |
| 459 | |
| 460 | =item [{cpf} : French-based Creoles and pidgins (Other)] |
| 461 | |
| 462 | =item [{cpp} : Portuguese-based Creoles and pidgins (Other)] |
| 463 | |
| 464 | =item [{crp} : Creoles and pidgins (Other)] |
| 465 | |
| 466 | =item {hr} : Croatian |
| 467 | |
| 468 | eq Croat. |
| 469 | |
| 470 | =item [{cus} : Cushitic (Other)] |
| 471 | |
| 472 | =item {cs} : Czech |
| 473 | |
| 474 | =item {dak} : Dakota |
| 475 | |
| 476 | eq Nakota. eq Latoka. |
| 477 | |
| 478 | =item {da} : Danish |
| 479 | |
| 480 | =item {day} : Dayak |
| 481 | |
| 482 | =item {i-default} : Default (Fallthru) Language |
| 483 | |
| 484 | Defined in RFC 2277, this is for tagging text |
| 485 | (which must include English text, and might/should include text |
| 486 | in other appropriate languages) that is emitted in a context |
| 487 | where language-negotiation wasn't possible -- in SMTP mail failure |
| 488 | messages, for example. |
| 489 | |
| 490 | =item {del} : Delaware |
| 491 | |
| 492 | =item {din} : Dinka |
| 493 | |
| 494 | =item {div} : Divehi |
| 495 | |
| 496 | =item {doi} : Dogri |
| 497 | |
| 498 | NOT Dogrib! |
| 499 | |
| 500 | =item {dgr} : Dogrib |
| 501 | |
| 502 | NOT Dogri! |
| 503 | |
| 504 | =item [{dra} : Dravidian (Other)] |
| 505 | |
| 506 | =item {dua} : Duala |
| 507 | |
| 508 | =item {nl} : Dutch |
| 509 | |
| 510 | eq Netherlander. Notable forms: |
| 511 | {nl-nl} Netherlands Dutch; |
| 512 | {nl-be} Belgian Dutch. |
| 513 | |
| 514 | =item {dum} : Middle Dutch (ca.1050-1350) |
| 515 | |
| 516 | (Historical) |
| 517 | |
| 518 | =item {dyu} : Dyula |
| 519 | |
| 520 | =item {dz} : Dzongkha |
| 521 | |
| 522 | =item {efi} : Efik |
| 523 | |
| 524 | =item {egy} : Ancient Egyptian |
| 525 | |
| 526 | (Historical) |
| 527 | |
| 528 | =item {eka} : Ekajuk |
| 529 | |
| 530 | =item {elx} : Elamite |
| 531 | |
| 532 | (Historical) |
| 533 | |
| 534 | =item {en} : English |
| 535 | |
| 536 | Notable forms: |
| 537 | {en-au} Australian English; |
| 538 | {en-bz} Belize English; |
| 539 | {en-ca} Canadian English; |
| 540 | {en-gb} UK English; |
| 541 | {en-ie} Irish English; |
| 542 | {en-jm} Jamaican English; |
| 543 | {en-nz} New Zealand English; |
| 544 | {en-ph} Philippine English; |
| 545 | {en-tt} Trinidad English; |
| 546 | {en-us} US English; |
| 547 | {en-za} South African English; |
| 548 | {en-zw} Zimbabwe English. |
| 549 | |
| 550 | =item {enm} : Old English (1100-1500) |
| 551 | |
| 552 | (Historical) |
| 553 | |
| 554 | =item {ang} : Old English (ca.450-1100) |
| 555 | |
| 556 | eq Anglo-Saxon. (Historical) |
| 557 | |
| 558 | =item {eo} : Esperanto |
| 559 | |
| 560 | (Artificial) |
| 561 | |
| 562 | =item {et} : Estonian |
| 563 | |
| 564 | =item {ewe} : Ewe |
| 565 | |
| 566 | =item {ewo} : Ewondo |
| 567 | |
| 568 | =item {fan} : Fang |
| 569 | |
| 570 | =item {fat} : Fanti |
| 571 | |
| 572 | =item {fo} : Faroese |
| 573 | |
| 574 | =item {fj} : Fijian |
| 575 | |
| 576 | =item {fi} : Finnish |
| 577 | |
| 578 | =item [{fiu} : Finno-Ugrian (Other)] |
| 579 | |
| 580 | eq Finno-Ugric. NOT Ugaritic! |
| 581 | |
| 582 | =item {fon} : Fon |
| 583 | |
| 584 | =item {fr} : French |
| 585 | |
| 586 | Notable forms: |
| 587 | {fr-fr} France French; |
| 588 | {fr-be} Belgian French; |
| 589 | {fr-ca} Canadian French; |
| 590 | {fr-ch} Swiss French; |
| 591 | {fr-lu} Luxembourg French; |
| 592 | {fr-mc} Monaco French. |
| 593 | |
| 594 | =item {frm} : Middle French (ca.1400-1600) |
| 595 | |
| 596 | (Historical) |
| 597 | |
