PHP 截取字符串专题集合

1、UTF-8、GB2312都支持的汉字截取函数


代码如下:

<?php
/*
Utf-8、gb2312都支持的汉字截取函数
cut_str(字符串, 截取长度, 开始长度, 编码);
编码默认为 utf-8
开始长度默认为 0
*/
function cut_str($string, $sublen, $start = 0, $code = 'UTF-8')
{
if($code == 'UTF-8')
{
$pa = "/[\x01-\x7f]|[\xc2-\xdf][\x80-\xbf]|\xe0[\xa0-\xbf][\x80-\xbf]|[\xe1-\xef][\x80-\xbf][\x80-\xbf]|\xf0[\x90-\xbf][\x80-\xbf][\x80-\xbf]|[\xf1-\xf7][\x80-\xbf][\x80-\xbf][\x80-\xbf]/";
preg_match_all($pa, $string, $t_string);
if(count($t_string[0]) - $start > $sublen) return join('', array_slice($t_string[0], $start, $sublen))."…";
return join('', array_slice($t_string[0], $start, $sublen));
}
else
{
$start = $start*2;
$sublen = $sublen*2;
$strlen = strlen($string);
$tmpstr = '';
for($i=0; $i< $strlen; $i++)
{
if($i>=$start && $i< ($start+$sublen))
{
if(ord(substr($string, $i, 1))>129)
{
$tmpstr.= substr($string, $i, 2);
}
else
{
$tmpstr.= substr($string, $i, 1);
}
}
if(ord(substr($string, $i, 1))>129) $i++;
}
if(strlen($tmpstr)< $strlen ) $tmpstr.= "…";
return $tmpstr;
}
}
$str = "abcd需要截取的字符串";
echo cut_str($str, 8, 0, 'gb2312');
?>

2、截取utf8编码的多字节字符串


代码如下:

<?php
//截取utf8字符串
function utf8Substr($str, $from, $len)
{
return preg_replace('#^(?:[\x00-\x7F]|[\xC0-\xFF][\x80-\xBF]+){0,'.$from.'}'.
'((?:[\x00-\x7F]|[\xC0-\xFF][\x80-\xBF]+){0,'.$len.'}).*#s',
'$1',$str);
}
?>

3、截取GB2312中文字符串


代码如下:

<?php
//截取中文字符串
function mysubstr($str, $start, $len) {
$tmpstr = "";
$strlen = $start + $len;
for($i = 0; $i < $strlen; $i++) {
if(ord(substr($str, $i, 1)) > 0xa0) {
$tmpstr .= substr($str, $i, 2);
$i++;
} else
$tmpstr .= substr($str, $i, 1);
}
return $tmpstr;
}
?>

4、BugFree 的字符截取函数


代码如下:

<?php
/**
* @package BugFree
* @version $Id: FunctionsMain.inc.php,v 1.32 2005/09/24 11:38:37 wwccss Exp $
*
*
* Return part of a string(Enhance the function substr())
*
* @param string $String the string to cut.
* @param int $Length the length of returned string.
* @param booble $Append whether append "…": false|true
* @return string the cutted string.
*/
function sysSubStr($String,$Length,$Append = false)
{
if (strlen($String) < = $Length )
{
return $String;
}
else
{
$I = 0;
while ($I < $Length)
{
$StringTMP = substr($String,$I,1);
if ( ord($StringTMP) >=224 )
{
$StringTMP = substr($String,$I,3);
$I = $I + 3;
}
elseif( ord($StringTMP) >=192 )
{
$StringTMP = substr($String,$I,2);
$I = $I + 2;
}
else
{
$I = $I + 1;
}
$StringLast[] = $StringTMP;
}
$StringLast = implode("",$StringLast);
if($Append)
{
$StringLast .= "…";
}
return $StringLast;
}
}
$String = "http://www.jb51.net — 简单、精彩、通用";
$Length = "18";
$Append = false;
echo sysSubStr($String,$Length,$Append);
?>

dedecms中的截取代码
这是从dedecms直接拿的代码，大家可以稍作修改即可。


代码如下:

//中文截取2，单字节截取模式
//如果是request的内容，必须使用这个函数
function cn_substrR($str,$slen,$startdd=0)
{
$str = cn_substr(stripslashes($str),$slen,$startdd);
return addslashes($str);
}
//中文截取2，单字节截取模式
function cn_substr($str,$slen,$startdd=0)
{
global $cfg_soft_lang;
if($cfg_soft_lang=='utf-8')
{
return cn_substr_utf8($str,$slen,$startdd);
}
$restr = '';
$c = '';
$str_len = strlen($str);
if($str_len < $startdd+1)
{
return '';
}
if($str_len < $startdd + $slen || $slen==0)
{
$slen = $str_len - $startdd;
}
$enddd = $startdd + $slen - 1;
for($i=0;$i<$str_len;$i++)
{
if($startdd==0)
{
$restr .= $c;
}
else if($i > $startdd)
{
$restr .= $c;
}
if(ord($str[$i])>0x80)
{
if($str_len>$i+1)
{
$c = $str[$i].$str[$i+1];
}
$i++;
}
else
{
$c = $str[$i];
}
if($i >= $enddd)
{
if(strlen($restr)+strlen($c)>$slen)
{
break;
}
else
{
$restr .= $c;
break;
}
}
}
return $restr;
}
//utf-8中文截取，单字节截取模式
function cn_substr_utf8($str, $length, $start=0)
{
if(strlen($str) < $start+1)
{
return '';
}
preg_match_all("/./su", $str, $ar);
$str = '';
$tstr = '';
//为了兼容mysql4.1以下版本,与数据库varchar一致,这里使用按字节截取
for($i=0; isset($ar[0][$i]); $i++)
{
if(strlen($tstr) < $start)
{
$tstr .= $ar[0][$i];
}
else
{
if(strlen($str) < $length + strlen($ar[0][$i]) )
{
$str .= $ar[0][$i];
}
else
{
break;
}
}
}
return $str;
}

phpcms中的字符串截取代码:


代码如下:

function str_cut($string, $length, $dot = '...')
{
$strlen = strlen($string);
if($strlen <= $length) return $string;
$string = str_replace(array(' ', '&', '"', ''', '“', '”', '—', '<', '>', '·', '…'), array(' ', '&', '"', "'", '“', '”', '—', '<', '>', '·', '…'), $string);
$strcut = '';
if(strtolower(CHARSET) == 'utf-8')
{
$n = $tn = $noc = 0;
while($n < $strlen)
{
$t = ord($string[$n]);
if($t == 9 || $t == 10 || (32 <= $t && $t <= 126)) {
$tn = 1; $n++; $noc++;
} elseif(194 <= $t && $t <= 223) {
$tn = 2; $n += 2; $noc += 2;
} elseif(224 <= $t && $t < 239) {
$tn = 3; $n += 3; $noc += 2;
} elseif(240 <= $t && $t <= 247) {
$tn = 4; $n += 4; $noc += 2;
} elseif(248 <= $t && $t <= 251) {
$tn = 5; $n += 5; $noc += 2;
} elseif($t == 252 || $t == 253) {
$tn = 6; $n += 6; $noc += 2;
} else {
$n++;
}
if($noc >= $length) break;
}
if($noc > $length) $n -= $tn;
$strcut = substr($string, 0, $n);
}
else
{
$dotlen = strlen($dot);
$maxi = $length - $dotlen - 1;
for($i = 0; $i < $maxi; $i++)
{
$strcut .= ord($string[$i]) > 127 ? $string[$i].$string[++$i] : $string[$i];
}
}
$strcut = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $strcut);
return $strcut.$dot;
}