- 论坛徽章:
- 0
|
程序代码:
/**
* filter all html element.
* For example:"www.sohu.com/test">hello!
* The filter result is :hello!
* Notice:This method filter the text between " and ">"
* @param element
* @return
*/
public static String getTxtWithoutHTMLElement (String element)
{
// String reg="]+>";
// return element.replaceAll(reg,"");
if(null==element||"".equals(element.trim()))
{
return element;
}
Pattern pattern=Pattern.compile("]*>");
Matcher matcher=pattern.matcher(element);
StringBuffer txt=new StringBuffer();
while(matcher.find())
{
String group=matcher.group();
if(group.matches(""))
{
matcher.appendReplacement(txt,group);
}
else
{
matcher.appendReplacement(txt,"");
}
}
matcher.appendTail(txt);
repaceEntities(txt,"&","&");
repaceEntities(txt,",");
repaceEntities(txt,">",">");
repaceEntities(txt,""","\"");
repaceEntities(txt," ","");
return txt.toString();
}
下面是测试用例:
public void testGetTxtWithoutHTMLElement ()
{
assertEquals("test",ExcelHssfView.getTxtWithoutHTMLElement("test"));
assertEquals("test",ExcelHssfView.getTxtWithoutHTMLElement("test"));
assertEquals("test",ExcelHssfView.getTxtWithoutHTMLElement("test"));
assertEquals("test",ExcelHssfView.getTxtWithoutHTMLElement("test"));
assertEquals("test",ExcelHssfView.getTxtWithoutHTMLElement("test"));
assertEquals("te,ExcelHssfView.getTxtWithoutHTMLElement("te));
assertEquals("te>st",ExcelHssfView.getTxtWithoutHTMLElement("te>st"));
assertEquals("tst",ExcelHssfView.getTxtWithoutHTMLElement("tst"));
assertEquals("t,ExcelHssfView.getTxtWithoutHTMLElement("tst"));
assertEquals("test",ExcelHssfView.getTxtWithoutHTMLElement("test"));
assertEquals("test",ExcelHssfView.getTxtWithoutHTMLElement("test"));
assertEquals("test",ExcelHssfView.getTxtWithoutHTMLElement("test"));
assertEquals("test",ExcelHssfView.getTxtWithoutHTMLElement(" test"));
}
本文来自ChinaUnix博客,如果查看原文请点:http://blog.chinaunix.net/u1/33099/showart_326025.html |
|