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
|
# -*- coding: utf-8 -*-
from __future__ import unicode_literals
from __future__ import print_function
from __future__ import division
from builtins import str, bytes, dict, int
from builtins import map, zip, filter
from builtins import object, range
import os
import sys
sys.path.insert(0, os.path.join(os.path.dirname(__file__), ".."))
import unittest
import subprocess
from pattern import it
from io import open
try:
PATH = os.path.dirname(os.path.realpath(__file__))
except:
PATH = ""
#---------------------------------------------------------------------------------------------------
class TestInflection(unittest.TestCase):
def setUp(self):
pass
def test_article(self):
# Assert definite and indefinite article inflection.
for a, n, g in (
("il" , "giorno" , it.M),
("l'" , "altro giorno", it.M),
("lo" , "zio" , it.M),
("l'" , "amica" , it.F),
("la" , "nouva amica" , it.F),
("i" , "giapponesi" , it.M + it.PL),
("gli", "italiani" , it.M + it.PL),
("gli", "zii" , it.M + it.PL),
("le" , "zie" , it.F + it.PL)):
v = it.article(n, "definite", gender=g)
self.assertEqual(a, v)
for a, n, g in (
("uno", "zio" , it.M),
("una", "zia" , it.F),
("un" , "amico", it.M),
("un'", "amica", it.F)):
v = it.article(n, "indefinite", gender=g)
self.assertEqual(a, v)
v = it.referenced("amica", gender="f")
self.assertEqual(v, "un'amica")
print("pattern.it.article()")
print("pattern.it.referenced()")
def test_gender(self):
# Assert the accuracy of the gender disambiguation algorithm.
from pattern.db import Datasheet
i, n = 0, 0
for pos, sg, pl, mf in Datasheet.load(os.path.join(PATH, "corpora", "wordforms-it-wiktionary.csv"), encoding='utf8'):
g = it.gender(sg)
if mf in g and it.PLURAL not in g:
i += 1
g = it.gender(pl)
if mf in g and it.PLURAL in g:
i += 1
n += 2
self.assertTrue(float(i) / n > 0.92)
print("pattern.it.gender()")
def test_pluralize(self):
# Assert the accuracy of the pluralization algorithm.
from pattern.db import Datasheet
i, n = 0, 0
for pos, sg, pl, mf in Datasheet.load(os.path.join(PATH, "corpora", "wordforms-it-wiktionary.csv"), encoding='utf8'):
if it.pluralize(sg) == pl:
i += 1
n += 1
self.assertTrue(float(i) / n > 0.93)
print("pattern.it.pluralize()")
def test_singularize(self):
# Assert the accuracy of the singularization algorithm.
from pattern.db import Datasheet
i, n = 0, 0
for pos, sg, pl, mf in Datasheet.load(os.path.join(PATH, "corpora", "wordforms-it-wiktionary.csv"), encoding='utf8'):
if it.singularize(pl) == sg:
i += 1
n += 1
self.assertTrue(float(i) / n > 0.84)
print("pattern.it.singularize()")
def test_predicative(self):
# Assert the accuracy of the predicative algorithm ("cruciali" => "cruciale").
from pattern.db import Datasheet
i, n = 0, 0
for pos, sg, pl, mf in Datasheet.load(os.path.join(PATH, "corpora", "wordforms-it-wiktionary.csv"), encoding='utf8'):
if pos != "j":
continue
if it.predicative(pl) == sg:
i += 1
n += 1
self.assertTrue(float(i) / n > 0.87)
print("pattern.it.predicative()")
def test_find_lemma(self):
# Assert the accuracy of the verb lemmatization algorithm.
i, n = 0, 0
r = 0
for v1, v2 in it.inflect.verbs.inflections.items():
if it.inflect.verbs.find_lemma(v1) == v2:
i += 1
n += 1
self.assertTrue(float(i) / n > 0.81)
print("pattern.it.inflect.verbs.find_lemma()")
def test_find_lexeme(self):
# Assert the accuracy of the verb conjugation algorithm.
i, n = 0, 0
for v, lexeme1 in it.inflect.verbs.infinitives.items():
lexeme2 = it.inflect.verbs.find_lexeme(v)
for j in range(len(lexeme2)):
if lexeme1[j] == lexeme2[j]:
i += 1
n += 1
self.assertTrue(float(i) / n > 0.89)
print("pattern.it.inflect.verbs.find_lexeme()")
def test_conjugate(self):
