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
|
// Copyright 2022 The Chromium Authors
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file.
#include "chromeos/ash/components/string_matching/prefix_matcher.h"
#include "chromeos/ash/components/string_matching/tokenized_string.h"
#include "testing/gtest/include/gtest/gtest.h"
namespace ash::string_matching {
namespace {
using prefix_matcher_constants::kIsFrontOfTokenCharScore;
using prefix_matcher_constants::kIsPrefixCharScore;
using prefix_matcher_constants::kIsWeakHitCharScore;
using prefix_matcher_constants::kNoMatchScore;
constexpr double kAbsError = 1e-5;
} // namespace
class PrefixMatcherTest : public testing::Test {};
// Note on expected score calculations:
//
// When a query successfully matches to a text, each letter of the query
// contributes some amount towards a final total. The expected score in
// each test is then the sum over all of the contributions of the individual
// query letters. This is described in more detail in prefix_matcher.cc.
//
// When a query does not successfully match to a text, the overall expected
// score is `kNoMatchScore`.
TEST_F(PrefixMatcherTest, ExactMatch) {
TokenizedString query(u"abc def");
TokenizedString text(u"abc def");
PrefixMatcher pm(query, text);
pm.Match();
double expected_score = kIsPrefixCharScore * 6;
EXPECT_NEAR(pm.relevance(), expected_score, kAbsError);
}
TEST_F(PrefixMatcherTest, ExactPrefixMatch) {
TokenizedString query(u"abc def");
TokenizedString text(u"abc defgh ijklm");
PrefixMatcher pm(query, text);
pm.Match();
double expected_score = kIsPrefixCharScore * 6;
EXPECT_NEAR(pm.relevance(), expected_score, kAbsError);
}
TEST_F(PrefixMatcherTest, ExactPrefixMatchFirstToken) {
TokenizedString query(u"ab");
TokenizedString text(u"abc def");
PrefixMatcher pm(query, text);
pm.Match();
double expected_score = kIsPrefixCharScore * 2;
EXPECT_NEAR(pm.relevance(), expected_score, kAbsError);
}
TEST_F(PrefixMatcherTest, ExactPrefixMatchNonFirstToken) {
TokenizedString query(u"de");
TokenizedString text(u"abc def");
PrefixMatcher pm(query, text);
pm.Match();
double expected_score = kIsFrontOfTokenCharScore + kIsWeakHitCharScore;
EXPECT_NEAR(pm.relevance(), expected_score, kAbsError);
}
TEST_F(PrefixMatcherTest, AcronymMatchFirstTokenMatchConsideredNonMatch) {
TokenizedString query(u"abc");
TokenizedString text(u"axx bxx cxx dxx exx");
PrefixMatcher pm(query, text);
pm.Match();
double expected_score = kNoMatchScore;
EXPECT_NEAR(pm.relevance(), expected_score, kAbsError);
}
TEST_F(PrefixMatcherTest, AcronymMatchNonFirstTokenMatchConsideredNonMatch) {
TokenizedString query(u"bcd");
TokenizedString text(u"axx bxx cxx dxx exx");
PrefixMatcher pm(query, text);
pm.Match();
double expected_score = kNoMatchScore;
EXPECT_NEAR(pm.relevance(), expected_score, kAbsError);
}
TEST_F(PrefixMatcherTest, AcronymMatchNonConsecutiveConsideredNonMatch) {
TokenizedString query(u"acd");
TokenizedString text(u"axx bxx cxx dxx exx");
PrefixMatcher pm(query, text);
pm.Match();
double expected_score = kNoMatchScore;
EXPECT_NEAR(pm.relevance(), expected_score, kAbsError);
}
TEST_F(PrefixMatcherTest, MixedAcronymAndPrefixMatchingConsideredNonMatch) {
TokenizedString query(u"adefg");
TokenizedString text(u"abc def ghi");
PrefixMatcher pm(query, text);
pm.Match();
double expected_score = kNoMatchScore;
EXPECT_NEAR(pm.relevance(), expected_score, kAbsError);
}
TEST_F(PrefixMatcherTest, FinalPartialTokenConsideredMatch) {
TokenizedString query(u"abc de");
TokenizedString text(u"abc def");
