Commit
·
3603160
1
Parent(s):
bc3dc36
Update spaCy pipeline
Browse files- README.md +27 -27
- accuracy.json +277 -277
- config.cfg +5 -4
- fi_core_news_md-any-py3-none-any.whl +2 -2
- lemmatizer/model +1 -1
- meta.json +280 -280
- morphologizer/model +1 -1
- ner/model +2 -2
- parser/model +1 -1
- senter/model +1 -1
- tagger/model +1 -1
- tok2vec/model +2 -2
- tokenizer +1 -1
- vocab/strings.json +2 -2
README.md
CHANGED
@@ -14,62 +14,62 @@ model-index:
|
|
14 |
metrics:
|
15 |
- name: NER Precision
|
16 |
type: precision
|
17 |
-
value: 0.
|
18 |
- name: NER Recall
|
19 |
type: recall
|
20 |
-
value: 0.
|
21 |
- name: NER F Score
|
22 |
type: f_score
|
23 |
-
value: 0.
|
24 |
- task:
|
25 |
name: TAG
|
26 |
type: token-classification
|
27 |
metrics:
|
28 |
- name: TAG (XPOS) Accuracy
|
29 |
type: accuracy
|
30 |
-
value: 0.
|
31 |
- task:
|
32 |
name: POS
|
33 |
type: token-classification
|
34 |
metrics:
|
35 |
- name: POS (UPOS) Accuracy
|
36 |
type: accuracy
|
37 |
-
value: 0.
|
38 |
- task:
|
39 |
name: MORPH
|
40 |
type: token-classification
|
41 |
metrics:
|
42 |
- name: Morph (UFeats) Accuracy
|
43 |
type: accuracy
|
44 |
-
value: 0.
|
45 |
- task:
|
46 |
name: LEMMA
|
47 |
type: token-classification
|
48 |
metrics:
|
49 |
- name: Lemma Accuracy
|
50 |
type: accuracy
|
51 |
-
value: 0.
|
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.
|
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.
|
66 |
- task:
|
67 |
name: SENTS
|
68 |
type: token-classification
|
69 |
metrics:
|
70 |
- name: Sentences F-Score
|
71 |
type: f_score
|
72 |
-
value: 0.
|
73 |
---
|
74 |
### Details: https://spacy.io/models/fi#fi_core_news_md
|
75 |
|
@@ -78,8 +78,8 @@ Finnish pipeline optimized for CPU. Components: tok2vec, tagger, morphologizer,
|
|
78 |
| Feature | Description |
|
79 |
| --- | --- |
|
80 |
| **Name** | `fi_core_news_md` |
|
81 |
-
| **Version** | `3.
|
82 |
-
| **spaCy** | `>=3.
|
83 |
| **Default Pipeline** | `tok2vec`, `tagger`, `morphologizer`, `parser`, `lemmatizer`, `attribute_ruler`, `ner` |
|
84 |
| **Components** | `tok2vec`, `tagger`, `morphologizer`, `parser`, `lemmatizer`, `senter`, `attribute_ruler`, `ner` |
|
85 |
| **Vectors** | floret (50000, 300) |
|
@@ -110,18 +110,18 @@ Finnish pipeline optimized for CPU. Components: tok2vec, tagger, morphologizer,
|
|
110 |
| `TOKEN_P` | 99.79 |
|
111 |
| `TOKEN_R` | 99.90 |
|
112 |
| `TOKEN_F` | 99.85 |
|
113 |
-
| `TAG_ACC` | 96.
|
114 |
-
| `POS_ACC` | 95.
|
115 |
-
| `MORPH_ACC` | 91.
|
116 |
-
| `MORPH_MICRO_P` | 95.
|
117 |
-
| `MORPH_MICRO_R` | 94.
|
118 |
-
| `MORPH_MICRO_F` | 95.
|
119 |
-
| `SENTS_P` |
|
120 |
-
| `SENTS_R` |
|
121 |
-
| `SENTS_F` |
|
122 |
-
| `DEP_UAS` |
|
123 |
-
| `DEP_LAS` |
|
124 |
-
| `LEMMA_ACC` | 86.
|
125 |
-
| `ENTS_P` | 81.
|
126 |
-
| `ENTS_R` |
|
127 |
-
| `ENTS_F` |
|
|
|
14 |
metrics:
|
15 |
- name: NER Precision
|
16 |
type: precision
|
17 |
+
value: 0.8190770962
|
18 |
- name: NER Recall
|
19 |
type: recall
|
20 |
+
value: 0.7968792773
|
21 |
- name: NER F Score
|
22 |
type: f_score
|
23 |
+
value: 0.807825725
|
24 |
- task:
|
25 |
name: TAG
|
26 |
type: token-classification
|
27 |
metrics:
|
28 |
- name: TAG (XPOS) Accuracy
|
29 |
type: accuracy
|
30 |
+
value: 0.9659361405
|
31 |
- task:
|
32 |
name: POS
|
33 |
type: token-classification
|
34 |
metrics:
|
35 |
- name: POS (UPOS) Accuracy
|
36 |
type: accuracy
|
37 |
+
value: 0.9586650253
|
38 |
- task:
|
39 |
name: MORPH
|
40 |
type: token-classification
|
41 |
metrics:
|
42 |
- name: Morph (UFeats) Accuracy
|
43 |
type: accuracy
|
44 |
+
value: 0.9186882914
|
45 |
- task:
|
46 |
name: LEMMA
|
47 |
type: token-classification
|
48 |
metrics:
|
49 |
- name: Lemma Accuracy
|
50 |
type: accuracy
|
51 |
+
value: 0.8602402419
|
52 |
- task:
|
53 |
name: UNLABELED_DEPENDENCIES
|
54 |
type: token-classification
|
55 |
metrics:
|
56 |
- name: Unlabeled Attachment Score (UAS)
|
57 |
type: f_score
|
58 |
+
value: 0.8321792131
|
59 |
- task:
|
60 |
name: LABELED_DEPENDENCIES
|
61 |
type: token-classification
|
62 |
metrics:
|
63 |
- name: Labeled Attachment Score (LAS)
|
64 |
type: f_score
|
65 |
+
value: 0.7845751467
|
66 |
- task:
|
67 |
name: SENTS
|
68 |
type: token-classification
|
69 |
metrics:
|
70 |
- name: Sentences F-Score
|
71 |
type: f_score
|
72 |
+
value: 0.8935543278
|
73 |
---
|
74 |
### Details: https://spacy.io/models/fi#fi_core_news_md
|
75 |
|
|
|
78 |
| Feature | Description |
|
79 |
| --- | --- |
|
80 |
| **Name** | `fi_core_news_md` |
|
81 |
+
| **Version** | `3.5.0` |
|
82 |
+
| **spaCy** | `>=3.5.0,<3.6.0` |
|
83 |
| **Default Pipeline** | `tok2vec`, `tagger`, `morphologizer`, `parser`, `lemmatizer`, `attribute_ruler`, `ner` |
|
84 |
| **Components** | `tok2vec`, `tagger`, `morphologizer`, `parser`, `lemmatizer`, `senter`, `attribute_ruler`, `ner` |
|
85 |
| **Vectors** | floret (50000, 300) |
|
|
|
110 |
| `TOKEN_P` | 99.79 |
|
111 |
| `TOKEN_R` | 99.90 |
|
112 |
| `TOKEN_F` | 99.85 |
|
113 |
+
| `TAG_ACC` | 96.59 |
|
114 |
+
| `POS_ACC` | 95.87 |
|
115 |
+
| `MORPH_ACC` | 91.87 |
|
116 |
+
| `MORPH_MICRO_P` | 95.90 |
|
117 |
+
| `MORPH_MICRO_R` | 94.93 |
|
118 |
+
| `MORPH_MICRO_F` | 95.41 |
|
119 |
+
| `SENTS_P` | 89.79 |
|
120 |
+
| `SENTS_R` | 88.93 |
|
121 |
+
| `SENTS_F` | 89.36 |
|
122 |
+
| `DEP_UAS` | 83.22 |
|
123 |
+
| `DEP_LAS` | 78.46 |
|
124 |
+
| `LEMMA_ACC` | 86.02 |
|
125 |
+
| `ENTS_P` | 81.91 |
|
126 |
+
| `ENTS_R` | 79.69 |
|
127 |
+
| `ENTS_F` | 80.78 |
|
accuracy.json
CHANGED
@@ -3,456 +3,456 @@
|
|
3 |
"token_p": 0.997946327,
|
4 |
"token_r": 0.998972108,
|
5 |
"token_f": 0.998458954,
|
6 |
-
"tag_acc": 0.
|
7 |
-
"pos_acc": 0.
|
8 |
-
"morph_acc": 0.
|
9 |
-
"morph_micro_p": 0.
|
10 |
-
"morph_micro_r": 0.
|
11 |
-
"morph_micro_f": 0.
|
12 |
"morph_per_feat": {
|
13 |
"Case": {
|
14 |
-
"p": 0.
|
15 |
-
"r": 0.
|
16 |
-
"f": 0.
|
17 |
},
|
18 |
"Number": {
|
19 |
-
"p": 0.
|
20 |
-
"r": 0.
|
21 |
-
"f": 0.
|
22 |
},
|
23 |
"Abbr": {
|
24 |
-
"p": 0.
|
25 |
-
"r": 0.
|
26 |
-
"f": 0.
|
27 |
},
|
28 |
"Derivation": {
|
29 |
-
"p": 0.
|
30 |
"r": 0.806763285,
|
31 |
-
"f": 0.
|
32 |
},
|
33 |
"Mood": {
|
34 |
-
"p": 0.
|
35 |
-
"r": 0.
|
36 |
-
"f": 0.
|
37 |
},
|
38 |
"Person": {
|
39 |
-
"p": 0.
|
40 |
-
"r": 0.
|
41 |
-
"f": 0.
|
42 |
},
|
43 |
"Tense": {
|
44 |
-
"p": 0.
|
45 |
-
"r": 0.
|
46 |
-
"f": 0.
|
47 |
},
|
48 |
"VerbForm": {
|
49 |
-
"p": 0.
|
50 |
-
"r": 0.
|
51 |
-
"f": 0.
|
52 |
},
|
53 |
"Voice": {
|
54 |
-
"p": 0.
|
55 |
-
"r": 0.
|
56 |
-
"f": 0.
|
57 |
},
|
58 |
"Degree": {
|
59 |
-
"p": 0.
|
60 |
-
"r": 0.
|
61 |
-
"f": 0.
|
62 |
},
|
63 |
"PartForm": {
|
64 |
-
"p": 0.
|
65 |
-
"r": 0.
|
66 |
-
"f": 0.
|
67 |
},
|
68 |
"Number[psor]": {
|
69 |
-
"p": 0.
|
70 |
-
"r": 0.
|
71 |
-
"f": 0.
|
72 |
},
|
73 |
"Person[psor]": {
|
74 |
-
"p": 0.
|
75 |
-
"r": 0.
|
76 |
-
"f": 0.
|
77 |
},
|
78 |
"AdpType": {
|
79 |
-
"p": 0.
|
80 |
-
"r": 0.
|
81 |
-
"f": 0.
|
82 |
},
|
83 |
"NumType": {
|
84 |
-
"p": 0.
|
85 |
-
"r": 0.
|
86 |
-
"f": 0.
|
87 |
},
|
88 |
"PronType": {
|
89 |
-
"p": 0.
|
90 |
-
"r": 0.
|
91 |
-
"f": 0.
|
92 |
},
|
93 |
"Typo": {
|
94 |
-
"p": 0.
|
95 |
-
"r": 0.
|
96 |
-
"f": 0.
|
97 |
},
|
98 |
"Clitic": {
|
99 |
-
"p": 0.
|
100 |
-
"r": 0.
|
101 |
-
"f": 0.
|
102 |
},
|
103 |
"Style": {
|
104 |
-
"p": 0.
|
105 |
"r": 0.6052631579,
|
106 |
-
"f": 0.
|
107 |
},
|
108 |
"InfForm": {
|
109 |
-
"p": 0.
|
110 |
-
"r": 0.
|
111 |
-
"f": 0.
|
112 |
},
|
113 |
"Polarity": {
|
114 |
-
"p": 0.
|
115 |
-
"r": 0.
|
116 |
-
"f": 0.
|
117 |
},
|
118 |
"Connegative": {
|
119 |
-
"p": 0.
|
120 |
-
"r": 0.
|
121 |
-
"f": 0.
|
122 |
},
|
123 |
"Foreign": {
|
124 |
-
"p": 0.
|
125 |
-
"r": 0.
|
126 |
-
"f": 0.
|
127 |
},
|
128 |
"Reflex": {
|
129 |
-
"p": 0
|
130 |
"r": 0.7619047619,
|
131 |
-
"f": 0.
|
132 |
}
|
133 |
},
|
134 |
-
"sents_p": 0.
|
135 |
-
"sents_r": 0.
|
136 |
-
"sents_f": 0.
|
137 |
-
"dep_uas": 0.
|
138 |
-
"dep_las": 0.
|
139 |
"dep_las_per_type": {
|
140 |
"root": {
|
141 |
-
"p": 0.
|
142 |
-
"r": 0.
|
143 |
-
"f": 0.
|
144 |
},
|
145 |
"flat:name": {
|
146 |
-
"p": 0.
|
147 |
"r": 0.8317307692,
|
148 |
-
"f": 0.
