/*
 * Jalview - A Sequence Alignment Editor and Viewer (Version 2.9.0b2)
 * Copyright (C) 2015 The Jalview Authors
 * 
 * This file is part of Jalview.
 * 
 * Jalview 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 3
 * of the License, or (at your option) any later version.
 *  
 * Jalview 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 Jalview.  If not, see <http://www.gnu.org/licenses/>.
 * The Jalview Authors are detailed in the 'AUTHORS' file.
 */
package jalview.ws.dbsources;

import static org.testng.AssertJUnit.assertEquals;
import static org.testng.AssertJUnit.assertNotNull;
import static org.testng.AssertJUnit.assertNull;

import jalview.datamodel.PDBEntry;
import jalview.datamodel.SequenceFeature;
import jalview.datamodel.SequenceI;
import jalview.datamodel.UniprotEntry;

import java.io.Reader;
import java.io.StringReader;
import java.util.Vector;

import org.testng.annotations.Test;

public class UniprotTest
{
  // adapted from http://www.uniprot.org/uniprot/A9CKP4.xml
  private static final String UNIPROT_XML = "<?xml version='1.0' encoding='UTF-8'?>"
          + "<uniprot>"
          + "<entry dataset=\"TrEMBL\" created=\"2008-01-15\" modified=\"2015-03-04\" version=\"38\">"
          + "<accession>A9CKP4</accession>"
          + "<accession>A9CKP5</accession>"
          + "<name>A9CKP4_AGRT5</name>"
          + "<name>A9CKP4_AGRT6</name>"
          + "<protein><recommendedName><fullName>Mitogen-activated protein kinase 13</fullName><fullName>Henry</fullName></recommendedName></protein>"
          + "<dbReference type=\"PDB\" id=\"2FSQ\"><property type=\"method\" value=\"X-ray\"/><property type=\"resolution\" value=\"1.40\"/></dbReference>"
          + "<dbReference type=\"PDBsum\" id=\"2FSR\"/>"
          + "<dbReference type=\"EMBL\" id=\"AE007869\"><property type=\"protein sequence ID\" value=\"AAK85932.1\"/><property type=\"molecule type\" value=\"Genomic_DNA\"/></dbReference>"
          + "<feature type=\"signal peptide\" evidence=\"7\"><location><begin position=\"1\"/><end position=\"18\"/></location></feature>"
          + "<feature type=\"propeptide\" description=\"Activation peptide\" id=\"PRO_0000027399\" evidence=\"9 16 17 18\"><location><begin position=\"19\"/><end position=\"20\"/></location></feature>"
          + "<feature type=\"chain\" description=\"Granzyme B\" id=\"PRO_0000027400\"><location><begin position=\"21\"/><end position=\"247\"/></location></feature>"
          + "<sequence length=\"10\" mass=\"27410\" checksum=\"8CB760AACF88FE6C\" modified=\"2008-01-15\" version=\"1\">MHAPL VSKDL</sequence></entry>"
          + "</uniprot>";

  /**
   * Test the method that unmarshals XML to a Uniprot model
   */
  @Test(groups = { "Functional" })
  public void testGetUniprotEntries()
  {
    Uniprot u = new Uniprot();
    Reader reader = new StringReader(UNIPROT_XML);
    Vector<UniprotEntry> entries = u.getUniprotEntries(reader);
    assertEquals(1, entries.size());
    UniprotEntry entry = entries.get(0);
    assertEquals(2, entry.getName().size());
    assertEquals("A9CKP4_AGRT5", entry.getName().get(0));
    assertEquals("A9CKP4_AGRT6", entry.getName().get(1));
    assertEquals(2, entry.getAccession().size());
    assertEquals("A9CKP4", entry.getAccession().get(0));
    assertEquals("A9CKP5", entry.getAccession().get(1));

