D-Net

package eu.dnetlib.msro.openaireplus.workflows.nodes.datacite;

import java.io.ByteArrayInputStream;

import java.io.InputStream;

import java.io.StringWriter;

import java.nio.charset.StandardCharsets;

import java.util.ArrayList;

import java.util.List;

import java.util.Map;

import java.util.Queue;

import javax.xml.XMLConstants;

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 javax.xml.xpath.XPath;

import javax.xml.xpath.XPathConstants;

import javax.xml.xpath.XPathFactory;

import com.google.common.collect.Maps;

import org.apache.commons.lang.StringUtils;

import org.apache.commons.logging.Log;

import org.apache.commons.logging.LogFactory;

import org.w3c.dom.*;

/**

 * The Class SplitterDatasetsIterator.

 */

public class SplitterDatasetsIterator {

	/**

	 * The Constant log.

	 */

	private static final Log log = LogFactory.getLog(SplitterDatasetsIterator.class);

	/**

	 * The end queue.

	 */

	public static String END_QUEUE = "END_QUEUE";

	/**

	 * The publications.

	 */

	private Queue<String> publications;

	/**

	 * The input epr.

	 */

	private Iterable<String> inputEPR;

	/**

	 * The root name.

	 */

	private String rootName;

	/**

	 * Instantiates a new splitter datasets iterator.

	 *

	 * @param publicationsQueue the publications queue

	 * @param inputEPR          the input epr

	 * @param rootName          the root name

	 */

	public SplitterDatasetsIterator(final Queue<String> publicationsQueue, final Iterable<String> inputEPR, final String rootName) {

		this.publications = publicationsQueue;

		this.inputEPR = inputEPR;

		this.rootName = rootName;

	}

	/**

	 * Populate queues.

	 */

	public void populateQueues() {

		if (this.inputEPR == null) return;

		for (String inputXML : inputEPR) {

			final ByteArrayInputStream bais = new ByteArrayInputStream(inputXML.getBytes(StandardCharsets.UTF_8));

			final List<String> publication_extracted = extractByTag(bais, "publication");

			if (publication_extracted != null) {

				publications.addAll(publication_extracted);

			}

		}

		publications.add(END_QUEUE);

	}

	/**

	 * Extract by tag.

	 *

	 * @param inputXML the input xml

	 * @param tag      the tag

	 * @return the list

	 */

	private List<String> extractByTag(final InputStream inputXML, final String tag) {

		try {

			DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();

			Document doc = dbf.newDocumentBuilder().parse(inputXML);

			XPath xpath = XPathFactory.newInstance().newXPath();

			Node rootNode = (Node) xpath.evaluate("//*[local-name()='" + this.rootName + "']", doc, XPathConstants.NODE);

			NamedNodeMap attributes = rootNode.getAttributes();

			Map<String, String> nameSpaces = Maps.newHashMap();

			for (int i = 0; i < attributes.getLength(); i++) {

				Node node = attributes.item(i);

				String name = node.getNodeName();

				if (name.startsWith("xmlns:")) {

					nameSpaces.put(StringUtils.substringAfter(name, "xmlns:"), node.getNodeValue());

				}

			}

			xpath = XPathFactory.newInstance().newXPath();

			NodeList nodes = (NodeList) xpath.evaluate("//*[local-name()='" + tag + "']/*[local-name()='record']", doc, XPathConstants.NODESET);

			if ((nodes != null) && (nodes.getLength() > 0)) {

				List<String> result = new ArrayList<>();

				for (int i = 0; i < nodes.getLength(); i++) {

					Document currentDoc = dbf.newDocumentBuilder().newDocument();

					Node imported = currentDoc.importNode(nodes.item(i), true);

					for (String key : nameSpaces.keySet()) {

						Element element = (Element) imported;

						element.setAttributeNS(XMLConstants.XMLNS_ATTRIBUTE_NS_URI, "xmlns:" + key, nameSpaces.get(key));

					}

					Transformer transformer = TransformerFactory.newInstance().newTransformer();

					DOMSource mydoc = new DOMSource(imported);

					StringWriter writer = new StringWriter();

					transformer.transform(mydoc, new StreamResult(writer));

					String record = writer.toString();

					result.add(record);

				}

				return result;

			}

		} catch (Exception e) {

			log.error("Error on extracting " + tag, e);

			return null;

		}

		return null;

	}

}