|
149 |
},
|
150 |
"nmod:poss": {
|
151 |
-
"p": 0.
|
152 |
-
"r": 0.
|
153 |
-
"f": 0.
|
154 |
},
|
155 |
"nsubj": {
|
156 |
-
"p": 0.
|
157 |
-
"r": 0.
|
158 |
-
"f": 0.
|
159 |
},
|
160 |
"acl": {
|
161 |
-
"p": 0.
|
162 |
"r": 0.7329545455,
|
163 |
-
"f": 0.
|
164 |
},
|
165 |
"obl": {
|
166 |
-
"p": 0.
|
167 |
-
"r": 0.
|
168 |
-
"f": 0.
|
169 |
},
|
170 |
"amod": {
|
171 |
-
"p": 0.
|
172 |
-
"r": 0.
|
173 |
-
"f": 0.
|
174 |
},
|
175 |
"obj": {
|
176 |
-
"p": 0.
|
177 |
-
"r": 0.
|
178 |
-
"f": 0.
|
179 |
},
|
180 |
"cc": {
|
181 |
-
"p": 0.
|
182 |
-
"r": 0.
|
183 |
-
"f": 0.
|
184 |
},
|
185 |
"conj": {
|
186 |
-
"p": 0.
|
187 |
-
"r": 0.
|
188 |
-
"f": 0.
|
189 |
},
|
190 |
"advmod": {
|
191 |
-
"p": 0.
|
192 |
-
"r": 0.
|
193 |
-
"f": 0.
|
194 |
},
|
195 |
"case": {
|
196 |
-
"p": 0.
|
197 |
-
"r": 0.
|
198 |
-
"f": 0.
|
199 |
},
|
200 |
"nummod": {
|
201 |
-
"p": 0.
|
202 |
"r": 0.9010238908,
|
203 |
-
"f": 0.
|
204 |
},
|
205 |
"acl:relcl": {
|
206 |
-
"p": 0.
|
207 |
-
"r": 0.
|
208 |
-
"f": 0.
|
209 |
},
|
210 |
"cop": {
|
211 |
-
"p": 0.
|
212 |
-
"r": 0.
|
213 |
-
"f": 0.
|
214 |
},
|
215 |
"mark": {
|
216 |
-
"p": 0.
|
217 |
-
"r": 0.
|
218 |
-
"f": 0.
|
219 |
},
|
220 |
"advcl": {
|
221 |
-
"p": 0.
|
222 |
-
"r": 0.
|
223 |
-
"f": 0.
|
224 |
},
|
225 |
"cop:own": {
|
226 |
-
"p": 0.
|
227 |
-
"r": 0.
|
228 |
-
"f": 0.
|
229 |
},
|
230 |
"nsubj:cop": {
|
231 |
-
"p": 0.
|
232 |
-
"r": 0.
|
233 |
-
"f": 0.
|
234 |
},
|
235 |
"nmod": {
|
236 |
-
"p": 0.
|
237 |
-
"r": 0.
|
238 |
-
"f": 0.
|
239 |
},
|
240 |
"xcomp": {
|
241 |
-
"p": 0.
|
242 |
-
"r": 0.
|
243 |
-
"f": 0.
|
244 |
},
|
245 |
"aux": {
|
246 |
-
"p": 0.
|
247 |
-
"r": 0.
|
248 |
-
"f": 0.
|
249 |
-
},
|
250 |
-
"csubj:cop": {
|
251 |
-
"p": 0.6666666667,
|
252 |
-
"r": 0.4444444444,
|
253 |
-
"f": 0.5333333333
|
254 |
-
},
|
255 |
-
"ccomp": {
|
256 |
-
"p": 0.7412935323,
|
257 |
-
"r": 0.7563451777,
|
258 |
-
"f": 0.7487437186
|
259 |
},
|
260 |
"compound:nn": {
|
261 |
-
"p": 0.
|
262 |
-
"r": 0.
|
263 |
-
"f": 0.
|
264 |
},
|
265 |
"det": {
|
266 |
-
"p": 0.
|
267 |
-
"r": 0.
|
268 |
-
"f": 0.
|
|
|
|
|
|
|
|
|
|
|
269 |
},
|
270 |
"discourse": {
|
271 |
-
"p": 0.
|
272 |
-
"r": 0.
|
273 |
-
"f": 0.
|
274 |
},
|
275 |
-
"
|
276 |
-
"p": 0.
|
277 |
-
"r": 0.
|
278 |
-
"f": 0.
|
279 |
},
|
280 |
"fixed": {
|
281 |
-
"p": 0.
|
282 |
-
"r": 0.
|
283 |
-
"f": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
284 |
},
|
285 |
"nmod:gobj": {
|
286 |
-
"p": 0.
|
287 |
-
"r": 0.
|
288 |
-
"f": 0.
|
289 |
},
|
290 |
-
"
|
291 |
-
"p": 0.
|
292 |
-
"r": 0.
|
293 |
-
"f": 0.
|
294 |
},
|
295 |
-
"
|
296 |
-
"p":
|
297 |
-
"r": 0.
|
298 |
-
"f": 0.
|
299 |
},
|
300 |
-
"
|
301 |
-
"p":
|
302 |
-
"r": 0.
|
303 |
-
"f": 0.
|
304 |
},
|
305 |
"appos": {
|
306 |
-
"p": 0.
|
307 |
-
"r": 0.
|
308 |
-
"f": 0.
|
309 |
-
},
|
310 |
-
"cc:preconj": {
|
311 |
-
"p": 0.3333333333,
|
312 |
-
"r": 0.2727272727,
|
313 |
-
"f": 0.3
|
314 |
},
|
315 |
-
"
|
316 |
-
"p": 0.
|
317 |
-
"r": 0.
|
318 |
-
"f": 0.
|
319 |
},
|
320 |
-
"
|
321 |
"p": 0.0,
|
322 |
"r": 0.0,
|
323 |
"f": 0.0
|
324 |
},
|
325 |
-
"
|
326 |
-
"p": 0.
|
327 |
-
"r": 0.
|
328 |
-
"f": 0.
|
329 |
-
},
|
330 |
-
"nmod:gsubj": {
|
331 |
-
"p": 0.65625,
|
332 |
-
"r": 0.5,
|
333 |
-
"f": 0.5675675676
|
334 |
},
|
335 |
"vocative": {
|
336 |
"p": 0.5714285714,
|
337 |
"r": 0.2352941176,
|
338 |
"f": 0.3333333333
|
339 |
},
|
|
|
|
|
|
|
|
|
|
|
340 |
"goeswith": {
|
341 |
"p": 0.0,
|
342 |
"r": 0.0,
|
343 |
"f": 0.0
|
344 |
},
|
345 |
"compound": {
|
346 |
-
"p": 0.
|
347 |
-
"r": 0.
|
348 |
-
"f": 0.
|
349 |
},
|
350 |
"compound:prt": {
|
351 |
-
"p": 0.
|
352 |
-
"r": 0.
|
353 |
-
"f": 0.
|
354 |
},
|
355 |
"flat": {
|
356 |
-
"p": 0.
|
357 |
"r": 0.6438356164,
|
358 |
-
"f": 0.
|
359 |
}
|
360 |
},
|
361 |
-
"lemma_acc": 0.
|
362 |
-
"ents_p": 0.
|
363 |
-
"ents_r": 0.
|
364 |
-
"ents_f": 0.
|
365 |
"ents_per_type": {
|
366 |
"DATE": {
|
367 |
-
"p": 0.
|
368 |
-
"r": 0.
|
369 |
-
"f": 0.
|
370 |
},
|
371 |
"ORG": {
|
372 |
-
"p": 0.
|
373 |
-
"r": 0.
|
374 |
-
"f": 0.
|
375 |
-
},
|
376 |
-
"PRODUCT": {
|
377 |
-
"p": 0.6477272727,
|
378 |
-
"r": 0.6951219512,
|
379 |
-
"f": 0.6705882353
|
380 |
-
},
|
381 |
-
"NORP": {
|
382 |
-
"p": 0.8099173554,
|
383 |
-
"r": 0.852173913,
|
384 |
-
"f": 0.8305084746
|
385 |
},
|
386 |
"PERSON": {
|
387 |
-
"p": 0.
|
388 |
-
"r": 0.
|
389 |
-
"f": 0.
|
390 |
},
|
391 |
"CARDINAL": {
|
392 |
-
"p": 0.
|
393 |
-
"r": 0.
|
394 |
-
"f": 0.
|
395 |
},
|
396 |
"WORK_OF_ART": {
|
397 |
-
"p": 0.
|
398 |
-
"r": 0.
|
399 |
-
"f": 0.
|
400 |
},
|
401 |
"GPE": {
|
402 |
-
"p": 0.
|
403 |
-
"r": 0.
|
404 |
-
"f": 0.
|
|
|
|
|
|
|
|
|
|
|
405 |
},
|
406 |
"TIME": {
|
407 |
-
"p": 0.
|
408 |
-
"r": 0.
|
409 |
-
"f": 0.
|
410 |
},
|
411 |
"ORDINAL": {
|
412 |
-
"p": 0.
|
413 |
-
"r": 0.
|
414 |
-
"f": 0.
|
415 |
},
|
416 |
"LOC": {
|
417 |
-
"p": 0.
|
418 |
-
"r": 0.
|
419 |
-
"f": 0.
|
|
|
|
|
|
|
|
|
|
|
420 |
},
|
421 |
"PERCENT": {
|
422 |
-
"p": 0
|
423 |
"r": 1.0,
|
424 |
-
"f": 0
|
425 |
},
|
426 |
"QUANTITY": {
|
427 |
-
"p": 0.
|
428 |
-
"r": 0.
|
429 |
-
"f": 0.
|
430 |
-
},
|
431 |
-
"LANGUAGE": {
|
432 |
-
"p": 0.8076923077,
|
433 |
-
"r": 0.6176470588,
|
434 |
-
"f": 0.7
|
435 |
},
|
436 |
"MONEY": {
|
437 |
-
"p": 0.
|
438 |
-
"r": 0.
|
439 |
-
"f": 0.
|
440 |
},
|
441 |
"EVENT": {
|
442 |
-
"p": 0.
|
443 |
-
"r": 0.
|
444 |
-
"f": 0.
|
445 |
},
|
446 |
"FAC": {
|
447 |
"p": 0.5,
|
448 |
-
"r": 0.
|
449 |
-
"f": 0.
|
450 |
},
|
451 |
"LAW": {
|
452 |
-
"p": 0.
|
453 |
-
"r": 0.
|
454 |
-
"f": 0.
