1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
|
"""
Basic testing of tokenization
"""
import pytest
import stanza
from stanza.tests import *
pytestmark = pytest.mark.pipeline
EN_DOC = "Joe Smith lives in California. Joe's favorite food is pizza. He enjoys going to the beach."
EN_DOC_WITH_EXTRA_WHITESPACE = "Joe Smith \n lives in\n California. Joe's favorite food \tis pizza. \t\t\tHe enjoys \t\tgoing to the beach."
EN_DOC_GOLD_TOKENS = """
<Token id=1;words=[<Word id=1;text=Joe>]>
<Token id=2;words=[<Word id=2;text=Smith>]>
<Token id=3;words=[<Word id=3;text=lives>]>
<Token id=4;words=[<Word id=4;text=in>]>
<Token id=5;words=[<Word id=5;text=California>]>
<Token id=6;words=[<Word id=6;text=.>]>
<Token id=1;words=[<Word id=1;text=Joe>]>
<Token id=2;words=[<Word id=2;text='s>]>
<Token id=3;words=[<Word id=3;text=favorite>]>
<Token id=4;words=[<Word id=4;text=food>]>
<Token id=5;words=[<Word id=5;text=is>]>
<Token id=6;words=[<Word id=6;text=pizza>]>
<Token id=7;words=[<Word id=7;text=.>]>
<Token id=1;words=[<Word id=1;text=He>]>
<Token id=2;words=[<Word id=2;text=enjoys>]>
<Token id=3;words=[<Word id=3;text=going>]>
<Token id=4;words=[<Word id=4;text=to>]>
<Token id=5;words=[<Word id=5;text=the>]>
<Token id=6;words=[<Word id=6;text=beach>]>
<Token id=7;words=[<Word id=7;text=.>]>
""".strip()
EN_DOC_GOLD_NOSSPLIT_TOKENS = """
<Token id=1;words=[<Word id=1;text=Joe>]>
<Token id=2;words=[<Word id=2;text=Smith>]>
<Token id=3;words=[<Word id=3;text=lives>]>
<Token id=4;words=[<Word id=4;text=in>]>
<Token id=5;words=[<Word id=5;text=California>]>
<Token id=6;words=[<Word id=6;text=.>]>
<Token id=7;words=[<Word id=7;text=Joe>]>
<Token id=8;words=[<Word id=8;text='s>]>
<Token id=9;words=[<Word id=9;text=favorite>]>
<Token id=10;words=[<Word id=10;text=food>]>
<Token id=11;words=[<Word id=11;text=is>]>
<Token id=12;words=[<Word id=12;text=pizza>]>
<Token id=13;words=[<Word id=13;text=.>]>
<Token id=14;words=[<Word id=14;text=He>]>
<Token id=15;words=[<Word id=15;text=enjoys>]>
<Token id=16;words=[<Word id=16;text=going>]>
<Token id=17;words=[<Word id=17;text=to>]>
<Token id=18;words=[<Word id=18;text=the>]>
<Token id=19;words=[<Word id=19;text=beach>]>
<Token id=20;words=[<Word id=20;text=.>]>
""".strip()
EN_DOC_PRETOKENIZED = \
"Joe Smith lives in California .\nJoe's favorite food is pizza .\n\nHe enjoys going to the beach.\n"
EN_DOC_PRETOKENIZED_GOLD_TOKENS = """
<Token id=1;words=[<Word id=1;text=Joe>]>
<Token id=2;words=[<Word id=2;text=Smith>]>
<Token id=3;words=[<Word id=3;text=lives>]>
<Token id=4;words=[<Word id=4;text=in>]>
<Token id=5;words=[<Word id=5;text=California>]>
<Token id=6;words=[<Word id=6;text=.>]>
<Token id=1;words=[<Word id=1;text=Joe's>]>
<Token id=2;words=[<Word id=2;text=favorite>]>
<Token id=3;words=[<Word id=3;text=food>]>
<Token id=4;words=[<Word id=4;text=is>]>
<Token id=5;words=[<Word id=5;text=pizza>]>
<Token id=6;words=[<Word id=6;text=.>]>
<Token id=1;words=[<Word id=1;text=He>]>
<Token id=2;words=[<Word id=2;text=enjoys>]>
<Token id=3;words=[<Word id=3;text=going>]>
<Token id=4;words=[<Word id=4;text=to>]>
<Token id=5;words=[<Word id=5;text=the>]>
<Token id=6;words=[<Word id=6;text=beach.>]>
""".strip()
EN_DOC_PRETOKENIZED_LIST = [['Joe', 'Smith', 'lives', 'in', 'California', '.'], ['He', 'loves', 'pizza', '.']]
