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
|
// tokenizer.cpp
/**
* Copyright (C) 2012 10gen Inc.
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License, version 3,
* as published by the Free Software Foundation.
*
* 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
* GNU Affero General Public License for more details.
*
* You should have received a copy of the GNU Affero General Public License
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
#include <string>
#include "mongo/db/fts/tokenizer.h"
#include "mongo/util/stringutils.h"
namespace mongo {
namespace fts {
Tokenizer::Tokenizer( const string& language, const StringData& str )
: _pos(0), _raw( str ) {
_english = language == "english";
_skipWhitespace();
_previousWhiteSpace = true;
}
bool Tokenizer::more() const {
return _pos < _raw.size();
}
Token Tokenizer::next() {
if ( _pos >= _raw.size() )
return Token( Token::INVALID, "", 0, false );
unsigned start = _pos++;
Token::Type type = _type( _raw[start] );
if ( type == Token::WHITESPACE ) abort();
if ( type == Token::TEXT )
while ( _pos < _raw.size() && _type( _raw[_pos] ) == type )
_pos++;
StringData ret = _raw.substr( start, _pos - start );
bool old = _previousWhiteSpace;
_previousWhiteSpace = _skipWhitespace();
return Token( type, ret, start, old );
}
bool Tokenizer::_skipWhitespace() {
unsigned start = _pos;
while ( _pos < _raw.size() && _type( _raw[_pos] ) == Token::WHITESPACE )
_pos++;
return _pos > start;
}
Token::Type Tokenizer::_type( char c ) const {
switch ( c ) {
case ' ':
case '\f':
case '\v':
case '\t':
case '\r':
case '\n':
return Token::WHITESPACE;
case '\'':
if ( _english )
return Token::TEXT;
else
return Token::WHITESPACE;
case '~':
case '`':
case '!':
case '@':
case '#':
case '$':
case '%':
case '^':
case '&':
case '*':
case '(':
case ')':
case '-':
case '=':
case '+':
case '[':
case ']':
case '{':
case '}':
case '|':
case '\\':
case ';':
case ':':
case '"':
case '<':
case '>':
case ',':
case '.':
case '/':
case '?':
return Token::DELIMITER;
default:
return Token::TEXT;
}
}
}
}
|