forked from explosion/spaCy
-
Notifications
You must be signed in to change notification settings - Fork 0
/
test_cli.py
1352 lines (1191 loc) · 48.6 KB
/
test_cli.py
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
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
import math
import os
import time
from collections import Counter
from pathlib import Path
from typing import Any, Dict, List, Tuple
import numpy
import pytest
import srsly
from click import NoSuchOption
from packaging.specifiers import SpecifierSet
from thinc.api import Config, ConfigValidationError
import spacy
from spacy import about
from spacy.cli import info
from spacy.cli._util import (
download_file,
is_subpath_of,
load_project_config,
parse_config_overrides,
string_to_list,
substitute_project_variables,
upload_file,
validate_project_commands,
walk_directory,
)
from spacy.cli.apply import apply
from spacy.cli.debug_data import (
_compile_gold,
_get_distribution,
_get_kl_divergence,
_get_labels_from_model,
_get_labels_from_spancat,
_get_span_characteristics,
_get_spans_length_freq_dist,
_print_span_characteristics,
)
from spacy.cli.download import get_compatibility, get_version
from spacy.cli.evaluate import render_parses
from spacy.cli.find_threshold import find_threshold
from spacy.cli.init_config import RECOMMENDATIONS, fill_config, init_config
from spacy.cli.init_pipeline import _init_labels
from spacy.cli.package import _is_permitted_package_name, get_third_party_dependencies
from spacy.cli.project.remote_storage import RemoteStorage
from spacy.cli.project.run import _check_requirements
from spacy.cli.validate import get_model_pkgs
from spacy.lang.en import English
from spacy.lang.nl import Dutch
from spacy.language import Language
from spacy.schemas import ProjectConfigSchema, RecommendationSchema, validate
from spacy.tokens import Doc, DocBin
from spacy.tokens.span import Span
from spacy.training import Example, docs_to_json, offsets_to_biluo_tags
from spacy.training.converters import conll_ner_to_docs, conllu_to_docs, iob_to_docs
from spacy.util import ENV_VARS, get_minor_version, load_config, load_model_from_config
from .util import make_tempdir
@pytest.mark.issue(4665)
def test_cli_converters_conllu_empty_heads_ner():
"""
conllu_to_docs should not raise an exception if the HEAD column contains an
underscore
"""
input_data = """
1 [ _ PUNCT -LRB- _ _ punct _ _
2 This _ DET DT _ _ det _ _
3 killing _ NOUN NN _ _ nsubj _ _
4 of _ ADP IN _ _ case _ _
5 a _ DET DT _ _ det _ _
6 respected _ ADJ JJ _ _ amod _ _
7 cleric _ NOUN NN _ _ nmod _ _
8 will _ AUX MD _ _ aux _ _
9 be _ AUX VB _ _ aux _ _
10 causing _ VERB VBG _ _ root _ _
11 us _ PRON PRP _ _ iobj _ _
12 trouble _ NOUN NN _ _ dobj _ _
13 for _ ADP IN _ _ case _ _
14 years _ NOUN NNS _ _ nmod _ _
15 to _ PART TO _ _ mark _ _
16 come _ VERB VB _ _ acl _ _
17 . _ PUNCT . _ _ punct _ _
18 ] _ PUNCT -RRB- _ _ punct _ _
"""
docs = list(conllu_to_docs(input_data))
# heads are all 0
assert not all([t.head.i for t in docs[0]])
# NER is unset
assert not docs[0].has_annotation("ENT_IOB")
@pytest.mark.issue(4924)
def test_issue4924():
nlp = Language()
example = Example.from_dict(nlp.make_doc(""), {})
nlp.evaluate([example])
@pytest.mark.issue(7055)
def test_issue7055():
"""Test that fill-config doesn't turn sourced components into factories."""
source_cfg = {
"nlp": {"lang": "en", "pipeline": ["tok2vec", "tagger"]},
"components": {
"tok2vec": {"factory": "tok2vec"},
"tagger": {"factory": "tagger"},
},
}
source_nlp = English.from_config(source_cfg)
with make_tempdir() as dir_path:
# We need to create a loadable source pipeline
source_path = dir_path / "test_model"
source_nlp.to_disk(source_path)
base_cfg = {
"nlp": {"lang": "en", "pipeline": ["tok2vec", "tagger", "ner"]},
"components": {
"tok2vec": {"source": str(source_path)},
"tagger": {"source": str(source_path)},
"ner": {"factory": "ner"},
},
}
base_cfg = Config(base_cfg)
base_path = dir_path / "base.cfg"
base_cfg.to_disk(base_path)
output_path = dir_path / "config.cfg"
fill_config(output_path, base_path, silent=True)
filled_cfg = load_config(output_path)
assert filled_cfg["components"]["tok2vec"]["source"] == str(source_path)
assert filled_cfg["components"]["tagger"]["source"] == str(source_path)
assert filled_cfg["components"]["ner"]["factory"] == "ner"
assert "model" in filled_cfg["components"]["ner"]
@pytest.mark.issue(11235)
def test_issue11235():
"""
Test that the cli handles interpolation in the directory names correctly when loading project config.
