JAVA通过XPath解析XML性能比较详解

<Workbook xmlns="urn:schemas-microsoft-com:office:spreadsheet" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:x="urn:schemas-microsoft-com:office:excel" xmlns:ss="urn:schemas-microsoft-com:office:spreadsheet" xmlns:html="http://www.w3.org/TR/REC-html40">
 <Worksheet ss:Name="Sheet1">
  <Table ss:ExpandedColumnCount="81" ss:ExpandedRowCount="687" x:FullColumns="1" x:FullRows="1" ss:DefaultColumnWidth="52.5" ss:DefaultRowHeight="15.5625">
   <Row ss:AutoFitHeight="0">
     <Cell>
     <Data ss:Type="String">敲代码的耗子</Data>
     </Cell> 
   </Row>
   <Row ss:AutoFitHeight="0">
     <Cell>
     <Data ss:Type="String">Sunny</Data>
     </Cell> 
   </Row>
  </Table>
 </Worksheet>
</Workbook>

package XPath;
import java.io.IOException;
import java.io.InputStream;
import java.util.HashMap;
import java.util.List;
import java.util.Map;

import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.parsers.ParserConfigurationException;
import javax.xml.xpath.XPathConstants;
import javax.xml.xpath.XPathExpression;
import javax.xml.xpath.XPathExpressionException;
import javax.xml.xpath.XPathFactory;

import org.dom4j.Document;
import org.dom4j.DocumentException;
import org.dom4j.Element;
import org.dom4j.XPath;
import org.dom4j.io.SAXReader;
import org.w3c.dom.NodeList;
import org.xml.sax.SAXException;

/**
 * DOM4J DOM XML XPath
 * @author hao
 */
public class TestDom4jXpath {
  public static void main(String[] args) {
    read1();
    read2();
    read3();
    read4();//read3（）方法一样，但是XPath表达式不同
    read5();
  }
  
  public static void read1() {
    /*
     * use local-name() and namespace-uri() in XPath
     */
    try {
      long startTime=System.currentTimeMillis();
      SAXReader reader = new SAXReader();
      InputStream in = TestDom4jXpath.class.getClassLoader().getResourceAsStream("XPath\\XXX.xml");
      Document doc = reader.read(in);
      /*String xpath ="//*[local-name()='Workbook' and namespace-uri()='urn:schemas-microsoft-com:office:spreadsheet']"
          + "/*[local-name()='Worksheet']"
          + "/*[local-name()='Table']"
          + "/*[local-name()='Row'][4]"
          + "/*[local-name()='Cell'][3]"
          + "/*[local-name()='Data'][1]";*/
      String xpath ="//*[local-name()='Row'][4]/*[local-name()='Cell'][3]/*[local-name()='Data'][1]";
      System.err.println("=====use local-name() and namespace-uri() in XPath====");
      System.err.println("XPath：" + xpath);
      @SuppressWarnings("unchecked")
      List<Element> list = doc.selectNodes(xpath);
      for(Object o:list){ 
        Element e = (Element) o; 
        String show=e.getStringValue();
        System.out.println("show = " + show); 
      long endTime=System.currentTimeMillis();
      System.out.println("程序运行时间： "+(endTime-startTime)+"ms");
      } 
    } catch (DocumentException e) {
      e.printStackTrace();
    }
  }
  
  public static void read2() {
    /*
     * set xpath namespace(setNamespaceURIs)
     */
    try {
      long startTime=System.currentTimeMillis();
      Map map = new HashMap();
      map.put("Workbook","urn:schemas-microsoft-com:office:spreadsheet");
      SAXReader reader = new SAXReader();
      InputStream in = TestDom4jXpath.class.getClassLoader().getResourceAsStream("XPath\\XXX.xml");
      Document doc = reader.read(in);
      String xpath ="//Workbook:Row[4]/Workbook:Cell[3]/Workbook:Data[1]";
      System.err.println("=====use setNamespaceURIs() to set xpath namespace====");
      System.err.println("XPath：" + xpath);
      XPath x = doc.createXPath(xpath);
      x.setNamespaceURIs(map);
      @SuppressWarnings("unchecked")
      List<Element> list = x.selectNodes(doc);
      for(Object o:list){ 
        Element e = (Element) o; 
        String show=e.getStringValue();
        System.out.println("show = " + show);  
      long endTime=System.currentTimeMillis();
      System.out.println("程序运行时间： "+(endTime-startTime)+"ms");
      } 
    } catch (DocumentException e) {
      e.printStackTrace();
    }
  }
  
