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 +1,448 @@
1
+ # for now, just include the Greek equivalent of "Mr."
2
+ κ
3
+
4
+ #unified abbreviation list
5
+ Acad
6
+ Adj
7
+ Adm
8
+ Adv
9
+ Affl
10
+ Apr
11
+ Art
12
+ Asst
13
+ Av
14
+ Avg
15
+ B.ches-du-Rh
16
+ Bart
17
+ Bco
18
+ Bldg
19
+ Brig
20
+ Bros
21
+ C.a
22
+ C.p.c.n
23
+ Ca
24
+ Capt
25
+ Cdt
26
+ Cf
27
+ Ch.-Mme
28
+ Chap
29
+ Cie
30
+ Cmdr
31
+ Col
32
+ Comdr
33
+ Con
34
+ Corp
35
+ Cpl
36
+ DR
37
+ DRA
38
+ Da
39
+ Dec
40
+ Dep
41
+ Dn
42
+ Dr
43
+ Dra
44
+ Dras
45
+ Drs
46
+ Eng
47
+ Enga
48
+ Engas
49
+ Engos
50
+ Ens
51
+ Ets
52
+ Euro
53
+ Ev
54
+ Ex
55
+ Excmo
56
+ Exmo
57
+ Exo
58
+ Fa
59
+ Fco
60
+ Feb
61
+ Fig
62
+ Fr
63
+ Gar
64
+ Gen
65
+ Gir
66
+ Gl
67
+ Gov
68
+ Hno
69
+ Hon
70
+ Hosp
71
+ Hr
72
+ Ilmo
73
+ Insp
74
+ J.-C
75
+ Jan
76
+ Jeu
77
+ Jr
78
+ Jul
79
+ Jun
80
+ Lda
81
+ Lieut
82
+ Lt
83
+ Lun
84
+ MM
85
+ MR
86
+ MRS
87
+ MS
88
+ MSc
89
+ Maj
90
+ Mar
91
+ Me
92
+ Mej
93
+ Mer
94
+ Mes
95
+ Messrs
96
+ Mgr
97
+ Mgrs
98
+ Mll
99
+ Mlle
100
+ Mlle(s)
101
+ Mme
102
+ Mme(s)
103
+ Mr
104
+ Mrs
105
+ Ms
106
+ Msgr
107
+ Mw
108
+ Nov
109
+ Npr
110
+ Nr
111
+ O.d.J
112
+ Okt
113
+ Op
114
+ Ord
115
+ Oz
116
+ P
117
+ P.D
118
+ P.ej
119
+ P.p.c
120
+ Pas
121
+ Pfc
122
+ Ph
123
+ Prim
124
+ Prof
125
+ Pte
126
+ Pts
127
+ Pvt
128
+ Rep
129
+ Reps
130
+ Res
131
+ Rev
132
+ Revd
133
+ Rh
134
+ Riv
135
+ Rt
136
+ S.Em
137
+ S.Exc
138
+ S.a.r.l
139
+ Sen
140
+ Sens
141
+ Sep
142
+ Sept
143
+ Sfc
144
+ Sgt
145
+ SGT
146
+ Sl
147
+ Sr
148
+ Sra
149
+ Sras
150
+ Srs
151
+ Srta
152
+ St
153
+ ST
154
+ Sta
155
+ Ste
156
+ Sto
157
+ Supt
158
+ Surg
159
+ Tj
160
+ Tr
161
+ Ud
162
+ Uds
163
+ V.Exc
164
+ Vd
165
+ Vda
166
+ Vds
167
+ Vz
168
+ Z.D
169
+ Z.D.H
170
+ Z.E
171
+ Z.Em
172
+ Z.H
173
+ Z.K.H
174
+ Z.K.M
175
+ Z.M
176
+ a
177
+ a./s
178
+ a.C
179
+ a.g.v
180
+ a.l
181
+ abrev
182
+ abs
183
+ ac
184
+ acc
185
+ acron
186
+ adj
187
+ adm
188
+ adr
189
+ adv
190
+ alt
191
+ anal
192
+ anat
193
+ angl
194
+ appos
195
+ apr
196
+ apr
197
+ asc
198
+ atm
199
+ auj
200
+ aux
201
+ av
202
+ avg
203
+ avr
204
+ b
205
+ b.a.o
206
+ b.a.p
207
+ b.a.r
208
+ bacc
209
+ bat
210
+ bc
211
+ bd
212
+ bde
213
+ bgen
214
+ bijv
215
+ bijz
216
+ br
217
+ bv
218
+ c
219
+ c.-a-d
220
+ c.a.f
221
+ c.i
222
+ cc
223
+ cf
224
+ cft
225
+ ch
226
+ ch.-l
227
+ chbre
228
