Java by API/org.w3c.dom/Document

Document: createCDATASection(String data) throws DOMException

  
import java.io.File;
import javax.xml.parsers.DocumentBuilderFactory;
import org.w3c.dom.CDATASection;
import org.w3c.dom.CharacterData;
import org.w3c.dom.rument;
import org.w3c.dom.Document;
import org.w3c.dom.Element;
import org.w3c.dom.Text;
public class Main {
  public static void main(String[] argv) throws Exception {
    DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
    factory.setValidating(true);
    factory.setExpandEntityReferences(false);
    Document doc = factory.newDocumentBuilder().parse(new File("filename"));
    Element element = doc.getElementById("key1");
    CDATASection cdataNode = doc.createCDATASection("");
    Comment commentNode = doc.createComment("");
    Text textNode = doc.createTextNode("");
 
    CharacterData cdata = cdataNode;
    cdata = commentNode;
    cdata = textNode;
    cdata.setData("some data");
    int len = cdata.getLength();
  }
}

Document: createComment(String data)

  
 
import java.io.File;
import javax.xml.parsers.DocumentBuilderFactory;
import org.w3c.dom.rument;
import org.w3c.dom.Document;
public class Main {
  public static void main(String[] argv) throws Exception {
    DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
    factory.setValidating(true);
    factory.setExpandEntityReferences(false);
    Document doc = factory.newDocumentBuilder().parse(new File("filename"));
    Comment comment = doc.createComment("invalid -- comment");
    boolean validComment = comment.getNodeValue().indexOf("--") < 0;
  }
}

Document: createElement(String tagName)

 
/*
 
 <?xml version="1.0" encoding="UTF-8"?>
 <book id="javanut4">
    <chapter>
       <title>Chapter 1</title>
       <para/>
    </chapter>
    <chapter>
       <title>Chapter 2</title>
       <para/>
    </chapter>
    <chapter>
       <title>Chapter 3</title>
       <para/>
    </chapter>
 </book>
 */
import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.transform.Transformer;
import javax.xml.transform.TransformerFactory;
import javax.xml.transform.dom.DOMSource;
import javax.xml.transform.stream.StreamResult;
import org.w3c.dom.Document;
import org.w3c.dom.Element;
public class MainClass {
  public static void main(String[] args) throws Exception{
    DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
    DocumentBuilder db = dbf.newDocumentBuilder();
    Document document = db.newDocument();
    Element book = document.createElement("book"); 
    book.setAttribute("id", "javanut4");           
    document.appendChild(book);                    
    for(int i = 1; i <= 3; i++) {                  
        Element chapter = document.createElement("chapter");
        Element title = document.createElement("title");
        title.appendChild(document.createTextNode("Chapter " + i));
        chapter.appendChild(title);
        chapter.appendChild(document.createElement("para"));
        book.appendChild(chapter);
    }
    TransformerFactory tf = TransformerFactory.newInstance();
    Transformer transformer = tf.newTransformer();
    DOMSource source = new DOMSource(document);          
    StreamResult result = new StreamResult(System.out);  
    transformer.transform(source, result);
  }
}

Document: createProcessingInstruction(String target, String data) throws DOMException

  
import java.io.File;
import javax.xml.parsers.DocumentBuilderFactory;
import org.w3c.dom.Document;
import org.w3c.dom.Element;
import org.w3c.dom.NodeList;
import org.w3c.dom.ProcessingInstruction;
public class Main {
  public static void main(String[] argv) throws Exception {
    DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
    factory.setValidating(true);
    factory.setExpandEntityReferences(false);
    Document doc = factory.newDocumentBuilder().parse(new File("filename"));
    // Add a PI at the beginning of the document
    Element element = doc.getDocumentElement();
    ProcessingInstruction pi = doc.createProcessingInstruction("target", "instruction");
    element.getParentNode().insertBefore(pi, element);

  }
}

Document: getDoctype()

 
/*
DOCTYPE node:
<!ELEMENT address (buildingnumber,street,city,state,zip)>
<!ATTLIST address xmlns CDATA #IMPLIED>
<!ELEMENT buildingnumber (#PCDATA)>
<!ELEMENT street (#PCDATA)>
<!ELEMENT city (#PCDATA)>
<!ELEMENT state (#PCDATA)>
<!ELEMENT zip (#PCDATA)>