|
|
|
|
|
|
|
|
|
|
|
455 |
}
|
456 |
},
|
457 |
-
"speed":
|
458 |
}
|
|
|
3 |
"token_p": 0.997946327,
|
4 |
"token_r": 0.998972108,
|
5 |
"token_f": 0.998458954,
|
6 |
+
"tag_acc": 0.9659361405,
|
7 |
+
"pos_acc": 0.9586650253,
|
8 |
+
"morph_acc": 0.9186882914,
|
9 |
+
"morph_micro_p": 0.9590494975,
|
10 |
+
"morph_micro_r": 0.9492864779,
|
11 |
+
"morph_micro_f": 0.954143014,
|
12 |
"morph_per_feat": {
|
13 |
"Case": {
|
14 |
+
"p": 0.9614104431,
|
15 |
+
"r": 0.9591159074,
|
16 |
+
"f": 0.9602618046
|
17 |
},
|
18 |
"Number": {
|
19 |
+
"p": 0.9791352438,
|
20 |
+
"r": 0.9770883853,
|
21 |
+
"f": 0.9781107437
|
22 |
},
|
23 |
"Abbr": {
|
24 |
+
"p": 0.8813559322,
|
25 |
+
"r": 0.6117647059,
|
26 |
+
"f": 0.7222222222
|
27 |
},
|
28 |
"Derivation": {
|
29 |
+
"p": 0.8428262437,
|
30 |
"r": 0.806763285,
|
31 |
+
"f": 0.8244005642
|
32 |
},
|
33 |
"Mood": {
|
34 |
+
"p": 0.9680111266,
|
35 |
+
"r": 0.9617687702,
|
36 |
+
"f": 0.9648798521
|
37 |
},
|
38 |
"Person": {
|
39 |
+
"p": 0.9384816754,
|
40 |
+
"r": 0.9344048653,
|
41 |
+
"f": 0.9364388333
|
42 |
},
|
43 |
"Tense": {
|
44 |
+
"p": 0.962720403,
|
45 |
+
"r": 0.9651515152,
|
46 |
+
"f": 0.9639344262
|
47 |
},
|
48 |
"VerbForm": {
|
49 |
+
"p": 0.9624373957,
|
50 |
+
"r": 0.9573761417,
|
51 |
+
"f": 0.9599000971
|
52 |
},
|
53 |
"Voice": {
|
54 |
+
"p": 0.9665016021,
|
55 |
+
"r": 0.9622969838,
|
56 |
+
"f": 0.9643947101
|
57 |
},
|
58 |
"Degree": {
|
59 |
+
"p": 0.928917609,
|
60 |
+
"r": 0.9209823812,
|
61 |
+
"f": 0.9249329759
|
62 |
},
|
63 |
"PartForm": {
|
64 |
+
"p": 0.9012517385,
|
65 |
+
"r": 0.8913342503,
|
66 |
+
"f": 0.8962655602
|
67 |
},
|
68 |
"Number[psor]": {
|
69 |
+
"p": 0.9380530973,
|
70 |
+
"r": 0.7910447761,
|
71 |
+
"f": 0.8582995951
|
72 |
},
|
73 |
"Person[psor]": {
|
74 |
+
"p": 0.953125,
|
75 |
+
"r": 0.8664772727,
|
76 |
+
"f": 0.9077380952
|
77 |
},
|
78 |
"AdpType": {
|
79 |
+
"p": 0.9621212121,
|
80 |
+
"r": 0.9202898551,
|
81 |
+
"f": 0.9407407407
|
82 |
},
|
83 |
"NumType": {
|
84 |
+
"p": 0.9479166667,
|
85 |
+
"r": 0.9323770492,
|
86 |
+
"f": 0.9400826446
|
87 |
},
|
88 |
"PronType": {
|
89 |
+
"p": 0.9797734628,
|
90 |
+
"r": 0.9618745036,
|
91 |
+
"f": 0.970741483
|
92 |
},
|
93 |
"Typo": {
|
94 |
+
"p": 0.4545454545,
|
95 |
+
"r": 0.1162790698,
|
96 |
+
"f": 0.1851851852
|
97 |
},
|
98 |
"Clitic": {
|
99 |
+
"p": 0.9044585987,
|
100 |
+
"r": 0.7357512953,
|
101 |
+
"f": 0.8114285714
|
102 |
},
|
103 |
"Style": {
|
104 |
+
"p": 0.8070175439,
|
105 |
"r": 0.6052631579,
|
106 |
+
"f": 0.6917293233
|
107 |
},
|
108 |
"InfForm": {
|
109 |
+
"p": 0.9284253579,
|
110 |
+
"r": 0.9341563786,
|
111 |
+
"f": 0.9312820513
|
112 |
},
|
113 |
"Polarity": {
|
114 |
+
"p": 0.9912663755,
|
115 |
+
"r": 0.9869565217,
|
116 |
+
"f": 0.9891067538
|
117 |
},
|
118 |
"Connegative": {
|
119 |
+
"p": 0.9470588235,
|
120 |
+
"r": 0.9147727273,
|
121 |
+
"f": 0.9306358382
|
122 |
},
|
123 |
"Foreign": {
|
124 |
+
"p": 0.8666666667,
|
125 |
+
"r": 0.2708333333,
|
126 |
+
"f": 0.4126984127
|
127 |
},
|
128 |
"Reflex": {
|
129 |
+
"p": 1.0,
|
130 |
"r": 0.7619047619,
|
131 |
+
"f": 0.8648648649
|
132 |
}
|
133 |
},
|
134 |
+
"sents_p": 0.8978534419,
|
135 |
+
"sents_r": 0.8892961877,
|
136 |
+
"sents_f": 0.8935543278,
|
137 |
+
"dep_uas": 0.8321792131,
|
138 |
+
"dep_las": 0.7845751467,
|
139 |
"dep_las_per_type": {
|
140 |
"root": {
|
141 |
+
"p": 0.8778682457,
|
142 |
+
"r": 0.8695014663,
|
143 |
+
"f": 0.873664825
|
144 |
},
|
145 |
"flat:name": {
|
146 |
+
"p": 0.8046511628,
|
147 |
"r": 0.8317307692,
|
148 |
+
"f": 0.8179669031
|
149 |
},
|
150 |
"nmod:poss": {
|
151 |
+
"p": 0.8027888446,
|
152 |
+
"r": 0.8538135593,
|
153 |
+
"f": 0.8275154004
|
154 |
},
|
155 |
"nsubj": {
|
156 |
+
"p": 0.8702064897,
|
157 |
+
"r": 0.859223301,
|
158 |
+
"f": 0.8646800195
|
159 |
},
|
160 |
"acl": {
|
161 |
+
"p": 0.7865853659,
|
162 |
"r": 0.7329545455,
|
163 |
+
"f": 0.7588235294
|
164 |
},
|
165 |
"obl": {
|
166 |
+
"p": 0.7417519909,
|
167 |
+
"r": 0.7761904762,
|
168 |
+
"f": 0.7585805701
|
169 |
},
|
170 |
"amod": {
|
171 |
+
"p": 0.8450560652,
|
172 |
+
"r": 0.869884575,
|
173 |
+
"f": 0.8572905895
|
174 |
},
|
175 |
"obj": {
|
176 |
+
"p": 0.7944186047,
|
177 |
+
"r": 0.8227360308,
|
178 |
+
"f": 0.8083293895
|
179 |
},
|
180 |
"cc": {
|
181 |
+
"p": 0.8590785908,
|
182 |
+
"r": 0.8532974428,
|
183 |
+
"f": 0.8561782579
|
184 |
},
|
185 |
"conj": {
|
186 |
+
"p": 0.6842650104,
|
187 |
+
"r": 0.6731160896,
|
188 |
+
"f": 0.6786447639
|
189 |
},
|
190 |
"advmod": {
|
191 |
+
"p": 0.7474509804,
|
192 |
+
"r": 0.7654618474,
|
193 |
+
"f": 0.7563492063
|
194 |
},
|
195 |
"case": {
|
196 |
+
"p": 0.8821428571,
|
197 |
+
"r": 0.8884892086,
|
198 |
+
"f": 0.8853046595
|
199 |
},
|
200 |
"nummod": {
|
201 |
+
"p": 0.8301886792,
|
202 |
"r": 0.9010238908,
|
203 |
+
"f": 0.8641571195
|
204 |
},
|
205 |
"acl:relcl": {
|
206 |
+
"p": 0.7783505155,
|
207 |
+
"r": 0.7704081633,
|
208 |
+
"f": 0.7743589744
|
209 |
},
|
210 |
"cop": {
|
211 |
+
"p": 0.8024439919,
|
212 |
+
"r": 0.8024439919,
|
213 |
+
"f": 0.8024439919
|
214 |
},
|
215 |
"mark": {
|
216 |
+
"p": 0.8658227848,
|
217 |
+
"r": 0.8592964824,
|
218 |
+
"f": 0.8625472888
|
219 |
},
|
220 |
"advcl": {
|
221 |
+
"p": 0.6414473684,
|
222 |
+
"r": 0.625,
|
223 |
+
"f": 0.6331168831
|
224 |
},
|
225 |
"cop:own": {
|
226 |
+
"p": 0.5384615385,
|
227 |
+
"r": 0.5,
|
228 |
+
"f": 0.5185185185
|
229 |
},
|
230 |
"nsubj:cop": {
|
231 |
+
"p": 0.7716894977,
|
232 |
+
"r": 0.7331887202,
|
233 |
+
"f": 0.7519466073
|
234 |
},
|
235 |
"nmod": {
|
236 |
+
"p": 0.4533678756,
|
237 |
+
"r": 0.4050925926,
|
238 |
+
"f": 0.4278728606
|
239 |
},
|
240 |
"xcomp": {
|
241 |
+
"p": 0.7257383966,
|
242 |
+
"r": 0.7926267281,
|
243 |
+
"f": 0.7577092511
|
244 |
},
|
245 |
"aux": {
|
246 |
+
"p": 0.8927203065,
|
247 |
+
"r": 0.91015625,
|
248 |
+
"f": 0.9013539652
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
249 |
},
|
250 |
"compound:nn": {
|
251 |
+
"p": 0.7196261682,
|
252 |
+
"r": 0.6416666667,
|
253 |
+
"f": 0.6784140969
|
254 |
},
|
255 |
"det": {
|
256 |
+
"p": 0.8696883853,
|
257 |
+
"r": 0.8721590909,
|
258 |
+
"f": 0.8709219858
|
259 |
+
},
|
260 |
+
"ccomp": {
|
261 |
+
"p": 0.7025641026,
|
262 |
+
"r": 0.6954314721,
|
263 |
+
"f": 0.6989795918
|
264 |
},
|
265 |
"discourse": {
|
266 |
+
"p": 0.7916666667,
|
267 |
+
"r": 0.5588235294,
|
268 |
+
"f": 0.6551724138
|
269 |
},
|
270 |
+
"orphan": {
|
271 |
+
"p": 0.1111111111,
|
272 |
+
"r": 0.0322580645,
|
273 |
+
"f": 0.05
|
274 |
},
|
275 |
"fixed": {
|
276 |
+
"p": 0.511627907,
|
277 |
+
"r": 0.5789473684,
|
278 |
+
"f": 0.5432098765
|
279 |
+
},
|
280 |
+
"xcomp:ds": {
|
281 |
+
"p": 0.7464788732,
|
282 |
+
"r": 0.6162790698,
|
283 |
+
"f": 0.6751592357
|
284 |
+
},
|
285 |
+
"csubj:cop": {
|
286 |
+
"p": 0.5882352941,
|
287 |
+
"r": 0.5555555556,
|
288 |
+
"f": 0.5714285714
|
289 |
},
|
290 |
"nmod:gobj": {
|
291 |
+
"p": 0.8235294118,
|
292 |
+
"r": 0.7974683544,
|
293 |
+
"f": 0.8102893891
|
294 |
},
|
295 |
+
"dep": {
|
296 |
+
"p": 0.0,
|
297 |
+
"r": 0.0,
|
298 |
+
"f": 0.0
|
299 |
},
|
300 |
+
"parataxis": {
|
301 |
+
"p": 0.4933333333,
|
302 |
+
"r": 0.5211267606,
|
303 |
+
"f": 0.5068493151
|
304 |
},
|
305 |
+
"aux:pass": {
|
306 |
+
"p": 0.9264705882,
|
307 |
+
"r": 0.9,
|
308 |
+
"f": 0.9130434783
|
309 |
},
|
310 |
"appos": {
|
311 |
+
"p": 0.504950495,
|
312 |
+
"r": 0.3805970149,
|
313 |
+
"f": 0.4340425532
|
|
|
|
|
|
|
|
|
|
|
314 |
},
|
315 |
+
"flat:foreign": {
|
316 |
+
"p": 0.8571428571,
|
317 |
+
"r": 0.3157894737,
|
318 |
+
"f": 0.4615384615
|
319 |
},
|
320 |
+
"csubj": {
|
321 |
"p": 0.0,
|
322 |
"r": 0.0,
|
323 |
"f": 0.0
|
324 |
},
|
325 |
+
"cc:preconj": {
|
326 |
+
"p": 0.8,
|
327 |
+
"r": 0.3636363636,
|
328 |
+
"f": 0.5
|
|
|
|
|
|
|
|
|
|
|
329 |
},
|
330 |
"vocative": {
|
331 |
"p": 0.5714285714,
|
332 |
"r": 0.2352941176,
|
333 |
"f": 0.3333333333
|
334 |
},
|
335 |
+
"nmod:gsubj": {
|
336 |
+
"p": 0.5517241379,
|
337 |
+
"r": 0.380952381,
|
338 |
+
"f": 0.4507042254
|
339 |
+
},
|
340 |
"goeswith": {
|
341 |
"p": 0.0,
|
342 |
"r": 0.0,
|
343 |
"f": 0.0
|
344 |
},
|
345 |
"compound": {
|
346 |
+
"p": 0.7857142857,
|
347 |
+
"r": 0.6875,
|
348 |
+
"f": 0.7333333333
|
349 |
},
|
350 |
"compound:prt": {
|
351 |
+
"p": 0.6363636364,
|
352 |
+
"r": 0.7,
|
353 |
+
"f": 0.6666666667
|
354 |
},
|
355 |
"flat": {
|
356 |
+
"p": 0.9215686275,
|
357 |
"r": 0.6438356164,
|
358 |
+
"f": 0.7580645161
|
359 |
}
|
360 |
},
|
361 |
+
"lemma_acc": 0.8602402419,
|
362 |
+
"ents_p": 0.8190770962,
|
363 |
+
"ents_r": 0.7968792773,
|
364 |
+
"ents_f": 0.807825725,
|
365 |
"ents_per_type": {
|
366 |
"DATE": {
|
367 |
+
"p": 0.8653846154,
|
368 |
+
"r": 0.8737864078,
|
369 |
+
"f": 0.8695652174
|
370 |
},
|
371 |
"ORG": {
|
372 |
+
