了解 XMLStreamReader 和 START_ELEMENT

Question

考虑以下 XML 文件：

% cat test.xml
<?xml version="1.0" encoding="utf-8"?>
<root>
</root>

为什么我在使用 XMLStreamReader. Code is (lifted from 时没有收到 START_ELEMENT 事件：

% cat Demo.java
import java.io.FileReader;
import javax.xml.stream.*;

public class Demo {

    public static void main(String[] args) throws Exception {
        XMLInputFactory factory = XMLInputFactory.newInstance();
        XMLStreamReader sr = factory.createXMLStreamReader(new FileReader("test.xml"));
        System.out.println(sr.getClass());

        while (sr.hasNext()) {
            int eventType = sr.next();

            if (eventType == XMLStreamReader.START_DOCUMENT) {
                System.out.println("Start Document" );
            } else if (eventType == XMLStreamReader.END_DOCUMENT) {
                System.out.println("End Document" );
            } else if (eventType == XMLStreamReader.END_ELEMENT) {
                System.out.println("End Element:    " + sr.getLocalName());
            } else if (eventType == XMLStreamReader.START_ELEMENT) {
                System.out.println("Start Element:  " + sr.getLocalName());
            }
        }
    }

}

我这边的输出：

% javac Demo.java
% java Demo test.xml
class com.sun.org.apache.xerces.internal.impl.XMLStreamReaderImpl
Start Element:  root
End Element:    root
End Document

参考：

% java --version
openjdk 11.0.14 2022-01-18
OpenJDK Runtime Environment (build 11.0.14+9-post-Debian-1deb11u1)
OpenJDK 64-Bit Server VM (build 11.0.14+9-post-Debian-1deb11u1, mixed mode, sharing)

Answer 1

原来文档有描述：

An XMLStreamReader instance is created with an initial event type START_DOCUMENT.

所以代码应该改为：

% cat Demo.java
import java.io.FileReader;
import javax.xml.stream.*;

public class Demo {

    public static void main(String[] args) throws Exception {
        XMLInputFactory factory = XMLInputFactory.newInstance();
        XMLStreamReader sr = factory.createXMLStreamReader(new FileReader("test.xml"));
        System.out.println(sr.getClass());

        boolean hasNext;
        do {
            int eventType = sr.getEventType();

            if (eventType == XMLStreamReader.START_DOCUMENT) {
                System.out.println("Start Document" );
            } else if (eventType == XMLStreamReader.END_DOCUMENT) {
                System.out.println("End Document" );
            } else if (eventType == XMLStreamReader.END_ELEMENT) {
                System.out.println("End Element:    " + sr.getLocalName());
            } else if (eventType == XMLStreamReader.START_ELEMENT) {
                System.out.println("Start Element:  " + sr.getLocalName());
            }
            hasNext = sr.hasNext();
            if(hasNext) sr.next();
        } while( hasNext );
    }
}

循环使用XMLEventReader更容易写：

% cat Demo2.java
import java.io.FileReader;
import javax.xml.stream.*;
import javax.xml.stream.events.*;

public class Demo2 {

    public static void main(String[] args) throws Exception {
        XMLInputFactory factory = XMLInputFactory.newInstance();
        XMLEventReader er = factory.createXMLEventReader(new FileReader("test.xml"));
        System.out.println(er.getClass());

        while(er.hasNext()) {
            XMLEvent xmlEvent = er.nextEvent();
            int eventType = xmlEvent.getEventType();
            if (eventType == XMLStreamConstants.START_DOCUMENT) {
                System.out.println("Start Document" );
            } else if (eventType == XMLStreamConstants.END_DOCUMENT) {
                System.out.println("End Document" );
            } else if (eventType == XMLStreamConstants.END_ELEMENT) {
                System.out.println("End Element:    " + xmlEvent.asEndElement().getName());
            } else if (eventType == XMLStreamConstants.START_ELEMENT) {
                System.out.println("Start Element:  " + xmlEvent.asStartElement().getName());
            }
        }
    }
}

了解 XMLStreamReader 和 START_ELEMENT

Understanding XMLStreamReader and START_ELEMENT

java

xml

stax