linguistics 1.0.9 → 2.0.0
Sign up to get free protection for your applications and to get access to all the features.
- data.tar.gz.sig +0 -0
- data/.gemtest +0 -0
- data/ChangeLog +849 -342
- data/History.rdoc +11 -0
- data/LICENSE +9 -9
- data/Manifest.txt +44 -0
- data/README.rdoc +226 -0
- data/Rakefile +32 -349
- data/examples/endocs.rb +272 -0
- data/examples/generalize_sentence.rb +2 -1
- data/examples/klingon.rb +22 -0
- data/lib/linguistics.rb +130 -292
- data/lib/linguistics/en.rb +337 -1628
- data/lib/linguistics/en/articles.rb +138 -0
- data/lib/linguistics/en/conjugation.rb +2245 -0
- data/lib/linguistics/en/conjunctions.rb +202 -0
- data/lib/linguistics/en/{infinitive.rb → infinitives.rb} +41 -55
- data/lib/linguistics/en/linkparser.rb +41 -49
- data/lib/linguistics/en/numbers.rb +483 -0
- data/lib/linguistics/en/participles.rb +33 -0
- data/lib/linguistics/en/pluralization.rb +810 -0
- data/lib/linguistics/en/stemmer.rb +75 -0
- data/lib/linguistics/en/titlecase.rb +121 -0
- data/lib/linguistics/en/wordnet.rb +63 -97
- data/lib/linguistics/inflector.rb +89 -0
- data/lib/linguistics/iso639.rb +534 -448
- data/lib/linguistics/languagebehavior.rb +36 -0
- data/lib/linguistics/monkeypatches.rb +42 -0
- data/spec/lib/constants.rb +15 -0
- data/spec/lib/helpers.rb +38 -0
- data/spec/linguistics/en/articles_spec.rb +797 -0
- data/spec/linguistics/en/conjugation_spec.rb +2083 -0
- data/spec/linguistics/en/conjunctions_spec.rb +154 -0
- data/spec/linguistics/en/infinitives_spec.rb +518 -0
- data/spec/linguistics/en/linkparser_spec.rb +66 -0
- data/spec/linguistics/en/numbers_spec.rb +1295 -0
- data/spec/linguistics/en/participles_spec.rb +55 -0
- data/spec/linguistics/en/pluralization_spec.rb +4636 -0
- data/spec/linguistics/en/stemmer_spec.rb +72 -0
- data/spec/linguistics/en/titlecase_spec.rb +841 -0
- data/spec/linguistics/en/wordnet_spec.rb +85 -0
- data/spec/linguistics/en_spec.rb +45 -167
- data/spec/linguistics/inflector_spec.rb +40 -0
- data/spec/linguistics/iso639_spec.rb +49 -53
- data/spec/linguistics/monkeypatches_spec.rb +40 -0
- data/spec/linguistics_spec.rb +46 -76
- metadata +241 -113
- metadata.gz.sig +0 -0
- data/README +0 -166
- data/README.english +0 -245
- data/rake/191_compat.rb +0 -26
- data/rake/dependencies.rb +0 -76
- data/rake/documentation.rb +0 -123
- data/rake/helpers.rb +0 -502
- data/rake/hg.rb +0 -318
- data/rake/manual.rb +0 -787
- data/rake/packaging.rb +0 -129
- data/rake/publishing.rb +0 -341
- data/rake/style.rb +0 -62
- data/rake/svn.rb +0 -668
- data/rake/testing.rb +0 -152
- data/rake/verifytask.rb +0 -64
