java - 如何在JAVA中读取一个大的XML文件并根据标签将其分割成小的XML文件？

Question

我是JAVA编程新手，现在我需要JAVA程序来读取包含..标签的大XML文件。输入示例如下。

输入.xml

<row>
<Name>Filename1</Name>
</row>
<row>
<Name>Filename2</Name>
</row>
<row>
<Name>Filename3</Name>
</row>
<row>
<Name>Filename4</Name>
</row>
<row>
<Name>Filename5</Name>
</row>
<row>
<Name>Filename6</Name>
</row>
 .
 .

我需要首先输出 <row> </row>作为单个 .xml 文件，文件名为 filename1.xml第二个 <row>..</row>如 filename2.xml 等。

谁能告诉我如何用Java以简单的方式做到这一点的步骤，如果你提供任何示例代码，这将非常有用？

Answer 1

您可以使用 StAX 执行以下操作，因为您说您的 xml 很大

适合您的用例的代码

以下代码使用 StAX API 来分解您问题中概述的文档:

 import java.io.*;
    import java.util.*;

    import javax.xml.namespace.QName;
    import javax.xml.stream.*;
    import javax.xml.stream.events.*;

    public class Demo {

        public static void main(String[] args) throws Exception  {
            Demo demo = new Demo();
            demo.split("src/forum7408938/input.xml", "nickname");
            //demo.split("src/forum7408938/input.xml", null);
        }

        private void split(String xmlResource, String condition) throws Exception {
            XMLEventFactory xef = XMLEventFactory.newFactory();
            XMLInputFactory xif = XMLInputFactory.newInstance();
            XMLEventReader xer = xif.createXMLEventReader(new FileReader(xmlResource));
            StartElement rootStartElement = xer.nextTag().asStartElement(); // Advance to statements element
            StartDocument startDocument = xef.createStartDocument();
            EndDocument endDocument = xef.createEndDocument();

            XMLOutputFactory xof = XMLOutputFactory.newFactory();
            while(xer.hasNext() && !xer.peek().isEndDocument()) {
                boolean metCondition;
                XMLEvent xmlEvent = xer.nextTag();
                if(!xmlEvent.isStartElement()) {
                    break;
                }
         // Be able to split XML file into n parts with x split elements(from
            // the dummy XML example staff is the split element).
            StartElement breakStartElement = xmlEvent.asStartElement();
            List<XMLEvent> cachedXMLEvents = new ArrayList<XMLEvent>();

            // BOUNTY CRITERIA
            // I'd like to be able to specify condition that must be in the 
            // split element i.e. I want only staff which have nickname, I want 
            // to discard those without nicknames. But be able to also split 
            // without conditions while running split without conditions.
            if(null == condition) {
                cachedXMLEvents.add(breakStartElement);
                metCondition = true;
            } else {
                cachedXMLEvents.add(breakStartElement);
                xmlEvent = xer.nextEvent();
                metCondition = false;
                while(!(xmlEvent.isEndElement() && xmlEvent.asEndElement().getName().equals(breakStartElement.getName()))) {
                    cachedXMLEvents.add(xmlEvent);
                    if(xmlEvent.isStartElement() && xmlEvent.asStartElement().getName().getLocalPart().equals(condition)) {
                        metCondition = true;
                        break;
                    }
                    xmlEvent = xer.nextEvent();
                }
            }

            if(metCondition) {
                // Create a file for the fragment, the name is derived from the value of the id attribute
                FileWriter fileWriter = null;
                fileWriter = new FileWriter("src/forum7408938/" + breakStartElement.getAttributeByName(new QName("id")).getValue() + ".xml");

                // A StAX XMLEventWriter will be used to write the XML fragment
                XMLEventWriter xew = xof.createXMLEventWriter(fileWriter);
                xew.add(startDocument);

                // BOUNTY CRITERIA
                // The content of the spitted files should be wrapped in the 
                // root element from the original file(like in the dummy example
                // company)
                xew.add(rootStartElement);

                // Write the XMLEvents that were cached while when we were
                // checking the fragment to see if it matched our criteria.
                for(XMLEvent cachedEvent : cachedXMLEvents) {
                    xew.add(cachedEvent);
                }

                // Write the XMLEvents that we still need to parse from this
                // fragment
                xmlEvent = xer.nextEvent();
                while(xer.hasNext() && !(xmlEvent.isEndElement() && xmlEvent.asEndElement().getName().equals(breakStartElement.getName()))) {
                    xew.add(xmlEvent);
                    xmlEvent = xer.nextEvent();
                }
                xew.add(xmlEvent);

                // Close everything we opened
                xew.add(xef.createEndElement(rootStartElement.getName(), null));
                xew.add(endDocument);
                fileWriter.close();
            }
        }
    }

}