Process parts of XML with XPath in Java

This shows you how to

1. Read in an XML file to a DOM
2. Filter out a set of Nodes with XPath
3. Perform a certain action on each of the extracted Nodes.

We will call the code with the following statement

processFilteredXml(xmlIn, xpathExpr,(node) -> {/*Do something...*/;});

In our case we want to print some creatorNames from a book.xml using “//book/creators/creator/creatorName” as xpath to perform a printNode action on each Node that matches the XPath.

Full code

@Test
public void printXml() {
    try (InputStream in = readFile("book.xml")) {
        processFilteredXml(in, "//book/creators/creator/creatorName", (node) -> {
            printNode(node, System.out);
        });
    } catch (Exception e) {
        throw new RuntimeException(e);
    }
}

private InputStream readFile(String yourSampleFile) {
    return Thread.currentThread().getContextClassLoader().getResourceAsStream(yourSampleFile);
}

private void processFilteredXml(InputStream in, String xpath, Consumer<Node> process) {
    Document doc = readXml(in);
    NodeList list = filterNodesByXPath(doc, xpath);
    for (int i = 0; i < list.getLength(); i++) {
        Node node = list.item(i);
        process.accept(node);
    }
}

public Document readXml(InputStream xmlin) {
    try {
        DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
        DocumentBuilder db = dbf.newDocumentBuilder();
        return db.parse(xmlin);
    } catch (Exception e) {
        throw new RuntimeException(e);
    }
}

private NodeList filterNodesByXPath(Document doc, String xpathExpr) {
    try {
        XPathFactory xPathFactory = XPathFactory.newInstance();
        XPath xpath = xPathFactory.newXPath();
        XPathExpression expr = xpath.compile(xpathExpr);
        Object eval = expr.evaluate(doc, XPathConstants.NODESET);
        return (NodeList) eval;
    } catch (Exception e) {
        throw new RuntimeException(e);
    }
}

private void printNode(Node node, PrintStream out) {
    try {
        Transformer transformer = TransformerFactory.newInstance().newTransformer();
        transformer.setOutputProperty(OutputKeys.INDENT, "yes");
        transformer.setOutputProperty(OutputKeys.OMIT_XML_DECLARATION, "yes");
        transformer.setOutputProperty("{http://xml.apache.org/xslt}indent-amount", "2");
        StreamResult result = new StreamResult(new StringWriter());
        DOMSource source = new DOMSource(node);
        transformer.transform(source, result);
        String xmlString = result.getWriter().toString();
        out.println(xmlString);
    } catch (Exception e) {
        throw new RuntimeException(e);
    }
}

Prints

<creatorName>Fosmire, Michael</creatorName>

<creatorName>Wertz, Ruth</creatorName>

<creatorName>Purzer, Senay</creatorName>

For book.xml

<book>
  <creators>
    <creator>
      <creatorName>Fosmire, Michael</creatorName>
      <givenName>Michael</givenName>
      <familyName>Fosmire</familyName>
    </creator>
    <creator>
      <creatorName>Wertz, Ruth</creatorName>
      <givenName>Ruth</givenName>
      <familyName>Wertz</familyName>
    </creator>
    <creator>
      <creatorName>Purzer, Senay</creatorName>
       <givenName>Senay</givenName>
       <familyName>Purzer</familyName>
    </creator>
  </creators>
  <titles>
    <title>Critical Engineering Literacy Test (CELT)</title>
  </titles>
</book>

See also

https://stackoverflow.com/a/52736526/1485527

https://github.com/jschnasse/overflow/tree/master/src/test/java/stack52720162