"p": 0.7802071346,
|
373 |
+
"r": 0.7829099307,
|
374 |
+
"f": 0.781556196
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
375 |
},
|
376 |
"PERSON": {
|
377 |
+
"p": 0.8172043011,
|
378 |
+
"r": 0.7786885246,
|
379 |
+
"f": 0.7974816369
|
380 |
},
|
381 |
"CARDINAL": {
|
382 |
+
"p": 0.9191011236,
|
383 |
+
"r": 0.9316628702,
|
384 |
+
"f": 0.9253393665
|
385 |
},
|
386 |
"WORK_OF_ART": {
|
387 |
+
"p": 0.5925925926,
|
388 |
+
"r": 0.2857142857,
|
389 |
+
"f": 0.3855421687
|
390 |
},
|
391 |
"GPE": {
|
392 |
+
"p": 0.8131021195,
|
393 |
+
"r": 0.8423153693,
|
394 |
+
"f": 0.8274509804
|
395 |
+
},
|
396 |
+
"PRODUCT": {
|
397 |
+
"p": 0.6808510638,
|
398 |
+
"r": 0.6504065041,
|
399 |
+
"f": 0.6652806653
|
400 |
},
|
401 |
"TIME": {
|
402 |
+
"p": 0.84,
|
403 |
+
"r": 0.6,
|
404 |
+
"f": 0.7
|
405 |
},
|
406 |
"ORDINAL": {
|
407 |
+
"p": 0.875,
|
408 |
+
"r": 0.9158878505,
|
409 |
+
"f": 0.8949771689
|
410 |
},
|
411 |
"LOC": {
|
412 |
+
"p": 0.6097560976,
|
413 |
+
"r": 0.462962963,
|
414 |
+
"f": 0.5263157895
|
415 |
+
},
|
416 |
+
"NORP": {
|
417 |
+
"p": 0.8290598291,
|
418 |
+
"r": 0.8434782609,
|
419 |
+
"f": 0.8362068966
|
420 |
},
|
421 |
"PERCENT": {
|
422 |
+
"p": 1.0,
|
423 |
"r": 1.0,
|
424 |
+
"f": 1.0
|
425 |
},
|
426 |
"QUANTITY": {
|
427 |
+
"p": 0.8181818182,
|
428 |
+
"r": 0.72,
|
429 |
+
"f": 0.7659574468
|
|
|
|
|
|
|
|
|
|
|
430 |
},
|
431 |
"MONEY": {
|
432 |
+
"p": 0.9130434783,
|
433 |
+
"r": 0.8936170213,
|
434 |
+
"f": 0.9032258065
|
435 |
},
|
436 |
"EVENT": {
|
437 |
+
"p": 0.5833333333,
|
438 |
+
"r": 0.21875,
|
439 |
+
"f": 0.3181818182
|
440 |
},
|
441 |
"FAC": {
|
442 |
"p": 0.5,
|
443 |
+
"r": 0.2,
|
444 |
+
"f": 0.2857142857
|
445 |
},
|
446 |
"LAW": {
|
447 |
+
"p": 0.8843537415,
|
448 |
+
"r": 0.8441558442,
|
449 |
+
"f": 0.8637873754
|
450 |
+
},
|
451 |
+
"LANGUAGE": {
|
452 |
+
"p": 0.8461538462,
|
453 |
+
"r": 0.6470588235,
|
454 |
+
"f": 0.7333333333
|
455 |
}
|
456 |
},
|
457 |
+
"speed": 8055.6028168949
|
458 |
}
|
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"
|
85 |
-
rows = [5000,1000,2500,2500
|
86 |
include_static_vectors = true
|
87 |
|
88 |
[components.ner.model.tok2vec.encode]
|
@@ -166,8 +166,8 @@ factory = "tok2vec"
|
|
166 |
[components.tok2vec.model.embed]
|
167 |
@architectures = "spacy.MultiHashEmbed.v2"
|
168 |
width = ${components.tok2vec.model.encode:width}
|
169 |
-
attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY"]
|
170 |
-
rows = [5000,1000,2500,2500,50]
|
171 |
include_static_vectors = true
|
172 |
|
173 |
[components.tok2vec.model.encode]
|
@@ -209,6 +209,7 @@ eval_frequency = 1000
|
|
209 |
frozen_components = []
|
210 |
before_to_disk = null
|
211 |
annotating_components = []
|
|
|
212 |
|
213 |
[training.batcher]
|
214 |
@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 = true
|
87 |
|
88 |
[components.ner.model.tok2vec.encode]
|
|
|
166 |
[components.tok2vec.model.embed]
|
167 |
@architectures = "spacy.MultiHashEmbed.v2"
|
168 |
width = ${components.tok2vec.model.encode:width}
|
169 |
+
attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY","IS_SPACE"]
|
170 |
+
rows = [5000,1000,2500,2500,50,50]
|
171 |
include_static_vectors = true
|
172 |
|
173 |
[components.tok2vec.model.encode]
|
|
|
209 |
frozen_components = []
|
210 |
before_to_disk = null
|
211 |
annotating_components = []
|
212 |
+
before_update = null
|
213 |
|
214 |
[training.batcher]
|
215 |
@batchers = "spacy.batch_by_words.v1"
|
fi_core_news_md-any-py3-none-any.whl
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f574a70d83aef42c99fda9f6d59f058557cc983eb13bb40564fb96427fb7c50f
|
3 |
+
size 68522231
|
lemmatizer/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 967726
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39247026e237b1411cf593f055785903293be029011e33a710425ab77afccd82
|
3 |
size 967726
|
meta.json
CHANGED
@@ -1,14 +1,14 @@
|
|
1 |
{
|
2 |
"lang":"fi",
|
3 |
"name":"core_news_md",
|
4 |
-
"version":"3.
|
5 |
"description":"Finnish pipeline optimized for CPU. Components: tok2vec, tagger, morphologizer, parser, lemmatizer (trainable_lemmatizer), senter, ner.",
|
6 |
"author":"Explosion",
|
7 |
"email":"contact@explosion.ai",
|
8 |
"url":"https://explosion.ai",
|
9 |
"license":"CC BY-SA 4.0",
|
10 |
-
"spacy_version":">=3.
|
11 |
-
"spacy_git_version":"
|
12 |
"vectors":{
|
13 |
"width":300,
|
14 |
"vectors":50000,
|
@@ -2203,458 +2203,458 @@
|
|
2203 |
"token_p":0.997946327,
|
2204 |
"token_r":0.998972108,
|
2205 |
"token_f":0.998458954,
|
2206 |
-
"tag_acc":0.
|
2207 |
-
"pos_acc":0.
|
2208 |
-
"morph_acc":0.
|
2209 |
-
"morph_micro_p":0.
|
2210 |
-
"morph_micro_r":0.
|
2211 |
-
"morph_micro_f":0.
|
2212 |
"morph_per_feat":{
|
2213 |
"Case":{
|
2214 |
-
"p":0.
|
2215 |
-
"r":0.
|
2216 |
-
"f":0.
|
2217 |
},
|
2218 |
"Number":{
|
2219 |
-
"p":0.
|
2220 |
-
"r":0.
|
2221 |
-
"f":0.
|
2222 |
},
|
2223 |
"Abbr":{
|
2224 |
-
"p":0.
|
2225 |
-
"r":0.
|
2226 |
-
"f":0.
|
2227 |
},
|
2228 |
"Derivation":{
|
2229 |
-
"p":0.
|
2230 |
"r":0.806763285,
|
2231 |
-
"f":0.
|
2232 |
},
|
2233 |
"Mood":{
|
2234 |
-
"p":0.
|
2235 |
-
"r":0.
|
2236 |
-
"f":0.
|
2237 |
},
|
2238 |
"Person":{
|
2239 |
-
"p":0.
|
2240 |
-
"r":0.
|
2241 |
-
"f":0.
|
2242 |
},
|
2243 |
"Tense":{
|
2244 |
-
"p":0.
|
2245 |
-
"r":0.
|
2246 |
-
"f":0.
|
2247 |
},
|
2248 |
"VerbForm":{
|
2249 |
-
"p":0.
|
2250 |
-
"r":0.
|
2251 |
-
"f":0.
|
2252 |
},
|
2253 |
"Voice":{
|
2254 |
-
"p":0.
|
2255 |
-
"r":0.
|
2256 |
-
"f":0.
|
2257 |
},
|
2258 |
"Degree":{
|
2259 |
-
"p":0.
|
2260 |
-
"r":0.
|
2261 |
-
"f":0.
|
2262 |
},
|
2263 |
"PartForm":{
|
2264 |
-
"p":0.
|
2265 |
-
"r":0.
|
2266 |
-
"f":0.
|
2267 |
},
|
2268 |
"Number[psor]":{
|
2269 |
-
"p":0.
|
2270 |
-
"r":0.
|
2271 |
-
"f":0.
|
2272 |
},
|
2273 |
"Person[psor]":{
|
2274 |
-
"p":0.
|
2275 |
-
"r":0.
|
2276 |
-
"f":0.
|
2277 |
},
|
2278 |
"AdpType":{
|
2279 |
-
"p":0.
|
2280 |
-
"r":0.
|
2281 |
-
"f":0.
|
2282 |
},
|
2283 |
"NumType":{
|
2284 |
-
"p":0.
|
2285 |
-
"r":0.
|
2286 |
-
"f":0.
|
2287 |
},
|
2288 |
"PronType":{
|
2289 |
-
"p":0.
|
2290 |
-
"r":0.
|
2291 |
-
"f":0.
|
2292 |
},
|
2293 |
"Typo":{
|
2294 |
-
"p":0.
|
2295 |
-
"r":0.
|
2296 |
-
"f":0.
|
2297 |
},
|
2298 |
"Clitic":{
|
2299 |
-
"p":0.
|
2300 |
-
"r":0.
|
2301 |
-
"f":0.
|
2302 |
},
|
2303 |
"Style":{
|
2304 |
-
"p":0.
|
2305 |
"r":0.6052631579,
|
2306 |
-
"f":0.
|
2307 |
},
|
2308 |
"InfForm":{
|
2309 |
-
"p":0.
|
2310 |
-
"r":0.
|
2311 |
-
"f":0.
|
2312 |
},
|
2313 |
"Polarity":{
|
2314 |
-
"p":0.
|
2315 |
-
"r":0.
|
2316 |
-
"f":0.
|
2317 |
},
|
2318 |
"Connegative":{
|
2319 |
-
"p":0.
|
2320 |
-
"r":0.
|
2321 |
-
"f":0.
|
2322 |
},
|
2323 |
"Foreign":{
|
2324 |
-
"p":0.
|
2325 |
-
"r":0.
|
2326 |
-
"f":0.
|
2327 |
},
|
2328 |
"Reflex":{
|
2329 |
-
"p":0
|
2330 |
"r":0.7619047619,
|
2331 |
-
"f":0.
|
2332 |
}
|
2333 |
},
|
2334 |
-
"sents_p":0.
|
2335 |
-
"sents_r":0.
|
2336 |
-
"sents_f":0.
|
2337 |
-
"dep_uas":0.
|
2338 |
-
"dep_las":0.
|
2339 |
"dep_las_per_type":{
|
2340 |
"root":{
|
2341 |
-
"p":0.
|
2342 |
-
"r":0.
|
2343 |
-
"f":0.
|
2344 |
},
|
2345 |
"flat:name":{
|
2346 |
-
"p":0.
|
2347 |
"r":0.8317307692,
|
2348 |
-
"f":0.
|
2349 |
},
|
2350 |
"nmod:poss":{
|
2351 |
-
"p":0.
|
2352 |
-
"r":0.
|
2353 |
-
"f":0.
|
2354 |
},
|
2355 |
"nsubj":{
|
2356 |
-
"p":0.
|
2357 |
-
"r":0.
|
2358 |
-
"f":0.
|
2359 |
},
|
2360 |
"acl":{
|
2361 |
-
"p":0.
|
2362 |
"r":0.7329545455,
|
2363 |
-
"f":0.
|
2364 |
},
|
2365 |
"obl":{
|
2366 |
-
"p":0.
|
2367 |
-
"r":0.
|
2368 |
-
"f":0.
|
2369 |
},
|
2370 |
"amod":{
|
2371 |
-
"p":0.
|
2372 |
-
"r":0.
|
2373 |
-
"f":0.
|
2374 |
},
|
2375 |
"obj":{
|
2376 |
-
"p":0.
|
2377 |
-
"r":0.
|
2378 |
-
"f":0.
|
2379 |
},
|
2380 |
"cc":{
|
2381 |
-
"p":0.
|
2382 |
-
"r":0.
|
2383 |
-
"f":0.
|
2384 |
},
|
2385 |
"conj":{
|
2386 |
-
"p":0.
|
2387 |
-
"r":0.
|
2388 |
-
"f":0.
|
2389 |
},
|
2390 |
"advmod":{
|
2391 |
-
"p":0.
|
2392 |
-
"r":0.
|
2393 |
-
"f":0.
|
2394 |
},
|
2395 |
"case":{
|
2396 |
-
"p":0.
|
2397 |
-
"r":0.
|
2398 |
-
"f":0.
|
2399 |
},
|
2400 |
"nummod":{
|
2401 |
-
"p":0.
|
2402 |
"r":0.9010238908,
|
2403 |
-
"f":0.
|
2404 |
},
|
2405 |
"acl:relcl":{
|
2406 |
-
"p":0.
|
2407 |
-
"r":0.
|
2408 |
-
"f":0.
|
2409 |
},
|
2410 |
"cop":{
|
2411 |
-
"p":0.
|
2412 |
-
"r":0.
|
2413 |
-
"f":0.
|
2414 |
},
|
2415 |
"mark":{
|
2416 |
-
"p":0.
|
2417 |
-
"r":0.
|
2418 |
-
"f":0.
|
2419 |
},
|
2420 |
"advcl":{
|
2421 |
-
"p":0.
|
2422 |
-
"r":0.
|
2423 |
-
"f":0.
|
2424 |
},
|
2425 |
"cop:own":{
|
2426 |
-
"p":0.
|
2427 |
-
"r":0.
|
2428 |
-
"f":0.
|
2429 |
},
|
2430 |
"nsubj:cop":{
|
2431 |
-
"p":0.
|
2432 |
-
"r":0.
|
2433 |
-
"f":0.
|
2434 |
},
|
2435 |
"nmod":{
|
2436 |
-
"p":0.
|
2437 |
-
"r":0.
|
2438 |
-
"f":0.
|
2439 |
},
|
2440 |
"xcomp":{
|
2441 |
-
"p":0.
|
2442 |
-
"r":0.
|
2443 |
-
"f":0.
