adrianeboyd commited on
Commit
dfb7e00
1 Parent(s): 987905d

Update spaCy pipeline

Browse files
README.md CHANGED
@@ -14,62 +14,62 @@ model-index:
14
  metrics:
15
  - name: NER Precision
16
  type: precision
17
- value: 0.8010335917
18
  - name: NER Recall
19
  type: recall
20
- value: 0.7903123008
21
  - name: NER F Score
22
  type: f_score
23
- value: 0.7956368303
24
  - task:
25
  name: TAG
26
  type: token-classification
27
  metrics:
28
  - name: TAG (XPOS) Accuracy
29
  type: accuracy
30
- value: 0.9793305286
31
  - task:
32
  name: POS
33
  type: token-classification
34
  metrics:
35
  - name: POS (UPOS) Accuracy
36
  type: accuracy
37
- value: 0.9697981705
38
  - task:
39
  name: MORPH
40
  type: token-classification
41
  metrics:
42
  - name: Morph (UFeats) Accuracy
43
  type: accuracy
44
- value: 0.8774950281
45
  - task:
46
  name: LEMMA
47
  type: token-classification
48
  metrics:
49
  - name: Lemma Accuracy
50
  type: accuracy
51
- value: 0.9303074713
52
  - task:
53
  name: UNLABELED_DEPENDENCIES
54
  type: token-classification
55
  metrics:
56
  - name: Unlabeled Attachment Score (UAS)
57
  type: f_score
58
- value: 0.8797280809
59
  - task:
60
  name: LABELED_DEPENDENCIES
61
  type: token-classification
62
  metrics:
63
  - name: Labeled Attachment Score (LAS)
64
  type: f_score
65
- value: 0.797664895
66
  - task:
67
  name: SENTS
68
  type: token-classification
69
  metrics:
70
  - name: Sentences F-Score
71
  type: f_score
72
- value: 0.9586814179
73
  ---
74
  ### Details: https://spacy.io/models/pl#pl_core_news_sm
75
 
@@ -78,8 +78,8 @@ Polish pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, l
78
  | Feature | Description |
79
  | --- | --- |
80
  | **Name** | `pl_core_news_sm` |
81
- | **Version** | `3.4.0` |
82
- | **spaCy** | `>=3.4.0,<3.5.0` |
83
  | **Default Pipeline** | `tok2vec`, `morphologizer`, `parser`, `lemmatizer`, `tagger`, `attribute_ruler`, `ner` |
84
  | **Components** | `tok2vec`, `morphologizer`, `parser`, `lemmatizer`, `tagger`, `senter`, `attribute_ruler`, `ner` |
85
  | **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
@@ -106,22 +106,22 @@ Polish pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, l
106
 
107
  | Type | Score |
108
  | --- | --- |
109
- | `TOKEN_ACC` | 99.99 |
110
  | `TOKEN_P` | 99.63 |
111
  | `TOKEN_R` | 99.83 |
112
  | `TOKEN_F` | 99.73 |
113
- | `POS_ACC` | 96.98 |
114
- | `MORPH_ACC` | 87.75 |
115
- | `MORPH_MICRO_P` | 93.73 |
116
- | `MORPH_MICRO_R` | 93.44 |
117
- | `MORPH_MICRO_F` | 93.58 |
118
- | `SENTS_P` | 95.89 |
119
- | `SENTS_R` | 95.85 |
120
- | `SENTS_F` | 95.87 |
121
- | `DEP_UAS` | 87.97 |
122
- | `DEP_LAS` | 79.77 |
123
- | `LEMMA_ACC` | 93.03 |
124
- | `TAG_ACC` | 97.93 |
125
- | `ENTS_P` | 80.10 |
126
- | `ENTS_R` | 79.03 |
127
- | `ENTS_F` | 79.56 |
14
  metrics:
15
  - name: NER Precision
16
  type: precision
17
+ value: 0.8019169329
18
  - name: NER Recall
19
  type: recall
20
+ value: 0.7998725303
21
  - name: NER F Score
22
  type: f_score
23
+ value: 0.8008934269
24
  - task:
25
  name: TAG
26
  type: token-classification
27
  metrics:
28
  - name: TAG (XPOS) Accuracy
29
  type: accuracy
30
+ value: 0.9793610146
31
  - task:
32
  name: POS
33
  type: token-classification
34
  metrics:
35
  - name: POS (UPOS) Accuracy
36
  type: accuracy
37
+ value: 0.9705532162
38
  - task:
39
  name: MORPH
40
  type: token-classification
41
  metrics:
42
  - name: Morph (UFeats) Accuracy
43
  type: accuracy
44
+ value: 0.8796817839
45
  - task:
46
  name: LEMMA
47
  type: token-classification
48
  metrics:
49
  - name: Lemma Accuracy
50
  type: accuracy
51
+ value: 0.9309169
52
  - task:
53
  name: UNLABELED_DEPENDENCIES
54
  type: token-classification
55
  metrics:
56
  - name: Unlabeled Attachment Score (UAS)
57
  type: f_score
58
+ value: 0.8774553377
59
  - task:
60
  name: LABELED_DEPENDENCIES
61
  type: token-classification
62
  metrics:
63
  - name: Labeled Attachment Score (LAS)
64
  type: f_score
65
+ value: 0.7968842575
66
  - task:
67
  name: SENTS
68
  type: token-classification
69
  metrics:
70
  - name: Sentences F-Score
71
  type: f_score
72
+ value: 0.9606868504
73
  ---
74
  ### Details: https://spacy.io/models/pl#pl_core_news_sm
75
 
78
  | Feature | Description |
79
  | --- | --- |
80
  | **Name** | `pl_core_news_sm` |
81
+ | **Version** | `3.5.0` |
82
+ | **spaCy** | `>=3.5.0,<3.6.0` |
83
  | **Default Pipeline** | `tok2vec`, `morphologizer`, `parser`, `lemmatizer`, `tagger`, `attribute_ruler`, `ner` |
84
  | **Components** | `tok2vec`, `morphologizer`, `parser`, `lemmatizer`, `tagger`, `senter`, `attribute_ruler`, `ner` |
85
  | **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
106
 
107
  | Type | Score |
108
  | --- | --- |
109
+ | `TOKEN_ACC` | 99.98 |
110
  | `TOKEN_P` | 99.63 |
111
  | `TOKEN_R` | 99.83 |
112
  | `TOKEN_F` | 99.73 |
113
+ | `POS_ACC` | 97.06 |
114
+ | `MORPH_ACC` | 87.97 |
115
+ | `MORPH_MICRO_P` | 93.82 |
116
+ | `MORPH_MICRO_R` | 93.59 |
117
+ | `MORPH_MICRO_F` | 93.70 |
118
+ | `SENTS_P` | 96.16 |
119
+ | `SENTS_R` | 95.98 |
120
+ | `SENTS_F` | 96.07 |
121
+ | `DEP_UAS` | 87.75 |
122
+ | `DEP_LAS` | 79.69 |
123
+ | `LEMMA_ACC` | 93.09 |
124
+ | `TAG_ACC` | 97.94 |
125
+ | `ENTS_P` | 80.19 |
126
+ | `ENTS_R` | 79.99 |
127
+ | `ENTS_F` | 80.09 |
accuracy.json CHANGED
@@ -1,158 +1,158 @@
1
  {
2
- "token_acc": 0.9998840378,
3
  "token_p": 0.99628964,
4
  "token_r": 0.9982863284,
5
  "token_f": 0.9972869848,
6
- "pos_acc": 0.9697981705,
7
- "morph_acc": 0.8774950281,
8
- "morph_micro_p": 0.9372763935,
9
- "morph_micro_r": 0.9343927541,
10
- "morph_micro_f": 0.9358323524,
11
  "morph_per_feat": {
12
  "Case": {
13
- "p": 0.9043985637,
14
- "r": 0.9035874439,
15
- "f": 0.9039928219
16
  },
17
  "Gender": {
18
- "p": 0.9121613698,
19
- "r": 0.9116268167,
20
- "f": 0.9118940149
21
  },
22
  "Number": {
23
- "p": 0.9695141148,
24
- "r": 0.9679903604,
25
- "f": 0.9687516384
26
  },
27
  "AdpType": {
28
- "p": 0.9994659546,
29
- "r": 0.9976012793,
30
- "f": 0.9985327464
31
  },
32
  "Variant": {
33
- "p": 0.9944913698,
34
- "r": 0.9955882353,
35
- "f": 0.9950395003
36
  },
37
  "Animacy": {
38
- "p": 0.8474107894,
39
- "r": 0.8422498209,
40
- "f": 0.8448224232
41
  },
42
  "Degree": {
43
- "p": 0.9113314448,
44
- "r": 0.9281592614,
45
- "f": 0.9196683819
46
  },
47
  "Aspect": {
48
- "p": 0.8885391594,
49
- "r": 0.881197209,
50
- "f": 0.8848529547
51
  },
52
  "Mood": {
53
- "p": 0.9746463838,
54
- "r": 0.9736070381,
55
- "f": 0.9741264337
56
  },
57
  "Person": {
58
- "p": 0.9753877276,
59
- "r": 0.9711312521,
60
- "f": 0.973254836
61
  },
62
  "Tense": {
63
- "p": 0.9618100968,
64
- "r": 0.9615585774,
65
- "f": 0.9616843206
66
  },
67
  "VerbForm": {
68
- "p": 0.9549745824,
69
  "r": 0.9463835912,
70
- "f": 0.9506596783
71
  },
72
  "Voice": {
73
- "p": 0.9660739832,
74
- "r": 0.9582404217,
75
- "f": 0.9621412579
76
  },
77
  "PunctType": {
78
- "p": 0.9984331476,
79
- "r": 0.9977383438,
80
- "f": 0.9980856248
81
  },
82
  "NumForm": {
83
- "p": 0.9772256729,
84
- "r": 0.9574036511,
85
- "f": 0.9672131148
86
  },
87
  "PrepCase": {
88
- "p": 0.987745098,
89
- "r": 0.9664268585,
90
- "f": 0.976969697
91
  },
92
  "PronType": {
93
- "p": 0.9676170363,
94
- "r": 0.9598463687,
95
- "f": 0.9637160386
96
  },
97
  "Reflex": {
98
- "p": 0.997260274,
99
- "r": 1.0,
100
- "f": 0.9986282579
101
  },
102
  "NumType": {
103
- "p": 0.9012987013,
104
- "r": 0.8525798526,
105
- "f": 0.8762626263
106
  },
107
  "Polarity": {
108
- "p": 0.8794579173,
109
- "r": 0.8480055021,
110
- "f": 0.8634453782
111
  },
112
  "Hyph": {
113
  "p": 1.0,
114
- "r": 0.9696969697,
115
- "f": 0.9846153846
116
  },
117
  "VerbType": {
118
- "p": 0.9266666667,
119
- "r": 0.9025974026,
120
- "f": 0.9144736842
121
  },
122
  "ConjType": {
123
- "p": 0.9473684211,
124
- "r": 0.9536423841,
125
- "f": 0.9504950495
126
  },
127
  "Clitic": {
128
- "p": 0.961352657,
129
- "r": 0.9802955665,
130
- "f": 0.9707317073
131
  },
132
  "Poss": {
133
  "p": 1.0,
134
- "r": 0.9941520468,
135
- "f": 0.9970674487
136
  },
137
  "Number[psor]": {
138
- "p": 0.9898989899,
139
  "r": 0.9607843137,
140
- "f": 0.9751243781
141
  },
142
  "PartType": {
143
- "p": 0.9090909091,
144
- "r": 0.8955223881,
145
- "f": 0.9022556391
146
  },
147
  "Abbr": {
148
- "p": 0.9353233831,
149
- "r": 0.9215686275,
150
- "f": 0.9283950617
151
  },
152
  "Pun": {
153
- "p": 0.9268292683,
154
- "r": 0.8837209302,
155
- "f": 0.9047619048
156
  },
157
  "PunctSide": {
158
  "p": 1.0,
@@ -161,190 +161,195 @@
161
  },
162
  "Foreign": {
163
  "p": 0.5,
164
- "r": 0.6666666667,
165
- "f": 0.5714285714
166
  },
167
  "Emphatic": {
168
  "p": 1.0,
169
- "r": 0.6666666667,
170
- "f": 0.8
171
  },
172
  "Polite": {
173
- "p": 0.0,
174
- "r": 0.0,
175
- "f": 0.0
176
  }
177
  },
178
- "sents_p": 0.9588979223,
179
- "sents_r": 0.9584650113,
180
- "sents_f": 0.9586814179,
181
- "dep_uas": 0.8797280809,
182
- "dep_las": 0.797664895,
183
  "dep_las_per_type": {
184
  "nsubj": {
185
- "p": 0.8311045072,
186
- "r": 0.8306930693,
187
- "f": 0.8308987373
188
  },
189
  "case": {
190
- "p": 0.9639737991,
191
- "r": 0.9684672333,
192
- "f": 0.966215292
193
  },
194
  "amod": {
195
- "p": 0.8689171416,
196
- "r": 0.8891879767,
197
- "f": 0.8789356984
198
  },
199
  "nmod": {
200
- "p": 0.5456193353,
201
- "r": 0.5601736973,
202
- "f": 0.5528007346
203
  },
204
  "cc": {
205
- "p": 0.8541266795,
206
- "r": 0.8666017527,
207
- "f": 0.8603189947
208
  },
209
  "conj": {
210
- "p": 0.6410579345,
211
- "r": 0.661038961,
212
- "f": 0.6508951407
213
  },
214
  "root": {
215
- "p": 0.9268953069,
216
- "r": 0.9273137698,
217
- "f": 0.9271044911
218
  },
219
  "obl": {
220
- "p": 0.6881778742,
221
- "r": 0.6942013129,
222
- "f": 0.6911764706
223
  },
224
  "obl:arg": {
225
- "p": 0.6206467662,
226
- "r": 0.5863689777,
227
- "f": 0.603021148
228
  },
229
  "nummod": {
230
- "p": 0.8489208633,
231
- "r": 0.8428571429,
232
- "f": 0.8458781362
233
  },
234
  "obj": {
235
- "p": 0.7969151671,
236
- "r": 0.8115183246,
237
- "f": 0.804150454
238
  },
239
  "advcl": {
240
- "p": 0.6713483146,
241
- "r": 0.6907514451,
242
- "f": 0.6809116809
243
  },
244
  "iobj": {
245
- "p": 0.7184942717,
246
- "r": 0.6827371695,
247
- "f": 0.7001594896
248
  },
249
  "det:numgov": {
250
- "p": 0.9107142857,
251
- "r": 0.8793103448,
252
- "f": 0.8947368421
253
  },
254
  "acl": {
255
- "p": 0.7101123596,
256
  "r": 0.6422764228,
257
- "f": 0.674493063
258
  },
259
  "nmod:arg": {
260
- "p": 0.5879732739,
261
- "r": 0.6061997704,
262
- "f": 0.5969474279
263
  },
264
  "fixed": {
265
- "p": 0.8542274052,
266
- "r": 0.7630208333,
267
- "f": 0.8060522696
268
  },
269
  "nummod:gov": {
270
- "p": 0.7889908257,
271
  "r": 0.7962962963,
272
- "f": 0.7926267281
273
  },
274
  "obl:agent": {
275
- "p": 0.8448275862,
276
- "r": 0.8032786885,
277
- "f": 0.8235294118
278
  },
279
  "expl:pv": {
280
- "p": 0.9700996678,
281
- "r": 0.9733333333,
282
- "f": 0.9717138103
283
  },
284
  "advmod": {
285
- "p": 0.8131578947,
286
- "r": 0.8276785714,
287
- "f": 0.8203539823
288
  },
289
  "acl:relcl": {
290
- "p": 0.7183098592,
291
- "r": 0.7034482759,
292
- "f": 0.7108013937
293
  },
294
  "advmod:emph": {
295
- "p": 0.6913580247,
296
- "r": 0.6970954357,
297
- "f": 0.694214876
298
  },
299
  "mark": {
300
- "p": 0.8635724332,
301
- "r": 0.8709219858,
302
- "f": 0.8672316384
303
  },
304
  "ccomp:obj": {
305
- "p": 0.6235294118,
306
- "r": 0.5888888889,
307
- "f": 0.6057142857
308
  },
309
- "ccomp": {
310
- "p": 0.6176470588,
311
- "r": 0.5887850467,
312
- "f": 0.6028708134
 
 
 
 
 
313
  },
314
  "xcomp": {
315
- "p": 0.9129464286,
316
- "r": 0.9211711712,
317
- "f": 0.9170403587
318
  },
319
  "advmod:neg": {
320
- "p": 0.9616438356,
321
- "r": 0.9696132597,
322
- "f": 0.9656121045
323
  },
324
  "det": {
325
- "p": 0.9086419753,
326
- "r": 0.8824940048,
327
- "f": 0.895377129
328
  },
329
  "cop": {
330
- "p": 0.881294964,
331
- "r": 0.8277027027,
332
- "f": 0.8536585366
333
  },
334
  "flat": {
335
- "p": 0.8213058419,
336
- "r": 0.8298611111,
337
- "f": 0.8255613126
338
  },
339
  "nsubj:pass": {
340
- "p": 0.7614678899,
341
- "r": 0.7614678899,
342
- "f": 0.7614678899
343
  },
344
  "aux:pass": {
345
- "p": 0.8766233766,
346
- "r": 0.9375,
347
- "f": 0.9060402685
348
  },
349
  "aux:imp": {
350
  "p": 1.0,
@@ -352,69 +357,69 @@
352
  "f": 1.0
353
  },
354
  "advcl:cmpr": {
355
- "p": 0.375,
356
- "r": 0.1875,
357
- "f": 0.25
358
  },
359
  "obl:cmpr": {
360
- "p": 0.7,
361
- "r": 0.5505617978,
362
- "f": 0.6163522013
 
 
 
 
 
