中文截取，支持gb2312,gbk,utf-8,big5

来源：互联网发布：素媛用什么软件看编辑：程序博客网时间：2024/05/22 06:47

/**
　* @todo 中文截取，支持gb2312,gbk,utf-8,big5
　*
　* @param string $str 要截取的字串
　* @param int $start 截取起始位置
　* @param int $length 截取长度
　* @param string $charset utf-8|gb2312|gbk|big5 编码
　* @param $suffix 是否加尾缀
　*/
function CsubStrPro($str, $start = 0, $length, $charset = "utf-8", $suffix = true)
{
if (function_exists ( "mb_substr" ))
return mb_substr ( $str, $start, $length, $charset );

    $re ['utf-8'] = "/[\x01-\x7f]|[\xc2-\xdf][\x80-\xbf]|[\xe0-\xef][\x80-\xbf]{2}|[\xf0-\xff][\x80-\xbf]{3}/";
    $re ['gb2312'] = "/[\x01-\x7f]|[\xb0-\xf7][\xa0-\xfe]/";
    $re ['gbk'] = "/[\x01-\x7f]|[\x81-\xfe][\x40-\xfe]/";
    $re ['big5'] = "/[\x01-\x7f]|[\x81-\xfe]([\x40-\x7e]|\xa1-\xfe])/";
    preg_match_all ( $re [$charset], $str, $match );
    $slice = join ( "", array_slice ( $match [0], $start, $length ) );
    if ($suffix)
        return $slice . "…";

return $slice;
}