Perfect-World

以無法為有法，以無限為有限！

日志

关于我

悠悠思恋

以无法为有法,以无限为有限！

文章分类

PHP 截取字符串

2008-11-12 17:04:55| 分类： PHP | 标签： |举报 |字号大中小订阅

下载LOFTER 我的照片书 |

1. 截取GB2312中文字符串

<?php
< ?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
< ?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. UTF-8、GB2312都支持的汉字截取函数

<?php
< ?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, $sublen, $start = 0, $code = 'UTF-8')
{
   if($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
< ?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                  UUMiss UUMiss@qq.com
* @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 = "CodeBit.cn -- 简单、精彩、通用";
$Length = "18";
$Append = false;
echo sysSubStr($String,$Length,$Append);
?>

以下代码试用于gb2312编码，截取中文字符串是php中一个头疼的问题，解决方法是根据值是否大于等于128来判断是否是双字节字符，以避免出现乱码的情况。但中英文混合、特殊符号等问题总是存在，现在写一个比较全面的，仅供参考：

程序说明：

1. len 参数以中文字符为标准，1len等于2个英文字符，为了形式上好看些

2. 如果将magic参数设为false，则中文和英文同等看待，取绝对的字符数

3. 特别适用于用htmlspecialchars()进行过编码的字符串

4. 能正确处理gb2312中实体字符模式（氰）

程序代码：

function fsubstr($title,$start,$len="",$magic=true)   {  /**    *  powered by smartpig    *  mailto:d.einstein@263.net    */      $length = 0;  if($len == "") $len = strlen($title);    //判断起始为不正确位置  if($start > 0)  {    $cnum = 0;    for($i=0;$i<$start;$i++)    {     if(ord(substr($title,$i,1)) >= 128) $cnum ++;    }    if($cnum%2 != 0) $start--;        unset($cnum);  }    if(strlen($title)<=$len) return substr($title,$start,$len);    $alen   = 0;  $blen = 0;    $realnum = 0;    for($i=$start;$i<strlen($title);$i++)  {    $ctype = 0;    $cstep = 0;    $cur = substr($title,$i,1);    if($cur == "&")    {     if(substr($title,$i,4) == "&lt;")     {      $cstep = 4;      $length += 4;      $i += 3;      $realnum ++;      if($magic)      {       $alen ++;      }     }     else if(substr($title,$i,4) == "&gt;")     {      $cstep = 4;      $length += 4;      $i += 3;      $realnum ++;      if($magic)      {       $alen ++;      }     }     else if(substr($title,$i,5) == "&amp;")     {      $cstep = 5;      $length += 5;      $i += 4;      $realnum ++;      if($magic)      {       $alen ++;      }     }     else if(substr($title,$i,6) == "&quot;")     {      $cstep = 6;      $length += 6;      $i += 5;      $realnum ++;      if($magic)      {       $alen ++;      }     }     else if(substr($title,$i,6) == "&#039;")     {      $cstep = 6;      $length += 6;      $i += 5;      $realnum ++;      if($magic)      {       $alen ++;      }     }     else if(preg_match("/&#(\d+);/i",substr($title,$i,8),$match))     {      $cstep = strlen($match[0]);      $length += strlen($match[0]);      $i += strlen($match[0])-1;      $realnum ++;      if($magic)      {       $blen ++;       $ctype = 1;      }     }    }else{     if(ord($cur)>=128)     {      $cstep = 2;      $length += 2;      $i += 1;      $realnum ++;      if($magic)      {       $blen ++;       $ctype = 1;      }     }else{      $cstep = 1;      $length +=1;      $realnum ++;      if($magic)      {       $alen++;      }     }    }        if($magic)    {     if(($blen*2+$alen) == ($len*2)) break;     if(($blen*2+$alen) == ($len*2+1))     {      if($ctype == 1)      {       $length -= $cstep;       break;      }else{       break;      }     }    }else{     if($realnum == $len) break;    }  }    unset($cur);  unset($alen);  unset($blen);  unset($realnum);  unset($ctype);  unset($cstep);    return substr($title,$start,$length);  }

