opener-tokenizer-base 1.0.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (44) hide show
  1. checksums.yaml +7 -0
  2. data/README.md +148 -0
  3. data/bin/tokenizer-base +5 -0
  4. data/bin/tokenizer-de +5 -0
  5. data/bin/tokenizer-en +5 -0
  6. data/bin/tokenizer-es +5 -0
  7. data/bin/tokenizer-fr +5 -0
  8. data/bin/tokenizer-it +5 -0
  9. data/bin/tokenizer-nl +5 -0
  10. data/core/lib/Data/OptList.pm +256 -0
  11. data/core/lib/Params/Util.pm +866 -0
  12. data/core/lib/Sub/Exporter.pm +1101 -0
  13. data/core/lib/Sub/Exporter/Cookbook.pod +309 -0
  14. data/core/lib/Sub/Exporter/Tutorial.pod +280 -0
  15. data/core/lib/Sub/Exporter/Util.pm +354 -0
  16. data/core/lib/Sub/Install.pm +329 -0
  17. data/core/lib/Time/Stamp.pm +808 -0
  18. data/core/load-prefixes.pl +43 -0
  19. data/core/nonbreaking_prefixes/abbreviation_list.kaf +0 -0
  20. data/core/nonbreaking_prefixes/abbreviation_list.txt +444 -0
  21. data/core/nonbreaking_prefixes/nonbreaking_prefix.ca +533 -0
  22. data/core/nonbreaking_prefixes/nonbreaking_prefix.de +781 -0
  23. data/core/nonbreaking_prefixes/nonbreaking_prefix.el +448 -0
  24. data/core/nonbreaking_prefixes/nonbreaking_prefix.en +564 -0
  25. data/core/nonbreaking_prefixes/nonbreaking_prefix.es +758 -0
  26. data/core/nonbreaking_prefixes/nonbreaking_prefix.fr +1027 -0
  27. data/core/nonbreaking_prefixes/nonbreaking_prefix.is +697 -0
  28. data/core/nonbreaking_prefixes/nonbreaking_prefix.it +641 -0
  29. data/core/nonbreaking_prefixes/nonbreaking_prefix.nl +739 -0
  30. data/core/nonbreaking_prefixes/nonbreaking_prefix.pl +729 -0
  31. data/core/nonbreaking_prefixes/nonbreaking_prefix.pt +656 -0
  32. data/core/nonbreaking_prefixes/nonbreaking_prefix.ro +484 -0
  33. data/core/nonbreaking_prefixes/nonbreaking_prefix.ru +705 -0
  34. data/core/nonbreaking_prefixes/nonbreaking_prefix.sk +920 -0
  35. data/core/nonbreaking_prefixes/nonbreaking_prefix.sl +524 -0
  36. data/core/nonbreaking_prefixes/nonbreaking_prefix.sv +492 -0
  37. data/core/split-sentences.pl +114 -0
  38. data/core/text-fixer.pl +169 -0
  39. data/core/tokenizer-cli.pl +363 -0
  40. data/core/tokenizer.pl +145 -0
  41. data/lib/opener/tokenizers/base.rb +84 -0
  42. data/lib/opener/tokenizers/base/version.rb +8 -0
  43. data/opener-tokenizer-base.gemspec +25 -0
  44. metadata +134 -0
