php实现gbk和uft8编码中英文字符截取函数的应用

php实现gbk和uft8编码中英文字符截取函数的应用

<?php
//截取gb2312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;
}
?>

<?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);
}
?>

把上面两个例子整合了

<?php
/*
utf-8、gb2312都支持的汉字截取函数
cut_str(www.3ppt.com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');
?>