linguistics 1.0.9 → 2.0.0

Sign up to get free protection for your applications and to get access to all the features.
Files changed (69) hide show
  1. data.tar.gz.sig +0 -0
  2. data/.gemtest +0 -0
  3. data/ChangeLog +849 -342
  4. data/History.rdoc +11 -0
  5. data/LICENSE +9 -9
  6. data/Manifest.txt +44 -0
  7. data/README.rdoc +226 -0
  8. data/Rakefile +32 -349
  9. data/examples/endocs.rb +272 -0
  10. data/examples/generalize_sentence.rb +2 -1
  11. data/examples/klingon.rb +22 -0
  12. data/lib/linguistics.rb +130 -292
  13. data/lib/linguistics/en.rb +337 -1628
  14. data/lib/linguistics/en/articles.rb +138 -0
  15. data/lib/linguistics/en/conjugation.rb +2245 -0
  16. data/lib/linguistics/en/conjunctions.rb +202 -0
  17. data/lib/linguistics/en/{infinitive.rb → infinitives.rb} +41 -55
  18. data/lib/linguistics/en/linkparser.rb +41 -49
  19. data/lib/linguistics/en/numbers.rb +483 -0
  20. data/lib/linguistics/en/participles.rb +33 -0
  21. data/lib/linguistics/en/pluralization.rb +810 -0
  22. data/lib/linguistics/en/stemmer.rb +75 -0
  23. data/lib/linguistics/en/titlecase.rb +121 -0
  24. data/lib/linguistics/en/wordnet.rb +63 -97
  25. data/lib/linguistics/inflector.rb +89 -0
  26. data/lib/linguistics/iso639.rb +534 -448
  27. data/lib/linguistics/languagebehavior.rb +36 -0
  28. data/lib/linguistics/monkeypatches.rb +42 -0
  29. data/spec/lib/constants.rb +15 -0
  30. data/spec/lib/helpers.rb +38 -0
  31. data/spec/linguistics/en/articles_spec.rb +797 -0
  32. data/spec/linguistics/en/conjugation_spec.rb +2083 -0
  33. data/spec/linguistics/en/conjunctions_spec.rb +154 -0
  34. data/spec/linguistics/en/infinitives_spec.rb +518 -0
  35. data/spec/linguistics/en/linkparser_spec.rb +66 -0
  36. data/spec/linguistics/en/numbers_spec.rb +1295 -0
  37. data/spec/linguistics/en/participles_spec.rb +55 -0
  38. data/spec/linguistics/en/pluralization_spec.rb +4636 -0
  39. data/spec/linguistics/en/stemmer_spec.rb +72 -0
  40. data/spec/linguistics/en/titlecase_spec.rb +841 -0
  41. data/spec/linguistics/en/wordnet_spec.rb +85 -0
  42. data/spec/linguistics/en_spec.rb +45 -167
  43. data/spec/linguistics/inflector_spec.rb +40 -0
  44. data/spec/linguistics/iso639_spec.rb +49 -53
  45. data/spec/linguistics/monkeypatches_spec.rb +40 -0
  46. data/spec/linguistics_spec.rb +46 -76
  47. metadata +241 -113
  48. metadata.gz.sig +0 -0
  49. data/README +0 -166
  50. data/README.english +0 -245
  51. data/rake/191_compat.rb +0 -26
  52. data/rake/dependencies.rb +0 -76
  53. data/rake/documentation.rb +0 -123
  54. data/rake/helpers.rb +0 -502
  55. data/rake/hg.rb +0 -318
  56. data/rake/manual.rb +0 -787
  57. data/rake/packaging.rb +0 -129
  58. data/rake/publishing.rb +0 -341
  59. data/rake/style.rb +0 -62
  60. data/rake/svn.rb +0 -668
  61. data/rake/testing.rb +0 -152
  62. data/rake/verifytask.rb +0 -64
  63. data/tests/en/infinitive.tests.rb +0 -207
  64. data/tests/en/inflect.tests.rb +0 -1389
  65. data/tests/en/lafcadio.tests.rb +0 -77
  66. data/tests/en/linkparser.tests.rb +0 -42
  67. data/tests/en/lprintf.tests.rb +0 -77
  68. data/tests/en/titlecase.tests.rb +0 -73
  69. data/tests/en/wordnet.tests.rb +0 -95
@@ -1,461 +1,547 @@
1
1
  #!/usr/bin/ruby
2
- #coding: utf-8
2
+ # coding: utf-8
3
3
 
4
- #
5
- # linguistics/iso639.rb - A hash of International 2- and 3-letter
6
- # ISO639-1 and ISO639-2 language codes. Each entry has two keys:
4
+ require 'linguistics' unless defined?( Linguistics )
5
+
6
+ # A hash of International 2- and 3-letter ISO639-1 and ISO639-2
7
+ # language codes information. Each entry is keyed by all of its
8
+ # language codes as Symbols, and the entry itself has three keys:
7
9
  #
8
10
  # [<tt>:codes</tt>]
9
- # All of the codes known for this language
10
- # [<tt>:desc</tt>]
11
- # The English-language description of the language.
12
- #
13
- # :include: LICENSE
14
- #
15
- #--
11
+ # All of the codes known for this language as Strings
12
+ # [<tt>:eng_name</tt>]
13
+ # The English-language name of the language.
14
+ # [<tt>:fre_name</tt>]
15
+ # The French-language name of the language.
16
16
  #
17
- # Please see the file LICENSE in the base directory for licensing details.
