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
|
<?php
/**
* Zend Framework
*
* LICENSE
*
* This source file is subject to version 1.0 of the Zend Framework
* license, that is bundled with this package in the file LICENSE, and
* is available through the world-wide-web at the following URL:
* http://www.zend.com/license/framework/1_0.txt. If you did not receive
* a copy of the Zend Framework license and are unable to obtain it
* through the world-wide-web, please send a note to license@zend.com
* so we can mail you a copy immediately.
*
* @package Zend_Search_Lucene
* @subpackage document
* @copyright Copyright (c) 2005-2006 Zend Technologies USA Inc. (http://www.zend.com)
* @license http://www.zend.com/license/framework/1_0.txt Zend Framework License version 1.0
*/
/**
*
* @package Zend_Search_Lucene
* @subpackage Analysis
* @copyright Copyright (c) 2005-2006 Zend Technologies USA Inc. (http://www.zend.com)
* @license http://www.zend.com/license/framework/1_0.txt Zend Framework License version 1.0
*/
class Zend_Search_Lucene_Analysis_Token
{
/**
* The text of the term.
*
* @var string
*/
private $_termText;
/**
* Start in source text.
*
* @var integer
*/
private $_startOffset;
/**
* End in source text
*
* @var integer
*/
private $_endOffset;
/**
* Lexical type.
*
* @var string
*/
private $_type;
/**
* The position of this token relative to the previous Token.
*
* The default value is one.
*
* Some common uses for this are:
* Set it to zero to put multiple terms in the same position. This is
* useful if, e.g., a word has multiple stems. Searches for phrases
* including either stem will match. In this case, all but the first stem's
* increment should be set to zero: the increment of the first instance
* should be one. Repeating a token with an increment of zero can also be
* used to boost the scores of matches on that token.
*
* Set it to values greater than one to inhibit exact phrase matches.
* If, for example, one does not want phrases to match across removed stop
* words, then one could build a stop word filter that removes stop words and
* also sets the increment to the number of stop words removed before each
* non-stop word. Then exact phrase queries will only match when the terms
* occur with no intervening stop words.
*
* @var integer
*/
private $_positionIncrement;
/**
* Object constructor
*
* @param string $text
* @param integer $start
* @param integer $end
* @param string $type
*/
public function __construct($text, $start, $end, $type = 'word' )
{
$this->_termText = $text;
$this->_startOffset = $start;
$this->_endOffset = $end;
$this->_type = $type;
$this->_positionIncrement = 1;
}
/**
* positionIncrement setter
*
* @param integer $positionIncrement
*/
public function setPositionIncrement($positionIncrement)
{
$this->_positionIncrement = $positionIncrement;
}
/**
* Returns the position increment of this Token.
*
* @return integer
*/
public function getPositionIncrement()
{
return $this->_positionIncrement;
}
/**
* Returns the Token's term text.
*
* @return string
*/
public function getTermText()
{
return $this->_termText;
}
/**
* Returns this Token's starting offset, the position of the first character
* corresponding to this token in the source text.
*
* Note:
* The difference between getEndOffset() and getStartOffset() may not be equal
* to strlen(Zend_Search_Lucene_Analysis_Token::getTermText()), as the term text may have been altered
* by a stemmer or some other filter.
*
* @return integer
*/
public function getStartOffset()
{
return $this->_startOffset;
}
/**
* Returns this Token's ending offset, one greater than the position of the
* last character corresponding to this token in the source text.
*
* @return integer
*/
public function getEndOffset()
{
return $this->_endOffset;
}
/**
* Returns this Token's lexical type. Defaults to 'word'.
*
* @return string
*/
public function getType()
{
return $this->_type;
}
}
|
