本文实例讲述了php自定义中文字符串截取函数substr_for_gb2312及substr_for_utf8用法。分享给大家供大家参考,具体如下:
/**gb2312中文字符串截取 */function substr_for_gb2312($str,$start,$len=null) { $totlelength = strlen($str); //特例情况 if ($len == null) $len = $totlelength; if ($len ==0) return ""; if ($len >= $totlelength && $start == 0 ) return $str; if ($start > $totlelength) return ""; //分析$start if ($start < 0 ) //$start<0时,转化为$start>0时的定位. { if ( abs($start) >= $totlelength ) $start = 0; else $start = $totlelength - abs($start); } //确定起始位置,当起始位拆分某汉字时,返回值包含此汉字. if ($start > 0) { $i = $start-1; $flag = -1; while ($i >= 0) { if ( ord(substr($str,$i,1)) > 160) { $flag = -1*$flag; } else break; $i--; } if($flag==1) { $start = $start - 1; $len++; //保证不位移. } } $str = substr($str,$start);//截除字符串$str的$start位前的字符 $totlelength = strlen($str); //确定结束位置,当结束位拆分某汉字时,返回值不包含此汉字. if ($len<0) $len = $totlelength - abs($len); if ($len <= 0) return ""; $i=min($len,$totlelength); $i--; $flag = -1; while ($i >= 0) { if (ord(substr($str,$i,1))>160) { $flag=-1*$flag; } else break; $i--; } if($flag == 1) $len=$len-1; $subit=substr($str,0,$len); return $subit; }/******************************************************************* PHP截取UTF-8字符串,解决半字符问题。* 英文、数字(半角)为1字节(8位),中文(全角)为3字节* @return 取出的字符串, 当$len小于等于0时, 会返回整个字符串* @param $str 源字符串* $len 左边的子串的长度****************************************************************/function substr_for_utf($str,$len){for($i=0;$i<$len;$i++){$temp_str=substr($str,0,1);if(ord($temp_str) > 127){$i++;if($i<$len){$new_str[]=substr($str,0,3);$str=substr($str,3);}}else{$new_str[]=substr($str,0,1);$str=substr($str,1);}}return join($new_str);}?>/*带start位置的utf8截取函数*/function utf8_substr($string, $start, $length) { preg_match_all ('/[/x00-/x7F]|[/xC2-/xDF][/x80-/xBF]|[/xE0-/xEF][/x80-/xBF][/x80-/xBF]|[/xF0-/xF4][/x80-/xBF][/x80-/xBF][/x80-/xBF]/', $string, $rs); $out = ''; $size = count ($rs[0]); $end = $start + $length; if ($end > $size ) { $end = $size; } for ($i = $start; $i < $end; $i++) { $out .= $rs[0][$i]; } return $out;}