EN_DOC_PRETOKENIZED_LIST_GOLD_TOKENS = """
<Token id=1;words=[<Word id=1;text=Joe>]>
<Token id=2;words=[<Word id=2;text=Smith>]>
<Token id=3;words=[<Word id=3;text=lives>]>
<Token id=4;words=[<Word id=4;text=in>]>
<Token id=5;words=[<Word id=5;text=California>]>
<Token id=6;words=[<Word id=6;text=.>]>
<Token id=1;words=[<Word id=1;text=He>]>
<Token id=2;words=[<Word id=2;text=loves>]>
<Token id=3;words=[<Word id=3;text=pizza>]>
<Token id=4;words=[<Word id=4;text=.>]>
""".strip()
EN_DOC_NO_SSPLIT = ["This is a sentence. This is another.", "This is a third."]
EN_DOC_NO_SSPLIT_SENTENCES = [['This', 'is', 'a', 'sentence', '.', 'This', 'is', 'another', '.'], ['This', 'is', 'a', 'third', '.']]
JA_DOC = "北京は中国の首都です。 北京の人口は2152万人です。\n" # add some random whitespaces that need to be skipped
JA_DOC_GOLD_TOKENS = """
<Token id=1;words=[<Word id=1;text=北京>]>
<Token id=2;words=[<Word id=2;text=は>]>
<Token id=3;words=[<Word id=3;text=中国>]>
<Token id=4;words=[<Word id=4;text=の>]>
<Token id=5;words=[<Word id=5;text=首都>]>
<Token id=6;words=[<Word id=6;text=です>]>
<Token id=7;words=[<Word id=7;text=。>]>
<Token id=1;words=[<Word id=1;text=北京>]>
<Token id=2;words=[<Word id=2;text=の>]>
<Token id=3;words=[<Word id=3;text=人口>]>
<Token id=4;words=[<Word id=4;text=は>]>
<Token id=5;words=[<Word id=5;text=2152万>]>
<Token id=6;words=[<Word id=6;text=人>]>
<Token id=7;words=[<Word id=7;text=です>]>
<Token id=8;words=[<Word id=8;text=。>]>
""".strip()
JA_DOC_GOLD_NOSSPLIT_TOKENS = """
<Token id=1;words=[<Word id=1;text=北京>]>
<Token id=2;words=[<Word id=2;text=は>]>
<Token id=3;words=[<Word id=3;text=中国>]>
<Token id=4;words=[<Word id=4;text=の>]>
<Token id=5;words=[<Word id=5;text=首都>]>
<Token id=6;words=[<Word id=6;text=です>]>
<Token id=7;words=[<Word id=7;text=。>]>
<Token id=8;words=[<Word id=8;text=北京>]>
<Token id=9;words=[<Word id=9;text=の>]>
<Token id=10;words=[<Word id=10;text=人口>]>
<Token id=11;words=[<Word id=11;text=は>]>
<Token id=12;words=[<Word id=12;text=2152万>]>
<Token id=13;words=[<Word id=13;text=人>]>
<Token id=14;words=[<Word id=14;text=です>]>
<Token id=15;words=[<Word id=15;text=。>]>
""".strip()
ZH_DOC = "北京是中国的首都。 北京有2100万人口，是一个直辖市。\n"
ZH_DOC1 = "北\n京是中\n国的首\n都。 北京有2100万人口，是一个直辖市。\n"
ZH_DOC_GOLD_TOKENS = """
<Token id=1;words=[<Word id=1;text=北京>]>
<Token id=2;words=[<Word id=2;text=是>]>
<Token id=3;words=[<Word id=3;text=中国>]>
<Token id=4;words=[<Word id=4;text=的>]>
<Token id=5;words=[<Word id=5;text=首都>]>
<Token id=6;words=[<Word id=6;text=。>]>
<Token id=1;words=[<Word id=1;text=北京>]>
<Token id=2;words=[<Word id=2;text=有>]>
<Token id=3;words=[<Word id=3;text=2100>]>
<Token id=4;words=[<Word id=4;text=万>]>
<Token id=5;words=[<Word id=5;text=人口>]>
<Token id=6;words=[<Word id=6;text=，>]>
<Token id=7;words=[<Word id=7;text=是>]>