|
2444 |
},
|
2445 |
"aux":{
|
2446 |
-
"p":0.
|
2447 |
-
"r":0.
|
2448 |
-
"f":0.
|
2449 |
-
},
|
2450 |
-
"csubj:cop":{
|
2451 |
-
"p":0.6666666667,
|
2452 |
-
"r":0.4444444444,
|
2453 |
-
"f":0.5333333333
|
2454 |
-
},
|
2455 |
-
"ccomp":{
|
2456 |
-
"p":0.7412935323,
|
2457 |
-
"r":0.7563451777,
|
2458 |
-
"f":0.7487437186
|
2459 |
},
|
2460 |
"compound:nn":{
|
2461 |
-
"p":0.
|
2462 |
-
"r":0.
|
2463 |
-
"f":0.
|
2464 |
},
|
2465 |
"det":{
|
2466 |
-
"p":0.
|
2467 |
-
"r":0.
|
2468 |
-
"f":0.
|
|
|
|
|
|
|
|
|
|
|
2469 |
},
|
2470 |
"discourse":{
|
2471 |
-
"p":0.
|
2472 |
-
"r":0.
|
2473 |
-
"f":0.
|
2474 |
},
|
2475 |
-
"
|
2476 |
-
"p":0.
|
2477 |
-
"r":0.
|
2478 |
-
"f":0.
|
2479 |
},
|
2480 |
"fixed":{
|
2481 |
-
"p":0.
|
2482 |
-
"r":0.
|
2483 |
-
"f":0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2484 |
},
|
2485 |
"nmod:gobj":{
|
2486 |
-
"p":0.
|
2487 |
-
"r":0.
|
2488 |
-
"f":0.
|
2489 |
},
|
2490 |
-
"
|
2491 |
-
"p":0.
|
2492 |
-
"r":0.
|
2493 |
-
"f":0.
|
2494 |
},
|
2495 |
-
"
|
2496 |
-
"p":
|
2497 |
-
"r":0.
|
2498 |
-
"f":0.
|
2499 |
},
|
2500 |
-
"
|
2501 |
-
"p":
|
2502 |
-
"r":0.
|
2503 |
-
"f":0.
|
2504 |
},
|
2505 |
"appos":{
|
2506 |
-
"p":0.
|
2507 |
-
"r":0.
|
2508 |
-
"f":0.
|
2509 |
-
},
|
2510 |
-
"cc:preconj":{
|
2511 |
-
"p":0.3333333333,
|
2512 |
-
"r":0.2727272727,
|
2513 |
-
"f":0.3
|
2514 |
},
|
2515 |
-
"
|
2516 |
-
"p":0.
|
2517 |
-
"r":0.
|
2518 |
-
"f":0.
|
2519 |
},
|
2520 |
-
"
|
2521 |
"p":0.0,
|
2522 |
"r":0.0,
|
2523 |
"f":0.0
|
2524 |
},
|
2525 |
-
"
|
2526 |
-
"p":0.
|
2527 |
-
"r":0.
|
2528 |
-
"f":0.
|
2529 |
-
},
|
2530 |
-
"nmod:gsubj":{
|
2531 |
-
"p":0.65625,
|
2532 |
-
"r":0.5,
|
2533 |
-
"f":0.5675675676
|
2534 |
},
|
2535 |
"vocative":{
|
2536 |
"p":0.5714285714,
|
2537 |
"r":0.2352941176,
|
2538 |
"f":0.3333333333
|
2539 |
},
|
|
|
|
|
|
|
|
|
|
|
2540 |
"goeswith":{
|
2541 |
"p":0.0,
|
2542 |
"r":0.0,
|
2543 |
"f":0.0
|
2544 |
},
|
2545 |
"compound":{
|
2546 |
-
"p":0.
|
2547 |
-
"r":0.
|
2548 |
-
"f":0.
|
2549 |
},
|
2550 |
"compound:prt":{
|
2551 |
-
"p":0.
|
2552 |
-
"r":0.
|
2553 |
-
"f":0.
|
2554 |
},
|
2555 |
"flat":{
|
2556 |
-
"p":0.
|
2557 |
"r":0.6438356164,
|
2558 |
-
"f":0.
|
2559 |
}
|
2560 |
},
|
2561 |
-
"lemma_acc":0.
|
2562 |
-
"ents_p":0.
|
2563 |
-
"ents_r":0.
|
2564 |
-
"ents_f":0.
|
2565 |
"ents_per_type":{
|
2566 |
"DATE":{
|
2567 |
-
"p":0.
|
2568 |
-
"r":0.
|
2569 |
-
"f":0.
|
2570 |
},
|
2571 |
"ORG":{
|
2572 |
-
"p":0.
|
2573 |
-
"r":0.
|
2574 |
-
"f":0.
|
2575 |
-
},
|
2576 |
-
"PRODUCT":{
|
2577 |
-
"p":0.6477272727,
|
2578 |
-
"r":0.6951219512,
|
2579 |
-
"f":0.6705882353
|
2580 |
-
},
|
2581 |
-
"NORP":{
|
2582 |
-
"p":0.8099173554,
|
2583 |
-
"r":0.852173913,
|
2584 |
-
"f":0.8305084746
|
2585 |
},
|
2586 |
"PERSON":{
|
2587 |
-
"p":0.
|
2588 |
-
"r":0.
|
2589 |
-
"f":0.
|
2590 |
},
|
2591 |
"CARDINAL":{
|
2592 |
-
"p":0.
|
2593 |
-
"r":0.
|
2594 |
-
"f":0.
|
2595 |
},
|
2596 |
"WORK_OF_ART":{
|
2597 |
-
"p":0.
|
2598 |
-
"r":0.
|
2599 |
-
"f":0.
|
2600 |
},
|
2601 |
"GPE":{
|
2602 |
-
"p":0.
|
2603 |
-
"r":0.
|
2604 |
-
"f":0.
|
|
|
|
|
|
|
|
|
|
|
2605 |
},
|
2606 |
"TIME":{
|
2607 |
-
"p":0.
|
2608 |
-
"r":0.
|
2609 |
-
"f":0.
|
2610 |
},
|
2611 |
"ORDINAL":{
|
2612 |
-
"p":0.
|
2613 |
-
"r":0.
|
2614 |
-
"f":0.
|
2615 |
},
|
2616 |
"LOC":{
|
2617 |
-
"p":0.
|
2618 |
-
"r":0.
|
2619 |
-
"f":0.
|
|
|
|
|
|
|
|
|
|
|
2620 |
},
|
2621 |
"PERCENT":{
|
2622 |
-
"p":0
|
2623 |
"r":1.0,
|
2624 |
-
"f":0
|
2625 |
},
|
2626 |
"QUANTITY":{
|
2627 |
-
"p":0.
|
2628 |
-
"r":0.
|
2629 |
-
"f":0.
|
2630 |
-
},
|
2631 |
-
"LANGUAGE":{
|
2632 |
-
"p":0.8076923077,
|
2633 |
-
"r":0.6176470588,
|
2634 |
-
"f":0.7
|
2635 |
},
|
2636 |
"MONEY":{
|
2637 |
-
"p":0.
|
2638 |
-
"r":0.
|
2639 |
-
"f":0.
|
2640 |
},
|
2641 |
"EVENT":{
|
2642 |
-
"p":0.
|
2643 |
-
"r":0.
|
2644 |
-
"f":0.
|
2645 |
},
|
2646 |
"FAC":{
|
2647 |
"p":0.5,
|
2648 |
-
"r":0.
|
2649 |
-
"f":0.
|
2650 |
},
|
2651 |
"LAW":{
|
2652 |
-
"p":0.
|
2653 |
-
"r":0.
|
2654 |
-
"f":0.
|
|
|
|
|
|
|
|
|
|
|
2655 |
}
|
2656 |
},
|
2657 |
-
"speed":
|
2658 |
},
|
2659 |
"sources":[
|
2660 |
{
|
|
|
1 |
{
|
2 |
"lang":"fi",
|
3 |
"name":"core_news_md",
|
4 |
+
"version":"3.5.0",
|
5 |
"description":"Finnish pipeline optimized for CPU. Components: tok2vec, tagger, morphologizer, parser, lemmatizer (trainable_lemmatizer), senter, ner.",
|
6 |
"author":"Explosion",
|
7 |
"email":"contact@explosion.ai",
|
8 |
"url":"https://explosion.ai",
|
9 |
"license":"CC BY-SA 4.0",
|
10 |
+
"spacy_version":">=3.5.0,<3.6.0",
|
11 |
+
"spacy_git_version":"9e0322de1",
|
12 |
"vectors":{
|
13 |
"width":300,
|
14 |
"vectors":50000,
|
|
|
2203 |
"token_p":0.997946327,
|
2204 |
"token_r":0.998972108,
|
2205 |
"token_f":0.998458954,
|
2206 |
+
"tag_acc":0.9659361405,
|
2207 |
+
"pos_acc":0.9586650253,
|
2208 |
+
"morph_acc":0.9186882914,
|
2209 |
+
"morph_micro_p":0.9590494975,
|
2210 |
+
"morph_micro_r":0.9492864779,
|
2211 |
+
"morph_micro_f":0.954143014,
|
2212 |
"morph_per_feat":{
|
2213 |
"Case":{
|
2214 |
+
"p":0.9614104431,
|
2215 |
+
"r":0.9591159074,
|
2216 |
+
"f":0.9602618046
|
2217 |
},
|
2218 |
"Number":{
|
2219 |
+
"p":0.9791352438,
|
2220 |
+
"r":0.9770883853,
|
2221 |
+
"f":0.9781107437
|
2222 |
},
|
2223 |
"Abbr":{
|
2224 |
+
"p":0.8813559322,
|
2225 |
+
"r":0.6117647059,
|
2226 |
+
"f":0.7222222222
|
2227 |
},
|
2228 |
"Derivation":{
|
2229 |
+
"p":0.8428262437,
|
2230 |
"r":0.806763285,
|
2231 |
+
"f":0.8244005642
|
2232 |
},
|
2233 |
"Mood":{
|
2234 |
+
"p":0.9680111266,
|
2235 |
+
"r":0.9617687702,
|
2236 |
+
"f":0.9648798521
|
2237 |
},
|
2238 |
"Person":{
|
2239 |
+
"p":0.9384816754,
|
2240 |
+
"r":0.9344048653,
|
2241 |
+
"f":0.9364388333
|
2242 |
},
|
2243 |
"Tense":{
|
2244 |
+
"p":0.962720403,
|
2245 |
+
"r":0.9651515152,
|
2246 |
+
"f":0.9639344262
|
2247 |
},
|
2248 |
"VerbForm":{
|
2249 |
+
"p":0.9624373957,
|
2250 |
+
"r":0.9573761417,
|
2251 |
+
"f":0.9599000971
|
2252 |
},
|
2253 |
"Voice":{
|
2254 |
+
"p":0.9665016021,
|
2255 |
+
"r":0.9622969838,
|
2256 |
+
"f":0.9643947101
|
2257 |
},
|
2258 |
"Degree":{
|
2259 |
+
"p":0.928917609,
|
2260 |
+
"r":0.9209823812,
|
2261 |
+
"f":0.9249329759
|
2262 |
},
|
2263 |
"PartForm":{
|
2264 |
+
"p":0.9012517385,
|
2265 |
+
"r":0.8913342503,
|
2266 |
+
"f":0.8962655602
|
2267 |
},
|
2268 |
"Number[psor]":{
|
2269 |
+
"p":0.9380530973,
|
2270 |
+
"r":0.7910447761,
|
2271 |
+
"f":0.8582995951
|
2272 |
},
|
2273 |
"Person[psor]":{
|
2274 |
+
"p":0.953125,
|
2275 |
+
"r":0.8664772727,
|
2276 |
+
"f":0.9077380952
|
2277 |
},
|
2278 |
"AdpType":{
|
2279 |
+
"p":0.9621212121,
|
2280 |
+
"r":0.9202898551,
|
2281 |
+
"f":0.9407407407
|
2282 |
},
|
2283 |
"NumType":{
|
2284 |
+
"p":0.9479166667,
|
2285 |
+
"r":0.9323770492,
|
2286 |
+
"f":0.9400826446
|
2287 |
},
|
2288 |
"PronType":{
|
2289 |
+
"p":0.9797734628,
|
2290 |
+
"r":0.9618745036,
|
2291 |
+
"f":0.970741483
|
2292 |
},
|
2293 |
"Typo":{
|
2294 |
+
"p":0.4545454545,
|
2295 |
+
"r":0.1162790698,
|
2296 |
+
"f":0.1851851852
|
2297 |
},
|
2298 |
"Clitic":{
|
2299 |
+
"p":0.9044585987,
|
2300 |
+
"r":0.7357512953,
|
2301 |
+
"f":0.8114285714
|
2302 |
},
|
2303 |
"Style":{
|
2304 |
+
"p":0.8070175439,
|
2305 |
"r":0.6052631579,
|
2306 |
+
"f":0.6917293233
|
2307 |
},
|
2308 |
"InfForm":{
|
2309 |
+
"p":0.9284253579,
|
2310 |
+
"r":0.9341563786,
|
2311 |
+
"f":0.9312820513
|
2312 |
},
|
2313 |
"Polarity":{
|
2314 |
+
"p":0.9912663755,
|
2315 |
+
"r":0.9869565217,
|
2316 |
+
"f":0.9891067538
|
2317 |
},
|
2318 |
"Connegative":{
|
2319 |
+
"p":0.9470588235,
|
2320 |
+
"r":0.9147727273,
|
2321 |
+
"f":0.9306358382
|
2322 |
},
|
2323 |
"Foreign":{
|
2324 |
+
"p":0.8666666667,
|
2325 |
+
"r":0.2708333333,
|
2326 |
+
"f":0.4126984127
|
2327 |
},
|
2328 |
"Reflex":{
|
2329 |
+
"p":1.0,
|
2330 |
"r":0.7619047619,
|
2331 |
+
"f":0.8648648649
|
2332 |
}
|
2333 |
},
|
2334 |
+
"sents_p":0.8978534419,
