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
|
/**
* 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.
*/
#pragma once
#include <cstdint>
#include "mongo/base/disallow_copying.h"
#include "mongo/base/string_data.h"
namespace mongo {
namespace fts {
class FTSLanguage;
class StopWords;
/**
* FTSTokenizer
* A iterator of "documents" where a document contains space delimited words. For each word returns
* a stem or lemma version of a word optimized for full text indexing. Supports various options to
* control how tokens are generated.
*/
class FTSTokenizer {
public:
virtual ~FTSTokenizer() = default;
/**
* Options for generating tokens.
*/
using Options = uint8_t;
/**
* Default means lower cased, diacritics removed, and stop words are not filtered.
*/
static const Options kNone = 0;
/**
* Do not lower case terms.
*/
static const Options kGenerateCaseSensitiveTokens = 1 << 0;
/**
* Filter out stop words from return tokens.
*/
static const Options kFilterStopWords = 1 << 1;
/**
* Do not remove diacritics from terms.
*/
static const Options kGenerateDiacriticSensitiveTokens = 1 << 2;
/**
* Process a new document, and discards any previous results.
* May be called multiple times on an instance of an iterator.
*/
virtual void reset(StringData document, Options options) = 0;
/**
* Moves to the next token in the iterator.
* Returns false when the iterator reaches end of the document.
*/
virtual bool moveNext() = 0;
/**
* Returns stemmed form, normalized, and lowercased depending on the parameter
* to the reset method.
* Returned StringData is valid until next call to moveNext().
*/
virtual StringData get() const = 0;
};
} // namespace fts
} // namespace mongo
|