| 598 | =item {fro} : Old French (842-ca.1400) |
| 599 | |
| 600 | (Historical) |
| 601 | |
| 602 | =item {fy} : Frisian |
| 603 | |
| 604 | =item {fur} : Friulian |
| 605 | |
| 606 | =item {ful} : Fulah |
| 607 | |
| 608 | =item {gaa} : Ga |
| 609 | |
| 610 | =item {gd} : Scots Gaelic |
| 611 | |
| 612 | NOT Scots! |
| 613 | |
| 614 | =item {gl} : Gallegan |
| 615 | |
| 616 | eq Galician |
| 617 | |
| 618 | =item {lug} : Ganda |
| 619 | |
| 620 | =item {gay} : Gayo |
| 621 | |
| 622 | =item {gba} : Gbaya |
| 623 | |
| 624 | =item {gez} : Geez |
| 625 | |
| 626 | eq Ge'ez |
| 627 | |
| 628 | =item {ka} : Georgian |
| 629 | |
| 630 | =item {de} : German |
| 631 | |
| 632 | Notable forms: |
| 633 | {de-at} Austrian German; |
| 634 | {de-be} Belgian German; |
| 635 | {de-ch} Swiss German; |
| 636 | {de-de} Germany German; |
| 637 | {de-li} Liechtenstein German; |
| 638 | {de-lu} Luxembourg German. |
| 639 | |
| 640 | =item {gmh} : Middle High German (ca.1050-1500) |
| 641 | |
| 642 | (Historical) |
| 643 | |
| 644 | =item {goh} : Old High German (ca.750-1050) |
| 645 | |
| 646 | (Historical) |
| 647 | |
| 648 | =item [{gem} : Germanic (Other)] |
| 649 | |
| 650 | =item {gil} : Gilbertese |
| 651 | |
| 652 | =item {gon} : Gondi |
| 653 | |
| 654 | =item {gor} : Gorontalo |
| 655 | |
| 656 | =item {got} : Gothic |
| 657 | |
| 658 | (Historical) |
| 659 | |
| 660 | =item {grb} : Grebo |
| 661 | |
| 662 | =item {grc} : Ancient Greek |
| 663 | |
| 664 | (Historical) (Until 15th century or so.) |
| 665 | |
| 666 | =item {el} : Modern Greek |
| 667 | |
| 668 | (Since 15th century or so.) |
| 669 | |
| 670 | =item {gn} : Guarani |
| 671 | |
| 672 | GuaranE<iacute> |
| 673 | |
| 674 | =item {gu} : Gujarati |
| 675 | |
| 676 | =item {gwi} : Gwich'in |
| 677 | |
| 678 | eq Gwichin |
| 679 | |
| 680 | =item {hai} : Haida |
| 681 | |
| 682 | =item {ha} : Hausa |
| 683 | |
| 684 | =item {haw} : Hawaiian |
| 685 | |
| 686 | Hawai'ian |
| 687 | |
| 688 | =item {he} : Hebrew |
| 689 | |
| 690 | (Formerly "iw".) |
| 691 | |
| 692 | =for etc |
| 693 | {iw} Hebrew (old tag) |
| 694 | |
| 695 | =item {hz} : Herero |
| 696 | |
| 697 | =item {hil} : Hiligaynon |
| 698 | |
| 699 | =item {him} : Himachali |
| 700 | |
| 701 | =item {hi} : Hindi |
| 702 | |
| 703 | =item {ho} : Hiri Motu |
| 704 | |
| 705 | =item {hit} : Hittite |
| 706 | |
| 707 | (Historical) |
| 708 | |
| 709 | =item {hmn} : Hmong |
| 710 | |
| 711 | =item {hu} : Hungarian |
| 712 | |
| 713 | =item {hup} : Hupa |
| 714 | |
| 715 | =item {iba} : Iban |
| 716 | |
| 717 | =item {is} : Icelandic |
| 718 | |
| 719 | =item {ibo} : Igbo |
| 720 | |
| 721 | =item {ijo} : Ijo |
| 722 | |
| 723 | =item {ilo} : Iloko |
| 724 | |
| 725 | =item [{inc} : Indic (Other)] |
| 726 | |
| 727 | =item [{ine} : Indo-European (Other)] |
| 728 | |
| 729 | =item {id} : Indonesian |
| 730 | |
| 731 | (Formerly "in".) |
| 732 | |
| 733 | =for etc |
| 734 | {in} Indonesian (old tag) |
| 735 | |
| 736 | =item {ia} : Interlingua (International Auxiliary Language Association) |
| 737 | |
| 738 | (Artificial) NOT Interlingue! |
| 739 | |
| 740 | =item {ie} : Interlingue |
| 741 | |
| 742 | (Artificial) NOT Interlingua! |
| 743 | |
| 744 | =item {iu} : Inuktitut |
| 745 | |
| 746 | A subform of "Eskimo". |
| 747 | |
| 748 | =item {ik} : Inupiaq |
| 749 | |
| 750 | A subform of "Eskimo". |
| 751 | |
| 752 | =item [{ira} : Iranian (Other)] |
| 753 | |
| 754 | =item {ga} : Irish |
| 755 | |
| 756 | =item {mga} : Middle Irish (900-1200) |
| 757 | |
