XML解析实例

1. XML解析有3中方式：

[1] DOM方式  把整个XML文档读入内存中，再DOM API来访问树形结构，获取数据; 缺点：文档很大时，消耗较多内存。

 

[2] SAX方式 基于事件驱动的，单向读取，优点:不占内存空间、解析属性方便，但缺点就是对于套嵌多个分支来说处理不是很方便。

 

[3] PULL方式 PULL常常用在J2ME对于节点处理比较好，类似SAX方式，同样很节省内存。

 

2. 首先需要解析的XML文件代码如下：

<?xml version="1.0" encoding="utf-8"?>
<rivers>
 <river name="灵渠" length="605">
     <introduction>
      灵渠在广西壮族自治区兴安县境内，是世界上最古老的运河之一，有着“世界古代水利建筑明珠”的美誉。灵渠古称秦凿渠、零渠、陡河、兴安运河，于公元前214年凿成通航，距今已2217年，仍然发挥着功用。
     </introduction>
     <imageurl>
      http://imgsrc.baidu.com/baike/pic/item/389aa8fdb7b8322e08244d3c.jpg
     </imageurl>
   </river> 
   
   <river name="胶莱运河" length="200">
     <introduction>
      胶莱运河南起黄海灵山海口，北抵渤海三山岛，流经现胶南、胶州、平度、高密、昌邑和莱州等，全长200公里，流域面积达5400平方公里，南北贯穿山东半岛，沟通黄渤两海。胶莱运河自平度姚家村东的分水岭南北分流。南流由麻湾口入胶州湾，为南胶莱河，长30公里。北流由海仓口入莱州湾,为北胶莱河,长100余公里。
     </introduction>
     <imageurl>
      http://imgsrc.baidu.com/baike/pic/item/389aa8fdb7b8322e08244d3c.jpg
     </imageurl>
   </river>
   
   <river name="苏北灌溉总渠" length="168"> 
     <introduction>
      位于淮河下游江苏省北部，西起洪泽湖边的高良涧，流经洪泽，青浦、淮安，阜宁、射阳，滨海等六县(区)，东至扁担港口入海的大型人工河道。全长168km。
     </introduction>
     <imageurl>
      http://imgsrc.baidu.com/baike/pic/item/389aa8fdb7b8322e08244d3c.jpg
     </imageurl>
   </river>
 </rivers>

 

3.RiverModel代码如下：

package com.testxml.demo;

import java.io.Serializable;

public class RiverModel implements Serializable {
	
	public static final String RIVERS = "rivers";
	public static final String RIVER  = "river";
	public static final String LENGTH = "length";
	public static final String NAME = "name";
	public static final String IMGURL = "imageurl";
	public static final String INTRODUCTION = "introduction";
	
	private int length;
	private String name;
	private String imgUrl;
	private String introduction;
	
	public int getLength() {
		return length;
	}
	public void setLength(int length) {
		this.length = length;
	}
	public String getName() {
		return name;
	}
	public void setName(String name) {
		this.name = name;
	}
	public String getImgUrl() {
		return imgUrl;
	}
	public void setImgUrl(String imgUrl) {
		this.imgUrl = imgUrl;
	}
	public String getIntroduction() {
		return introduction;
	}
	public void setIntroduction(String introduction) {
		this.introduction = introduction;
	}
}

 

4.activity代码如下：

package com.testxml.demo;

import java.util.ArrayList;

import android.app.Activity;
import android.os.Bundle;
import android.view.View;
import android.view.View.OnClickListener;
import android.widget.Button;
import android.widget.TextView;

public class ParseXMLActivity extends Activity implements OnClickListener {
	
	private Button mButtonDOM;
	private Button mButtonSAX;
	private Button mButtonPULL;
	
	private TextView mTextView;
	
	private ArrayList<RiverModel> rivers = null;
	
	@Override
    public void onCreate(Bundle savedInstanceState) {
        super.onCreate(savedInstanceState);
        setContentView(R.layout.main);
        initViews();
        initControl();
	}
	
	private void initViews()
	{
		mButtonDOM = (Button) findViewById(R.id.btn_dom);
		mButtonSAX = (Button) findViewById(R.id.btn_sax);
		mButtonPULL= (Button) findViewById(R.id.btn_pull);
		
		mTextView = (TextView) findViewById(R.id.txt_content);
	}
	
	private void initControl() {
		mButtonDOM.setOnClickListener(this);
		mButtonSAX.setOnClickListener(this);
		mButtonPULL.setOnClickListener(this);
	}

