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
|
import pytest
from lunr.token_set import TokenSet
from lunr.exceptions import BaseLunrException
class TestTokenSetStr:
def test_str_includes_node_finality(self):
non_final = TokenSet()
final = TokenSet()
other_final = TokenSet()
final.final = True
other_final.final = True
assert str(non_final) != str(final)
assert str(other_final) == str(final)
def test_str_includes_all_edges(self):
zero_edges = TokenSet()
one_edge = TokenSet()
two_edges = TokenSet()
one_edge.edges["a"] = 1
two_edges.edges["a"] = 1
two_edges.edges["b"] = 1
assert str(zero_edges) != str(one_edge)
assert str(two_edges) != str(one_edge)
assert str(two_edges) != str(zero_edges)
def test_str_includes_edge_id(self):
child_a = TokenSet()
child_b = TokenSet()
parent_a = TokenSet()
parent_b = TokenSet()
parent_c = TokenSet()
parent_a.edges["a"] = child_a
parent_b.edges["a"] = child_b
parent_c.edges["a"] = child_b
assert str(parent_b) == str(parent_c)
assert str(parent_a) != str(parent_c)
assert str(parent_a) != str(parent_b)
class TestTokenSetFromString:
def test_from_string_without_wildcard(self):
TokenSet._next_id = 1
x = TokenSet.from_string("a")
assert str(x) == "0a2"
assert x.edges["a"].final
def test_from_string_with_trailing_wildcard(self):
x = TokenSet.from_string("a*")
wild = x.edges["a"].edges["*"]
assert wild == wild.edges["*"]
assert wild.final
class TestTokenSetFromList:
def test_from_list_with_unsorted_list(self):
with pytest.raises(BaseLunrException):
TokenSet.from_list(["z", "a"])
def test_from_list_with_sorted_list(self):
token_set = TokenSet.from_list(["a", "z"])
assert ["a", "z"] == sorted(token_set.to_list())
def test_from_list_is_minimal(self):
token_set = TokenSet.from_list(["ac", "dc"])
ac_node = token_set.edges["a"].edges["c"]
dc_node = token_set.edges["d"].edges["c"]
assert ac_node == dc_node
class TestTokenSetToList:
def test_to_list_includes_all_words(self):
words = ["bat", "cat"]
token_set = TokenSet.from_list(words)
assert set(words) == set(token_set.to_list())
def test_to_list_includes_single_words(self):
word = "bat"
token_set = TokenSet.from_string(word)
assert {word} == set(token_set.to_list())
class TestTokenSetIntersect:
def test_no_intersection(self):
x = TokenSet.from_string("cat")
y = TokenSet.from_string("bar")
z = x.intersect(y)
assert len(z.to_list()) == 0
def test_simple_intersection(self):
x = TokenSet.from_string("cat")
y = TokenSet.from_string("cat")
z = x.intersect(y)
assert {"cat"} == set(z.to_list())
def test_trailing_wildcard_intersection(self):
x = TokenSet.from_string("cat")
y = TokenSet.from_string("c*")
z = x.intersect(y)
assert {"cat"} == set(z.to_list())
def test_trailing_wildcard_no_intersection(self):
x = TokenSet.from_string("cat")
y = TokenSet.from_string("b*")
z = x.intersect(y)
assert len(z.to_list()) == 0
def test_leading_wildcard_intersection(self):
x = TokenSet.from_string("cat")
y = TokenSet.from_string("*t")
z = x.intersect(y)
assert {"cat"} == set(z.to_list())
def test_leading_wildcard_no_intersection(self):
x = TokenSet.from_string("cat")
y = TokenSet.from_string("*r")
z = x.intersect(y)
assert len(z.to_list()) == 0
def test_contained_wildcard_intersection(self):
x = TokenSet.from_string("foo")
y = TokenSet.from_string("f*o")
z = x.intersect(y)
assert {"foo"} == set(z.to_list())
def test_contained_wildcard_no_intersection(self):
x = TokenSet.from_string("foo")
y = TokenSet.from_string("b*r")
z = x.intersect(y)
assert len(z.to_list()) == 0
def test_wildcard_zero_or_more_characters(self):
x = TokenSet.from_string("foo")
y = TokenSet.from_string("foo*")
z = x.intersect(y)
assert {"foo"} == set(z.to_list())
def test_with_fuzzy_string_substitution(self):
