PositionalXMLReader.java

package com.kodcu.other;


import org.w3c.dom.Document;
import org.w3c.dom.Element;
import org.w3c.dom.Node;
import org.xml.sax.Attributes;
import org.xml.sax.Locator;
import org.xml.sax.SAXException;
import org.xml.sax.helpers.DefaultHandler;

import javax.xml.parsers.*;
import javax.xml.transform.Result;
import javax.xml.transform.Transformer;
import javax.xml.transform.TransformerException;
import javax.xml.transform.TransformerFactory;
import javax.xml.transform.dom.DOMSource;
import javax.xml.transform.stream.StreamResult;
import java.io.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
import java.io.IOException;
import java.util.Stack;

/**
 * Created by usta on 20.09.2015.
 */
public class PositionalXMLReader {

    final static String LINE_NUMBER_KEY_NAME = "lineNumber";

    public static Document readXML(final Document inDocument) throws Exception {

        SAXParser parser;
        Document outDocument;

        try {
            final SAXParserFactory factory = SAXParserFactory.newInstance();
            parser = factory.newSAXParser();
            final DocumentBuilderFactory docBuilderFactory = DocumentBuilderFactory.newInstance();
            final DocumentBuilder docBuilder = docBuilderFactory.newDocumentBuilder();
            outDocument = docBuilder.newDocument();
        } catch (final ParserConfigurationException e) {
            throw new RuntimeException("Can't create SAX parser / DOM builder.", e);
        }

        final Stack<Element> elementStack = new Stack<Element>();
        final StringBuilder textBuffer = new StringBuilder();
        final DefaultHandler handler = new DefaultHandler() {
            private Locator locator;

            @Override
            public void setDocumentLocator(final Locator locator) {
                this.locator = locator; // Save the locator, so that it can be used later for line tracking when traversing nodes.
            }

            @Override
            public void startElement(final String uri, final String localName, final String qName, final Attributes attributes)
                    throws SAXException {
                addTextIfNeeded();
                final Element el = outDocument.createElement(qName);
                for (int i = 0; i < attributes.getLength(); i++) {
                    el.setAttribute(attributes.getQName(i), attributes.getValue(i));
                }
                el.setUserData(LINE_NUMBER_KEY_NAME, String.valueOf(this.locator.getLineNumber()), null);
                elementStack.push(el);
            }

            @Override
            public void endElement(final String uri, final String localName, final String qName) {
                addTextIfNeeded();
                final Element closedEl = elementStack.pop();
                if (elementStack.isEmpty()) { // Is this the root element?
                    outDocument.appendChild(closedEl);
                } else {
                    final Element parentEl = elementStack.peek();
                    parentEl.appendChild(closedEl);
                }
            }

            @Override
            public void characters(final char ch[], final int start, final int length) throws SAXException {
                textBuffer.append(ch, start, length);
            }

            // Outputs text accumulated under the current node
            private void addTextIfNeeded() {
                if (textBuffer.length() > 0) {
                    final Element el = elementStack.peek();
                    final Node textNode = outDocument.createTextNode(textBuffer.toString());
                    el.appendChild(textNode);
                    textBuffer.delete(0, textBuffer.length());
                }
            }
        };
        try (ByteArrayInputStream is = nodeToInputStream(inDocument);) {
            parser.parse(is, handler);
        }

        return outDocument;
    }

    private static ByteArrayInputStream nodeToInputStream(Node node) throws TransformerException, IOException {

        ByteArrayInputStream inputStream;

        try (ByteArrayOutputStream outputStream = new ByteArrayOutputStream();) {
            Result outputTarget = new StreamResult(outputStream);
            Transformer t = TransformerFactory.newInstance().newTransformer();
            t.transform(new DOMSource(node), outputTarget);
            inputStream = new ByteArrayInputStream(outputStream.toByteArray());
        }

        return inputStream;
    }
}