<Token id=8;words=[<Word id=8;text=一个>]>
<Token id=9;words=[<Word id=9;text=直辖市>]>
<Token id=10;words=[<Word id=10;text=。>]>
""".strip()
ZH_DOC1_GOLD_TOKENS="""
<Token id=1;words=[<Word id=1;text=北京;lemma=北京;upos=PROPN;xpos=NNP;head=5;deprel=nsubj>]>
<Token id=2;words=[<Word id=2;text=是;lemma=是;upos=AUX;xpos=VC;head=5;deprel=cop>]>
<Token id=3;words=[<Word id=3;text=中国;lemma=中国;upos=PROPN;xpos=NNP;head=5;deprel=nmod>]>
<Token id=4;words=[<Word id=4;text=的;lemma=的;upos=PART;xpos=DEC;feats=Case=Gen;head=3;deprel=case:dec>]>
<Token id=5;words=[<Word id=5;text=首都;lemma=首都;upos=NOUN;xpos=NN;head=0;deprel=root>]>
<Token id=6;words=[<Word id=6;text=。;lemma=。;upos=PUNCT;xpos=.;head=5;deprel=punct>]>
<Token id=1;words=[<Word id=1;text=北京;lemma=北京;upos=PROPN;xpos=NNP;head=2;deprel=nsubj>]>
<Token id=2;words=[<Word id=2;text=有;lemma=有;upos=VERB;xpos=VV;head=11;deprel=acl>]>
<Token id=3;words=[<Word id=3;text=2100万;lemma=2100万;upos=NUM;xpos=CD;feats=NumType=Card;head=4;deprel=nummod>]>
<Token id=4;words=[<Word id=4;text=人;lemma=人;upos=NOUN;xpos=NN;head=5;deprel=compound>]>
<Token id=5;words=[<Word id=5;text=口;lemma=口;upos=PART;xpos=SFN;head=2;deprel=obj>]>
<Token id=6;words=[<Word id=6;text=，;lemma=，;upos=PUNCT;xpos=,;head=11;deprel=punct>]>
<Token id=7;words=[<Word id=7;text=是;lemma=是;upos=AUX;xpos=VC;head=11;deprel=cop>]>
<Token id=8;words=[<Word id=8;text=一;lemma=一;upos=NUM;xpos=CD;feats=NumType=Card;head=9;deprel=nummod>]>
<Token id=9;words=[<Word id=9;text=个;lemma=个;upos=NOUN;xpos=NNB;head=11;deprel=nmod>]>
<Token id=10;words=[<Word id=10;text=直辖;lemma=直辖;upos=VERB;xpos=VV;head=11;deprel=compound>]>
<Token id=11;words=[<Word id=11;text=市;lemma=市;upos=PART;xpos=SFN;head=0;deprel=root>]>
<Token id=12;words=[<Word id=12;text=。;lemma=。;upos=PUNCT;xpos=.;head=11;deprel=punct>]>
""".strip()
ZH_DOC_GOLD_NOSSPLIT_TOKENS = """
<Token id=1;words=[<Word id=1;text=北京>]>
<Token id=2;words=[<Word id=2;text=是>]>
<Token id=3;words=[<Word id=3;text=中国>]>
<Token id=4;words=[<Word id=4;text=的>]>
<Token id=5;words=[<Word id=5;text=首都>]>
<Token id=6;words=[<Word id=6;text=。>]>
<Token id=7;words=[<Word id=7;text=北京>]>
<Token id=8;words=[<Word id=8;text=有>]>
<Token id=9;words=[<Word id=9;text=2100>]>
<Token id=10;words=[<Word id=10;text=万>]>
<Token id=11;words=[<Word id=11;text=人口>]>
<Token id=12;words=[<Word id=12;text=，>]>
<Token id=13;words=[<Word id=13;text=是>]>
<Token id=14;words=[<Word id=14;text=一个>]>
<Token id=15;words=[<Word id=15;text=直辖市>]>
<Token id=16;words=[<Word id=16;text=。>]>
""".strip()
ZH_PARENS_DOC = "我们一起学(猫叫)"
TH_DOC = "ข้าราชการได้รับการหมุนเวียนเป็นระยะ และเขาได้รับมอบหมายให้ประจำในระดับภูมิภาค"
TH_DOC_GOLD_TOKENS = """
<Token id=1;words=[<Word id=1;text=ข้าราชการ>]>
<Token id=2;words=[<Word id=2;text=ได้รับ>]>
