| 12
 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
 
 |  
class Application_Analyzer_Accent extends Zend_Search_Lucene_Analysis_Analyzer_Common
{
    /**
     * Current char position in an UTF-8 stream
     *
     * @var integer
     */
    private $_position;
 
    /**
     * Current binary position in an UTF-8 stream
     *
     * @var integer
     */
    private $_bytePosition;
 
    /**
     * Object constructor
     *
     * @throws Zend_Search_Lucene_Exception
     */
    public function __construct()
    {
        if (@preg_match('/\pL/u', 'a') != 1) {
            // PCRE unicode support is turned off
            require_once 'Zend/Search/Lucene/Exception.php';
            throw new Zend_Search_Lucene_Exception('Utf8 analyzer needs PCRE unicode support to be enabled.');
        }
    }
 
    /**
     * Reset token stream
     */
    public function reset()
    {
        $this->_position     = 0;
        $this->_bytePosition = 0;
 
        // convert input into UTF-8
        if (strcasecmp($this->_encoding, 'utf8' ) != 0  &&
            strcasecmp($this->_encoding, 'utf-8') != 0 ) {
                $this->_input = iconv($this->_encoding, 'UTF-8', $this->_input);
                $this->_encoding = 'UTF-8';
        }
    }
 
    /**
     * Tokenization stream API
     * Get next token
     * Returns null at the end of stream
     *
     * @return Zend_Search_Lucene_Analysis_Token|null
     */
    public function nextToken()
    {
        if ($this->_input === null) {
            return null;
        }
 
        //$match = $this->deleteAccent($match);
        $this->_input = $this->deleteAccent($this->_input);
        $this->_input = strtolower($this->_input);
 
        do {
            if (! preg_match('/[\p{L}]+/u', $this->_input, $match, PREG_OFFSET_CAPTURE, $this->_bytePosition)) {
                // It covers both cases a) there are no matches (preg_match(...) === 0)
                // b) error occured (preg_match(...) === FALSE)
                return null;
            }
 
            // matched string
            $matchedWord = $match[0][0];
 
            // binary position of the matched word in the input stream
            $binStartPos = $match[0][1];
 
            // character position of the matched word in the input stream
            $startPos = $this->_position +
                        iconv_strlen(substr($this->_input,
                                            $this->_bytePosition,
                                            $binStartPos - $this->_bytePosition),
                                     'UTF-8');
            // character postion of the end of matched word in the input stream
            $endPos = $startPos + iconv_strlen($matchedWord, 'UTF-8');
 
            $this->_bytePosition = $binStartPos + strlen($matchedWord);
            $this->_position     = $endPos;
 
            $token = $this->normalize(new Zend_Search_Lucene_Analysis_Token($matchedWord, $startPos, $endPos));
        } while ($token === null); // try again if token is skipped
		//print_r($token);
        return $token;
    }
 
    private function deleteAccent($str)
    {
		return iconv('UTF-8', 'ASCII//TRANSLIT//IGNORE', $str);
    }
} | 
Partager