"""
lang_var = "en"
variables = {"lang": lang_var}
commands = [{"name": "x", "script": ["hello ${vars.lang}"]}]
directories = ["cfg", "${vars.lang}_model"]
project = {"commands": commands, "vars": variables, "directories": directories}
with make_tempdir() as d:
srsly.write_yaml(d / "project.yml", project)
cfg = load_project_config(d)
# Check that the directories are interpolated and created correctly
assert os.path.exists(d / "cfg")
assert os.path.exists(d / f"{lang_var}_model")
assert cfg["commands"][0]["script"][0] == f"hello {lang_var}"
@pytest.mark.issue(12566)
@pytest.mark.parametrize(
"factory,output_file",
[("deps", "parses.html"), ("ents", "entities.html"), ("spans", "spans.html")],
)
def test_issue12566(factory: str, output_file: str):
"""
Test if all displaCy types (ents, dep, spans) produce an HTML file
"""
with make_tempdir() as tmp_dir:
# Create sample spaCy file
doc_json = {
"ents": [
{"end": 54, "label": "nam_adj_country", "start": 44},
{"end": 83, "label": "nam_liv_person", "start": 69},
{"end": 100, "label": "nam_pro_title_book", "start": 86},
],
"spans": {
"sc": [
{"end": 54, "kb_id": "", "label": "nam_adj_country", "start": 44},
{"end": 83, "kb_id": "", "label": "nam_liv_person", "start": 69},
{
"end": 100,
"kb_id": "",
"label": "nam_pro_title_book",
"start": 86,
},
]
},
"text": "Niedawno czytał em nową książkę znakomitego szkockiego medioznawcy , "
"Briana McNaira - Cultural Chaos .",
"tokens": [
# fmt: off
{"id": 0, "start": 0, "end": 8, "tag": "ADV", "pos": "ADV", "morph": "Degree=Pos", "lemma": "niedawno", "dep": "advmod", "head": 1, },
{"id": 1, "start": 9, "end": 15, "tag": "PRAET", "pos": "VERB", "morph": "Animacy=Hum|Aspect=Imp|Gender=Masc|Mood=Ind|Number=Sing|Tense=Past|VerbForm=Fin|Voice=Act", "lemma": "czytać", "dep": "ROOT", "head": 1, },
{"id": 2, "start": 16, "end": 18, "tag": "AGLT", "pos": "NOUN", "morph": "Animacy=Inan|Case=Ins|Gender=Masc|Number=Sing", "lemma": "em", "dep": "iobj", "head": 1, },
{"id": 3, "start": 19, "end": 23, "tag": "ADJ", "pos": "ADJ", "morph": "Case=Acc|Degree=Pos|Gender=Fem|Number=Sing", "lemma": "nowy", "dep": "amod", "head": 4, },
{"id": 4, "start": 24, "end": 31, "tag": "SUBST", "pos": "NOUN", "morph": "Case=Acc|Gender=Fem|Number=Sing", "lemma": "książka", "dep": "obj", "head": 1, },
{"id": 5, "start": 32, "end": 43, "tag": "ADJ", "pos": "ADJ", "morph": "Animacy=Nhum|Case=Gen|Degree=Pos|Gender=Masc|Number=Sing", "lemma": "znakomit", "dep": "acl", "head": 4, },
{"id": 6, "start": 44, "end": 54, "tag": "ADJ", "pos": "ADJ", "morph": "Animacy=Hum|Case=Gen|Degree=Pos|Gender=Masc|Number=Sing", "lemma": "szkockiy", "dep": "amod", "head": 7, },
{"id": 7, "start": 55, "end": 66, "tag": "SUBST", "pos": "NOUN", "morph": "Animacy=Hum|Case=Gen|Gender=Masc|Number=Sing", "lemma": "medioznawca", "dep": "iobj", "head": 5, },
{"id": 8, "start": 67, "end": 68, "tag": "INTERP", "pos": "PUNCT", "morph": "PunctType=Comm", "lemma": ",", "dep": "punct", "head": 9, },
{"id": 9, "start": 69, "end": 75, "tag": "SUBST", "pos": "PROPN", "morph": "Animacy=Hum|Case=Gen|Gender=Masc|Number=Sing", "lemma": "Brian", "dep": "nmod", "head": 4, },
{"id": 10, "start": 76, "end": 83, "tag": "SUBST", "pos": "PROPN", "morph": "Animacy=Hum|Case=Gen|Gender=Masc|Number=Sing", "lemma": "McNair", "dep": "flat", "head": 9, },
{"id": 11, "start": 84, "end": 85, "tag": "INTERP", "pos": "PUNCT", "morph": "PunctType=Dash", "lemma": "-", "dep": "punct", "head": 12, },
{"id": 12, "start": 86, "end": 94, "tag": "SUBST", "pos": "PROPN", "morph": "Animacy=Inan|Case=Nom|Gender=Masc|Number=Sing", "lemma": "Cultural", "dep": "conj", "head": 4, },
