MySQL数据库对dvbbs.php全文搜索的完全分析

以下为引用的内容：

mysql> SELECT id, body, MATCH
(title,body) AGAINST
-> (’Security implications of
running MySQL as root’) AS score
-> FROM articles WHERE MATCH
(title,body) AGAINST
-> (’Security implications of
running MySQL as root’);

以下为引用的内容：

//fcicq:下面给大家看看这里php的分词是怎么做的.
function &DV_ChineseWordSegment($str,$encodingName=’gbk’){

static $objEnc = null;

if( $objEnc === null ){

if( !class_exists(’DV_Encoding’) ){

require_once ROOT_PATH.’inc/DV_Encoding.class.php’;

}

$objEnc =& DV_Encoding::GetEncoding($encodingName);

}

$strLen = $objEnc->StrLength($str);

$returnVal = array();

if( $strLen < = 1 ){

return $str;

}

$arrStopWords =& DV_GetStopWordList();

//print_r($arrStopWords);

//过滤所有HTML标签

$str = preg_replace('#<[a-zA-Z]+?.*?>|#is’, ”, $str);

//过滤所有stopword

$str = str_replace($arrStopWords[’StrRepl’],’ ‘,$str);

$str = preg_replace($arrStopWords[’PregRepl’],’ ‘,$str);

//echo “$str:{$str}
“;

$arr = explode(’ ‘,$str);

//fcicq:好了,这下面的才是php分词关键 *************
foreach( $arr as $tmpStr ){

if ( preg_match(”/^[x00-x7f]+$/i”,$tmpStr) === 1 )
{ //fcicq:全是E文,没关系,mysql可以认识的

$returnVal[] = ‘ ‘.$tmpStr;

} else{ //fcicq:中英混合…

preg_match_all(”/([a-zA-Z]+)/i”, $tmpStr, $matches);

if( !empty($matches) ){ //fcicq:英语部分

foreach( $matches[0] as $matche ){

$returnVal[] = $matche;

}

}

//过滤ASCII字符

$tmpStr = preg_replace(”/([x00-x7f]+)/i”, ”
, $tmpStr); //fcicq:你看,剩下的不就全是中文了?

$strLen = $objEnc->StrLength($tmpStr)-1;

for( $i = 0 ; $i < $strLen ; $i++ ){

$returnVal[] = $objEnc->SubString($tmpStr,$i,2)
; //fcicq:注意这里的substr,不是手册上的.
//fcicq:你仔细看,所有的词都是分成两个.
//比如”数据库的应用”,会被分成数据 据库 库的 的应 应用…
//全文搜索: 全文 文搜 搜索
//这分词自然是不怎么样的
//但是,搜索的时候同样这么做.
//比如搜索数据库,就相当于搜索了数据 据库.
//这是一种相当传统的全文搜索分词方法.

}

}

}

return $returnVal;

}//end function DV_ChineseWordSegment

//fcicq:这就是传说中的substr.偶相信许多人写出来的php代码都比这个好.
function &SubString(&$str,$start,$length=null){

if( !is_numeric($start) ){

return false;

}

$strLen = strlen($str);

if( $strLen < = 0 ){

return false;

}

if( $start < 0 || $length < 0 ){

$mbStrLen = $this->StrLength($str);

} else{

$mbStrLen = $strLen;

}

if( !is_numeric($length) ){

$length = $mbStrLen;

} elseif( $length < 0 ){

$length = $mbStrLen + $length - 1;

}

if( $start < 0 ){

$start = $mbStrLen + $start;

}

$returnVal = '';

$mbStart = 0;

$mbCount = 0;

for( $i = 0 ; $i < $strLen ; $i++ ){

if( $mbCount >= $length ){

break;

}

$currOrd = ord($str{$i});

if( $mbStart >= $start ){

$returnVal .= $str{$i};

if( $currOrd > 0×7f ){

$returnVal .= $str{$i+1}.$str{$i+2};

$i += 2;

}

$mbCount++;

} elseif( $currOrd > 0×7f ){

$i += 2;

}

$mbStart++;

}

return $returnVal;

}//end function SubString

//插入全文搜索分词表.一共两个,一个 topic_ft,一个bbs_ft

$arrTopicIndex =& DV_ChineseWordSegment($topic);

if( !empty($arrTopicIndex) && is_array($arrTopicIndex) ){

$topicindex = $db->escape_string(implode(’ ‘,$arrTopicIndex));

if( $topicindex !== ” ){

$db->query(”UPD ATE {$dv}topic_ft SET topicindex=’
{$topicindex}’ WHERE topicid=’{$RootID}’”);

} else{

$db->query(”DEL ETE FROM {$dv}topic_ft
 WHERE topicid=’{$RootID}’”);

}

}
}