1 <?php

     2 /**

     3  * Zend Framework

     4  *

     5  * LICENSE

     6  *

     7  * This source file is subject to the new BSD license that is bundled

     8  * with this package in the file LICENSE.txt.

     9  * It is also available through the world-wide-web at this URL:

    10  * http://framework.zend.com/license/new-bsd

    11  * If you did not receive a copy of the license and are unable to

    12  * obtain it through the world-wide-web, please send an email

    13  * to license@zend.com so we can send you a copy immediately.

    14  *

    15  * @category   Zend

    16  * @package    Zend_Search_Lucene

    17  * @subpackage Analysis

    18  * @copyright  Copyright (c) 2005-2010 Zend Technologies USA Inc. (http://www.zend.com)

    19  * @license    http://framework.zend.com/license/new-bsd     New BSD License

    20  * @version    $Id: Token.php 20096 2010-01-06 02:05:09Z bkarwin $

    21  */

    22 

    23 

    24 /**

    25  * @category   Zend

    26  * @package    Zend_Search_Lucene

    27  * @subpackage Analysis

    28  * @copyright  Copyright (c) 2005-2010 Zend Technologies USA Inc. (http://www.zend.com)

    29  * @license    http://framework.zend.com/license/new-bsd     New BSD License

    30  */

    31 class Zend_Search_Lucene_Analysis_Token

    32 {

    33     /**

    34      * The text of the term.

    35      *

    36      * @var string

    37      */

    38     private $_termText;

    39 

    40     /**

    41      * Start in source text.

    42      *

    43      * @var integer

    44      */

    45     private $_startOffset;

    46 

    47     /**

    48      * End in source text

    49      *

    50      * @var integer

    51      */

    52     private $_endOffset;

    53 

    54     /**

    55      * The position of this token relative to the previous Token.

    56      *

    57      * The default value is one.

    58      *

    59      * Some common uses for this are:

    60      * Set it to zero to put multiple terms in the same position.  This is

    61      * useful if, e.g., a word has multiple stems.  Searches for phrases

    62      * including either stem will match.  In this case, all but the first stem's

    63      * increment should be set to zero: the increment of the first instance

    64      * should be one.  Repeating a token with an increment of zero can also be

    65      * used to boost the scores of matches on that token.

    66      *

    67      * Set it to values greater than one to inhibit exact phrase matches.

    68      * If, for example, one does not want phrases to match across removed stop

    69      * words, then one could build a stop word filter that removes stop words and

    70      * also sets the increment to the number of stop words removed before each

    71      * non-stop word.  Then exact phrase queries will only match when the terms

    72      * occur with no intervening stop words.

    73      *

    74      * @var integer

    75      */

    76     private $_positionIncrement;

    77 

    78 

    79     /**

    80      * Object constructor

    81      *

    82      * @param string  $text

    83      * @param integer $start

    84      * @param integer $end

    85      * @param string  $type

    86      */

    87     public function __construct($text, $start, $end)

    88     {

    89         $this->_termText    = $text;

    90         $this->_startOffset = $start;

    91         $this->_endOffset   = $end;

    92 

    93         $this->_positionIncrement = 1;

    94     }

    95 

    96 

    97     /**

    98      * positionIncrement setter

    99      *

   100      * @param integer $positionIncrement

   101      */

   102     public function setPositionIncrement($positionIncrement)

   103     {

   104         $this->_positionIncrement = $positionIncrement;

   105     }

   106 

   107     /**

   108      * Returns the position increment of this Token.

   109      *

   110      * @return integer

   111      */

   112     public function getPositionIncrement()

   113     {

   114         return $this->_positionIncrement;

   115     }

   116 

   117     /**

   118      * Returns the Token's term text.

   119      *

   120      * @return string

   121      */

   122     public function getTermText()

   123     {

   124         return $this->_termText;

   125     }

   126 

   127     /**

   128      * Returns this Token's starting offset, the position of the first character

   129      * corresponding to this token in the source text.

   130      *

   131      * Note:

   132      * The difference between getEndOffset() and getStartOffset() may not be equal

   133      * to strlen(Zend_Search_Lucene_Analysis_Token::getTermText()), as the term text may have been altered

   134      * by a stemmer or some other filter.

   135      *

   136      * @return integer

   137      */

   138     public function getStartOffset()

   139     {

   140         return $this->_startOffset;

   141     }

   142 

   143     /**

   144      * Returns this Token's ending offset, one greater than the position of the

   145      * last character corresponding to this token in the source text.

   146      *

   147      * @return integer

   148      */

   149     public function getEndOffset()

   150     {

   151         return $this->_endOffset;

   152     }

   153 }

   154