{"id": 13, "start": 95, "end": 100, "tag": "SUBST", "pos": "NOUN", "morph": "Animacy=Inan|Case=Nom|Gender=Masc|Number=Sing", "lemma": "Chaos", "dep": "flat", "head": 12, },
{"id": 14, "start": 101, "end": 102, "tag": "INTERP", "pos": "PUNCT", "morph": "PunctType=Peri", "lemma": ".", "dep": "punct", "head": 1, },
# fmt: on
],
}
# Create a .spacy file
nlp = spacy.blank("pl")
doc = Doc(nlp.vocab).from_json(doc_json)
# Run the evaluate command and check if the html files exist
render_parses(
docs=[doc], output_path=tmp_dir, model_name="", limit=1, **{factory: True}
)
assert (tmp_dir / output_file).is_file()
def test_cli_info():
nlp = Dutch()
nlp.add_pipe("textcat")
with make_tempdir() as tmp_dir:
nlp.to_disk(tmp_dir)
raw_data = info(tmp_dir, exclude=[""])
assert raw_data["lang"] == "nl"
assert raw_data["components"] == ["textcat"]
def test_cli_converters_conllu_to_docs():
# from NorNE: https://github.com/ltgoslo/norne/blob/3d23274965f513f23aa48455b28b1878dad23c05/ud/nob/no_bokmaal-ud-dev.conllu
lines = [
"1\tDommer\tdommer\tNOUN\t_\tDefinite=Ind|Gender=Masc|Number=Sing\t2\tappos\t_\tO",
"2\tFinn\tFinn\tPROPN\t_\tGender=Masc\t4\tnsubj\t_\tB-PER",
"3\tEilertsen\tEilertsen\tPROPN\t_\t_\t2\tname\t_\tI-PER",
"4\tavstår\tavstå\tVERB\t_\tMood=Ind|Tense=Pres|VerbForm=Fin\t0\troot\t_\tO",
]
input_data = "\n".join(lines)
converted_docs = list(conllu_to_docs(input_data, n_sents=1))
assert len(converted_docs) == 1
converted = [docs_to_json(converted_docs)]
assert converted[0]["id"] == 0
assert len(converted[0]["paragraphs"]) == 1
assert len(converted[0]["paragraphs"][0]["sentences"]) == 1
sent = converted[0]["paragraphs"][0]["sentences"][0]
assert len(sent["tokens"]) == 4
tokens = sent["tokens"]
assert [t["orth"] for t in tokens] == ["Dommer", "Finn", "Eilertsen", "avstår"]
assert [t["tag"] for t in tokens] == ["NOUN", "PROPN", "PROPN", "VERB"]
assert [t["head"] for t in tokens] == [1, 2, -1, 0]
assert [t["dep"] for t in tokens] == ["appos", "nsubj", "name", "ROOT"]
ent_offsets = [
(e[0], e[1], e[2]) for e in converted[0]["paragraphs"][0]["entities"]
]
biluo_tags = offsets_to_biluo_tags(converted_docs[0], ent_offsets, missing="O")
assert biluo_tags == ["O", "B-PER", "L-PER", "O"]
@pytest.mark.parametrize(
"lines",
[
(
"1\tDommer\tdommer\tNOUN\t_\tDefinite=Ind|Gender=Masc|Number=Sing\t2\tappos\t_\tname=O",
"2\tFinn\tFinn\tPROPN\t_\tGender=Masc\t4\tnsubj\t_\tSpaceAfter=No|name=B-PER",
"3\tEilertsen\tEilertsen\tPROPN\t_\t_\t2\tname\t_\tname=I-PER",
"4\tavstår\tavstå\tVERB\t_\tMood=Ind|Tense=Pres|VerbForm=Fin\t0\troot\t_\tSpaceAfter=No|name=O",
"5\t.\t$.\tPUNCT\t_\t_\t4\tpunct\t_\tname=B-BAD",
),
(
"1\tDommer\tdommer\tNOUN\t_\tDefinite=Ind|Gender=Masc|Number=Sing\t2\tappos\t_\t_",
"2\tFinn\tFinn\tPROPN\t_\tGender=Masc\t4\tnsubj\t_\tSpaceAfter=No|NE=B-PER",
"3\tEilertsen\tEilertsen\tPROPN\t_\t_\t2\tname\t_\tNE=L-PER",
"4\tavstår\tavstå\tVERB\t_\tMood=Ind|Tense=Pres|VerbForm=Fin\t0\troot\t_\tSpaceAfter=No",
"5\t.\t$.\tPUNCT\t_\t_\t4\tpunct\t_\tNE=B-BAD",
),
],
)
def test_cli_converters_conllu_to_docs_name_ner_map(lines):
input_data = "\n".join(lines)
converted_docs = list(
conllu_to_docs(input_data, n_sents=1, ner_map={"PER": "PERSON", "BAD": ""})
)
assert len(converted_docs) == 1
converted = [docs_to_json(converted_docs)]
assert converted[0]["id"] == 0
assert len(converted[0]["paragraphs"]) == 1
assert converted[0]["paragraphs"][0]["raw"] == "Dommer FinnEilertsen avstår. "
assert len(converted[0]["paragraphs"][0]["sentences"]) == 1
sent = converted[0]["paragraphs"][0]["sentences"][0]
assert len(sent["tokens"]) == 5
tokens = sent["tokens"]
assert [t["orth"] for t in tokens] == ["Dommer", "Finn", "Eilertsen", "avstår", "."]