	@Override
	public void onClick(View v) {
		int id = v.getId();
		switch (id) {
		case R.id.btn_dom:
			rivers = (ArrayList<RiverModel>) XMLHelper.DOMMannerParse(this, "test.xml");
			String s = "";
			for(RiverModel rm:rivers) {
				s += "DOM: name:"+rm.getName()+", length:"+rm.getLength()+"\n info:"+rm.getIntroduction()+"\n";
			}
			mTextView.setText(s);
			break;
		
		case R.id.btn_pull: 
			rivers = (ArrayList<RiverModel>) XMLHelper.DOMMannerParse(this, "test.xml");
			String s1 = "";
			for(RiverModel rm:rivers) {
				s1 += "PULL: name:"+rm.getName()+", length:"+rm.getLength()+"\n info:"+rm.getIntroduction()+"\n";
			}
			mTextView.setText(s1);
			break;
		case R.id.btn_sax: 
			rivers = (ArrayList<RiverModel>) XMLHelper.SAXParseXML(this, "test.xml");
			String s2 = "";
			for(RiverModel rm:rivers) {
				s2 += "SAX: name:"+rm.getName()+", length:"+rm.getLength()+"\n info:"+rm.getIntroduction()+"\n";
			}
			mTextView.setText(s2);
			break;
				
		default:
			break;
		}
	}
	
}

 

5.XMLHelper类实现3种方式解析XML代码如下：

package com.testxml.demo;

import java.io.IOException;
import java.io.InputStream;
import java.util.ArrayList;
import java.util.List;

import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.parsers.ParserConfigurationException;
import javax.xml.parsers.SAXParser;
import javax.xml.parsers.SAXParserFactory;

import org.w3c.dom.Document;
import org.w3c.dom.Element;
import org.w3c.dom.NodeList;
import org.xml.sax.Attributes;
import org.xml.sax.InputSource;
import org.xml.sax.SAXException;
import org.xml.sax.SAXParseException;
import org.xml.sax.XMLReader;
import org.xml.sax.helpers.DefaultHandler;
import org.xmlpull.v1.XmlPullParser;
import org.xmlpull.v1.XmlPullParserException;

import android.content.Context;
import android.util.Xml;

public class XMLHelper {

	// DOM方式解析 把整个XML文档读入内存中，再DOM API来访问树形结构，获取数据; 缺点：文档很大时，消耗很多内存
	public static List<RiverModel> DOMMannerParse(Context context,
			String fileName) {
		List<RiverModel> rivers = new ArrayList<RiverModel>();
		DocumentBuilderFactory factory = null;
		DocumentBuilder builder = null;
		Document document = null;
		InputStream inputStream = null;
		factory = DocumentBuilderFactory.newInstance();
		try {
			builder = factory.newDocumentBuilder();
			inputStream = context.getResources().getAssets().open(fileName);

			document = builder.parse(inputStream);
			Element root = document.getDocumentElement();
			// 解析子节点
			NodeList nodeList = root.getElementsByTagName(RiverModel.RIVER);
			RiverModel riverModel = null;
			for (int i = 0; i < nodeList.getLength(); i++) {
				riverModel = new RiverModel();
				Element riverElement = (Element) nodeList.item(i);
				riverModel.setName(riverElement.getAttribute(RiverModel.NAME));
				riverModel.setLength(Integer.parseInt(riverElement
						.getAttribute(RiverModel.LENGTH)));

				// 解析子节点
				Element introduction = (Element) riverElement
						.getElementsByTagName(RiverModel.INTRODUCTION).item(0);
				riverModel.setIntroduction(introduction.getFirstChild()
						.getNodeValue());
				Element imgurl = (Element) riverElement.getElementsByTagName(
						RiverModel.IMGURL).item(0);
				riverModel.setImgUrl(imgurl.getFirstChild().getNodeValue());
				rivers.add(riverModel);
			}
		} catch (IOException e) {
			e.printStackTrace();
		} catch (SAXException e) {
			e.printStackTrace();
		} catch (ParserConfigurationException e) {
			e.printStackTrace();
		} finally {
			try {
				inputStream.close();
			} catch (Exception e) {
				e.printStackTrace();
			}
		}
		return rivers;
	}