363
  },
364
  "nmod:poss": {
365
- "p": 0.5,
366
  "r": 0.1666666667,
367
- "f": 0.25
368
  },
369
  "parataxis:insert": {
370
- "p": 0.5918367347,
371
- "r": 0.4285714286,
372
- "f": 0.4971428571
373
  },
374
  "det:poss": {
375
- "p": 0.993902439,
376
- "r": 0.9476744186,
377
- "f": 0.9702380952
378
  },
379
  "aux": {
380
- "p": 0.8220338983,
381
- "r": 0.8899082569,
382
- "f": 0.8546255507
383
- },
384
- "cc:preconj": {
385
- "p": 0.6,
386
- "r": 0.6923076923,
387
- "f": 0.6428571429
388
- },
389
- "appos": {
390
- "p": 0.6093023256,
391
- "r": 0.5481171548,
392
- "f": 0.577092511
393
  },
394
  "xcomp:pred": {
395
- "p": 0.65,
396
- "r": 0.6341463415,
397
- "f": 0.6419753086
398
- },
399
- "parataxis:obj": {
400
- "p": 0.7417840376,
401
- "r": 0.8186528497,
402
- "f": 0.7783251232
403
  },
404
- "vocative": {
405
- "p": 0.5416666667,
406
- "r": 0.4642857143,
407
- "f": 0.5
408
  },
409
  "dep": {
410
  "p": 0.0,
411
  "r": 0.0,
412
  "f": 0.0
413
  },
 
 
 
 
 
 
 
 
 
 
414
  "aux:cnd": {
415
  "p": 1.0,
416
- "r": 0.75,
417
- "f": 0.8571428571
418
  },
419
  "advmod:arg": {
420
  "p": 0.0,
@@ -422,34 +427,19 @@
422
  "f": 0.0
423
  },
424
  "csubj": {
425
- "p": 0.5789473684,
426
- "r": 0.5,
427
- "f": 0.5365853659
428
- },
429
- "advcl:relcl": {
430
- "p": 0.4,
431
- "r": 0.5,
432
- "f": 0.4444444444
433
  },
434
  "amod:flat": {
435
- "p": 0.7668393782,
436
- "r": 0.7830687831,
437
- "f": 0.7748691099
438
- },
439
- "discourse:intj": {
440
- "p": 0.125,
441
- "r": 0.1111111111,
442
- "f": 0.1176470588
443
  },
444
  "nmod:flat": {
445
- "p": 0.7631578947,
446
- "r": 0.725,
447
- "f": 0.7435897436
448
- },
449
- "orphan": {
450
- "p": 0.0,
451
- "r": 0.0,
452
- "f": 0.0
453
  },
454
  "det:nummod": {
455
  "p": 1.0,
@@ -467,46 +457,51 @@
467
  "f": 0.8823529412
468
  },
469
  "list": {
470
- "p": 0.7567567568,
471
- "r": 0.7179487179,
472
- "f": 0.7368421053
473
  },
474
  "xcomp:subj": {
475
  "p": 0.0,
476
  "r": 0.0,
477
  "f": 0.0
478
  },
479
- "xcomp:cleft": {
480
- "p": 1.0,
481
- "r": 1.0,
482
- "f": 1.0
483
- },
484
- "flat:foreign": {
485
  "p": 0.0,
486
  "r": 0.0,
487
  "f": 0.0
488
  },
 
 
 
 
 
 
 
 
 
 
489
  "obl:orphan": {
490
  "p": 0.0,
491
  "r": 0.0,
492
  "f": 0.0
493
  }
494
  },
495
- "lemma_acc": 0.9303074713,
496
- "tag_acc": 0.9793305286,
497
- "ents_p": 0.8010335917,
498
- "ents_r": 0.7903123008,
499
- "ents_f": 0.7956368303,
500
  "ents_per_type": {
501
  "placeName": {
502
- "p": 0.7919621749,
503
- "r": 0.7827102804,
504
- "f": 0.7873090482
505
  },
506
  "orgName": {
507
- "p": 0.7028753994,
508
- "r": 0.7051282051,
509
- "f": 0.704
510
  },
511
  "date": {
512
  "p": 0.9142857143,
@@ -514,9 +509,9 @@
514
  "f": 0.9014084507
515
  },
516
  "persName": {
517
- "p": 0.8747855918,
518
  "r": 0.8629441624,
519
- "f": 0.8688245315
520
  },
521
  "time": {
522
  "p": 0.8518518519,
@@ -524,10 +519,10 @@
524
  "f": 0.8846153846
525
  },
526
  "geogName": {
527
- "p": 0.5773195876,
528
- "r": 0.5333333333,
529
- "f": 0.5544554455
530
  }
531
  },
532
- "speed": 8667.8864535478
533
  }
1
  {
2
+ "token_acc": 0.9997681025,
3
  "token_p": 0.99628964,
4
  "token_r": 0.9982863284,
5
  "token_f": 0.9972869848,
6
+ "pos_acc": 0.9705532162,
7
+ "morph_acc": 0.8796817839,
8
+ "morph_micro_p": 0.9382125213,
9
+ "morph_micro_r": 0.9358539197,
10
+ "morph_micro_f": 0.9370317363,
11
  "morph_per_feat": {
12
  "Case": {
13
+ "p": 0.9054557125,
14
+ "r": 0.9037155669,
15
+ "f": 0.9045848028
16
  },
17
  "Gender": {
18
+ "p": 0.9157375895,
19
+ "r": 0.914556962,
20
+ "f": 0.915146895
21
  },
22
  "Number": {
23
+ "p": 0.9700246732,
24
+ "r": 0.9680427494,
25
+ "f": 0.9690326979
26
  },
27
  "AdpType": {
28
+ "p": 0.9997330486,
29
+ "r": 0.9981343284,
30
+ "f": 0.9989330488
31
  },
32
  "Variant": {
33
+ "p": 0.9930300807,
34
+ "r": 0.9952205882,
35
+ "f": 0.9941241278
36
  },
37
  "Animacy": {
38
+ "p": 0.8441450036,
39
+ "r": 0.8453546692,
40
+ "f": 0.8447494033
41
  },
42
  "Degree": {
43
+ "p": 0.9093959732,
44
+ "r": 0.9382573572,
45
+ "f": 0.9236012496
46
  },
47
  "Aspect": {
48
+ "p": 0.8886207537,
49
+ "r": 0.8789937569,
50
+ "f": 0.8837810394
51
  },
52
  "Mood": {
53
+ "p": 0.9758043074,
54
+ "r": 0.9784057585,
55
+ "f": 0.9771033014
56
  },
57
  "Person": {
58
+ "p": 0.9778300302,
59
+ "r": 0.9771735482,
60
+ "f": 0.977501679
61
  },
62
  "Tense": {
63
+ "p": 0.9611878093,
64
+ "r": 0.964958159,
65
+ "f": 0.963069294
66
  },
67
  "VerbForm": {
68
+ "p": 0.9563636364,
69
  "r": 0.9463835912,
70
+ "f": 0.9513474408
71
  },
72
  "Voice": {
73
+ "p": 0.9666734819,
74
+ "r": 0.958443138,
75
+ "f": 0.9625407166
76
  },
77
  "PunctType": {
78
+ "p": 0.9989545217,
79
+ "r": 0.9973903967,
80
+ "f": 0.9981718464
81
  },
82
  "NumForm": {
83
+ "p": 0.9795081967,
84
+ "r": 0.9695740365,
85
+ "f": 0.9745158002
86
  },
87
  "PrepCase": {
88
+ "p": 0.9902439024,
89
+ "r": 0.9736211031,
90
+ "f": 0.9818621524
91
  },
92
  "PronType": {
93
+ "p": 0.9721634954,
94
+ "r": 0.9633379888,
95
+ "f": 0.9677306208
96
  },
97
  "Reflex": {
98
+ "p": 0.995890411,
99
+ "r": 0.9986263736,
100
+ "f": 0.9972565158
101
  },
102
  "NumType": {
103
+ "p": 0.9119170984,
104
+ "r": 0.8648648649,
105
+ "f": 0.8877679697
106
  },
107
  "Polarity": {
108
+ "p": 0.8898550725,
109
+ "r": 0.8445667125,
110
+ "f": 0.8666196189
111
  },
112
  "Hyph": {
113
  "p": 1.0,
114
+ "r": 1.0,
115
+ "f": 1.0
116
  },
117
  "VerbType": {
118
+ "p": 0.9215686275,
119
+ "r": 0.9155844156,
120
+ "f": 0.9185667752
121
  },
122
  "ConjType": {
123
+ "p": 0.9591836735,
124
+ "r": 0.9337748344,
125
+ "f": 0.9463087248
126
  },
127
  "Clitic": {
128
+ "p": 0.9428571429,
129
+ "r": 0.9753694581,
130
+ "f": 0.9588377724
131
  },
132
  "Poss": {
133
  "p": 1.0,
134
+ "r": 0.9824561404,
135
+ "f": 0.9911504425
136
  },
137
  "Number[psor]": {
138
+ "p": 1.0,
139
  "r": 0.9607843137,
140
+ "f": 0.98
141
  },
142
  "PartType": {
143
+ "p": 0.9672131148,
144
+ "r": 0.8805970149,
145
+ "f": 0.921875
146
  },
147
  "Abbr": {
148
+ "p": 0.9343434343,
149
+ "r": 0.9068627451,
150
+ "f": 0.92039801
151
  },
152
  "Pun": {
153
+ "p": 0.9202453988,
154
+ "r": 0.8720930233,
155
+ "f": 0.8955223881
156
  },
157
  "PunctSide": {
158
  "p": 1.0,
161
  },
162
  "Foreign": {
163
  "p": 0.5,
164
+ "r": 0.8333333333,
165
+ "f": 0.625
166
  },
167
  "Emphatic": {
168
  "p": 1.0,
169
+ "r": 0.5,
170
+ "f": 0.6666666667
171
  },
172
  "Polite": {
173
+ "p": 1.0,
174
+ "r": 1.0,
175
+ "f": 1.0
176
  }
177
  },
178
+ "sents_p": 0.9615558571,
179
+ "sents_r": 0.9598194131,
180
+ "sents_f": 0.9606868504,
181
+ "dep_uas": 0.8774553377,
182
+ "dep_las": 0.7968842575,
183
  "dep_las_per_type": {
184
  "nsubj": {
185
+ "p": 0.8176527643,
186
+ "r": 0.8346534653,
187
+ "f": 0.8260656541
188
  },
189
  "case": {
190
+ "p": 0.9658563234,
191
+ "r": 0.9695640252,
192
+ "f": 0.9677066229
193
  },
194
  "amod": {
195
+ "p": 0.8649475524,
196
+ "r": 0.8878420817,
197
+ "f": 0.8762452956
198
  },
199
  "nmod": {
200
+ "p": 0.5413122722,
201
+ "r": 0.5527295285,
202
+ "f": 0.546961326
203
  },
204
  "cc": {
205
+ "p": 0.8657004831,
206
+ "r": 0.8724440117,
207
+ "f": 0.8690591659
208
  },
209
  "conj": {
210
+ "p": 0.6382036686,
211
+ "r": 0.6551948052,
212
+ "f": 0.6465876322
213
  },
214
  "root": {
215
+ "p": 0.9213737009,
216
+ "r": 0.9205417607,
217
+ "f": 0.9209575429
218
  },
219
  "obl": {
220
+ "p": 0.694274597,
221
+ "r": 0.6832603939,
222
+ "f": 0.6887234629
223
  },
224
  "obl:arg": {
225
+ "p": 0.6512758202,
226
+ "r": 0.6298472385,
227
+ "f": 0.6403823178
228
  },
229
  "nummod": {
230
+ "p": 0.8571428571,
231
+ "r": 0.8571428571,
232
+ "f": 0.8571428571
233
  },
234
  "obj": {
235
+ "p": 0.796013289,
236
+ "r": 0.7840314136,
237
+ "f": 0.7899769205
238
  },
239
  "advcl": {
240
+ "p": 0.7074626866,
241
+ "r": 0.6849710983,
242
+ "f": 0.6960352423
243
  },
244
  "iobj": {
245
+ "p": 0.7351443124,
246
+ "r": 0.6734059098,
247
+ "f": 0.7029220779
248
  },
249
  "det:numgov": {
250
+ "p": 0.9615384615,
251
+ "r": 0.8620689655,
252
+ "f": 0.9090909091
253
  },
254
  "acl": {
255
+ "p": 0.7053571429,
256
  "r": 0.6422764228,
257
+ "f": 0.6723404255
258
  },
259
  "nmod:arg": {
260
+ "p": 0.5755319149,
261
+ "r": 0.6211251435,
262
+ "f": 0.5974599669
263
  },
264
  "fixed": {
265
+ "p": 0.8550724638,
266
+ "r": 0.7682291667,
267
+ "f": 0.8093278464
268
  },
269
  "nummod:gov": {
270
+ "p": 0.8349514563,
271
  "r": 0.7962962963,
272
+ "f": 0.8151658768
273
  },
274
  "obl:agent": {
275
+ "p": 0.8620689655,
276
+ "r": 0.8196721311,
277
+ "f": 0.8403361345
278
  },
279
  "expl:pv": {
280
+ "p": 0.9685430464,
281
+ "r": 0.975,
282
+ "f": 0.9717607973
283
  },
284
  "advmod": {
285
+ "p": 0.8077586207,
286
+ "r": 0.8366071429,
287
+ "f": 0.8219298246
288
  },
289
  "acl:relcl": {
290
+ "p": 0.7092198582,
291
+ "r": 0.6896551724,
292
+ "f": 0.6993006993
293
  },
294
  "advmod:emph": {
295
+ "p": 0.6981519507,
296
+ "r": 0.7053941909,
297
+ "f": 0.701754386
298
  },
299
  "mark": {
300
+ "p": 0.8732193732,
301
+ "r": 0.8695035461,
302
+ "f": 0.8713574982
303
  },
304
  "ccomp:obj": {
305
+ "p": 0.5909090909,
306
+ "r": 0.5777777778,
307
+ "f": 0.5842696629
308
  },
309
+ "advcl:relcl": {
310
+ "p": 0.1428571429,
311
+ "r": 0.25,
312
+ "f": 0.1818181818
313
+ },
314
+ "appos": {
315
+ "p": 0.6079295154,
316
+ "r": 0.5774058577,
317
+ "f": 0.5922746781
318
  },
319
  "xcomp": {
320
+ "p": 0.90625,
321
+ "r": 0.9144144144,
322
+ "f": 0.9103139013
323
  },
324
  "advmod:neg": {
325
+ "p": 0.9696969697,
326
+ "r": 0.9723756906,
327
+ "f": 0.9710344828
328
  },
329
  "det": {
330
+ "p": 0.9183168317,
331
+ "r": 0.8896882494,
332
+ "f": 0.9037758831
333
  },
334
  "cop": {
335
+ "p": 0.8732394366,
336
+ "r": 0.8378378378,
337
+ "f": 0.8551724138
338
  },
339
  "flat": {
340
+ "p": 0.8093645485,
341
+ "r": 0.8402777778,
342
+ "f": 0.8245315162
343
  },
344
  "nsubj:pass": {
345
+ "p": 0.7818181818,
346
+ "r": 0.7889908257,
347
+ "f": 0.7853881279
348
  },
349
  "aux:pass": {
350
+ "p": 0.9256756757,
351
+ "r": 0.9513888889,
352
+ "f": 0.9383561644
353
  },
354
  "aux:imp": {
355
  "p": 1.0,
357
  "f": 1.0
358
  },
359
  "advcl:cmpr": {
360
+ "p": 0.6,
361
+ "r": 0.375,
362
+ "f": 0.4615384615
363
  },
364
  "obl:cmpr": {
365
+ "p": 0.6578947368,
366
+ "r": 0.5617977528,
367
+ "f": 0.6060606061
368
+ },
369
+ "ccomp": {
370
+ "p": 0.600896861,
371
+ "r": 0.6261682243,
372
+ "f": 0.6132723112
373
  },
374
  "nmod:poss": {
375
+ "p": 0.3333333333,
376
  "r": 0.1666666667,
377
+ "f": 0.2222222222
378
  },
379
  "parataxis:insert": {
380
+ "p": 0.5782312925,
381
+ "r": 0.4187192118,
382
+ "f": 0.4857142857
383
  },
384
  "det:poss": {
385
+ "p": 0.9759036145,
386
+ "r": 0.9418604651,
387
+ "f": 0.9585798817
388
  },
389
  "aux": {
390
+ "p": 0.7948717949,
391
+ "r": 0.8532110092,
392
+ "f": 0.8230088496
 
 
 
 
 
 
 
 
 
 
393
  },
394
  "xcomp:pred": {
395
+ "p": 0.5945945946,
396
+ "r": 0.5365853659,
397
+ "f": 0.5641025641
 
 
 
 
 
398
  },
399
+ "cc:preconj": {
400
+ "p": 0.5,
401
+ "r": 0.4615384615,
402
+ "f": 0.48
403
  },
404
  "dep": {
405
  "p": 0.0,
406
  "r": 0.0,
407
  "f": 0.0
408
  },
409
+ "vocative": {
410
+ "p": 0.7272727273,
411
+ "r": 0.5714285714,
412
+ "f": 0.64
413
+ },
414
+ "parataxis:obj": {
415
+ "p": 0.7073170732,
416
+ "r": 0.7512953368,
417
+ "f": 0.7286432161
418
+ },
419
  "aux:cnd": {
420
  "p": 1.0,
421
+ "r": 0.875,
422
+ "f": 0.9333333333
423
  },
424
  "advmod:arg": {
425
  "p": 0.0,
427
  "f": 0.0
428
  },
429
  "csubj": {
430
+ "p": 0.7368421053,
431
+ "r": 0.6363636364,
432
+ "f": 0.6829268293
 
 
 
 
 
433
  },
434
  "amod:flat": {
435
+ "p": 0.7783505155,
436
+ "r": 0.7989417989,
437
+ "f": 0.7885117493
 
 
 
 
 
438
  },
439
  "nmod:flat": {
440
+ "p": 0.7777777778,
441
+ "r": 0.7,
442
+ "f": 0.7368421053
 
 
 
 
 