17
+ # Entries for 'ja' and 'en':
18
18
  #
19
- module Linguistics
19
+ # irb > Linguistics::ISO639::LANGUAGE_CODES[:en]
20
+ # => {:eng_name=>"English", :fre_name=>"anglais", :codes=>["en", "eng"]}
21
+ # irb > Linguistics::ISO639::LANGUAGE_CODES[:eng]
22
+ # => {:eng_name=>"English", :fre_name=>"anglais", :codes=>["en", "eng"]}
23
+ # irb > Linguistics::ISO639::LANGUAGE_CODES[:ja]
24
+ # => {:eng_name=>"Japanese", :fre_name=>"japonais", :codes=>["ja", "jpn"]}
25
+
26
+ module Linguistics::ISO639
20
27
 
21
28
  # Hash of ISO639 2- and 3-letter language codes
22
- LanguageCodes = {}
29
+ LANGUAGE_CODES = {}
30
+
31
+ # Read everything after the __END__
32
+ _, data = File.read( __FILE__, :encoding => 'utf-8' ).split( /^__END__$/, 2 )
33
+
34
+ # To read the files, please note that one line of text contains one
35
+ # entry. An alpha-3 (bibliographic) code, an alpha-3 (terminologic)
36
+ # code (when given), an alpha-2 code (when given), an English name,
37
+ # and a French name of a language are all separated by pipe (|)
38
+ # characters. If one of these elements is not applicable to the entry,
39
+ # the field is left empty, i.e., a pipe (|) character immediately
40
+ # follows the preceding entry. The Line terminator is the LF character.
23
41
 
24
- # Read through the source for this file, capturing everything
25
- # between __END__ and __END_DATA__ tokens.
26
- in_data_section = false
27
- File::readlines( __FILE__ ).each {|line|
28
- case line
29
- when /^__END_DATA__$/
30
- in_data_section = false
31
- false
42
+ # bib_alpha3|term_alpha3|alpha2|eng_name|fre_name
43
+ # E.g., "eng||en|English|anglais"
44
+ data.lines do |line|
45
+ next unless line =~ /\|/ # Skip non-language lines
46
+ bib_alpha3, term_alpha3, alpha2, eng_name, fre_name = line.chomp.split( '|', 5 )
47
+ entry = {
48
+ :eng_name => eng_name,
49
+ :fre_name => fre_name,
50
+ :codes => [ bib_alpha3, alpha2, term_alpha3 ].reject {|item| item.empty? }
51
+ }
52
+ $stderr.puts " adding language code entry %p from line: %p" %
53
+ [ entry, line ] if $DEBUG
32
54
 
33
- when /^__END__$/
34
- in_data_section = true
35
- false
55
+ LANGUAGE_CODES[ bib_alpha3.to_sym ] = entry
56
+ LANGUAGE_CODES[ alpha2.to_sym ] = entry if alpha2
57
+ end
36
58
 
37
- else
38
- if in_data_section
39
- codes, desc = line[0,15].split(%r{/|\s+}), line[15...-1]
40
- codes.delete_if {|code| code.empty?}
41
- entry = {
42
- :desc => desc.strip,
43
- :codes => codes.dup,
44
- }
45
- codes.each {|code|
46
- raise "Duplicate language code #{code}:"\
47
- "(#{LanguageCodes[code][:desc]}})}" \
48
- if LanguageCodes.key?( code )
49
- LanguageCodes[ code.strip ] = entry
50
- }
51
- end
52
- end
53
- }
54
- end
59
+ end # module Linguistics::ISO639
55
60
 
61
+ # Data from: http://www.loc.gov/standards/iso639-2/ISO-639-2_utf-8.txt
56
62
  __END__
57
- abk ab Abkhazian
58
- ace Achinese
59
- ach Acoli
60
- ada Adangme
61
- aar aa Afar
62
- afh Afrihili
63
- afr af Afrikaans
64
- afa Afro-Asiatic (Other)
65
- aka Akan
66
- akk Akkadian
67
- alb/sqi sq Albanian
68
- ale Aleut
69
- alg Algonquian languages
70
- tut Altaic (Other)
71
- amh am Amharic
72
- apa Apache languages
73
- ara ar Arabic
74
- arc Aramaic
75
- arp Arapaho
76
- arn Araucanian
77
- arw Arawak
78
- arm/hye hy Armenian
79
- art Artificial (Other)
80
- asm as Assamese
81
- ath Athapascan languages
82
- map Austronesian (Other)
83
- ava Avaric
84
- ave Avestan
85
- awa Awadhi
86
- aym ay Aymara
87
- aze az Azerbaijani
88
- nah Aztec
89
- ban Balinese
90
- bat Baltic (Other)
91
- bal Baluchi
92
- bam Bambara
93
- bai Bamileke languages
94
- bad Banda
95
- bnt Bantu (Other)
96
- bas Basa
97
- bak ba Bashkir
98
- baq/eus eu Basque
99
- bej Beja
100
- bem Bemba
101
- ben bn Bengali
102
- ber Berber (Other)
103
- bho Bhojpuri
104
- bih bh Bihari
105
- bik Bikol
106
- bin Bini
107
- bis bi Bislama
108
- bra Braj
109
- bre br Breton
110
- bug Buginese
111
- bul bg Bulgarian
112
- bua Buriat
113
- bur/mya my Burmese
114
- bel be Byelorussian
115
- cad Caddo
116
- car Carib
117
- cat ca Catalan
118
- cau Caucasian (Other)
119
- ceb Cebuano
120
- cel Celtic (Other)
121
- cai Central American Indian (Other)
122
- chg Chagatai
123
- cha Chamorro
124
- che Chechen
125
- chr Cherokee
126
- chy Cheyenne
127
- chb Chibcha
128
- chi/zho zh Chinese
129
- chn Chinook jargon
130
- cho Choctaw
131
- chu Church Slavic
132
- chv Chuvash
133
- cop Coptic
134
- cor Cornish
135
- cos co Corsican
136
- cre Cree
137
- mus Creek
138
- crp Creoles and Pidgins (Other)
139
- cpe Creoles and Pidgins, English-based (Other)
140