# Assert different tenses with different conjugations.
for (v1, v2, tense) in (
("essere", "essere", it.INFINITIVE),
("essere", "sono", (it.PRESENT, 1, it.SINGULAR)),
("essere", "sei", (it.PRESENT, 2, it.SINGULAR)),
("essere", "è", (it.PRESENT, 3, it.SINGULAR)),
("essere", "siamo", (it.PRESENT, 1, it.PLURAL)),
("essere", "siete", (it.PRESENT, 2, it.PLURAL)),
("essere", "sono", (it.PRESENT, 3, it.PLURAL)),
("essere", "essendo", (it.PRESENT + it.PARTICIPLE)),
("essere", "stato", (it.PAST + it.PARTICIPLE)),
("essere", "ero", (it.IMPERFECT, 1, it.SINGULAR)),
("essere", "eri", (it.IMPERFECT, 2, it.SINGULAR)),
("essere", "era", (it.IMPERFECT, 3, it.SINGULAR)),
("essere", "eravamo", (it.IMPERFECT, 1, it.PLURAL)),
("essere", "eravate", (it.IMPERFECT, 2, it.PLURAL)),
("essere", "erano", (it.IMPERFECT, 3, it.PLURAL)),
("essere", "fui", (it.PRETERITE, 1, it.SINGULAR)),
("essere", "fosti", (it.PRETERITE, 2, it.SINGULAR)),
("essere", "fu", (it.PRETERITE, 3, it.SINGULAR)),
("essere", "fummo", (it.PRETERITE, 1, it.PLURAL)),
("essere", "foste", (it.PRETERITE, 2, it.PLURAL)),
("essere", "furono", (it.PRETERITE, 3, it.PLURAL)),
("essere", "sarei", (it.CONDITIONAL, 1, it.SINGULAR)),
("essere", "saresti", (it.CONDITIONAL, 2, it.SINGULAR)),
("essere", "sarebbe", (it.CONDITIONAL, 3, it.SINGULAR)),
("essere", "saremmo", (it.CONDITIONAL, 1, it.PLURAL)),
("essere", "sareste", (it.CONDITIONAL, 2, it.PLURAL)),
("essere", "sarebbero", (it.CONDITIONAL, 3, it.PLURAL)),
("essere", "sarò", (it.FUTURE, 1, it.SINGULAR)),
("essere", "sarai", (it.FUTURE, 2, it.SINGULAR)),
("essere", "sarà", (it.FUTURE, 3, it.SINGULAR)),
("essere", "saremo", (it.FUTURE, 1, it.PLURAL)),
("essere", "sarete", (it.FUTURE, 2, it.PLURAL)),
("essere", "saranno", (it.FUTURE, 3, it.PLURAL)),
("essere", "sii", (it.PRESENT, 2, it.SINGULAR, it.IMPERATIVE)),
("essere", "sia", (it.PRESENT, 3, it.SINGULAR, it.IMPERATIVE)),
("essere", "siamo", (it.PRESENT, 1, it.PLURAL, it.IMPERATIVE)),
("essere", "siate", (it.PRESENT, 2, it.PLURAL, it.IMPERATIVE)),
("essere", "siano", (it.PRESENT, 3, it.PLURAL, it.IMPERATIVE)),
("essere", "sia", (it.PRESENT, 1, it.SINGULAR, it.SUBJUNCTIVE)),
("essere", "sia", (it.PRESENT, 2, it.SINGULAR, it.SUBJUNCTIVE)),
("essere", "sia", (it.PRESENT, 3, it.SINGULAR, it.SUBJUNCTIVE)),
("essere", "siamo", (it.PRESENT, 1, it.PLURAL, it.SUBJUNCTIVE)),
("essere", "siate", (it.PRESENT, 2, it.PLURAL, it.SUBJUNCTIVE)),
("essere", "siano", (it.PRESENT, 3, it.PLURAL, it.SUBJUNCTIVE)),
("essere", "fossi", (it.PAST, 1, it.SINGULAR, it.SUBJUNCTIVE)),
("essere", "fossi", (it.PAST, 2, it.SINGULAR, it.SUBJUNCTIVE)),
("essere", "fosse", (it.PAST, 3, it.SINGULAR, it.SUBJUNCTIVE)),
("essere", "fossimo", (it.PAST, 1, it.PLURAL, it.SUBJUNCTIVE)),
("essere", "foste", (it.PAST, 2, it.PLURAL, it.SUBJUNCTIVE)),
("essere", "fossero", (it.PAST, 3, it.PLURAL, it.SUBJUNCTIVE))):
self.assertEqual(it.conjugate(v1, tense), v2)
print("pattern.it.conjugate()")
def test_lexeme(self):
