| 1 |
lars |
1 |
<?php
|
|
|
2 |
/**
|
|
|
3 |
* Zend Framework
|
|
|
4 |
*
|
|
|
5 |
* LICENSE
|
|
|
6 |
*
|
|
|
7 |
* This source file is subject to version 1.0 of the Zend Framework
|
|
|
8 |
* license, that is bundled with this package in the file LICENSE, and
|
|
|
9 |
* is available through the world-wide-web at the following URL:
|
|
|
10 |
* http://www.zend.com/license/framework/1_0.txt. If you did not receive
|
|
|
11 |
* a copy of the Zend Framework license and are unable to obtain it
|
|
|
12 |
* through the world-wide-web, please send a note to license@zend.com
|
|
|
13 |
* so we can mail you a copy immediately.
|
|
|
14 |
*
|
|
|
15 |
* @package Zend_Search_Lucene
|
|
|
16 |
* @subpackage document
|
|
|
17 |
* @copyright Copyright (c) 2005-2006 Zend Technologies USA Inc. (http://www.zend.com)
|
|
|
18 |
* @license http://www.zend.com/license/framework/1_0.txt Zend Framework License version 1.0
|
|
|
19 |
*/
|
|
|
20 |
|
|
|
21 |
|
|
|
22 |
/**
|
|
|
23 |
*
|
|
|
24 |
* @package Zend_Search_Lucene
|
|
|
25 |
* @subpackage Analysis
|
|
|
26 |
* @copyright Copyright (c) 2005-2006 Zend Technologies USA Inc. (http://www.zend.com)
|
|
|
27 |
* @license http://www.zend.com/license/framework/1_0.txt Zend Framework License version 1.0
|
|
|
28 |
*/
|
|
|
29 |
class Zend_Search_Lucene_Analysis_Token
|
|
|
30 |
{
|
|
|
31 |
/**
|
|
|
32 |
* The text of the term.
|
|
|
33 |
*
|
|
|
34 |
* @var string
|
|
|
35 |
*/
|
|
|
36 |
private $_termText;
|
|
|
37 |
|
|
|
38 |
/**
|
|
|
39 |
* Start in source text.
|
|
|
40 |
*
|
|
|
41 |
* @var integer
|
|
|
42 |
*/
|
|
|
43 |
private $_startOffset;
|
|
|
44 |
|
|
|
45 |
/**
|
|
|
46 |
* End in source text
|
|
|
47 |
*
|
|
|
48 |
* @var integer
|
|
|
49 |
*/
|
|
|
50 |
private $_endOffset;
|
|
|
51 |
|
|
|
52 |
/**
|
|
|
53 |
* Lexical type.
|
|
|
54 |
*
|
|
|
55 |
* @var string
|
|
|
56 |
*/
|
|
|
57 |
private $_type;
|
|
|
58 |
|
|
|
59 |
/**
|
|
|
60 |
* The position of this token relative to the previous Token.
|
|
|
61 |
*
|
|
|
62 |
* The default value is one.
|
|
|
63 |
*
|
|
|
64 |
* Some common uses for this are:
|
|
|
65 |
* Set it to zero to put multiple terms in the same position. This is
|
|
|
66 |
* useful if, e.g., a word has multiple stems. Searches for phrases
|
|
|
67 |
* including either stem will match. In this case, all but the first stem's
|
|
|
68 |
* increment should be set to zero: the increment of the first instance
|
|
|
69 |
* should be one. Repeating a token with an increment of zero can also be
|
|
|
70 |
* used to boost the scores of matches on that token.
|
|
|
71 |
*
|
|
|
72 |
* Set it to values greater than one to inhibit exact phrase matches.
|
|
|
73 |
* If, for example, one does not want phrases to match across removed stop
|
|
|
74 |
* words, then one could build a stop word filter that removes stop words and
|
|
|
75 |
* also sets the increment to the number of stop words removed before each
|
|
|
76 |
* non-stop word. Then exact phrase queries will only match when the terms
|
|
|
77 |
* occur with no intervening stop words.