| 758 | (Historical) |
| 759 | |
| 760 | =item {sga} : Old Irish (to 900) |
| 761 | |
| 762 | (Historical) |
| 763 | |
| 764 | =item [{iro} : Iroquoian languages] |
| 765 | |
| 766 | =item {it} : Italian |
| 767 | |
| 768 | Notable forms: |
| 769 | {it-it} Italy Italian; |
| 770 | {it-ch} Swiss Italian. |
| 771 | |
| 772 | =item {ja} : Japanese |
| 773 | |
| 774 | (NOT "jp"!) |
| 775 | |
| 776 | =item {jw} : Javanese |
| 777 | |
| 778 | =item {jrb} : Judeo-Arabic |
| 779 | |
| 780 | =item {jpr} : Judeo-Persian |
| 781 | |
| 782 | =item {kab} : Kabyle |
| 783 | |
| 784 | =item {kac} : Kachin |
| 785 | |
| 786 | =item {kl} : Kalaallisut |
| 787 | |
| 788 | eq Greenlandic "Eskimo" |
| 789 | |
| 790 | =item {kam} : Kamba |
| 791 | |
| 792 | =item {kn} : Kannada |
| 793 | |
| 794 | eq Kanarese. NOT Canadian! |
| 795 | |
| 796 | =item {kau} : Kanuri |
| 797 | |
| 798 | =item {kaa} : Kara-Kalpak |
| 799 | |
| 800 | =item {kar} : Karen |
| 801 | |
| 802 | =item {ks} : Kashmiri |
| 803 | |
| 804 | =item {kaw} : Kawi |
| 805 | |
| 806 | =item {kk} : Kazakh |
| 807 | |
| 808 | =item {kha} : Khasi |
| 809 | |
| 810 | =item {km} : Khmer |
| 811 | |
| 812 | eq Cambodian. eq Kampuchean. |
| 813 | |
| 814 | =item [{khi} : Khoisan (Other)] |
| 815 | |
| 816 | =item {kho} : Khotanese |
| 817 | |
| 818 | =item {ki} : Kikuyu |
| 819 | |
| 820 | eq Gikuyu. |
| 821 | |
| 822 | =item {kmb} : Kimbundu |
| 823 | |
| 824 | =item {rw} : Kinyarwanda |
| 825 | |
| 826 | =item {ky} : Kirghiz |
| 827 | |
| 828 | =item {i-klingon} : Klingon |
| 829 | |
| 830 | =item {kv} : Komi |
| 831 | |
| 832 | =item {kon} : Kongo |
| 833 | |
| 834 | =item {kok} : Konkani |
| 835 | |
| 836 | =item {ko} : Korean |
| 837 | |
| 838 | =item {kos} : Kosraean |
| 839 | |
| 840 | =item {kpe} : Kpelle |
| 841 | |
| 842 | =item {kro} : Kru |
| 843 | |
| 844 | =item {kj} : Kuanyama |
| 845 | |
| 846 | =item {kum} : Kumyk |
| 847 | |
| 848 | =item {ku} : Kurdish |
| 849 | |
| 850 | =item {kru} : Kurukh |
| 851 | |
| 852 | =item {kut} : Kutenai |
| 853 | |
| 854 | =item {lad} : Ladino |
| 855 | |
| 856 | eq Judeo-Spanish. NOT Ladin (a minority language in Italy). |
| 857 | |
| 858 | =item {lah} : Lahnda |
| 859 | |
| 860 | NOT Lamba! |
| 861 | |
| 862 | =item {lam} : Lamba |
| 863 | |
| 864 | NOT Lahnda! |
| 865 | |
| 866 | =item {lo} : Lao |
| 867 | |
| 868 | eq Laotian. |
| 869 | |
| 870 | =item {la} : Latin |
| 871 | |
| 872 | (Historical) NOT Ladin! NOT Ladino! |
| 873 | |
| 874 | =item {lv} : Latvian |
| 875 | |
| 876 | eq Lettish. |
| 877 | |
| 878 | =item {lb} : Letzeburgesch |
| 879 | |
| 880 | eq Luxemburgian, eq Luxemburger. (Formerly i-lux.) |
| 881 | |
| 882 | =for etc |
| 883 | {i-lux} Letzeburgesch (old tag) |
| 884 | |
| 885 | =item {lez} : Lezghian |
| 886 | |
| 887 | =item {ln} : Lingala |
| 888 | |
| 889 | =item {lt} : Lithuanian |
| 890 | |
| 891 | =item {nds} : Low German |
| 892 | |
| 893 | eq Low Saxon. eq Low German. eq Low Saxon. |
| 894 | |
| 895 | =item {loz} : Lozi |
| 896 | |
| 897 | =item {lub} : Luba-Katanga |
| 898 | |
| 899 | =item {lua} : Luba-Lulua |
| 900 | |
| 901 | =item {lui} : Luiseno |
| 902 | |
| 903 | eq LuiseE<ntilde>o. |
| 904 | |
| 905 | =item {lun} : Lunda |
| 906 | |
| 907 | =item {luo} : Luo (Kenya and Tanzania) |
| 908 | |
| 909 | =item {lus} : Lushai |
| 910 | |
| 911 | =item {mk} : Macedonian |
| 912 | |
| 913 | eq the modern Slavic language spoken in what was Yugoslavia. |
| 914 | NOT the form of Greek spoken in Greek Macedonia! |
| 915 | |
| 916 | =item {mad} : Madurese |