	// PULL方式解析
	public static List<RiverModel> PULLParseXML(Context context, String fileName) {
		List<RiverModel> rivers = new ArrayList<RiverModel>();
		RiverModel riverModel = null;
		InputStream inputStream = null;
		XmlPullParser xmlPullParser = Xml.newPullParser();
		try {
			inputStream = context.getResources().getAssets().open(fileName);
			xmlPullParser.setInput(inputStream, "utf-8");
			int evtType = xmlPullParser.getEventType();
			while (evtType != XmlPullParser.END_DOCUMENT) {
				switch (evtType) {
				case XmlPullParser.START_TAG:
					String tag = xmlPullParser.getName();
					if (tag.equalsIgnoreCase(RiverModel.RIVER)) {
						riverModel = new RiverModel();
						riverModel.setName(xmlPullParser.getAttributeValue(
								null, RiverModel.NAME));
						riverModel.setLength(Integer.parseInt(xmlPullParser
								.getAttributeValue(null, RiverModel.LENGTH)));
					}
					// 如果是解析子节点
					else if (riverModel != null) {
						if (tag.equalsIgnoreCase(RiverModel.INTRODUCTION)) {
							riverModel
									.setIntroduction(xmlPullParser.nextText());
						} else if (tag.equalsIgnoreCase(RiverModel.IMGURL)) {
							riverModel.setImgUrl(xmlPullParser.nextText());
						}
					}
					break;

				case XmlPullParser.END_TAG:
					// 当碰到river结束时，添加RiverModel进rivers中去
					if (xmlPullParser.getName().equalsIgnoreCase(
							RiverModel.RIVER)
							&& riverModel != null) {
						rivers.add(riverModel);
						riverModel = null;
					}
					break;

				default:
					break;
				}
			}
		} catch (XmlPullParserException e) {
			e.printStackTrace();
		} catch (IOException e) {
			e.printStackTrace();
		}

		return rivers;
	}

	// SAX方式解析
	public static List<RiverModel> SAXParseXML(Context context, String fileName) {
		List<RiverModel> rivers = null;
		SAXParserFactory factory = SAXParserFactory.newInstance();
		try {
			SAXParser parser = factory.newSAXParser();
			XMLReader xmlReader = parser.getXMLReader();
			MyContentHandler handler = new MyContentHandler();
			xmlReader.setContentHandler(handler);
			xmlReader.parse(new InputSource(context.getResources().getAssets()
					.open(fileName)));
			rivers = handler.getRivers();
		} catch (ParserConfigurationException e) {
			e.printStackTrace();
		} catch (SAXException e) {
			e.printStackTrace();
		} catch (IOException e) {
			e.printStackTrace();
		}

		return rivers;
	}

	static class MyContentHandler extends DefaultHandler {

		private boolean isRiver = false;
		private boolean isIntroduction = false;
		private boolean isImageUrl = false;
		private RiverModel riverModel = null;
		private List<RiverModel> rivers = new ArrayList<RiverModel>();

		public List<RiverModel> getRivers() {
			return rivers;
		}

		@Override
		public void startElement(String uri, String localName, String qName,
				Attributes attributes) throws SAXException {
			String tagName = localName.length() != 0 ? localName : qName;
			tagName = tagName.toLowerCase().trim();
			if (tagName.equals(RiverModel.RIVER)) {
				isRiver = true;
				riverModel = new RiverModel();

				riverModel.setName(attributes.getValue(RiverModel.NAME));
				riverModel.setLength(Integer.parseInt(attributes
						.getValue(RiverModel.LENGTH)));
			}

			if (isRiver) {
				if (tagName.equals(RiverModel.INTRODUCTION)) {
					isIntroduction = true;
				} else if (tagName.equals(RiverModel.IMGURL)) {
					isImageUrl = true;
				}
			}

			// super.startElement(uri, localName, qName, attributes);
		}

		@Override
		public void characters(char[] ch, int start, int length)
				throws SAXException {

			if (isIntroduction) {
				riverModel
						.setIntroduction(riverModel.getIntroduction() == null ? new String(
								ch, start, length) : riverModel
								.getIntroduction()
								+ new String(ch, start, length));
			} else if (isImageUrl) {
				riverModel
						.setImgUrl(riverModel.getImgUrl() == null ? new String(
								ch, start, length) : riverModel.getImgUrl()
								+ new String(ch, start, length));
			}

			// super.characters(ch, start, length);
		}

		@Override
		public void endElement(String uri, String localName, String qName)
				throws SAXException {
			String tagName = localName.length() != 0 ? localName : qName;
			tagName = tagName.toLowerCase().trim();

			if (tagName.equals(RiverModel.RIVER)) {
				isRiver = true;
				rivers.add(riverModel);
			}

			if (isRiver) {
				if (tagName.equals(RiverModel.INTRODUCTION)) {
					isIntroduction = false;
				} else if (tagName.equals(RiverModel.IMGURL)) {
					isImageUrl = false;
				}
			}

			// super.endElement(uri, localName, qName);
		}

	}

}