+ chbs
229
+ chf
230
+ col
231
+ coll
232
+ cpl
233
+ cpt
234
+ cpte
235
+ cta
236
+ d
237
+ d.c
238
+ d.w.z
239
+ dcha
240
+ dec
241
+ def
242
+ dem
243
+ dep
244
+ dept
245
+ dhr
246
+ dipl
247
+ dispo
248
+ div
249
+ dpto
250
+ dr
251
+ dr.h.c
252
+ dra
253
+ dras
254
+ drs
255
+ ds
256
+ dz
257
+ e.c
258
+ e.g
259
+ e.g
260
+ e.k
261
+ eccles
262
+ ecol
263
+ econ
264
+ ed
265
+ ej
266
+ env
267
+ ep
268
+ eq
269
+ et
270
+ etc
271
+ ev
272
+ ex
273
+ exmo
274
+ exo
275
+ exp
276
+ expo
277
+ f.a.c
278
+ fa
279
+ fam
280
+ fasc
281
+ fbg
282
+ feb
283
+ fem
284
+ fevr
285
+ ff
286
+ fl
287
+ fol
288
+ fr
289
+ fs
290
+ fut
291
+ gd
292
+ gde
293
+ gdes
294
+ gds
295
+ gen
296
+ gl
297
+ grd
298
+ h.-t
299
+ hab
300
+ i.e
301
+ i.p.v
302
+ i.s.m
303
+ i.t.t
304
+ i.v.m
305
+ ibid
306
+ id
307
+ imp
308
+ ing
309
+ ir
310
+ iron
311
+ itd
312
+ itn
313
+ itp
314
+ izq
315
+ j
316
+ janv
317
+ jhr
318
+ jkvr
319
+ jr
320
+ l
321
+ lat
322
+ lex
323
+ lgen
324
+ lib
325
+ lieut
326
+ liv
327
+ lkol
328
+ loc
329
+ lof
330
+ m
331
+ m.a.w
332
+ m.b.t
333
+ m.b.v
334
+ m.h.o
335
+ m.i
336
+ m.i.v
337
+ maj
338
+ mar
339
+ mas
340
+ max
341
+ med
342
+ mevr
343
+ min
344
+ mll
345
+ mr
346
+ ms
347
+ mtr
348
+ mtrs
349
+ n
350
+ n
351
+ n.f
352
+ n.f.pl
353
+ n.m
354
+ n.m.pl
355
+ npr
356
+ o
357
+ o.b.s
358
+ obs
359
+ oct
360
+ okt
361
+ ord
362
+ oz
363
+ p
364
+ p
365
+ p.a
366
+ p.ej
367
+ p.ex
368
+ p.g.c.d
369
+ p.i
370
+ p.j
371
+ p.m
372
+ p.o
373
+ p.p
374
+ p.p.c.d
375
+ p.p.c.m
376
+ p.pa
377
+ p.pr
378
+ pl
379
+ plv
380
+ poe
381
+ pp
382
+ pp
383
+ pr
384
+ pr
385
+ pres
386
+ prev
387
+ prof
388
+ px
389
+ q.s
390
+ qqch
391
+ qqf
392
+ qqn
393
+ qqns
394
+ r.-de-ch
395
+ r.p.m
396
+ rc
397
+ rd
398
+ ref
399
+ refl
400
+ reg
401
+ rev
402
+ ro
403
+ rte
404
+ s
405
+ s
406
+ s.a
407
+ s.b.f
408
+ s.d
409
+ s.e
410
+ s.l
411
+ s.l.n.d
412
+ s.l.p
413
+ s.t.p
414
+ s.v.p
415
+ s/c
416
+ sc
417
+ sf
418
+ sgt
419
+ sl
420
+ sr
421
+ sra
422
+ sras
423
+ srs
424
+ ss
425
+ sto
426
+ t
427
+ t.s.v.p
428
+ tec
429
+ tel
430
+ terr
431
+ tg
432
+ tint
433
+ tit
434
+ tj
435
+ tr
436
+ travx
437
+ v
438
+ v.intr
439
+ v.tr
440
+ v.w.t
441
+ var
442
+ vs
443
+ vta
444
+ vx
445
+ z.v
446
+ zool
447
+ Št
448
+ št
@@ -0,0 +1,564 @@
1
+
2
+
3
+ #Special cases are included for prefixes that ONLY appear before 0-9 numbers.