| 917 | |
| 918 | =item {mag} : Magahi |
| 919 | |
| 920 | =item {mai} : Maithili |
| 921 | |
| 922 | =item {mak} : Makasar |
| 923 | |
| 924 | =item {mg} : Malagasy |
| 925 | |
| 926 | =item {ms} : Malay |
| 927 | |
| 928 | NOT Malayalam! |
| 929 | |
| 930 | =item {ml} : Malayalam |
| 931 | |
| 932 | NOT Malay! |
| 933 | |
| 934 | =item {mt} : Maltese |
| 935 | |
| 936 | =item {mnc} : Manchu |
| 937 | |
| 938 | =item {mdr} : Mandar |
| 939 | |
| 940 | NOT Mandarin! |
| 941 | |
| 942 | =item {man} : Mandingo |
| 943 | |
| 944 | =item {mni} : Manipuri |
| 945 | |
| 946 | eq Meithei. |
| 947 | |
| 948 | =item [{mno} : Manobo languages] |
| 949 | |
| 950 | =item {gv} : Manx |
| 951 | |
| 952 | =item {mi} : Maori |
| 953 | |
| 954 | NOT Mari! |
| 955 | |
| 956 | =item {mr} : Marathi |
| 957 | |
| 958 | =item {chm} : Mari |
| 959 | |
| 960 | NOT Maori! |
| 961 | |
| 962 | =item {mh} : Marshall |
| 963 | |
| 964 | eq Marshallese. |
| 965 | |
| 966 | =item {mwr} : Marwari |
| 967 | |
| 968 | =item {mas} : Masai |
| 969 | |
| 970 | =item [{myn} : Mayan languages] |
| 971 | |
| 972 | =item {men} : Mende |
| 973 | |
| 974 | =item {mic} : Micmac |
| 975 | |
| 976 | =item {min} : Minangkabau |
| 977 | |
| 978 | =item {i-mingo} : Mingo |
| 979 | |
| 980 | eq the Irquoian language West Virginia Seneca. NOT New York Seneca! |
| 981 | |
| 982 | =item [{mis} : Miscellaneous languages] |
| 983 | |
| 984 | Don't use this. |
| 985 | |
| 986 | =item {moh} : Mohawk |
| 987 | |
| 988 | =item {mo} : Moldavian |
| 989 | |
| 990 | eq Moldovan. |
| 991 | |
| 992 | =item [{mkh} : Mon-Khmer (Other)] |
| 993 | |
| 994 | =item {lol} : Mongo |
| 995 | |
| 996 | =item {mn} : Mongolian |
| 997 | |
| 998 | eq Mongol. |
| 999 | |
| 1000 | =item {mos} : Mossi |
| 1001 | |
| 1002 | =item [{mul} : Multiple languages] |
| 1003 | |
| 1004 | Not for normal use. |
| 1005 | |
| 1006 | =item [{mun} : Munda languages] |
| 1007 | |
| 1008 | =item {nah} : Nahuatl |
| 1009 | |
| 1010 | =item {na} : Nauru |
| 1011 | |
| 1012 | =item {nv} : Navajo |
| 1013 | |
| 1014 | eq Navaho. (Formerly i-navajo.) |
| 1015 | |
| 1016 | =for etc |
| 1017 | {i-navajo} Navajo (old tag) |
| 1018 | |
| 1019 | =item {nd} : North Ndebele |
| 1020 | |
| 1021 | =item {nr} : South Ndebele |
| 1022 | |
| 1023 | =item {ng} : Ndonga |
| 1024 | |
| 1025 | =item {ne} : Nepali |
| 1026 | |
| 1027 | eq Nepalese. Notable forms: |
| 1028 | {ne-np} Nepal Nepali; |
| 1029 | {ne-in} India Nepali. |
| 1030 | |
| 1031 | =item {new} : Newari |
| 1032 | |
| 1033 | =item {nia} : Nias |
| 1034 | |
| 1035 | =item [{nic} : Niger-Kordofanian (Other)] |
| 1036 | |
| 1037 | =item [{ssa} : Nilo-Saharan (Other)] |
| 1038 | |
| 1039 | =item {niu} : Niuean |
| 1040 | |
| 1041 | =item {non} : Old Norse |
| 1042 | |
| 1043 | (Historical) |
| 1044 | |
| 1045 | =item [{nai} : North American Indian] |
| 1046 | |
| 1047 | Do not use this. |
| 1048 | |
| 1049 | =item {se} : Northern Sami |
| 1050 | |
| 1051 | eq Lappish. eq Lapp. eq (Northern) Saami. |
| 1052 | |
| 1053 | =item {no} : Norwegian |
| 1054 | |
| 1055 | Note the two following forms: |
| 1056 | |
| 1057 | =item {nb} : Norwegian Bokmal |
| 1058 | |
| 1059 | eq BokmE<aring>l, (A form of Norwegian.) (Formerly no-bok.) |
| 1060 | |
| 1061 | =for etc |
| 1062 | {no-bok} Norwegian Bokmal (old tag) |
| 1063 | |
| 1064 | =item {nn} : Norwegian Nynorsk |
| 1065 | |
| 1066 | (A form of Norwegian.) (Formerly no-nyn.) |
| 1067 | |
| 1068 | =for etc |
| 1069 | {no-nyn} Norwegian Nynorsk (old tag) |
| 1070 | |
