Home >Backend Development >PHP Tutorial >PHP interception Chinese string function ~ including GB2312 and UT-8_PHP tutorial
/*
Chinese character interception function supported by Utf-8 and gb2312
cut_str(string, cut length, starting length, encoding);
The encoding defaults to utf-8
Start length defaults to 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;
}
}
$str = "The string that abcd needs to intercept";
echo cut_str($str, 8, 0, 'gb2312');
?>
//Intercept Chinese string
//Support GB2312
Function mysubstr($str, $start, $len) {
$tmpstr = "";
$strlen = $start + $len;
for($i = 0; $i < $strlen; $i++) {
$tmpstr .= substr($str, $i, 2);
$i++;
} else
$tmpstr .= substr($str, $i, 1);
}
return $tmpstr;
}
?>
//Intercept utf8 string
function utf8Substr($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);
}
?>
Excerpted from Internet Marketing Blog