Stax和DOM解析之间的性能差异

Faz*_*zal 4 java xml-parsing

我已经使用DOM很长一段时间了,因此DOM解析性能非常好.即使在处理大约4-7 MB的XML时,解析速度也很快.我们面临的DOM问题是内存占用空间,一旦我们开始处理大型XML,就会变得非常庞大.

最近我尝试转移到Stax(用于XML的流解析器),它们被认为是第二代解析器(阅读Stax,它说它现在是最快的解析器).当我尝试用于大型XML的Stax解析器大约4MB时,内存占用量明显减少,但是解析整个XML并创建java对象的时间比DOM增加了近5倍.

我使用了stax的sjsxp.jar实现.

我可以在某种程度上从逻辑上推断,由于解析器的流性质但性能可能不是很好,但减少了5倍(例如,DOM为此XML构建对象需要大约8秒,而Stax解析平均需要大约40秒绝对不会被接受.

我完全错过了一些观点,因为我无法接受这些性能数字

小智 7

package parsers;

/**
 *
 * @author Arthur Kushman
 */

import java.io.File;
import java.io.IOException;

import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;

import org.w3c.dom.Document;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;
import org.w3c.dom.Element;


public class DOMTest {

  public static void main(String[] args) {
  long time1 = System.currentTimeMillis();
   try {
    DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
    DocumentBuilder db = dbf.newDocumentBuilder();
    Document doc = db.parse(new File("/Users/macpro/Desktop/myxml.xml"));
    doc.getDocumentElement().normalize();
    // System.out.println("Root Element: "+doc.getDocumentElement().getNodeName());
    NodeList nodeList = doc.getElementsByTagName("input");
    // System.out.println("Information of all elements in input");

    for (int s=0;s<nodeList.getLength();s++) {
      Node firstNode = nodeList.item(s);
      if (firstNode.getNodeType() == Node.ELEMENT_NODE) {
        Element firstElement = (Element)firstNode;
        NodeList firstNameElementList = firstElement.getElementsByTagName("href");
        Element firstNameElement = (Element)firstNameElementList.item(0);
        NodeList firstName = firstNameElement.getChildNodes();
        System.out.println("First Name: "+((Node)firstName.item(s)).getNodeValue());        
      }
    }


   } catch (Exception ex) {
    System.out.println(ex.getMessage());
    System.exit(1);
   }
  long time2 = System.currentTimeMillis() - time1;
  System.out.println(time2);
  }

}
Run Code Online (Sandbox Code Playgroud)

45工厂

package parsers;

/**
 *
 * @author Arthur Kushman
 */
import javax.xml.stream.*;
import java.io.*;
import javax.xml.namespace.QName;

public class StAXTest {

  public static void main(String[] args) throws Exception {
  long time1 = System.currentTimeMillis();
    XMLInputFactory factory = XMLInputFactory.newInstance();
    // factory.setXMLReporter(myXMLReporter);
    XMLStreamReader reader = factory.createXMLStreamReader(
            new FileInputStream(
            new File("/Users/macpro/Desktop/myxml.xml")));

    /*String encoding = reader.getEncoding();

    System.out.println("Encoding: "+encoding);

    while (reader.hasNext()) {
      int event = reader.next();
      if (event == XMLStreamConstants.START_ELEMENT) {
        QName element = reader.getName();
        // String text = reader.getText();
        System.out.println("Element: "+element);
        // while (event != XMLStreamConstants.END_ELEMENT) {
          System.out.println("Text: "+reader.getLocalName());
        // }
      }
    }*/

  try {
    int inElement = 0;
    for (int event = reader.next();event != XMLStreamConstants.END_DOCUMENT;
    event = reader.next()) {
      switch (event) {
        case XMLStreamConstants.START_ELEMENT:
          if (isElement(reader.getLocalName(), "href")) {
            inElement++;
          }
          break;
        case XMLStreamConstants.END_ELEMENT:
          if (isElement(reader.getLocalName(), "href")) {
            inElement--;
            if (inElement == 0) System.out.println();
          }
          break;
        case XMLStreamConstants.CHARACTERS:
          if (inElement>0) System.out.println(reader.getText());
          break;
        case XMLStreamConstants.CDATA:
          if (inElement>0)  System.out.println(reader.getText());
          break;
      }
    }
    reader.close();
  } catch (XMLStreamException ex) {
    System.out.println(ex.getMessage());
    System.exit(1);
  }
    // System.out.println(System.currentTimeMillis());
    long time2 = System.currentTimeMillis() - time1;
    System.out.println(time2);
 }

  public static boolean isElement(String name, String element) {
    if (name.equals(element)) return true;
    return false;
  }

}
Run Code Online (Sandbox Code Playgroud)

23工厂

StAX获胜=)