php分词搜索数据库,MySQL中文全文搜索：PHP简单中文分词函数

function string2words($s,$return_string = true,$encode64 = true)

{

$re = '';

//匹配汉字

if (preg_match_all("/([x{4e00}-x{9fff}]{2,})/u",$s,$ms))

{

foreach($ms[0] as $w)

{

//关键部分：分词

$l = strlen($w)/3;

for($i=0;$i

{

$wi = substr($w,$i*3,6);

if (strlen($wi) > 3)

{

$re .= ($encode64)?' '.str_replace(',','@',base64_encode($wi)):' '.$wi;

}

}

}

}

//匹配数字

if (preg_match_all("/(d+[.]?d+)/",$s,$ms))

{

foreach($ms[0] as $wi)

{

if(strlen($wi) >= 2)

{

$re .= ($encode64)?' '.str_replace(',','@',base64_encode($wi)):' '.$wi;

}

}

$s = preg_replace("/(d+[.]?d+)/",' ',$s);

}

//去掉所有双字节字符

$s = preg_replace("/([^x{00}-x{ff}]+)/u",' ',$s);

$re = $s.' '.$re;

if (!$return_string)

{

$re = preg_replace("/([^d])([,.-?n])([^d])/",'$1 $3',$re);

$re = trim(preg_replace("/[s]{2,}/",' ',$re));

$arr = explode(' ',$re);

$re = array();

foreach($arr as $a)

{

if (strlen($a) >= 2) $re[] = $a;

}

return $re;

}

else

{

$re = trim(preg_replace("/[s,.]{2,}/",' ',$re));

return $re;

}

}