x1 = TokenSet.from_string("bar")
x2 = TokenSet.from_string("cur")
x3 = TokenSet.from_string("cat")
x4 = TokenSet.from_string("car")
x5 = TokenSet.from_string("foo")
y = TokenSet.from_fuzzy_string("car", 1)
assert x1.intersect(y).to_list() == ["bar"]
assert x2.intersect(y).to_list() == ["cur"]
assert x3.intersect(y).to_list() == ["cat"]
assert x4.intersect(y).to_list() == ["car"]
assert x5.intersect(y).to_list() == []
def test_with_fuzzy_string_deletion(self):
x1 = TokenSet.from_string("ar")
x2 = TokenSet.from_string("br")
x3 = TokenSet.from_string("ba")
x4 = TokenSet.from_string("bar")
x5 = TokenSet.from_string("foo")
y = TokenSet.from_fuzzy_string("bar", 1)
assert x1.intersect(y).to_list() == ["ar"]
assert x2.intersect(y).to_list() == ["br"]
assert x3.intersect(y).to_list() == ["ba"]
assert x4.intersect(y).to_list() == ["bar"]
assert x5.intersect(y).to_list() == []
def test_with_fuzzy_string_insertion(self):
x1 = TokenSet.from_string("bbar")
x2 = TokenSet.from_string("baar")
x3 = TokenSet.from_string("barr")
x4 = TokenSet.from_string("bar")
x5 = TokenSet.from_string("ba")
x6 = TokenSet.from_string("foo")
x7 = TokenSet.from_string("bara")
y = TokenSet.from_fuzzy_string("bar", 1)
assert x1.intersect(y).to_list() == ["bbar"]
assert x2.intersect(y).to_list() == ["baar"]
assert x3.intersect(y).to_list() == ["barr"]
assert x4.intersect(y).to_list() == ["bar"]
assert x5.intersect(y).to_list() == ["ba"]
assert x6.intersect(y).to_list() == []
assert x7.intersect(y).to_list() == ["bara"]
def test_with_fuzzy_string_transpose(self):
x1 = TokenSet.from_string("abr")
x2 = TokenSet.from_string("bra")
x3 = TokenSet.from_string("foo")
y = TokenSet.from_fuzzy_string("bar", 1)
assert x1.intersect(y).to_list() == ["abr"]
assert x2.intersect(y).to_list() == ["bra"]
assert x3.intersect(y).to_list() == []
def test_fuzzy_string_insertion(self):
x = TokenSet.from_string("abcxx")
y = TokenSet.from_fuzzy_string("abc", 2)
assert x.intersect(y).to_list() == ["abcxx"]
def test_fuzzy_string_substitution(self):
x = TokenSet.from_string("axx")
y = TokenSet.from_fuzzy_string("abc", 2)
assert x.intersect(y).to_list() == ["axx"]
def test_fuzzy_string_deletion(self):
x = TokenSet.from_string("a")
y = TokenSet.from_fuzzy_string("abc", 2)
assert x.intersect(y).to_list() == ["a"]
def test_fuzzy_string_transpose(self):
x = TokenSet.from_string("bca")
y = TokenSet.from_fuzzy_string("abc", 2)
assert x.intersect(y).to_list() == ["bca"]
def test_leading_wildcard_backtracking_intersection(self):
x = TokenSet.from_string("aaacbab")
y = TokenSet.from_string("*ab")
assert x.intersect(y).to_list() == ["aaacbab"]
def test_leading_wildcard_backtracking_no_intersection(self):
x = TokenSet.from_string("aaacbab")
y = TokenSet.from_string("*abc")
assert x.intersect(y).to_list() == []
def test_contained_wildcard_backtracking_intersection(self):
x = TokenSet.from_string("ababc")
y = TokenSet.from_string("a*bc")
assert x.intersect(y).to_list() == ["ababc"]
def test_contained_wildcard_backtracking_no_intersection(self):
x = TokenSet.from_string("ababc")
y = TokenSet.from_string("a*ac")
assert x.intersect(y).to_list() == []
@pytest.mark.timeout(2)
def test_catastrophic_backtracking_with_leading_characters(self):
x = TokenSet.from_string("f" * 100)
y = TokenSet.from_string("*f")
assert len(x.intersect(y).to_list()) == 1
def test_leading_trailing_wildcard_backtracking_intersection(self):
x = TokenSet.from_string("acbaabab")
y = TokenSet.from_string("*ab*")
assert x.intersect(y).to_list() == ["acbaabab"]
def test_leading_atrailing_wildcard_backtracking_intersection(self):
x = TokenSet.from_string("acbaabab")
y = TokenSet.from_string("a*ba*b")
assert x.intersect(y).to_list() == ["acbaabab"]
|
