java - JAXB 可以分块解析大型 XML 文件吗

Question

我需要解析可能很大的 XML 文件，其中的模式已经在多个 XSD 文件中提供给我，因此 XML 绑定(bind)非常受欢迎。我想知道是否可以使用 JAXB 分 block 解析文件，如果可以，如何。

Answer 1

因为代码很重要，这里是 PartialUnmarshaller谁将大文件读入 block 中。可以这样使用new PartialUnmarshaller<YourClass>(stream, YourClass.class)

import javax.xml.bind.JAXBContext;
import javax.xml.bind.JAXBException;
import javax.xml.bind.Unmarshaller;
import javax.xml.stream.*;
import java.io.InputStream;
import java.util.List;
import java.util.NoSuchElementException;
import java.util.stream.Collectors;
import java.util.stream.IntStream;

import static javax.xml.stream.XMLStreamConstants.*;

public class PartialUnmarshaller<T> {
    XMLStreamReader reader;
    Class<T> clazz;
    Unmarshaller unmarshaller;

    public PartialUnmarshaller(InputStream stream, Class<T> clazz) throws XMLStreamException, FactoryConfigurationError, JAXBException {
        this.clazz = clazz;
        this.unmarshaller = JAXBContext.newInstance(clazz).createUnmarshaller();
        this.reader = XMLInputFactory.newInstance().createXMLStreamReader(stream);

        /* ignore headers */
        skipElements(START_DOCUMENT, DTD);
        /* ignore root element */
        reader.nextTag();
        /* if there's no tag, ignore root element's end */
        skipElements(END_ELEMENT);
    }

    public T next() throws XMLStreamException, JAXBException {
        if (!hasNext())
            throw new NoSuchElementException();

        T value = unmarshaller.unmarshal(reader, clazz).getValue();

        skipElements(CHARACTERS, END_ELEMENT);
        return value;
    }

    public boolean hasNext() throws XMLStreamException {
        return reader.hasNext();
    }

    public void close() throws XMLStreamException {
        reader.close();
    }

    void skipElements(int... elements) throws XMLStreamException {
        int eventType = reader.getEventType();

        List<Integer> types = asList(elements);
        while (types.contains(eventType))
            eventType = reader.next();
    }
}