php多言語切り取り文字列関数

3212 ワード

<?php
header("Content-Type:text/html;charset=utf-8");
function msubstr($str, $start = 0, $length, $lenth2, $suffix = true){ 
//$length       ,$lenth2       $suffix       
$charset = 'utf-8'; 
if (LANG_SET != 'zh'){ 
    $length = $lenth2; 
} 
$str = preg_replace("/(\<[^\<]*\>|\r|
|\s|\[.+?\])/is", ' ', $str); if (function_exists("mb_substr")) $slice = mb_substr($str, $start, $length, $charset); elseif (function_exists('iconv_substr')) { $slice = iconv_substr($str, $start, $length, $charset); if (false === $slice) { $slice = ''; } } else { $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)); } $fix = ''; if (LANG_SET == 'zh') { $slice = str_replace(' ', '', $slice); if (strlen($slice) > $length) { $fix = '...'; } } else { if (strlen($str) > $lenth2) { $fix = '...'; } } return $suffix ? $slice . $fix : $slice; } $str = "dsd dsad dd ddsddsadsadsads "; echo msubstr($str,1,2,20,true); ?>