评论这张

转发至微博

阅读(867)| 评论(0)

历史上的今天

this.p={  m:2,
              b:2,
              loftPermalink:'',
              id:'fks_085071082095086070093094084095086082083070083081094065',
              blogTitle:'PHP 截取字符串',
              blogAbstract:'<P\>1. 截取GB2312中文字符串 </P\>  <DIV\>  <DIV\><SPAN style=\"COLOR: blue;\"  \><?php</SPAN\><SPAN style=\"COLOR: gray;\"  \><BR\>< ?</SPAN\><SPAN style=\"COLOR: blue;\"  \>php</SPAN\><SPAN style=\"COLOR: gray;\"  \> <BR\></SPAN\><SPAN style=\"COLOR: #ffa500;\"  \>//截取中文字符串</SPAN\><SPAN style=\"COLOR: gray;\"  \><BR\></SPAN\><SPAN style=\"COLOR: green;\"  \>function</SPAN\><SPAN style=\"COLOR: gray;\"  \> </SPAN\><SPAN style=\"COLOR: blue;\"  \>mysubstr</SPAN\><SPAN style=\"COLOR: olive;\"  \>(</SPAN\><SPAN style=\"COLOR: #00008b;\"  \>$str</SPAN\><SPAN style=\"COLOR: gray;\"  \>, </SPAN\><SPAN style=\"COLOR: #00008b;\"  \>$start</SPAN\><SPAN style=\"COLOR: gray;\"  \>, </SPAN\><SPAN style=\"COLOR: #00008b;\"  \>$len</SPAN\><SPAN style=\"COLOR: olive;\"  \>)</SPAN\><SPAN style=\"COLOR: gray;\"  \> </SPAN\><SPAN style=\"COLOR: olive;\"  \>{</SPAN\><SPAN style=\"COLOR: gray;\"  \><BR\>    </SPAN\></DIV\></DIV\>',
              blogTag:'',
              blogUrl:'blog/static/24257782200810125455539',
              isPublished:1,
              istop:false,
              type:2,
              modifyTime:1317337118139,
              publishTime:1226480695539,
              permalink:'blog/static/24257782200810125455539',
              commentCount:0,
              mainCommentCount:0,
              recommendCount:0,
              bsrk:-100,
              publisherId:0,
              recomBlogHome:false,
              currentRecomBlog:false,
              attachmentsFileIds:[],
              vote:{},
              groupInfo:{},
              friendstatus:'none',
              followstatus:'unFollow',
              pubSucc:'',
              visitorProvince:'',
              visitorCity:'',
              visitorNewUser:false,
              postAddInfo:{},
              mset:'000',
              mcon:'',
              srk:-100,
              remindgoodnightblog:false,
              isBlackVisitor:false,
              isShowYodaoAd:true,
              hostIntro:'以无法为有法,以无限为有限！',
              hmcon:'1',
              selfRecomBlogCount:'0',
              lofter_single:'<iframe width="140" height="560" style="overflow:hidden;" src="http://www.lofter.com/mailEntry.do?blogad=1&blog" frameBorder="0"></iframe>'
            }

{list a as x}
    {if !!x}
    <div class="iblock nbw-fce nbw-f40">
      <a class="fc03 noul" target="_blank" hidefocus="true" href="http://blog.163.com/${x.visitorName}/">
      {if x.visitorName==visitor.userName}
      <img alt="${x.visitorNickname|escape}" onerror="this.src=location.f40" class="cwd bdwa bdc0" src="${fn1(x.visitorName)}&r=${visitor.imageUpdateTime}"/>
      {else}
      <img alt="${x.visitorNickname|escape}" onerror="this.src=location.f40" class="cwd bdwa bdc0" src="${fn1(x.visitorName)}"/>
      {/if}
      </a>
      <div class="cwd vname thide">
        {if x.moveFrom=='wap'}
          <a class="noul pnt" target="_blank" href="http://blog.163.com/services/wapblog.html?frompersonalbloghome"><span title="来自网易手机博客" class="iblock wapIcon"> </span></a>
        {elseif x.moveFrom=='iphone'}
          <a class="noul pnt" target="_blank"><span title="来自iPhone客户端" class="iblock iphoneIcon"> </span></a>
        {elseif x.moveFrom=='android'}
          <a class="noul pnt" target="_blank"><span title="来自Android客户端" class="iblock androidIcon"> </span></a>
        {elseif x.moveFrom=='mobile'}
          <a class="noul pnt" target="_blank" href="http://blog.163.com/services/emsblog.html?frompersonalbloghome"><span title="来自网易短信写博" class="iblock wapIcon"> </span></a>
        {/if}
        <a class="fc03 m2a"  target="_blank" hidefocus="true" href="http://blog.163.com/${x.visitorName}/">
          ${fn(x.visitorNickname,8)|escape}
        </a>
      </div>
    </div>
    {/if}
    {/list}

