TIPS - XML CDATA中的非法字符处理

XML解析过程中，常遇见CDATA中存在非法字符，尤其在火星文盛行的当下，论坛数据五花八门，令哥蛋疼，采用如下简单处理：

String EMPTY_STRING = "";
public static String regularizeXmlString(String strInput){
		if(strInput == null || strInput.length() == 0){
			return EMPTY_STRING;
		}
		String result = strInput.replaceAll("[\\x00-\\x08|\\x0b-\\x0c|\\x0e-\\x1f]",EMPTY_STRING);
		return result;
}

评论

1 楼 haixin3036 2014-07-17  

<table width="766" border="0" >
<tr align="left">
<td class="STYLE1" ><span >网站地图(Build090324)：(2014-07-17 11:32:08)</span></td>
</tr>
   <tr align="left">
<td width="760" class="STYLE1">1.&nbsp;<a href="http://www.adminwang.com/php/12.html">PHP常量</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">2.&nbsp;<a href="http://www.adminwang.com/php/27.html">时间和日期</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">3.&nbsp;<a href="http://www.adminwang.com/javascript/40.html">JavaScript 基本语法</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">4.&nbsp;<a href="http://www.adminwang.com/javascript/49.html">JavaScript 事件</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">5.&nbsp;<a href="http://www.adminwang.com/javascript/50.html">小结(需要注意的一些问题)</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">6.&nbsp;<a href="http://www.adminwang.com/php/26.html">PHP核心技术</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">7.&nbsp;<a href="http://www.adminwang.com/php/24.html">PHP连接Mysql数据库</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">8.&nbsp;<a href="http://www.adminwang.com/html/35.html">HTML绝对路径和相对路径</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">9.&nbsp;<a href="http://www.adminwang.com/php/7.html">PHP简介</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">10.&nbsp;<a href="http://www.adminwang.com/html/37.html">HTML有序列表(OL)</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">11.&nbsp;<a href="http://www.adminwang.com/php/22.html">字符串中变量的解析</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">12.&nbsp;<a href="http://www.adminwang.com/php/8.html">配置PHP开发环境</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">13.&nbsp;<a href="http://www.adminwang.com/php/20.html">数组的遍历</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">14.&nbsp;<a href="http://www.adminwang.com/javascript/44.html">JavaScript分支结构</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">15.&nbsp;<a href="http://www.adminwang.com/html/55.html">HTML框架</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">16.&nbsp;<a href="http://www.adminwang.com/html/33.html">HTML图片(IMG)</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">17.&nbsp;<a href="http://www.adminwang.com/php/11.html">PHP数据类型</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">18.&nbsp;<a href="http://www.adminwang.com/html/38.html">HTML多媒体&lt;Embed&gt;</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">19.&nbsp;<a href="http://www.adminwang.com/blog/2.html">discuz配置单页面(单板)论坛的方法</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">20.&nbsp;<a href="http://www.adminwang.com/php/18.html">PHP变量的范围</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">21.&nbsp;<a href="http://www.adminwang.com/javascript/45.html">JavaScript循环结构</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">22.&nbsp;<a href="http://www.adminwang.com/php/10.html">PHP变量</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">23.&nbsp;<a href="http://www.adminwang.com/php/17.html">PHP函数</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">24.&nbsp;<a href="http://www.adminwang.com/html/31.html">HTML结构与语法</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">25.&nbsp;<a href="http://www.adminwang.com/php/16.html">特殊的流程控制语句</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">26.&nbsp;<a href="http://www.adminwang.com/javascript/46.html">Break与Continue</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">27.&nbsp;<a href="http://www.adminwang.com/html/30.html">HTML是什么</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">28.&nbsp;<a href="http://www.adminwang.com/php/28.html">目录操作</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">29.&nbsp;<a href="http://www.adminwang.com/html/36.html">HTML无序列表(UL)</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">30.&nbsp;<a href="http://www.adminwang.com/html/54.html">HTML头部标签&lt;Meta&gt;</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">31.&nbsp;<a href="http://www.adminwang.com/php/14.html">PHP流程控制语句</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">32.&nbsp;<a href="http://www.adminwang.com/html/32.html">HTML文字与段落</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">33.&nbsp;<a href="http://www.adminwang.com/php/15.html">循环结构语句</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">34.&nbsp;<a href="http://www.adminwang.com/php/29.html">文件处理</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">35.&nbsp;<a href="http://www.adminwang.com/blog/1.html">DedeCMS与Ueditor 1.3.6整合</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">36.&nbsp;<a href="http://www.adminwang.com/javascript/47.html">JavaScript 函数（Function）</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">37.&nbsp;<a href="http://www.adminwang.com/html/52.html">HTML表格&lt;table&gt;</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">38.&nbsp;<a href="http://www.adminwang.com">AW 专注于Web开发技术</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">39.&nbsp;<a href="http://www.adminwang.com/blog/51.html">判断UA自动跳转至移动端页面JS代码</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">40.&nbsp;<a href="http://www.adminwang.com/php/13.html">PHP运算符</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">41.&nbsp;<a href="http://www.adminwang.com/php/21.html">字符串处理</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">42.&nbsp;<a href="http://www.adminwang.com/php/19.html">PHP数组</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">43.&nbsp;<a href="http://www.adminwang.com/javascript/42.html">JavaScript数据类型</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">44.&nbsp;<a href="http://www.adminwang.com/javascript/43.html">JavaScript运算符</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">45.&nbsp;<a href="http://www.adminwang.com/html/34.html">HTML链接(Link)</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">46.&nbsp;<a href="http://www.adminwang.com/php/23.html">表单提交</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">47.&nbsp;<a href="http://www.adminwang.com/html/53.html">HTML表单&lt;Form&gt;</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">48.&nbsp;<a href="http://www.adminwang.com/javascript/41.html">JavaScript变量</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">49.&nbsp;<a href="http://www.adminwang.com/php/9.html">PHP基本语法</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">50.&nbsp;<a href="http://www.adminwang.com/javascript/48.html">JavaScript 弹出框</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">51.&nbsp;<a href="http://www.adminwang.com/php/25.html">PHP基础总结</a></td>
</tr>
  <tr align="left">
<td width="760" class="STYLE1">52.&nbsp;<a href="http://www.adminwang.com/javascript/39.html">JavaScript简介</a></td>
</tr>
</table>