assert [t["tag"] for t in tokens] == ["NOUN", "PROPN", "PROPN", "VERB", "PUNCT"]
assert [t["head"] for t in tokens] == [1, 2, -1, 0, -1]
assert [t["dep"] for t in tokens] == ["appos", "nsubj", "name", "ROOT", "punct"]
ent_offsets = [
(e[0], e[1], e[2]) for e in converted[0]["paragraphs"][0]["entities"]
]
biluo_tags = offsets_to_biluo_tags(converted_docs[0], ent_offsets, missing="O")
assert biluo_tags == ["O", "B-PERSON", "L-PERSON", "O", "O"]
def test_cli_converters_conllu_to_docs_subtokens():
# https://raw.githubusercontent.com/ohenrik/nb_news_ud_sm/master/original_data/no-ud-dev-ner.conllu
lines = [
"1\tDommer\tdommer\tNOUN\t_\tDefinite=Ind|Gender=Masc|Number=Sing\t2\tappos\t_\tname=O",
"2-3\tFE\t_\t_\t_\t_\t_\t_\t_\t_",
"2\tFinn\tFinn\tPROPN\t_\tGender=Masc\t4\tnsubj\t_\tname=B-PER",
"3\tEilertsen\tEilertsen\tX\t_\tGender=Fem|Tense=past\t2\tname\t_\tname=I-PER",
"4\tavstår\tavstå\tVERB\t_\tMood=Ind|Tense=Pres|VerbForm=Fin\t0\troot\t_\tSpaceAfter=No|name=O",
"5\t.\t$.\tPUNCT\t_\t_\t4\tpunct\t_\tname=O",
]
input_data = "\n".join(lines)
converted_docs = list(
conllu_to_docs(
input_data, n_sents=1, merge_subtokens=True, append_morphology=True
)
)
assert len(converted_docs) == 1
converted = [docs_to_json(converted_docs)]
assert converted[0]["id"] == 0
assert len(converted[0]["paragraphs"]) == 1
assert converted[0]["paragraphs"][0]["raw"] == "Dommer FE avstår. "
assert len(converted[0]["paragraphs"][0]["sentences"]) == 1
sent = converted[0]["paragraphs"][0]["sentences"][0]
assert len(sent["tokens"]) == 4
tokens = sent["tokens"]
assert [t["orth"] for t in tokens] == ["Dommer", "FE", "avstår", "."]
assert [t["tag"] for t in tokens] == [
"NOUN__Definite=Ind|Gender=Masc|Number=Sing",
"PROPN_X__Gender=Fem,Masc|Tense=past",
"VERB__Mood=Ind|Tense=Pres|VerbForm=Fin",
"PUNCT",
]
assert [t["pos"] for t in tokens] == ["NOUN", "PROPN", "VERB", "PUNCT"]
assert [t["morph"] for t in tokens] == [
"Definite=Ind|Gender=Masc|Number=Sing",
"Gender=Fem,Masc|Tense=past",
"Mood=Ind|Tense=Pres|VerbForm=Fin",
"",
]
assert [t["lemma"] for t in tokens] == ["dommer", "Finn Eilertsen", "avstå", "$."]
assert [t["head"] for t in tokens] == [1, 1, 0, -1]
assert [t["dep"] for t in tokens] == ["appos", "nsubj", "ROOT", "punct"]
ent_offsets = [
(e[0], e[1], e[2]) for e in converted[0]["paragraphs"][0]["entities"]
]
biluo_tags = offsets_to_biluo_tags(converted_docs[0], ent_offsets, missing="O")
assert biluo_tags == ["O", "U-PER", "O", "O"]
def test_cli_converters_iob_to_docs():
lines = [
"I|O like|O London|I-GPE and|O New|B-GPE York|I-GPE City|I-GPE .|O",
"I|O like|O London|B-GPE and|O New|B-GPE York|I-GPE City|I-GPE .|O",
"I|PRP|O like|VBP|O London|NNP|I-GPE and|CC|O New|NNP|B-GPE York|NNP|I-GPE City|NNP|I-GPE .|.|O",
"I|PRP|O like|VBP|O London|NNP|B-GPE and|CC|O New|NNP|B-GPE York|NNP|I-GPE City|NNP|I-GPE .|.|O",
]
input_data = "\n".join(lines)
converted_docs = list(iob_to_docs(input_data, n_sents=10))
assert len(converted_docs) == 1
converted = docs_to_json(converted_docs)
assert converted["id"] == 0
assert len(converted["paragraphs"]) == 1
assert len(converted["paragraphs"][0]["sentences"]) == 4
for i in range(0, 4):
sent = converted["paragraphs"][0]["sentences"][i]
assert len(sent["tokens"]) == 8
tokens = sent["tokens"]
expected = ["I", "like", "London", "and", "New", "York", "City", "."]
