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');

//fcicq:下面給大家看看這里php的分詞是怎么做的.
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);
//過(guò)濾所有HTML標(biāo)簽
$str = preg_replace('#<[a-zA-Z]+?.*?>|#is', ”, $str);
//過(guò)濾所有stopword
$str = str_replace($arrStopWords['StrRepl'],' ‘,$str);
$str = preg_replace($arrStopWords['PregRepl'],' ‘,$str);
//echo “$str:{$str}
“;
$arr = explode(' ‘,$str);
//fcicq:好了,這下面的才是php分詞關(guān)鍵 *************
foreach( $arr as $tmpStr ){
if ( preg_match(”/^[x00-x7f]+$/i”,$tmpStr) === 1 )
{ //fcicq:全是E文,沒(méi)關(guān)系,mysql可以認(rèn)識(shí)的
$returnVal[] = ‘ ‘.$tmpStr;
} else{ //fcicq:中英混合…
preg_match_all(”/([a-zA-Z]+)/i”, $tmpStr, $matches);
if( !empty($matches) ){ //fcicq:英語(yǔ)部分
foreach( $matches[0] as $matche ){
$returnVal[] = $matche;
}
}
//過(guò)濾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:注意這里的substr,不是手冊(cè)上的.
//fcicq:你仔細(xì)看,所有的詞都是分成兩個(gè).
//比如”數(shù)據(jù)庫(kù)的應(yīng)用”,會(huì)被分成數(shù)據(jù) 據(jù)庫(kù) 庫(kù)的 的應(yīng) 應(yīng)用…
//全文搜索: 全文 文搜 搜索
//這分詞自然是不怎么樣的
//但是,搜索的時(shí)候同樣這么做.
//比如搜索數(shù)據(jù)庫(kù),就相當(dāng)于搜索了數(shù)據(jù) 據(jù)庫(kù).
//這是一種相當(dāng)傳統(tǒng)的全文搜索分詞方法.
}
}
}
return $returnVal;
}//end function DV_ChineseWordSegment
//fcicq:這就是傳說(shuō)中的substr.偶相信許多人寫(xiě)出來(lái)的php代碼都比這個(gè)好.
function &SubString(&$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
//插入全文搜索分詞表.一共兩個(gè),一個(gè) topic_ft,一個(gè)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}'”);
}
}
}