@@ -0,0 +1,697 @@
1
+ no #NUMERIC_ONLY#
2
+ No #NUMERIC_ONLY#
3
+ nr #NUMERIC_ONLY#
4
+ Nr #NUMERIC_ONLY#
5
+ nR #NUMERIC_ONLY#
6
+ NR #NUMERIC_ONLY#
7
+ a
8
+ b
9
+ c
10
+ d
11
+ e
12
+ f
13
+ g
14
+ h
15
+ i
16
+ j
17
+ k
18
+ l
19
+ m
20
+ n
21
+ o
22
+ p
23
+ q
24
+ r
25
+ s
26
+ t
27
+ u
28
+ v
29
+ w
30
+ x
31
+ y
32
+ z
33
+ ^
34
+ í
35
+ á
36
+ ó
37
+ æ
38
+ A
39
+ B
40
+ C
41
+ D
42
+ E
43
+ F
44
+ G
45
+ H
46
+ I
47
+ J
48
+ K
49
+ L
50
+ M
51
+ N
52
+ O
53
+ P
54
+ Q
55
+ R
56
+ S
57
+ T
58
+ U
59
+ V
60
+ W
61
+ X
62
+ Y
63
+ Z
64
+ ab.fn
65
+ a.fn
66
+ afs
67
+ al
68
+ alm
69
+ alg
70
+ andh
71
+ ath
72
+ aths
73
+ atr
74
+ ao
75
+ au
76
+ aukaf
77
+ áfn
78
+ áhrl.s
79
+ áhrs
80
+ ákv.gr
81
+ ákv
82
+ bh
83
+ bls
84
+ dr
85
+ e.Kr
86
+ et
87
+ ef
88
+ efn
89
+ ennfr
90
+ eink
91
+ end
92
+ e.st
93
+ erl
94
+ fél
95
+ fskj
96
+ fh
97
+ f.hl
98
+ físl
99
+ fl
100
+ fn
101
+ fo
102
+ forl
103
+ frb
104
+ frl
105
+ frh
106
+ frt
107
+ fsl
108
+ fsh
109
+ fs
110
+ fsk
111
+ fst
112
+ f.Kr
113
+ ft
114
+ fv
115
+ fyrrn
116
+ fyrrv
117
+ germ
118
+ gm
119
+ gr
120
+ hdl
121
+ hdr
122
+ hf
123
+ hl
124
+ hlsk
125
+ hljsk
126
+ hljv
127
+ hljóðv
128
+ hr
129
+ hv
130
+ hvk
131
+ holl
132
+ Hos
133
+ höf
134
+ hk
135
+ hrl
136
+ ísl
137
+ kaf
138
+ kap
139
+ Khöfn
140
+ kk
141
+ kg
142
+ kk
143
+ km
144
+ kl
145
+ klst
146
+ kr
147
+ kt
148
+ kgúrsk
149
+ kvk
150
+ leturbr
151
+ lh
152
+ lh.nt
153
+ lh.þt
154
+ lo
155
+ ltr
156
+ mlja
157
+ mljó
158
+ millj
159
+ mm
160
+ mms
161
+ m.fl
162
+ miðm
163
+ mgr
164
+ mst
165
+ mín
166
+ nf
167
+ nh
168
+ nhm
169
+ nl
170
+ nk
171
+ nmgr
172
+ no
173
+ núv
174
+ nt
175
+ o.áfr
176
+ o.m.fl
177
+ ohf
178
+ o.fl
179
+ o.s.frv
180
+ ófn
181
+ ób
182
+ óákv.gr
183
+ óákv
184
+ pfn
185
+ PR
186
+ pr
187
+ Ritstj
188
+ Rvík
189
+ Rvk
190
+ samb
191
+ samhlj
192
+ samn
193
+ samn
194
+ sbr
195
+ sek
196
+ sérn
197
+ sf
198
+ sfn
199
+ sh
200
+ sfn
201
+ sh
202
+ s.hl
203
+ sk
204
+ skv
205
+ sl
206
+ sn
207
+ so
208
+ ss.us
209
+ s.st
210
+ samþ
211
+ sbr
212
+ shlj
213
+ sign
214
+ skál
215
+ st
216
+ st.s
217
+ stk
218
+
219
+ teg
220
+ tbl
221
+ tfn
222
+ tl
223
+ tvíhlj
224
+ tvt
225
+ till
226
+ to
227
+ umr
228
+ uh
229
+ us
230
+ uppl
231
+ útg
232
+ vb
233
+ Vf
234
+ vh
235
+ vkf
236
+ Vl
237
+ vl
238
+ vlf
239
+ vmf
240
+ 8vo
241
+ vsk
242
+ vth
243
+ þt