assert [t["orth"] for t in tokens] == expected
assert len(converted_docs[0].ents) == 8
for ent in converted_docs[0].ents:
assert ent.text in ["New York City", "London"]
def test_cli_converters_conll_ner_to_docs():
lines = [
"-DOCSTART- -X- O O",
"",
"I\tO",
"like\tO",
"London\tB-GPE",
"and\tO",
"New\tB-GPE",
"York\tI-GPE",
"City\tI-GPE",
".\tO",
"",
"I O",
"like O",
"London B-GPE",
"and O",
"New B-GPE",
"York I-GPE",
"City I-GPE",
". O",
"",
"I PRP O",
"like VBP O",
"London NNP B-GPE",
"and CC O",
"New NNP B-GPE",
"York NNP I-GPE",
"City NNP I-GPE",
". . O",
"",
"I PRP _ O",
"like VBP _ O",
"London NNP _ B-GPE",
"and CC _ O",
"New NNP _ B-GPE",
"York NNP _ I-GPE",
"City NNP _ I-GPE",
". . _ O",
"",
"I\tPRP\t_\tO",
"like\tVBP\t_\tO",
"London\tNNP\t_\tB-GPE",
"and\tCC\t_\tO",
"New\tNNP\t_\tB-GPE",
"York\tNNP\t_\tI-GPE",
"City\tNNP\t_\tI-GPE",
".\t.\t_\tO",
]
input_data = "\n".join(lines)
converted_docs = list(conll_ner_to_docs(input_data, n_sents=10))
assert len(converted_docs) == 1
converted = docs_to_json(converted_docs)
assert converted["id"] == 0
assert len(converted["paragraphs"]) == 1
assert len(converted["paragraphs"][0]["sentences"]) == 5
for i in range(0, 5):
sent = converted["paragraphs"][0]["sentences"][i]
assert len(sent["tokens"]) == 8
tokens = sent["tokens"]
# fmt: off
assert [t["orth"] for t in tokens] == ["I", "like", "London", "and", "New", "York", "City", "."]
# fmt: on
assert len(converted_docs[0].ents) == 10
for ent in converted_docs[0].ents:
assert ent.text in ["New York City", "London"]
def test_project_config_validation_full():
config = {
"vars": {"some_var": 20},
"directories": ["assets", "configs", "corpus", "scripts", "training"],
"assets": [
{
"dest": "x",
"extra": True,
"url": "https://example.com",
"checksum": "63373dd656daa1fd3043ce166a59474c",
},
{
"dest": "y",
"git": {
"repo": "https://github.com/example/repo",
"branch": "develop",
"path": "y",
},
},
{
"dest": "z",
"extra": False,
"url": "https://example.com",
"checksum": "63373dd656daa1fd3043ce166a59474c",
},
],
"commands": [
{
"name": "train",
"help": "Train a model",
"script": ["python -m spacy train config.cfg -o training"],
"deps": ["config.cfg", "corpus/training.spcy"],
"outputs": ["training/model-best"],
},
{"name": "test", "script": ["pytest", "custom.py"], "no_skip": True},
],
"workflows": {"all": ["train", "test"], "train": ["train"]},
}
errors = validate(ProjectConfigSchema, config)
assert not errors
@pytest.mark.parametrize(
"config",
[
{"commands": [{"name": "a"}, {"name": "a"}]},
{"commands": [{"name": "a"}], "workflows": {"a": []}},
{"commands": [{"name": "a"}], "workflows": {"b": ["c"]}},
],
)
def test_project_config_validation1(config):
with pytest.raises(SystemExit):
validate_project_commands(config)
@pytest.mark.parametrize(
"config,n_errors",
[
({"commands": {"a": []}}, 1),
({"commands": [{"help": "..."}]}, 1),
({"commands": [{"name": "a", "extra": "b"}]}, 1),
({"commands": [{"extra": "b"}]}, 2),
({"commands": [{"name": "a", "deps": [123]}]}, 1),
],
)
def test_project_config_validation2(config, n_errors):
errors = validate(ProjectConfigSchema, config)
assert len(errors) == n_errors
@pytest.mark.parametrize(
"int_value",
[10, pytest.param("10", marks=pytest.mark.xfail)],
)
def test_project_config_interpolation(int_value):
variables = {"a": int_value, "b": {"c": "foo", "d": True}}
commands = [
{"name": "x", "script": ["hello ${vars.a} ${vars.b.c}"]},
{"name": "y", "script": ["${vars.b.c} ${vars.b.d}"]},
]
project = {"commands": commands, "vars": variables}
with make_tempdir() as d:
srsly.write_yaml(d / "project.yml", project)
cfg = load_project_config(d)
assert type(cfg) == dict
assert type(cfg["commands"]) == list
assert cfg["commands"][0]["script"][0] == "hello 10 foo"
assert cfg["commands"][1]["script"][0] == "foo true"
commands = [{"name": "x", "script": ["hello ${vars.a} ${vars.b.e}"]}]
project = {"commands": commands, "vars": variables}
with pytest.raises(ConfigValidationError):
substitute_project_variables(project)
@pytest.mark.parametrize(
"greeting",
[342, "everyone", "tout le monde", pytest.param("42", marks=pytest.mark.xfail)],
)
def test_project_config_interpolation_override(greeting):
variables = {"a": "world"}
commands = [
{"name": "x", "script": ["hello ${vars.a}"]},
]
overrides = {"vars.a": greeting}
project = {"commands": commands, "vars": variables}
with make_tempdir() as d:
srsly.write_yaml(d / "project.yml", project)
cfg = load_project_config(d, overrides=overrides)
assert type(cfg) == dict
assert type(cfg["commands"]) == list
assert cfg["commands"][0]["script"][0] == f"hello {greeting}"
def test_project_config_interpolation_env():
variables = {"a": 10}
env_var = "SPACY_TEST_FOO"
env_vars = {"foo": env_var}
commands = [{"name": "x", "script": ["hello ${vars.a} ${env.foo}"]}]
project = {"commands": commands, "vars": variables, "env": env_vars}
with make_tempdir() as d:
srsly.write_yaml(d / "project.yml", project)
cfg = load_project_config(d)
assert cfg["commands"][0]["script"][0] == "hello 10 "
os.environ[env_var] = "123"
with make_tempdir() as d:
srsly.write_yaml(d / "project.yml", project)
cfg = load_project_config(d)
assert cfg["commands"][0]["script"][0] == "hello 10 123"
@pytest.mark.parametrize(
"args,expected",
[
# fmt: off
(["--x.foo", "10"], {"x.foo": 10}),
(["--x.foo=10"], {"x.foo": 10}),
(["--x.foo", "bar"], {"x.foo": "bar"}),
(["--x.foo=bar"], {"x.foo": "bar"}),
(["--x.foo", "--x.bar", "baz"], {"x.foo": True, "x.bar": "baz"}),
(["--x.foo", "--x.bar=baz"], {"x.foo": True, "x.bar": "baz"}),
(["--x.foo", "10.1", "--x.bar", "--x.baz", "false"], {"x.foo": 10.1, "x.bar": True, "x.baz": False}),
(["--x.foo", "10.1", "--x.bar", "--x.baz=false"], {"x.foo": 10.1, "x.bar": True, "x.baz": False})
# fmt: on
],
)
def test_parse_config_overrides(args, expected):
assert parse_config_overrides(args) == expected
@pytest.mark.parametrize("args", [["--foo"], ["--x.foo", "bar", "--baz"]])
def test_parse_config_overrides_invalid(args):
with pytest.raises(NoSuchOption):
parse_config_overrides(args)
@pytest.mark.parametrize("args", [["--x.foo", "bar", "baz"], ["x.foo"]])
def test_parse_config_overrides_invalid_2(args):
with pytest.raises(SystemExit):
parse_config_overrides(args)
def test_parse_cli_overrides():
overrides = "--x.foo bar --x.bar=12 --x.baz false --y.foo=hello"
os.environ[ENV_VARS.CONFIG_OVERRIDES] = overrides
result = parse_config_overrides([])
assert len(result) == 4
assert result["x.foo"] == "bar"
assert result["x.bar"] == 12
assert result["x.baz"] is False
assert result["y.foo"] == "hello"
os.environ[ENV_VARS.CONFIG_OVERRIDES] = "--x"
assert parse_config_overrides([], env_var=None) == {}
with pytest.raises(SystemExit):
parse_config_overrides([])
os.environ[ENV_VARS.CONFIG_OVERRIDES] = "hello world"
with pytest.raises(SystemExit):
parse_config_overrides([])
del os.environ[ENV_VARS.CONFIG_OVERRIDES]
@pytest.mark.parametrize("lang", ["en", "nl"])
@pytest.mark.parametrize(
"pipeline",
[
["tagger", "parser", "ner"],
[],
["ner", "textcat", "sentencizer"],
["morphologizer", "spancat", "entity_linker"],
["spancat_singlelabel", "textcat_multilabel"],
],
)
@pytest.mark.parametrize("optimize", ["efficiency", "accuracy"])
@pytest.mark.parametrize("pretraining", [True, False])
def test_init_config(lang, pipeline, optimize, pretraining):
# TODO: add more tests and also check for GPU with transformers
config = init_config(
lang=lang,
pipeline=pipeline,
optimize=optimize,
pretraining=pretraining,
gpu=False,
)
assert isinstance(config, Config)
if pretraining:
config["paths"]["raw_text"] = "my_data.jsonl"
load_model_from_config(config, auto_fill=True)
def test_model_recommendations():
for lang, data in RECOMMENDATIONS.items():
assert RecommendationSchema(**data)
@pytest.mark.parametrize(
"value",
[
# fmt: off
"parser,textcat,tagger",
" parser, textcat ,tagger ",
'parser,textcat,tagger',
' parser, textcat ,tagger ',
' "parser"," textcat " ,"tagger "',
" 'parser',' textcat ' ,'tagger '",
'[parser,textcat,tagger]',
'["parser","textcat","tagger"]',
'[" parser" ,"textcat ", " tagger " ]',
"[parser,textcat,tagger]",
"[ parser, textcat , tagger]",
"['parser','textcat','tagger']",
"[' parser' , 'textcat', ' tagger ' ]",
# fmt: on
],
)
def test_string_to_list(value):
assert string_to_list(value, intify=False) == ["parser", "textcat", "tagger"]
@pytest.mark.parametrize(
"value",
[
# fmt: off
"1,2,3",
'[1,2,3]',
'["1","2","3"]',
'[" 1" ,"2 ", " 3 " ]',
"[' 1' , '2', ' 3 ' ]",
# fmt: on
],
)
def test_string_to_list_intify(value):
assert string_to_list(value, intify=False) == ["1", "2", "3"]
assert string_to_list(value, intify=True) == [1, 2, 3]
def test_download_compatibility():
spec = SpecifierSet("==" + about.__version__)
spec.prereleases = False
if about.__version__ in spec:
model_name = "en_core_web_sm"
compatibility = get_compatibility()
version = get_version(model_name, compatibility)
assert get_minor_version(about.__version__) == get_minor_version(version)
def test_validate_compatibility_table():
spec = SpecifierSet("==" + about.__version__)
spec.prereleases = False
if about.__version__ in spec:
model_pkgs, compat = get_model_pkgs()
spacy_version = get_minor_version(about.__version__)
current_compat = compat.get(spacy_version, {})
assert len(current_compat) > 0
assert "en_core_web_sm" in current_compat
@pytest.mark.parametrize("component_name", ["ner", "textcat", "spancat", "tagger"])
def test_init_labels(component_name):
nlp = Dutch()
component = nlp.add_pipe(component_name)
for label in ["T1", "T2", "T3", "T4"]:
component.add_label(label)
assert len(nlp.get_pipe(component_name).labels) == 4
with make_tempdir() as tmp_dir:
_init_labels(nlp, tmp_dir)
config = init_config(
lang="nl",
pipeline=[component_name],
optimize="efficiency",
gpu=False,
)
config["initialize"]["components"][component_name] = {
"labels": {
"@readers": "spacy.read_labels.v1",
"path": f"{tmp_dir}/{component_name}.json",
}
}
nlp2 = load_model_from_config(config, auto_fill=True)
assert len(nlp2.get_pipe(component_name).labels) == 0
nlp2.initialize()
assert len(nlp2.get_pipe(component_name).labels) == 4
def test_get_third_party_dependencies():