PrefixMatcher pm(query, text);
pm.Match();
double expected_score = kIsPrefixCharScore * 5;
EXPECT_NEAR(pm.relevance(), expected_score, kAbsError);
}
TEST_F(PrefixMatcherTest, NonFinalPartialTokenConsideredNonMatch) {
TokenizedString query(u"abce");
TokenizedString text(u"a bcd e");
PrefixMatcher pm(query, text);
pm.Match();
double expected_score = kNoMatchScore;
EXPECT_NEAR(pm.relevance(), expected_score, kAbsError);
}
TEST_F(PrefixMatcherTest, ExactPrefixMatchDiscrete) {
TokenizedString query(u"abc ghi");
TokenizedString text(u"abc def ghi");
PrefixMatcher pm(query, text);
pm.Match();
double expected_score = kIsPrefixCharScore * 3 + kIsFrontOfTokenCharScore +
kIsWeakHitCharScore * 2;
EXPECT_NEAR(pm.relevance(), expected_score, kAbsError);
}
TEST_F(PrefixMatcherTest, ExactPrefixMatchDiscreteNonFirstToken) {
TokenizedString query(u"abc ghi");
TokenizedString text(u"jkl abc def ghi");
PrefixMatcher pm(query, text);
pm.Match();
double expected_score =
kIsFrontOfTokenCharScore * 2 + kIsWeakHitCharScore * 4;
EXPECT_NEAR(pm.relevance(), expected_score, kAbsError);
}
TEST_F(PrefixMatcherTest, ExactPrefixMatchOrderVariation) {
TokenizedString query(u"ghi abc");
TokenizedString text(u"abc ghi");
PrefixMatcher pm(query, text);
pm.Match();
double expected_score =
kIsFrontOfTokenCharScore * 2 + kIsWeakHitCharScore * 4;
EXPECT_NEAR(pm.relevance(), expected_score, kAbsError);
}
TEST_F(PrefixMatcherTest, ExactPrefixMatchOrderVariationNonFirstToken) {
TokenizedString query(u"ghi abc");
TokenizedString text(u"jkl abc ghi");
PrefixMatcher pm(query, text);
pm.Match();
double expected_score =
kIsFrontOfTokenCharScore * 2 + kIsWeakHitCharScore * 4;
EXPECT_NEAR(pm.relevance(), expected_score, kAbsError);
}
TEST_F(PrefixMatcherTest, ExactPrefixMatchOrderVariationAndDiscrete) {
TokenizedString query(u"ghi abc");
TokenizedString text(u"jkl abc def ghi");
PrefixMatcher pm(query, text);
pm.Match();
double expected_score =
kIsFrontOfTokenCharScore * 2 + kIsWeakHitCharScore * 4;
EXPECT_NEAR(pm.relevance(), expected_score, kAbsError);
}
TEST_F(PrefixMatcherTest, SentencePrefixMatch) {
TokenizedString query(u"abcd");
TokenizedString text(u"a bcd e");
PrefixMatcher pm(query, text);
pm.Match();
double expected_score = kIsPrefixCharScore * 4;
EXPECT_NEAR(pm.relevance(), expected_score, kAbsError);
}
TEST_F(PrefixMatcherTest, SentencePrefixMatchNotInFront) {
TokenizedString query(u"abcd");
TokenizedString text(u"fgh a bcd e");
PrefixMatcher pm(query, text);
pm.Match();
double expected_score = (kIsFrontOfTokenCharScore + kIsWeakHitCharScore) * 2;
EXPECT_NEAR(pm.relevance(), expected_score, kAbsError);
}
TEST_F(PrefixMatcherTest, CaseSentencePrefixMatchPreferred) {
TokenizedString query(u"abc def");
TokenizedString text(u"abcdef abc def");
PrefixMatcher pm(query, text);
pm.Match();
double expected_score = kIsPrefixCharScore * 6;
EXPECT_NEAR(pm.relevance(), expected_score, kAbsError);
}
TEST_F(PrefixMatcherTest, CaseTokenPrefixMatchPreferred) {
TokenizedString query(u"abc def");
TokenizedString text(u"def abc abcdef");
PrefixMatcher pm(query, text);
pm.Match();
double expected_score =
kIsFrontOfTokenCharScore * 2 + kIsWeakHitCharScore * 4;
EXPECT_NEAR(pm.relevance(), expected_score, kAbsError);
}
TEST_F(PrefixMatcherTest, LastQueryTokenCanBeMatchedAtMostOnce) {
TokenizedString query(u"about c");
TokenizedString text(u"Chrome Canvas");
PrefixMatcher pm(query, text);
pm.Match();
double expected_score = 0;
EXPECT_NEAR(pm.relevance(), expected_score, kAbsError);
}
} // namespace ash::string_matching
|
