解析xml提供的字符串錯誤

Question

我想解析一個rss提要，但它在某些字符處失敗，例如「>」char和所有在這個字符之前。

例子：

<title>[Maths I &gt; Theory] Maths I, T1.pdf: One file added.</title> 

輸出：

[Maths I 

這是我RSSHandler：

public class RSSHandler extends DefaultHandler { 

final int state_unknown = 0; 
final int state_title = 1; 
final int state_description = 2; 
final int state_link = 3; 
final int state_pubdate = 4; 
int currentState = state_unknown; 

RSSFeed feed; 
RSSItem item; 

boolean itemFound = false; 

RSSHandler(){ 
} 

RSSFeed getFeed(){ 
return feed; 
} 

@Override 
public void startDocument() throws SAXException { 
// TODO Auto-generated method stub 
feed = new RSSFeed(); 
item = new RSSItem(); 

} 

@Override 
public void endDocument() throws SAXException { 
// TODO Auto-generated method stub 
} 

@Override 
public void startElement(String uri, String localName, String qName, 
Attributes attributes) throws SAXException { 
// TODO Auto-generated method stub 

if (localName.equalsIgnoreCase("item")){ 
itemFound = true; 
item = new RSSItem(); 
currentState = state_unknown; 
} 
else if (localName.equalsIgnoreCase("title")){ 
currentState = state_title; 
} 
else if (localName.equalsIgnoreCase("description")){ 
currentState = state_description; 
} 
else if (localName.equalsIgnoreCase("link")){ 
currentState = state_link; 
} 
else if (localName.equalsIgnoreCase("pubdate")){ 
currentState = state_pubdate; 
} 
else{ 
currentState = state_unknown; 
} 

} 

@Override 
public void endElement(String uri, String localName, String qName) 
throws SAXException { 
// TODO Auto-generated method stub 
if (localName.equalsIgnoreCase("item")){ 
feed.addItem(item); 
} 
} 

@Override 
public void characters(char[] ch, int start, int length) 
throws SAXException { 
// TODO Auto-generated method stub 

String strCharacters = new String(ch,start,length); 

if (itemFound==true){ 
// "item" tag found, it's item's parameter 
switch(currentState){ 
case state_title: 
item.setTitle(strCharacters); 
break; 
case state_description: 
item.setDescription(strCharacters); 
break; 
case state_link: 
item.setLink(strCharacters); 
break; 
case state_pubdate: 
item.setPubdate(strCharacters); 
break; 
default: 
break; 
} 
} 
else{ 
// not "item" tag found, it's feed's parameter 
switch(currentState){ 
case state_title: 
feed.setTitle(strCharacters); 
break; 
case state_description: 
feed.setDescription(strCharacters); 
break; 
case state_link: 
feed.setLink(strCharacters); 
break; 
case state_pubdate: 
feed.setPubdate(strCharacters); 
break; 
default: 
break; 
} 
} 

currentState = state_unknown; 
} 


} 

Answer 1

這是一個稍微修改的版本，可以很好地解析RSS文件。我希望它有幫助。

首先，State枚舉：

public enum State { 

    unknown, title, description, link, pubdate 

} 

隨後處理類：

import org.xml.sax.Attributes; 
import org.xml.sax.SAXException; 
import org.xml.sax.helpers.DefaultHandler; 

public class RSSHandler extends DefaultHandler { 

    private State currentState = State.unknown; 

    private RSSFeed feed; 
    private RSSItem item; 

    private boolean itemFound = false; 

    private StringBuilder tagContent; 

    public RSSHandler() { 
    } 

    @Override 
    public void startDocument() throws SAXException { 
     feed = new RSSFeed(); 
     item = new RSSItem(); 
    } 

    @Override 
    public void startElement(final String uri, final String localName, 
      final String qName, final Attributes attributes) 
      throws SAXException { 
     currentState = State.unknown; 
     tagContent = new StringBuilder(); 
     if (localName.equalsIgnoreCase("item")) { 
      itemFound = true; 
      item = new RSSItem(); 
      currentState = State.unknown; 
     } else if (localName.equalsIgnoreCase("title")) { 
      currentState = State.title; 
     } else if (localName.equalsIgnoreCase("description")) { 
      currentState = State.description; 
     } else if (localName.equalsIgnoreCase("link")) { 
      currentState = State.link; 
     } else if (localName.equalsIgnoreCase("pubdate")) { 
      currentState = State.pubdate; 
     } 
     System.out.println("new state: " + currentState); 

    } 

    @Override 
    public void endElement(final String uri, final String localName, 
      final String qName) throws SAXException { 
     if (localName.equalsIgnoreCase("item")) { 
      feed.addItem(item); 
     } 
     if (itemFound == true) { 
      // "item" tag found, it's item's parameter 
      switch (currentState) { 
       case title: 
        item.setTitle(tagContent.toString()); 
        break; 
       case description: 
        item.setDescription(tagContent.toString()); 
        break; 
       case link: 
        item.setLink(tagContent.toString()); 
        break; 
       case pubdate: 
        item.setPubdate(tagContent.toString()); 
        break; 
       default: 
        break; 
      } 
     } else { 
      // not "item" tag found, it's feed's parameter 
      switch (currentState) { 
       case title: 
        feed.setTitle(tagContent.toString()); 
        break; 
       case description: 
        feed.setDescription(tagContent.toString()); 
        break; 
       case link: 
        feed.setLink(tagContent.toString()); 
        break; 
       case pubdate: 
        feed.setPubdate(tagContent.toString()); 
        break; 
       default: 
        break; 
      } 
     } 
    } 

    @Override 
    public void characters(final char[] ch, final int start, final int length) 
      throws SAXException { 
     tagContent.append(ch, start, length); 
    } 

    public RSSFeed getFeed() { 
     return feed; 
    } 

} 

Answer 2

你得到至少5個回調到characters方法：

1st: [Maths I 
2nd: > 
3rd: Theory 
4th: ] 
5th: Maths I, T1.pdf: One file added. 

您不應該在characters方法的最後一行中更改currentState，並且您必須緩衝String並稍後將它們連接起來。