# We can't easily test the detection of third-party packages here, but we
# can at least make sure that the function and its importlib magic runs.
nlp = Dutch()
# Test with component factory based on Cython module
nlp.add_pipe("tagger")
assert get_third_party_dependencies(nlp.config) == []
# Test with legacy function
nlp = Dutch()
nlp.add_pipe(
"textcat",
config={
"model": {
# Do not update from legacy architecture spacy.TextCatBOW.v1
"@architectures": "spacy.TextCatBOW.v1",
"exclusive_classes": True,
"ngram_size": 1,
"no_output_layer": False,
}
},
)
assert get_third_party_dependencies(nlp.config) == []
# Test with lang-specific factory
@Dutch.factory("third_party_test")
def test_factory(nlp, name):
return lambda x: x
nlp.add_pipe("third_party_test")
# Before #9674 this would throw an exception
get_third_party_dependencies(nlp.config)
@pytest.mark.parametrize(
"parent,child,expected",
[
("/tmp", "/tmp", True),
("/tmp", "/", False),
("/tmp", "/tmp/subdir", True),
("/tmp", "/tmpdir", False),
("/tmp", "/tmp/subdir/..", True),
("/tmp", "/tmp/..", False),
],
)
def test_is_subpath_of(parent, child, expected):
assert is_subpath_of(parent, child) == expected
@pytest.mark.slow
@pytest.mark.parametrize(
"factory_name,pipe_name",
[
("ner", "ner"),
("ner", "my_ner"),
("spancat", "spancat"),
("spancat", "my_spancat"),
],
)
def test_get_labels_from_model(factory_name, pipe_name):
labels = ("A", "B")
nlp = English()
pipe = nlp.add_pipe(factory_name, name=pipe_name)
for label in labels:
pipe.add_label(label)
nlp.initialize()
assert nlp.get_pipe(pipe_name).labels == labels
if factory_name == "spancat":
assert _get_labels_from_spancat(nlp)[pipe.key] == set(labels)
else:
assert _get_labels_from_model(nlp, factory_name) == set(labels)
def test_permitted_package_names():
# https://www.python.org/dev/peps/pep-0426/#name
assert _is_permitted_package_name("Meine_Bäume") == False
assert _is_permitted_package_name("_package") == False
assert _is_permitted_package_name("package_") == False
assert _is_permitted_package_name(".package") == False
assert _is_permitted_package_name("package.") == False
assert _is_permitted_package_name("-package") == False
assert _is_permitted_package_name("package-") == False
def test_debug_data_compile_gold():
nlp = English()
pred = Doc(nlp.vocab, words=["Token", ".", "New", "York", "City"])
ref = Doc(
nlp.vocab,
words=["Token", ".", "New York City"],
sent_starts=[True, False, True],
ents=["O", "O", "B-ENT"],
)
eg = Example(pred, ref)
data = _compile_gold([eg], ["ner"], nlp, True)
assert data["boundary_cross_ents"] == 0
pred = Doc(nlp.vocab, words=["Token", ".", "New", "York", "City"])
ref = Doc(
nlp.vocab,
words=["Token", ".", "New York City"],
sent_starts=[True, False, True],
ents=["O", "B-ENT", "I-ENT"],
)
eg = Example(pred, ref)
data = _compile_gold([eg], ["ner"], nlp, True)
assert data["boundary_cross_ents"] == 1
@pytest.mark.parametrize("component_name", ["spancat", "spancat_singlelabel"])
def test_debug_data_compile_gold_for_spans(component_name):
nlp = English()
spans_key = "sc"
pred = Doc(nlp.vocab, words=["Welcome", "to", "the", "Bank", "of", "China", "."])
pred.spans[spans_key] = [Span(pred, 3, 6, "ORG"), Span(pred, 5, 6, "GPE")]
ref = Doc(nlp.vocab, words=["Welcome", "to", "the", "Bank", "of", "China", "."])