4
+
5
+ #any single upper case letter followed by a period is not a sentence ender (excluding I occasionally, but we leave it in)
6
+ #usually upper case letters are initials in a name
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
+ #List of titles. These are often followed by upper-case names, but do not indicate sentence breaks
35
+ Adj
36
+ Adm
37
+ Adv
38
+ Asst
39
+ Bart
40
+ Bldg
41
+ Brig
42
+ Bros
43
+ Capt
44
+ Cmdr
45
+ Col
46
+ Comdr
47
+ Con
48
+ Corp
49
+ Cpl
50
+ DR
51
+ Dr
52
+ Drs
53
+ Ens
54
+ Gen
55
+ Gov
56
+ Hon
57
+ Hr
58
+ Hosp
59
+ Insp
60
+ Lt
61
+ MM
62
+ MR
63
+ MRS
64
+ MS
65
+ Maj
66
+ Messrs
67
+ Mlle
68
+ Mme
69
+ Mr
70
+ Mrs
71
+ Ms
72
+ Msgr
73
+ Op
74
+ Ord
75
+ Pfc
76
+ Ph
77
+ Prof
78
+ Pvt
79
+ Rep
80
+ Reps
81
+ Res
82
+ Rev
83
+ Rt
84
+ Sen
85
+ Sens
86
+ Sfc
87
+ Sgt
88
+ Sr
89
+ St
90
+ Supt
91
+ Surg
92
+
93
+ #misc - odd period-ending items that NEVER indicate breaks (p.m. does NOT fall into this category - it sometimes ends a sentence)
94
+ v
95
+ vs
96
+ i.e
97
+ rev
98
+ e.g
99
+
100
+ #Numbers only. These should only induce breaks when followed by a numeric sequence
101
+ # add NUMERIC_ONLY after the word for this function
102
+ #This case is mostly for the english "No." which can either be a sentence of its own, or
103
+ #if followed by a number, a non-breaking prefix
104
+ No #NUMERIC_ONLY#
105
+ Nos
106
+ Art #NUMERIC_ONLY#
107
+ Nr
108
+ pp #NUMERIC_ONLY#
109
+
110
+ #unified abbreviation list
111
+ Acad
112
+ Adj
113
+ Adm
114
+ Adv
115
+ Affl
116
+ Apr
117
+ Art
118
+ Asst
119
+ Aug
120
+ Av
121
+ Avg
122
+ B.ches-du-Rh
123
+ Bart
124
+ Bco
125
+ Bldg
126
+ Brig
127
+ Bros
128
+ C.a
129
+ C.p.c.n
130
+ Ca
131
+ Capt
132
+ Cdt
133
+ Cf
134
+ Ch.-Mme
135
+ Chap
136
+ Cie
137
+ Cmdr
138
+ Col
139
+ Comdr
140
+ Con
141
+ Corp
142
+ Cpl
143
+ DR
144
+ DRA
145
+ Da
146
+ Dec
147
+ Dep
148
+ Dn
149
+ Dr
150
+ Dra
151
+ Dras
152
+ Drs
153
+ Eng
154
+ Enga
155
+ Engas
156
+ Engos
157
+ Ens
158
+ Ets
159
+ Euro
160
+ Ev
161
+ Ex
162
+ Excmo
163
+ Exmo
164
+ Exo