<Token id=3;words=[<Word id=3;text=การ>]>
<Token id=4;words=[<Word id=4;text=หมุนเวียน>]>
<Token id=5;words=[<Word id=5;text=เป็นระยะ>]>
<Token id=1;words=[<Word id=1;text=และ>]>
<Token id=2;words=[<Word id=2;text=เขา>]>
<Token id=3;words=[<Word id=3;text=ได้>]>
<Token id=4;words=[<Word id=4;text=รับมอบหมาย>]>
<Token id=5;words=[<Word id=5;text=ให้>]>
<Token id=6;words=[<Word id=6;text=ประจำ>]>
<Token id=7;words=[<Word id=7;text=ใน>]>
<Token id=8;words=[<Word id=8;text=ระดับ>]>
<Token id=9;words=[<Word id=9;text=ภูมิภาค>]>
""".strip()
TH_DOC_GOLD_NOSSPLIT_TOKENS = """
<Token id=1;words=[<Word id=1;text=ข้าราชการ>]>
<Token id=2;words=[<Word id=2;text=ได้รับ>]>
<Token id=3;words=[<Word id=3;text=การ>]>
<Token id=4;words=[<Word id=4;text=หมุนเวียน>]>
<Token id=5;words=[<Word id=5;text=เป็นระยะ>]>
<Token id=6;words=[<Word id=6;text=และ>]>
<Token id=7;words=[<Word id=7;text=เขา>]>
<Token id=8;words=[<Word id=8;text=ได้>]>
<Token id=9;words=[<Word id=9;text=รับมอบหมาย>]>
<Token id=10;words=[<Word id=10;text=ให้>]>
<Token id=11;words=[<Word id=11;text=ประจำ>]>
<Token id=12;words=[<Word id=12;text=ใน>]>
<Token id=13;words=[<Word id=13;text=ระดับ>]>
<Token id=14;words=[<Word id=14;text=ภูมิภาค>]>
""".strip()
def test_tokenize():
nlp = stanza.Pipeline(processors='tokenize', dir=TEST_MODELS_DIR, lang='en')
doc = nlp(EN_DOC)
assert EN_DOC_GOLD_TOKENS == '\n\n'.join([sent.tokens_string() for sent in doc.sentences])
assert all([doc.text[token._start_char: token._end_char] == token.text for sent in doc.sentences for token in sent.tokens])
def test_tokenize_ssplit_robustness():
nlp = stanza.Pipeline(processors='tokenize', dir=TEST_MODELS_DIR, lang='en')
doc = nlp(EN_DOC_WITH_EXTRA_WHITESPACE)
assert EN_DOC_GOLD_TOKENS == '\n\n'.join([sent.tokens_string() for sent in doc.sentences])
assert all([doc.text[token._start_char: token._end_char] == token.text for sent in doc.sentences for token in sent.tokens])
def test_pretokenized():
nlp = stanza.Pipeline(**{'processors': 'tokenize', 'dir': TEST_MODELS_DIR, 'lang': 'en',
'tokenize_pretokenized': True})
doc = nlp(EN_DOC_PRETOKENIZED)
assert EN_DOC_PRETOKENIZED_GOLD_TOKENS == '\n\n'.join([sent.tokens_string() for sent in doc.sentences])
assert all([doc.text[token._start_char: token._end_char] == token.text for sent in doc.sentences for token in sent.tokens])
doc = nlp(EN_DOC_PRETOKENIZED_LIST)
assert EN_DOC_PRETOKENIZED_LIST_GOLD_TOKENS == '\n\n'.join([sent.tokens_string() for sent in doc.sentences])
assert all([doc.text[token._start_char: token._end_char] == token.text for sent in doc.sentences for token in sent.tokens])
def test_pretokenized_multidoc():
nlp = stanza.Pipeline(**{'processors': 'tokenize', 'dir': TEST_MODELS_DIR, 'lang': 'en',
'tokenize_pretokenized': True})