  public static void read3() {
    /*
     * set DocumentFactory() namespace(setXPathNamespaceURIs)
     */
    try {
      long startTime=System.currentTimeMillis();
      Map map = new HashMap();
      map.put("Workbook","urn:schemas-microsoft-com:office:spreadsheet");
      SAXReader reader = new SAXReader();
      InputStream in = TestDom4jXpath.class.getClassLoader().getResourceAsStream("XPath\\XXX.xml");
      reader.getDocumentFactory().setXPathNamespaceURIs(map);
      Document doc = reader.read(in);
      String xpath ="//Workbook:Row[4]/Workbook:Cell[3]/Workbook:Data[1]";
      System.err.println("=====use setXPathNamespaceURIs() to set DocumentFactory() namespace====");
      System.err.println("XPath：" + xpath);
      @SuppressWarnings("unchecked")
      List<Element> list = doc.selectNodes(xpath);
      for(Object o:list){ 
        Element e = (Element) o; 
        String show=e.getStringValue();
        System.out.println("show = " + show);
      long endTime=System.currentTimeMillis();
      System.out.println("程序运行时间： "+(endTime-startTime)+"ms");  
      } 
    } catch (DocumentException e) {
      e.printStackTrace();
    }
  }
  
  public static void read4() {
    /*
     * 同read3（）方法一样，但是XPath表达式不同
     */
    try {
      long startTime=System.currentTimeMillis();
      Map map = new HashMap();
      map.put("Workbook","urn:schemas-microsoft-com:office:spreadsheet");
      SAXReader reader = new SAXReader();
      InputStream in = TestDom4jXpath.class.getClassLoader().getResourceAsStream("XPath\\XXX.xml");
      reader.getDocumentFactory().setXPathNamespaceURIs(map);
      Document doc = reader.read(in);
      String xpath ="//Workbook:Worksheet/Workbook:Table/Workbook:Row[4]/Workbook:Cell[3]/Workbook:Data[1]";
      System.err.println("=====use setXPathNamespaceURIs() to set DocumentFactory() namespace====");
      System.err.println("XPath：" + xpath);
      @SuppressWarnings("unchecked")
      List<Element> list = doc.selectNodes(xpath);
      for(Object o:list){ 
        Element e = (Element) o; 
        String show=e.getStringValue();
        System.out.println("show = " + show);
      long endTime=System.currentTimeMillis();
      System.out.println("程序运行时间： "+(endTime-startTime)+"ms");  
      } 
    } catch (DocumentException e) {
      e.printStackTrace();
    }
  }
  
  public static void read5() {
    /*
     * DOM and XPath
     */
    try {
      long startTime=System.currentTimeMillis();
      DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
      dbf.setNamespaceAware(false);
      DocumentBuilder builder = dbf.newDocumentBuilder();
      InputStream in = TestDom4jXpath.class.getClassLoader().getResourceAsStream("XPath\\XXX.xml");
      org.w3c.dom.Document doc = builder.parse(in);
      XPathFactory factory = XPathFactory.newInstance();
      javax.xml.xpath.XPath x = factory.newXPath();
      //选取所有class元素的name属性
      String xpath = "//Workbook/Worksheet/Table/Row[4]/Cell[3]/Data[1]";
      System.err.println("=====Dom XPath====");
      System.err.println("XPath：" + xpath);
      XPathExpression expr = x.compile(xpath);
      NodeList nodes = (NodeList)expr.evaluate(doc, XPathConstants.NODE);
      for(int i = 0; i<nodes.getLength();i++) {
        System.out.println("show = " + nodes.item(i).getNodeValue());
      long endTime=System.currentTimeMillis();
      System.out.println("程序运行时间： "+(endTime-startTime)+"ms");
      }
    } catch(XPathExpressionException e) {
      e.printStackTrace();
    } catch(ParserConfigurationException e) {
      e.printStackTrace();
    } catch(SAXException e) {
      e.printStackTrace();
    } catch(IOException e) {
      e.printStackTrace();
    }
  }
}