165
+ Fa
166
+ Fco
167
+ Feb
168
+ Fig
169
+ Fr
170
+ Gar
171
+ Gen
172
+ Gir
173
+ Gl
174
+ Gov
175
+ Hno
176
+ Hon
177
+ Hosp
178
+ Hr
179
+ Ilmo
180
+ Insp
181
+ J.-C
182
+ Jan
183
+ Jeu
184
+ Jr
185
+ Jul
186
+ Jun
187
+ Lda
188
+ Lieut
189
+ Lt
190
+ Lun
191
+ MM
192
+ MR
193
+ MRS
194
+ MS
195
+ MSc
196
+ Maj
197
+ Mar
198
+ May
199
+ Me
200
+ Mej
201
+ Mer
202
+ Mes
203
+ Messrs
204
+ Mgr
205
+ Mgrs
206
+ Mll
207
+ Mlle
208
+ Mlle(s)
209
+ Mme
210
+ Mme(s)
211
+ Mr
212
+ Mrs
213
+ Ms
214
+ Msgr
215
+ Mw
216
+ Nov
217
+ Npr
218
+ Nr
219
+ O.d.J
220
+ Oct
221
+ Okt
222
+ Op
223
+ Ord
224
+ Oz
225
+ P
226
+ P.D
227
+ P.ej
228
+ P.p.c
229
+ Pas
230
+ Pfc
231
+ Ph
232
+ Prim
233
+ Prof
234
+ Pte
235
+ Pts
236
+ Pvt
237
+ Rep
238
+ Reps
239
+ Res
240
+ Rev
241
+ Revd
242
+ Rh
243
+ Riv
244
+ Rt
245
+ S.Em
246
+ S.Exc
247
+ S.a.r.l
248
+ Sen
249
+ Sens
250
+ Sep
251
+ Sept
252
+ Sfc
253
+ Sgt
254
+ SGT
255
+ Sl
256
+ Sr
257
+ Sra
258
+ Sras
259
+ Srs
260
+ Srta
261
+ St
262
+ ST
263
+ Sta
264
+ Ste
265
+ Sto
266
+ Supt
267
+ Surg
268
+ Tj
269
+ Tr
270
+ Ud
271
+ Uds
272
+ V.Exc
273
+ Vd
274
+ Vda
275
+ Vds
276
+ Vz
277
+ Z.D
278
+ Z.D.H
279
+ Z.E
280
+ Z.Em
281
+ Z.H
282
+ Z.K.H
283
+ Z.K.M
284
+ Z.M
285
+ a
286
+ a./s
287
+ a.C
288
+ a.g.v
289
+ a.l
290
+ abrev
291
+ abs
292
+ ac
293
+ acc
294
+ acron
295
+ adj
296
+ adm
297
+ adr
298
+ adv
299
+ alt
300
+ anal
301
+ anat
302
+ angl
303
+ appos
304
+ apr
305
+ asc
306
+ atm
307
+ aug
308
+ auj
309
+ aux
310
+ av
311
+ avg
312
+ avr
313
+ b
314
+ b.a.o
315
+ b.a.p
316
+ b.a.r
317
+ bacc
318
+ bat
319
+ bc
320
+ bd
321
+ bde
322
+ bgen
323
+ bijv
324
+ bijz
325
+ br
326
+ bv
327
+ c
328
+ c.-a-d
329
+ c.a.f
330
+ c.i
331
+ cc
332
+ cf
333
+ cft
334
+ ch
335
+ ch.-l
336
+ chbre
337
+ chbs
338
+ chf
339
+ col
340
+ coll
341
+ cpl
342
+ cpt
343
+ cpte
344
+ cta
345
+ d
346
+ d.c
347
+ d.w.z
348
+ dcha
349
+ dec
350
+ def
351
+ dem
352
+ dep
353
+ dept
354
+ dhr
355
+ dipl
356
+ dispo
357
+ div
358
+ dpto
359
+ dr
360
+ dr.h.c
361
+ dra
362
+ dras
363
+ drs
364