443
  },
444
  "det:nummod": {
445
  "p": 1.0,
457
  "f": 0.8823529412
458
  },
459
  "list": {
460
+ "p": 0.6153846154,
461
+ "r": 0.6153846154,
462
+ "f": 0.6153846154
463
  },
464
  "xcomp:subj": {
465
  "p": 0.0,
466
  "r": 0.0,
467
  "f": 0.0
468
  },
469
+ "orphan": {
 
 
 
 
 
470
  "p": 0.0,
471
  "r": 0.0,
472
  "f": 0.0
473
  },
474
+ "discourse:intj": {
475
+ "p": 0.1428571429,
476
+ "r": 0.1111111111,
477
+ "f": 0.125
478
+ },
479
+ "xcomp:cleft": {
480
+ "p": 1.0,
481
+ "r": 0.6666666667,
482
+ "f": 0.8
483
+ },
484
  "obl:orphan": {
485
  "p": 0.0,
486
  "r": 0.0,
487
  "f": 0.0
488
  }
489
  },
490
+ "lemma_acc": 0.9309169,
491
+ "tag_acc": 0.9793610146,
492
+ "ents_p": 0.8019169329,
493
+ "ents_r": 0.7998725303,
494
+ "ents_f": 0.8008934269,
495
  "ents_per_type": {
496
  "placeName": {
497
+ "p": 0.7958236659,
498
+ "r": 0.8014018692,
499
+ "f": 0.7986030268
500
  },
501
  "orgName": {
502
+ "p": 0.7320261438,
503
+ "r": 0.7179487179,
504
+ "f": 0.7249190939
505
  },
506
  "date": {
507
  "p": 0.9142857143,
509
  "f": 0.9014084507
510
  },
511
  "persName": {
512
+ "p": 0.8401976936,
513
  "r": 0.8629441624,
514
+ "f": 0.8514190317
515
  },
516
  "time": {
517
  "p": 0.8518518519,
519
  "f": 0.8846153846
520
  },
521
  "geogName": {
522
+ "p": 0.6629213483,
523
+ "r": 0.5619047619,
524
+ "f": 0.6082474227
525
  }
526
  },
527
+ "speed": 8236.5356506521
528
  }
config.cfg CHANGED
@@ -81,8 +81,8 @@ nO = null
81
  [components.ner.model.tok2vec.embed]
82
  @architectures = "spacy.MultiHashEmbed.v2"
83
  width = 96
84
- attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY"]
85
- rows = [5000,1000,2500,2500,50]
86
  include_static_vectors = false
87
 
88
  [components.ner.model.tok2vec.encode]
@@ -158,8 +158,8 @@ normalize = false
158
  [components.tagger.model.tok2vec.embed]
159
  @architectures = "spacy.MultiHashEmbed.v2"
160
  width = 96
161
- attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY"]
162
- rows = [5000,1000,2500,2500,50]
163
  include_static_vectors = false
164
 
165
  [components.tagger.model.tok2vec.encode]
@@ -178,8 +178,8 @@ factory = "tok2vec"
178
  [components.tok2vec.model.embed]
179
  @architectures = "spacy.MultiHashEmbed.v2"
180
  width = ${components.tok2vec.model.encode:width}
181
- attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY"]
182
- rows = [5000,1000,2500,2500,50]
183
  include_static_vectors = false
184
 
185
  [components.tok2vec.model.encode]
@@ -221,6 +221,7 @@ eval_frequency = 1000
221
  frozen_components = []
222
  before_to_disk = null
223
  annotating_components = []
 
224
 
225
  [training.batcher]
226
  @batchers = "spacy.batch_by_words.v1"
81
  [components.ner.model.tok2vec.embed]
82
  @architectures = "spacy.MultiHashEmbed.v2"
83
  width = 96
84
+ attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
85
+ rows = [5000,1000,2500,2500]
86
  include_static_vectors = false
87
 
88
  [components.ner.model.tok2vec.encode]
158
  [components.tagger.model.tok2vec.embed]
159
  @architectures = "spacy.MultiHashEmbed.v2"
160
  width = 96
161
+ attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY","IS_SPACE"]
162
+ rows = [5000,1000,2500,2500,50,50]
163
  include_static_vectors = false
164
 
165
  [components.tagger.model.tok2vec.encode]
178
  [components.tok2vec.model.embed]
179
  @architectures = "spacy.MultiHashEmbed.v2"
180
  width = ${components.tok2vec.model.encode:width}
181
+ attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY","IS_SPACE"]
182
+ rows = [5000,1000,2500,2500,50,50]
183
  include_static_vectors = false
184
 
185
  [components.tok2vec.model.encode]
221
  frozen_components = []
222
  before_to_disk = null
223
  annotating_components = []
224
+ before_update = null
225
 
226
  [training.batcher]
227
  @batchers = "spacy.batch_by_words.v1"
lemmatizer/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a9dcf297bd1d85064d90f9133dbdfe4ea9dc091abaa31fb90dd651001e6fa522
3
  size 829986
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edb6909189e6af98f47e0921988a817a74cabae520c75a63240ae49853417afd
3
  size 829986
meta.json CHANGED
@@ -1,14 +1,14 @@
1
  {
2
  "lang":"pl",
3
  "name":"core_news_sm",
4
- "version":"3.4.0",
5
  "description":"Polish pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, lemmatizer (trainable_lemmatizer), tagger, senter, ner.",
6
  "author":"Explosion",
7
  "email":"contact@explosion.ai",
8
  "url":"https://explosion.ai",
9
  "license":"GNU GPL 3.0",
10
- "spacy_version":">=3.4.0,<3.5.0",
11
- "spacy_git_version":"dd038b536",
12
  "vectors":{
13
  "width":0,
14
  "vectors":0,
@@ -1780,160 +1780,160 @@
1780
  "senter"
1781
  ],
1782
  "performance":{
1783
- "token_acc":0.9998840378,
1784
  "token_p":0.99628964,
1785
  "token_r":0.9982863284,
1786
  "token_f":0.9972869848,
1787
- "pos_acc":0.9697981705,
1788
- "morph_acc":0.8774950281,
1789
- "morph_micro_p":0.9372763935,
1790
- "morph_micro_r":0.9343927541,
1791
- "morph_micro_f":0.9358323524,
1792
  "morph_per_feat":{
1793
  "Case":{
1794
- "p":0.9043985637,
1795
- "r":0.9035874439,
1796
- "f":0.9039928219
1797
  },
1798
  "Gender":{
1799
- "p":0.9121613698,
1800
- "r":0.9116268167,
1801
- "f":0.9118940149
1802
  },
1803
  "Number":{
1804
- "p":0.9695141148,
1805
- "r":0.9679903604,
1806
- "f":0.9687516384
1807
  },
1808
  "AdpType":{
1809
- "p":0.9994659546,
1810
- "r":0.9976012793,
1811
- "f":0.9985327464
1812
  },
1813
  "Variant":{
1814
- "p":0.9944913698,
1815
- "r":0.9955882353,
1816
- "f":0.9950395003
1817
  },
1818
  "Animacy":{
1819
- "p":0.8474107894,
1820
- "r":0.8422498209,
1821
- "f":0.8448224232
1822
  },
1823
  "Degree":{
1824
- "p":0.9113314448,
1825
- "r":0.9281592614,
1826
- "f":0.9196683819
1827
  },
1828
  "Aspect":{
1829
- "p":0.8885391594,
1830
- "r":0.881197209,
1831
- "f":0.8848529547
1832
  },
1833
  "Mood":{
1834
- "p":0.9746463838,
1835
- "r":0.9736070381,
1836
- "f":0.9741264337
1837
  },
1838
  "Person":{
1839
- "p":0.9753877276,
1840
- "r":0.9711312521,
1841
- "f":0.973254836
1842
  },
1843
  "Tense":{
1844
- "p":0.9618100968,
1845
- "r":0.9615585774,
1846
- "f":0.9616843206
1847
  },
1848
  "VerbForm":{
1849
- "p":0.9549745824,
1850
  "r":0.9463835912,
1851
- "f":0.9506596783
1852
  },
1853
  "Voice":{
1854
- "p":0.9660739832,
1855
- "r":0.9582404217,
1856
- "f":0.9621412579
1857
  },
1858
  "PunctType":{
1859
- "p":0.9984331476,
1860
- "r":0.9977383438,
1861
- "f":0.9980856248
1862
  },
1863
  "NumForm":{
1864
- "p":0.9772256729,
1865
- "r":0.9574036511,
1866
- "f":0.9672131148
1867
  },
1868
  "PrepCase":{
1869
- "p":0.987745098,
1870
- "r":0.9664268585,
1871
- "f":0.976969697
1872
  },
1873
  "PronType":{
1874
- "p":0.9676170363,
1875
- "r":0.9598463687,
1876
- "f":0.9637160386
1877
  },
1878
  "Reflex":{
1879
- "p":0.997260274,
1880
- "r":1.0,
1881
- "f":0.9986282579
1882
  },
1883
  "NumType":{
1884
- "p":0.9012987013,
1885
- "r":0.8525798526,
1886
- "f":0.8762626263
1887
  },
1888
  "Polarity":{
1889
- "p":0.8794579173,
1890
- "r":0.8480055021,
1891
- "f":0.8634453782
1892
  },
1893
  "Hyph":{
1894
  "p":1.0,
1895
- "r":0.9696969697,
1896
- "f":0.9846153846
1897
  },
1898
  "VerbType":{
1899
- "p":0.9266666667,
1900
- "r":0.9025974026,
1901
- "f":0.9144736842
1902
  },
1903
  "ConjType":{
1904
- "p":0.9473684211,
1905
- "r":0.9536423841,
1906
- "f":0.9504950495
1907
  },
1908
  "Clitic":{
1909
- "p":0.961352657,
1910
- "r":0.9802955665,
1911
- "f":0.9707317073
1912
  },
1913
  "Poss":{
1914
  "p":1.0,
1915
- "r":0.9941520468,
1916
- "f":0.9970674487
1917
  },
1918
  "Number[psor]":{
1919
- "p":0.9898989899,
1920
  "r":0.9607843137,
1921
- "f":0.9751243781
1922
  },
1923
  "PartType":{
1924
- "p":0.9090909091,
1925
- "r":0.8955223881,
1926
- "f":0.9022556391
1927
  },
1928
  "Abbr":{
1929
- "p":0.9353233831,
1930
- "r":0.9215686275,
1931
- "f":0.9283950617
1932
  },
1933
  "Pun":{
1934
- "p":0.9268292683,
1935
- "r":0.8837209302,
1936
- "f":0.9047619048
1937
  },
1938
  "PunctSide":{
1939
  "p":1.0,
@@ -1942,190 +1942,195 @@
1942
  },
1943
  "Foreign":{
1944
  "p":0.5,
1945
- "r":0.6666666667,
1946
- "f":0.5714285714
1947
  },
1948
  "Emphatic":{
1949
  "p":1.0,
1950
- "r":0.6666666667,
1951
- "f":0.8
1952
  },
1953
  "Polite":{
1954
- "p":0.0,
1955
- "r":0.0,
1956
- "f":0.0
1957
  }
1958
  },
1959
- "sents_p":0.9588979223,
1960
- "sents_r":0.9584650113,
1961
- "sents_f":0.9586814179,
1962
- "dep_uas":0.8797280809,
1963
- "dep_las":0.797664895,
1964
  "dep_las_per_type":{
1965
  "nsubj":{
1966
- "p":0.8311045072,
1967
- "r":0.8306930693,
1968
- "f":0.8308987373
1969
  },
1970
  "case":{
1971
- "p":0.9639737991,
1972
- "r":0.9684672333,
1973
- "f":0.966215292
1974
  },
1975
  "amod":{
1976
- "p":0.8689171416,
1977
- "r":0.8891879767,
1978
- "f":0.8789356984
1979
  },
1980
  "nmod":{
1981
- "p":0.5456193353,
1982
- "r":0.5601736973,
1983
- "f":0.5528007346
1984
  },
1985
  "cc":{
1986
- "p":0.8541266795,
1987
- "r":0.8666017527,
1988
- "f":0.8603189947
1989
  },
1990
  "conj":{
1991
- "p":0.6410579345,
1992
- "r":0.661038961,
1993
- "f":0.6508951407
1994
  },
1995
  "root":{
1996
- "p":0.9268953069,
1997
- "r":0.9273137698,
1998
- "f":0.9271044911
1999
  },
2000
  "obl":{
2001
- "p":0.6881778742,
2002
- "r":0.6942013129,
2003
- "f":0.6911764706
2004
  },
2005
  "obl:arg":{
2006
- "p":0.6206467662,
2007
- "r":0.5863689777,
2008
- "f":0.603021148
2009
  },
2010
  "nummod":{
2011
- "p":0.8489208633,
2012
- "r":0.8428571429,
2013
- "f":0.8458781362
2014
  },
2015
  "obj":{
2016
- "p":0.7969151671,
2017
- "r":0.8115183246,
2018
- "f":0.804150454
2019
  },
2020
  "advcl":{
2021
- "p":0.6713483146,
2022
- "r":0.6907514451,
2023
- "f":0.6809116809
2024
  },
2025
  "iobj":{
2026
- "p":0.7184942717,
2027
- "r":0.6827371695,
2028
- "f":0.7001594896
2029
  },
2030
  "det:numgov":{
2031
- "p":0.9107142857,
2032
- "r":0.8793103448,
2033
- "f":0.8947368421
2034
  },
2035
  "acl":{
2036
- "p":0.7101123596,
2037
  "r":0.6422764228,
2038
- "f":0.674493063
2039
  },
2040
  "nmod:arg":{
2041
- "p":0.5879732739,
2042
- "r":0.6061997704,
2043
- "f":0.5969474279
2044
  },
2045
  "fixed":{
2046
- "p":0.8542274052,
2047
- "r":0.7630208333,
2048
- "f":0.8060522696
2049
  },
2050
  "nummod:gov":{
2051
- "p":0.7889908257,
2052
  "r":0.7962962963,
2053
- "f":0.7926267281
2054
  },
2055
  "obl:agent":{
2056
- "p":0.8448275862,
2057
- "r":0.8032786885,
2058
- "f":0.8235294118
2059
  },
2060
  "expl:pv":{
2061
- "p":0.9700996678,
2062
- "r":0.9733333333,
2063
- "f":0.9717138103
2064
  },
2065
  "advmod":{
2066
- "p":0.8131578947,
2067
- "r":0.8276785714,
2068
- "f":0.8203539823
2069
  },
2070
  "acl:relcl":{
2071
- "p":0.7183098592,
2072
- "r":0.7034482759,
2073
- "f":0.7108013937
2074
  },
2075
  "advmod:emph":{
2076
- "p":0.6913580247,
2077
- "r":0.6970954357,
2078
- "f":0.694214876
2079
  },
2080
  "mark":{
2081
- "p":0.8635724332,
2082
- "r":0.8709219858,
2083
- "f":0.8672316384
2084
  },
2085
  "ccomp:obj":{
2086
- "p":0.6235294118,
2087
- "r":0.5888888889,
2088
- "f":0.6057142857
2089
  },
2090
- "ccomp":{
2091
- "p":0.6176470588,
2092
- "r":0.5887850467,
2093
- "f":0.6028708134
 
 
 
 
 
2094
  },
2095
  "xcomp":{
2096
- "p":0.9129464286,
2097
- "r":0.9211711712,
2098
- "f":0.9170403587
2099
  },
2100
  "advmod:neg":{
2101
- "p":0.9616438356,
2102
- "r":0.9696132597,
2103
- "f":0.9656121045
2104
  },
2105
  "det":{
2106
- "p":0.9086419753,
2107
- "r":0.8824940048,
2108
- "f":0.895377129
2109
  },
2110
  "cop":{
2111
- "p":0.881294964,
2112
- "r":0.8277027027,
2113
- "f":0.8536585366
2114
  },
2115
  "flat":{
2116
- "p":0.8213058419,
2117
- "r":0.8298611111,
2118
- "f":0.8255613126
2119
  },
2120
  "nsubj:pass":{
2121
- "p":0.7614678899,
2122
- "r":0.7614678899,
2123
- "f":0.7614678899
2124
  },
2125
  "aux:pass":{
2126
- "p":0.8766233766,
2127
- "r":0.9375,
2128
- "f":0.9060402685
2129
  },
2130
  "aux:imp":{
2131
  "p":1.0,
@@ -2133,69 +2138,69 @@
2133
  "f":1.0
2134
  },
2135
  "advcl:cmpr":{
2136
- "p":0.375,
2137
- "r":0.1875,
2138
- "f":0.25
2139
  },
2140
  "obl:cmpr":{
2141
- "p":0.7,
2142
- "r":0.5505617978,
2143
- "f":0.6163522013
 
 
 
 
 
2144
  },
2145
  "nmod:poss":{
2146
- "p":0.5,
2147
  "r":0.1666666667,
2148
- "f":0.25
2149
  },
2150
  "parataxis:insert":{
2151
- "p":0.5918367347,
2152
- "r":0.4285714286,
2153
- "f":0.4971428571
2154
  },
2155
  "det:poss":{
2156
- "p":0.993902439,
2157
- "r":0.9476744186,
2158
- "f":0.9702380952
2159
  },
2160
  "aux":{
2161
- "p":0.8220338983,
2162
- "r":0.8899082569,
2163
- "f":0.8546255507
2164
- },
2165
- "cc:preconj":{
2166
- "p":0.6,
2167
- "r":0.6923076923,
2168
- "f":0.6428571429
2169
- },
2170
- "appos":{
2171
- "p":0.6093023256,
2172
- "r":0.5481171548,
2173
- "f":0.577092511
2174
  },
2175
  "xcomp:pred":{
2176
- "p":0.65,
2177
- "r":0.6341463415,
2178
- "f":0.6419753086
2179
- },
2180
- "parataxis:obj":{
2181
- "p":0.7417840376,
2182
- "r":0.8186528497,
2183
- "f":0.7783251232
2184
  },
2185
- "vocative":{
2186
- "p":0.5416666667,
2187
- "r":0.4642857143,
2188
- "f":0.5
2189
  },
2190
  "dep":{
2191
  "p":0.0,
2192
  "r":0.0,
2193
  "f":0.0
2194
  },
 