- cpf Creoles and Pidgins, French-based (Other)
141
- cpp Creoles and Pidgins, Portuguese-based (Other)
142
- cus Cushitic (Other)
143
- hr Croatian
144
- ces/cze cs Czech
145
- dak Dakota
146
- dan da Danish
147
- del Delaware
148
- din Dinka
149
- div Divehi
150
- doi Dogri
151
- dra Dravidian (Other)
152
- dua Duala
153
- dut/nla nl Dutch
154
- dum Dutch, Middle (ca. 1050-1350)
155
- dyu Dyula
156
- dzo dz Dzongkha
157
- efi Efik
158
- egy Egyptian (Ancient)
159
- eka Ekajuk
160
- elx Elamite
161
- eng en English
162
- enm English, Middle (ca. 1100-1500)
163
- ang English, Old (ca. 450-1100)
164
- esk Eskimo (Other)
165
- epo eo Esperanto
166
- est et Estonian
167
- ewe Ewe
168
- ewo Ewondo
169
- fan Fang
170
- fat Fanti
171
- fao fo Faroese
172
- fij fj Fijian
173
- fin fi Finnish
174
- fiu Finno-Ugrian (Other)
175
- fon Fon
176
- fra/fre fr French
177
- frm French, Middle (ca. 1400-1600)
178
- fro French, Old (842- ca. 1400)
179
- fry fy Frisian
180
- ful Fulah
181
- gaa Ga
182
- gae/gdh Gaelic (Scots)
183
- glg gl Gallegan
184
- lug Ganda
185
- gay Gayo
186
- gez Geez
187
- geo/kat ka Georgian
188
- deu/ger de German
189
- gmh German, Middle High (ca. 1050-1500)
190
- goh German, Old High (ca. 750-1050)
191
- gem Germanic (Other)
192
- gil Gilbertese
193
- gon Gondi
194
- got Gothic
195
- grb Grebo
196
- grc Greek, Ancient (to 1453)
197
- ell/gre el Greek, Modern (1453-)
198
- kal kl Greenlandic
199
- grn gn Guarani
200
- guj gu Gujarati
201
- hai Haida
202
- hau ha Hausa
203
- haw Hawaiian
204
- heb he Hebrew
205
- her Herero
206
- hil Hiligaynon
207
- him Himachali
208
- hin hi Hindi
209
- hmo Hiri Motu
210
- hun hu Hungarian
211
- hup Hupa
212
- iba Iban
213
- ice/isl is Icelandic
214
- ibo Igbo
215
- ijo Ijo
216
- ilo Iloko
217
- inc Indic (Other)
218
- ine Indo-European (Other)
219
- ind id Indonesian
220
- ina ia Interlingua (International Auxiliary language Association)
221
- ile Interlingue
222
- iku iu Inuktitut
223
- ipk ik Inupiak
224
- ira Iranian (Other)
225
- gai/iri ga Irish
226
- sga Irish, Old (to 900)
227
- mga Irish, Middle (900 - 1200)
228
- iro Iroquoian languages
229
- ita it Italian
230
- jpn ja Japanese
231
- jav/jaw jv/jw Javanese
232
- jrb Judeo-Arabic
233
- jpr Judeo-Persian
234
- kab Kabyle
235
- kac Kachin
236
- kam Kamba
237
- kan kn Kannada
238
- kau Kanuri
239
- kaa Kara-Kalpak
240
- kar Karen
241
- kas ks Kashmiri
242
- kaw Kawi
243
- kaz kk Kazakh
244
- kha Khasi
245
- khm km Khmer
246
- khi Khoisan (Other)
247
- kho Khotanese
248
- kik Kikuyu
249
- kin rw Kinyarwanda
250
- kir ky Kirghiz
251
- kom Komi
252
- kon Kongo
253
- kok Konkani
254
- kor ko Korean
255
- kpe Kpelle
256
- kro Kru
257
- kua Kuanyama
258
- kum Kumyk
259
- kur ku Kurdish
260
- kru Kurukh
261
- kus Kusaie
262
- kut Kutenai
263
- lad Ladino
264
- lah Lahnda
265
- lam Lamba
266
- oci oc Langue d'Oc (post 1500)
267
- lao lo Lao
268
- lat la Latin
269
- lav lv Latvian
270
- ltz Letzeburgesch
271
- lez Lezghian
272
- lin ln Lingala
273
- lit lt Lithuanian
274
- loz Lozi
275
- lub Luba-Katanga
276
- lui Luiseno
277
- lun Lunda
278
- luo Luo (Kenya and Tanzania)
279
- mac/mke mk Macedonian
280
- mad Madurese
281
- mag Magahi
282
- mai Maithili
283
- mak Makasar
284
- mlg mg Malagasy
285
- may/msa ms Malay
286
- mal Malayalam
287
- mlt ml Maltese
288
- man Mandingo
289
- mni Manipuri
290
- mno Manobo languages
291
- max Manx
292
- mao/mri mi Maori
293
- mar mr Marathi
294
- chm Mari
295
- mah Marshall
296
- mwr Marwari
297
- mas Masai
298
- myn Mayan languages
299
- men Mende
300
- mic Micmac
301
- min Minangkabau
302
- mis Miscellaneous (Other)
303
- moh Mohawk
304
- mol mo Moldavian
305
- mkh Mon-Kmer (Other)
306
- lol Mongo
307
- mon mn Mongolian
308
- mos Mossi
309
- mul Multiple languages
310
- mun Munda languages
311
- nau na Nauru
312
- nav Navajo
313
- nde Ndebele, North
314
- nbl Ndebele, South
315
- ndo Ndongo
316
- nep ne Nepali
317
- new Newari
318
- nic Niger-Kordofanian (Other)
319
- ssa Nilo-Saharan (Other)
320
- niu Niuean
321
- non Norse, Old
322
- nai North American Indian (Other)
323
- nor no Norwegian
324
- nno Norwegian (Nynorsk)
325
- nub Nubian languages
326
- nym Nyamwezi
327
- nya Nyanja
328
- nyn Nyankole
329
- nyo Nyoro
330
- nzi Nzima
331
- oji Ojibwa
332
- ori or Oriya
333
- orm om Oromo
334
- osa Osage
335
- oss Ossetic
336
- oto Otomian languages
337
- pal Pahlavi
338
- pau Palauan
339
- pli Pali
340
- pam Pampanga
341
- pag Pangasinan
342
- pan pa Panjabi
343
- pap Papiamento
344
- paa Papuan-Australian (Other)
345
- fas/per fa Persian
346
- peo Persian, Old (ca 600 - 400 B.C.)
