xml解析

dom解析(Document object model文档对象模型，官方推荐)

• dom解析特点
  • 将整个xml文档存入内存中，即一个document对象
  • 优点
    • dom解析，实现xml解析方便,操作速度快
  • 缺点
    • 使用dom解析xml文档，如果文件比较大，对内存消耗就特别大，极容易导致内存溢出， 所以dom方式不适合操作大的xml文档

sax解析

• sax解析特点
  • 优点
    • 解析速度快、对内存占用少，查找数据特别方便
  • 缺点
    • 由于是逐行读取，所以只适合查找数据，不适合增删改操作

xml解析包

• JAXP（sun公司，官方解析,dom解析）
  • 实例代码

public classJaxp {    /**     * 使用jaxp操作xml文档     *     * @param args     * @throws ParserConfigurationException     * @throws IOException     * @throws SAXException     */    public static void main(String[] args) throws ParserConfigurationException, SAXException, IOException {        //1.获取工厂        DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();        //2.产生解析器        DocumentBuilder builder = factory.newDocumentBuilder();        //3.解析xml文档，得到代表文档的document        Document document = builder.parse(new File("src/book1.xml"));        //遍历        list(document);    }    //得到售价结点的值    @Test    public void read() throws Exception {        //1.获取工厂        DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();        DocumentBuilder builder = factory.newDocumentBuilder();        Document document = builder.parse(new File("src/book.xml"));        NodeList list = document.getElementsByTagName("售价");        Node price = list.item(0);        String value = price.getTextContent();        System.out.println(value);    }    //修改结点的值:<售价>39.00元</售价>改为109    @Test    public void update() throws Exception {        DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();        DocumentBuilder builder = factory.newDocumentBuilder();        Document document = builder.parse(new File("src/book1.xml"));        Node price = document.getElementsByTagName("售价").item(0);        price.setTextContent("109");        //把内存中的document写到xml文档        TransformerFactory tf = TransformerFactory.newInstance();        //得到转换器        Transformer ts = tf.newTransformer();        ts.transform(new DOMSource(document), new StreamResult(new File("src/book1.xml")));    }    //向指定节点中增加孩子节点（售价节点）    @Test    public void add() throws Exception {        DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();        DocumentBuilder builder = factory.newDocumentBuilder();        Document document = builder.parse(new File("src/book1.xml"));        //创建需要增加的节点        Node price = document.createElement("售价");        price.setTextContent("59元");        //得到需要增加的节点的父亲        Node parent = document.getElementsByTagName("书").item(0);        //把需要增加的节点挂到父结点上        parent.appendChild(price);        TransformerFactory tf = TransformerFactory.newInstance();        Transformer ts = tf.newTransformer();        ts.transform(new DOMSource(document), new StreamResult(new File("src/book1.xml")));    }    //向指定位置上插入售价节点    @Test    public void add2() throws Exception {        DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();        DocumentBuilder builder = factory.newDocumentBuilder();        Document document = builder.parse(new File("src/book1.xml"));        Node node = document.createElement("售价");        node.setTextContent("39元");        Node parent = document.getElementsByTagName("书").item(0);        parent.insertBefore(node, document.getElementsByTagName("书名").item(0));        TransformerFactory tf = TransformerFactory.newInstance();        Transformer ts = tf.newTransformer();        ts.transform(new DOMSource(document), new StreamResult(new File("src/book1.xml")));    }    //删除xml文档的售价结点    @Test    public void delete() throws Exception {        DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();        DocumentBuilder builder = factory.newDocumentBuilder();        Document document = builder.parse(new File("src/book1.xml"));        Node node = document.getElementsByTagName("售价").item(2);        node.getParentNode().removeChild(node);        TransformerFactory tf = TransformerFactory.newInstance();        Transformer ts = tf.newTransformer();        ts.transform(new DOMSource(document), new StreamResult(new File("src/book1.xml")));    }    //操作xml文档属性    @Test    public void updateAttribute() throws Exception {        DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();        DocumentBuilder builder = factory.newDocumentBuilder();        Document document = builder.parse(new File("src/book1.xml"));        //操作xml文档的元素时，一般都把元素当作node对象，但是程序员如果发现node不好使时，就应把node强转成相应类型        Node node = document.getElementsByTagName("书").item(0);        Element book = null;        if (node.getNodeType() == Node.ELEMENT_NODE) {  //在作结点转换之前，最好先判断结点类型            book = (Element) node;        }        book.setAttribute("name", "yyyyyyy");        book.setAttribute("password", "123");        book.removeAttribute("password");        TransformerFactory tf = TransformerFactory.newInstance();        Transformer ts = tf.newTransformer();        ts.transform(new DOMSource(document), new StreamResult(new File("src/book1.xml")));    }    //遍历    public static void list(Node node) {        if (node.getNodeType() == Node.ELEMENT_NODE) {            System.out.println(node.getNodeName());        }        NodeList list = node.getChildNodes();        for (int i = 0; i < list.getLength(); i++) {            Node child = list.item(i);            list(child);        }    }}