 
 
 
 
 
 
 
 
 
2195
  "aux:cnd":{
2196
  "p":1.0,
2197
- "r":0.75,
2198
- "f":0.8571428571
2199
  },
2200
  "advmod:arg":{
2201
  "p":0.0,
@@ -2203,34 +2208,19 @@
2203
  "f":0.0
2204
  },
2205
  "csubj":{
2206
- "p":0.5789473684,
2207
- "r":0.5,
2208
- "f":0.5365853659
2209
- },
2210
- "advcl:relcl":{
2211
- "p":0.4,
2212
- "r":0.5,
2213
- "f":0.4444444444
2214
  },
2215
  "amod:flat":{
2216
- "p":0.7668393782,
2217
- "r":0.7830687831,
2218
- "f":0.7748691099
2219
- },
2220
- "discourse:intj":{
2221
- "p":0.125,
2222
- "r":0.1111111111,
2223
- "f":0.1176470588
2224
  },
2225
  "nmod:flat":{
2226
- "p":0.7631578947,
2227
- "r":0.725,
2228
- "f":0.7435897436
2229
- },
2230
- "orphan":{
2231
- "p":0.0,
2232
- "r":0.0,
2233
- "f":0.0
2234
  },
2235
  "det:nummod":{
2236
  "p":1.0,
@@ -2248,46 +2238,51 @@
2248
  "f":0.8823529412
2249
  },
2250
  "list":{
2251
- "p":0.7567567568,
2252
- "r":0.7179487179,
2253
- "f":0.7368421053
2254
  },
2255
  "xcomp:subj":{
2256
  "p":0.0,
2257
  "r":0.0,
2258
  "f":0.0
2259
  },
2260
- "xcomp:cleft":{
2261
- "p":1.0,
2262
- "r":1.0,
2263
- "f":1.0
2264
- },
2265
- "flat:foreign":{
2266
  "p":0.0,
2267
  "r":0.0,
2268
  "f":0.0
2269
  },
 
 
 
 
 
 
 
 
 
 
2270
  "obl:orphan":{
2271
  "p":0.0,
2272
  "r":0.0,
2273
  "f":0.0
2274
  }
2275
  },
2276
- "lemma_acc":0.9303074713,
2277
- "tag_acc":0.9793305286,
2278
- "ents_p":0.8010335917,
2279
- "ents_r":0.7903123008,
2280
- "ents_f":0.7956368303,
2281
  "ents_per_type":{
2282
  "placeName":{
2283
- "p":0.7919621749,
2284
- "r":0.7827102804,
2285
- "f":0.7873090482
2286
  },
2287
  "orgName":{
2288
- "p":0.7028753994,
2289
- "r":0.7051282051,
2290
- "f":0.704
2291
  },
2292
  "date":{
2293
  "p":0.9142857143,
@@ -2295,9 +2290,9 @@
2295
  "f":0.9014084507
2296
  },
2297
  "persName":{
2298
- "p":0.8747855918,
2299
  "r":0.8629441624,
2300
- "f":0.8688245315
2301
  },
2302
  "time":{
2303
  "p":0.8518518519,
@@ -2305,12 +2300,12 @@
2305
  "f":0.8846153846
2306
  },
2307
  "geogName":{
2308
- "p":0.5773195876,
2309
- "r":0.5333333333,
2310
- "f":0.5544554455
2311
  }
2312
  },
2313
- "speed":8667.8864535478
2314
  },
2315
  "sources":[
2316
  {
1
  {
2
  "lang":"pl",
3
  "name":"core_news_sm",
4
+ "version":"3.5.0",
5
  "description":"Polish pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, lemmatizer (trainable_lemmatizer), tagger, senter, ner.",
6
  "author":"Explosion",
7
  "email":"contact@explosion.ai",
8
  "url":"https://explosion.ai",
9
  "license":"GNU GPL 3.0",
10
+ "spacy_version":">=3.5.0,<3.6.0",
11
+ "spacy_git_version":"9e0322de1",
12
  "vectors":{
13
  "width":0,
14
  "vectors":0,
1780
  "senter"
1781
  ],
1782
  "performance":{
1783
+ "token_acc":0.9997681025,
1784
  "token_p":0.99628964,
1785
  "token_r":0.9982863284,
1786
  "token_f":0.9972869848,
1787
+ "pos_acc":0.9705532162,
1788
+ "morph_acc":0.8796817839,
1789
+ "morph_micro_p":0.9382125213,
1790
+ "morph_micro_r":0.9358539197,
1791
+ "morph_micro_f":0.9370317363,
1792
  "morph_per_feat":{
1793
  "Case":{
1794
+ "p":0.9054557125,
1795
+ "r":0.9037155669,
1796
+ "f":0.9045848028
1797
  },
1798
  "Gender":{
1799
+ "p":0.9157375895,
1800
+ "r":0.914556962,
1801
+ "f":0.915146895
1802
  },
1803
  "Number":{
1804
+ "p":0.9700246732,
1805
+ "r":0.9680427494,
1806
+ "f":0.9690326979
1807
  },
1808
  "AdpType":{
1809
+ "p":0.9997330486,
1810
+ "r":0.9981343284,
1811
+ "f":0.9989330488
1812
  },
1813
  "Variant":{
1814
+ "p":0.9930300807,
1815
+ "r":0.9952205882,
1816
+ "f":0.9941241278
1817
  },
1818
  "Animacy":{
1819
+ "p":0.8441450036,
1820
+ "r":0.8453546692,
1821
+ "f":0.8447494033
1822
  },
1823
  "Degree":{
1824
+ "p":0.9093959732,
1825
+ "r":0.9382573572,
1826
+ "f":0.9236012496
1827
  },
1828
  "Aspect":{
1829
+ "p":0.8886207537,
1830
+ "r":0.8789937569,
1831
+ "f":0.8837810394
1832
  },
1833
  "Mood":{
1834
+ "p":0.9758043074,
1835
+ "r":0.9784057585,
1836
+ "f":0.9771033014
1837
  },
1838
  "Person":{
1839
+ "p":0.9778300302,
1840
+ "r":0.9771735482,
1841
+ "f":0.977501679
1842
  },
1843
  "Tense":{
1844
+ "p":0.9611878093,
1845
+ "r":0.964958159,
1846
+ "f":0.963069294
1847
  },
1848
  "VerbForm":{
1849
+ "p":0.9563636364,
1850
  "r":0.9463835912,
1851
+ "f":0.9513474408
1852
  },
1853
  "Voice":{
1854
+ "p":0.9666734819,
1855
+ "r":0.958443138,
1856
+ "f":0.9625407166
1857
  },
1858
  "PunctType":{
1859
+ "p":0.9989545217,
1860
+ "r":0.9973903967,
1861
+ "f":0.9981718464
1862
  },
1863
  "NumForm":{
1864
+ "p":0.9795081967,
1865
+ "r":0.9695740365,
1866
+ "f":0.9745158002
1867
  },
1868
  "PrepCase":{
1869
+ "p":0.9902439024,
1870
+ "r":0.9736211031,
1871
+ "f":0.9818621524
1872
  },
1873
  "PronType":{
1874
+ "p":0.9721634954,
1875
+ "r":0.9633379888,
1876
+ "f":0.9677306208
1877
  },
1878
  "Reflex":{
1879
+ "p":0.995890411,
1880
+ "r":0.9986263736,
1881
+ "f":0.9972565158
1882
  },
1883
  "NumType":{
1884
+ "p":0.9119170984,
1885
+ "r":0.8648648649,
1886
+ "f":0.8877679697
1887
  },
1888
  "Polarity":{
1889
+ "p":0.8898550725,
1890
+ "r":0.8445667125,
1891
+ "f":0.8666196189
1892
  },
1893
  "Hyph":{
1894
  "p":1.0,
1895
+ "r":1.0,
1896
+ "f":1.0
1897
  },
1898
  "VerbType":{
1899
+ "p":0.9215686275,
1900
+ "r":0.9155844156,
1901
+ "f":0.9185667752
1902
  },
1903
  "ConjType":{
1904
+ "p":0.9591836735,
1905
+ "r":0.9337748344,
1906
+ "f":0.9463087248
1907
  },
1908
  "Clitic":{
1909
+ "p":0.9428571429,
1910
+ "r":0.9753694581,
1911
+ "f":0.9588377724
1912
  },
1913
  "Poss":{
1914
  "p":1.0,
1915
+ "r":0.9824561404,
1916
+ "f":0.9911504425
1917
  },
1918
  "Number[psor]":{
1919
+ "p":1.0,
1920
  "r":0.9607843137,
1921
+ "f":0.98
1922
  },
1923
  "PartType":{
1924
+ "p":0.9672131148,
1925
+ "r":0.8805970149,
1926
+ "f":0.921875
1927
  },
1928
  "Abbr":{
1929
+ "p":0.9343434343,
1930
+ "r":0.9068627451,
1931
+ "f":0.92039801
1932
  },
1933
  "Pun":{
1934
+ "p":0.9202453988,
1935
+ "r":0.8720930233,
1936
+ "f":0.8955223881
1937
  },
1938
  "PunctSide":{
1939
  "p":1.0,
1942
  },
1943
  "Foreign":{
1944
  "p":0.5,
1945
+ "r":0.8333333333,
1946
+ "f":0.625
1947
  },
1948
  "Emphatic":{
1949
  "p":1.0,
1950
+ "r":0.5,
1951
+ "f":0.6666666667
1952
  },
1953
  "Polite":{
1954
+ "p":1.0,
1955
+ "r":1.0,
1956
+ "f":1.0
1957
  }
1958
  },
1959
+ "sents_p":0.9615558571,
1960
+ "sents_r":0.9598194131,
1961
+ "sents_f":0.9606868504,
1962
+ "dep_uas":0.8774553377,
1963
+ "dep_las":0.7968842575,
1964
  "dep_las_per_type":{
1965
  "nsubj":{
1966
+ "p":0.8176527643,
1967
+ "r":0.8346534653,
1968
+ "f":0.8260656541
1969
  },
1970
  "case":{
1971
+ "p":0.9658563234,
1972
+ "r":0.9695640252,
1973
+ "f":0.9677066229
1974
  },
1975
  "amod":{
1976
+ "p":0.8649475524,
1977
+ "r":0.8878420817,
1978
+ "f":0.8762452956
1979
  },
1980
  "nmod":{
1981
+ "p":0.5413122722,
1982
+ "r":0.5527295285,
1983
+ "f":0.546961326
1984
  },
1985
  "cc":{
1986
+ "p":0.8657004831,
1987
+ "r":0.8724440117,
1988
+ "f":0.8690591659
1989
  },
1990
  "conj":{
1991
+ "p":0.6382036686,
1992
+ "r":0.6551948052,
1993
+ "f":0.6465876322
1994
  },
1995
  "root":{
1996
+ "p":0.9213737009,
1997
+ "r":0.9205417607,
1998
+ "f":0.9209575429
1999
  },
2000
  "obl":{
2001
+ "p":0.694274597,
2002
+ "r":0.6832603939,
2003
+ "f":0.6887234629
2004
  },
2005
  "obl:arg":{
2006
+ "p":0.6512758202,
2007
+ "r":0.6298472385,
2008
+ "f":0.6403823178
2009
  },
2010
  "nummod":{
2011
+ "p":0.8571428571,
2012
+ "r":0.8571428571,
2013
+ "f":0.8571428571
2014
  },
2015
  "obj":{
2016
+ "p":0.796013289,
2017
+ "r":0.7840314136,
2018
+ "f":0.7899769205
2019
  },
2020
  "advcl":{
2021
+ "p":0.7074626866,
2022
+ "r":0.6849710983,
2023
+ "f":0.6960352423
2024
  },
2025
  "iobj":{
2026
+ "p":0.7351443124,
2027
+ "r":0.6734059098,
2028
+ "f":0.7029220779
2029
  },
2030
  "det:numgov":{
2031
+ "p":0.9615384615,
2032
+ "r":0.8620689655,
2033
+ "f":0.9090909091
2034
  },
2035
  "acl":{
2036
+ "p":0.7053571429,
2037
  "r":0.6422764228,
2038
+ "f":0.6723404255
2039
  },
2040
  "nmod:arg":{
2041
+ "p":0.5755319149,
2042
+ "r":0.6211251435,
2043
+ "f":0.5974599669
2044
  },
2045
  "fixed":{
2046
+ "p":0.8550724638,
2047
+ "r":0.7682291667,
2048
+ "f":0.8093278464
2049
  },
2050
  "nummod:gov":{
2051
+ "p":0.8349514563,
2052
  "r":0.7962962963,
2053
+ "f":0.8151658768
2054
  },
2055
  "obl:agent":{
2056
+ "p":0.8620689655,
2057
+ "r":0.8196721311,
2058
+ "f":0.8403361345
2059
  },
2060
  "expl:pv":{
2061
+ "p":0.9685430464,
2062
+ "r":0.975,
2063
+ "f":0.9717607973
2064
  },
2065
  "advmod":{
2066
+ "p":0.8077586207,
2067
+ "r":0.8366071429,
2068
+ "f":0.8219298246
2069
  },
2070
  "acl:relcl":{
2071
+ "p":0.7092198582,
2072
+ "r":0.6896551724,
2073
+ "f":0.6993006993
2074
  },
2075
  "advmod:emph":{
2076
+ "p":0.6981519507,
2077
+ "r":0.7053941909,
2078
+ "f":0.701754386
2079
  },
2080
  "mark":{
2081
+ "p":0.8732193732,
2082
+ "r":0.8695035461,
2083
+ "f":0.8713574982
2084
  },
2085
  "ccomp:obj":{
2086
+ "p":0.5909090909,
2087
+ "r":0.5777777778,
2088
+ "f":0.5842696629
2089
  },
2090
+ "advcl:relcl":{
2091
+ "p":0.1428571429,
2092
+ "r":0.25,
2093
+ "f":0.1818181818
2094
+ },
2095
+ "appos":{
2096
+ "p":0.6079295154,
2097
+ "r":0.5774058577,
2098
+ "f":0.5922746781
2099
  },
2100
  "xcomp":{
2101
+ "p":0.90625,
2102
+ "r":0.9144144144,
2103
+ "f":0.9103139013
2104
  },
2105
  "advmod:neg":{
2106
+ "p":0.9696969697,
2107
+ "r":0.9723756906,
2108
+ "f":0.9710344828
2109
  },
2110
  "det":{
2111
+ "p":0.9183168317,
2112
+ "r":0.8896882494,
2113
+ "f":0.9037758831
2114
  },
2115
  "cop":{
2116
+ "p":0.8732394366,
2117
+ "r":0.8378378378,
2118
+ "f":0.8551724138
2119
  },
2120
  "flat":{
2121
+ "p":0.8093645485,
2122
+ "r":0.8402777778,
2123
+ "f":0.8245315162
2124
  },
2125
  "nsubj:pass":{
2126
+ "p":0.7818181818,
2127
+ "r":0.7889908257,
2128
+ "f":0.7853881279
2129
  },
2130
  "aux:pass":{
2131
+ "p":0.9256756757,
2132
+ "r":0.9513888889,
2133
+ "f":0.9383561644
2134
  },
2135
  "aux:imp":{
2136
  "p":1.0,
2138
  "f":1.0
2139
  },
2140
  "advcl:cmpr":{
2141
+ "p":0.6,
2142
+ "r":0.375,
2143
+ "f":0.4615384615
2144
  },
2145
  "obl:cmpr":{
2146
+ "p":0.6578947368,
2147
+ "r":0.5617977528,
2148
+ "f":0.6060606061
2149
+ },
2150
+ "ccomp":{
2151
+ "p":0.600896861,
2152
+ "r":0.6261682243,
2153
+ "f":0.6132723112
2154
  },
2155
  "nmod:poss":{
2156
+ "p":0.3333333333,
2157
  "r":0.1666666667,
2158
+ "f":0.2222222222
2159
  },
2160
  "parataxis:insert":{
2161
+ "p":0.5782312925,
2162
+ "r":0.4187192118,
2163
+ "f":0.4857142857
2164
  },
2165
  "det:poss":{
2166
+ "p":0.9759036145,
2167
+ "r":0.9418604651,
2168
+ "f":0.9585798817
2169
  },
2170
  "aux":{
2171
+ "p":0.7948717949,
2172
+ "r":0.8532110092,
2173
+ "f":0.8230088496
 
 
 
 
 
 
 
 
 
 
2174
  },
2175
  "xcomp:pred":{
2176
+ "p":0.5945945946,
2177
+ "r":0.5365853659,
2178
+ "f":0.5641025641
 
 
 
 
 
2179
  },
2180
+ "cc:preconj":{
2181
+ "p":0.5,
2182
+ "r":0.4615384615,
2183
+ "f":0.48
2184
  },
2185
  "dep":{
2186
  "p":0.0,
2187
  "r":0.0,
2188
  "f":0.0
2189
  },
2190
+ "vocative":{
2191
+ "p":0.7272727273,
2192
+ "r":0.5714285714,
2193
+ "f":0.64
2194
+ },
2195
+ "parataxis:obj":{
2196
+ "p":0.7073170732,
2197
+ "r":0.7512953368,
2198
+ "f":0.7286432161
2199
+ },
2200
  "aux:cnd":{
2201
  "p":1.0,
2202
+ "r":0.875,
2203
+ "f":0.9333333333
2204
  },
2205
  "advmod:arg":{
2206
  "p":0.0,
2208
  "f":0.0
2209
  },
2210
  "csubj":{
2211
+ "p":0.7368421053,
2212
+ "r":0.6363636364,
2213
+ "f":0.6829268293
 
 
 
 
 
2214
  },
2215
  "amod:flat":{
2216
+ "p":0.7783505155,
2217
+ "r":0.7989417989,
2218
+ "f":0.7885117493
 
 
 
 
 
2219
  },
2220
  "nmod:flat":{
2221
+ "p":0.7777777778,
2222
+ "r":0.7,
2223
+ "f":0.7368421053
 
 
 
 
 