|
|
|
78 |
*
|
|
|
79 |
* @var integer
|
|
|
80 |
*/
|
|
|
81 |
private $_positionIncrement;
|
|
|
82 |
|
|
|
83 |
|
|
|
84 |
/**
|
|
|
85 |
* Object constructor
|
|
|
86 |
*
|
|
|
87 |
* @param string $text
|
|
|
88 |
* @param integer $start
|
|
|
89 |
* @param integer $end
|
|
|
90 |
* @param string $type
|
|
|
91 |
*/
|
|
|
92 |
public function __construct($text, $start, $end, $type = 'word' )
|
|
|
93 |
{
|
|
|
94 |
$this->_termText = $text;
|
|
|
95 |
$this->_startOffset = $start;
|
|
|
96 |
$this->_endOffset = $end;
|
|
|
97 |
$this->_type = $type;
|
|
|
98 |
|
|
|
99 |
$this->_positionIncrement = 1;
|
|
|
100 |
}
|
|
|
101 |
|
|
|
102 |
|
|
|
103 |
/**
|
|
|
104 |
* positionIncrement setter
|
|
|
105 |
*
|
|
|
106 |
* @param integer $positionIncrement
|
|
|
107 |
*/
|
|
|
108 |
public function setPositionIncrement($positionIncrement)
|
|
|
109 |
{
|
|
|
110 |
$this->_positionIncrement = $positionIncrement;
|
|
|
111 |
}
|
|
|
112 |
|
|
|
113 |
/**
|
|
|
114 |
* Returns the position increment of this Token.
|
|
|
115 |
*
|
|
|
116 |
* @return integer
|
|
|
117 |
*/
|
|
|
118 |
public function getPositionIncrement()
|
|
|
119 |
{
|
|
|
120 |
return $this->_positionIncrement;
|
|
|
121 |
}
|
|
|
122 |
|
|
|
123 |
/**
|
|
|
124 |
* Returns the Token's term text.
|
|
|
125 |
*
|
|
|
126 |
* @return string
|
|
|
127 |
*/
|
|
|
128 |
public function getTermText()
|
|
|
129 |
{
|
|
|
130 |
return $this->_termText;
|
|
|
131 |
}
|
|
|
132 |
|
|
|
133 |
/**
|
|
|
134 |
* Returns this Token's starting offset, the position of the first character
|
|
|
135 |
* corresponding to this token in the source text.
|
|
|
136 |
*
|
|
|
137 |
* Note:
|
|
|
138 |
* The difference between getEndOffset() and getStartOffset() may not be equal
|
|
|
139 |
* to strlen(Zend_Search_Lucene_Analysis_Token::getTermText()), as the term text may have been altered
|
|
|
140 |
* by a stemmer or some other filter.
|
|
|
141 |
*
|
|
|
142 |
* @return integer
|
|
|
143 |
*/
|
|
|
144 |
public function getStartOffset()
|
|
|
145 |
{
|
|
|
146 |
return $this->_startOffset;
|
|
|
147 |
}
|
|
|
148 |
|
|
|
149 |
/**
|
|
|
150 |
* Returns this Token's ending offset, one greater than the position of the
|
|
|
151 |
* last character corresponding to this token in the source text.
|
|
|
152 |
*
|
|
|
153 |
* @return integer
|
|
|
154 |
*/
|
|
|
155 |
public function getEndOffset()
|
|
|
156 |
{
|
|
|
157 |
return $this->_endOffset;
|
|
|
158 |
}
|
|
|
159 |
|
|
|
160 |
/**
|
|
|
161 |
* Returns this Token's lexical type. Defaults to 'word'.
|
|
|
162 |
*
|
|
|
163 |
* @return string
|
|
|
164 |
*/
|
|
|
165 |
public function getType()
|
|
|
166 |
{
|
|
|
167 |
return $this->_type;
|
|
|
168 |
}
|
|
|
169 |
}
|
|
|
170 |
|