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
|
import tempfile
import warnings
from pathlib import Path
import pytest
import wn
@pytest.mark.usefixtures('mini_db_1_1')
def test_wordnet_lexicons():
en = wn.Wordnet('test-en')
assert len(en.lexicons()) == 1
assert len(en.expanded_lexicons()) == 0
en1 = wn.Wordnet('test-en:1')
assert en.lexicons() == en1.lexicons()
assert en.expanded_lexicons() == en1.expanded_lexicons()
en2 = wn.Wordnet(lang='en')
assert len(en2.lexicons()) == 2
assert len(en2.expanded_lexicons()) == 0
es = wn.Wordnet('test-es')
assert len(es.lexicons()) == 1
assert len(es.expanded_lexicons()) == 0
es2 = wn.Wordnet('test-es', expand='test-en')
assert len(es2.lexicons()) == 1
assert len(es2.expanded_lexicons()) == 1
ja = wn.Wordnet('test-ja')
assert len(ja.lexicons()) == 1
assert len(ja.expanded_lexicons()) == 1
ja2 = wn.Wordnet('test-ja', expand='')
assert len(ja2.lexicons()) == 1
assert len(ja2.expanded_lexicons()) == 0
@pytest.mark.usefixtures('mini_db')
def test_wordnet_normalize():
es = wn.Wordnet('test-es')
assert es.words('Informacion') == es.words('información')
assert es.words('ínfórmácíón') == es.words('información')
es = wn.Wordnet('test-es', normalizer=None)
assert es.words('informacion') == []
assert es.words('Información') == []
# The following doesn't necessarily work because any non-None
# normalizer causes the normalized form column to be tested with
# the original form
# es = wn.Wordnet('test-es', normalizer=str.lower)
# assert es.words('informacion') == []
# assert es.words('Información') == es.words('información')
@pytest.mark.usefixtures('mini_db')
def test_wordnet_lemmatize():
# default lemmatizer compares alternative forms
en = wn.Wordnet('test-en')
assert en.words('examples') == []
assert en.words('exemplifying') == en.words('exemplify')
assert en.words('data') == en.words('datum')
en = wn.Wordnet('test-en', search_all_forms=False)
assert en.words('examples') == []
assert en.words('exemplifying') == []
assert en.words('data') == []
def morphy_lite(form, pos):
result = {pos: {form}}
if pos in ('n', None) and form.endswith('s'):
result.setdefault('n', set()).add(form[:-1])
return result
en = wn.Wordnet('test-en', lemmatizer=morphy_lite, search_all_forms=False)
assert en.words('examples', pos='n') == en.words('example')
assert en.words('examples') == en.words('example')
assert en.words('exemplifying') == []
assert en.words('data') == []
en = wn.Wordnet('test-en', lemmatizer=morphy_lite, search_all_forms=True)
assert en.words('data') == en.words('datum')
assert en.words('exemplifying') == en.words('exemplify')
def test_portable_entities_issue_226(monkeypatch, datadir):
# instead use ignore_cleanup_errors=True from Python 3.10
tempdir = tempfile.TemporaryDirectory('wn_issue_226')
with tempdir as dir:
with monkeypatch.context() as m:
m.setattr(wn.config, 'data_directory', Path(dir))
wn.add(datadir / 'mini-lmf-1.0.xml')
en = wn.Wordnet('test-en')
info1 = en.synsets('information')[0]
wn.remove('test-en')
wn.add(datadir / 'mini-lmf-1.0.xml')
info2 = en.synsets('information')[0] # en Wordnet object still works
assert info1 == info2 # synsets are equivalent
wn._db.clear_connections()
# Not needed if ignore_cleanup_errors=True and delete=True above
try:
tempdir.cleanup()
except PermissionError:
warnings.warn(
f"Failed to clean up temporary directory {dir!s}",
stacklevel=1,
)
|