+ ds
365
+ dz
366
+ e.c
367
+ e.g
368
+ e.g
369
+ e.k
370
+ eccles
371
+ ecol
372
+ econ
373
+ ed
374
+ ej
375
+ env
376
+ ep
377
+ eq
378
+ et
379
+ etc
380
+ ev
381
+ ex
382
+ exmo
383
+ exo
384
+ exp
385
+ expo
386
+ f.a.c
387
+ fa
388
+ fam
389
+ fasc
390
+ fbg
391
+ feb
392
+ fem
393
+ fevr
394
+ ff
395
+ fl
396
+ fol
397
+ fr
398
+ fs
399
+ fut
400
+ gd
401
+ gde
402
+ gdes
403
+ gds
404
+ gen
405
+ gl
406
+ grd
407
+ h.-t
408
+ hab
409
+ i.e
410
+ i.p.v
411
+ i.s.m
412
+ i.t.t
413
+ i.v.m
414
+ ibid
415
+ id
416
+ imp
417
+ ing
418
+ ir
419
+ iron
420
+ itd
421
+ itn
422
+ itp
423
+ izq
424
+ j
425
+ jan
426
+ janv
427
+ jhr
428
+ jkvr
429
+ jr
430
+ jul
431
+ jun
432
+ l
433
+ lat
434
+ lex
435
+ lgen
436
+ lib
437
+ lieut
438
+ liv
439
+ lkol
440
+ loc
441
+ lof
442
+ #m
443
+ m.a.w
444
+ m.b.t
445
+ m.b.v
446
+ m.h.o
447
+ m.i
448
+ m.i.v
449
+ maj
450
+ mar
451
+ mas
452
+ max
453
+ may
454
+ med
455
+ mevr
456
+ min
457
+ mll
458
+ mr
459
+ ms
460
+ mtr
461
+ mtrs
462
+ n
463
+ n
464
+ n.f
465
+ n.f.pl
466
+ n.m
467
+ n.m.pl
468
+ nov
469
+ npr
470
+ o
471
+ o.b.s
472
+ obs
473
+ oct
474
+ okt
475
+ ord
476
+ oz
477
+ p
478
+ p
479
+ p.a
480
+ p.ej
481
+ p.ex
482
+ p.g.c.d
483
+ p.i
484
+ p.j
485
+ p.m
486
+ p.o
487
+ p.p
488
+ p.p.c.d
489
+ p.p.c.m
490
+ p.pa
491
+ p.pr
492
+ pl
493
+ plv
494
+ poe
495
+ pp
496
+ pp
497
+ pr
498
+ pr
499
+ pres
500
+ prev
501
+ prof
502
+ px
503
+ q.s
504
+ qqch
505
+ qqf
506
+ qqn
507
+ qqns
508
+ r.-de-ch
509
+ r.p.m
510
+ rc
511
+ rd
512
+ ref
513
+ refl
514
+ reg
515
+ rev
516
+ ro
517
+ rte
518
+ s
519
+ s
520
+ s.a
521
+ s.b.f
522
+ s.d
523
+ s.e
524
+ s.l
525
+ s.l.n.d
526
+ s.l.p
527
+ s.t.p
528
+ s.v.p
529
+ s/c
530
+ sc
531
+ sep
532
+ sept
533
+ sf
534
+ sgt
535
+ sl
536
+ sr
537
+ sra
538
+ sras
539
+ srs
540
+ ss
541
+ sto
542
+ t
543
+ t.s.v.p
544
+ tec
545
+ tel
546
+ terr
547
+ tg
548
+ tint
549
+ tit
550
+ tj
551
+ tr
552
+ travx
553
+ v
554
+ v.intr
555
+ v.tr
556
+ v.w.t
557
+ var
558
+ vs
559
+ vta
560
+ vx
561
+ z.v
562
+ zool
563
+ Št
564
+ št