以下代码试用于GB2312编码,截取中文字符串是PHP中一个头疼的问题,解决方法是根据值是否大于等于128来判断是否是双字节字符,以避免出现乱码的情况。但中英文混合、特殊符号等问题总是存在,现在写一个比较全面的,仅供参考:
1. len 参数以中文字符为标准,1len等于2个英文字符,为了形式上好看些
2. 如果将magic参数设为false,则中文和英文同等看待,取绝对的字符数
3. 特别适用于用htmlspecialchars()进行过编码的字符串
4. 能正确处理GB2312中实体字符模式(𖰰)
function FSubstr($title,$start,$len="",$magic=true)
{
/**
* powered by Smartpig
*
mailto:d.einstein@263.net */
$length = 0;
if($len == "") $len = strlen($title);
//判断起始为不正确位置
if($start > 0)
{
$cnum = 0;
for($i=0;$i<$start;$i++)
{
if(ord(substr($title,$i,1)) >= 128) $cnum ++;
}
if($cnum%2 != 0) $start--;
unset($cnum);
}
if(strlen($title)<=$len) return substr($title,$start,$len);
$alen = 0;
$blen = 0;
$realnum = 0;
for($i=$start;$i<strlen($title);$i++)
{
$ctype = 0;
$cstep = 0;
$cur = substr($title,$i,1);
if($cur == "&")
{
if(substr($title,$i,4) == "<")
{
$cstep = 4;
$length += 4;
$i += 3;
$realnum ++;
if($magic)
{
$alen ++;
}
}
else if(substr($title,$i,4) == ">")
{
$cstep = 4;
$length += 4;
$i += 3;
$realnum ++;
if($magic)
{
$alen ++;
}
}
else if(substr($title,$i,5) == "&")
{
$cstep = 5;
$length += 5;
$i += 4;
$realnum ++;
if($magic)
{
$alen ++;
}
}
else if(substr($title,$i,6) == """)
{
$cstep = 6;
$length += 6;
$i += 5;
$realnum ++;
if($magic)
{
$alen ++;
}
}
else if(substr($title,$i,6) == "'")
{
$cstep = 6;
$length += 6;
$i += 5;
$realnum ++;
if($magic)
{
$alen ++;
}
}
else if(preg_match("/&#(\d+);/i",substr($title,$i,8),$match))
{
$cstep = strlen($match[0]);
$length += strlen($match[0]);
$i += strlen($match[0])-1;
$realnum ++;
if($magic)
{
$blen ++;
$ctype = 1;
}
}
}else{
if(ord($cur)>=128)
{
$cstep = 2;
$length += 2;
$i += 1;
$realnum ++;
if($magic)
{
$blen ++;
$ctype = 1;
}
}else{
$cstep = 1;
$length +=1;
$realnum ++;
if($magic)
{
$alen++;
}
}
}
if($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,$start,$length);
}