Document body contents are:
 Node: address
 Node Type: Element
 Child Nodes of address are:
   Node: buildingnumber
   Node Type: Element
   Child Nodes of buildingnumber are:
     Node: #text
     Node Type: Text
     Content is:  29 
   Node: street
   Node Type: Element
   Child Nodes of street are:
     Node: #text
     Node Type: Text
     Content is:  South Street
   Node: city
   Node Type: Element
   Child Nodes of city are:
     Node: #text
     Node Type: Text
     Content is: Vancouver
   Node: state
   Node Type: Element
   Child Nodes of state are:
     Node: #text
     Node Type: Text
     Content is: BC
   Node: zip
   Node Type: Element
   Child Nodes of zip are:
     Node: #text
     Node Type: Text
     Content is: V6V 4U7
 */
import static org.w3c.dom.Node.ATTRIBUTE_NODE;
import static org.w3c.dom.Node.CDATA_SECTION_NODE;
import static org.w3c.dom.Node.ruMENT_NODE;
import static org.w3c.dom.Node.DOCUMENT_TYPE_NODE;
import static org.w3c.dom.Node.ELEMENT_NODE;
import static org.w3c.dom.Node.ENTITY_NODE;
import static org.w3c.dom.Node.ENTITY_REFERENCE_NODE;
import static org.w3c.dom.Node.NOTATION_NODE;
import static org.w3c.dom.Node.PROCESSING_INSTRUCTION_NODE;
import static org.w3c.dom.Node.TEXT_NODE;
import java.io.IOException;
import java.io.StringReader;
import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.parsers.ParserConfigurationException;
import org.w3c.dom.Document;
import org.w3c.dom.DocumentType;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;
import org.w3c.dom.Text;
import org.xml.sax.InputSource;
import org.xml.sax.SAXException;
public class MainClass {
  public static void main(String args[]) {
    DocumentBuilderFactory builderFactory = DocumentBuilderFactory.newInstance();
    builderFactory.setNamespaceAware(true);       // Set namespace aware
    builderFactory.setValidating(true);           // and validating parser feaures
    builderFactory.setIgnoringElementContentWhitespace(true); 
    
    DocumentBuilder builder = null;
    try {
      builder = builderFactory.newDocumentBuilder();  // Create the parser
    } catch(ParserConfigurationException e) {
      e.printStackTrace();
    }
    Document xmlDoc = null;
    try {
      xmlDoc = builder.parse(new InputSource(new StringReader(xmlString)));
    } catch(SAXException e) {
      e.printStackTrace();
    } catch(IOException e) {
      e.printStackTrace();
    }
    DocumentType doctype = xmlDoc.getDoctype();       
    if(doctype == null) {                             
      System.out.println("DOCTYPE is null");
    } else {                                          
      System.out.println("DOCTYPE node:\n" + doctype.getInternalSubset());
    }
    System.out.println("\nDocument body contents are:");
    listNodes(xmlDoc.getDocumentElement(),"");         // Root element & children
  }
  static void listNodes(Node node, String indent) {
    String nodeName = node.getNodeName();
    System.out.println(indent+" Node: " + nodeName);
    short type = node.getNodeType();
    System.out.println(indent+" Node Type: " + nodeType(type));
    if(type == TEXT_NODE){
      System.out.println(indent+" Content is: "+((Text)node).getWholeText());
    }
    