244
+ þf
245
+ þjs
246
+ þgf
247
+ þlt
248
+ þolm
249
+ þm
250
+ þml
251
+ þýð
252
+
253
+ #unified abbreviation list
254
+ Acad
255
+ Adj
256
+ Adm
257
+ Adv
258
+ Affl
259
+ Apr
260
+ Art
261
+ Asst
262
+ Av
263
+ Avg
264
+ B.ches-du-Rh
265
+ Bart
266
+ Bco
267
+ Bldg
268
+ Brig
269
+ Bros
270
+ C.a
271
+ C.p.c.n
272
+ Ca
273
+ Capt
274
+ Cdt
275
+ Cf
276
+ Ch.-Mme
277
+ Chap
278
+ Cie
279
+ Cmdr
280
+ Col
281
+ Comdr
282
+ Con
283
+ Corp
284
+ Cpl
285
+ DR
286
+ DRA
287
+ Da
288
+ Dec
289
+ Dep
290
+ Dn
291
+ Dr
292
+ Dra
293
+ Dras
294
+ Drs
295
+ Eng
296
+ Enga
297
+ Engas
298
+ Engos
299
+ Ens
300
+ Ets
301
+ Euro
302
+ Ev
303
+ Ex
304
+ Excmo
305
+ Exmo
306
+ Exo
307
+ Fa
308
+ Fco
309
+ Feb
310
+ Fig
311
+ Fr
312
+ Gar
313
+ Gen
314
+ Gir
315
+ Gl
316
+ Gov
317
+ Hno
318
+ Hon
319
+ Hosp
320
+ Hr
321
+ Ilmo
322
+ Insp
323
+ J.-C
324
+ Jan
325
+ Jeu
326
+ Jr
327
+ Jul
328
+ Jun
329
+ Lda
330
+ Lieut
331
+ Lt
332
+ Lun
333
+ MM
334
+ MR
335
+ MRS
336
+ MS
337
+ MSc
338
+ Maj
339
+ Mar
340
+ Me
341
+ Mej
342
+ Mer
343
+ Mes
344
+ Messrs
345
+ Mgr
346
+ Mgrs
347
+ Mll
348
+ Mlle
349
+ Mlle(s)
350
+ Mme
351
+ Mme(s)
352
+ Mr
353
+ Mrs
354
+ Ms
355
+ Msgr
356
+ Mw
357
+ Nov
358
+ Npr
359
+ Nr
360
+ O.d.J
361
+ Okt
362
+ Op
363
+ Ord
364
+ Oz
365
+ P
366
+ P.D
367
+ P.ej
368
+ P.p.c
369
+ Pas
370
+ Pfc
371
+ Ph
372
+ Prim
373
+ Prof
374
+ Pte
375
+ Pts
376
+ Pvt
377
+ Rep
378
+ Reps
379
+ Res
380
+ Rev
381
+ Revd
382
+ Rh
383
+ Riv
384
+ Rt
385
+ S.Em
386
+ S.Exc
387
+ S.a.r.l
388
+ Sen
389
+ Sens
390
+ Sep
391
+ Sept
392
+ Sfc
393
+ Sgt
394
+ SGT
395
+ Sl
396
+ Sr
397
+ Sra
398
+ Sras
399
+ Srs
400
+ Srta
401
+ St
402
+ ST
403
+ Sta
404
+ Ste
405
+ Sto
406
+ Supt
407
+ Surg
408
+ Tj
409
+ Tr
410
+ Ud
411
+ Uds
412
+ V.Exc
413
+ Vd
414
+ Vda
415
+ Vds
416
+ Vz
417
+ Z.D
418
+ Z.D.H
419
+ Z.E
420
+ Z.Em
421
+ Z.H
422
+ Z.K.H
423
+ Z.K.M
424
+ Z.M
425
+ a
426
+ a./s
427
+ a.C
428
+ a.g.v
429
+ a.l
430
+ abrev
431
+ abs
432
+ ac
433
+ acc
434
+ acron
435
+ adj
436
+ adm
437
+ adr
438
+ adv
439
+ alt
440
+ anal
441
+ anat
442
+ angl
443
+ appos
444
+ apr
445
+ apr
446
+ asc
447
+ atm
448
+ auj
449
+ aux
450
+ av
451
+ avg
452
+ avr
453
+ b
454
+ b.a.o
455
+ b.a.p
456
+ b.a.r
457
+ bacc
458
+ bat
459
+ bc
460
+ bd
461
+ bde
462
+ bgen
463
+ bijv
464
+ bijz
465
+ br
466
+ bv
467
+ c
468
+ c.-a-d
469