| 1071 | =item [{nub} : Nubian languages] |
| 1072 | |
| 1073 | =item {nym} : Nyamwezi |
| 1074 | |
| 1075 | =item {nyn} : Nyankole |
| 1076 | |
| 1077 | =item {nyo} : Nyoro |
| 1078 | |
| 1079 | =item {nzi} : Nzima |
| 1080 | |
| 1081 | =item {oc} : Occitan (post 1500) |
| 1082 | |
| 1083 | eq ProvenE<ccedil>al, eq Provencal |
| 1084 | |
| 1085 | =item {oji} : Ojibwa |
| 1086 | |
| 1087 | eq Ojibwe. |
| 1088 | |
| 1089 | =item {or} : Oriya |
| 1090 | |
| 1091 | =item {om} : Oromo |
| 1092 | |
| 1093 | =item {osa} : Osage |
| 1094 | |
| 1095 | =item {os} : Ossetian; Ossetic |
| 1096 | |
| 1097 | =item [{oto} : Otomian languages] |
| 1098 | |
| 1099 | Group of languages collectively called "OtomE<iacute>". |
| 1100 | |
| 1101 | =item {pal} : Pahlavi |
| 1102 | |
| 1103 | eq Pahlevi |
| 1104 | |
| 1105 | =item {i-pwn} : Paiwan |
| 1106 | |
| 1107 | eq Pariwan |
| 1108 | |
| 1109 | =item {pau} : Palauan |
| 1110 | |
| 1111 | =item {pi} : Pali |
| 1112 | |
| 1113 | (Historical?) |
| 1114 | |
| 1115 | =item {pam} : Pampanga |
| 1116 | |
| 1117 | =item {pag} : Pangasinan |
| 1118 | |
| 1119 | =item {pa} : Panjabi |
| 1120 | |
| 1121 | eq Punjabi |
| 1122 | |
| 1123 | =item {pap} : Papiamento |
| 1124 | |
| 1125 | eq Papiamentu. |
| 1126 | |
| 1127 | =item [{paa} : Papuan (Other)] |
| 1128 | |
| 1129 | =item {fa} : Persian |
| 1130 | |
| 1131 | eq Farsi. eq Iranian. |
| 1132 | |
| 1133 | =item {peo} : Old Persian (ca.600-400 B.C.) |
| 1134 | |
| 1135 | =item [{phi} : Philippine (Other)] |
| 1136 | |
| 1137 | =item {phn} : Phoenician |
| 1138 | |
| 1139 | (Historical) |
| 1140 | |
| 1141 | =item {pon} : Pohnpeian |
| 1142 | |
| 1143 | NOT Pompeiian! |
| 1144 | |
| 1145 | =item {pl} : Polish |
| 1146 | |
| 1147 | =item {pt} : Portuguese |
| 1148 | |
| 1149 | eq Portugese. Notable forms: |
| 1150 | {pt-pt} Portugal Portuguese; |
| 1151 | {pt-br} Brazilian Portuguese. |
| 1152 | |
| 1153 | =item [{pra} : Prakrit languages] |
| 1154 | |
| 1155 | =item {pro} : Old Provencal (to 1500) |
| 1156 | |
| 1157 | eq Old ProvenE<ccedil>al. (Historical.) |
| 1158 | |
| 1159 | =item {ps} : Pushto |
| 1160 | |
| 1161 | eq Pashto. eq Pushtu. |
| 1162 | |
| 1163 | =item {qu} : Quechua |
| 1164 | |
| 1165 | eq Quecha. |
| 1166 | |
| 1167 | =item {rm} : Raeto-Romance |
| 1168 | |
| 1169 | eq Romansh. |
| 1170 | |
| 1171 | =item {raj} : Rajasthani |
| 1172 | |
| 1173 | =item {rap} : Rapanui |
| 1174 | |
| 1175 | =item {rar} : Rarotongan |
| 1176 | |
| 1177 | =item [{qaa - qtz} : Reserved for local use.] |
| 1178 | |
| 1179 | =item [{roa} : Romance (Other)] |
| 1180 | |
| 1181 | NOT Romanian! NOT Romany! NOT Romansh! |
| 1182 | |
| 1183 | =item {ro} : Romanian |
| 1184 | |
| 1185 | eq Rumanian. NOT Romany! |
| 1186 | |
| 1187 | =item {rom} : Romany |
| 1188 | |
| 1189 | eq Rom. NOT Romanian! |
| 1190 | |
| 1191 | =item {rn} : Rundi |
| 1192 | |
| 1193 | =item {ru} : Russian |
| 1194 | |
| 1195 | NOT White Russian! NOT Rusyn! |
| 1196 | |
| 1197 | =item [{sal} : Salishan languages] |
| 1198 | |
| 1199 | Large language group. |
| 1200 | |
| 1201 | =item {sam} : Samaritan Aramaic |
| 1202 | |
| 1203 | NOT Aramaic! |
| 1204 | |
| 1205 | =item [{smi} : Sami languages (Other)] |
| 1206 | |
| 1207 | =item {sm} : Samoan |
| 1208 | |
| 1209 | =item {sad} : Sandawe |
| 1210 | |
| 1211 | =item {sg} : Sango |
| 1212 | |
| 1213 | =item {sa} : Sanskrit |
| 1214 | |
| 1215 | (Historical) |
| 1216 | |
| 1217 | =item {sat} : Santali |
| 1218 | |
| 1219 | =item {sc} : Sardinian |
| 1220 | |