347
- phn Phoenician
348
- pol pl Polish
349
- pon Ponape
350
- por pt Portuguese
351
- pra Prakrit languages
352
- pro Provencal, Old (to 1500)
353
- pus ps Pushto
354
- que qu Quechua
355
- roh rm Rhaeto-Romance
356
- raj Rajasthani
357
- rar Rarotongan
358
- roa Romance (Other)
359
- ron/rum ro Romanian
360
- rom Romany
361
- run rn Rundi
362
- rus ru Russian
363
- sal Salishan languages
364
- sam Samaritan Aramaic
365
- smi Sami languages
366
- smo sm Samoan
367
- sad Sandawe
368
- sag sg Sango
369
- san sa Sanskrit
370
- srd Sardinian
371
- sco Scots
372
- sel Selkup
373
- sem Semitic (Other)
374
- sr Serbian
375
- scr sh Serbo-Croatian
376
- srr Serer
377
- shn Shan
378
- sna sn Shona
379
- sid Sidamo
380
- bla Siksika
381
- snd sd Sindhi
382
- sin si Singhalese
383
- sit Sino-Tibetan (Other)
384
- sio Siouan languages
385
- sla Slavic (Other)
386
- ss Siswati
387
- slk/slo sk Slovak
388
- slv sl Slovenian
389
- sog Sogdian
390
- som so Somali
391
- son Songhai
392
- wen Sorbian languages
393
- nso Sotho, Northern
394
- sot st Sotho, Southern
395
- sai South American Indian (Other)
396
- esl/spa es Spanish
397
- suk Sukuma
398
- sux Sumerian
399
- sun su Sudanese
400
- sus Susu
401
- swa sw Swahili
402
- ssw Swazi
403
- sve/swe sv Swedish
404
- syr Syriac
405
- tgl tl Tagalog
406
- tah Tahitian
407
- tgk tg Tajik
408
- tmh Tamashek
409
- tam ta Tamil
410
- tat tt Tatar
411
- tel te Telugu
412
- ter Tereno
413
- tha th Thai
414
- bod/tib bo Tibetan
415
- tig Tigre
416
- tir ti Tigrinya
417
- tem Timne
418
- tiv Tivi
419
- tli Tlingit
420
- tog to Tonga (Nyasa)
421
- ton Tonga (Tonga Islands)
422
- tru Truk
423
- tsi Tsimshian
424
- tso ts Tsonga
425
- tsn tn Tswana
426
- tum Tumbuka
427
- tur tr Turkish
428
- ota Turkish, Ottoman (1500 - 1928)
429
- tuk tk Turkmen
430
- tyv Tuvinian
431
- twi tw Twi
432
- uga Ugaritic
433
- uig ug Uighur
434
- ukr uk Ukrainian
435
- umb Umbundu
436
- und Undetermined
437
- urd ur Urdu
438
- uzb uz Uzbek
439
- vai Vai
440
- ven Venda
441
- vie vi Vietnamese
442
- vol vo Volap�k
443
- vot Votic
444
- wak Wakashan languages
445
- wal Walamo
446
- war Waray
447
- was Washo
448
- cym/wel cy Welsh
449
- wol wo Wolof
450
- xho xh Xhosa
451
- sah Yakut
452
- yao Yao
453
- yap Yap
454
- yid yi Yiddish
455
- yor yo Yoruba
456
- zap Zapotec
457
- zen Zenaga
458
- zha za Zhuang
459
- zul zu Zulu
460
- zun Zuni
461
- __END_DATA__
63
+ aar||aa|Afar|afar
64
+ abk||ab|Abkhazian|abkhaze
65
+ ace|||Achinese|aceh
66
+ ach|||Acoli|acoli
67
+ ada|||Adangme|adangme
68
+ ady|||Adyghe; Adygei|adyghé
69
+ afa|||Afro-Asiatic languages|afro-asiatiques, langues
70
+ afh|||Afrihili|afrihili
71
+ afr||af|Afrikaans|afrikaans
72
+ ain|||Ainu|aïnou
73
+ aka||ak|Akan|akan
74
+ akk|||Akkadian|akkadien
75
+ alb|sqi|sq|Albanian|albanais
76
+ ale|||Aleut|aléoute
77
+ alg|||Algonquian languages|algonquines, langues
78
+ alt|||Southern Altai|altai du Sud
79
+ amh||am|Amharic|amharique
80
+ ang|||English, Old (ca.450-1100)|anglo-saxon (ca.450-1100)
81
+ anp|||Angika|angika
82
+ apa|||Apache languages|apaches, langues
83
+ ara||ar|Arabic|arabe
84
+ arc|||Official Aramaic (700-300 BCE); Imperial Aramaic (700-300 BCE)|araméen d'empire (700-300 BCE)
85
+ arg||an|Aragonese|aragonais
86
+ arm|hye|hy|Armenian|arménien
87
+ arn|||Mapudungun; Mapuche|mapudungun; mapuche; mapuce
88
+ arp|||Arapaho|arapaho
89
+ art|||Artificial languages|artificielles, langues
90
+ arw|||Arawak|arawak
91
+ asm||as|Assamese|assamais
92
+ ast|||Asturian; Bable; Leonese; Asturleonese|asturien; bable; léonais; asturoléonais
93
+ ath|||Athapascan languages|athapascanes, langues
94
+ aus|||Australian languages|australiennes, langues
95
+ ava||av|Avaric|avar
96
+ ave||ae|Avestan|avestique
97
+ awa|||Awadhi|awadhi
98
+ aym||ay|Aymara|aymara
99
+ aze||az|Azerbaijani|azéri
100
+ bad|||Banda languages|banda, langues
101
