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
|
# -*- coding: utf-8 -*-
#
# SPDX-License-Identifier: LicenseRef-scancode-public-domain
# See https://github.com/nexB/license-expression for support or download.
# See https://aboutcode.org for more information about nexB OSS projects.
"""
Tests for Aho-Corasick string search algorithm.
Original Author: Wojciech Muła, wojciech_mula@poczta.onet.pl
WWW : http://0x80.pl
License : public domain
Modified for use in the license_expression library.
"""
import unittest
from license_expression._pyahocorasick import Trie
from license_expression._pyahocorasick import Token
class TestTrie(unittest.TestCase):
def test_add_can_get(self):
t = Trie()
t.add('python', 'value')
assert ('python', 'value') == t.get('python')
def test_add_existing_WordShouldReplaceAssociatedValue(self):
t = Trie()
t.add('python', 'value')
assert ('python', 'value') == t.get('python')
t.add('python', 'other')
assert ('python', 'other') == t.get('python')
def test_get_UnknowWordWithoutDefaultValueShouldRaiseException(self):
t = Trie()
with self.assertRaises(KeyError):
t.get('python')
def test_get_UnknowWordWithDefaultValueShouldReturnDefault(self):
t = Trie()
self.assertEqual(t.get('python', 'default'), 'default')
def test_exists_ShouldDetectAddedWords(self):
t = Trie()
t.add('python', 'value')
t.add('ada', 'value')
self.assertTrue(t.exists('python'))
self.assertTrue(t.exists('ada'))
def test_exists_ShouldReturnFailOnUnknownWord(self):
t = Trie()
t.add('python', 'value')
self.assertFalse(t.exists('ada'))
def test_is_prefix_ShouldDetecAllPrefixesIncludingWord(self):
t = Trie()
t.add('python', 'value')
t.add('ada lovelace', 'value')
self.assertFalse(t.is_prefix('a'))
self.assertFalse(t.is_prefix('ad'))
self.assertTrue(t.is_prefix('ada'))
self.assertFalse(t.is_prefix('p'))
self.assertFalse(t.is_prefix('py'))
self.assertFalse(t.is_prefix('pyt'))
self.assertFalse(t.is_prefix('pyth'))
self.assertFalse(t.is_prefix('pytho'))
self.assertTrue(t.is_prefix('python'))
self.assertFalse(t.is_prefix('lovelace'))
def test_items_ShouldReturnAllItemsAlreadyAddedToTheTrie(self):
t = Trie()
t.add('python', 1)
t.add('ada', 2)
t.add('perl', 3)
t.add('pascal', 4)
t.add('php', 5)
t.add('php that', 6)
result = list(t.items())
self.assertIn(('python', 1), result)
self.assertIn(('ada', 2), result)
self.assertIn(('perl', 3), result)
self.assertIn(('pascal', 4), result)
self.assertIn(('php', 5), result)
self.assertIn(('php that', 6), result)
def test_keys_ShouldReturnAllKeysAlreadyAddedToTheTrie(self):
t = Trie()
t.add('python', 1)
t.add('ada', 2)
t.add('perl', 3)
t.add('pascal', 4)
t.add('php', 5)
t.add('php that', 6)
result = list(t.keys())
self.assertIn('python', result)
self.assertIn('ada', result)
self.assertIn('perl', result)
self.assertIn('pascal', result)
self.assertIn('php', result)
self.assertIn('php that', result)
def test_values_ShouldReturnAllValuesAlreadyAddedToTheTrie(self):
t = Trie()
t.add('python', 1)
t.add('ada', 2)
t.add('perl', 3)
t.add('pascal', 4)
t.add('php', 5)
result = list(t.values())
self.assertIn(1, result)
self.assertIn(2, result)
self.assertIn(3, result)
self.assertIn(4, result)
self.assertIn(5, result)
def test_iter_should_not_return_non_matches_by_default(self):
def get_test_automaton():
words = 'he her hers his she hi him man himan'.split()
t = Trie()
for w in words:
t.add(w, w)
t.make_automaton()
return t
test_string = 'he she himan'
t = get_test_automaton()
result = list(t.iter(test_string))
assert 'he she himan'.split() == [r.value for r in result]
def test_iter_should_can_return_non_matches_optionally(self):
def get_test_automaton():
words = 'he her hers his she hi him man himan'.split()
t = Trie()
for w in words:
t.add(w, w)
t.make_automaton()
return t
test_string = ' he she junk himan other stuffs '
# 111111111122222222223333333
# 0123456789012345678901234567890123456
t = get_test_automaton()
result = list(t.iter(test_string, include_unmatched=True, include_space=True))
expected = [
Token(0, 1, u' ', None),
Token(2, 3, u'he', u'he'),
Token(4, 4, u' ', None),
