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
|
"""
Test the semgrex interface
"""
import pytest
import stanza
import stanza.server.semgrex as semgrex
from stanza.protobuf import SemgrexRequest
from stanza.models.common.doc import Document
from tests import *
pytestmark = [pytest.mark.travis, pytest.mark.client]
TEST_ONE_SENTENCE = [[
{
"id": 1,
"text": "Unban",
"lemma": "unban",
"upos": "VERB",
"xpos": "VB",
"feats": "Mood=Imp|VerbForm=Fin",
"head": 0,
"deprel": "root",
"misc": "start_char=0|end_char=5"
},
{
"id": 2,
"text": "Mox",
"lemma": "Mox",
"upos": "PROPN",
"xpos": "NNP",
"feats": "Number=Sing",
"head": 3,
"deprel": "compound",
"misc": "start_char=6|end_char=9"
},
{
"id": 3,
"text": "Opal",
"lemma": "Opal",
"upos": "PROPN",
"xpos": "NNP",
"feats": "Number=Sing",
"head": 1,
"deprel": "obj",
"misc": "start_char=10|end_char=14",
"ner": "GEM"
},
{
"id": 4,
"text": "!",
"lemma": "!",
"upos": "PUNCT",
"xpos": ".",
"head": 1,
"deprel": "punct",
"misc": "start_char=14|end_char=15"
}]]
TEST_TWO_SENTENCES = [[
{
"id": 1,
"text": "Unban",
"lemma": "unban",
"upos": "VERB",
"xpos": "VB",
"feats": "Mood=Imp|VerbForm=Fin",
"head": 0,
"deprel": "root",
"misc": "start_char=0|end_char=5"
},
{
"id": 2,
"text": "Mox",
"lemma": "Mox",
"upos": "PROPN",
"xpos": "NNP",
"feats": "Number=Sing",
"head": 3,
"deprel": "compound",
"misc": "start_char=6|end_char=9"
},
{
"id": 3,
"text": "Opal",
"lemma": "Opal",
"upos": "PROPN",
"xpos": "NNP",
"feats": "Number=Sing",
"head": 1,
"deprel": "obj",
"misc": "start_char=10|end_char=14"
},
{
"id": 4,
"text": "!",
"lemma": "!",
"upos": "PUNCT",
"xpos": ".",
"head": 1,
"deprel": "punct",
"misc": "start_char=14|end_char=15"
}],
[{
"id": 1,
"text": "Unban",
"lemma": "unban",
"upos": "VERB",
"xpos": "VB",
"feats": "Mood=Imp|VerbForm=Fin",
"head": 0,
"deprel": "root",
"misc": "start_char=16|end_char=21"
},
{
"id": 2,
"text": "Mox",
"lemma": "Mox",
"upos": "PROPN",
"xpos": "NNP",
"feats": "Number=Sing",
"head": 3,
"deprel": "compound",
"misc": "start_char=22|end_char=25"
},
{
"id": 3,
"text": "Opal",
"lemma": "Opal",
"upos": "PROPN",
"xpos": "NNP",
"feats": "Number=Sing",
"head": 1,
"deprel": "obj",
"misc": "start_char=26|end_char=30"
},
{
"id": 4,
"text": "!",
"lemma": "!",
"upos": "PUNCT",
"xpos": ".",
"head": 1,
"deprel": "punct",
"misc": "start_char=30|end_char=31"
}]]
def check_response(response, response_len=1, semgrex_len=1, source_index=1, target_index=3, reln='obj'):
assert len(response.result) == response_len
assert len(response.result[0].result) == semgrex_len
for semgrex_result in response.result[0].result:
assert len(semgrex_result.match) == 1
assert semgrex_result.match[0].index == source_index
for match in semgrex_result.match:
assert len(match.node) == 2
assert match.node[0].name == 'source'
assert match.node[0].index == source_index
assert match.node[1].name == 'target'
assert match.node[1].index == target_index
assert len(match.reln) == 1
assert match.reln[0].name == 'zzz'
assert match.reln[0].reln == reln
def test_single_sentence():
doc = Document(TEST_ONE_SENTENCE)
response = semgrex.process_doc(doc, "{}=source >obj=zzz {}=target")
check_response(response)
def test_two_semgrex():
doc = Document(TEST_ONE_SENTENCE)
response = semgrex.process_doc(doc, "{}=source >obj=zzz {}=target", "{}=source >obj=zzz {}=target")
check_response(response, semgrex_len=2)
def test_two_sentences():
doc = Document(TEST_TWO_SENTENCES)
response = semgrex.process_doc(doc, "{}=source >obj=zzz {}=target")
check_response(response, response_len=2)
def test_word_attribute():
doc = Document(TEST_ONE_SENTENCE)
response = semgrex.process_doc(doc, "{word:Mox}=source <=zzz {word:Opal}=target")
check_response(response, response_len=1, source_index=2, reln='compound')
def test_lemma_attribute():
doc = Document(TEST_ONE_SENTENCE)
response = semgrex.process_doc(doc, "{lemma:Mox}=source <=zzz {lemma:Opal}=target")
check_response(response, response_len=1, source_index=2, reln='compound')
def test_xpos_attribute():
doc = Document(TEST_ONE_SENTENCE)
response = semgrex.process_doc(doc, "{tag:NNP}=source <=zzz {word:Opal}=target")
check_response(response, response_len=1, source_index=2, reln='compound')
response = semgrex.process_doc(doc, "{pos:NNP}=source <=zzz {word:Opal}=target")
check_response(response, response_len=1, source_index=2, reln='compound')
def test_upos_attribute():
doc = Document(TEST_ONE_SENTENCE)
response = semgrex.process_doc(doc, "{cpos:PROPN}=source <=zzz {word:Opal}=target")
check_response(response, response_len=1, source_index=2, reln='compound')
def test_ner_attribute():
doc = Document(TEST_ONE_SENTENCE)
response = semgrex.process_doc(doc, "{cpos:PROPN}=source <=zzz {ner:GEM}=target")
check_response(response, response_len=1, source_index=2, reln='compound')
def test_hand_built_request():
"""
Essentially a test program: the result should be a response with
one match, two named nodes, one named relation
"""
request = SemgrexRequest()
request.semgrex.append("{}=source >obj=zzz {}=target")
query = request.query.add()
for idx, word in enumerate(['Unban', 'Mox', 'Opal']):
token = query.token.add()
token.word = word
token.value = word
node = query.graph.node.add()
node.sentenceIndex = 1
node.index = idx+1
edge = query.graph.edge.add()
edge.source = 1
edge.target = 3
edge.dep = 'obj'
edge = query.graph.edge.add()
edge.source = 3
edge.target = 2
edge.dep = 'compound'
response = semgrex.send_semgrex_request(request)
check_response(response)
|