+ bai|||Bamileke languages|bamiléké, langues
102
+ bak||ba|Bashkir|bachkir
103
+ bal|||Baluchi|baloutchi
104
+ bam||bm|Bambara|bambara
105
+ ban|||Balinese|balinais
106
+ baq|eus|eu|Basque|basque
107
+ bas|||Basa|basa
108
+ bat|||Baltic languages|baltes, langues
109
+ bej|||Beja; Bedawiyet|bedja
110
+ bel||be|Belarusian|biélorusse
111
+ bem|||Bemba|bemba
112
+ ben||bn|Bengali|bengali
113
+ ber|||Berber languages|berbères, langues
114
+ bho|||Bhojpuri|bhojpuri
115
+ bih||bh|Bihari languages|langues biharis
116
+ bik|||Bikol|bikol
117
+ bin|||Bini; Edo|bini; edo
118
+ bis||bi|Bislama|bichlamar
119
+ bla|||Siksika|blackfoot
120
+ bnt|||Bantu (Other)|bantoues, autres langues
121
+ bos||bs|Bosnian|bosniaque
122
+ bra|||Braj|braj
123
+ bre||br|Breton|breton
124
+ btk|||Batak languages|batak, langues
125
+ bua|||Buriat|bouriate
126
+ bug|||Buginese|bugi
127
+ bul||bg|Bulgarian|bulgare
128
+ bur|mya|my|Burmese|birman
129
+ byn|||Blin; Bilin|blin; bilen
130
+ cad|||Caddo|caddo
131
+ cai|||Central American Indian languages|amérindiennes de L'Amérique centrale, langues
132
+ car|||Galibi Carib|karib; galibi; carib
133
+ cat||ca|Catalan; Valencian|catalan; valencien
134
+ cau|||Caucasian languages|caucasiennes, langues
135
+ ceb|||Cebuano|cebuano
136
+ cel|||Celtic languages|celtiques, langues; celtes, langues
137
+ cha||ch|Chamorro|chamorro
138
+ chb|||Chibcha|chibcha
139
+ che||ce|Chechen|tchétchène
140
+ chg|||Chagatai|djaghataï
141
+ chi|zho|zh|Chinese|chinois
142
+ chk|||Chuukese|chuuk
143
+ chm|||Mari|mari
144
+ chn|||Chinook jargon|chinook, jargon
145
+ cho|||Choctaw|choctaw
146
+ chp|||Chipewyan; Dene Suline|chipewyan
147
+ chr|||Cherokee|cherokee
148
+ chu||cu|Church Slavic; Old Slavonic; Church Slavonic; Old Bulgarian; Old Church Slavonic|slavon d'église; vieux slave; slavon liturgique; vieux bulgare
149
+ chv||cv|Chuvash|tchouvache
150
+ chy|||Cheyenne|cheyenne
151
+ cmc|||Chamic languages|chames, langues
152
+ cop|||Coptic|copte
153
+ cor||kw|Cornish|cornique
154
+ cos||co|Corsican|corse
155
+ cpe|||Creoles and pidgins, English based|créoles et pidgins basés sur l'anglais
156
+ cpf|||Creoles and pidgins, French-based |créoles et pidgins basés sur le français
157
+ cpp|||Creoles and pidgins, Portuguese-based |créoles et pidgins basés sur le portugais
158
+ cre||cr|Cree|cree
159
+ crh|||Crimean Tatar; Crimean Turkish|tatar de Crimé
160
+ crp|||Creoles and pidgins |créoles et pidgins
161
+ csb|||Kashubian|kachoube
162
+ cus|||Cushitic languages|couchitiques, langues
163
+ cze|ces|cs|Czech|tchèque
164
+ dak|||Dakota|dakota
165
+ dan||da|Danish|danois
166
+ dar|||Dargwa|dargwa
167
+ day|||Land Dayak languages|dayak, langues
168
+ del|||Delaware|delaware
169
+ den|||Slave (Athapascan)|esclave (athapascan)
170
+ dgr|||Dogrib|dogrib
171
+ din|||Dinka|dinka
172
+ div||dv|Divehi; Dhivehi; Maldivian|maldivien
173
+ doi|||Dogri|dogri
174
+ dra|||Dravidian languages|dravidiennes, langues
175
+ dsb|||Lower Sorbian|bas-sorabe
176
+ dua|||Duala|douala
177
+ dum|||Dutch, Middle (ca.1050-1350)|néerlandais moyen (ca. 1050-1350)
178
+ dut|nld|nl|Dutch; Flemish|néerlandais; flamand
179
+ dyu|||Dyula|dioula
180
+ dzo||dz|Dzongkha|dzongkha
181
+ efi|||Efik|efik
182
+ egy|||Egyptian (Ancient)|égyptien
183
+ eka|||Ekajuk|ekajuk
184
+ elx|||Elamite|élamite
185
+ eng||en|English|anglais
186
+ enm|||English, Middle (1100-1500)|anglais moyen (1100-1500)
187
+ epo||eo|Esperanto|espéranto
188
+ est||et|Estonian|estonien
189
+ ewe||ee|Ewe|éwé
190
+ ewo|||Ewondo|éwondo
191
+ fan|||Fang|fang
192
+ fao||fo|Faroese|féroïen
193
+ fat|||Fanti|fanti
194
+ fij||fj|Fijian|fidjien
195
+ fil|||Filipino; Pilipino|filipino; pilipino
196
+ fin||fi|Finnish|finnois
197
+ fiu|||Finno-Ugrian languages|finno-ougriennes, langues
198
+ fon|||Fon|fon
199
+ fre|fra|fr|French|français
200
+ frm|||French, Middle (ca.1400-1600)|français moyen (1400-1600)
201