| 1221 | eq Sard. |
| 1222 | |
| 1223 | =item {sas} : Sasak |
| 1224 | |
| 1225 | =item {sco} : Scots |
| 1226 | |
| 1227 | NOT Scots Gaelic! |
| 1228 | |
| 1229 | =item {sel} : Selkup |
| 1230 | |
| 1231 | =item [{sem} : Semitic (Other)] |
| 1232 | |
| 1233 | =item {sr} : Serbian |
| 1234 | |
| 1235 | eq Serb. NOT Sorbian. |
| 1236 | |
| 1237 | =item {srr} : Serer |
| 1238 | |
| 1239 | =item {shn} : Shan |
| 1240 | |
| 1241 | =item {sn} : Shona |
| 1242 | |
| 1243 | =item {sid} : Sidamo |
| 1244 | |
| 1245 | =item {sgn-...} : Sign Languages |
| 1246 | |
| 1247 | Always use with a subtag. Notable forms: |
| 1248 | {sgn-gb} British Sign Language (BSL); |
| 1249 | {sgn-ie} Irish Sign Language (ESL); |
| 1250 | {sgn-ni} Nicaraguan Sign Language (ISN); |
| 1251 | {sgn-us} American Sign Language (ASL). |
| 1252 | |
| 1253 | =item {bla} : Siksika |
| 1254 | |
| 1255 | eq Blackfoot. eq Pikanii. |
| 1256 | |
| 1257 | =item {sd} : Sindhi |
| 1258 | |
| 1259 | =item {si} : Sinhalese |
| 1260 | |
| 1261 | eq Sinhala. |
| 1262 | |
| 1263 | =item [{sit} : Sino-Tibetan (Other)] |
| 1264 | |
| 1265 | =item [{sio} : Siouan languages] |
| 1266 | |
| 1267 | =item {den} : Slave (Athapascan) |
| 1268 | |
| 1269 | ("Slavey" is a subform.) |
| 1270 | |
| 1271 | =item [{sla} : Slavic (Other)] |
| 1272 | |
| 1273 | =item {sk} : Slovak |
| 1274 | |
| 1275 | eq Slovakian. |
| 1276 | |
| 1277 | =item {sl} : Slovenian |
| 1278 | |
| 1279 | eq Slovene. |
| 1280 | |
| 1281 | =item {sog} : Sogdian |
| 1282 | |
| 1283 | =item {so} : Somali |
| 1284 | |
| 1285 | =item {son} : Songhai |
| 1286 | |
| 1287 | =item {snk} : Soninke |
| 1288 | |
| 1289 | =item {wen} : Sorbian languages |
| 1290 | |
| 1291 | eq Wendish. eq Sorb. eq Lusatian. eq Wend. NOT Venda! NOT Serbian! |
| 1292 | |
| 1293 | =item {nso} : Northern Sotho |
| 1294 | |
| 1295 | =item {st} : Southern Sotho |
| 1296 | |
| 1297 | eq Sutu. eq Sesotho. |
| 1298 | |
| 1299 | =item [{sai} : South American Indian (Other)] |
| 1300 | |
| 1301 | =item {es} : Spanish |
| 1302 | |
| 1303 | Notable forms: |
| 1304 | {es-ar} Argentine Spanish; |
| 1305 | {es-bo} Bolivian Spanish; |
| 1306 | {es-cl} Chilean Spanish; |
| 1307 | {es-co} Colombian Spanish; |
| 1308 | {es-do} Dominican Spanish; |
| 1309 | {es-ec} Ecuadorian Spanish; |
| 1310 | {es-es} Spain Spanish; |
| 1311 | {es-gt} Guatemalan Spanish; |
| 1312 | {es-hn} Honduran Spanish; |
| 1313 | {es-mx} Mexican Spanish; |
| 1314 | {es-pa} Panamanian Spanish; |
| 1315 | {es-pe} Peruvian Spanish; |
| 1316 | {es-pr} Puerto Rican Spanish; |
| 1317 | {es-py} Paraguay Spanish; |
| 1318 | {es-sv} Salvadoran Spanish; |
| 1319 | {es-us} US Spanish; |
| 1320 | {es-uy} Uruguayan Spanish; |
| 1321 | {es-ve} Venezuelan Spanish. |
| 1322 | |
| 1323 | =item {suk} : Sukuma |
| 1324 | |
| 1325 | =item {sux} : Sumerian |
| 1326 | |
| 1327 | (Historical) |
| 1328 | |
| 1329 | =item {su} : Sundanese |
| 1330 | |
| 1331 | =item {sus} : Susu |
| 1332 | |
| 1333 | =item {sw} : Swahili |
| 1334 | |
| 1335 | eq Kiswahili |
| 1336 | |
| 1337 | =item {ss} : Swati |
| 1338 | |
| 1339 | =item {sv} : Swedish |
| 1340 | |
| 1341 | Notable forms: |
| 1342 | {sv-se} Sweden Swedish; |
| 1343 | {sv-fi} Finland Swedish. |
| 1344 | |
| 1345 | =item {syr} : Syriac |
| 1346 | |
| 1347 | =item {tl} : Tagalog |
| 1348 | |
| 1349 | =item {ty} : Tahitian |
| 1350 | |
| 1351 | =item [{tai} : Tai (Other)] |
| 1352 | |
| 1353 | NOT Thai! |
| 1354 | |
| 1355 | =item {tg} : Tajik |
| 1356 | |
| 1357 | =item {tmh} : Tamashek |
| 1358 | |