<#--最新日志，群博日志--> <#--推荐日志-->

<p class="fc06">推荐过这篇日志的人：</p>
    <div>
      {list a as x}
      {if !!x}
      <div class="iblock nbw-fce nbw-f40">
        <a class="fc03 noul" target="_blank" hidefocus="true" href="http://blog.163.com/${x.recommenderName}/">
        <img alt="${x.recommenderNickname|escape}" onerror="this.src=location.f40" class="cwd bdwa bdc0" src="${fn1(x.recommenderName)}"/>
        </a>
        <div class="cwd thide">
          <a class="fc03 m2a" target="_blank" hidefocus="true" href="http://blog.163.com/${x.recommenderName}/">
            ${fn(x.recommenderNickname,6)|escape}
          </a>
        </div>
      </div>
      {/if}
      {/list}
    </div>
    {if !!b&&b.length>0}
    <p  class="fc06">他们还推荐了：</p>
    <ul>
    {list b as y}
      {if !!y}
        <li class="rrb"><span class="iblock">·</span><a class="fc03 m2a" target="_blank" href="http://blog.163.com/${y.recommendBlogPermalink}/?from=blog/static/24257782200810125455539">${y.recommendBlogTitle|escape}</a></li>
      {/if}
    {/list}
    </ul>
    {/if}

<#--引用记录--> <#--博主推荐--> <#--随机阅读--> <#--首页推荐--> <#--历史上的今天--> <#--被推荐日志--> <#--上一篇，下一篇--> <#-- 热度 -->

{list a as x}
    {if !!x}
    <div class="hotItem iblock nbw-fce nbw-f40">
      <a class="fc03 noul" target="_blank" hidefocus="true" href="http://blog.163.com/${x.publisherUsername}/">
      {if x.publisherUsername==visitor.userName}
      <img alt="${x.publisherNickname|escape}" onerror="this.src=location.f40" class="cwd bdwa bdc0" src="${fn1(x.publisherUsername)}&r=${visitor.imageUpdateTime}"/>
      {else}
      <img alt="${x.publisherNickname|escape}" onerror="this.src=location.f40" class="cwd bdwa bdc0" src="${fn1(x.publisherUsername)}"/>
      {/if}
      </a>
      <div class="cwd vname thide">
        <a class="fc03 m2a"  target="_blank" hidefocus="true" href="http://blog.163.com/${x.publisherUsername}/">
          ${fn(x.publisherNickname,8)|escape}
        </a>
      </div>
      <a class="f-myLikeIcons hottype {if x.type==1} js-liketype{elseif x.type==2} js-reblogtype{elseif x.type==3} js-sharetype{else}{/if}" target="_blank" hidefocus="true" href="http://blog.163.com/${x.publisherUsername}/"> </a>
    </div>
    {/if}
    {/list}

<#-- 网易新闻广告 --> <#--右边模块结构--> <#--评论模块结构--> <#--引用模块结构--> <#--博主发起的投票-->

页脚

我的照片书 - 手机博客 - 下载LOFTER APP - 订阅此博客

Perfect-World

导航

日志

PHP 截取字符串

历史上的今天

最近读者

热度

评论

页脚