/*
* Jalview - A Sequence Alignment Editor and Viewer
* Copyright (C) 2006 AM Waterhouse, J Procter, G Barton, M Clamp, S Searle
*
* 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., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA
*/
package jalview.io;

import jalview.datamodel.*;

import jalview.gui.*;

import java.io.*;

import java.util.*;

import org.exolab.castor.mapping.Mapping;

import org.exolab.castor.xml.*;
import jalview.analysis.AlignSeq;



/**
 * DOCUMENT ME!
 *
 * @author $author$
 * @version $Revision$
 */
public class DBRefFetcher implements Runnable
{
  AlignmentI align;
  AlignmentI dataset;
  AlignFrame af;
  ArrayList unknownSequences;
  CutAndPasteTransfer output = new CutAndPasteTransfer();
  StringBuffer sbuffer = new StringBuffer();
  boolean uniprotFlag = false;
  boolean running = false;

  public DBRefFetcher()
  {}

  public Vector getUniprotEntries(File file)
  {
    UniprotFile uni = new UniprotFile();
    try
    {
      // 1. Load the mapping information from the file
      Mapping map = new Mapping(uni.getClass().getClassLoader());
      java.net.URL url = getClass().getResource("/uniprot_mapping.xml");
      map.loadMapping(url);

      // 2. Unmarshal the data
      Unmarshaller unmar = new Unmarshaller(uni);
      unmar.setIgnoreExtraElements(true);
      unmar.setMapping(map);
   //   unmar.setDebug(true);

      uni = (UniprotFile) unmar.unmarshal(new FileReader(file));
    }
    catch (Exception e)
    {
      System.out.println("Error getUniprotEntries() "+e);
    }


    return uni.getUniprotEntries();
  }

  /**
   * Creates a new SequenceFeatureFetcher object.
   *
   * @param align DOCUMENT ME!
   * @param ap DOCUMENT ME!
   */
  public DBRefFetcher(AlignmentI align, AlignFrame af)
  {
    this.af = af;
    unknownSequences = new ArrayList();
    this.align = align;
    this.dataset = align.getDataset();
  }

  public boolean fetchDBRefs(boolean waitTillFinished)
  {
    Thread thread = new Thread(this);
    thread.start();
    running = true;

    if(waitTillFinished)
    {
      while(running)
      {
        try{
          Thread.sleep(500);
        }catch(Exception ex){}
      }
    }

    return true;
  }

  /**
   * DOCUMENT ME!
   */
  public void run()
  {
    long startTime = System.currentTimeMillis();
    af.setProgressBar("Fetching db refs", startTime);
    running = true;

    try
    {
      int seqIndex = 0;
      Vector sequences = dataset.getSequences();

      while (seqIndex < sequences.size())
      {
        Vector ids = new Vector();

        for (int i = 0; (seqIndex < sequences.size()) && (i < 50);
             seqIndex++, i++)
        {
          Sequence sequence = (Sequence) sequences.get(seqIndex);
          DBRefEntry [] uprefs = jalview.util.DBRefUtils.selectRefs(sequence.getDBRef(), new String[] {
              jalview.datamodel.DBRefSource.UNIPROT});
          if (uprefs!=null)
          {
            // we know the id for this entry, so don't note its ID in the unknownSequences list
            for (int j=0,k=uprefs.length; j<k; j++)
              ids.add(uprefs[j].getAccessionId());
            unknownSequences.add(sequence);
          } else {
            if (!ids.contains(sequence.getName()))
            {
              ids.add(sequence.getName());
              unknownSequences.add(sequence);
            }
          }
        }

        ///////////////////////////////////
        ///READ FROM EBI
        if (ids.size() > 0)
        {
          StringBuffer remainingIds = new StringBuffer("uniprot:");
          for (int i = 0; i < ids.size(); i++)
           {
             if(ids.get(i).toString().indexOf("|")>-1)
             {
               remainingIds.append(ids.get(i).toString().substring(
                   ids.get(i).toString().lastIndexOf("|") + 1));
               uniprotFlag = true;
             }
             else
               remainingIds.append(ids.get(i));

             remainingIds.append(";");
           }

          EBIFetchClient ebi = new EBIFetchClient();
          File file = ebi.fetchDataAsFile(remainingIds.toString(),
                                          "xml", "raw");



          if (file != null)
          {
            ReadUniprotFile(file, ids);
          }
        }
      }
    }
    catch (Exception ex)
    {
      ex.printStackTrace();
    }

    if (sbuffer.length() > 0)
    {
      output.setText(
          "Your sequences have been matched to Uniprot. Some of the ids have been\n" +
          "altered, most likely the start/end residue will have been updated.\n" +
          "Save your alignment to maintain the updated id.\n\n" +
          sbuffer.toString());
      Desktop.addInternalFrame(output, "Sequence names updated ", 600, 300);
      // The above is the dataset, we must now find out the index
      // of the viewed sequence

