[Dlsciences-dlese-tools] dlese-tools-project/src/org/dlese/dpc/xml NSDLDCNormalizer.java, NONE, 1.1,

[John W. <jwe...@us...>]

Update of /cvsroot/dlsciences/dlese-tools-project/src/org/dlese/dpc/xml
In directory sfp-cvsdas-3.v30.ch3.sourceforge.com:/tmp/cvs-serv4368/src/org/dlese/dpc/xml

Added Files:
	NSDLDCNormalizer.java 
Log Message:
new functionality for NSDL DC normalization

--- NEW FILE: NSDLDCNormalizer.java ---
/*
 *  License and Copyright:
 *
 *  The contents of this file are subject to the Educational Community License v1.0 (the "License"); you may
 *  not use this file except in compliance with the License. You should have received a copy of the License
 *  along with this software; if not, you may obtain a copy of the License at
 *  http://www.opensource.org/licenses/ecl1.php.
 *
 *  Software distributed under the License is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY KIND,
 *  either express or implied. See the License for the specific language governing rights and limitations
 *  under the License.
 *
 *  Copyright 2002-2011 by Digital Learning Sciences, University Corporation for Atmospheric Research (UCAR).
 *  All rights reserved.
 */
package org.dlese.dpc.xml;

import java.io.*;
import java.util.*;
import java.net.URL;
import java.net.MalformedURLException;

import java.text.*;
import java.io.*;

import org.dom4j.*;
import org.dlese.dpc.xml.Dom4jUtils;
import org.dlese.dpc.util.URLConnectionTimedOutException;
import java.net.URLEncoder;

/**
 *  Normalizes NSDL DC records to conform to standard vocabularies in specific data elements like audience,
 *  education level, and type. Uses groups files to define the data elements and vocabularies. Lazy-loads the
 *  groups files and caches them once loaded. Create a new NSDLDCNormalizer to release the cache and refresh
 *  the vocabularies.
 *
 * @author    John Weatherley
 */
public class NSDLDCNormalizer {
	private static boolean debug = true;

	private String nsdlDcVocabSelectionsUrlStr = null;

	private Document _vocabSelectionsDom = null;


	/**
	 *  Constructors a NSDLDCNormalizer object. Create a new NSDLDCNormalizer to refresh the vocabularies.
	 *
	 * @param  nsdlDcVocabSelectionsUrl     NOT YET DOCUMENTED
	 */
	public NSDLDCNormalizer(String nsdlDcVocabSelectionsUrl) {
		this.nsdlDcVocabSelectionsUrlStr = nsdlDcVocabSelectionsUrl;
	}


	private List _xpathsToModify = null;
	private Map _groupsFileDoms = null;
	private Map _fromXpathsLists = null;


	/**
	 *  Normalizes the given NSDL DC record.
	 *
	 * @param  nsdlDcRecordDoc  An NSDL DC record Document
	 * @return                  Normalized NSDL DC record Document
	 */
	public Document normalizeNsdlDcRecord(Document nsdlDcRecordDoc) {
		Document newDoc = null;
		try {
			initAllData();
			if (_xpathsToModify == null || _xpathsToModify.size() == 0 || nsdlDcRecordDoc == null)
				return nsdlDcRecordDoc;

			newDoc = (Document) nsdlDcRecordDoc.clone();
			for (int i = 0; i < _xpathsToModify.size(); i++) {
				String xPathToModify = (String) _xpathsToModify.get(i);

				// First remove all the existing elements from the new Document:
				List existingElms = newDoc.selectNodes(xPathToModify);
				for (int ii = 0; ii < existingElms.size(); ii++)
					((Node) existingElms.get(ii)).detach();

				Document groupsDom = (Document) _groupsFileDoms.get(xPathToModify);
				List fromXpathsList = (List) _fromXpathsLists.get(xPathToModify);

				// Only process if we've got something to process...
				if (groupsDom != null && fromXpathsList != null || fromXpathsList.size() > 0) {