| 1359 | =item {ta} : Tamil |
| 1360 | |
| 1361 | =item {i-tao} : Tao |
| 1362 | |
| 1363 | eq Yami. |
| 1364 | |
| 1365 | =item {tt} : Tatar |
| 1366 | |
| 1367 | =item {i-tay} : Tayal |
| 1368 | |
| 1369 | eq Atayal. eq Atayan. |
| 1370 | |
| 1371 | =item {te} : Telugu |
| 1372 | |
| 1373 | =item {ter} : Tereno |
| 1374 | |
| 1375 | =item {tet} : Tetum |
| 1376 | |
| 1377 | =item {th} : Thai |
| 1378 | |
| 1379 | NOT Tai! |
| 1380 | |
| 1381 | =item {bo} : Tibetan |
| 1382 | |
| 1383 | =item {tig} : Tigre |
| 1384 | |
| 1385 | =item {ti} : Tigrinya |
| 1386 | |
| 1387 | =item {tem} : Timne |
| 1388 | |
| 1389 | eq Themne. eq Timene. |
| 1390 | |
| 1391 | =item {tiv} : Tiv |
| 1392 | |
| 1393 | =item {tli} : Tlingit |
| 1394 | |
| 1395 | =item {tpi} : Tok Pisin |
| 1396 | |
| 1397 | =item {tkl} : Tokelau |
| 1398 | |
| 1399 | =item {tog} : Tonga (Nyasa) |
| 1400 | |
| 1401 | NOT Tsonga! |
| 1402 | |
| 1403 | =item {to} : Tonga (Tonga Islands) |
| 1404 | |
| 1405 | (Pronounced "Tong-a", not "Tong-ga") |
| 1406 | |
| 1407 | NOT Tsonga! |
| 1408 | |
| 1409 | =item {tsi} : Tsimshian |
| 1410 | |
| 1411 | eq Sm'algyax |
| 1412 | |
| 1413 | =item {ts} : Tsonga |
| 1414 | |
| 1415 | NOT Tonga! |
| 1416 | |
| 1417 | =item {i-tsu} : Tsou |
| 1418 | |
| 1419 | =item {tn} : Tswana |
| 1420 | |
| 1421 | Same as Setswana. |
| 1422 | |
| 1423 | =item {tum} : Tumbuka |
| 1424 | |
| 1425 | =item {tr} : Turkish |
| 1426 | |
| 1427 | (Typically in Roman script) |
| 1428 | |
| 1429 | =item {ota} : Ottoman Turkish (1500-1928) |
| 1430 | |
| 1431 | (Typically in Arabic script) (Historical) |
| 1432 | |
| 1433 | =item {tk} : Turkmen |
| 1434 | |
| 1435 | eq Turkmeni. |
| 1436 | |
| 1437 | =item {tvl} : Tuvalu |
| 1438 | |
| 1439 | =item {tyv} : Tuvinian |
| 1440 | |
| 1441 | eq Tuvan. eq Tuvin. |
| 1442 | |
| 1443 | =item {tw} : Twi |
| 1444 | |
| 1445 | =item {uga} : Ugaritic |
| 1446 | |
| 1447 | NOT Ugric! |
| 1448 | |
| 1449 | =item {ug} : Uighur |
| 1450 | |
| 1451 | =item {uk} : Ukrainian |
| 1452 | |
| 1453 | =item {umb} : Umbundu |
| 1454 | |
| 1455 | =item {und} : Undetermined |
| 1456 | |
| 1457 | Not a tag for normal use. |
| 1458 | |
| 1459 | =item {ur} : Urdu |
| 1460 | |
| 1461 | =item {uz} : Uzbek |
| 1462 | |
| 1463 | eq E<Ouml>zbek |
| 1464 | |
| 1465 | =item {vai} : Vai |
| 1466 | |
| 1467 | =item {ven} : Venda |
| 1468 | |
| 1469 | NOT Wendish! NOT Wend! NOT Avestan! |
| 1470 | |
| 1471 | =item {vi} : Vietnamese |
| 1472 | |
| 1473 | eq Viet. |
| 1474 | |
| 1475 | =item {vo} : Volapuk |
| 1476 | |
| 1477 | eq VolapE<uuml>k. (Artificial) |
| 1478 | |
| 1479 | =item {vot} : Votic |
| 1480 | |
| 1481 | eq Votian. eq Vod. |
| 1482 | |
| 1483 | =item [{wak} : Wakashan languages] |
| 1484 | |
| 1485 | =item {wal} : Walamo |
| 1486 | |
| 1487 | eq Wolaytta. |
| 1488 | |
| 1489 | =item {war} : Waray |
| 1490 | |
| 1491 | Presumably the Philippine language Waray-Waray (SamareE<ntilde>o), |
| 1492 | not the smaller Philippine language Waray Sorsogon, nor the extinct |
| 1493 | Australian language Waray. |
| 1494 | |
| 1495 | =item {was} : Washo |
| 1496 | |
| 1497 | eq Washoe |
| 1498 | |
| 1499 | =item {cy} : Welsh |
| 1500 | |
| 1501 | =item {wo} : Wolof |
| 1502 | |
| 1503 | =item {x-...} : Unregistered (Semi-Private Use) |
| 1504 | |
| 1505 | "x-" is a prefix for language tags that are not registered with ISO |
| 1506 | or IANA. Example, x-double-dutch |
| 1507 | |
| 1508 | =item {xh} : Xhosa |
| 1509 | |
| 1510 | =item {sah} : Yakut |
| 1511 | |
| 1512 | =item {yao} : Yao |