|
2335 |
+
"sents_r":0.8892961877,
|
2336 |
+
"sents_f":0.8935543278,
|
2337 |
+
"dep_uas":0.8321792131,
|
2338 |
+
"dep_las":0.7845751467,
|
2339 |
"dep_las_per_type":{
|
2340 |
"root":{
|
2341 |
+
"p":0.8778682457,
|
2342 |
+
"r":0.8695014663,
|
2343 |
+
"f":0.873664825
|
2344 |
},
|
2345 |
"flat:name":{
|
2346 |
+
"p":0.8046511628,
|
2347 |
"r":0.8317307692,
|
2348 |
+
"f":0.8179669031
|
2349 |
},
|
2350 |
"nmod:poss":{
|
2351 |
+
"p":0.8027888446,
|
2352 |
+
"r":0.8538135593,
|
2353 |
+
"f":0.8275154004
|
2354 |
},
|
2355 |
"nsubj":{
|
2356 |
+
"p":0.8702064897,
|
2357 |
+
"r":0.859223301,
|
2358 |
+
"f":0.8646800195
|
2359 |
},
|
2360 |
"acl":{
|
2361 |
+
"p":0.7865853659,
|
2362 |
"r":0.7329545455,
|
2363 |
+
"f":0.7588235294
|
2364 |
},
|
2365 |
"obl":{
|
2366 |
+
"p":0.7417519909,
|
2367 |
+
"r":0.7761904762,
|
2368 |
+
"f":0.7585805701
|
2369 |
},
|
2370 |
"amod":{
|
2371 |
+
"p":0.8450560652,
|
2372 |
+
"r":0.869884575,
|
2373 |
+
"f":0.8572905895
|
2374 |
},
|
2375 |
"obj":{
|
2376 |
+
"p":0.7944186047,
|
2377 |
+
"r":0.8227360308,
|
2378 |
+
"f":0.8083293895
|
2379 |
},
|
2380 |
"cc":{
|
2381 |
+
"p":0.8590785908,
|
2382 |
+
"r":0.8532974428,
|
2383 |
+
"f":0.8561782579
|
2384 |
},
|
2385 |
"conj":{
|
2386 |
+
"p":0.6842650104,
|
2387 |
+
"r":0.6731160896,
|
2388 |
+
"f":0.6786447639
|
2389 |
},
|
2390 |
"advmod":{
|
2391 |
+
"p":0.7474509804,
|
2392 |
+
"r":0.7654618474,
|
2393 |
+
"f":0.7563492063
|
2394 |
},
|
2395 |
"case":{
|
2396 |
+
"p":0.8821428571,
|
2397 |
+
"r":0.8884892086,
|
2398 |
+
"f":0.8853046595
|
2399 |
},
|
2400 |
"nummod":{
|
2401 |
+
"p":0.8301886792,
|
2402 |
"r":0.9010238908,
|
2403 |
+
"f":0.8641571195
|
2404 |
},
|
2405 |
"acl:relcl":{
|
2406 |
+
"p":0.7783505155,
|
2407 |
+
"r":0.7704081633,
|
2408 |
+
"f":0.7743589744
|
2409 |
},
|
2410 |
"cop":{
|
2411 |
+
"p":0.8024439919,
|
2412 |
+
"r":0.8024439919,
|
2413 |
+
"f":0.8024439919
|
2414 |
},
|
2415 |
"mark":{
|
2416 |
+
"p":0.8658227848,
|
2417 |
+
"r":0.8592964824,
|
2418 |
+
"f":0.8625472888
|
2419 |
},
|
2420 |
"advcl":{
|
2421 |
+
"p":0.6414473684,
|
2422 |
+
"r":0.625,
|
2423 |
+
"f":0.6331168831
|
2424 |
},
|
2425 |
"cop:own":{
|
2426 |
+
"p":0.5384615385,
|
2427 |
+
"r":0.5,
|
2428 |
+
"f":0.5185185185
|
2429 |
},
|
2430 |
"nsubj:cop":{
|
2431 |
+
"p":0.7716894977,
|
2432 |
+
"r":0.7331887202,
|
2433 |
+
"f":0.7519466073
|
2434 |
},
|
2435 |
"nmod":{
|
2436 |
+
"p":0.4533678756,
|
2437 |
+
"r":0.4050925926,
|
2438 |
+
"f":0.4278728606
|
2439 |
},
|
2440 |
"xcomp":{
|
2441 |
+
"p":0.7257383966,
|
2442 |
+
"r":0.7926267281,
|
2443 |
+
"f":0.7577092511
|
2444 |
},
|
2445 |
"aux":{
|
2446 |
+
"p":0.8927203065,
|
2447 |
+
"r":0.91015625,
|
2448 |
+
"f":0.9013539652
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2449 |
},
|
2450 |
"compound:nn":{
|
2451 |
+
"p":0.7196261682,
|
2452 |
+
"r":0.6416666667,
|
2453 |
+
"f":0.6784140969
|
2454 |
},
|
2455 |
"det":{
|
2456 |
+
"p":0.8696883853,
|
2457 |
+
"r":0.8721590909,
|
2458 |
+
"f":0.8709219858
|
2459 |
+
},
|
2460 |
+
"ccomp":{
|
2461 |
+
"p":0.7025641026,
|
2462 |
+
"r":0.6954314721,
|
2463 |
+
"f":0.6989795918
|
2464 |
},
|
2465 |
"discourse":{
|
2466 |
+
"p":0.7916666667,
|
2467 |
+
"r":0.5588235294,
|
2468 |
+
"f":0.6551724138
|
2469 |
},
|
2470 |
+
"orphan":{
|
2471 |
+
"p":0.1111111111,
|
2472 |
+
"r":0.0322580645,
|
2473 |
+
"f":0.05
|
2474 |
},
|
2475 |
"fixed":{
|
2476 |
+
"p":0.511627907,
|
2477 |
+
"r":0.5789473684,
|
2478 |
+
"f":0.5432098765
|
2479 |
+
},
|
2480 |
+
"xcomp:ds":{
|
2481 |
+
"p":0.7464788732,
|
2482 |
+
"r":0.6162790698,
|
2483 |
+
"f":0.6751592357
|
2484 |
+
},
|
2485 |
+
"csubj:cop":{
|
2486 |
+
"p":0.5882352941,
|
2487 |
+
"r":0.5555555556,
|
2488 |
+
"f":0.5714285714
|
2489 |
},
|
2490 |
"nmod:gobj":{
|
2491 |
+
"p":0.8235294118,
|
2492 |
+
"r":0.7974683544,
|
2493 |
+
"f":0.8102893891
|
2494 |
},
|
2495 |
+
"dep":{
|
2496 |
+
"p":0.0,
|
2497 |
+
"r":0.0,
|
2498 |
+
"f":0.0
|
2499 |
},
|
2500 |
+
"parataxis":{
|
2501 |
+
"p":0.4933333333,
|
2502 |
+
"r":0.5211267606,
|
2503 |
+
"f":0.5068493151
|
2504 |
},
|
2505 |
+
"aux:pass":{
|
2506 |
+
"p":0.9264705882,
|
2507 |
+
"r":0.9,
|
2508 |
+
"f":0.9130434783
|
2509 |
},
|
2510 |
"appos":{
|
2511 |
+
"p":0.504950495,
|
2512 |
+
"r":0.3805970149,
|
2513 |
+
"f":0.4340425532
|
|
|
|
|
|
|
|
|
|
|
2514 |
},
|
2515 |
+
"flat:foreign":{
|
2516 |
+
"p":0.8571428571,
|
2517 |
+
"r":0.3157894737,
|
2518 |
+
"f":0.4615384615
|
2519 |
},
|
2520 |
+
"csubj":{
|
2521 |
"p":0.0,
|
2522 |
"r":0.0,
|
2523 |
"f":0.0
|
2524 |
},
|
2525 |
+
"cc:preconj":{
|
2526 |
+
"p":0.8,
|
2527 |
+
"r":0.3636363636,
|
2528 |
+
"f":0.5
|
|
|
|
|
|
|
|
|
|
|
2529 |
},
|
2530 |
"vocative":{
|
2531 |
"p":0.5714285714,
|
2532 |
"r":0.2352941176,
|
2533 |
"f":0.3333333333
|
2534 |
},
|
2535 |
+
"nmod:gsubj":{
|
2536 |
+
"p":0.5517241379,
|
2537 |
+
"r":0.380952381,
|
2538 |
+
"f":0.4507042254
|
2539 |
+
},
|
2540 |
"goeswith":{
|
2541 |
"p":0.0,
|
2542 |
"r":0.0,
|
2543 |
"f":0.0
|
2544 |
},
|
2545 |
"compound":{
|
2546 |
+
"p":0.7857142857,
|
2547 |
+
"r":0.6875,
|
2548 |
+
"f":0.7333333333
|
2549 |
},
|
2550 |
"compound:prt":{
|
2551 |
+
"p":0.6363636364,
|
2552 |
+
"r":0.7,
|
2553 |
+
"f":0.6666666667
|
2554 |
},
|
2555 |
"flat":{
|
2556 |
+
"p":0.9215686275,
|
2557 |
"r":0.6438356164,
|
2558 |
+
"f":0.7580645161
|
2559 |
}
|
2560 |
},
|
2561 |
+
"lemma_acc":0.8602402419,
|
2562 |
+
"ents_p":0.8190770962,
|
2563 |
+
"ents_r":0.7968792773,
|
2564 |
+
"ents_f":0.807825725,
|
2565 |
"ents_per_type":{
|
2566 |
"DATE":{
|
2567 |
+
"p":0.8653846154,
|
2568 |
+
"r":0.8737864078,
|
2569 |
+
"f":0.8695652174
|
2570 |
},
|
2571 |
"ORG":{
|
2572 |
+
"p":0.7802071346,
|
2573 |
+
"r":0.7829099307,
|
2574 |
+
"f":0.781556196
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2575 |
},
|
2576 |
"PERSON":{
|
2577 |
+
"p":0.8172043011,
|
2578 |
+
"r":0.7786885246,
|
2579 |
+
"f":0.7974816369
|
2580 |
},
|
2581 |
"CARDINAL":{
|
2582 |
+
"p":0.9191011236,
|
2583 |
+
"r":0.9316628702,
|
2584 |
+
"f":0.9253393665
|
2585 |
},
|
2586 |
"WORK_OF_ART":{
|
2587 |
+
"p":0.5925925926,
|
2588 |
+
"r":0.2857142857,
|
2589 |
+
"f":0.3855421687
|
2590 |
},
|
2591 |
"GPE":{
|
2592 |
+
"p":0.8131021195,
|
2593 |
+
"r":0.8423153693,
|
2594 |
+
"f":0.8274509804
|
2595 |
+
},
|
2596 |
+
"PRODUCT":{
|
2597 |
+
"p":0.6808510638,
|
2598 |
+
"r":0.6504065041,
|
2599 |
+
"f":0.6652806653
|
2600 |
},
|
2601 |
"TIME":{
|
2602 |
+
"p":0.84,
|
2603 |
+
"r":0.6,
|
2604 |
+
"f":0.7
|
2605 |
},
|
2606 |
"ORDINAL":{
|
2607 |
+
"p":0.875,
|
2608 |
+
"r":0.9158878505,
|
2609 |
+
"f":0.8949771689
|
2610 |
},
|
2611 |
"LOC":{
|
2612 |
+
"p":0.6097560976,
|
2613 |
+
"r":0.462962963,
|
2614 |
+
"f":0.5263157895
|
2615 |
+
},
|
2616 |
+
"NORP":{
|
2617 |
+
"p":0.8290598291,
|
2618 |
+
"r":0.8434782609,
|
2619 |
+
"f":0.8362068966
|
2620 |
},
|
2621 |
"PERCENT":{
|
2622 |
+
"p":1.0,
|
2623 |
"r":1.0,
|
2624 |
+
"f":1.0
|
2625 |
},
|
2626 |
"QUANTITY":{
|
2627 |
+
"p":0.8181818182,
|
2628 |
+
"r":0.72,
|
2629 |
+
"f":0.7659574468
|
|
|
|
|
|
|
|
|
|
|
2630 |
},
|
2631 |
"MONEY":{
|
2632 |
+
"p":0.9130434783,
|
2633 |
+
"r":0.8936170213,
|
2634 |
+
"f":0.9032258065
|
2635 |
},
|
2636 |
"EVENT":{
|
2637 |
+
"p":0.5833333333,
|
2638 |
+
"r":0.21875,
|
2639 |
+
"f":0.3181818182
|
2640 |
},
|
2641 |
"FAC":{
|
2642 |
"p":0.5,
|
2643 |
+
"r":0.2,
|
2644 |
+
"f":0.2857142857
|
2645 |
},
|
2646 |
"LAW":{
|
2647 |
+
"p":0.8843537415,
|
2648 |
+
"r":0.8441558442,
|
2649 |
+
"f":0.8637873754
|
2650 |
+
},
|
2651 |
+
"LANGUAGE":{
|
2652 |
+
"p":0.8461538462,
|
2653 |
+
"r":0.6470588235,
|
2654 |
+
"f":0.7333333333
|
2655 |
}
|
2656 |
},
|
2657 |
+
"speed":8055.6028168949
|
2658 |
},
|
2659 |
"sources":[
|
2660 |
{
|
morphologizer/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 802050
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96a7443ae58ea146ffca285dc30307fa7572901f4f9687a05dbaa4d63aaff34d