    NodeList list = node.getChildNodes();       
    if(list.getLength() > 0) {                  
      System.out.println(indent+" Child Nodes of "+nodeName+" are:");
      for(int i = 0 ; i<list.getLength() ; i++) {
        listNodes(list.item(i),indent+"  ");     
      }
    }         
  }
  static String nodeType(short type) {
    switch(type) {
      case ELEMENT_NODE:                return "Element";
      case DOCUMENT_TYPE_NODE:          return "Document type";
      case ENTITY_NODE:                 return "Entity";
      case ENTITY_REFERENCE_NODE:       return "Entity reference";
      case NOTATION_NODE:               return "Notation";
      case TEXT_NODE:                   return "Text";
      case COMMENT_NODE:                return "Comment";
      case CDATA_SECTION_NODE:          return "CDATA Section";
      case ATTRIBUTE_NODE:              return "Attribute";
      case PROCESSING_INSTRUCTION_NODE: return "Attribute";
    }
    return "Unidentified";
  }
  static String xmlString ="<?xml version=\"1.0\"?>" +
      "  <!DOCTYPE address" +
      "  [" +
      "     <!ELEMENT address (buildingnumber, street, city, state, zip)>" +
      "     <!ATTLIST address xmlns CDATA #IMPLIED>" +
      "     <!ELEMENT buildingnumber (#PCDATA)>" +
      "     <!ELEMENT street (#PCDATA)>" +
      "     <!ELEMENT city (#PCDATA)>" +
      "     <!ELEMENT state (#PCDATA)>" +
      "     <!ELEMENT zip (#PCDATA)>" +
      "  ]>" +
      "" +
      "  <address>" +
      "    <buildingnumber> 29 </buildingnumber>" +
      "    <street> South Street</street>" +
      "    <city>Vancouver</city>" +
      "" +
      "    <state>BC</state>" +
      "    <zip>V6V 4U7</zip>" +
      "  </address>";
}

Document: getDocumentElement()

 
/*
DOCTYPE node:
<!ELEMENT address (buildingnumber,street,city,state,zip)>
<!ATTLIST address xmlns CDATA #IMPLIED>
<!ELEMENT buildingnumber (#PCDATA)>
<!ELEMENT street (#PCDATA)>
<!ELEMENT city (#PCDATA)>
<!ELEMENT state (#PCDATA)>
<!ELEMENT zip (#PCDATA)>

Document body contents are:
 Node: address
 Node Type: Element
 Child Nodes of address are:
   Node: buildingnumber
   Node Type: Element
   Child Nodes of buildingnumber are:
     Node: #text
     Node Type: Text
     Content is:  29 
   Node: street
   Node Type: Element
   Child Nodes of street are:
     Node: #text
     Node Type: Text
     Content is:  South Street
   Node: city
   Node Type: Element
   Child Nodes of city are:
     Node: #text
     Node Type: Text
     Content is: Vancouver
   Node: state
   Node Type: Element
   Child Nodes of state are:
     Node: #text
     Node Type: Text
     Content is: BC
   Node: zip
   Node Type: Element
   Child Nodes of zip are:
     Node: #text
     Node Type: Text
     Content is: V6V 4U7
 */
import static org.w3c.dom.Node.ATTRIBUTE_NODE;
import static org.w3c.dom.Node.CDATA_SECTION_NODE;
import static org.w3c.dom.Node.ruMENT_NODE;
import static org.w3c.dom.Node.DOCUMENT_TYPE_NODE;
import static org.w3c.dom.Node.ELEMENT_NODE;
import static org.w3c.dom.Node.ENTITY_NODE;
import static org.w3c.dom.Node.ENTITY_REFERENCE_NODE;
import static org.w3c.dom.Node.NOTATION_NODE;
import static org.w3c.dom.Node.PROCESSING_INSTRUCTION_NODE;
import static org.w3c.dom.Node.TEXT_NODE;
import java.io.IOException;
import java.io.StringReader;
import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.parsers.ParserConfigurationException;
import org.w3c.dom.Document;
import org.w3c.dom.DocumentType;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;
import org.w3c.dom.Text;
import org.xml.sax.InputSource;
import org.xml.sax.SAXException;
public class MainClass {
  public static void main(String args[]) {
    DocumentBuilderFactory builderFactory = DocumentBuilderFactory.newInstance();
    builderFactory.setNamespaceAware(true);       // Set namespace aware
    builderFactory.setValidating(true);           // and validating parser feaures
    builderFactory.setIgnoringElementContentWhitespace(true); 
    
