PHP截取中文字符串方法总结

function msubstr($str,$start,$len) {
$tmpstr = "";
$strlen = $start + $len;
for($i = 0; $i < $strlen; $i++) {
if(ord(substr($str,$i,1)) > 0xa0) {
$tmpstr .= substr($str,2);
$i++;
} else
$tmpstr .= substr($str,1);
}
return $tmpstr;
}

/******************************************************************
* PHP截取UTF-8字符串，解决半字符问题。
* 英文、数字（半角）为1字节（8位），中文（全角）为3字节
* @return 取出的字符串,当$len小于等于0时,会返回整个字符串
* @param $str 源字符串
* $len 左边的子串的长度
****************************************************************/
function utf_substr($str,$len)
{
for($i=0;$i<$len;$i++)
{
$temp_str=substr($str,1);
if(ord($temp_str) > 127)
{
$i++;
if($i<$len)
{
$new_str[]=substr($str,3);
$str=substr($str,3);
}
}
else
{
$new_str[]=substr($str,1);
$str=substr($str,1);
}
}
return join($new_str);
}
?>

<?
function cutstr($string,$length) {
preg_match_all("/[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]/",$string,$info);
for($i=0; $i<count($info[0]); $i++) {
$wordscut .= $info[0][$i];
$j = ord($info[0][$i]) > 127 ? $j + 2 : $j + 1;
if ($j > $length - 3) {
return $wordscut." ...";
}
}
return join('',$info[0]);
}
$string="242432反对感是456犯得上广泛大使馆地方7890";
for($i=0;$i<strlen($string);$i++)
{
echo cutstr($string,$i)."<br>";
}
?>

<?php // Cut_Str;
//$sourcestr 是要处理的字符串
//$cutlength 为截取的长度(即字数)
function cut_str($sourcestr,$cutlength)
{
$returnstr='';
$i=0;
$n=0;
$str_length=strlen($sourcestr);//字符串的字节数
while (($n<$cutlength) and ($i<=$str_length))
{
$temp_str=substr($sourcestr,1);
$ascnum=Ord($temp_str);//得到字符串中第$i位字符的ascii码
if ($ascnum>=224) //如果ASCII位高与224，
{
$returnstr=$returnstr.substr($sourcestr,3); //根据UTF-8编码规范，将3个连续的字符计为单个字符
$i=$i+3; //实际Byte计为3
$n++; //字串长度计1
}
elseif ($ascnum>=192) //如果ASCII位高与192，
{
$returnstr=$returnstr.substr($sourcestr,2); //根据UTF-8编码规范，将2个连续的字符计为单个字符
$i=$i+2; //实际Byte计为2
$n++; //字串长度计1
}
elseif ($ascnum>=65 && $ascnum<=90) //如果是大写字母，
{
$returnstr=$returnstr.substr($sourcestr,1);
$i=$i+1; //实际的Byte数仍计1个
$n++; //但考虑整体美观，大写字母计成一个高位字符
}
else //其他情况下，包括小写字母和半角标点符号，
{
$returnstr=$returnstr.substr($sourcestr,1);
$i=$i+1; //实际的Byte数计1个
$n=$n+0.5; //小写字母和半角标点等与半个高位字符宽...
}
}
if ($str_length>$cutlength){
$returnstr = $returnstr . "...";//超过长度时在尾处加上省略号
}
return $returnstr;

}

function FSubstr($title,$len="",$magic=true)
{

if($len == "") $len=strlen($title);

if($start != 0)
{
$startv = ord(substr($title,1));
if($startv >= 128)
{
if($startv < 192)
{
for($i=$start-1;$i>0;$i--)
{
$tempv = ord(substr($title,1));
if($tempv >= 192) break;
}
$start = $i;
}
}
}

if(strlen($title)<=$len) return substr($title,$len);

$alen = 0;
$blen = 0;

$realnum = 0;

for($i=$start;$i<strlen($title);$i++)
{
$ctype = 0;
$cstep = 0;

$cur = substr($title,1);
if($cur == "&")
{
if(substr($title,4) == "&lt;")
{
$cstep = 4;
$length += 4;
$i += 3;
$realnum ++;
if($magic)
{
$alen ++;
}
}
else if(substr($title,4) == "&gt;")
{
$cstep = 4;
$length += 4;
$i += 3;
$realnum ++;
if($magic)
{
$alen ++;
}
}
else if(substr($title,5) == "&amp;")
{
$cstep = 5;
$length += 5;
$i += 4;
$realnum ++;
if($magic)
{
$alen ++;
}
}
else if(substr($title,6) == "&quot;")
{
$cstep = 6;
$length += 6;
$i += 5;
$realnum ++;
if($magic)
{
$alen ++;
}
}
else if(preg_match("/&#(d+);?/i",substr($title,8),$match))
{
$cstep = strlen($match[0]);
$length += strlen($match[0]);
$i += strlen($match[0])-1;
$realnum ++;
if($magic)
{
$blen ++;
$ctype = 1;
}
}
}else{
if(ord($cur)>=252)
{
$cstep = 6;
$length += 6;
$i += 5;
$realnum ++;
if($magic)
{
$blen ++;
$ctype = 1;
}
}elseif(ord($cur)>=248){
$cstep = 5;
$length += 5;
$i += 4;
$realnum ++;
if($magic)
{
$ctype = 1;
$blen ++;
}
}elseif(ord($cur)>=240){
$cstep = 4;
$length += 4;
$i += 3;
$realnum ++;
if($magic)
{
$blen ++;
$ctype = 1;
}
}elseif(ord($cur)>=224){
$cstep = 3;
$length += 3;
$i += 2;
$realnum ++;
if($magic)
{
$ctype = 1;
$blen ++;
}
}elseif(ord($cur)>=192){
$cstep = 2;
$length += 2;
$i += 1;
$realnum ++;
if($magic)
{
$blen ++;
$ctype = 1;
}
}elseif(ord($cur)>=128){
$length += 1;
}else{
$cstep = 1;
$length +=1;
$realnum ++;
if($magic)
{
if(ord($cur) >= 65 && ord($cur) <= 90)
{
$blen++;
}else{
$alen++;
}
}
}
}

if($magic)
{
if(($blen*2+$alen) == ($len*2)) break;
if(($blen*2+$alen) == ($len*2+1))
{
if($ctype == 1)
{
$length -= $cstep;
break;
}else{
break;
}
}
}else{
if($realnum == $len) break;
}
}

unset($cur);
unset($alen);
unset($blen);
unset($realnum);
unset($ctype);
unset($cstep);

return substr($title,$length);
}