1. 适用于GB2312中文字符串
<?php //截取中文字符串 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 $tmpstr; } ?>
2. 适用于utf8
<?php //截取utf8字符串 function utf8Substr($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); } ?>
3。全部都适用
function csubstr($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 $slice; }
4. BugFree 的字符截取函数
<?php function sysSubStr($String,$Length,$Append = false) { if (strlen($String) <= $Length ) { return $String; } else { $I = 0; while ($I < $Length) { $StringTMP = substr($String,$I,1); if ( ord($StringTMP) >=224 ) { $StringTMP = substr($String,$I,3); $I = $I + 3; } elseif( ord($StringTMP) >=192 ) { $StringTMP = substr($String,$I,2); $I = $I + 2; } else { $I = $I + 1; } $StringLast[] = $StringTMP; } $StringLast = implode("",$StringLast); if($Append) { $StringLast .= "..."; } return $StringLast; } }$String = "www.at0915.cn"; $Length = "18"; $Append = false; echo sysSubStr($String,$Length,$Append); ?>
The above is the detailed content of Summary of Chinese string interception function code examples suitable for different encodings. For more information, please follow other related articles on the PHP Chinese website!