- data/tests/en/infinitive.tests.rb +0 -207
- data/tests/en/inflect.tests.rb +0 -1389
- data/tests/en/lafcadio.tests.rb +0 -77
- data/tests/en/linkparser.tests.rb +0 -42
- data/tests/en/lprintf.tests.rb +0 -77
- data/tests/en/titlecase.tests.rb +0 -73
- data/tests/en/wordnet.tests.rb +0 -95
data/lib/linguistics/iso639.rb
CHANGED
@@ -1,461 +1,547 @@
|
|
1
1
|
#!/usr/bin/ruby
|
2
|
-
#coding: utf-8
|
2
|
+
# coding: utf-8
|
3
3
|
|
4
|
-
|
5
|
-
|
6
|
-
# ISO639-1 and ISO639-2
|
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>:
|
11
|
-
# The English-language
|
12
|
-
#
|
13
|
-
#
|
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
|
-
#
|
17
|
+
# Entries for 'ja' and 'en':
|
18
18
|
#
|
19
|
-
|
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
|
-
|
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
|
-
#
|
25
|
-
#
|
26
|
-
|
27
|
-
|
28
|
-
|
29
|
-
|
30
|
-
|
31
|
-
|
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
|
-
|
34
|
-
|
35
|
-
|
55
|
+
LANGUAGE_CODES[ bib_alpha3.to_sym ] = entry
|
56
|
+
LANGUAGE_CODES[ alpha2.to_sym ] = entry if alpha2
|
57
|
+
end
|
36
58
|
|
37
|
-
|
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
|
-
|
58
|
-
|
59
|
-
|
60
|
-
|
61
|
-
|
62
|
-
|
63
|
-
|
64
|
-
|
65
|
-
|
66
|
-
|
67
|
-
|
68
|
-
|
69
|
-
|
70
|
-
|
71
|
-
|
72
|
-
|
73
|
-
|
74
|
-
|
75
|
-
|
76
|
-
|
77
|
-
|
78
|
-
|
79
|
-
|
80
|
-
|
81
|
-
|
82
|
-
|
83
|
-
|
84
|
-
|
85
|
-
|
86
|
-
|
87
|
-
|
88
|
-
|
89
|
-
|
90
|
-
|
91
|
-
|
92
|
-
|
93
|
-
|
94
|
-
bad
|
95
|
-
|
96
|
-
|
97
|
-
|
98
|
-
|
99
|
-
|
100
|
-
|
101
|
-
|
102
|
-
|
103
|
-
|
104
|
-
|
105
|
-
|
106
|
-
|
107
|
-
|
108
|
-
|
109
|
-
|
110
|
-
|
111
|
-
|
112
|
-
|
113
|
-
|
114
|
-
|
115
|
-
|
116
|
-
|
117
|
-
|
118
|
-
|
119
|
-
|
120
|
-
|
121
|
-
|
122
|
-
|
123
|
-
|
124
|
-
|
125
|
-
|
126
|
-
|
127
|
-
|
128
|
-
|
129
|
-
|
130
|
-
|
131
|
-
|
132
|
-
|
133
|
-
|
134
|
-
|
135
|
-
|
136
|
-
|
137
|
-
|
138
|
-
|
139
|
-
|
140
|
-
|
141
|
-
|
142
|
-
|
143
|
-
|
144
|
-
|
145
|
-
|
146
|
-
|
147
|
-
|
148
|
-
|
149
|
-
|
150
|
-
|
151
|
-
|
152
|
-
|
153
|
-
|
154
|
-
|
155
|
-
|
156
|
-
|
157
|
-
|
158
|
-
|
159
|
-
|
160
|
-
|
161
|
-
|
162
|
-
|
163
|
-
|
164
|
-
|
165
|
-
|
166
|
-
|
167
|
-
|
168
|
-
|
169
|
-
|
170
|
-
|
171
|
-
|
172
|
-
|
173
|
-
|
174
|
-
|
175
|
-
|
176
|
-
|
177
|
-
|
178
|
-
|
179
|
-
|
180
|
-
|
181
|
-
|
182
|
-
|
183
|
-
|
184
|
-
|
185
|
-
|
186
|
-
|
187
|
-
|
188
|
-
|
189
|
-
|
190
|
-
|
191
|
-
|
192
|
-
|
193
|
-
|
194
|
-
|
195
|
-
|
196
|
-
|
197
|
-
|
198
|
-
|
199
|
-
|
200
|
-
|
201
|
-
|
202
|
-
|
203
|
-
|
204
|
-
|
205
|
-
|
