PHP中文分词
<div id="cnblogs_post_body">最常见的词语二分法:<div class="cnblogs_Highlighter">$str = '这是我的网站www.7di.net！';//$str = iconv('GB2312','UTF-8',$str);$result = spStr($str);print_r($result); /*** UTF-8版 中文二元分词*/function spStr($str){ $cstr = array(); $search = array(",", "/", "\\", ".", ";", ":", "\"", "!", "~", "`", "^", "(", ")", "?", "-", "\t", "\n", "'", "<", ">", "\r", "\r\n", "{1}quot;", "&", "%", "#", "@", "+", "=", "{", "}", "[", "]", "：", "）", "（", "．", "。", "，", "！", "；", "&ldquo;", "&rdquo;", "&lsquo;", "&rsquo;", "［", "］", "、", "&mdash;", " ", "《", "》", "－", "&hellip;", "【", "】",); $str = str_replace($search, " ", $str); preg_match_all("/+/", $str, $estr); preg_match_all("/+/", $str, $nstr); $str = preg_replace("/+/", " ", $str); $str = preg_replace("/\s{2,}/", " ", $str); $str = explode(" ", trim($str)); foreach ($str as $s) { $l = strlen($s); $bf = null; for ($i= 0; $i< $l; $i=$i+3) { $ns1 = $s{$i}.$s{$i+1}.$s{$i+2}; if (isset($s{$i+3})) { $ns2 = $s{$i+3}.$s{$i+4}.$s{$i+5}; if (preg_match("/[\x80-\xff]{3}/",$ns2)) $cstr[] = $ns1.$ns2; } else if ($i == 0) { $cstr[] = $ns1; } } } $estr = isset($estr)?$estr:array(); $nstr = isset($nstr)?$nstr:array(); return array_merge($nstr,$estr,$cstr);}
页:
[1]