共享:在UTF-8编码情况下PHP截取中文字符串的代码

本文链接：https://blog.csdn.net/d_einstein/article/details/666853

以下程序主要处理在UTF-8编码下PHP程序截取中文、日文、韩文等字符串，程序基本逻辑与之前写过的PHP处理GB2312下中文字符串的代码类似，主要不同在于UTF-8对于中文、日文字符的编码字节数不同，具体可以参考unicode 编码的说明。不多做解释，希望能对大家有所帮助！程序仅供参考，细节和性能方面不做推敲。转载请注明出处，多谢！

function FSubstr($title,$start,$len="",$magic=true)
{
/**
  *  powered by Smartpig
  *  mailto:d.einstein@263.net
  */

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

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

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)
    {
     $alen ++;
    }
   }
   else if(preg_match("/&#(/d+);?/i",substr($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)>=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($title,$start,$length);
}