206
|
-
|
207
|
-
|
208
|
-
|
209
|
-
|
210
|
-
|
211
|
-
|
212
|
-
|
213
|
-
|
214
|
-
|
215
|
-
|
216
|
-
|
217
|
-
|
218
|
-
|
219
|
-
|
220
|
-
|
221
|
-
|
222
|
-
|
223
|
-
|
224
|
-
|
225
|
-
|
226
|
-
|
227
|
-
|
228
|
-
|
229
|
-
|
230
|
-
|
231
|
-
|
232
|
-
|
233
|
-
|
234
|
-
|
235
|
-
|
236
|
-
|
237
|
-
|
238
|
-
|
239
|
-
|
240
|
-
|
241
|
-
|
242
|
-
|
243
|
-
|
244
|
-
|
245
|
-
|
246
|
-
|
247
|
-
|
248
|
-
|
249
|
-
|
250
|
-
|
251
|
-
|
252
|
-
|
253
|
-
|
254
|
-
|
255
|
-
|
256
|
-
|
257
|
-
|
258
|
-
|
259
|
-
|
260
|
-
|
261
|
-
|
262
|
-
|
263
|
-
|
264
|
-
|
265
|
-
|
266
|
-
|
267
|
-
|
268
|
-
|
269
|
-
|
270
|
-
|
271
|
-
|
272
|
-
|
273
|
-
|
274
|
-
|
275
|
-
|
276
|
-
|
277
|
-
|
278
|
-
|
279
|
-
|
280
|
-
|
281
|
-
|
282
|
-
|
283
|
-
|
284
|
-
|
285
|
-
|
286
|
-
|
287
|
-
|
288
|
-
|
289
|
-
|
290
|
-
|
291
|
-
|
292
|
-
|
293
|
-
|
294
|
-
|
295
|
-
|
296
|
-
|
297
|
-
|
298
|
-
|
299
|
-
|
300
|
-
|
301
|
-
|
302
|
-
|
303
|
-
|
304
|
-
|
305
|
-
|
306
|
-
|
307
|
-
|
308
|
-
|
309
|
-
|
310
|
-
|
311
|
-
|
312
|
-
|
313
|
-
|
314
|
-
|
315
|
-
|
316
|
-
|
317
|
-
|
318
|
-
|
319
|
-
|
320
|
-
|
321
|
-
|
322
|
-
|
323
|
-
|
324
|
-
|
325
|
-
|
326
|
-
|
327
|
-
|
328
|
-
|
329
|
-
|
330
|
-
|
331
|
-
|
332
|
-
|
333
|
-
|
334
|
-
|
335
|
-
|
336
|
-
|
337
|
-
|
338
|
-
|
339
|
-
|
340
|
-
|
341
|
-
|
342
|
-
|
343
|
-
|
344
|
-
|
345
|
-
|
346
|
-
|
347
|
-
|
348
|
-
|
349
|
-
|
350
|
-
|
351
|
-
|
352
|
-
|
353
|
-
|
354
|
-
|
355
|
-
|
356
|
-
|
357
|
-
|
358
|
-
|
359
|
-
|
360
|
-
|
361
|
-
|
362
|
-
|
363
|
-
|
364
|
-
|
365
|
-
|
366
|
-
|
367
|
-
|
368
|
-
|
369
|
-
|
370
|
-
|
371
|
-
|
372
|
-
|
373
|
-
|
374
|
-
|
375
|
-
|
376
|
-
|
377
|
-
|
378
|
-
|
379
|
-
|
380
|
-
|
381
|
-
|
382
|
-
|
383
|
-
|
384
|
-
|
385
|
-
|
386
|
-
|
387
|
-
|
388
|
-
|
389
|
-
|
390
|
-
|
391
|
-
|
392
|
-
|
393
|
-
|
394
|
-
|
395
|
-
|
396
|
-
|
397
|
-
|
398
|
-
|
399
|
-
|
400
|
-
|
401
|
-
|
402
|
-
|
403
|
-
|
404
|
-
|
405
|
-
|
406
|
-
|
407
|
-
|
408
|
-
|
409
|
-
|
410
|
-
|
411
|
-
|
412
|
-
|
413
|
-
|
414
|
-
|
415
|
-
|
416
|
-
|
417
|
-
|
418
|
-
|
419
|
-
|
420
|
-
|
421
|
-
|
422
|
-
|
423
|
-
|
424
|
-
|
425
|
-
|
426
|
-
|
427
|
-
|
428
|
-
|
429
|
-
|
430
|
-
|
431
|
-
|
432
|
-
|
433
|
-
|
434
|
-
|
435
|
-
|
436
|
-
|
437
|
-
|
438
|
-
|
439
|
-
|
440
|
-
|
441
|
-
|
442
|
-
|
443
|
-
|
444
|
-
|
445
|
-
|
446
|
-
|
447
|
-
|
448
|
-
|
449
|
-
|
450
|
-
|
451
|
-
|
452
|
-
|
453
|
-
|
454
|
-
|
455
|
-
|
456
|
-
|
457
|
-
|
458
|
-
|
459
|
-
|
460
|
-
|
461
|
-
|
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
|