    /*
     * UniprotSequence drops any space characters
     */
    assertEquals("MHAPLVSKDL", entry.getUniprotSequence().getContent());

    assertEquals(2, entry.getProtein().getName().size());
    assertEquals("Mitogen-activated protein kinase 13", entry.getProtein()
            .getName().get(0));
    assertEquals("Henry", entry.getProtein().getName().get(1));

    /*
     * Check sequence features
     */
    Vector<SequenceFeature> features = entry.getFeature();
    assertEquals(3, features.size());
    SequenceFeature sf = features.get(0);
    assertEquals("signal peptide", sf.getType());
    assertNull(sf.getDescription());
    assertNull(sf.getStatus());
    assertEquals(1, sf.getPosition());
    assertEquals(1, sf.getBegin());
    assertEquals(18, sf.getEnd());
    sf = features.get(1);
    assertEquals("propeptide", sf.getType());
    assertEquals("Activation peptide", sf.getDescription());
    assertEquals(19, sf.getPosition());
    assertEquals(19, sf.getBegin());
    assertEquals(20, sf.getEnd());
    sf = features.get(2);
    assertEquals("chain", sf.getType());
    assertEquals("Granzyme B", sf.getDescription());
    assertEquals(21, sf.getPosition());
    assertEquals(21, sf.getBegin());
    assertEquals(247, sf.getEnd());

    /*
     * Check cross-references
     */
    Vector<PDBEntry> xrefs = entry.getDbReference();
    assertEquals(3, xrefs.size());

    PDBEntry xref = xrefs.get(0);
    assertEquals("2FSQ", xref.getId());
    assertEquals("PDB", xref.getType());
    assertEquals(2, xref.getProperty().size());
    assertEquals("X-ray", xref.getProperty().get("method"));
    assertEquals("1.40", xref.getProperty().get("resolution"));

    xref = xrefs.get(1);
    assertEquals("2FSR", xref.getId());
    assertEquals("PDBsum", xref.getType());
    assertNull(xref.getProperty());

    xref = xrefs.get(2);
    assertEquals("AE007869", xref.getId());
    assertEquals("EMBL", xref.getType());
    assertNotNull(xref.getProperty());
    assertEquals("AAK85932.1",
            (String) xref.getProperty().get("protein sequence ID"));
    assertEquals("Genomic_DNA",
            (String) xref.getProperty().get("molecule type"));
    assertEquals(2, xref.getProperty().size());

  }

  @Test(groups = { "Functional" })
  public void testGetUniprotSequence()
  {
    UniprotEntry entry = new Uniprot().getUniprotEntries(
            new StringReader(UNIPROT_XML)).get(0);
    SequenceI seq = new Uniprot().uniprotEntryToSequenceI(entry);
    assertNotNull(seq);
    assertEquals(6, seq.getDBRefs().length); // 2*Uniprot, PDB, PDBsum, 2*EMBL

  }

  /**
   * Test the method that formats the sequence id
   */
  @Test(groups = { "Functional" })
  public void testGetUniprotEntryId()
  {
    UniprotEntry entry = new Uniprot().getUniprotEntries(
            new StringReader(UNIPROT_XML)).get(0);

    /*
     * name formatted as source | accession ids | names
     * source database converted to Jalview canonical name
     */
    String expectedName = "UNIPROT|A9CKP4|A9CKP5|A9CKP4_AGRT5|A9CKP4_AGRT6";
    assertEquals(expectedName, Uniprot.getUniprotEntryId(entry));
  }

  /**
   * Test the method that formats the sequence description
   */
  @Test(groups = { "Functional" })
  public void testGetUniprotEntryDescription()
  {
    UniprotEntry entry = new Uniprot().getUniprotEntries(
            new StringReader(UNIPROT_XML)).get(0);

    /*
     * recommended names concatenated with space separator
     */
    String expectedDescription = "Mitogen-activated protein kinase 13 Henry";
    assertEquals(expectedDescription,
            Uniprot.getUniprotEntryDescription(entry));
  }
}