• dom4j解析包
  • 代码实例

public classDom4j {    //读取xml文档数据：<书名>Java就业培训教程</书名>    @Test    public void read() throws Exception {        SAXReader reader = new SAXReader();        Document document = reader.read(new File("src/book1.xml"));        Element root = document.getRootElement();        Element bookname = root.element("书").element("书名");        System.out.println(bookname.getText());    }    //<书 name="yyyyyyy">    @Test    public void readAttr() throws Exception {        SAXReader reader = new SAXReader();        Document document = reader.read(new File("src/book1.xml"));        Element root = document.getRootElement();        String value = root.element("书").attributeValue("name");        System.out.println(value);    }    //向xml文档中添加<售价>19元</售价>    @Test    public void add() throws Exception {        SAXReader reader = new SAXReader();        Document document = reader.read(new File("src/book1.xml"));        Element price = DocumentHelper.createElement("售价");        price.setText("19元");        document.getRootElement().element("书").add(price);        OutputFormat format = OutputFormat.createPrettyPrint();        format.setEncoding("UTF-8");        XMLWriter writer = new XMLWriter(new FileOutputStream("src/book1.xml"), format);        writer.write(document);  //utf-8        writer.close();    }    //修改：<售价>109</售价>  为209    @Test    public void update() throws Exception {        SAXReader reader = new SAXReader();        Document document = reader.read(new File("src/book1.xml"));        Element price = (Element) document.getRootElement().element("书").elements("售价").get(1);        price.setText("209元");        OutputFormat format = OutputFormat.createPrettyPrint();        format.setEncoding("UTF-8");        XMLWriter writer = new XMLWriter(new FileOutputStream("src/book1.xml"), format);        writer.write(document);  //utf-8        writer.close();    }    //删除：<售价>109</售价>    @Test    public void delete() throws Exception {        SAXReader reader = new SAXReader();        Document document = reader.read(new File("src/book1.xml"));        Element price = (Element) document.getRootElement().element("书").elements("售价").get(0);        price.getParent().remove(price);        OutputFormat format = OutputFormat.createPrettyPrint();        format.setEncoding("UTF-8");        XMLWriter writer = new XMLWriter(new FileOutputStream("src/book1.xml"), format);        writer.write(document);  //utf-8        writer.close();    }    //向指定位置增加售价结点    @Test    public void add2() throws Exception {        SAXReader reader = new SAXReader();        Document document = reader.read(new File("src/book1.xml"));        Element price = DocumentHelper.createElement("售价");        price.setText("19元");        List list = document.getRootElement().element("书").elements();        list.add(1, price);        OutputFormat format = OutputFormat.createPrettyPrint();        format.setEncoding("UTF-8");        XMLWriter writer = new XMLWriter(new FileOutputStream("src/book1.xml"), format);        writer.write(document);  //utf-8        writer.close();    }    @Test    public void findWithXpath() throws Exception {        SAXReader reader = new SAXReader();        Document document = reader.read(new File("src/book1.xml"));        Element e = (Element) document.selectNodes("//书名").get(1);        System.out.println(e.getText());    }    @Test    public void findUser() throws Exception {        String username = "aaa";        String password = "1233";        SAXReader reader = new SAXReader();        Document document = reader.read(new File("src/users.xml"));        Element e = (Element) document.selectSingleNode("//user[@username='" + username + "' and @password='" + password + "']");        if (e != null) {            System.out.println("让用户登陆成功！！");        } else {            System.out.println("用户名和密码不正确！！");        }    }}