|
3 |
size 802050
|
ner/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e7e34eb985bee1a8746401432fdd086df3ffe461879dc8881095ace4deb2db5
|
3 |
+
size 6380943
|
parser/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 311069
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:203b0f2da36b9cc636a77bd3900618e7923b5ba23c9e22e183744071db7a5bca
|
3 |
size 311069
|
senter/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 219953
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:458373a0abb56962b60b5cf889165ce93011ce7975780ef2ffd11e31d0ed7585
|
3 |
size 219953
|
tagger/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 7025
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8bc1aae4fbd5817ea2b977e60805b21252da503a45ccd62aa017411832ca4b4d
|
3 |
size 7025
|
tok2vec/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6a6389232b5271d80872a92ca25039f3cf4ec7b90195f3a80e84fc1a5426725
|
3 |
+
size 6495793
|
tokenizer
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
-
��prefix_search�~^§|^%|^=|^—|^–|^\+(?![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�2a…$|……$|,$|:$|;$|\!$|\?$|¿$|؟$|¡$|\($|\)$|\[$|\]$|\{$|\}$|<$|>$|_$|#$|\*$|&$|。$|?$|!$|,$|、$|;$|:$|~$|·$|।$|،$|۔$|؛$|٪$|\.\.+$|…$|"$|”$|“$|`$|‘$|´$|’$|‚$|,$|„$|»$|«$|「$|」$|『$|』$|($|)$|〔$|〕$|【$|】$|《$|》$|〈$|〉$|[\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][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�G�\.\.+|…|[\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]|(?<=[a-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])\.(?=[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])|(?<=[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-\U0002FA1F0-9])[<>=/](?=[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�-__-�._.��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�:’)�:’-(��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++�Ehkei��A�EhkC�ehkä�A�eiC�ei�Ehkeivat��A�EhkC�ehkä�A�eivatC�eivät�Ehkeivät��A�EhkC�ehkä�A�eivätC�eivät�Ehkemme��A�EhkC�ehkä�A�emmeC�emme�Ehken��A�EhkC�ehkä�A�enC�en�Ehket��A�EhkC�ehkä�A�etC�et�Ehkette��A�EhkC�ehkä�A�etteC�ette�Ellei��A�EllC�jos�A�eiC�ei�Elleivat��A�EllC�jos�A�eivatC�eivät�Elleivät��A�EllC�jos�A�eivätC�eivät�Ellemme��A�EllC�jos�A�emmeC�emme�Ellen��A�EllC�jos�A�enC�en�Ellet��A�EllC�jos�A�etC�et�Ellette��A�EllC�jos�A�etteC�ette�Ettei��A�EttC�että�A�eiC�ei�Etteivat��A�EttC�että�A�eivatC�eivät�Etteivät��A�EttC�että�A�eivätC�eivät�Ettemme��A�EttC�että�A�emmeC�emme�Etten��A�EttC�että�A�enC�en�Ettet��A�EttC�että�A�etC�et�Ettette��A�EttC�että�A�etteC�ette�Jollei��A�JollC�jos�A�eiC�ei�Jolleivat��A�JollC�jos�A�eivatC�eivät�Jolleivät��A�JollC�jos�A�eivätC�eivät�Jollemme��A�JollC�jos�A�emmeC�emme�Jollen��A�JollC�jos�A�enC�en�Jollet��A�JollC�jos�A�etC�et�Jollette��A�JollC�jos�A�etteC�ette�Jottei��A�JottC�jotta�A�eiC�ei�Jotteivat��A�JottC�jotta�A�eivatC�eivät�Jotteivät��A�JottC�jotta�A�eivätC�eivät�Jottemme��A�JottC�jotta�A�emmeC�emme�Jotten��A�JottC�jotta�A�enC�en�Jottet��A�JottC�jotta�A�etC�et�Jottette��A�JottC�jotta�A�etteC�ette�Koskei��A�KoskC�koska�A�eiC�ei�Koskeivat��A�KoskC�koska�A�eivatC�eivät�Koskeivät��A�KoskC�koska�A�eivätC�eivät�Koskemme��A�KoskC�koska�A�emmeC�emme�Kosken��A�KoskC�koska�A�enC�en�Kosket��A�KoskC�koska�A�etC�et�Koskette��A�KoskC�koska�A�etteC�ette�Miksei��A�MiksC�miksi�A�eiC�ei�Mikseivat��A�MiksC�miksi�A�eivatC�eivät�Mikseivät��A�MiksC�miksi�A�eivätC�eivät�Miksemme��A�MiksC�miksi�A�emmeC�emme�Miksen��A�MiksC�miksi�A�enC�en�Mikset��A�MiksC�miksi�A�etC�et�Miksette��A�MiksC�miksi�A�etteC�ette�Mm.��A�Mm.�Muttei��A�MuttC�mutta�A�eiC�ei�Mutteivat��A�MuttC�mutta�A�eivatC�eivät�Mutteivät��A�MuttC�mutta�A�eivätC�eivät�Muttemme��A�MuttC�mutta�A�emmeC�emme�Mutten��A�MuttC�mutta�A�enC�en�Muttet��A�MuttC�mutta�A�etC�et�Muttette��A�MuttC�mutta�A�etteC�ette�N:o��A�N:o�O.O��A�O.O�O.o��A�O.o�O_O��A�O_O�O_o��A�O_o�Siksei��A�SiksC�siksi�A�eiC�ei�Sikseivat��A�SiksC�siksi�A�eivatC�eivät�Sikseivät��A�SiksC�siksi�A�eivätC�eivät�Siksemme��A�SiksC�siksi�A�emmeC�emme�Siksen��A�SiksC�siksi�A�enC�en�Sikset��A�SiksC�siksi�A�etC�et�Siksette��A�SiksC�siksi�A�etteC�ette�V.V��A�V.V�V_V��A�V_V�Vaikkei��A�VaikkC�vaikka�A�eiC�ei�Vaikkeivat��A�VaikkC�vaikka�A�eivatC�eivät�Vaikkeivät��A�VaikkC�vaikka�A�eivätC�eivät�Vaikkemme��A�VaikkC�vaikka�A�emmeC�emme�Vaikken��A�VaikkC�vaikka�A�enC�en�Vaikket��A�VaikkC�vaikka�A�etC�et�Vaikkette��A�VaikkC�vaikka�A�etteC�ette�XD��A�XD�XDD��A�XDD�[-:��A�[-:�[:��A�[:�[=��A�[=�\")��A�\")�\n��A�\n�\t��A�\t�]=��A�]=�^_^��A�^_^�^__^��A�^__^�^___^��A�^___^�a.��A�a.�aik.��A�aik.�alk.��A�alk.�alv.��A�alv.�ao.��A�ao.�ark.��A�ark.�as.��A�as.�b.��A�b.�c.��A�c.�d.��A�d.�e.��A�e.�eaa.��A�eaa.�ed.��A�ed.�ehkei��A�ehkC�ehkä�A�eiC�ei�ehkeivat��A�ehkC�ehkä�A�eivatC�eivät�ehkeivät��A�ehkC�ehkä�A�eivätC�eivät�ehkemme��A�ehkC�ehkä�A�emmeC�emme�ehken��A�ehkC�ehkä�A�enC�en�ehket��A�ehkC�ehkä�A�etC�et�ehkette��A�ehkC�ehkä�A�etteC�ette�ellei��A�ellC�jos�A�eiC�ei�elleivat��A�ellC�jos�A�eivatC�eivät�elleivät��A�ellC�jos�A�eivätC�eivät�ellemme��A�ellC�jos�A�emmeC�emme�ellen��A�ellC�jos�A�enC�en�ellet��A�ellC�jos�A�etC�et�ellette��A�ellC�jos�A�etteC�ette�em.��A�em.�esim.��A�esim.�ettei��A�ettC�että�A�eiC�ei�etteivat��A�ettC�että�A�eivatC�eivät�etteivät��A�ettC�että�A�eivätC�eivät�ettemme��A�ettC�että�A�emmeC�emme�etten��A�ettC�että�A�enC�en�ettet��A�ettC�että�A�etC�et�ettette��A�ettC�että�A�etteC�ette�f.��A�f.�g.��A�g.�h.��A�h.�huom.��A�huom.�i.��A�i.�j.��A�j.�jne.��A�jne.�joht.��A�joht.�jollei��A�jollC�jos�A�eiC�ei�jolleivat��A�jollC�jos�A�eivatC�eivät�jolleivät��A�jollC�jos�A�eivätC�eivät�jollemme��A�jollC�jos�A�emmeC�emme�jollen��A�jollC�jos�A�enC�en�jollet��A�jollC�jos�A�etC�et�jollette��A�jollC�jos�A�etteC�ette�jottei��A�jottC�jotta�A�eiC�ei�jotteivat��A�jottC�jotta�A�eivatC�eivät�jotteivät��A�jottC�jotta�A�eivätC�eivät�jottemme��A�jottC�jotta�A�emmeC�emme�jotten��A�jottC�jotta�A�enC�en�jottet��A�jottC�jotta�A�etC�et�jottette��A�jottC�jotta�A�etteC�ette�k.��A�k.�ko.��A�ko.�koskei��A�koskC�koska�A�eiC�ei�koskeivat��A�koskC�koska�A�eivatC�eivät�koskeivät��A�koskC�koska�A�eivätC�eivät�koskemme��A�koskC�koska�A�emmeC�emme�kosken��A�koskC�koska�A�enC�en�kosket��A�koskC�koska�A�etC�et�koskette��A�koskC�koska�A�etteC�ette�ks.��A�ks.�l.��A�l.�lk.��A�lk.�lkm.��A�lkm.�lyh.��A�lyh.�läh.��A�läh.�m.��A�m.�miel.��A�miel.�miksei��A�miksC�miksi�A�eiC�ei�mikseivat��A�miksC�miksi�A�eivatC�eivät�mikseivät��A�miksC�miksi�A�eivätC�eivät�miksemme��A�miksC�miksi�A�emmeC�emme�miksen��A�miksC�miksi�A�enC�en�mikset��A�miksC�miksi�A�etC�et�miksette��A�miksC�miksi�A�etteC�ette�milj.��A�milj.�ml.��A�ml.�mm.��A�mm.�muttei��A�muttC�mutta�A�eiC�ei�mutteivat��A�muttC�mutta�A�eivatC�eivät�mutteivät��A�muttC�mutta�A�eivätC�eivät�muttemme��A�muttC�mutta�A�emmeC�emme�mutten��A�muttC�mutta�A�enC�en�muttet��A�muttC�mutta�A�etC�et�muttette��A�muttC�mutta�A�etteC�ette�myöh.��A�myöh.�n.��A�n.�n:o��A�n:o�nimim.��A�nimim.�nro��A�nro�ns.��A�ns.�nyk.��A�nyk.�o.��A�o.�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�oik.��A�oik.�os.��A�os.�p.��A�p.�par.��A�par.�per.��A�per.�pj.��A�pj.�po.��A�po.�prof.��A�prof.�puh.��A�puh.�puh.joht.��A�puh.joht.�pvm.��A�pvm.�q.��A�q.�r.��A�r.�rak.��A�rak.�ry.��A�ry.�s.��A�s.�siht.��A�siht.�siksei��A�siksC�siksi�A�eiC�ei�sikseivat��A�siksC�siksi�A�eivatC�eivät�sikseivät��A�siksC�siksi�A�eivätC�eivät�siksemme��A�siksC�siksi�A�emmeC�emme�siksen��A�siksC�siksi�A�enC�en�sikset��A�siksC�siksi�A�etC�et�siksette��A�siksC�siksi�A�etteC�ette�so.��A�so.�srk.��A�srk.�synt.��A�synt.�t.��A�t.�tark.��A�tark.�til.��A�til.�tms.��A�tms.�toim.��A�toim.�ts.��A�ts.�u.��A�u.�v.��A�v.�v.v��A�v.v�v_v��A�v_v�vaikkei��A�vaikkC�vaikka�A�eiC�ei�vaikkeivat��A�vaikkC�vaikka�A�eivatC�eivät�vaikkeivät��A�vaikkC�vaikka�A�eivätC�eivät�vaikkemme��A�vaikkC�vaikka�A�emmeC�emme�vaikken��A�vaikkC�vaikka�A�enC�en�vaikket��A�vaikkC�vaikka�A�etC�et�vaikkette��A�vaikkC�vaikka�A�etteC�ette�vas.��A�vas.�vast.��A�vast.�vm.��A�vm.�vrt.��A�vrt.�w.��A�w.�x.��A�x.�xD��A�xD�xDD��A�xDD�y.��A�y.�yht.��A�yht.�yl.��A�yl.�yliopp.��A�yliopp.�ym.��A�ym.�yms.��A�yms.�yo.��A�yo.�z.��A�z.� ��A� C� �¯\(ツ)/¯��A�¯\(ツ)/¯�°C.��A�°�A�C�A�.�°F.��A�°�A�F�A�.�°K.��A�°�A�K�A�.�°c.��A�°�A�c�A�.�°f.��A�°�A�f�A�.�°k.��A�°�A�k�A�.�ä.��A�ä.�ö.��A�ö.�ü.��A�ü.�ಠ_ಠ��A�ಠ_ಠ�ಠ︵ಠ��A�ಠ︵ಠ�—��A�—�’��A�’�’’��A�’’�faster_heuristics�
