sax解析xml的特殊字符解决方法

1. 如果特殊字符很少，并且出现在特定的tag里，最简单的方法就是生成xml的时候加入标志“<![CDATA[formula]]>”如，

<?xml version='1.0' encoding='UTF-8' standalone='yes' ?>
<Root>
	<ITEM>
		<AreaID>1</AreaID>
		<ParentID>0</ParentID>
		<AreaName>0</AreaName>
	</ITEM>
	<ITEM>
		<AreaID>2</AreaID>
		<ParentID>1</ParentID>
		<AreaName><![CDATA[aaa<bbb?1:2]]></AreaName>
	</ITEM>
</Root>

2. 如果不确定哪一个tag会有像<，>等的特殊字符，或者出现特殊字符的tag比较多，则最好使用转义

因为SAX解析判断是否是一个element是通过<>,</>来判断的，所以想大于号、小于号等为了避免混淆，要使用转义

小于号 < &lt;

大于号 > &gt;

与号 & &amp;

单引号 ‘ &apos;

双引号 “ &quot;

比如，

<?xml version='1.0' encoding='UTF-8' standalone='yes' ?>
<Root>
	<ITEM>
		<AreaID>1</AreaID>
		<ParentID>0</ParentID>
		<AreaName>0</AreaName>
	</ITEM>
	<ITEM>
		<AreaID>2</AreaID>
		<ParentID>1</ParentID>
		<AreaName>a&lt;b</AreaName>
	</ITEM>
</Root>

<AreaName>a&lt;b</AreaName>

解析的时候，sax解析AreaName的时候进入startElement进入一次，会进入characters至少3次(说至少的意思是有些tag中间会有空格或TAB，本例中只会调用3次)，分别会返回”a“, "<", "b",把这三次拼接起来就是我们需要的字串，完整程序如下

package com.kingman.hello.xml;

import org.xml.sax.Attributes;
import org.xml.sax.SAXException;
import org.xml.sax.helpers.DefaultHandler;
import android.util.Log;

public class AreaHandler extends DefaultHandler{
	private static final String TAG = "AreaHandler";
    final int AREA_ID = 1;
	final int PARENT_ID = 2;
	final int AREA_NAME = 3;
	AreaFeed mAreaFeed;
	AreaItem mAreaItem;
	private int currentstate;
	private StringBuffer str = null; 
	
	public AreaHandler() {
		
	}
	
	@Override
	public void startDocument() throws SAXException {
	    Log.v(TAG, "startDocument");
		mAreaFeed = new AreaFeed();
		mAreaItem = new AreaItem();
	}

	@Override
	public void endDocument() throws SAXException {
	    Log.v(TAG, "endDocument");
	}

	@Override
	public void startElement(String uri, String localName, String qName,
			Attributes attributes) throws SAXException {
	    Log.v(TAG, "startElement");
	    str = new StringBuffer();
		if (localName.equals("ITEM"))
		{
			mAreaItem = new AreaItem();
			return;
		}
		if (localName.equals("AreaID"))
		{
			currentstate = AREA_ID;
			return;
		}
		if (localName.equals("ParentID"))
		{
			currentstate = PARENT_ID;
			return;
		}
		if (localName.equals("AreaName"))
		{
			currentstate = AREA_NAME;
			return;
		}
	}

	@Override
	public void endElement(String uri, String localName, String qName)
			throws SAXException {
	    Log.v(TAG, "endElement");
	    super.endElement(uri, localName, qName);
		if (localName.equals("ITEM"))
		{
			mAreaFeed.addItem(mAreaItem);
			return;
		}
		switch (currentstate)
        {
            case AREA_ID:
                mAreaItem.setmAreaID(str.toString());
                currentstate = 0;
                break;
            case PARENT_ID:
                mAreaItem.setmParentID(str.toString());
                currentstate = 0;
                break;
            case AREA_NAME:
                Log.v(TAG, "AREA_NAME - str = " + str);
                mAreaItem.setmAreaName(str.toString());
                currentstate = 0;
                break;
            default:
                return;
        }

	}

	@Override
	public void characters(char[] ch, int start, int length)
			throws SAXException {
		String theString = new String(ch,start,length);
		str.append(theString);
		Log.v(TAG, "str = " + str);
	}

	public AreaFeed getFeed() {
		return mAreaFeed;
	}

}

package com.kingman.hello.xml;

import java.io.InputStream;
import javax.xml.parsers.SAXParser;
import javax.xml.parsers.SAXParserFactory;
import org.xml.sax.InputSource;
import org.xml.sax.XMLReader;
import android.app.Activity;
import android.os.Bundle;
import android.util.Log;
import android.widget.ListView;
import android.widget.SimpleAdapter;
import com.kingman.hello.R;

public class SAXParseActivity extends Activity{
	public final String TAG = "XMLParseActivity";
	private AreaFeed feed = null;
	
	@Override
	protected void onCreate(Bundle savedInstanceState) {
		super.onCreate(savedInstanceState);
		this.setContentView(R.layout.xml_listview);
		feed = getFeed(R.raw.area);
		showListView();
	}

	private AreaFeed getFeed(int r_id) {
		try
    	{
    	   InputStream inputStream = null;
           
           //xml file 放到 assets目录中的
    	   inputStream = getResources().getAssets().open("blog.xml");
    	   //inputStream = openFileInput("blog.xml");
           
           //创建SAX解析工厂
           SAXParserFactory factory = SAXParserFactory.newInstance();
           SAXParser parser = factory.newSAXParser();
           XMLReader xmlreader = parser.getXMLReader();
           //为XMLReader设置内容处理器
           AreaHandler xmlHandler = new AreaHandler();
           xmlreader.setContentHandler(xmlHandler);	//设置事件处理函数

           InputSource is = new InputSource(inputStream);
           //开始解析文件
           xmlreader.parse(is);
  
           return xmlHandler.getFeed();
    	} catch (Exception ee){
    		return null;
    	}
	}

	private void showListView()
    {
		Log.v(TAG, "showListView");
        ListView itemlist = (ListView) findViewById(R.id.itemlist);
        if (feed == null)
        {
        	setTitle("Can't display");
        	return;
        }

        SimpleAdapter adapter = new SimpleAdapter(this, feed.getAllItemsForListView(),
       		 R.layout.xml_three_textview, new String[] { AreaItem.AREA_ID, AreaItem.PARENT_ID , AreaItem.AREA_NAME},
       		 new int[] { R.id.tv1 , R.id.tv2, R.id.tv3});
        itemlist.setAdapter(adapter);
        itemlist.setSelection(0);
        
    }
}