    }

    af.setProgressBar("DBRef search completed", startTime);
   // promptBeforeBlast();

   running = false;

  }


  void promptBeforeBlast()
   {
     // This must be outside the run() body as java 1.5
     // will not return any value from the OptionPane to the expired thread.
      if (unknownSequences.size() > 0)
      {
       // int reply = javax.swing.JOptionPane.showConfirmDialog(
       //     Desktop.desktop, "Couldn't find a match for "+unknownSequences.size()+" sequences."
        //        +"\nPerform blast for unknown sequences?",
        //            "Blast for Unidentified Sequences",
        //             javax.swing.JOptionPane.YES_NO_OPTION, javax.swing.JOptionPane.QUESTION_MESSAGE);
     javax.swing.JOptionPane.showMessageDialog(
    Desktop.desktop, "Couldn't find a match for "+unknownSequences.size()+" sequences.",
            "Unidentified Sequences",
             javax.swing.JOptionPane.WARNING_MESSAGE);


      //  if(reply == javax.swing.JOptionPane.YES_OPTION)
     //    new WSWUBlastClient(ap, align, unknownSequences);
      }
  }

  /**
   * DOCUMENT ME!
   *
   * @param result DOCUMENT ME!
   * @param out DOCUMENT ME!
   * @param align DOCUMENT ME!
   */
  void ReadUniprotFile(File file, Vector ids)
  {
    if(!file.exists())
      return;

    SequenceI [] sequence = null;

    Vector entries = getUniprotEntries(file);

    int i, iSize = entries==null?0:entries.size();
    UniprotEntry entry;
    for (i = 0; i < iSize; i++)
    {
      entry = (UniprotEntry) entries.elementAt(i);
      String idmatch = entry.getAccession().elementAt(0).toString();
      sequence = dataset.findSequenceMatch(idmatch);

      if (sequence.length==0)
      {
        //Sequence maybe Name, not Accession
        idmatch = entry.getName().elementAt(0).toString();
        sequence = dataset.findSequenceMatch(idmatch);
      }

      if(sequence.length>0)
        ids.remove(sequence[0].getName());

      else  if (sequence.length==0 && uniprotFlag)
      {
          StringBuffer upid = new StringBuffer("UniProt/Swiss-Prot|");
          for(int u=0; u<entry.getAccession().size(); u++)
            upid.append(entry.getAccession().elementAt(u)+"|");

          sequence = dataset.findSequenceMatch(upid+idmatch);
          ids.remove(idmatch);
      }

      if(sequence.length==0)
      {
        System.out.println(idmatch+" not found");
        continue;
      }

      for(int m=0; m<sequence.length; m++)
      {

      sequence[m].addDBRef(new DBRefEntry(DBRefSource.UNIPROT,
                                       "0",
                                       entry.getAccession().elementAt(0).toString()));

      System.out.println("Adding dbref to "+sequence[m].getName()+" : "+
                         entry.getAccession().elementAt(0).toString());

      String nonGapped = AlignSeq.extractGaps("-. ", sequence[m].getSequence());

      int absStart = entry.getUniprotSequence().getContent().indexOf(
          nonGapped.toString());

      if (absStart == -1)
      {
        // Is UniprotSequence contained in dataset sequence?
        absStart = nonGapped.toString().indexOf(entry.getUniprotSequence().getContent());
        if(absStart == -1)
        {
          sbuffer.append(sequence[m].getName() +
                         " SEQUENCE NOT %100 MATCH \n");

          continue;
        }

        if (entry.getFeature() != null)
        {
          Enumeration e = entry.getFeature().elements();
          while (e.hasMoreElements())
          {
            SequenceFeature sf = (SequenceFeature) e.nextElement();
            sf.setBegin(sf.getBegin() + absStart + 1);
            sf.setEnd(sf.getEnd() + absStart + 1);
          }

          sbuffer.append(sequence[m].getName() +
                         " HAS " + absStart +
              " PREFIXED RESIDUES COMPARED TO UNIPROT - ANY SEQUENCE FEATURES"
                         + " HAVE BEEN ADJUSTED ACCORDINGLY \n");
          absStart = 0;
        }

      }

      unknownSequences.remove(sequence);

      int absEnd = absStart + nonGapped.toString().length();
      absStart += 1;

      Enumeration e = entry.getDbReference().elements();
      Vector onlyPdbEntries = new Vector();
      while(e.hasMoreElements())
      {
        PDBEntry pdb = (PDBEntry)e.nextElement();
        if(!pdb.getType().equals(DBRefSource.PDB))
          continue;

        sequence[m].addDBRef(new DBRefEntry(DBRefSource.PDB,
                                       "0",
                                       pdb.getId()));

        onlyPdbEntries.addElement(pdb);
      }

      sequence[m].setPDBId(onlyPdbEntries);

      sequence[m].setStart(absStart);
      sequence[m].setEnd(absEnd);


      }
    }
  }
}