doc = nlp(EN_DOC_PRETOKENIZED)
assert EN_DOC_PRETOKENIZED_GOLD_TOKENS == '\n\n'.join([sent.tokens_string() for sent in doc.sentences])
assert all([doc.text[token._start_char: token._end_char] == token.text for sent in doc.sentences for token in sent.tokens])
doc = nlp([stanza.Document([], text=EN_DOC_PRETOKENIZED_LIST)])[0]
assert EN_DOC_PRETOKENIZED_LIST_GOLD_TOKENS == '\n\n'.join([sent.tokens_string() for sent in doc.sentences])
assert all([doc.text[token._start_char: token._end_char] == token.text for sent in doc.sentences for token in sent.tokens])
def test_no_ssplit():
nlp = stanza.Pipeline(**{'processors': 'tokenize', 'dir': TEST_MODELS_DIR, 'lang': 'en',
'tokenize_no_ssplit': True})
doc = nlp(EN_DOC_NO_SSPLIT)
assert EN_DOC_NO_SSPLIT_SENTENCES == [[w.text for w in s.words] for s in doc.sentences]
assert all([doc.text[token._start_char: token._end_char] == token.text for sent in doc.sentences for token in sent.tokens])
def test_zh_tokenizer_skip_newline():
nlp = stanza.Pipeline(lang='zh', dir=TEST_MODELS_DIR)
doc = nlp(ZH_DOC1)
assert ZH_DOC1_GOLD_TOKENS == '\n\n'.join([sent.tokens_string() for sent in doc.sentences])
assert all([doc.text[token._start_char: token._end_char].replace('\n', '') == token.text for sent in doc.sentences for token in sent.tokens])
def test_zh_tokenizer_parens():
"""
The original fix for newlines in Chinese text broke () in Chinese text
"""
nlp = stanza.Pipeline(lang='zh', processors="tokenize", dir=TEST_MODELS_DIR)
doc = nlp(ZH_PARENS_DOC)
# ... the results are kind of bad for this expression, so no testing of the results yet
#assert ZH_PARENS_DOC_GOLD_TOKENS == '\n\n'.join([sent.tokens_string() for sent in doc.sentences])
def test_spacy():
nlp = stanza.Pipeline(processors='tokenize', dir=TEST_MODELS_DIR, lang='en', tokenize_with_spacy=True)
doc = nlp(EN_DOC)
# make sure the loaded tokenizer is actually spacy
assert "SpacyTokenizer" == nlp.processors['tokenize']._variant.__class__.__name__
assert EN_DOC_GOLD_TOKENS == '\n\n'.join([sent.tokens_string() for sent in doc.sentences])
assert all([doc.text[token._start_char: token._end_char] == token.text for sent in doc.sentences for token in sent.tokens])
def test_spacy_no_ssplit():
nlp = stanza.Pipeline(processors='tokenize', dir=TEST_MODELS_DIR, lang='en', tokenize_with_spacy=True, tokenize_no_ssplit=True)
doc = nlp(EN_DOC)
# make sure the loaded tokenizer is actually spacy
assert "SpacyTokenizer" == nlp.processors['tokenize']._variant.__class__.__name__
assert EN_DOC_GOLD_NOSSPLIT_TOKENS == '\n\n'.join([sent.tokens_string() for sent in doc.sentences])
assert all([doc.text[token._start_char: token._end_char] == token.text for sent in doc.sentences for token in sent.tokens])
def test_sudachipy():