# Assert all inflections of "essere".
v = it.lexeme("essere")
self.assertEqual(v, [
'essere', 'sono', 'sei', 'è', 'siamo', 'siete', 'essendo',
'fui', 'fosti', 'fu', 'fummo', 'foste', 'furono', 'stato',
'ero', 'eri', 'era', 'eravamo', 'eravate', 'erano',
'sarò', 'sarai', 'sarà', 'saremo', 'sarete', 'saranno',
'sarei', 'saresti', 'sarebbe', 'saremmo', 'sareste', 'sarebbero',
'sii', 'sia', 'siate', 'siano',
'fossi', 'fosse', 'fossimo', 'fossero'
])
print("pattern.it.inflect.lexeme()")
def test_tenses(self):
# Assert tense recognition.
self.assertTrue((it.PRESENT, 3, it.SG) in it.tenses("è"))
self.assertTrue("2sg" in it.tenses("sei"))
print("pattern.it.tenses()")
#---------------------------------------------------------------------------------------------------
class TestParser(unittest.TestCase):
def setUp(self):
pass
def test_find_lemmata(self):
# Assert lemmata for nouns, adjectives, verbs and determiners.
v = it.parser.find_lemmata([
["I", "DT"], ["gatti", "NNS"], ["neri", "JJ"],
["seduti", "VB"], ["sul", "IN"], ["tatami", "NN"]])
self.assertEqual(v, [
["I", "DT", "il"],
["gatti", "NNS", "gatto"],
["neri", "JJ", "nero"],
["seduti", "VB", "sedutare"],
["sul", "IN", "sul"],
["tatami", "NN", "tatami"]])
print("pattern.it.parser.find_lemmata()")
def test_parse(self):
# Assert parsed output with Penn Treebank II tags (slash-formatted).
# "il gatto nero" is a noun phrase, "sulla stuoia" is a prepositional noun phrase.
v = it.parser.parse("Il gatto nero seduto sulla stuoia.")
self.assertEqual(v,
"Il/DT/B-NP/O gatto/NN/I-NP/O nero/JJ/I-NP/O " +
"seduto/VB/B-VP/O " + \
"sulla/IN/B-PP/B-PNP stuoia/NN/B-NP/I-PNP ././O/O"
)
# Assert the accuracy of the Italian tagger.
i, n = 0, 0
with open(os.path.join(PATH, "corpora", "tagged-it-wacky.txt"), encoding='utf8') as f:
sentences = f.readlines()
for sentence in sentences:
sentence = sentence.strip()
s1 = [w.split("/") for w in sentence.split(" ")]
s2 = [[w for w, pos in s1]]
s2 = it.parse(s2, tokenize=False)
s2 = [w.split("/") for w in s2.split(" ")]
for j in range(len(s1)):
t1 = s1[j][1]
t2 = s2[j][1]
# WaCKy test set tags plural nouns as "NN", pattern.it as "NNS".
# Some punctuation marks are also tagged differently,
# but these are not necessarily errors.
if t1 == t2 or (t1 == "NN" and t2.startswith("NN")) or s1[j][0] in "\":;)-":
i += 1
n += 1
#print(float(i) / n)
self.assertTrue(float(i) / n > 0.92)
print("pattern.it.parser.parse()")
def test_tag(self):
# Assert [("il", "DT"), ("gatto", "NN"), ("nero", "JJ")].
v = it.tag("il gatto nero")
self.assertEqual(v, [("il", "DT"), ("gatto", "NN"), ("nero", "JJ")])
print("pattern.it.tag()")
def test_command_line(self):
# Assert parsed output from the command-line (example from the documentation).
p = ["python3", "-m", "pattern.it", "-s", "Il gatto nero.", "-OTCRL"]
with subprocess.Popen(p, stdout=subprocess.PIPE) as p:
p.wait()
v = p.stdout.read().decode('utf-8')
v = v.strip()
self.assertEqual(v, "Il/DT/B-NP/O/O/il gatto/NN/I-NP/O/O/gatto nero/JJ/I-NP/O/O/nero ././O/O/O/.")
print("python3 -m pattern.it")
#---------------------------------------------------------------------------------------------------
def suite():
suite = unittest.TestSuite()
suite.addTest(unittest.TestLoader().loadTestsFromTestCase(TestInflection))
suite.addTest(unittest.TestLoader().loadTestsFromTestCase(TestParser))
return suite
if __name__ == "__main__":
result = unittest.TextTestRunner(verbosity=1).run(suite())
sys.exit(not result.wasSuccessful())
|