2224
  },
2225
  "det:nummod":{
2226
  "p":1.0,
2238
  "f":0.8823529412
2239
  },
2240
  "list":{
2241
+ "p":0.6153846154,
2242
+ "r":0.6153846154,
2243
+ "f":0.6153846154
2244
  },
2245
  "xcomp:subj":{
2246
  "p":0.0,
2247
  "r":0.0,
2248
  "f":0.0
2249
  },
2250
+ "orphan":{
 
 
 
 
 
2251
  "p":0.0,
2252
  "r":0.0,
2253
  "f":0.0
2254
  },
2255
+ "discourse:intj":{
2256
+ "p":0.1428571429,
2257
+ "r":0.1111111111,
2258
+ "f":0.125
2259
+ },
2260
+ "xcomp:cleft":{
2261
+ "p":1.0,
2262
+ "r":0.6666666667,
2263
+ "f":0.8
2264
+ },
2265
  "obl:orphan":{
2266
  "p":0.0,
2267
  "r":0.0,
2268
  "f":0.0
2269
  }
2270
  },
2271
+ "lemma_acc":0.9309169,
2272
+ "tag_acc":0.9793610146,
2273
+ "ents_p":0.8019169329,
2274
+ "ents_r":0.7998725303,
2275
+ "ents_f":0.8008934269,
2276
  "ents_per_type":{
2277
  "placeName":{
2278
+ "p":0.7958236659,
2279
+ "r":0.8014018692,
2280
+ "f":0.7986030268
2281
  },
2282
  "orgName":{
2283
+ "p":0.7320261438,
2284
+ "r":0.7179487179,
2285
+ "f":0.7249190939
2286
  },
2287
  "date":{
2288
  "p":0.9142857143,
2290
  "f":0.9014084507
2291
  },
2292
  "persName":{
2293
+ "p":0.8401976936,
2294
  "r":0.8629441624,
2295
+ "f":0.8514190317
2296
  },
2297
  "time":{
2298
  "p":0.8518518519,
2300
  "f":0.8846153846
2301
  },
2302
  "geogName":{
2303
+ "p":0.6629213483,
2304
+ "r":0.5619047619,
2305
+ "f":0.6082474227
2306
  }
2307
  },
2308
+ "speed":8236.5356506521
2309
  },
2310
  "sources":[
2311
  {
morphologizer/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e5e511946aceba449800e03eaf90a0e36de844d2d2d768c466f5397882558e2
3
  size 630554
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47a0af55dfb4211028175d7aff43569d243c17f0a7eb9336b9aa2d94a3db3bb1
3
  size 630554
ner/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:283aa25279777fd73f6c6cf6b05bae01bfd3028003860f57b157c6a36dbf9c47
3
- size 6272282
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7cae691141e3b093d999cc60c76a7230c82ff8900f31ea488e764df665f58ec
3
+ size 6142120
parser/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f8e7cdd654b8ca28ff7fea3a9950f09a807c28d99d626244b0e613d66a4d43b4
3
  size 318869
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2de5cf4bdf9743d4d39ca31939340fc761bbbf747c07006c06e760a6537e909f
3
  size 318869
pl_core_news_sm-any-py3-none-any.whl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9461887710b51961e0b0e2f7791fdeef54163436b353dcd85f74c4300081be32
3
- size 20089573
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4dc5ae4c983aaad674451670532ea74861e1cf6ee730e3f2164522e91c860d0
3
+ size 20214436
senter/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ba387a51c0e670dbef63b3cb0dd29db6d72ab4da1133171d189ef23f38440381
3
  size 197089
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a363510a6c9d01a5ad7d003675b6c4bc8937ccce1d92196d72bbcd6f6dc9b8f3
3
  size 197089
tagger/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c252ea5ae09e97089065c038d17b3869de14bf0d8108382026befc04feada21
3
- size 6153971
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6864b734647fc0f6e2ddcd1e78f14a27c5624938b200e7e263038ce7cce8ca63
3
+ size 6284136
tok2vec/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:054bcd28c5f59201ee5375fee453c34b0abf71c98c67d0ce38ff910101b794f6
3
- size 6139229
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:065424818390e228d8f77c31aa6a6f6c3438a44c1fdd79bbf06360835224234a
3
+ size 6269370
tokenizer CHANGED
@@ -1,3 +1,3 @@
1
- ��prefix_search� �^(długo|krótko|jedno|dwu|trzy|cztero)-|^§|^%|^=|^—|^–|^\+(?![0-9])|^…|^……|^,|^:|^;|^\!|^\?|^¿|^؟|^¡|^\(|^\)|^\[|^\]|^\{|^\}|^<|^>|^_|^#|^\*|^&|^。|^?|^!|^,|^、|^;|^:|^~|^·|^।|^،|^۔|^؛|^٪|^\.\.+|^…|^\'|^"|^”|^“|^`|^‘|^´|^’|^‚|^,|^„|^»|^«|^「|^」|^『|^』|^(|^)|^〔|^〕|^【|^】|^《|^》|^〈|^〉|^\$|^£|^€|^¥|^฿|^US\$|^C\$|^A\$|^₽|^﷼|^₴|^₠|^₡|^₢|^₣|^₤|^₥|^₦|^₧|^₨|^₩|^₪|^₫|^€|^₭|^₮|^₯|^₰|^₱|^₲|^₳|^₴|^₵|^₶|^₷|^₸|^₹|^₺|^₻|^₼|^₽|^₾|^₿|^[\u00A6\u00A9\u00AE\u00B0\u0482\u058D\u058E\u060E\u060F\u06DE\u06E9\u06FD\u06FE\u07F6\u09FA\u0B70\u0BF3-\u0BF8\u0BFA\u0C7F\u0D4F\u0D79\u0F01-\u0F03\u0F13\u0F15-\u0F17\u0F1A-\u0F1F\u0F34\u0F36\u0F38\u0FBE-\u0FC5\u0FC7-\u0FCC\u0FCE\u0FCF\u0FD5-\u0FD8\u109E\u109F\u1390-\u1399\u1940\u19DE-\u19FF\u1B61-\u1B6A\u1B74-\u1B7C\u2100\u2101\u2103-\u2106\u2108\u2109\u2114\u2116\u2117\u211E-\u2123\u2125\u2127\u2129\u212E\u213A\u213B\u214A\u214C\u214D\u214F\u218A\u218B\u2195-\u2199\u219C-\u219F\u21A1\u21A2\u21A4\u21A5\u21A7-\u21AD\u21AF-\u21CD\u21D0\u21D1\u21D3\u21D5-\u21F3\u2300-\u2307\u230C-\u231F\u2322-\u2328\u232B-\u237B\u237D-\u239A\u23B4-\u23DB\u23E2-\u2426\u2440-\u244A\u249C-\u24E9\u2500-\u25B6\u25B8-\u25C0\u25C2-\u25F7\u2600-\u266E\u2670-\u2767\u2794-\u27BF\u2800-\u28FF\u2B00-\u2B2F\u2B45\u2B46\u2B4D-\u2B73\u2B76-\u2B95\u2B98-\u2BC8\u2BCA-\u2BFE\u2CE5-\u2CEA\u2E80-\u2E99\u2E9B-\u2EF3\u2F00-\u2FD5\u2FF0-\u2FFB\u3004\u3012\u3013\u3020\u3036\u3037\u303E\u303F\u3190\u3191\u3196-\u319F\u31C0-\u31E3\u3200-\u321E\u322A-\u3247\u3250\u3260-\u327F\u328A-\u32B0\u32C0-\u32FE\u3300-\u33FF\u4DC0-\u4DFF\uA490-\uA4C6\uA828-\uA82B\uA836\uA837\uA839\uAA77-\uAA79\uFDFD\uFFE4\uFFE8\uFFED\uFFEE\uFFFC\uFFFD\U00010137-\U0001013F\U00010179-\U00010189\U0001018C-\U0001018E\U00010190-\U0001019B\U000101A0\U000101D0-\U000101FC\U00010877\U00010878\U00010AC8\U0001173F\U00016B3C-\U00016B3F\U00016B45\U0001BC9C\U0001D000-\U0001D0F5\U0001D100-\U0001D126\U0001D129-\U0001D164\U0001D16A-\U0001D16C\U0001D183\U0001D184\U0001D18C-\U0001D1A9\U0001D1AE-\U0001D1E8\U0001D200-\U0001D241\U0001D245\U0001D300-\U0001D356\U0001D800-\U0001D9FF\U0001DA37-\U0001DA3A\U0001DA6D-\U0001DA74\U0001DA76-\U0001DA83\U0001DA85\U0001DA86\U0001ECAC\U0001F000-\U0001F02B\U0001F030-\U0001F093\U0001F0A0-\U0001F0AE\U0001F0B1-\U0001F0BF\U0001F0C1-\U0001F0CF\U0001F0D1-\U0001F0F5\U0001F110-\U0001F16B\U0001F170-\U0001F1AC\U0001F1E6-\U0001F202\U0001F210-\U0001F23B\U0001F240-\U0001F248\U0001F250\U0001F251\U0001F260-\U0001F265\U0001F300-\U0001F3FA\U0001F400-\U0001F6D4\U0001F6E0-\U0001F6EC\U0001F6F0-\U0001F6F9\U0001F700-\U0001F773\U0001F780-\U0001F7D8\U0001F800-\U0001F80B\U0001F810-\U0001F847\U0001F850-\U0001F859\U0001F860-\U0001F887\U0001F890-\U0001F8AD\U0001F900-\U0001F90B\U0001F910-\U0001F93E\U0001F940-\U0001F970\U0001F973-\U0001F976\U0001F97A\U0001F97C-\U0001F9A2\U0001F9B0-\U0001F9B9\U0001F9C0-\U0001F9C2\U0001F9D0-\U0001F9FF\U0001FA60-\U0001FA6D]�suffix_search�&m''$|’’$|\.$|…$|…$|……$|,$|:$|;$|\!$|\?$|¿$|؟$|¡$|\($|\)$|\[$|\]$|\{$|\}$|<$|>$|_$|#$|\*$|&$|。$|?$|!$|,$|、$|;$|:$|~$|·$|।$|،$|۔$|؛$|٪$|\'$|"$|”$|“$|`$|‘$|´$|’$|‚$|,$|„$|»$|«$|「$|」$|『$|』$|($|)$|〔$|〕$|【$|】$|《$|》$|〈$|〉$|[\u00A6\u00A9\u00AE\u00B0\u0482\u058D\u058E\u060E\u060F\u06DE\u06E9\u06FD\u06FE\u07F6\u09FA\u0B70\u0BF3-\u0BF8\u0BFA\u0C7F\u0D4F\u0D79\u0F01-\u0F03\u0F13\u0F15-\u0F17\u0F1A-\u0F1F\u0F34\u0F36\u0F38\u0FBE-\u0FC5\u0FC7-\u0FCC\u0FCE\u0FCF\u0FD5-\u0FD8\u109E\u109F\u1390-\u1399\u1940\u19DE-\u19FF\u1B61-\u1B6A\u1B74-\u1B7C\u2100\u2101\u2103-\u2106\u2108\u2109\u2114\u2116\u2117\u211E-\u2123\u2125\u2127\u2129\u212E\u213A\u213B\u214A\u214C\u214D\u214F\u218A\u218B\u2195-\u2199\u219C-\u219F\u21A1\u21A2\u21A4\u21A5\u21A7-\u21AD\u21AF-\u21CD\u21D0\u21D1\u21D3\u21D5-\u21F3\u2300-\u2307\u230C-\u231F\u2322-\u2328\u232B-\u237B\u237D-\u239A\u23B4-\u23DB\u23E2-\u2426\u2440-\u244A\u249C-\u24E9\u2500-\u25B6\u25B8-\u25C0\u25C2-\u25F7\u2600-\u266E\u2670-\u2767\u2794-\u27BF\u2800-\u28FF\u2B00-\u2B2F\u2B45\u2B46\u2B4D-\u2B73\u2B76-\u2B95\u2B98-\u2BC8\u2BCA-\u2BFE\u2CE5-\u2CEA\u2E80-\u2E99\u2E9B-\u2EF3\u2F00-\u2FD5\u2FF0-\u2FFB\u3004\u3012\u3013\u3020\u3036\u3037\u303E\u303F\u3190\u3191\u3196-\u319F\u31C0-\u31E3\u3200-\u321E\u322A-\u3247\u3250\u3260-\u327F\u328A-\u32B0\u32C0-\u32FE\u3300-\u33FF\u4DC0-\u4DFF\uA490-\uA4C6\uA828-\uA82B\uA836\uA837\uA839\uAA77-\uAA79\uFDFD\uFFE4\uFFE8\uFFED\uFFEE\uFFFC\uFFFD\U00010137-\U0001013F\U00010179-\U00010189\U0001018C-\U0001018E\U00010190-\U0001019B\U000101A0\U000101D0-\U000101FC\U00010877\U00010878\U00010AC8\U0001173F\U00016B3C-\U00016B3F\U00016B45\U0001BC9C\U0001D000-\U0001D0F5\U0001D100-\U0001D126\U0001D129-\U0001D164\U0001D16A-\U0001D16C\U0001D183\U0001D184\U0001D18C-\U0001D1A9\U0001D1AE-\U0001D1E8\U0001D200-\U0001D241\U0001D245\U0001D300-\U0001D356\U0001D800-\U0001D9FF\U0001DA37-\U0001DA3A\U0001DA6D-\U0001DA74\U0001DA76-\U0001DA83\U0001DA85\U0001DA86\U0001ECAC\U0001F000-\U0001F02B\U0001F030-\U0001F093\U0001F0A0-\U0001F0AE\U0001F0B1-\U0001F0BF\U0001F0C1-\U0001F0CF\U0001F0D1-\U0001F0F5\U0001F110-\U0001F16B\U0001F170-\U0001F1AC\U0001F1E6-\U0001F202\U0001F210-\U0001F23B\U0001F240-\U0001F248\U0001F250\U0001F251\U0001F260-\U0001F265\U0001F300-\U0001F3FA\U0001F400-\U0001F6D4\U0001F6E0-\U0001F6EC\U0001F6F0-\U0001F6F9\U0001F700-\U0001F773\U0001F780-\U0001F7D8\U0001F800-\U0001F80B\U0001F810-\U0001F847\U0001F850-\U0001F859\U0001F860-\U0001F887\U0001F890-\U0001F8AD\U0001F900-\U0001F90B\U0001F910-\U0001F93E\U0001F940-\U0001F970\U0001F973-\U0001F976\U0001F97A\U0001F97C-\U0001F9A2\U0001F9B0-\U0001F9B9\U0001F9C0-\U0001F9C2\U0001F9D0-\U0001F9FF\U0001FA60-\U0001FA6D]$|(?<=[0-9])\+$|(?<=°[FfCcKk])\.$|(?<=[0-9])(?:\$|£|€|¥|฿|US\$|C\$|A\$|₽|﷼|₴|₠|₡|₢|₣|₤|₥|₦|₧|₨|₩|₪|₫|€|₭|₮|₯|₰|₱|₲|₳|₴|₵|₶|₷|₸|₹|₺|₻|₼|₽|₾|₿)$|(?<=[0-9])(?:km|km²|km³|m|m²|m³|dm|dm²|dm³|cm|cm²|cm³|mm|mm²|mm³|ha|µm|nm|yd|in|ft|kg|g|mg|µg|t|lb|oz|m/s|km/h|kmh|mph|hPa|Pa|mbar|mb|MB|kb|KB|gb|GB|tb|TB|T|G|M|K|%|км|км²|км³|м|м²|м³|дм|дм²|дм³|см|см²|см³|мм|мм²|мм³|нм|кг|г|мг|м/с|км/ч|кПа|Па|мбар|Кб|КБ|кб|Мб|МБ|мб|Гб|ГБ|гб|Тб|ТБ|тбكم|كم²|كم³|م|م²|م³|سم|سم²|سم³|مم|مم²|مم³|كم|غرام|جرام|جم|كغ|ملغ|كوب|اكواب)$|(?