Token(5, 7, u'she', u'she'),
Token(8, 8, u' ', None),
Token(9, 12, u'junk', None),
Token(13, 14, u' ', None),
Token(15, 19, u'himan', u'himan'),
Token(20, 21, u' ', None),
Token(22, 26, u'other', None),
Token(27, 27, u' ', None),
Token(28, 33, u'stuffs', None),
Token(34, 36, u' ', None),
]
assert expected == result
def test_iter_vs_tokenize(self):
def get_test_automaton():
words = '( AND ) OR'.split()
t = Trie()
for w in words:
t.add(w, w)
t.make_automaton()
return t
test_string = '((l-a + AND l-b) OR (l -c+))'
t = get_test_automaton()
result = list(t.iter(test_string, include_unmatched=True, include_space=True))
expected = [
Token(0, 0, u'(', u'('),
Token(1, 1, u'(', u'('),
Token(2, 4, u'l-a', None),
Token(5, 5, u' ', None),
Token(6, 6, u'+', None),
Token(7, 7, u' ', None),
Token(8, 10, u'AND', u'AND'),
Token(11, 11, u' ', None),
Token(12, 14, u'l-b', None),
Token(15, 15, u')', u')'),
Token(16, 16, u' ', None),
Token(17, 18, u'OR', u'OR'),
Token(19, 19, u' ', None),
Token(20, 20, u'(', u'('),
Token(21, 21, u'l', None),
Token(22, 22, u' ', None),
Token(23, 25, u'-c+', None),
Token(26, 26, u')', u')'),
Token(27, 27, u')', u')')
]
assert expected == result
result = list(t.tokenize(test_string, include_unmatched=True, include_space=True))
assert expected == result
def test_tokenize_with_unmatched_and_space(self):
def get_test_automaton():
words = '( AND ) OR'.split()
t = Trie()
for w in words:
t.add(w, w)
t.make_automaton()
return t
test_string = '((l-a + AND l-b) OR an (l -c+))'
# 111111111122222222223
# 0123456789012345678901234567890
t = get_test_automaton()
result = list(t.tokenize(test_string, include_unmatched=True, include_space=True))
expected = [
Token(0, 0, u'(', u'('),
Token(1, 1, u'(', u'('),
Token(2, 4, u'l-a', None),
Token(5, 5, u' ', None),
Token(6, 6, u'+', None),
Token(7, 7, u' ', None),
Token(8, 10, u'AND', u'AND'),
Token(11, 11, u' ', None),
Token(12, 14, u'l-b', None),
Token(15, 15, u')', u')'),
Token(16, 16, u' ', None),
Token(17, 18, u'OR', u'OR'),
Token(19, 19, u' ', None),
Token(20, 21, u'an', None),
Token(22, 22, u' ', None),
Token(23, 23, u'(', u'('),
Token(24, 24, u'l', None),
Token(25, 25, u' ', None),
Token(26, 28, u'-c+', None),
Token(29, 29, u')', u')'),
Token(30, 30, u')', u')')
]
assert expected == result
assert test_string == ''.join(t.string for t in result)
def test_iter_with_unmatched_simple(self):
t = Trie()
t.add('And', 'And')
t.make_automaton()
test_string = 'AND an a And'
result = list(t.iter(test_string))
assert ['And', 'And'] == [r.value for r in result]
def test_iter_with_unmatched_simple2(self):
t = Trie()
t.add('AND', 'AND')
t.make_automaton()
test_string = 'AND an a and'
result = list(t.iter(test_string))
assert ['AND', 'AND'] == [r.value for r in result]
def test_iter_with_unmatched_simple3(self):
t = Trie()
t.add('AND', 'AND')
t.make_automaton()
test_string = 'AND an a andersom'
result = list(t.iter(test_string))
assert ['AND'] == [r.value for r in result]
def test_iter_simple(self):
t = Trie()
t.add('AND', 'AND')
t.add('OR', 'OR')
t.add('WITH', 'WITH')
t.add('(', '(')
t.add(')', ')')
t.add('GPL-2.0', 'GPL-2.0')
t.add('mit', 'MIT')
t.add('Classpath', 'Classpath')
t.make_automaton()
test_string = '(GPL-2.0 with Classpath) or (gpl-2.0) and (classpath or gpl-2.0 OR mit) '
# 111111111122222222223333333333444444444455555555556666666666777
# 0123456789012345678901234567890123456789012345678901234567890123456789012
result = list(t.iter(test_string))
expected = [
Token(0, 0, u'(', u'('),
Token(1, 7, u'GPL-2.0', u'GPL-2.0'),
Token(9, 12, u'with', u'WITH'),
Token(14, 22, u'Classpath', u'Classpath'),
Token(23, 23, u')', u')'),
Token(25, 26, u'or', u'OR'),
Token(28, 28, u'(', u'('),
Token(29, 35, u'gpl-2.0', u'GPL-2.0'),
Token(36, 36, u')', u')'),
Token(38, 40, u'and', u'AND'),
Token(42, 42, u'(', u'('),
Token(43, 51, u'classpath', u'Classpath'),
Token(53, 54, u'or', u'OR'),
Token(57, 63, u'gpl-2.0', u'GPL-2.0'),
Token(65, 66, u'OR', u'OR'),
Token(68, 70, u'mit', u'MIT'),
Token(71, 71, u')', u')')
]
assert expected == result
|