| 1513 | |
| 1514 | (The Yao in Malawi?) |
| 1515 | |
| 1516 | =item {yap} : Yapese |
| 1517 | |
| 1518 | eq Yap |
| 1519 | |
| 1520 | =item {yi} : Yiddish |
| 1521 | |
| 1522 | Formerly "ji". Sometimes in Roman script, sometimes in Hebrew script. |
| 1523 | |
| 1524 | =for etc |
| 1525 | {ji} Yiddish (old tag) |
| 1526 | |
| 1527 | =item {yo} : Yoruba |
| 1528 | |
| 1529 | =item [{ypk} : Yupik languages] |
| 1530 | |
| 1531 | Several "Eskimo" languages. |
| 1532 | |
| 1533 | =item {znd} : Zande |
| 1534 | |
| 1535 | =item [{zap} : Zapotec] |
| 1536 | |
| 1537 | (A group of languages.) |
| 1538 | |
| 1539 | =item {zen} : Zenaga |
| 1540 | |
| 1541 | NOT Zend. |
| 1542 | |
| 1543 | =item {za} : Zhuang |
| 1544 | |
| 1545 | =item {zu} : Zulu |
| 1546 | |
| 1547 | =item {zun} : Zuni |
| 1548 | |
| 1549 | eq ZuE<ntilde>i |
| 1550 | |
| 1551 | =back |
| 1552 | |
| 1553 | =for woohah END |
| 1554 | |
| 1555 | =head1 SEE ALSO |
| 1556 | |
| 1557 | L<I18N::LangTags|I18N::LangTags> and its "See Also" section. |
| 1558 | |
| 1559 | =head1 COPYRIGHT AND DISCLAIMER |
| 1560 | |
| 1561 | Copyright (c) 2001,2002 Sean M. Burke. All rights reserved. |
| 1562 | |
| 1563 | You can redistribute and/or |
| 1564 | modify this document under the same terms as Perl itself. |
| 1565 | |
| 1566 | This document is provided in the hope that it will be |
| 1567 | useful, but without any warranty; |
| 1568 | without even the implied warranty of accuracy, authoritativeness, |
| 1569 | completeness, merchantability, or fitness for a particular purpose. |
| 1570 | |
| 1571 | Email any corrections or questions to me. |
| 1572 | |
| 1573 | =head1 AUTHOR |
| 1574 | |
| 1575 | Sean M. Burke, sburkeE<64>cpan.org |
| 1576 | |
| 1577 | =cut |
| 1578 | |
| 1579 | |
| 1580 | # To generate a list of just the two and three-letter codes: |
| 1581 | |
| 1582 | #!/usr/local/bin/perl -w |
| 1583 | |
| 1584 | require 5; # Time-stamp: "2001-03-13 21:53:39 MST" |
| 1585 | # Sean M. Burke, sburke@cpan.org |
| 1586 | # This program is for generating the language_codes.txt file |
| 1587 | use strict; |
| 1588 | use LWP::Simple; |
| 1589 | use HTML::TreeBuilder 3.10; |
| 1590 | my $root = HTML::TreeBuilder->new(); |
| 1591 | my $url = 'http://lcweb.loc.gov/standards/iso639-2/bibcodes.html'; |
| 1592 | $root->parse(get($url) || die "Can't get $url"); |
| 1593 | $root->eof(); |
| 1594 | |
| 1595 | my @codes; |
| 1596 | |
| 1597 | foreach my $tr ($root->find_by_tag_name('tr')) { |
| 1598 | my @f = map $_->as_text(), $tr->content_list(); |
| 1599 | #print map("<$_> ", @f), "\n"; |
| 1600 | next unless @f == 5; |
| 1601 | pop @f; # nix the French name |
| 1602 | next if $f[-1] eq 'Language Name (English)'; # it's a header line |
| 1603 | my $xx = splice(@f, 2,1); # pull out the two-letter code |
| 1604 | $f[-1] =~ s/^\s+//; |
| 1605 | $f[-1] =~ s/\s+$//; |
| 1606 | if($xx =~ m/[a-zA-Z]/) { # there's a two-letter code for it |
| 1607 | push @codes, [ lc($f[-1]), "$xx\t$f[-1]\n" ]; |
| 1608 | } else { # print the three-letter codes. |
| 1609 | if($f[0] eq $f[1]) { |
| 1610 | push @codes, [ lc($f[-1]), "$f[1]\t$f[2]\n" ]; |
| 1611 | } else { # shouldn't happen |
| 1612 | push @codes, [ lc($f[-1]), "@f !!!!!!!!!!\n" ]; |
| 1613 | } |
| 1614 | } |
| 1615 | } |
| 1616 | |
| 1617 | print map $_->[1], sort {; $a->[0] cmp $b->[0] } @codes; |
| 1618 | print "[ based on $url\n at ", scalar(localtime), "]\n", |
| 1619 | "[Note: doesn't include IANA-registered codes.]\n"; |
| 1620 | exit; |
| 1621 | __END__ |
| 1622 | |