PHP函数之中文字符串截取

王

1. 截取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. 截取utf8编码的多字节字符串

< ?php
//截取utf8字符串
function cut_str($string, $length, $dot = '...',$charset='utf-8')
{
$strlen = strlen($string);
if($strlen <= $length) return $string;
$string = str_replace(array('&nbsp;', '&amp;', '&quot;', '&#039;', '&ldquo;', '&rdquo;', '&mdash;', '&lt;', '&gt;', '&middot;', '&hellip;'), array(' ', '&', '"', "'", '“', '”', '—', '<', '>', '·', '…'), $string);
$strcut = '';
if($charset == 'utf-8')
{
$n = $tn = $noc = 0;
while($n < $strlen)
{
$t = ord($string[$n]);
if($t == 9 || $t == 10 || (32 <= $t && $t <= 126)) {
$tn = 1; $n++; $noc++;
} elseif(194 <= $t && $t <= 223) {
$tn = 2; $n += 2; $noc += 2;
} elseif(224 <= $t && $t < 239) {
$tn = 3; $n += 3; $noc += 2;
} elseif(240 <= $t && $t <= 247) {
$tn = 4; $n += 4; $noc += 2;
} elseif(248 <= $t && $t <= 251) {
$tn = 5; $n += 5; $noc += 2;
} elseif($t == 252 || $t == 253) {
$tn = 6; $n += 6; $noc += 2;
} else {
$n++;
}
if($noc >= $length) break;
}
if($noc > $length) $n -= $tn;
$strcut = substr($string, 0, $n);
}
else
{
$dotlen = strlen($dot);
$maxi = $length - $dotlen - 1;
for($i = 0; $i < $maxi; $i++)
{
$strcut .= ord($string[$i]) > 127 ? $string[$i].$string[++$i] : $string[$i];
}
}
$strcut = str_replace(array('&', '"', "'", '<', '>'), array('&amp;', '&quot;', '&#039;', '&lt;', '&gt;'), $strcut);
if(strlen($strcut)< $strlen ) $strcut.= $dot;
return $strcut;
}

 

3. UTF-8、GB2312都支持的汉字截取函数

< ?php
/*
Utf-8、gb2312都支持的汉字截取函数
cut_str(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, $start = 0, $sublen, $code = 'UTF-8')
{
    if($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');
?>

4. BugFree 的字符截取函数

< ?php
/**
 * @package     BugFree
 * @version     $Id: FunctionsMain.inc.php,v 1.32 2005/09/24 11:38:37 wwccss Exp $
 *
 *
 * Return part of a string(Enhance the function substr())
 *
 * @author                  Chunsheng Wang <wwccss@263.net>
 * @param string  $String  the string to cut.
 * @param int     $Length  the length of returned string.
 * @param booble  $Append  whether append "...": false|true
 * @return string           the cutted string.
 */
function sysSubStr($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 = "17test.info 走在中国自动化测试的前沿";
$Length = "18";
$Append = false;
echo sysSubStr($String,$Length,$Append);
?>