ref.spans[spans_key] = [Span(ref, 3, 6, "ORG"), Span(ref, 5, 6, "GPE")]
eg = Example(pred, ref)
data = _compile_gold([eg], [component_name], nlp, True)
assert data["spancat"][spans_key] == Counter({"ORG": 1, "GPE": 1})
assert data["spans_length"][spans_key] == {"ORG": [3], "GPE": [1]}
assert data["spans_per_type"][spans_key] == {
"ORG": [Span(ref, 3, 6, "ORG")],
"GPE": [Span(ref, 5, 6, "GPE")],
}
assert data["sb_per_type"][spans_key] == {
"ORG": {"start": [ref[2:3]], "end": [ref[6:7]]},
"GPE": {"start": [ref[4:5]], "end": [ref[6:7]]},
}
def test_frequency_distribution_is_correct():
nlp = English()
docs = [
Doc(nlp.vocab, words=["Bank", "of", "China"]),
Doc(nlp.vocab, words=["China"]),
]
expected = Counter({"china": 0.5, "bank": 0.25, "of": 0.25})
freq_distribution = _get_distribution(docs, normalize=True)
assert freq_distribution == expected
def test_kl_divergence_computation_is_correct():
p = Counter({"a": 0.5, "b": 0.25})
q = Counter({"a": 0.25, "b": 0.50, "c": 0.15, "d": 0.10})
result = _get_kl_divergence(p, q)
expected = 0.1733
assert math.isclose(result, expected, rel_tol=1e-3)
def test_get_span_characteristics_return_value():
nlp = English()
spans_key = "sc"
pred = Doc(nlp.vocab, words=["Welcome", "to", "the", "Bank", "of", "China", "."])
pred.spans[spans_key] = [Span(pred, 3, 6, "ORG"), Span(pred, 5, 6, "GPE")]
ref = Doc(nlp.vocab, words=["Welcome", "to", "the", "Bank", "of", "China", "."])
ref.spans[spans_key] = [Span(ref, 3, 6, "ORG"), Span(ref, 5, 6, "GPE")]
eg = Example(pred, ref)
examples = [eg]
data = _compile_gold(examples, ["spancat"], nlp, True)
span_characteristics = _get_span_characteristics(
examples=examples, compiled_gold=data, spans_key=spans_key
)
assert {"sd", "bd", "lengths"}.issubset(span_characteristics.keys())
assert span_characteristics["min_length"] == 1
assert span_characteristics["max_length"] == 3
def test_ensure_print_span_characteristics_wont_fail():
"""Test if interface between two methods aren't destroyed if refactored"""
nlp = English()
spans_key = "sc"
pred = Doc(nlp.vocab, words=["Welcome", "to", "the", "Bank", "of", "China", "."])
pred.spans[spans_key] = [Span(pred, 3, 6, "ORG"), Span(pred, 5, 6, "GPE")]
ref = Doc(nlp.vocab, words=["Welcome", "to", "the", "Bank", "of", "China", "."])
ref.spans[spans_key] = [Span(ref, 3, 6, "ORG"), Span(ref, 5, 6, "GPE")]
eg = Example(pred, ref)
examples = [eg]
data = _compile_gold(examples, ["spancat"], nlp, True)
span_characteristics = _get_span_characteristics(
examples=examples, compiled_gold=data, spans_key=spans_key
)
_print_span_characteristics(span_characteristics)
@pytest.mark.parametrize("threshold", [70, 80, 85, 90, 95])
def test_span_length_freq_dist_threshold_must_be_correct(threshold):
sample_span_lengths = {
"span_type_1": [1, 4, 4, 5],
"span_type_2": [5, 3, 3, 2],
"span_type_3": [3, 1, 3, 3],
}
span_freqs = _get_spans_length_freq_dist(sample_span_lengths, threshold)
assert sum(span_freqs.values()) >= threshold
def test_span_length_freq_dist_output_must_be_correct():
sample_span_lengths = {
"span_type_1": [1, 4, 4, 5],
"span_type_2": [5, 3, 3, 2],
"span_type_3": [3, 1, 3, 3],
}
threshold = 90
span_freqs = _get_spans_length_freq_dist(sample_span_lengths, threshold)
assert sum(span_freqs.values()) >= threshold
assert list(span_freqs.keys()) == [3, 1, 4, 5, 2]
def test_applycli_empty_dir():
with make_tempdir() as data_path:
output = data_path / "test.spacy"
apply(data_path, output, "blank:en", "text", 1, 1)
def test_applycli_docbin():
with make_tempdir() as data_path:
output = data_path / "testout.spacy"
nlp = spacy.blank("en")
doc = nlp("testing apply cli.")
# test empty DocBin case
docbin = DocBin()
docbin.to_disk(data_path / "testin.spacy")
apply(data_path, output, "blank:en", "text", 1, 1)
docbin.add(doc)
docbin.to_disk(data_path / "testin.spacy")
apply(data_path, output, "blank:en", "text", 1, 1)
def test_applycli_jsonl():
with make_tempdir() as data_path:
output = data_path / "testout.spacy"
data = [{"field": "Testing apply cli.", "key": 234}]
data2 = [{"field": "234"}]
srsly.write_jsonl(data_path / "test.jsonl", data)
apply(data_path, output, "blank:en", "field", 1, 1)
srsly.write_jsonl(data_path / "test2.jsonl", data2)
apply(data_path, output, "blank:en", "field", 1, 1)
def test_applycli_txt():