+ fro|||French, Old (842-ca.1400)|français ancien (842-ca.1400)
202
+ frr|||Northern Frisian|frison septentrional
203
+ frs|||Eastern Frisian|frison oriental
204
+ fry||fy|Western Frisian|frison occidental
205
+ ful||ff|Fulah|peul
206
+ fur|||Friulian|frioulan
207
+ gaa|||Ga|ga
208
+ gay|||Gayo|gayo
209
+ gba|||Gbaya|gbaya
210
+ gem|||Germanic languages|germaniques, langues
211
+ geo|kat|ka|Georgian|géorgien
212
+ ger|deu|de|German|allemand
213
+ gez|||Geez|guèze
214
+ gil|||Gilbertese|kiribati
215
+ gla||gd|Gaelic; Scottish Gaelic|gaélique; gaélique écossais
216
+ gle||ga|Irish|irlandais
217
+ glg||gl|Galician|galicien
218
+ glv||gv|Manx|manx; mannois
219
+ gmh|||German, Middle High (ca.1050-1500)|allemand, moyen haut (ca. 1050-1500)
220
+ goh|||German, Old High (ca.750-1050)|allemand, vieux haut (ca. 750-1050)
221
+ gon|||Gondi|gond
222
+ gor|||Gorontalo|gorontalo
223
+ got|||Gothic|gothique
224
+ grb|||Grebo|grebo
225
+ grc|||Greek, Ancient (to 1453)|grec ancien (jusqu'à 1453)
226
+ gre|ell|el|Greek, Modern (1453-)|grec moderne (après 1453)
227
+ grn||gn|Guarani|guarani
228
+ gsw|||Swiss German; Alemannic; Alsatian|suisse alémanique; alémanique; alsacien
229
+ guj||gu|Gujarati|goudjrati
230
+ gwi|||Gwich'in|gwich'in
231
+ hai|||Haida|haida
232
+ hat||ht|Haitian; Haitian Creole|haïtien; créole haïtien
233
+ hau||ha|Hausa|haoussa
234
+ haw|||Hawaiian|hawaïen
235
+ heb||he|Hebrew|hébreu
236
+ her||hz|Herero|herero
237
+ hil|||Hiligaynon|hiligaynon
238
+ him|||Himachali languages; Western Pahari languages|langues himachalis; langues paharis occidentales
239
+ hin||hi|Hindi|hindi
240
+ hit|||Hittite|hittite
241
+ hmn|||Hmong|hmong
242
+ hmo||ho|Hiri Motu|hiri motu
243
+ hrv||hr|Croatian|croate
244
+ hsb|||Upper Sorbian|haut-sorabe
245
+ hun||hu|Hungarian|hongrois
246
+ hup|||Hupa|hupa
247
+ iba|||Iban|iban
248
+ ibo||ig|Igbo|igbo
249
+ ice|isl|is|Icelandic|islandais
250
+ ido||io|Ido|ido
251
+ iii||ii|Sichuan Yi; Nuosu|yi de Sichuan
252
+ ijo|||Ijo languages|ijo, langues
253
+ iku||iu|Inuktitut|inuktitut
254
+ ile||ie|Interlingue; Occidental|interlingue
255
+ ilo|||Iloko|ilocano
256
+ ina||ia|Interlingua (International Auxiliary Language Association)|interlingua (langue auxiliaire internationale)
257
+ inc|||Indic languages|indo-aryennes, langues
258
+ ind||id|Indonesian|indonésien
259
+ ine|||Indo-European languages|indo-européennes, langues
260
+ inh|||Ingush|ingouche
261
+ ipk||ik|Inupiaq|inupiaq
262
+ ira|||Iranian languages|iraniennes, langues
263
+ iro|||Iroquoian languages|iroquoises, langues
264
+ ita||it|Italian|italien
265
+ jav||jv|Javanese|javanais
266
+ jbo|||Lojban|lojban
267
+ jpn||ja|Japanese|japonais
268
+ jpr|||Judeo-Persian|judéo-persan
269
+ jrb|||Judeo-Arabic|judéo-arabe
270
+ kaa|||Kara-Kalpak|karakalpak
271
+ kab|||Kabyle|kabyle
272
+ kac|||Kachin; Jingpho|kachin; jingpho
273
+ kal||kl|Kalaallisut; Greenlandic|groenlandais
274
+ kam|||Kamba|kamba
275
+ kan||kn|Kannada|kannada
276
+ kar|||Karen languages|karen, langues
277
+ kas||ks|Kashmiri|kashmiri
278
+ kau||kr|Kanuri|kanouri
279
+ kaw|||Kawi|kawi
280
+ kaz||kk|Kazakh|kazakh
281
+ kbd|||Kabardian|kabardien
282
+ kha|||Khasi|khasi
283
+ khi|||Khoisan languages|khoïsan, langues
284
+ khm||km|Central Khmer|khmer central
285
+ kho|||Khotanese; Sakan|khotanais; sakan
286
+ kik||ki|Kikuyu; Gikuyu|kikuyu
287
+ kin||rw|Kinyarwanda|rwanda
288
+ kir||ky|Kirghiz; Kyrgyz|kirghiz
289
+ kmb|||Kimbundu|kimbundu
290
+ kok|||Konkani|konkani
291
+ kom||kv|Komi|kom
292
+ kon||kg|Kongo|kongo
293
+ kor||ko|Korean|coréen
294
+ kos|||Kosraean|kosrae
295
+ kpe|||Kpelle|kpellé
296
+ krc|||Karachay-Balkar|karatchai balkar
297
+ krl|||Karelian|carélien
298
+ kro|||Kru languages|krou, langues
299
+ kru|||Kurukh|kurukh
300
+ kua||kj|Kuanyama; Kwanyama|kuanyama; kwanyama
301
+ kum|||Kumyk|koumyk
302
+ kur||ku|Kurdish|kurde
303
+ kut|||Kutenai|kutenai
304