    DocumentBuilder builder = null;
    try {
      builder = builderFactory.newDocumentBuilder();  // Create the parser
    } catch(ParserConfigurationException e) {
      e.printStackTrace();
    }
    Document xmlDoc = null;
    try {
      xmlDoc = builder.parse(new InputSource(new StringReader(xmlString)));
    } catch(SAXException e) {
      e.printStackTrace();
    } catch(IOException e) {
      e.printStackTrace();
    }
    DocumentType doctype = xmlDoc.getDoctype();       
    if(doctype == null) {                             
      System.out.println("DOCTYPE is null");
    } else {                                          
      System.out.println("DOCTYPE node:\n" + doctype.getInternalSubset());
    }
    System.out.println("\nDocument body contents are:");
    listNodes(xmlDoc.getDocumentElement(),"");         // Root element & children
  }
  static void listNodes(Node node, String indent) {
    String nodeName = node.getNodeName();
    System.out.println(indent+" Node: " + nodeName);
    short type = node.getNodeType();
    System.out.println(indent+" Node Type: " + nodeType(type));
    if(type == TEXT_NODE){
      System.out.println(indent+" Content is: "+((Text)node).getWholeText());
    }
    
    NodeList list = node.getChildNodes();       
    if(list.getLength() > 0) {                  
      System.out.println(indent+" Child Nodes of "+nodeName+" are:");
      for(int i = 0 ; i<list.getLength() ; i++) {
        listNodes(list.item(i),indent+"  ");     
      }
    }         
  }
  static String nodeType(short type) {
    switch(type) {
      case ELEMENT_NODE:                return "Element";
      case DOCUMENT_TYPE_NODE:          return "Document type";
      case ENTITY_NODE:                 return "Entity";
      case ENTITY_REFERENCE_NODE:       return "Entity reference";
      case NOTATION_NODE:               return "Notation";
      case TEXT_NODE:                   return "Text";
      case COMMENT_NODE:                return "Comment";
      case CDATA_SECTION_NODE:          return "CDATA Section";
      case ATTRIBUTE_NODE:              return "Attribute";
      case PROCESSING_INSTRUCTION_NODE: return "Attribute";
    }
    return "Unidentified";
  }
  static String xmlString ="<?xml version=\"1.0\"?>" +
      "  <!DOCTYPE address" +
      "  [" +
      "     <!ELEMENT address (buildingnumber, street, city, state, zip)>" +
      "     <!ATTLIST address xmlns CDATA #IMPLIED>" +
      "     <!ELEMENT buildingnumber (#PCDATA)>" +
      "     <!ELEMENT street (#PCDATA)>" +
      "     <!ELEMENT city (#PCDATA)>" +
      "     <!ELEMENT state (#PCDATA)>" +
      "     <!ELEMENT zip (#PCDATA)>" +
      "  ]>" +
      "" +
      "  <address>" +
      "    <buildingnumber> 29 </buildingnumber>" +
      "    <street> South Street</street>" +
      "    <city>Vancouver</city>" +
      "" +
      "    <state>BC</state>" +
      "    <zip>V6V 4U7</zip>" +
      "  </address>";
}

Document: getElementsByTagName(String tagname)

 
import java.io.File;
import java.io.IOException;
import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.parsers.ParserConfigurationException;
import org.w3c.dom.Document;
import org.w3c.dom.Element;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;
public class MainClass {
  public static void main(String[] args) throws IOException, ParserConfigurationException,
      org.xml.sax.SAXException {
    DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
    factory.setIgnoringComments(true);
    factory.setCoalescing(true); // Convert CDATA to Text nodes
    factory.setNamespaceAware(false); // No namespaces: this is default
    factory.setValidating(false); // Don"t validate DTD: also default
    DocumentBuilder parser = factory.newDocumentBuilder();
    Document document = parser.parse(new File(args[0]));
    NodeList sections = document.getElementsByTagName("sect1");
    int numSections = sections.getLength();
    for (int i = 0; i < numSections; i++) {
      Element section = (Element) sections.item(i); // A <sect1>
      Node title = section.getFirstChild();
      while (title != null && title.getNodeType() != Node.ELEMENT_NODE)
        title = title.getNextSibling();
      if (title != null)
        System.out.println(title.getFirstChild().getNodeValue());
    }
  }
}