|
|
|
1 |
+
��prefix_search��^§|^%|^=|^—|^–|^\+(?![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�2�…$|……$|,$|:$|;$|\!$|\?$|¿$|؟$|¡$|\($|\)$|\[$|\]$|\{$|\}$|<$|>$|_$|#$|\*$|&$|。$|?$|!$|,$|、$|;$|:$|~$|·$|।$|،$|۔$|؛$|٪$|\.\.+$|…$|"$|”$|“$|`$|‘$|´$|’$|‚$|,$|„$|»$|«$|「$|」$|『$|』$|($|)$|〔$|〕$|【$|】$|《$|》$|〈$|〉$|〈$|〉$|⟦$|⟧$|[\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][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�H\.\.+|…|[\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]|(?<=[a-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])\.(?=[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])|(?<=[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-ω��έίόώήύΑ-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-\U0002FA1F0-9])[<>=/](?=[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�-__-�._.��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�:’)�:’-(��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++�Ehkei��A�EhkC�ehkä�A�eiC�ei�Ehkeivat��A�EhkC�ehkä�A�eivatC�eivät�Ehkeivät��A�EhkC�ehkä�A�eivätC�eivät�Ehkemme��A�EhkC�ehkä�A�emmeC�emme�Ehken��A�EhkC�ehkä�A�enC�en�Ehket��A�EhkC�ehkä�A�etC�et�Ehkette��A�EhkC�ehkä�A�etteC�ette�Ellei��A�EllC�jos�A�eiC�ei�Elleivat��A�EllC�jos�A�eivatC�eivät�Elleivät��A�EllC�jos�A�eivätC�eivät�Ellemme��A�EllC�jos�A�emmeC�emme�Ellen��A�EllC�jos�A�enC�en�Ellet��A�EllC�jos�A�etC�et�Ellette��A�EllC�jos�A�etteC�ette�Ettei��A�EttC�että�A�eiC�ei�Etteivat��A�EttC�että�A�eivatC�eivät�Etteivät��A�EttC�että�A�eivätC�eivät�Ettemme��A�EttC�että�A�emmeC�emme�Etten��A�EttC�että�A�enC�en�Ettet��A�EttC�että�A�etC�et�Ettette��A�EttC�että�A�etteC�ette�Jollei��A�JollC�jos�A�eiC�ei�Jolleivat��A�JollC�jos�A�eivatC�eivät�Jolleivät��A�JollC�jos�A�eivätC�eivät�Jollemme��A�JollC�jos�A�emmeC�emme�Jollen��A�JollC�jos�A�enC�en�Jollet��A�JollC�jos�A�etC�et�Jollette��A�JollC�jos�A�etteC�ette�Jottei��A�JottC�jotta�A�eiC�ei�Jotteivat��A�JottC�jotta�A�eivatC�eivät�Jotteivät��A�JottC�jotta�A�eivätC�eivät�Jottemme��A�JottC�jotta�A�emmeC�emme�Jotten��A�JottC�jotta�A�enC�en�Jottet��A�JottC�jotta�A�etC�et�Jottette��A�JottC�jotta�A�etteC�ette�Koskei��A�KoskC�koska�A�eiC�ei�Koskeivat��A�KoskC�koska�A�eivatC�eivät�Koskeivät��A�KoskC�koska�A�eivätC�eivät�Koskemme��A�KoskC�koska�A�emmeC�emme�Kosken��A�KoskC�koska�A�enC�en�Kosket��A�KoskC�koska�A�etC�et�Koskette��A�KoskC�koska�A�etteC�ette�Miksei��A�MiksC�miksi�A�eiC�ei�Mikseivat��A�MiksC�miksi�A�eivatC�eivät�Mikseivät��A�MiksC�miksi�A�eivätC�eivät�Miksemme��A�MiksC�miksi�A�emmeC�emme�Miksen��A�MiksC�miksi�A�enC�en�Mikset��A�MiksC�miksi�A�etC�et�Miksette��A�MiksC�miksi�A�etteC�ette�Mm.��A�Mm.�Muttei��A�MuttC�mutta�A�eiC�ei�Mutteivat��A�MuttC�mutta�A�eivatC�eivät�Mutteivät��A�MuttC�mutta�A�eivätC�eivät�Muttemme��A�MuttC�mutta�A�emmeC�emme�Mutten��A�MuttC�mutta�A�enC�en�Muttet��A�MuttC�mutta�A�etC�et�Muttette��A�MuttC�mutta�A�etteC�ette�N:o��A�N:o�O.O��A�O.O�O.o��A�O.o�O_O��A�O_O�O_o��A�O_o�Siksei��A�SiksC�siksi�A�eiC�ei�Sikseivat��A�SiksC�siksi�A�eivatC�eivät�Sikseivät��A�SiksC�siksi�A�eivätC�eivät�Siksemme��A�SiksC�siksi�A�emmeC�emme�Siksen��A�SiksC�siksi�A�enC�en�Sikset��A�SiksC�siksi�A�etC�et�Siksette��A�SiksC�siksi�A�etteC�ette�V.V��A�V.V�V_V��A�V_V�Vaikkei��A�VaikkC�vaikka�A�eiC�ei�Vaikkeivat��A�VaikkC�vaikka�A�eivatC�eivät�Vaikkeivät��A�VaikkC�vaikka�A�eivätC�eivät�Vaikkemme��A�VaikkC�vaikka�A�emmeC�emme�Vaikken��A�VaikkC�vaikka�A�enC�en�Vaikket��A�VaikkC�vaikka�A�etC�et�Vaikkette��A�VaikkC�vaikka�A�etteC�ette�XD��A�XD�XDD��A�XDD�[-:��A�[-:�[:��A�[:�[=��A�[=�\")��A�\")�\n��A�\n�\t��A�\t�]=��A�]=�^_^��A�^_^�^__^��A�^__^�^___^��A�^___^�a.��A�a.�aik.��A�aik.�alk.��A�alk.�alv.��A�alv.�ao.��A�ao.�ark.��A�ark.�as.��A�as.�b.��A�b.�c.��A�c.�d.��A�d.�e.��A�e.�eaa.��A�eaa.�ed.��A�ed.�ehkei��A�ehkC�ehkä�A�eiC�ei�ehkeivat��A�ehkC�ehkä�A�eivatC�eivät�ehkeivät��A�ehkC�ehkä�A�eivätC�eivät�ehkemme��A�ehkC�ehkä�A�emmeC�emme�ehken��A�ehkC�ehkä�A�enC�en�ehket��A�ehkC�ehkä�A�etC�et�ehkette��A�ehkC�ehkä�A�etteC�ette�ellei��A�ellC�jos�A�eiC�ei�elleivat��A�ellC�jos�A�eivatC�eivät�elleivät��A�ellC�jos�A�eivätC�eivät�ellemme��A�ellC�jos�A�emmeC�emme�ellen��A�ellC�jos�A�enC�en�ellet��A�ellC�jos�A�etC�et�ellette��A�ellC�jos�A�etteC�ette�em.��A�em.�esim.��A�esim.�ettei��A�ettC�että�A�eiC�ei�etteivat��A�ettC�että�A�eivatC�eivät�etteivät��A�ettC�että�A�eivätC�eivät�ettemme��A�ettC�että�A�emmeC�emme�etten��A�ettC�että�A�enC�en�ettet��A�ettC�että�A�etC�et�ettette��A�ettC�että�A�etteC�ette�f.��A�f.�g.��A�g.�h.��A�h.�huom.��A�huom.�i.��A�i.�j.��A�j.�jne.��A�jne.�joht.��A�joht.�jollei��A�jollC�jos�A�eiC�ei�jolleivat��A�jollC�jos�A�eivatC�eivät�jolleivät��A�jollC�jos�A�eivätC�eivät�jollemme��A�jollC�jos�A�emmeC�emme�jollen��A�jollC�jos�A�enC�en�jollet��A�jollC�jos�A�etC�et�jollette��A�jollC�jos�A�etteC�ette�jottei��A�jottC�jotta�A�eiC�ei�jotteivat��A�jottC�jotta�A�eivatC�eivät�jotteivät��A�jottC�jotta�A�eivätC�eivät�jottemme��A�jottC�jotta�A�emmeC�emme�jotten��A�jottC�jotta�A�enC�en�jottet��A�jottC�jotta�A�etC�et�jottette��A�jottC�jotta�A�etteC�ette�k.��A�k.�ko.��A�ko.�koskei��A�koskC�koska�A�eiC�ei�koskeivat��A�koskC�koska�A�eivatC�eivät�koskeivät��A�koskC�koska�A�eivätC�eivät�koskemme��A�koskC�koska�A�emmeC�emme�kosken��A�koskC�koska�A�enC�en�kosket��A�koskC�koska�A�etC�et�koskette��A�koskC�koska�A�etteC�ette�ks.��A�ks.�l.��A�l.�lk.��A�lk.�lkm.��A�lkm.�lyh.��A�lyh.�läh.��A�läh.�m.��A�m.�miel.��A�miel.�miksei��A�miksC�miksi�A�eiC�ei�mikseivat��A�miksC�miksi�A�eivatC�eivät�mikseivät��A�miksC�miksi�A�eivätC�eivät�miksemme��A�miksC�miksi�A�emmeC�emme�miksen��A�miksC�miksi�A�enC�en�mikset��A�miksC�miksi�A�etC�et�miksette��A�miksC�miksi�A�etteC�ette�milj.��A�milj.�ml.��A�ml.�mm.��A�mm.�muttei��A�muttC�mutta�A�eiC�ei�mutteivat��A�muttC�mutta�A�eivatC�eivät�mutteivät��A�muttC�mutta�A�eivätC�eivät�muttemme��A�muttC�mutta�A�emmeC�emme�mutten��A�muttC�mutta�A�enC�en�muttet��A�muttC�mutta�A�etC�et�muttette��A�muttC�mutta�A�etteC�ette�myöh.��A�myöh.�n.��A�n.�n:o��A�n:o�nimim.��A�nimim.�nro��A�nro�ns.��A�ns.�nyk.��A�nyk.�o.��A�o.�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�oik.��A�oik.�os.��A�os.�p.��A�p.�par.��A�par.�per.��A�per.�pj.��A�pj.�po.��A�po.�prof.��A�prof.�puh.��A�puh.�puh.joht.��A�puh.joht.�pvm.��A�pvm.�q.��A�q.�r.��A�r.�rak.��A�rak.�ry.��A�ry.�s.��A�s.�siht.��A�siht.�siksei��A�siksC�siksi�A�eiC�ei�sikseivat��A�siksC�siksi�A�eivatC�eivät�sikseivät��A�siksC�siksi�A�eivätC�eivät�siksemme��A�siksC�siksi�A�emmeC�emme�siksen��A�siksC�siksi�A�enC�en�sikset��A�siksC�siksi�A�etC�et�siksette��A�siksC�siksi�A�etteC�ette�so.��A�so.�srk.��A�srk.�synt.��A�synt.�t.��A�t.�tark.��A�tark.�til.��A�til.�tms.��A�tms.�toim.��A�toim.�ts.��A�ts.�u.��A�u.�v.��A�v.�v.v��A�v.v�v_v��A�v_v�vaikkei��A�vaikkC�vaikka�A�eiC�ei�vaikkeivat��A�vaikkC�vaikka�A�eivatC�eivät�vaikkeivät��A�vaikkC�vaikka�A�eivätC�eivät�vaikkemme��A�vaikkC�vaikka�A�emmeC�emme�vaikken��A�vaikkC�vaikka�A�enC�en�vaikket��A�vaikkC�vaikka�A�etC�et�vaikkette��A�vaikkC�vaikka�A�etteC�ette�vas.��A�vas.�vast.��A�vast.�vm.��A�vm.�vrt.��A�vrt.�w.��A�w.�x.��A�x.�xD��A�xD�xDD��A�xDD�y.��A�y.�yht.��A�yht.�yl.��A�yl.�yliopp.��A�yliopp.�ym.��A�ym.�yms.��A�yms.�yo.��A�yo.�z.��A�z.� ��A� C� �¯\(ツ)/¯��A�¯\(ツ)/¯�°C.��A�°�A�C�A�.�°F.��A�°�A�F�A�.�°K.��A�°�A�K�A�.�°c.��A�°�A�c�A�.�°f.��A�°�A�f�A�.�°k.��A�°�A�k�A�.�ä.��A�ä.�ö.��A�ö.�ü.��A�ü.�ಠ_ಠ��A�ಠ_ಠ�ಠ︵ಠ��A�ಠ︵ಠ�—��A�—�’��A�’�’’��A�’’�faster_heuristics�
|
vocab/strings.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b78005b33f182f5324c2a1c7ae21bd2e80803115993dcbba49445c84f1af61d6
|
3 |
+
size 2597680
|