+ lad|||Ladino|judéo-espagnol
305
+ lah|||Lahnda|lahnda
306
+ lam|||Lamba|lamba
307
+ lao||lo|Lao|lao
308
+ lat||la|Latin|latin
309
+ lav||lv|Latvian|letton
310
+ lez|||Lezghian|lezghien
311
+ lim||li|Limburgan; Limburger; Limburgish|limbourgeois
312
+ lin||ln|Lingala|lingala
313
+ lit||lt|Lithuanian|lituanien
314
+ lol|||Mongo|mongo
315
+ loz|||Lozi|lozi
316
+ ltz||lb|Luxembourgish; Letzeburgesch|luxembourgeois
317
+ lua|||Luba-Lulua|luba-lulua
318
+ lub||lu|Luba-Katanga|luba-katanga
319
+ lug||lg|Ganda|ganda
320
+ lui|||Luiseno|luiseno
321
+ lun|||Lunda|lunda
322
+ luo|||Luo (Kenya and Tanzania)|luo (Kenya et Tanzanie)
323
+ lus|||Lushai|lushai
324
+ mac|mkd|mk|Macedonian|macédonien
325
+ mad|||Madurese|madourais
326
+ mag|||Magahi|magahi
327
+ mah||mh|Marshallese|marshall
328
+ mai|||Maithili|maithili
329
+ mak|||Makasar|makassar
330
+ mal||ml|Malayalam|malayalam
331
+ man|||Mandingo|mandingue
332
+ mao|mri|mi|Maori|maori
333
+ map|||Austronesian languages|austronésiennes, langues
334
+ mar||mr|Marathi|marathe
335
+ mas|||Masai|massaï
336
+ may|msa|ms|Malay|malais
337
+ mdf|||Moksha|moksa
338
+ mdr|||Mandar|mandar
339
+ men|||Mende|mendé
340
+ mga|||Irish, Middle (900-1200)|irlandais moyen (900-1200)
341
+ mic|||Mi'kmaq; Micmac|mi'kmaq; micmac
342
+ min|||Minangkabau|minangkabau
343
+ mis|||Uncoded languages|langues non codées
344
+ mkh|||Mon-Khmer languages|môn-khmer, langues
345
+ mlg||mg|Malagasy|malgache
346
+ mlt||mt|Maltese|maltais
347
+ mnc|||Manchu|mandchou
348
+ mni|||Manipuri|manipuri
349
+ mno|||Manobo languages|manobo, langues
350
+ moh|||Mohawk|mohawk
351
+ mon||mn|Mongolian|mongol
352
+ mos|||Mossi|moré
353
+ mul|||Multiple languages|multilingue
354
+ mun|||Munda languages|mounda, langues
355
+ mus|||Creek|muskogee
356
+ mwl|||Mirandese|mirandais
357
+ mwr|||Marwari|marvari
358
+ myn|||Mayan languages|maya, langues
359
+ myv|||Erzya|erza
360
+ nah|||Nahuatl languages|nahuatl, langues
361
+ nai|||North American Indian languages|nord-amérindiennes, langues
362
+ nap|||Neapolitan|napolitain
363
+ nau||na|Nauru|nauruan
364
+ nav||nv|Navajo; Navaho|navaho
365
+ nbl||nr|Ndebele, South; South Ndebele|ndébélé du Sud
366
+ nde||nd|Ndebele, North; North Ndebele|ndébélé du Nord
367
+ ndo||ng|Ndonga|ndonga
368
+ nds|||Low German; Low Saxon; German, Low; Saxon, Low|bas allemand; bas saxon; allemand, bas; saxon, bas
369
+ nep||ne|Nepali|népalais
370
+ new|||Nepal Bhasa; Newari|nepal bhasa; newari
371
+ nia|||Nias|nias
372
+ nic|||Niger-Kordofanian languages|nigéro-kordofaniennes, langues
373
+ niu|||Niuean|niué
374
+ nno||nn|Norwegian Nynorsk; Nynorsk, Norwegian|norvégien nynorsk; nynorsk, norvégien
375
+ nob||nb|Bokmål, Norwegian; Norwegian Bokmål|norvégien bokmål
376
+ nog|||Nogai|nogaï; nogay
377
+ non|||Norse, Old|norrois, vieux
378
+ nor||no|Norwegian|norvégien
379
+ nqo|||N'Ko|n'ko
380
+ nso|||Pedi; Sepedi; Northern Sotho|pedi; sepedi; sotho du Nord
381
+ nub|||Nubian languages|nubiennes, langues
382
+ nwc|||Classical Newari; Old Newari; Classical Nepal Bhasa|newari classique
383
+ nya||ny|Chichewa; Chewa; Nyanja|chichewa; chewa; nyanja
384
+ nym|||Nyamwezi|nyamwezi
385
+ nyn|||Nyankole|nyankolé
386
+ nyo|||Nyoro|nyoro
387
+ nzi|||Nzima|nzema
388
+ oci||oc|Occitan (post 1500); Provençal|occitan (après 1500); provençal
389
+ oji||oj|Ojibwa|ojibwa
390
+ ori||or|Oriya|oriya
391
+ orm||om|Oromo|galla
392
+ osa|||Osage|osage
393
+ oss||os|Ossetian; Ossetic|ossète
394
+ ota|||Turkish, Ottoman (1500-1928)|turc ottoman (1500-1928)
395
+ oto|||Otomian languages|otomi, langues
396
+ paa|||Papuan languages|papoues, langues
397
+ pag|||Pangasinan|pangasinan
398
+ pal|||Pahlavi|pahlavi
399
+ pam|||Pampanga; Kapampangan|pampangan
400
+ pan||pa|Panjabi; Punjabi|pendjabi
401
+ pap|||Papiamento|papiamento
402
+ pau|||Palauan|palau
403
+ peo|||Persian, Old (ca.600-400 B.C.)|perse, vieux (ca. 600-400 av. J.-C.)
