Metacat

/**

 *  '$RCSfile$'

 *  Copyright: 2004 University of New Mexico and the

 *                  Regents of the University of California

 *     '$Date$'

 * '$Revision$'

 *

 * This program is free software; you can redistribute it and/or modify

 * it under the terms of the GNU General Public License as published by

 * the Free Software Foundation; either version 2 of the License, or

 * (at your option) any later version.

 *

 * This program is distributed in the hope that it will be useful,

 * but WITHOUT ANY WARRANTY; without even the implied warranty of

 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the

 * GNU General Public License for more details.

 *

 * You should have received a copy of the GNU General Public License

 * along with this program; if not, write to the Free Software

 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA

package edu.ucsb.nceas.metacat.harvesterClient;

import java.io.InputStream;

import java.io.InputStreamReader;

import java.io.IOException;

import java.net.MalformedURLException;

import java.net.URL;

import java.sql.SQLException;

import java.sql.Statement;

import edu.ucsb.nceas.metacat.client.Metacat;

import edu.ucsb.nceas.metacat.client.MetacatException;

import edu.ucsb.nceas.metacat.client.MetacatInaccessibleException;

/**

 * HarvestDocument manages operations and data for a single document to be

 * harvested.

 *

 * @author  costa

 */

public class HarvestDocument {

  private String docid;                      // scope + identifier

  private String docidFull;                  // scope + identifier + revision

  String documentURL;

  private HarvestSiteSchedule harvestSiteSchedule;

  int revision;

  String scope;

  /* These booleans keep track of status information. They are used when

   * generating email reports.

   */

  boolean accessError = false;

  boolean inserted = false;

  boolean metacatHasIt = false;

  boolean updated = false;

  boolean uploadError = false;

  /**

   * Creates a new instance of HarvestDocument. Initialized with the data

   * that was read from a single <document> element in site document list.

   *

   * @param harvester            the parent Harvester object

   * @param harvestSiteSchedule  the parent HarvestSiteSchedule object

   * @param scope                the value of the <scope> element

   * @param identifier           the value of the <identifier> element

   * @param revision             the value of the <revision> element

   * @param documentType         the value of the <documentType> element

   * @param documentURL          the value of the <documentURL> element

   */

                          HarvestSiteSchedule harvestSiteSchedule,

                          String scope,

                          int identifier,

                          int revision,

                          String documentType,

                          String documentURL

                        ) {

    this.harvester = harvester;

    this.harvestSiteSchedule = harvestSiteSchedule;

    this.documentType = documentType;

    this.documentURL = documentURL;

    this.scope = scope;

    this.identifier = identifier;

    this.revision = revision;

    this.docidFull = this.docid + "." + revision;

  /**

   * Retrieve the document from the site using its <documentURL> value.

   *

   * @return   A StringReader containing the document string.

   */

    InputStream inputStream;

    InputStreamReader inputStreamReader;

    StringReader stringReader = null;

    URL url;

    try {

      url = new URL(documentURL);

      inputStream = url.openStream();

      inputStreamReader = new InputStreamReader(inputStream);

      documentString = IOUtil.getAsString(inputStreamReader, true);

      stringReader = new StringReader(documentString);

                            "Retrieved: " + documentURL,

                            null,

                            "");

    catch (MalformedURLException e) {

                            "MalformedURLException: " + e.getMessage());

    catch (IOException e) {

                            "IOException: " + e.getMessage());

    return stringReader;

  }

  /**

   * Harvest the document from the site. Unless Metacat already has the

   * document, retrieve the document from the site and put (insert or

   * update) it to Metacat. If Metacat already has the document, determine

   * the highest revision stored in Metacat so that this can be reported

   * back to the user.

   */

  public void harvestDocument() {

    int highestRevision;

    StringReader stringReader;

    /* If metacat already has this document, determine the highest revision in

     * metacat and report it to the user; else, insert or delete the document

     * into metacat.

     */

    if (highestRevision == -1) {

      insert = true;

    }

    else if (revision > highestRevision) {

      update = true;

    }

    else {

                            revision + ". Metacat has document revision " +

                            highestRevision + ".",

                            null,

                            "");

    if (insert || update) {

      if (stringReader != null) {

          putMetacatDocument(insert, update, stringReader);

      }

    }

  }

  /**

   *

   * @param insert               true if insert operation, false is update

   * @param metacatReturnString  string returned from the insert or update

   * @param exceptionName        name of the exception class

   * @param e                    the exception object

   */

  private void logMetacatError (boolean insert,

                                String metacatReturnString,

                                String exceptionName,

                                Exception e

                               ) {

                            metacatReturnString,

                            this,

                            exceptionName + ": " + e.getMessage());

    else {

                            metacatReturnString,

                            this,

                            exceptionName + ": " + e.getMessage());

  }

  /**

   *

   *          Metacat. Returns -1 if Metacat does not currently hold the

   *          document.

    Connection conn = harvester.getConnection();

		String query = "SELECT REV FROM XML_DOCUMENTS WHERE DOCID = " +

                   "'" + docid + "'";

		Statement stmt;

			while (rs.next()) {

				highestRevision = rs.getInt("REV");

			}

			stmt.close();

		}

    catch(SQLException e) {

			System.out.println("SQLException: " + e.getMessage());

    return highestRevision;

  /**

   * Print the data fields and values in this HarvestDocument object.

   * @param out   the PrintStream to write to

    out.println("* identifier:           " + identifier);

    out.println("* revision:             " + revision);

    out.println("* documentType:         " + documentType);

    out.println("* documentURL:          " + documentURL);

  /**

   * Used for report generation.

   *

   * @param out   the PrintStream to write to

   */

  public void prettyPrint(PrintStream out) {

    out.println("*   " + docidFull + "  (" + documentURL + ")");

  }

  /**

   * insert; otherwise, do an update.

   * @param insert       true if this is an insert operation

   * @param update       true if this is an update operation

   * @param stringReader the StringReader object holding the document text

                                  boolean update,

                                  StringReader stringReader) {

    String metacatReturnString = "";

      try {

                                null, "");

          metacatReturnString = metacat.update(docidFull, stringReader, null);

                                null, "");

      }

      catch (MetacatInaccessibleException e) {

                        "MetacatInaccessibleException", e);

      catch (InsufficientKarmaException e) {

                        "InsufficientKarmaException", e);

      catch (MetacatException e) {

      catch (IOException e) {

    }

  }

  /**

   * Validate the document to determine whether it is valid EML prior to

   * inserting or updating it to Metacat. This is QA/QC measure.

   * Not yet implemented.

   *

   * @return  true if the document is valid EML, otherwise false

   */

  private boolean validateDocument () {

    boolean success = true;

    /*if (success) {

      harvester.addLogEntry(0,

                            "Validated: " + documentURL,

                            null,

                            "");

    }

    else {

    }*/

    return success;

  }