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
|
/**
* Copyright (C) 2018-present MongoDB, Inc.
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the Server Side Public License, version 1,
* as published by MongoDB, Inc.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* Server Side Public License for more details.
*
* You should have received a copy of the Server Side Public License
* along with this program. If not, see
* <http://www.mongodb.com/licensing/server-side-public-license>.
*
* As a special exception, the copyright holders give permission to link the
* code of portions of this program with the OpenSSL library under certain
* conditions as described in each individual source file and distribute
* linked combinations including the program with the OpenSSL library. You
* must comply with the Server Side Public License in all respects for
* all of the code used other than as permitted herein. If you modify file(s)
* with this exception, you may extend this exception to your version of the
* file(s), but you are not obligated to do so. If you do not wish to do so,
* delete this exception statement from your version. If you delete this
* exception statement from all source files in the program, then also delete
* it in the license file.
*/
#include "mongo/platform/basic.h"
#include "mongo/db/fts/fts_spec.h"
#include "mongo/db/fts/tokenizer.h"
#include "mongo/unittest/unittest.h"
namespace mongo {
namespace fts {
TEST(Tokenizer, Empty1) {
Tokenizer i(&languageEnglishV2, "");
ASSERT(!i.more());
}
TEST(Tokenizer, Basic1) {
Tokenizer i(&languageEnglishV2, "blue red green");
ASSERT(i.more());
ASSERT_EQUALS(i.next().data.toString(), "blue");
ASSERT(i.more());
ASSERT_EQUALS(i.next().data.toString(), "red");
ASSERT(i.more());
ASSERT_EQUALS(i.next().data.toString(), "green");
ASSERT(!i.more());
}
TEST(Tokenizer, Basic2) {
Tokenizer i(&languageEnglishV2, "blue-red");
Token a = i.next();
Token b = i.next();
Token c = i.next();
Token d = i.next();
ASSERT_EQUALS(Token::TEXT, a.type);
ASSERT_EQUALS(Token::DELIMITER, b.type);
ASSERT_EQUALS(Token::TEXT, c.type);
ASSERT_EQUALS(Token::INVALID, d.type);
ASSERT_EQUALS("blue", a.data.toString());
ASSERT_EQUALS("-", b.data.toString());
ASSERT_EQUALS("red", c.data.toString());
}
TEST(Tokenizer, Basic3) {
Tokenizer i(&languageEnglishV2, "blue -red");
Token a = i.next();
Token b = i.next();
Token c = i.next();
Token d = i.next();
ASSERT_EQUALS(Token::TEXT, a.type);
ASSERT_EQUALS(Token::DELIMITER, b.type);
ASSERT_EQUALS(Token::TEXT, c.type);
ASSERT_EQUALS(Token::INVALID, d.type);
ASSERT_EQUALS("blue", a.data.toString());
ASSERT_EQUALS("-", b.data.toString());
ASSERT_EQUALS("red", c.data.toString());
ASSERT_EQUALS(0U, a.offset);
ASSERT_EQUALS(5U, b.offset);
ASSERT_EQUALS(6U, c.offset);
}
TEST(Tokenizer, Quote1English) {
Tokenizer i(&languageEnglishV2, "eliot's car");
Token a = i.next();
Token b = i.next();
ASSERT_EQUALS("eliot's", a.data.toString());
ASSERT_EQUALS("car", b.data.toString());
}
TEST(Tokenizer, Quote1French) {
Tokenizer i(&languageFrenchV2, "eliot's car");
Token a = i.next();
Token b = i.next();
Token c = i.next();
ASSERT_EQUALS("eliot", a.data.toString());
ASSERT_EQUALS("s", b.data.toString());
ASSERT_EQUALS("car", c.data.toString());
}
}
}
|