<=[0-9a-z\uFF41-\uFF5A\u00DF-\u00F6\u00F8-\u00FF\u0101\u0103\u0105\u0107\u0109\u010B\u010D\u010F\u0111\u0113\u0115\u0117\u0119\u011B\u011D\u011F\u0121\u0123\u0125\u0127\u0129\u012B\u012D\u012F\u0131\u0133\u0135\u0137\u0138\u013A\u013C\u013E\u0140\u0142\u0144\u0146\u0148\u0149\u014B\u014D\u014F\u0151\u0153\u0155\u0157\u0159\u015B\u015D\u015F\u0161\u0163\u0165\u0167\u0169\u016B\u016D\u016F\u0171\u0173\u0175\u0177\u017A\u017C\u017E\u017F\u0180\u0183\u0185\u0188\u018C\u018D\u0192\u0195\u0199-\u019B\u019E\u01A1\u01A3\u01A5\u01A8\u01AA\u01AB\u01AD\u01B0\u01B4\u01B6\u01B9\u01BA\u01BD-\u01BF\u01C6\u01C9\u01CC\u01CE\u01D0\u01D2\u01D4\u01D6\u01D8\u01DA\u01DC\u01DD\u01DF\u01E1\u01E3\u01E5\u01E7\u01E9\u01EB\u01ED\u01EF\u01F0\u01F3\u01F5\u01F9\u01FB\u01FD\u01FF\u0201\u0203\u0205\u0207\u0209\u020B\u020D\u020F\u0211\u0213\u0215\u0217\u0219\u021B\u021D\u021F\u0221\u0223\u0225\u0227\u0229\u022B\u022D\u022F\u0231\u0233-\u0239\u023C\u023F\u0240\u0242\u0247\u0249\u024B\u024D\u024F\u2C61\u2C65\u2C66\u2C68\u2C6A\u2C6C\u2C71\u2C73\u2C74\u2C76-\u2C7B\uA723\uA725\uA727\uA729\uA72B\uA72D\uA72F-\uA731\uA733\uA735\uA737\uA739\uA73B\uA73D\uA73F\uA741\uA743\uA745\uA747\uA749\uA74B\uA74D\uA74F\uA751\uA753\uA755\uA757\uA759\uA75B\uA75D\uA75F\uA761\uA763\uA765\uA767\uA769\uA76B\uA76D\uA76F\uA771-\uA778\uA77A\uA77C\uA77F\uA781\uA783\uA785\uA787\uA78C\uA78E\uA791\uA793-\uA795\uA797\uA799\uA79B\uA79D\uA79F\uA7A1\uA7A3\uA7A5\uA7A7\uA7A9\uA7AF\uA7B5\uA7B7\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E01\u1E03\u1E05\u1E07\u1E09\u1E0B\u1E0D\u1E0F\u1E11\u1E13\u1E15\u1E17\u1E19\u1E1B\u1E1D\u1E1F\u1E21\u1E23\u1E25\u1E27\u1E29\u1E2B\u1E2D\u1E2F\u1E31\u1E33\u1E35\u1E37\u1E39\u1E3B\u1E3D\u1E3F\u1E41\u1E43\u1E45\u1E47\u1E49\u1E4B\u1E4D\u1E4F\u1E51\u1E53\u1E55\u1E57\u1E59\u1E5B\u1E5D\u1E5F\u1E61\u1E63\u1E65\u1E67\u1E69\u1E6B\u1E6D\u1E6F\u1E71\u1E73\u1E75\u1E77\u1E79\u1E7B\u1E7D\u1E7F\u1E81\u1E83\u1E85\u1E87\u1E89\u1E8B\u1E8D\u1E8F\u1E91\u1E93\u1E95-\u1E9D\u1E9F\u1EA1\u1EA3\u1EA5\u1EA7\u1EA9\u1EAB\u1EAD\u1EAF\u1EB1\u1EB3\u1EB5\u1EB7\u1EB9\u1EBB\u1EBD\u1EBF\u1EC1\u1EC3\u1EC5\u1EC7\u1EC9\u1ECB\u1ECD\u1ECF\u1ED1\u1ED3\u1ED5\u1ED7\u1ED9\u1EDB\u1EDD\u1EDF\u1EE1\u1EE3\u1EE5\u1EE7\u1EE9\u1EEB\u1EED\u1EEF\u1EF1\u1EF3\u1EF5\u1EF7\u1EF9\u1EFB\u1EFD\u1EFFёа-яәөүҗңһα-ωάέίόώήύа-щюяіїєґѓѕјљњќѐѝ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F%²\-\+…|……|,|:|;|\!|\?|¿|؟|¡|\(|\)|\[|\]|\{|\}|<|>|_|#|\*|&|。|?|!|,|、|;|:|~|·|।|،|۔|؛|٪(?:\'"”“`‘´’‚,„»«「」『』()〔〕【】《》〈〉)])\.$|(?<=[A-Z\uFF21-\uFF3A\u00C0-\u00D6\u00D8-\u00DE\u0100\u0102\u0104\u0106\u0108\u010A\u010C\u010E\u0110\u0112\u0114\u0116\u0118\u011A\u011C\u011E\u0120\u0122\u0124\u0126\u0128\u012A\u012C\u012E\u0130\u0132\u0134\u0136\u0139\u013B\u013D\u013F\u0141\u0143\u0145\u0147\u014A\u014C\u014E\u0150\u0152\u0154\u0156\u0158\u015A\u015C\u015E\u0160\u0162\u0164\u0166\u0168\u016A\u016C\u016E\u0170\u0172\u0174\u0176\u0178\u0179\u017B\u017D\u0181\u0182\u0184\u0186\u0187\u0189-\u018B\u018E-\u0191\u0193\u0194\u0196-\u0198\u019C\u019D\u019F\u01A0\u01A2\u01A4\u01A6\u01A7\u01A9\u01AC\u01AE\u01AF\u01B1-\u01B3\u01B5\u01B7\u01B8\u01BC\u01C4\u01C7\u01CA\u01CD\u01CF\u01D1\u01D3\u01D5\u01D7\u01D9\u01DB\u01DE\u01E0\u01E2\u01E4\u01E6\u01E8\u01EA\u01EC\u01EE\u01F1\u01F4\u01F6-\u01F8\u01FA\u01FC\u01FE\u0200\u0202\u0204\u0206\u0208\u020A\u020C\u020E\u0210\u0212\u0214\u0216\u0218\u021A\u021C\u021E\u0220\u0222\u0224\u0226\u0228\u022A\u022C\u022E\u0230\u0232\u023A\u023B\u023D\u023E\u0241\u0243-\u0246\u0248\u024A\u024C\u024E\u2C60\u2C62-\u2C64\u2C67\u2C69\u2C6B\u2C6D-\u2C70\u2C72\u2C75\u2C7E\u2C7F\uA722\uA724\uA726\uA728\uA72A\uA72C\uA72E\uA732\uA734\uA736\uA738\uA73A\uA73C\uA73E\uA740\uA742\uA744\uA746\uA748\uA74A\uA74C\uA74E\uA750\uA752\uA754\uA756\uA758\uA75A\uA75C\uA75E\uA760\uA762\uA764\uA766\uA768\uA76A\uA76C\uA76E\uA779\uA77B\uA77D\uA77E\uA780\uA782\uA784\uA786\uA78B\uA78D\uA790\uA792\uA796\uA798\uA79A\uA79C\uA79E\uA7A0\uA7A2\uA7A4\uA7A6\uA7A8\uA7AA-\uA7AE\uA7B0-\uA7B4\uA7B6\uA7B8\u1E00\u1E02\u1E04\u1E06\u1E08\u1E0A\u1E0C\u1E0E\u1E10\u1E12\u1E14\u1E16\u1E18\u1E1A\u1E1C\u1E1E\u1E20\u1E22\u1E24\u1E26\u1E28\u1E2A\u1E2C\u1E2E\u1E30\u1E32\u1E34\u1E36\u1E38\u1E3A\u1E3C\u1E3E\u1E40\u1E42\u1E44\u1E46\u1E48\u1E4A\u1E4C\u1E4E\u1E50\u1E52\u1E54\u1E56\u1E58\u1E5A\u1E5C\u1E5E\u1E60\u1E62\u1E64\u1E66\u1E68\u1E6A\u1E6C\u1E6E\u1E70\u1E72\u1E74\u1E76\u1E78\u1E7A\u1E7C\u1E7E\u1E80\u1E82\u1E84\u1E86\u1E88\u1E8A\u1E8C\u1E8E\u1E90\u1E92\u1E94\u1E9E\u1EA0\u1EA2\u1EA4\u1EA6\u1EA8\u1EAA\u1EAC\u1EAE\u1EB0\u1EB2\u1EB4\u1EB6\u1EB8\u1EBA\u1EBC\u1EBE\u1EC0\u1EC2\u1EC4\u1EC6\u1EC8\u1ECA\u1ECC\u1ECE\u1ED0\u1ED2\u1ED4\u1ED6\u1ED8\u1EDA\u1EDC\u1EDE\u1EE0\u1EE2\u1EE4\u1EE6\u1EE8\u1EEA\u1EEC\u1EEE\u1EF0\u1EF2\u1EF4\u1EF6\u1EF8\u1EFA\u1EFC\u1EFEЁА-ЯӘӨҮҖҢҺΑ-ΩΆΈΊΌΏΉΎА-ЩЮЯІЇЄҐЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])\.$�infix_finditer�@�\.\.+|…|[\u00A6\u00A9\u00AE\u00B0\u0482\u058D\u058E\u060E\u060F\u06DE\u06E9\u06FD\u06FE\u07F6\u09FA\u0B70\u0BF3-\u0BF8\u0BFA\u0C7F\u0D4F\u0D79\u0F01-\u0F03\u0F13\u0F15-\u0F17\u0F1A-\u0F1F\u0F34\u0F36\u0F38\u0FBE-\u0FC5\u0FC7-\u0FCC\u0FCE\u0FCF\u0FD5-\u0FD8\u109E\u109F\u1390-\u1399\u1940\u19DE-\u19FF\u1B61-\u1B6A\u1B74-\u1B7C\u2100\u2101\u2103-\u2106\u2108\u2109\u2114\u2116\u2117\u211E-\u2123\u2125\u2127\u2129\u212E\u213A\u213B\u214A\u214C\u214D\u214F\u218A\u218B\u2195-\u2199\u219C-\u219F\u21A1\u21A2\u21A4\u21A5\u21A7-\u21AD\u21AF-\u21CD\u21D0\u21D1\u21D3\u21D5-\u21F3\u2300-\u2307\u230C-\u231F\u2322-\u2328\u232B-\u237B\u237D-\u239A\u23B4-\u23DB\u23E2-\u2426\u2440-\u244A\u249C-\u24E9\u2500-\u25B6\u25B8-\u25C0\u25C2-\u25F7\u2600-\u266E\u2670-\u2767\u2794-\u27BF\u2800-\u28FF\u2B00-\u2B2F\u2B45\u2B46\u2B4D-\u2B73\u2B76-\u2B95\u2B98-\u2BC8\u2BCA-\u2BFE\u2CE5-\u2CEA\u2E80-\u2E99\u2E9B-\u2EF3\u2F00-\u2FD5\u2FF0-\u2FFB\u3004\u3012\u3013\u3020\u3036\u3037\u303E\u303F\u3190\u3191\u3196-\u319F\u31C0-\u31E3\u3200-\u321E\u322A-\u3247\u3250\u3260-\u327F\u328A-\u32B0\u32C0-\u32FE\u3300-\u33FF\u4DC0-\u4DFF\uA490-\uA4C6\uA828-\uA82B\uA836\uA837\uA839\uAA77-\uAA79\uFDFD\uFFE4\uFFE8\uFFED\uFFEE\uFFFC\uFFFD\U00010137-\U0001013F\U00010179-\U00010189\U0001018C-\U0001018E\U00010190-\U0001019B\U000101A0\U000101D0-\U000101FC\U00010877\U00010878\U00010AC8\U0001173F\U00016B3C-\U00016B3F\U00016B45\U0001BC9C\U0001D000-\U0001D0F5\U0001D100-\U0001D126\U0001D129-\U0001D164\U0001D16A-\U0001D16C\U0001D183\U0001D184\U0001D18C-\U0001D1A9\U0001D1AE-\U0001D1E8\U0001D200-\U0001D241\U0001D245\U0001D300-\U0001D356\U0001D800-\U0001D9FF\U0001DA37-\U0001DA3A\U0001DA6D-\U0001DA74\U0001DA76-\U0001DA83\U0001DA85\U0001DA86\U0001ECAC\U0001F000-\U0001F02B\U0001F030-\U0001F093\U0001F0A0-\U0001F0AE\U0001F0B1-\U0001F0BF\U0001F0C1-\U0001F0CF\U0001F0D1-\U0001F0F5\U0001F110-\U0001F16B\U0001F170-\U0001F1AC\U0001F1E6-\U0001F202\U0001F210-\U0001F23B\U0001F240-\U0001F248\U0001F250\U0001F251\U0001F260-\U0001F265\U0001F300-\U0001F3FA\U0001F400-\U0001F6D4\U0001F6E0-\U0001F6EC\U0001F6F0-\U0001F6F9\U0001F700-\U0001F773\U0001F780-\U0001F7D8\U0001F800-\U0001F80B\U0001F810-\U0001F847\U0001F850-\U0001F859\U0001F860-\U0001F887\U0001F890-\U0001F8AD\U0001F900-\U0001F90B\U0001F910-\U0001F93E\U0001F940-\U0001F970\U0001F973-\U0001F976\U0001F97A\U0001F97C-\U0001F9A2\U0001F9B0-\U0001F9B9\U0001F9C0-\U0001F9C2\U0001F9D0-\U0001F9FF\U0001FA60-\U0001FA6D]|-|–|—|--|---|——|~|(?<=[0-9A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])\.(?=[0-9A-Z\uFF21-\uFF3A\u00C0-\u00D6\u00D8-\u00DE\u0100\u0102\u0104\u0106\u0108\u010A\u010C\u010E\u0110\u0112\u0114\u0116\u0118\u011A\u011C\u011E\u0120\u0122\u0124\u0126\u0128\u012A\u012C\u012E\u0130\u0132\u0134\u0136\u0139\u013B\u013D\u013F\u0141\u0143\u0145\u0147\u014A\u014C\u014E\u0150\u0152\u0154\u0156\u0158\u015A\u015C\u015E\u0160\u0162\u0164\u0166\u0168\u016A\u016C\u016E\u0170\u0172\u0174\u0176\u0178\u0179\u017B\u017D\u0181\u0182\u0184\u0186\u0187\u0189-\u018B\u018E-\u0191\u0193\u0194\u0196-\u0198\u019C\u019D\u019F\u01A0\u01A2\u01A4\u01A6\u01A7\u01A9\u01AC\u01AE\u01AF\u01B1-\u01B3\u01B5\u01B7\u01B8\u01BC\u01C4\u01C7\u01CA\u01CD\u01CF\u01D1\u01D3\u01D5\u01D7\u01D9\u01DB\u01DE\u01E0\u01E2\u01E4\u01E6\u01E8\u01EA\u01EC\u01EE\u01F1\u01F4\u01F6-\u01F8\u01FA\u01FC\u01FE\u0200\u0202\u0204\u0206\u0208\u020A\u020C\u020E\u0210\u0212\u0214\u0216\u0218\u021A\u021C\u021E\u0220\u0222\u0224\u0226\u0228\u022A\u022C\u022E\u0230\u0232\u023A\u023B\u023D\u023E\u0241\u0243-\u0246\u0248\u024A\u024C\u024E\u2C60\u2C62-\u2C64\u2C67\u2C69\u2C6B\u2C6D-\u2C70\u2C72\u2C75\u2C7E\u2C7F\uA722\uA724\uA726\uA728\uA72A\uA72C\uA72E\uA732\uA734\uA736\uA738\uA73A\uA73C\uA73E\uA740\uA742\uA744\uA746\uA748\uA74A\uA74C\uA74E\uA750\uA752\uA754\uA756\uA758\uA75A\uA75C\uA75E\uA760\uA762\uA764\uA766\uA768\uA76A\uA76C\uA76E\uA779\uA77B\uA77D\uA77E\uA780\uA782\uA784\uA786\uA78B\uA78D\uA790\uA792\uA796\uA798\uA79A\uA79C\uA79E\uA7A0\uA7A2\uA7A4\uA7A6\uA7A8\uA7AA-\uA7AE\uA7B0-\uA7B4\uA7B6\uA7B8\u1E00\u1E02\u1E04\u1E06\u1E08\u1E0A\u1E0C\u1E0E\u1E10\u1E12\u1E14\u1E16\u1E18\u1E1A\u1E1C\u1E1E\u1E20\u1E22\u1E24\u1E26\u1E28\u1E2A\u1E2C\u1E2E\u1E30\u1E32\u1E34\u1E36\u1E38\u1E3A\u1E3C\u1E3E\u1E40\u1E42\u1E44\u1E46\u1E48\u1E4A\u1E4C\u1E4E\u1E50\u1E52\u1E54\u1E56\u1E58\u1E5A\u1E5C\u1E5E\u1E60\u1E62\u1E64\u1E66\u1E68\u1E6A\u1E6C\u1E6E\u1E70\u1E72\u1E74\u1E76\u1E78\u1E7A\u1E7C\u1E7E\u1E80\u1E82\u1E84\u1E86\u1E88\u1E8A\u1E8C\u1E8E\u1E90\u1E92\u1E94\u1E9E\u1EA0\u1EA2\u1EA4\u1EA6\u1EA8\u1EAA\u1EAC\u1EAE\u1EB0\u1EB2\u1EB4\u1EB6\u1EB8\u1EBA\u1EBC\u1EBE\u1EC0\u1EC2\u1EC4\u1EC6\u1EC8\u1ECA\u1ECC\u1ECE\u1ED0\u1ED2\u1ED4\u1ED6\u1ED8\u1EDA\u1EDC\u1EDE\u1EE0\u1EE2\u1EE4\u1EE6\u1EE8\u1EEA\u1EEC\u1EEE\u1EF0\u1EF2\u1EF4\u1EF6\u1EF8\u1EFA\u1EFC\u1EFEЁА-ЯӘӨҮҖҢҺΑ-ΩΆΈΊΌΏΉΎА-ЩЮЯІЇЄҐЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])|(?<=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])[,!?](?=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])|(?<=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])[:<>=\/](?=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])|(?<=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F]),(?=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])|(?<=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])([\"”“`‘´’‚,„»«「」『』()〔〕【】《》〈〉\)\]\(\[])(?=[\-A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])�token_match��url_match�
2
  ��A�
3
  � ��A� �'��A�'�''��A�''�(*_*)��A�(*_*)�(-8��A�(-8�(-:��A�(-:�(-;��A�(-;�(-_-)��A�(-_-)�(._.)��A�(._.)�(:��A�(:�(;��A�(;�(=��A�(=�(>_<)��A�(>_<)�(^_^)��A�(^_^)�(o:��A�(o:�(¬_¬)��A�(¬_¬)�(ಠ_ಠ)��A�(ಠ_ಠ)�(╯°□°)╯︵┻━┻��A�(╯°□°)╯︵┻━┻�)-:��A�)-:�):��A�):�-_-��A�-_-�-__-��A�-__-�0.0��A�0.0�0.o��A�0.o�0_0��A�0_0�0_o��A�0_o�8)��A�8)�8-)��A�8-)�8-D��A�8-D�8D��A�8D�:'(��A�:'(�:')��A�:')�:'-(��A�:'-(�:'-)��A�:'-)�:(��A�:(�:((��A�:((�:(((��A�:(((�:()��A�:()�:)��A�:)�:))��A�:))�:)))��A�:)))�:*��A�:*�:-(��A�:-(�:-((��A�:-((�:-(((��A�:-(((�:-)��A�:-)�:-))��A�:-))�:-)))��A�:-)))�:-*��A�:-*�:-/��A�:-/�:-0��A�:-0�:-3��A�:-3�:->��A�:->�:-D��A�:-D�:-O��A�:-O�:-P��A�:-P�:-X��A�:-X�:-]��A�:-]�:-o��A�:-o�:-p��A�:-p�:-x��A�:-x�:-|��A�:-|�:-}��A�:-}�:/��A�:/�:0��A�:0�:1��A�:1�:3��A�:3�:>��A�:>�:D��A�:D�:O��A�:O�:P��A�:P�:X��A�:X�:]��A�:]�:o��A�:o�:o)��A�:o)�:p��A�:p�:x��A�:x�:|��A�:|�:}��A�:}�;)��A�;)�;-)��A�;-)�;-D��A�;-D�;D��A�;D�;_;��A�;_;�<.<��A�<.<�</3��A�</3�<3��A�<3�<33��A�<33�<333��A�<333�<space>��A�<space>�=(��A�=(�=)��A�=)�=/��A�=/�=3��A�=3�=D��A�=D�=[��A�=[�=]��A�=]�=|��A�=|�>.<��A�>.<�>.>��A�>.>�>:(��A�>:(�>:o��A�>:o�><(((*>��A�><(((*>�@_@��A�@_@�C++��A�C++�O.O��A�O.O�O.o��A�O.o�O_O��A�O_O�O_o��A�O_o�V.V��A�V.V�V_V��A�V_V�XD��A�XD�XDD��A�XDD�[-:��A�[-:�[:��A�[:�[=��A�[=�\")��A�\")�\n��A�\n�\t��A�\t�]=��A�]=�^_^��A�^_^�^__^��A�^__^�^___^��A�^___^�o.0��A�o.0�o.O��A�o.O�o.o��A�o.o�o_0��A�o_0�o_O��A�o_O�o_o��A�o_o�v.v��A�v.v�v_v��A�v_v�xD��A�xD�xDD��A�xDD� ��A� C� �¯\(ツ)/¯��A�¯\(ツ)/¯�ಠ_ಠ��A�ಠ_ಠ�ಠ︵ಠ��A�ಠ︵ಠ�—��A�—�faster_heuristics�
1
+ ��prefix_search� �^(długo|krótko|jedno|dwu|trzy|cztero)-|^§|^%|^=|^—|^–|^\+(?![0-9])|^…|^……|^,|^:|^;|^\!|^\?|^¿|^؟|^¡|^\(|^\)|^\[|^\]|^\{|^\}|^<|^>|^_|^#|^\*|^&|^。|^?|^!|^,|^、|^;|^:|^~|^·|^।|^،|^۔|^؛|^٪|^\.\.+|^…|^\'|^"|^”|^“|^`|^‘|^´|^’|^‚|^,|^„|^»|^«|^「|^」|^『|^』|^(|^)|^〔|^〕|^【|^】|^《|^》|^〈|^〉|^〈|^〉|^⟦|^⟧|^\$|^£|^€|^¥|^฿|^US\$|^C\$|^A\$|^₽|^﷼|^₴|^₠|^₡|^₢|^₣|^₤|^₥|^₦|^₧|^₨|^₩|^₪|^₫|^€|^₭|^₮|^₯|^₰|^₱|^₲|^₳|^₴|^₵|^₶|^₷|^₸|^₹|^₺|^₻|^₼|^₽|^₾|^₿|^[\u00A6\u00A9\u00AE\u00B0\u0482\u058D\u058E\u060E\u060F\u06DE\u06E9\u06FD\u06FE\u07F6\u09FA\u0B70\u0BF3-\u0BF8\u0BFA\u0C7F\u0D4F\u0D79\u0F01-\u0F03\u0F13\u0F15-\u0F17\u0F1A-\u0F1F\u0F34\u0F36\u0F38\u0FBE-\u0FC5\u0FC7-\u0FCC\u0FCE\u0FCF\u0FD5-\u0FD8\u109E\u109F\u1390-\u1399\u1940\u19DE-\u19FF\u1B61-\u1B6A\u1B74-\u1B7C\u2100\u2101\u2103-\u2106\u2108\u2109\u2114\u2116\u2117\u211E-\u2123\u2125\u2127\u2129\u212E\u213A\u213B\u214A\u214C\u214D\u214F\u218A\u218B\u2195-\u2199\u219C-\u219F\u21A1\u21A2\u21A4\u21A5\u21A7-\u21AD\u21AF-\u21CD\u21D0\u21D1\u21D3\u21D5-\u21F3\u2300-\u2307\u230C-\u231F\u2322-\u2328\u232B-\u237B\u237D-\u239A\u23B4-\u23DB\u23E2-\u2426\u2440-\u244A\u249C-\u24E9\u2500-\u25B6\u25B8-\u25C0\u25C2-\u25F7\u2600-\u266E\u2670-\u2767\u2794-\u27BF\u2800-\u28FF\u2B00-\u2B2F\u2B45\u2B46\u2B4D-\u2B73\u2B76-\u2B95\u2B98-\u2BC8\u2BCA-\u2BFE\u2CE5-\u2CEA\u2E80-\u2E99\u2E9B-\u2EF3\u2F00-\u2FD5\u2FF0-\u2FFB\u3004\u3012\u3013\u3020\u3036\u3037\u303E\u303F\u3190\u3191\u3196-\u319F\u31C0-\u31E3\u3200-\u321E\u322A-\u3247\u3250\u3260-\u327F\u328A-\u32B0\u32C0-\u32FE\u3300-\u33FF\u4DC0-\u4DFF\uA490-\uA4C6\uA828-\uA82B\uA836\uA837\uA839\uAA77-\uAA79\uFDFD\uFFE4\uFFE8\uFFED\uFFEE\uFFFC\uFFFD\U00010137-\U0001013F\U00010179-\U00010189\U0001018C-\U0001018E\U00010190-\U0001019B\U000101A0\U000101D0-\U000101FC\U00010877\U00010878\U00010AC8\U0001173F\U00016B3C-\U00016B3F\U00016B45\U0001BC9C\U0001D000-\U0001D0F5\U0001D100-\U0001D126\U0001D129-\U0001D164\U0001D16A-\U0001D16C\U0001D183\U0001D184\U0001D18C-\U0001D1A9\U0001D1AE-\U0001D1E8\U0001D200-\U0001D241\U0001D245\U0001D300-\U0001D356\U0001D800-\U0001D9FF\U0001DA37-\U0001DA3A\U0001DA6D-\U0001DA74\U0001DA76-\U0001DA83\U0001DA85\U0001DA86\U0001ECAC\U0001F000-\U0001F02B\U0001F030-\U0001F093\U0001F0A0-\U0001F0AE\U0001F0B1-\U0001F0BF\U0001F0C1-\U0001F0CF\U0001F0D1-\U0001F0F5\U0001F110-\U0001F16B\U0001F170-\U0001F1AC\U0001F1E6-\U0001F202\U0001F210-\U0001F23B\U0001F240-\U0001F248\U0001F250\U0001F251\U0001F260-\U0001F265\U0001F300-\U0001F3FA\U0001F400-\U0001F6D4\U0001F6E0-\U0001F6EC\U0001F6F0-\U0001F6F9\U0001F700-\U0001F773\U0001F780-\U0001F7D8\U0001F800-\U0001F80B\U0001F810-\U0001F847\U0001F850-\U0001F859\U0001F860-\U0001F887\U0001F890-\U0001F8AD\U0001F900-\U0001F90B\U0001F910-\U0001F93E\U0001F940-\U0001F970\U0001F973-\U0001F976\U0001F97A\U0001F97C-\U0001F9A2\U0001F9B0-\U0001F9B9\U0001F9C0-\U0001F9C2\U0001F9D0-\U0001F9FF\U0001FA60-\U0001FA6D]�suffix_search�&�''$|’’$|\.$|…$|…$|……$|,$|:$|;$|\!$|\?$|¿$|؟$|¡$|\($|\)$|\[$|\]$|\{$|\}$|<$|>$|_$|#$|\*$|&$|。$|?$|!$|,$|、$|;$|:$|~$|·$|।$|،$|۔$|؛$|٪$|\'$|"$|”$|“$|`$|‘$|´$|’$|‚$|,$|„$|»$|«$|「$|」$|『$|』$|($|)$|〔$|〕$|【$|】$|《$|》$|〈$|〉$|〈$|〉$|⟦$|⟧$|[\u00A6\u00A9\u00AE\u00B0\u0482\u058D\u058E\u060E\u060F\u06DE\u06E9\u06FD\u06FE\u07F6\u09FA\u0B70\u0BF3-\u0BF8\u0BFA\u0C7F\u0D4F\u0D79\u0F01-\u0F03\u0F13\u0F15-\u0F17\u0F1A-\u0F1F\u0F34\u0F36\u0F38\u0FBE-\u0FC5\u0FC7-\u0FCC\u0FCE\u0FCF\u0FD5-\u0FD8\u109E\u109F\u1390-\u1399\u1940\u19DE-\u19FF\u1B61-\u1B6A\u1B74-\u1B7C\u2100\u2101\u2103-\u2106\u2108\u2109\u2114\u2116\u2117\u211E-\u2123\u2125\u2127\u2129\u212E\u213A\u213B\u214A\u214C\u214D\u214F\u218A\u218B\u2195-\u2199\u219C-\u219F\u21A1\u21A2\u21A4\u21A5\u21A7-\u21AD\u21AF-\u21CD\u21D0\u21D1\u21D3\u21D5-\u21F3\u2300-\u2307\u230C-\u231F\u2322-\u2328\u232B-\u237B\u237D-\u239A\u23B4-\u23DB\u23E2-\u2426\u2440-\u244A\u249C-\u24E9\u2500-\u25B6\u25B8-\u25C0\u25C2-\u25F7\u2600-\u266E\u2670-\u2767\u2794-\u27BF\u2800-\u28FF\u2B00-\u2B2F\u2B45\u2B46\u2B4D-\u2B73\u2B76-\u2B95\u2B98-\u2BC8\u2BCA-\u2BFE\u2CE5-\u2CEA\u2E80-\u2E99\u2E9B-\u2EF3\u2F00-\u2FD5\u2FF0-\u2FFB\u3004\u3012\u3013\u3020\u3036\u3037\u303E\u303F\u3190\u3191\u3196-\u319F\u31C0-\u31E3\u3200-\u321E\u322A-\u3247\u3250\u3260-\u327F\u328A-\u32B0\u32C0-\u32FE\u3300-\u33FF\u4DC0-\u4DFF\uA490-\uA4C6\uA828-\uA82B\uA836\uA837\uA839\uAA77-\uAA79\uFDFD\uFFE4\uFFE8\uFFED\uFFEE\uFFFC\uFFFD\U00010137-\U0001013F\U00010179-\U00010189\U0001018C-\U0001018E\U00010190-\U0001019B\U000101A0\U000101D0-\U000101FC\U00010877\U00010878\U00010AC8\U0001173F\U00016B3C-\U00016B3F\U00016B45\U0001BC9C\U0001D000-\U0001D0F5\U0001D100-\U0001D126\U0001D129-\U0001D164\U0001D16A-\U0001D16C\U0001D183\U0001D184\U0001D18C-\U0001D1A9\U0001D1AE-\U0001D1E8\U0001D200-\U0001D241\U0001D245\U0001D300-\U0001D356\U0001D800-\U0001D9FF\U0001DA37-\U0001DA3A\U0001DA6D-\U0001DA74\U0001DA76-\U0001DA83\U0001DA85\U0001DA86\U0001ECAC\U0001F000-\U0001F02B\U0001F030-\U0001F093\U0001F0A0-\U0001F0AE\U0001F0B1-\U0001F0BF\U0001F0C1-\U0001F0CF\U0001F0D1-\U0001F0F5\U0001F110-\U0001F16B\U0001F170-\U0001F1AC\U0001F1E6-\U0001F202\U0001F210-\U0001F23B\U0001F240-\U0001F248\U0001F250\U0001F251\U0001F260-\U0001F265\U0001F300-\U0001F3FA\U0001F400-\U0001F6D4\U0001F6E0-\U0001F6EC\U0001F6F0-\U0001F6F9\U0001F700-\U0001F773\U0001F780-\U0001F7D8\U0001F800-\U0001F80B\U0001F810-\U0001F847\U0001F850-\U0001F859\U0001F860-\U0001F887\U0001F890-\U0001F8AD\U0001F900-\U0001F90B\U0001F910-\U0001F93E\U0001F940-\U0001F970\U0001F973-\U0001F976\U0001F97A\U0001F97C-\U0001F9A2\U0001F9B0-\U0001F9B9\U0001F9C0-\U0001F9C2\U0001F9D0-\U0001F9FF\U0001FA60-\U0001FA6D]$|(?<=[0-9])\+$|(?<=°[FfCcKk])\.$|(?<=[0-9])(?:\$|£|€|¥|฿|US\$|C\$|A\$|₽|﷼|₴|₠|₡|₢|₣|₤|₥|₦|₧|₨|₩|₪|₫|€|₭|₮|₯|₰|₱|₲|₳|₴|₵|₶|₷|₸|₹|₺|₻|₼|₽|₾|₿)$|(?<=[0-9])(?:km|km²|km³|m|m²|m³|dm|dm²|dm³|cm|cm²|cm³|mm|mm²|mm³|ha|µm|nm|yd|in|ft|kg|g|mg|µg|t|lb|oz|m/s|km/h|kmh|mph|hPa|Pa|mbar|mb|MB|kb|KB|gb|GB|tb|TB|T|G|M|K|%|км|км²|км³|м|м²|м³|дм|дм²|дм³|см|см²|см³|мм|мм²|мм³|нм|кг|г|мг|м/с|км/ч|кПа|Па|мбар|Кб|КБ|кб|Мб|МБ|мб|Гб|ГБ|гб|Тб|ТБ|тбكم|كم²|كم³|م|م²|م³|سم|سم²|سم³|مم|مم²|مم³|كم|غرام|جرام|جم|كغ|ملغ|كوب|اكواب)$|(?<=[0-9a-z\uFF41-\uFF5A\u00DF-\u00F6\u00F8-\u00FF\u0101\u0103\u0105\u0107\u0109\u010B\u010D\u010F\u0111\u0113\u0115\u0117\u0119\u011B\u011D\u011F\u0121\u0123\u0125\u0127\u0129\u012B\u012D\u012F\u0131\u0133\u0135\u0137\u0138\u013A\u013C\u013E\u0140\u0142\u0144\u0146\u0148\u0149\u014B\u014D\u014F\u0151\u0153\u0155\u0157\u0159\u015B\u015D\u015F\u0161\u0163\u0165\u0167\u0169\u016B\u016D\u016F\u0171\u0173\u0175\u0177\u017A\u017C\u017E\u017F\u0180\u0183\u0185\u0188\u018C\u018D\u0192\u0195\u0199-\u019B\u019E\u01A1\u01A3\u01A5\u01A8\u01AA\u01AB\u01AD\u01B0\u01B4\u01B6\u01B9\u01BA\u01BD-\u01BF\u01C6\u01C9\u01CC\u01CE\u01D0\u01D2\u01D4\u01D6\u01D8\u01DA\u01DC\u01DD\u01DF\u01E1\u01E3\u01E5\u01E7\u01E9\u01EB\u01ED\u01EF\u01F0\u01F3\u01F5\u01F9\u01FB\u01FD\u01FF\u0201\u0203\u0205\u0207\u0209\u020B\u020D\u020F\u0211\u0213\u0215\u0217\u0219\u021B\u021D\u021F\u0221\u0223\u0225\u0227\u0229\u022B\u022D\u022F\u0231\u0233-\u0239\u023C\u023F\u0240\u0242\u0247\u0249\u024B\u024D\u024F\u2C61\u2C65\u2C66\u2C68\u2C6A\u2C6C\u2C71\u2C73\u2C74\u2C76-\u2C7B\uA723\uA725\uA727\uA729\uA72B\uA72D\uA72F-\uA731\uA733\uA735\uA737\uA739\uA73B\uA73D\uA73F\uA741\uA743\uA745\uA747\uA749\uA74B\uA74D\uA74F\uA751\uA753\uA755\uA757\uA759\uA75B\uA75D\uA75F\uA761\uA763\uA765\uA767\uA769\uA76B\uA76D\uA76F\uA771-\uA778\uA77A\uA77C\uA77F\uA781\uA783\uA785\uA787\uA78C\uA78E\uA791\uA793-\uA795\uA797\uA799\uA79B\uA79D\uA79F\uA7A1\uA7A3\uA7A5\uA7A7\uA7A9\uA7AF\uA7B5\uA7B7\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E01\u1E03\u1E05\u1E07\u1E09\u1E0B\u1E0D\u1E0F\u1E11\u1E13\u1E15\u1E17\u1E19\u1E1B\u1E1D\u1E1F\u1E21\u1E23\u1E25\u1E27\u1E29\u1E2B\u1E2D\u1E2F\u1E31\u1E33\u1E35\u1E37\u1E39\u1E3B\u1E3D\u1E3F\u1E41\u1E43\u1E45\u1E47\u1E49\u1E4B\u1E4D\u1E4F\u1E51\u1E53\u1E55\u1E57\u1E59\u1E5B\u1E5D\u1E5F\u1E61\u1E63\u1E65\u1E67\u1E69\u1E6B\u1E6D\u1E6F\u1E71\u1E73\u1E75\u1E77\u1E79\u1E7B\u1E7D\u1E7F\u1E81\u1E83\u1E85\u1E87\u1E89\u1E8B\u1E8D\u1E8F\u1E91\u1E93\u1E95-\u1E9D\u1E9F\u1EA1\u1EA3\u1EA5\u1EA7\u1EA9\u1EAB\u1EAD\u1EAF\u1EB1\u1EB3\u1EB5\u1EB7\u1EB9\u1EBB\u1EBD\u1EBF\u1EC1\u1EC3\u1EC5\u1EC7\u1EC9\u1ECB\u1ECD\u1ECF\u1ED1\u1ED3\u1ED5\u1ED7\u1ED9\u1EDB\u1EDD\u1EDF\u1EE1\u1EE3\u1EE5\u1EE7\u1EE9\u1EEB\u1EED\u1EEF\u1EF1\u1EF3\u1EF5\u1EF7\u1EF9\u1EFB\u1EFD\u1EFFёа-яәөүҗңһα-ωάέίόώήύа-щюяіїєґѓѕјљњќѐѝ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F%²\-\+…|……|,|:|;|\!