+ c.a.f
470
+ c.i
471
+ cc
472
+ cf
473
+ cft
474
+ ch
475
+ ch.-l
476
+ chbre
477
+ chbs
478
+ chf
479
+ col
480
+ coll
481
+ cpl
482
+ cpt
483
+ cpte
484
+ cta
485
+ d
486
+ d.c
487
+ d.w.z
488
+ dcha
489
+ dec
490
+ def
491
+ dem
492
+ dep
493
+ dept
494
+ dhr
495
+ dipl
496
+ dispo
497
+ div
498
+ dpto
499
+ dr
500
+ dr.h.c
501
+ dra
502
+ dras
503
+ drs
504
+ ds
505
+ dz
506
+ e.c
507
+ e.g
508
+ e.g
509
+ e.k
510
+ eccles
511
+ ecol
512
+ econ
513
+ ed
514
+ ej
515
+ env
516
+ ep
517
+ eq
518
+ et
519
+ etc
520
+ ev
521
+ ex
522
+ exmo
523
+ exo
524
+ exp
525
+ expo
526
+ f.a.c
527
+ fa
528
+ fam
529
+ fasc
530
+ fbg
531
+ feb
532
+ fem
533
+ fevr
534
+ ff
535
+ fl
536
+ fol
537
+ fr
538
+ fs
539
+ fut
540
+ gd
541
+ gde
542
+ gdes
543
+ gds
544
+ gen
545
+ gl
546
+ grd
547
+ h.-t
548
+ hab
549
+ i.e
550
+ i.p.v
551
+ i.s.m
552
+ i.t.t
553
+ i.v.m
554
+ ibid
555
+ id
556
+ imp
557
+ ing
558
+ ir
559
+ iron
560
+ itd
561
+ itn
562
+ itp
563
+ izq
564
+ j
565
+ janv
566
+ jhr
567
+ jkvr
568
+ jr
569
+ l
570
+ lat
571
+ lex
572
+ lgen
573
+ lib
574
+ lieut
575
+ liv
576
+ lkol
577
+ loc
578
+ lof
579
+ m
580
+ m.a.w
581
+ m.b.t
582
+ m.b.v
583
+ m.h.o
584
+ m.i
585
+ m.i.v
586
+ maj
587
+ mar
588
+ mas
589
+ max
590
+ med
591
+ mevr
592
+ min
593
+ mll
594
+ mr
595
+ ms
596
+ mtr
597
+ mtrs
598
+ n
599
+ n
600
+ n.f
601
+ n.f.pl
602
+ n.m
603
+ n.m.pl
604
+ npr
605
+ o
606
+ o.b.s
607
+ obs
608
+ oct
609
+ okt
610
+ ord
611
+ oz
612
+ p
613
+ p
614
+ p.a
615
+ p.ej
616
+ p.ex
617
+ p.g.c.d
618
+ p.i
619
+ p.j
620
+ p.m
621
+ p.o
622
+ p.p
623
+ p.p.c.d
624
+ p.p.c.m
625
+ p.pa
626
+ p.pr
627
+ pl
628
+ plv
629
+ poe
630
+ pp
631
+ pp
632
+ pr
633
+ pr
634
+ pres
635
+ prev
636
+ prof
637
+ px
638
+ q.s
639
+ qqch
640
+ qqf
641
+ qqn
642
+ qqns
643
+ r.-de-ch
644
+ r.p.m
645
+ rc
646
+ rd
647
+ ref
648
+ refl
649
+ reg
650
+ rev
651
+ ro
652
+ rte
653
+ s
654
+ s
655
+ s.a
656
+ s.b.f
657
+ s.d
658
+ s.e
659
+ s.l
660
+ s.l.n.d
661
+ s.l.p
662
+ s.t.p
663
+ s.v.p
664
+ s/c
665
+ sc
666
+ sf
667
+ sgt
668
+ sl
669
+ sr
670
+ sra
671
+ sras
672
+ srs
673
+ ss
674
+ sto
675
+ t
676
+ t.s.v.p
677
+ tec
678
+ tel
679
+ terr
680
+ tg
681
+ tint
682
+ tit
683
+ tj
684
+ tr
685
+ travx
686
+ v
687
+ v.intr
688
+ v.tr
689
+ v.w.t
690
+ var
691
+ vs
692
+ vta
693
+ vx
694
+ z.v
695
+ zool
696
+ Št
697
+ št