读取多个xml文件java

Question

我有 ~25000 个 XML 文件需要用 Java 读取。这是我的代码：

private static void ProcessFile() {

    try {

        File fXmlFile = new File("C:/Users/Emolk/Desktop/000010.xml");

        DocumentBuilderFactory dbFactory = DocumentBuilderFactory.newInstance();

        DocumentBuilder dBuilder = dbFactory.newDocumentBuilder();

        Document doc = dBuilder.parse(fXmlFile);

        doc.getDocumentElement().normalize();

        System.out.println("Root element :" + doc.getDocumentElement().getNodeName());

        NodeList nList = doc.getElementsByTagName("sindex");

        System.out.println("----------------------------");

        for (int temp = 0; temp < nList.getLength(); temp++) {

            Node nNode = nList.item(temp);

            System.out.println("");

            if (nNode.getNodeType() == Node.ELEMENT_NODE) {

                Element eElement = (Element) nNode;

                System.out.println("Name : " + eElement.getElementsByTagName("name").item(0).getTextContent());

                System.out.println("Count : " + eElement.getElementsByTagName("count").item(0).getTextContent());

                Entity CE = new Entity(eElement.getElementsByTagName("name").item(0).getTextContent(), Integer.parseInt(eElement.getElementsByTagName("count").item(0).getTextContent()));

                Entities.add(CE);

                System.out.println("Entity added! ");

            }

        }

        System.out.println(Entities);

        } catch (Exception e) {

        e.printStackTrace();

        }

}

我如何读取 25000 个文件而不是一个？

我尝试使用以下方法将所有 xml 文件连接在一起：https : //www.sobolsoft.com/howtouse/combine-xml-files.htm

但这给了我这个错误：

[Fatal Error] joined.xml:130:2: The markup in the document following the 

root element must be well-formed.

Answer 1

如果性能不是问题，那么您可以执行以下操作，&nbsp; &nbsp; import java.io.File;&nbsp; &nbsp; import java.util.List;&nbsp; &nbsp; import javax.xml.parsers.DocumentBuilder;&nbsp; &nbsp; import javax.xml.parsers.DocumentBuilderFactory;&nbsp; &nbsp; import org.w3c.dom.Document;&nbsp; &nbsp; import org.w3c.dom.NodeList;&nbsp; &nbsp; public class ReadFiles {&nbsp; &nbsp; &nbsp; &nbsp; public static void main(String[] args) {&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; File dir = new File("D:/Work"); //Directory where your file exists&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; File [] files = dir.listFiles();&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; for(File file : files) {&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; if(file.isFile() && file.getName().endsWith(".xml")) { //You can validate file name with extension if needed&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; ProcessFile(file, Entities);&nbsp; // Assumed you have declared Entities, may be list of other collection&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; }&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; }&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; System.out.println(Entities);&nbsp; &nbsp; &nbsp; &nbsp; }&nbsp; &nbsp; &nbsp; &nbsp; private static void ProcessFile(File fXmlFile, List<E> Entities) {&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; try {&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; DocumentBuilderFactory dbFactory = DocumentBuilderFactory.newInstance();&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; DocumentBuilder dBuilder = dbFactory.newDocumentBuilder();&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; Document doc = dBuilder.parse(fXmlFile);&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; doc.getDocumentElement().normalize();&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; System.out.println("Root element :" + doc.getDocumentElement().getNodeName());&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; NodeList nList = doc.getElementsByTagName("sindex");&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; System.out.println("----------------------------");&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; for (int temp = 0; temp < nList.getLength(); temp++) {&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; Node nNode = nList.item(temp);&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; System.out.println("");&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; if (nNode.getNodeType() == Node.ELEMENT_NODE) {&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; Element eElement = (Element) nNode;&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; System.out.println("Name : " + eElement.getElementsByTagName("name").item(0).getTextContent());&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; System.out.println("Count : " + eElement.getElementsByTagName("count").item(0).getTextContent());&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; Entity CE = new Entity(eElement.getElementsByTagName("name").item(0).getTextContent(), Integer.parseInt(eElement.getElementsByTagName("count").item(0).getTextContent()));&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; Entities.add(CE);&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; System.out.println("Entity added! ");&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; }&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; }&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp;&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; } catch (Exception e) {&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; e.printStackTrace();&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; }&nbsp; &nbsp; &nbsp; &nbsp; }&nbsp; &nbsp; }

Answer 2

要读取多个文件，您应该使用某种循环进行迭代。您可以扫描目录中的所有有效文件。File folder = new File("path/to/directory");File[] files = folder.listFiles();for (int i = 0; i < files.length; i++) {&nbsp; &nbsp; // you can also filter for .xml if needed&nbsp; &nbsp; if (files[i].isFile()) {&nbsp; &nbsp; &nbsp; &nbsp; // parse the file&nbsp; &nbsp; }}接下来，您需要决定如何解析文件：顺序或并行。由于您使用多个线程来解析文件，因此 Parallel 会快很多。一根线您可以重用您已经编写的代码，并遍历文件：for (File file : files) {&nbsp; &nbsp; processFile(file, yourListOfEntities);}多线程：获取一个ScheduledExecutorService并提交多个任务。ExecutorService service = Executors.newFixedThreadPool(5);for (File file : files) {&nbsp; &nbsp; service.execute(() -> processFile(file, yourListOfEntities));}这里有一个重要的注意事项： 的默认实现ArrayList不是线程安全的，所以你应该（因为List被多个线程使用）同步对它的访问：List<Entity> synchronizedList = Collections.synchronizedList(yourListOfEntities);此外，DocumentBuilder不是线程安全的，应该为每个线程创建一次（如果你只是调用你的方法，你就对了）。如果您考虑优化它，则此注释仅适用于这种情况。