最快，最优化的方式读取xml

Question

我在XML文件下面有这个

<book>
<person>
  <first>Kiran</first>
  <last>Pai</last>
  <age>22</age>
</person>
<person>
  <first>Bill</first>
  <last>Gates</last>
  <age>46</age>
</person>
<person>
  <first>Steve</first>
  <last>Jobs</last>
  <age>40</age>
</person>
</book>

现在，下面显示了从XML文件读取数据的Java程序。

import java.io.File;
import org.w3c.dom.Document;
import org.w3c.dom.*;

import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.parsers.DocumentBuilder;
import org.xml.sax.SAXException;
import org.xml.sax.SAXParseException;

public class ReadAndPrintXMLFile{

    public static void main (String argv []){
    try {

            DocumentBuilderFactory docBuilderFactory = DocumentBuilderFactory.newInstance();
            DocumentBuilder docBuilder = docBuilderFactory.newDocumentBuilder();
            Document doc = docBuilder.parse (new File("book.xml"));

            // normalize text representation
            doc.getDocumentElement ().normalize ();
            System.out.println ("Root element of the doc is " + 
                 doc.getDocumentElement().getNodeName());


            NodeList listOfPersons = doc.getElementsByTagName("person");
            int totalPersons = listOfPersons.getLength();
            System.out.println("Total no of people : " + totalPersons);

            for(int s=0; s<listOfPersons.getLength() ; s++){


                Node firstPersonNode = listOfPersons.item(s);
                if(firstPersonNode.getNodeType() == Node.ELEMENT_NODE){


                    Element firstPersonElement = (Element)firstPersonNode;

                    //-------
                    NodeList firstNameList = firstPersonElement.getElementsByTagName("first");
                    Element firstNameElement = (Element)firstNameList.item(0);

                    NodeList textFNList = firstNameElement.getChildNodes();
                    System.out.println("First Name : " + 
                           ((Node)textFNList.item(0)).getNodeValue().trim());

                    //-------
                    NodeList lastNameList = firstPersonElement.getElementsByTagName("last");
                    Element lastNameElement = (Element)lastNameList.item(0);

                    NodeList textLNList = lastNameElement.getChildNodes();
                    System.out.println("Last Name : " + 
                           ((Node)textLNList.item(0)).getNodeValue().trim());

                    //----
                    NodeList ageList = firstPersonElement.getElementsByTagName("age");
                    Element ageElement = (Element)ageList.item(0);

                    NodeList textAgeList = ageElement.getChildNodes();
                    System.out.println("Age : " + 
                           ((Node)textAgeList.item(0)).getNodeValue().trim());

                    //------


                }//end of if clause


            }//end of for loop with s var


        }catch (SAXParseException err) {
        System.out.println ("** Parsing error" + ", line " 
             + err.getLineNumber () + ", uri " + err.getSystemId ());
        System.out.println(" " + err.getMessage ());

        }catch (SAXException e) {
        Exception x = e.getException ();
        ((x == null) ? e : x).printStackTrace ();

        }catch (Throwable t) {
        t.printStackTrace ();
        }
        //System.exit (0);

    }//end of main


}

结果是..

Root element of the doc is book
Total no of people : 3
First Name : Kiran
Last Name : Pai
Age : 22
First Name : Bill
Last Name : Gates
Age : 46
First Name : Steve
Last Name : Jobs
Age : 40

现在，我的查询是请告知是否还有其他最快的方式来读取此xml，我正在查看斋戒，请告知..！

Answer 1

如果性能对您而言很重要，则应首选SAX或StAX（http://en.wikipedia.org/wiki/StAX）而不是DOM。

使用时DOM，第一次将XML文件解析为对象模型，然后您可以提出要求。因此，对您而言，算法有两遍。

使用时SAX，在解析过程中，某些基于事件或推送模型的回调将被调用（startDocument，endElement...） 。SAX

使用StAX，您可以控制解析。您将光标从一个元素移动到另一个。这是拉模型。

对于包含32910000人的文件，我将我的版本与SAX的（Blaise Doughan的）过度回答进行了比较StAX。我删除了所有System.out.println指示。我的程序花了106秒读取所有文件，另一个花了94秒。我想这SAX是较慢的，因为callback即使它们都不执行任何操作都将被调用（push模型），而使用StAX时，光标仅在“ interresting”元素（pull模型）上移动。

例如，使用Java 7：

import java.io.File;

import javax.xml.parsers.SAXParser;
import javax.xml.parsers.SAXParserFactory;

import org.xml.sax.Attributes;
import org.xml.sax.SAXException;
import org.xml.sax.helpers.DefaultHandler;

public class ReadAndPrintXMLFileWithSax {

    public static void main(String[] args) throws Exception {
        SAXParserFactory fabrique = SAXParserFactory.newInstance();
        SAXParser parser = fabrique.newSAXParser();

        File file = new File("book.xml");
        BookHandler handler = new BookHandler();
        parser.parse(file, handler);
    }

    public static class BookHandler extends DefaultHandler {
        private int count = 0;
        private StringBuilder buffer;

        @Override
        public void startElement(String uri, String localName, String qName,
                Attributes attributes) throws SAXException {
            switch (qName) {
            case "person":
                count++;
                break;
            case "first":
                buffer = new StringBuilder("First Name : ");
                break;
            case "last":
                buffer = new StringBuilder("Last Name : ");
                break;
            case "age":
                buffer = new StringBuilder("Age : ");
                break;
            }
        }

        @Override
        public void characters(char[] ch, int start, int length)
                throws SAXException {
            String content = new String(ch, start, length);
            if (buffer != null)
                buffer.append(content);
        }

        @Override
        public void endElement(String uri, String localName, String qName)
                throws SAXException {
            switch (qName) {
            case "first":
            case "last":
            case "age":
                System.out.println(buffer.toString());
                break;
            }
        }

        @Override
        public void endDocument() throws SAXException {
            System.out.println(count + " persons");
        }
    }
}