nlp = stanza.Pipeline(lang='ja', dir=TEST_MODELS_DIR, processors={'tokenize': 'sudachipy'}, package=None)
doc = nlp(JA_DOC)
assert "SudachiPyTokenizer" == nlp.processors['tokenize']._variant.__class__.__name__
assert JA_DOC_GOLD_TOKENS == '\n\n'.join([sent.tokens_string() for sent in doc.sentences])
assert all([doc.text[token._start_char: token._end_char] == token.text for sent in doc.sentences for token in sent.tokens])
def test_sudachipy_no_ssplit():
nlp = stanza.Pipeline(lang='ja', dir=TEST_MODELS_DIR, processors={'tokenize': 'sudachipy'}, tokenize_no_ssplit=True, package=None)
doc = nlp(JA_DOC)
assert "SudachiPyTokenizer" == nlp.processors['tokenize']._variant.__class__.__name__
assert JA_DOC_GOLD_NOSSPLIT_TOKENS == '\n\n'.join([sent.tokens_string() for sent in doc.sentences])
assert all([doc.text[token._start_char: token._end_char] == token.text for sent in doc.sentences for token in sent.tokens])
def test_jieba():
nlp = stanza.Pipeline(lang='zh', dir=TEST_MODELS_DIR, processors={'tokenize': 'jieba'}, package=None)
doc = nlp(ZH_DOC)
assert "JiebaTokenizer" == nlp.processors['tokenize']._variant.__class__.__name__
assert ZH_DOC_GOLD_TOKENS == '\n\n'.join([sent.tokens_string() for sent in doc.sentences])
assert all([doc.text[token._start_char: token._end_char] == token.text for sent in doc.sentences for token in sent.tokens])
def test_jieba_no_ssplit():
nlp = stanza.Pipeline(lang='zh', dir=TEST_MODELS_DIR, processors={'tokenize': 'jieba'}, tokenize_no_ssplit=True, package=None)
doc = nlp(ZH_DOC)
assert "JiebaTokenizer" == nlp.processors['tokenize']._variant.__class__.__name__
assert ZH_DOC_GOLD_NOSSPLIT_TOKENS == '\n\n'.join([sent.tokens_string() for sent in doc.sentences])
assert all([doc.text[token._start_char: token._end_char] == token.text for sent in doc.sentences for token in sent.tokens])
def test_pythainlp():
nlp = stanza.Pipeline(lang='th', dir=TEST_MODELS_DIR, processors={'tokenize': 'pythainlp'}, package=None)
doc = nlp(TH_DOC)
assert "PyThaiNLPTokenizer" == nlp.processors['tokenize']._variant.__class__.__name__
assert TH_DOC_GOLD_TOKENS == '\n\n'.join([sent.tokens_string() for sent in doc.sentences])
assert all([doc.text[token._start_char: token._end_char] == token.text for sent in doc.sentences for token in sent.tokens])
def test_pythainlp_no_ssplit():
nlp = stanza.Pipeline(lang='th', dir=TEST_MODELS_DIR, processors={'tokenize': 'pythainlp'}, tokenize_no_ssplit=True, package=None)
doc = nlp(TH_DOC)
assert "PyThaiNLPTokenizer" == nlp.processors['tokenize']._variant.__class__.__name__
assert TH_DOC_GOLD_NOSSPLIT_TOKENS == '\n\n'.join([sent.tokens_string() for sent in doc.sentences])
assert all([doc.text[token._start_char: token._end_char] == token.text for sent in doc.sentences for token in sent.tokens])
|