					// For each xPath to pull from, grab it's value and translate to the new value:
					for (int j = 0; j < fromXpathsList.size(); j++) {
						String fromXpath = (String) fromXpathsList.get(j);
						prtln("fromXpath: " + fromXpath);
						List existingDCElms = nsdlDcRecordDoc.selectNodes(fromXpath);
						for (int k = 0; k < existingDCElms.size(); k++) {
							String existingValue = ((Node) existingDCElms.get(k)).getText();
							prtln("existingValue: " + existingValue);
							//prtln("groupsDom:\n" + groupsDom.asXML());
							List outlineNodes = groupsDom.selectNodes("/opml/body//outline[@vocab='" + existingValue + "']");
							prtln("numOutlineNodes: " + outlineNodes.size());
							for (int m = 0; m < outlineNodes.size(); m++) {
								Node outlineNode = (Node) outlineNodes.get(m);
								List newValueOutlineNodes = outlineNode.selectNodes(".[@type='group']|..[@type='group']|../..[@type='group']"); // Go one and two levels up, for nested vocabs like EdLevel
								prtln("numVewValueOutlineNodes: " + newValueOutlineNodes.size());
								for (int n = 0; n < newValueOutlineNodes.size(); n++) {
									Node newValueOutlineNode = (Node) newValueOutlineNodes.get(n);
									String newValue = newValueOutlineNode.valueOf("@vocab").trim();
									String xsiType = newValueOutlineNode.valueOf("@attribution").trim();
									prtln("xPathToModify:" + xPathToModify + " existingValue:'" + existingValue + "' newValue:'" + newValue + "' xsiType:'" + xsiType + "'");
								}
							}
						}
					}
				}
			}

			prtln("exisingNsdlDC:\n" + nsdlDcRecordDoc.asXML());
			prtln("newNsdlDC:\n" + newDoc.asXML());
		} catch (Throwable t) {
			prtlnErr("Error normalizing NSDL DC record: " + t);
			t.printStackTrace();
			return nsdlDcRecordDoc;
		}

		return newDoc;
	}


	private void initAllData() {
		// Init only if not done so previously:
		if (_vocabSelectionsDom == null) {
			try {
				_vocabSelectionsDom = Dom4jUtils.getXmlDocument(nsdlDcVocabSelectionsUrlStr, 5000);
			} catch (Throwable t) {
				prtlnErr("Error fetching vocab selections file from URL '" + nsdlDcVocabSelectionsUrlStr + "': " + t);
				return;
			}
			if (_vocabSelectionsDom == null)
				return;

			List groupsFileNodes = _vocabSelectionsDom.selectNodes("/groupsFiles/groupsFile");
			if (groupsFileNodes.size() == 0)
				return;

			_xpathsToModify = new ArrayList();
			_groupsFileDoms = new TreeMap();
			_fromXpathsLists = new TreeMap();
			for (int i = 0; i < groupsFileNodes.size(); i++) {
				Node groupsFileNode = (Node) groupsFileNodes.get(i);
				String toXpath = groupsFileNode.valueOf("toXpath").trim();
				String url = groupsFileNode.valueOf("url").trim();
				List fromXpaths = groupsFileNode.selectNodes("fromXpaths/fromXpath");
				if (toXpath.length() > 0 && url.length() > 0 && fromXpaths.size() > 0) {
					Document groupsDom = null;
					try {
						groupsDom = Dom4jUtils.localizeXml(Dom4jUtils.getXmlDocument(url, 5000));
					} catch (Throwable t) {
						prtlnErr("Error fetching groups file  rom URL '" + url + "': " + t);
						continue;
					}
					List fromXpathsStrings = new ArrayList();
					for (int j = 0; j < fromXpaths.size(); j++)
						fromXpathsStrings.add(((Node) fromXpaths.get(j)).getText().trim());
					_xpathsToModify.add(toXpath);
					_groupsFileDoms.put(toXpath, groupsDom);
					_fromXpathsLists.put(toXpath, fromXpathsStrings);
				}
			}
		}
	}


	/* ---------------------- Debug methods ----------------------- */
	/**
	 *  Return a string for the current time and date, sutiable for display in log files and output to standout:
	 *
	 * @return    The dateStamp value
	 */
	public static String getDateStamp() {
		return
			new SimpleDateFormat("MMM d, yyyy h:mm:ss a zzz").format(new Date());
	}


	/**
	 *  Output a line of text to error out, with datestamp.
	 *
	 * @param  s  The text that will be output to error out.
	 */
	private final static void prtlnErr(String s) {
		System.err.println(getDateStamp() + " NSDLDCNormalizer Error: " + s);
	}


	/**
	 *  Output a line of text to standard out, with datestamp, if debug is set to true.
	 *
	 * @param  s  The String that will be output.
	 */
	private final static void prtln(String s) {
		if (debug) {
			System.out.println(getDateStamp() + " NSDLDCNormalizer: " + s);
		}
	}


	/**
	 *  Sets the debug attribute of the NSDLDCNormalizer object
	 *
	 * @param  db  The new debug value
	 */
	public final void setDebug(boolean db) {
		debug = db;
	}
}