SAX解析XML

介绍

Java解析XML有两种基本的方式，DOM和SAX。今天先简单记录下SAX解析XML。

SAX（Simple API for XML），既是一种接口，也是一种软件包。它是一种XML解析的替代方法。SAX不同于DOM解析，它逐行扫描文档，一边扫描一边解析。

示例

book.xml

<?xml version="1.0" encoding="UTF-8"?>  
<books>  
    <book id="1">  
        <name>平凡的世界</name>  
        <author>路遥</author>  
    </book>  
    <book id="2">  
        <name>活着</name>  
        <author>余华</author>  
    </book>  
</books>

Book.java

public class Book{
	private int id;
	private String name;
	private String author;

    public int getId() {
        return id;
    }

    public void setId(int id) {
        this.id = id;
    }

    public String getName() {
        return name;
    }

    public void setName(String name) {
        this.name = name;
    }

    public String getAuthor() {
        return author;
    }

    public void setAuthor(String author) {
        this.author = author;
    }
}

SaxParseXmlHandler.java

public class SaxParseXmlHandler extends DefaultHandler{
	private List<Book> books;
	private Book book;
	private String nodeName;

	//开始解析文档
	@Override
	public void startDocument() throws SAXException {
    	books = new ArrayList<>();
	}

	//解析开始节点
	@Override
	public void startElement(String uri, String localName, String qName, Attributes attributes) throws SAXException {
		if("book".equals(qName)){
			book=new Book();
			//获取book节点的id属性
			book.setId(Integer.parseInt(attributes.getValue(0)));
		}
		nodeName=qName;
	}

	//获取节点内容
	@Override
	public void characters(char[] ch, int start, int length) throws SAXException {
		if(null!=nodeName){
			String content=new String(ch,start,length);
			switch(nodeName){
				case "name":
					book.setName(content);
					break;
				case "author":
					book.setAuthor(content);
					break;
			}
		}
	}

	//解析结束节点
	@Override
	public void endElement(String uri, String localName, String qName) throws SAXException {
		if("book".equals(qName)){
			books.add(book);
			book=null;
		}
		nodeName=null;
	}

	//结束解析文档
	@Override
	public void endDocument() throws SAXException {
    	super.endDocument();
	}

	//返回解析结果
	public List<Book> getBooks(){
		return boooks;
	}
	
}

Test.java

public class Test{
	public static void main(String[] args) {
		try {
            //创建SAX解析器工厂
            SAXParserFactory factory = SAXParserFactory.newInstance();
            //创建SAX解析器
            SAXParser saxParser = factory.newSAXParser();
            //获取XML读取器
            XMLReader reader = saxParser.getXMLReader();
            //实例化SaxParseXmlHandler
            SaxParseXmlHandler handler = new SaxParseXmlHandler();
			//设置内容处理器
            reader.setContentHandler(handler);
            //读取XML
            reader.parse("book.xml");

            List<Book> books = handler.getBooks();
            for (Book book : books) {
                System.out.println("id:" + book.getId() + ",name:" + book.getName() + ",author:" + book.getAuthor());
            }
        } catch (ParserConfigurationException e) {
            e.printStackTrace();
        } catch (SAXException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }
	}
}

打印结果

注意事项

读取XML文件时，如果XML文件和当前类不在同一个路径，可采用写完整路径的方式读取。如：

InputStream is = Test.class.getClassLoader().getResourceAsStream("com/ywb/context/config/book.xml");
reader.parse(new InputSource(is));