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
|
from xml.etree import ElementTree as ET
from wn import lmf
def test_is_lmf(datadir):
assert lmf.is_lmf(datadir / "mini-lmf-1.0.xml")
assert lmf.is_lmf(str(datadir / "mini-lmf-1.0.xml"))
assert not lmf.is_lmf(datadir / "README.md")
assert not lmf.is_lmf(datadir / "missing.xml")
assert lmf.is_lmf(datadir / "mini-lmf-1.1.xml")
def test_scan_lexicons(datadir):
assert lmf.scan_lexicons(datadir / "mini-lmf-1.0.xml") == [
{
"id": "test-en",
"version": "1",
"label": "Testing English WordNet",
"extends": None,
},
{
"id": "test-es",
"version": "1",
"label": "Testing Spanish WordNet",
"extends": None,
},
]
assert lmf.scan_lexicons(datadir / "mini-lmf-1.1.xml") == [
{
"id": "test-ja",
"version": "1",
"label": "Testing Japanese WordNet",
"extends": None,
},
{
"id": "test-en-ext",
"version": "1",
"label": "Testing English Extension",
"extends": {
"id": "test-en",
"version": "1",
},
},
]
def test_load_1_0(datadir):
resource = lmf.load(datadir / "mini-lmf-1.0.xml")
lexicons = resource["lexicons"]
assert len(lexicons) == 2
lexicon = lexicons[0]
assert lexicon["id"] == "test-en"
assert lexicon["label"] == "Testing English WordNet"
assert lexicon["language"] == "en"
assert lexicon["email"] == "maintainer@example.com"
assert lexicon["license"] == "https://creativecommons.org/licenses/by/4.0/"
assert lexicon["version"] == "1"
assert lexicon["url"] == "https://example.com/test-en"
assert len(lexicon["entries"]) == 9
le = lexicon["entries"][0]
assert le["id"] == "test-en-information-n"
assert le["lemma"]["writtenForm"] == "information"
assert le["lemma"]["partOfSpeech"] == "n"
assert le["lemma"]["script"] == "Latn"
assert len(le["lemma"]["tags"]) == 1
assert len(le.get("forms", [])) == 0
assert len(le["senses"]) == 1
sense = le["senses"][0]
assert sense["id"] == "test-en-information-n-0001-01"
assert sense["synset"] == "test-en-0001-n"
assert len(sense.get("relations", [])) == 0
# assert sense["relations"][0]["target"] == "test-en-exemplify-v-01023137-01"
# assert sense["relations"][0]["type"] == "derivation"
assert len(lexicon.get("frames", [])) == 0 # frames are on lexical entry
assert len(lexicon["entries"][6]["frames"]) == 2
frames = lexicon["entries"][6]["frames"]
assert frames[0]["subcategorizationFrame"] == "Somebody ----s something"
assert frames[0]["senses"] == ["test-en-illustrate-v-0003-01"]
assert len(lexicon["synsets"]) == 8
assert lexicons[1]["id"] == "test-es"
def test_load_1_1(datadir):
resource = lmf.load(datadir / "mini-lmf-1.1.xml")
lexicons = resource["lexicons"]
assert len(lexicons) == 2
lexicon = lexicons[0]
assert lexicon["id"] == "test-ja"
assert lexicon["version"] == "1"
# assert lexicon.logo == "logo.svg"
assert lexicon.get("requires") == [{"id": "test-en", "version": "1"}]
lexicon = lexicons[1]
assert lexicon["id"] == "test-en-ext"
assert lexicon.get("extends") == {
"id": "test-en",
"url": "https://example.com/test-en",
"version": "1",
}
def test_load_1_3(datadir):
resource = lmf.load(datadir / "mini-lmf-1.3.xml")
lexicons = resource["lexicons"]
assert len(lexicons) == 1
lexicon = lexicons[0]
synsets = lexicon["synsets"]
assert synsets[0]["definitions"][0]["text"] == "one two three"
assert synsets[1]["definitions"][0]["text"] == "one two three"
assert (
synsets[2]["definitions"][0]["text"]
== """
one
two
three
"""
)
def test_load_1_4(datadir):
resource = lmf.load(datadir / "mini-lmf-1.4.xml")
lexicons = resource["lexicons"]
assert len(lexicons) == 2
lexicon = lexicons[0]
assert lexicon["entries"][0].get("index") == "foo_bar"
assert lexicon["entries"][1].get("index") == "foo_bar"
assert lexicon["entries"][2].get("index") is None
assert lexicon["entries"][3].get("index") == "baz"
assert lexicon["entries"][4].get("index") is None
assert lexicon["entries"][5].get("index") == "baz"
assert lexicon["entries"][0]["senses"][0].get("n") == 3
assert lexicon["entries"][1]["senses"][0].get("n") == 2
assert lexicon["entries"][1]["senses"][1].get("n") == 1
assert lexicon["entries"][2]["senses"][0].get("n") is None
assert lexicon["entries"][3]["senses"][0].get("n") == 2
assert lexicon["entries"][4]["senses"][0].get("n") == 2
assert lexicon["entries"][4]["senses"][1].get("n") is None
assert lexicon["entries"][5]["senses"][0].get("n") == 1
extension = lexicons[1]
assert extension["id"] == "test-ext-1.4"
assert extension.get("extends") == {
"id": "test-en",
"version": "1",
"url": "https://example.com/test-en",
}
def test_dump(datadir, tmp_path):
tmpdir = tmp_path / "test_dump"
tmpdir.mkdir()
tmppath = tmpdir / "mini_lmf_dump.xml"
def assert_xml_equal(mini_lmf, dump_lmf):
orig = ET.canonicalize(from_file=mini_lmf, strip_text=True)
temp = ET.canonicalize(from_file=dump_lmf, strip_text=True)
# additional transformation to help with debugging
orig = orig.replace("<", "\n<")
temp = temp.replace("<", "\n<")
assert orig == temp
lmf.dump(lmf.load(datadir / "mini-lmf-1.0.xml"), tmppath)
assert_xml_equal(datadir / "mini-lmf-1.0.xml", tmppath)
lmf.dump(lmf.load(datadir / "mini-lmf-1.1.xml"), tmppath)
assert_xml_equal(datadir / "mini-lmf-1.1.xml", tmppath)
lmf.dump(lmf.load(datadir / "mini-lmf-1.4.xml"), tmppath)
assert_xml_equal(datadir / "mini-lmf-1.4.xml", tmppath)
|