sax解析原理和实例

publicclassSax {    /**     * sax方式解析book1.xml文件     *     * @throws SAXException     * @throws ParserConfigurationException     * @throws IOException     */publicstaticvoidmain(String[] args) throws ParserConfigurationException, SAXException, IOException {        //1.创建工厂        SAXParserFactory factory = SAXParserFactory.newInstance();        //2.用工厂创建解析器        SAXParser sp = factory.newSAXParser();        //3.利用解析器得到reader        XMLReader reader = sp.getXMLReader();        //4、在解析xml文档之前，设置好事件处理器        reader.setContentHandler(new MyContentHandler2());        //4.利用reader读取 xml文档        reader.parse("src/book1.xml");    }    //用于获取第一个售价节点的值：<售价>109</售价>classMyContentHandler2extendsDefaultHandler {        privateboolean isOk = false;        privateint index = 1;        @Override        publicvoidcharacters(char[] ch, int start, int length)                throws SAXException {            if (isOk == true && index == 1) {                System.out.println(new String(ch, start, length));            }        }        @Override        publicvoidstartElement(String uri, String localName, String name,                                 Attributes attributes) throws SAXException {            if (name.equals("售价")) {                isOk = true;            }        }        @Override        publicvoidendElement(String uri, String localName, String name)                throws SAXException {            if (name.equals("售价")) {                isOk = false;                index++;            }        }    }    //得到xml文档内容的事件处理器classMyContentHandlerimplementsContentHandler {        publicvoidstartElement(String uri, String localName, String name,                                 Attributes atts) throws SAXException {            System.out.println("当前解析到了:" + name + ",这个标签是开始标签");            for (int i = 0; i < atts.getLength(); i++) {                String attname = atts.getQName(i);                String attvalue = atts.getValue(i);                System.out.println(attname + "=" + attvalue);            }        }        publicvoidendElement(String uri, String localName, String name)                throws SAXException {            System.out.println("当前解析到了:" + name + ",这个标签是结束标签");        }        publicvoidcharacters(char[] ch, int start, int length)                throws SAXException {            System.out.println("当前解析到了内容：" + new String(ch, start, length));        }        publicvoidendDocument() throws SAXException {            // TODO Auto-generated method stub        }        publicvoidendPrefixMapping(String prefix) throws SAXException {            // TODO Auto-generated method stub        }        publicvoidignorableWhitespace(char[] ch, int start, int length)                throws SAXException {            // TODO Auto-generated method stub        }        publicvoidprocessingInstruction(String target, String data)                throws SAXException {            // TODO Auto-generated method stub        }        publicvoidsetDocumentLocator(Locator locator) {            // TODO Auto-generated method stub        }        publicvoidskippedEntity(String name) throws SAXException {            // TODO Auto-generated method stub        }        publicvoidstartDocument() throws SAXException {            // TODO Auto-generated method stub        }        publicvoidstartPrefixMapping(String prefix, String uri)                throws SAXException {            // TODO Auto-generated method stub        }    }}

XPATH(属于dom4j的包,需要导入使用xpath需要导入jaxen-1.1-beta-6)

• xpath学习文档