|\?|¿|؟|¡|\(|\)|\[|\]|\{|\}|<|>|_|#|\*|&|。|?|!|,|、|;|:|~|·|।|،|۔|؛|٪(?:\'"”“`‘´’‚,„»«「」『』()〔〕【】《》〈〉〈〉⟦⟧)])\.$|(?<=[A-Z\uFF21-\uFF3A\u00C0-\u00D6\u00D8-\u00DE\u0100\u0102\u0104\u0106\u0108\u010A\u010C\u010E\u0110\u0112\u0114\u0116\u0118\u011A\u011C\u011E\u0120\u0122\u0124\u0126\u0128\u012A\u012C\u012E\u0130\u0132\u0134\u0136\u0139\u013B\u013D\u013F\u0141\u0143\u0145\u0147\u014A\u014C\u014E\u0150\u0152\u0154\u0156\u0158\u015A\u015C\u015E\u0160\u0162\u0164\u0166\u0168\u016A\u016C\u016E\u0170\u0172\u0174\u0176\u0178\u0179\u017B\u017D\u0181\u0182\u0184\u0186\u0187\u0189-\u018B\u018E-\u0191\u0193\u0194\u0196-\u0198\u019C\u019D\u019F\u01A0\u01A2\u01A4\u01A6\u01A7\u01A9\u01AC\u01AE\u01AF\u01B1-\u01B3\u01B5\u01B7\u01B8\u01BC\u01C4\u01C7\u01CA\u01CD\u01CF\u01D1\u01D3\u01D5\u01D7\u01D9\u01DB\u01DE\u01E0\u01E2\u01E4\u01E6\u01E8\u01EA\u01EC\u01EE\u01F1\u01F4\u01F6-\u01F8\u01FA\u01FC\u01FE\u0200\u0202\u0204\u0206\u0208\u020A\u020C\u020E\u0210\u0212\u0214\u0216\u0218\u021A\u021C\u021E\u0220\u0222\u0224\u0226\u0228\u022A\u022C\u022E\u0230\u0232\u023A\u023B\u023D\u023E\u0241\u0243-\u0246\u0248\u024A\u024C\u024E\u2C60\u2C62-\u2C64\u2C67\u2C69\u2C6B\u2C6D-\u2C70\u2C72\u2C75\u2C7E\u2C7F\uA722\uA724\uA726\uA728\uA72A\uA72C\uA72E\uA732\uA734\uA736\uA738\uA73A\uA73C\uA73E\uA740\uA742\uA744\uA746\uA748\uA74A\uA74C\uA74E\uA750\uA752\uA754\uA756\uA758\uA75A\uA75C\uA75E\uA760\uA762\uA764\uA766\uA768\uA76A\uA76C\uA76E\uA779\uA77B\uA77D\uA77E\uA780\uA782\uA784\uA786\uA78B\uA78D\uA790\uA792\uA796\uA798\uA79A\uA79C\uA79E\uA7A0\uA7A2\uA7A4\uA7A6\uA7A8\uA7AA-\uA7AE\uA7B0-\uA7B4\uA7B6\uA7B8\u1E00\u1E02\u1E04\u1E06\u1E08\u1E0A\u1E0C\u1E0E\u1E10\u1E12\u1E14\u1E16\u1E18\u1E1A\u1E1C\u1E1E\u1E20\u1E22\u1E24\u1E26\u1E28\u1E2A\u1E2C\u1E2E\u1E30\u1E32\u1E34\u1E36\u1E38\u1E3A\u1E3C\u1E3E\u1E40\u1E42\u1E44\u1E46\u1E48\u1E4A\u1E4C\u1E4E\u1E50\u1E52\u1E54\u1E56\u1E58\u1E5A\u1E5C\u1E5E\u1E60\u1E62\u1E64\u1E66\u1E68\u1E6A\u1E6C\u1E6E\u1E70\u1E72\u1E74\u1E76\u1E78\u1E7A\u1E7C\u1E7E\u1E80\u1E82\u1E84\u1E86\u1E88\u1E8A\u1E8C\u1E8E\u1E90\u1E92\u1E94\u1E9E\u1EA0\u1EA2\u1EA4\u1EA6\u1EA8\u1EAA\u1EAC\u1EAE\u1EB0\u1EB2\u1EB4\u1EB6\u1EB8\u1EBA\u1EBC\u1EBE\u1EC0\u1EC2\u1EC4\u1EC6\u1EC8\u1ECA\u1ECC\u1ECE\u1ED0\u1ED2\u1ED4\u1ED6\u1ED8\u1EDA\u1EDC\u1EDE\u1EE0\u1EE2\u1EE4\u1EE6\u1EE8\u1EEA\u1EEC\u1EEE\u1EF0\u1EF2\u1EF4\u1EF6\u1EF8\u1EFA\u1EFC\u1EFEЁА-ЯӘӨҮҖҢҺΑ-ΩΆΈΊΌΏΉΎА-ЩЮЯІЇЄҐЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])\.$�infix_finditer�@�\.\.+|…|[\u00A6\u00A9\u00AE\u00B0\u0482\u058D\u058E\u060E\u060F\u06DE\u06E9\u06FD\u06FE\u07F6\u09FA\u0B70\u0BF3-\u0BF8\u0BFA\u0C7F\u0D4F\u0D79\u0F01-\u0F03\u0F13\u0F15-\u0F17\u0F1A-\u0F1F\u0F34\u0F36\u0F38\u0FBE-\u0FC5\u0FC7-\u0FCC\u0FCE\u0FCF\u0FD5-\u0FD8\u109E\u109F\u1390-\u1399\u1940\u19DE-\u19FF\u1B61-\u1B6A\u1B74-\u1B7C\u2100\u2101\u2103-\u2106\u2108\u2109\u2114\u2116\u2117\u211E-\u2123\u2125\u2127\u2129\u212E\u213A\u213B\u214A\u214C\u214D\u214F\u218A\u218B\u2195-\u2199\u219C-\u219F\u21A1\u21A2\u21A4\u21A5\u21A7-\u21AD\u21AF-\u21CD\u21D0\u21D1\u21D3\u21D5-\u21F3\u2300-\u2307\u230C-\u231F\u2322-\u2328\u232B-\u237B\u237D-\u239A\u23B4-\u23DB\u23E2-\u2426\u2440-\u244A\u249C-\u24E9\u2500-\u25B6\u25B8-\u25C0\u25C2-\u25F7\u2600-\u266E\u2670-\u2767\u2794-\u27BF\u2800-\u28FF\u2B00-\u2B2F\u2B45\u2B46\u2B4D-\u2B73\u2B76-\u2B95\u2B98-\u2BC8\u2BCA-\u2BFE\u2CE5-\u2CEA\u2E80-\u2E99\u2E9B-\u2EF3\u2F00-\u2FD5\u2FF0-\u2FFB\u3004\u3012\u3013\u3020\u3036\u3037\u303E\u303F\u3190\u3191\u3196-\u319F\u31C0-\u31E3\u3200-\u321E\u322A-\u3247\u3250\u3260-\u327F\u328A-\u32B0\u32C0-\u32FE\u3300-\u33FF\u4DC0-\u4DFF\uA490-\uA4C6\uA828-\uA82B\uA836\uA837\uA839\uAA77-\uAA79\uFDFD\uFFE4\uFFE8\uFFED\uFFEE\uFFFC\uFFFD\U00010137-\U0001013F\U00010179-\U00010189\U0001018C-\U0001018E\U00010190-\U0001019B\U000101A0\U000101D0-\U000101FC\U00010877\U00010878\U00010AC8\U0001173F\U00016B3C-\U00016B3F\U00016B45\U0001BC9C\U0001D000-\U0001D0F5\U0001D100-\U0001D126\U0001D129-\U0001D164\U0001D16A-\U0001D16C\U0001D183\U0001D184\U0001D18C-\U0001D1A9\U0001D1AE-\U0001D1E8\U0001D200-\U0001D241\U0001D245\U0001D300-\U0001D356\U0001D800-\U0001D9FF\U0001DA37-\U0001DA3A\U0001DA6D-\U0001DA74\U0001DA76-\U0001DA83\U0001DA85\U0001DA86\U0001ECAC\U0001F000-\U0001F02B\U0001F030-\U0001F093\U0001F0A0-\U0001F0AE\U0001F0B1-\U0001F0BF\U0001F0C1-\U0001F0CF\U0001F0D1-\U0001F0F5\U0001F110-\U0001F16B\U0001F170-\U0001F1AC\U0001F1E6-\U0001F202\U0001F210-\U0001F23B\U0001F240-\U0001F248\U0001F250\U0001F251\U0001F260-\U0001F265\U0001F300-\U0001F3FA\U0001F400-\U0001F6D4\U0001F6E0-\U0001F6EC\U0001F6F0-\U0001F6F9\U0001F700-\U0001F773\U0001F780-\U0001F7D8\U0001F800-\U0001F80B\U0001F810-\U0001F847\U0001F850-\U0001F859\U0001F860-\U0001F887\U0001F890-\U0001F8AD\U0001F900-\U0001F90B\U0001F910-\U0001F93E\U0001F940-\U0001F970\U0001F973-\U0001F976\U0001F97A\U0001F97C-\U0001F9A2\U0001F9B0-\U0001F9B9\U0001F9C0-\U0001F9C2\U0001F9D0-\U0001F9FF\U0001FA60-\U0001FA6D]|-|–|—|--|---|——|~|(?<=[0-9A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])\.(?=[0-9A-Z\uFF21-\uFF3A\u00C0-\u00D6\u00D8-\u00DE\u0100\u0102\u0104\u0106\u0108\u010A\u010C\u010E\u0110\u0112\u0114\u0116\u0118\u011A\u011C\u011E\u0120\u0122\u0124\u0126\u0128\u012A\u012C\u012E\u0130\u0132\u0134\u0136\u0139\u013B\u013D\u013F\u0141\u0143\u0145\u0147\u014A\u014C\u014E\u0150\u0152\u0154\u0156\u0158\u015A\u015C\u015E\u0160\u0162\u0164\u0166\u0168\u016A\u016C\u016E\u0170\u0172\u0174\u0176\u0178\u0179\u017B\u017D\u0181\u0182\u0184\u0186\u0187\u0189-\u018B\u018E-\u0191\u0193\u0194\u0196-\u0198\u019C\u019D\u019F\u01A0\u01A2\u01A4\u01A6\u01A7\u01A9\u01AC\u01AE\u01AF\u01B1-\u01B3\u01B5\u01B7\u01B8\u01BC\u01C4\u01C7\u01CA\u01CD\u01CF\u01D1\u01D3\u01D5\u01D7\u01D9\u01DB\u01DE\u01E0\u01E2\u01E4\u01E6\u01E8\u01EA\u01EC\u01EE\u01F1\u01F4\u01F6-\u01F8\u01FA\u01FC\u01FE\u0200\u0202\u0204\u0206\u0208\u020A\u020C\u020E\u0210\u0212\u0214\u0216\u0218\u021A\u021C\u021E\u0220\u0222\u0224\u0226\u0228\u022A\u022C\u022E\u0230\u0232\u023A\u023B\u023D\u023E\u0241\u0243-\u0246\u0248\u024A\u024C\u024E\u2C60\u2C62-\u2C64\u2C67\u2C69\u2C6B\u2C6D-\u2C70\u2C72\u2C75\u2C7E\u2C7F\uA722\uA724\uA726\uA728\uA72A\uA72C\uA72E\uA732\uA734\uA736\uA738\uA73A\uA73C\uA73E\uA740\uA742\uA744\uA746\uA748\uA74A\uA74C\uA74E\uA750\uA752\uA754\uA756\uA758\uA75A\uA75C\uA75E\uA760\uA762\uA764\uA766\uA768\uA76A\uA76C\uA76E\uA779\uA77B\uA77D\uA77E\uA780\uA782\uA784\uA786\uA78B\uA78D\uA790\uA792\uA796\uA798\uA79A\uA79C\uA79E\uA7A0\uA7A2\uA7A4\uA7A6\uA7A8\uA7AA-\uA7AE\uA7B0-\uA7B4\uA7B6\uA7B8\u1E00\u1E02\u1E04\u1E06\u1E08\u1E0A\u1E0C\u1E0E\u1E10\u1E12\u1E14\u1E16\u1E18\u1E1A\u1E1C\u1E1E\u1E20\u1E22\u1E24\u1E26\u1E28\u1E2A\u1E2C\u1E2E\u1E30\u1E32\u1E34\u1E36\u1E38\u1E3A\u1E3C\u1E3E\u1E40\u1E42\u1E44\u1E46\u1E48\u1E4A\u1E4C\u1E4E\u1E50\u1E52\u1E54\u1E56\u1E58\u1E5A\u1E5C\u1E5E\u1E60\u1E62\u1E64\u1E66\u1E68\u1E6A\u1E6C\u1E6E\u1E70\u1E72\u1E74\u1E76\u1E78\u1E7A\u1E7C\u1E7E\u1E80\u1E82\u1E84\u1E86\u1E88\u1E8A\u1E8C\u1E8E\u1E90\u1E92\u1E94\u1E9E\u1EA0\u1EA2\u1EA4\u1EA6\u1EA8\u1EAA\u1EAC\u1EAE\u1EB0\u1EB2\u1EB4\u1EB6\u1EB8\u1EBA\u1EBC\u1EBE\u1EC0\u1EC2\u1EC4\u1EC6\u1EC8\u1ECA\u1ECC\u1ECE\u1ED0\u1ED2\u1ED4\u1ED6\u1ED8\u1EDA\u1EDC\u1EDE\u1EE0\u1EE2\u1EE4\u1EE6\u1EE8\u1EEA\u1EEC\u1EEE\u1EF0\u1EF2\u1EF4\u1EF6\u1EF8\u1EFA\u1EFC\u1EFEЁА-ЯӘӨҮҖҢҺΑ-ΩΆΈΊΌΏΉΎА-ЩЮЯІЇЄҐЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])|(?<=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])[,!?](?=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])|(?<=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])[:<>=\/](?=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])|(?<=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F]),(?=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])|(?<=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])([\"”“`‘´’‚,„»«「」『』()〔〕【】《》〈〉〈〉⟦⟧\)\]\(\[])(?=[\-A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])�token_match��url_match�
2
  ��A�
3
  � ��A� �'��A�'�''��A�''�(*_*)��A�(*_*)�(-8��A�(-8�(-:��A�(-:�(-;��A�(-;�(-_-)��A�(-_-)�(._.)��A�(._.)�(:��A�(:�(;��A�(;�(=��A�(=�(>_<)��A�(>_<)�(^_^)��A�(^_^)�(o:��A�(o:�(¬_¬)��A�(¬_¬)�(ಠ_ಠ)��A�(ಠ_ಠ)�(╯°□°)╯︵┻━┻��A�(╯°□°)╯︵┻━┻�)-:��A�)-:�):��A�):�-_-��A�-_-�-__-��A�-__-�0.0��A�0.0�0.o��A�0.o�0_0��A�0_0�0_o��A�0_o�8)��A�8)�8-)��A�8-)�8-D��A�8-D�8D��A�8D�:'(��A�:'(�:')��A�:')�:'-(��A�:'-(�:'-)��A�:'-)�:(��A�:(�:((��A�:((�:(((��A�:(((�:()��A�:()�:)��A�:)�:))��A�:))�:)))��A�:)))�:*��A�:*�:-(��A�:-(�:-((��A�:-((�:-(((��A�:-(((�:-)��A�:-)�:-))��A�:-))�:-)))��A�:-)))�:-*��A�:-*�:-/��A�:-/�:-0��A�:-0�:-3��A�:-3�:->��A�:->�:-D��A�:-D�:-O��A�:-O�:-P��A�:-P�:-X��A�:-X�:-]��A�:-]�:-o��A�:-o�:-p��A�:-p�:-x��A�:-x�:-|��A�:-|�:-}��A�:-}�:/��A�:/�:0��A�:0�:1��A�:1�:3��A�:3�:>��A�:>�:D��A�:D�:O��A�:O�:P��A�:P�:X��A�:X�:]��A�:]�:o��A�:o�:o)��A�:o)�:p��A�:p�:x��A�:x�:|��A�:|�:}��A�:}�;)��A�;)�;-)��A�;-)�;-D��A�;-D�;D��A�;D�;_;��A�;_;�<.<��A�<.<�</3��A�</3�<3��A�<3�<33��A�<33�<333��A�<333�<space>��A�<space>�=(��A�=(�=)��A�=)�=/��A�=/�=3��A�=3�=D��A�=D�=[��A�=[�=]��A�=]�=|��A�=|�>.<��A�>.<�>.>��A�>.>�>:(��A�>:(�>:o��A�>:o�><(((*>��A�><(((*>�@_@��A�@_@�C++��A�C++�O.O��A�O.O�O.o��A�O.o�O_O��A�O_O�O_o��A�O_o�V.V��A�V.V�V_V��A�V_V�XD��A�XD�XDD��A�XDD�[-:��A�[-:�[:��A�[:�[=��A�[=�\")��A�\")�\n��A�\n�\t��A�\t�]=��A�]=�^_^��A�^_^�^__^��A�^__^�^___^��A�^___^�o.0��A�o.0�o.O��A�o.O�o.o��A�o.o�o_0��A�o_0�o_O��A�o_O�o_o��A�o_o�v.v��A�v.v�v_v��A�v_v�xD��A�xD�xDD��A�xDD� ��A� C� �¯\(ツ)/¯��A�¯\(ツ)/¯�ಠ_ಠ��A�ಠ_ಠ�ಠ︵ಠ��A�ಠ︵ಠ�—��A�—�faster_heuristics�
vocab/strings.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c211b6f5f3e6f073956aac11971aa77cd754903a4b6e6d63f9de38a0878e7106
3
- size 4575238
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:306c8bd44017d1f1c6c5a0a9ff0629a1fa65f278a4d6bf6971b79d7a7dc787c5
3
+ size 4579186