404
+ per|fas|fa|Persian|persan
405
+ phi|||Philippine languages|philippines, langues
406
+ phn|||Phoenician|phénicien
407
+ pli||pi|Pali|pali
408
+ pol||pl|Polish|polonais
409
+ pon|||Pohnpeian|pohnpei
410
+ por||pt|Portuguese|portugais
411
+ pra|||Prakrit languages|prâkrit, langues
412
+ pro|||Provençal, Old (to 1500)|provençal ancien (jusqu'à 1500)
413
+ pus||ps|Pushto; Pashto|pachto
414
+ qaa-qtz|||Reserved for local use|réservée à l'usage local
415
+ que||qu|Quechua|quechua
416
+ raj|||Rajasthani|rajasthani
417
+ rap|||Rapanui|rapanui
418
+ rar|||Rarotongan; Cook Islands Maori|rarotonga; maori des îles Cook
419
+ roa|||Romance languages|romanes, langues
420
+ roh||rm|Romansh|romanche
421
+ rom|||Romany|tsigane
422
+ rum|ron|ro|Romanian; Moldavian; Moldovan|roumain; moldave
423
+ run||rn|Rundi|rundi
424
+ rup|||Aromanian; Arumanian; Macedo-Romanian|aroumain; macédo-roumain
425
+ rus||ru|Russian|russe
426
+ sad|||Sandawe|sandawe
427
+ sag||sg|Sango|sango
428
+ sah|||Yakut|iakoute
429
+ sai|||South American Indian (Other)|indiennes d'Amérique du Sud, autres langues
430
+ sal|||Salishan languages|salishennes, langues
431
+ sam|||Samaritan Aramaic|samaritain
432
+ san||sa|Sanskrit|sanskrit
433
+ sas|||Sasak|sasak
434
+ sat|||Santali|santal
435
+ scn|||Sicilian|sicilien
436
+ sco|||Scots|écossais
437
+ sel|||Selkup|selkoupe
438
+ sem|||Semitic languages|sémitiques, langues
439
+ sga|||Irish, Old (to 900)|irlandais ancien (jusqu'à 900)
440
+ sgn|||Sign Languages|langues des signes
441
+ shn|||Shan|chan
442
+ sid|||Sidamo|sidamo
443
+ sin||si|Sinhala; Sinhalese|singhalais
444
+ sio|||Siouan languages|sioux, langues
445
+ sit|||Sino-Tibetan languages|sino-tibétaines, langues
446
+ sla|||Slavic languages|slaves, langues
447
+ slo|slk|sk|Slovak|slovaque
448
+ slv||sl|Slovenian|slovène
449
+ sma|||Southern Sami|sami du Sud
450
+ sme||se|Northern Sami|sami du Nord
451
+ smi|||Sami languages|sames, langues
452
+ smj|||Lule Sami|sami de Lule
453
+ smn|||Inari Sami|sami d'Inari
454
+ smo||sm|Samoan|samoan
455
+ sms|||Skolt Sami|sami skolt
456
+ sna||sn|Shona|shona
457
+ snd||sd|Sindhi|sindhi
458
+ snk|||Soninke|soninké
459
+ sog|||Sogdian|sogdien
460
+ som||so|Somali|somali
461
+ son|||Songhai languages|songhai, langues
462
+ sot||st|Sotho, Southern|sotho du Sud
463
+ spa||es|Spanish; Castilian|espagnol; castillan
464
+ srd||sc|Sardinian|sarde
465
+ srn|||Sranan Tongo|sranan tongo
466
+ srp||sr|Serbian|serbe
467
+ srr|||Serer|sérère
468
+ ssa|||Nilo-Saharan languages|nilo-sahariennes, langues
469
+ ssw||ss|Swati|swati
470
+ suk|||Sukuma|sukuma
471
+ sun||su|Sundanese|soundanais
472
+ sus|||Susu|soussou
473
+ sux|||Sumerian|sumérien
474
+ swa||sw|Swahili|swahili
475
+ swe||sv|Swedish|suédois
476
+ syc|||Classical Syriac|syriaque classique
477
+ syr|||Syriac|syriaque
478
+ tah||ty|Tahitian|tahitien
479
+ tai|||Tai languages|tai, langues
480
+ tam||ta|Tamil|tamoul
481
+ tat||tt|Tatar|tatar
482
+ tel||te|Telugu|télougou
483
+ tem|||Timne|temne
484
+ ter|||Tereno|tereno
485
+ tet|||Tetum|tetum
486
+ tgk||tg|Tajik|tadjik
487
+ tgl||tl|Tagalog|tagalog
488
+ tha||th|Thai|thaï
489
+ tib|bod|bo|Tibetan|tibétain
490
+ tig|||Tigre|tigré
491
+ tir||ti|Tigrinya|tigrigna
492
+ tiv|||Tiv|tiv
493
+ tkl|||Tokelau|tokelau
494
+ tlh|||Klingon; tlhIngan-Hol|klingon
495
+ tli|||Tlingit|tlingit
496
+ tmh|||Tamashek|tamacheq
497
+ tog|||Tonga (Nyasa)|tonga (Nyasa)
498
+ ton||to|Tonga (Tonga Islands)|tongan (Îles Tonga)
499
+ tpi|||Tok Pisin|tok pisin
500
+ tsi|||Tsimshian|tsimshian
501
+ tsn||tn|Tswana|tswana
502
+ tso||ts|Tsonga|tsonga
503
+ tuk||tk|Turkmen|turkmène
504
+ tum|||Tumbuka|tumbuka
505
+ tup|||Tupi languages|tupi, langues
506
+ tur||tr|Turkish|turc
507
+ tut|||Altaic languages|altaïques, langues
508
+ tvl|||Tuvalu|tuvalu
509
+ twi||tw|Twi|twi
510
+ tyv|||Tuvinian|touva
511
+ udm|||Udmurt|oudmourte
512
+ uga|||Ugaritic|ougaritique
513
+ uig||ug|Uighur; Uyghur|ouïgour
514
+ ukr||uk|Ukrainian|ukrainien
515
+ umb|||Umbundu|umbundu
516
+ und|||Undetermined|indéterminée
517
+ urd||ur|Urdu|ourdou
518
+ uzb||uz|Uzbek|ouszbek
519
+ vai|||Vai|vaï
520
+ ven||ve|Venda|venda
521
+ vie||vi|Vietnamese|vietnamien
522
+ vol||vo|Volapük|volapük
523
+ vot|||Votic|vote
524
+ wak|||Wakashan languages|wakashanes, langues
525
+ wal|||Walamo|walamo
526
+ war|||Waray|waray
527
+ was|||Washo|washo
528
+ wel|cym|cy|Welsh|gallois
529
+ wen|||Sorbian languages|sorabes, langues
530
+ wln||wa|Walloon|wallon
531
+ wol||wo|Wolof|wolof
532
+ xal|||Kalmyk; Oirat|kalmouk; oïrat
533
+ xho||xh|Xhosa|xhosa
534
+ yao|||Yao|yao
535
+ yap|||Yapese|yapois
536
+ yid||yi|Yiddish|yiddish
537
+ yor||yo|Yoruba|yoruba
538
+ ypk|||Yupik languages|yupik, langues
539
+ zap|||Zapotec|zapotèque
540
+ zbl|||Blissymbols; Blissymbolics; Bliss|symboles Bliss; Bliss
541
+ zen|||Zenaga|zenaga
542
+ zha||za|Zhuang; Chuang|zhuang; chuang
543
+ znd|||Zande languages|zandé, langues
544
+ zul||zu|Zulu|zoulou
545
+ zun|||Zuni|zuni
546
+ zxx|||No linguistic content; Not applicable|pas de contenu linguistique; non applicable
547
+ zza|||Zaza; Dimili; Dimli; Kirdki; Kirmanjki; Zazaki|zaza; dimili; dimli; kirdki; kirmanjki; zazaki