X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Futil%2FMappingUtils.java;h=0933b978db6b993dc27940168d21e2411582ba6a;hb=17e77c3f2949a0729322b4a8d907f3f34b6a9914;hp=4cfb49ea09f72eecf4e59e9c87eec6d9953b4ab1;hpb=be32c14cd8e48fe0a207cd7030cb9cd46f894678;p=jalview.git

diff --git a/src/jalview/util/MappingUtils.java b/src/jalview/util/MappingUtils.java
index 4cfb49e..0933b97 100644
--- a/src/jalview/util/MappingUtils.java
+++ b/src/jalview/util/MappingUtils.java
@@ -1,3 +1,23 @@
+/*
+ * Jalview - A Sequence Alignment Editor and Viewer (Version 2.9)
+ * 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.util;
 
 import jalview.analysis.AlignmentSorter;
@@ -18,6 +38,7 @@ import jalview.datamodel.SequenceGroup;
 import jalview.datamodel.SequenceI;
 
 import java.util.ArrayList;
+import java.util.Collections;
 import java.util.HashMap;
 import java.util.Iterator;
 import java.util.List;
@@ -199,8 +220,8 @@ public final class MappingUtils
              */
             int mappedEditPos = action == Action.DELETE_GAP ? match[0]
                     - mappedCount : match[0];
-            Edit e = result.new Edit(action, new SequenceI[]
-            { targetSeq }, mappedEditPos, mappedCount, gapChar);
+            Edit e = result.new Edit(action, new SequenceI[] { targetSeq },
+                    mappedEditPos, mappedCount, gapChar);
             result.addEdit(e);
 
             /*
@@ -249,8 +270,23 @@ public final class MappingUtils
   public static SearchResults buildSearchResults(SequenceI seq, int index,
           Set<AlignedCodonFrame> seqmappings)
   {
-    SearchResults results;
-    results = new SearchResults();
+    SearchResults results = new SearchResults();
+    addSearchResults(results, seq, index, seqmappings);
+    return results;
+  }
+
+  /**
+   * Adds entries to a SearchResults object describing the mapped region
+   * corresponding to the specified sequence position.
+   * 
+   * @param results
+   * @param seq
+   * @param index
+   * @param seqmappings
+   */
+  public static void addSearchResults(SearchResults results, SequenceI seq,
+          int index, Set<AlignedCodonFrame> seqmappings)
+  {
     if (index >= seq.getStart() && index <= seq.getEnd())
     {
       for (AlignedCodonFrame acf : seqmappings)
@@ -258,7 +294,6 @@ public final class MappingUtils
         acf.markMappedRegion(seq, index, results);
       }
     }
-    return results;
   }
 
   /**
@@ -270,8 +305,8 @@ public final class MappingUtils
    * @param mapTo
    * @return
    */
-  public static SequenceGroup mapSequenceGroup(SequenceGroup sg,
-          AlignViewportI mapFrom, AlignViewportI mapTo)
+  public static SequenceGroup mapSequenceGroup(final SequenceGroup sg,
+          final AlignViewportI mapFrom, final AlignViewportI mapTo)
   {
     /*
      * Note the SequenceGroup holds aligned sequences, the mappings hold dataset
@@ -281,18 +316,50 @@ public final class MappingUtils
     AlignViewportI protein = targetIsNucleotide ? mapFrom : mapTo;
     Set<AlignedCodonFrame> codonFrames = protein.getAlignment()
             .getCodonFrames();
-
     /*
-     * Copy group name, name colours, but not sequences or sequence colour
-     * scheme
+     * Copy group name, colours etc, but not sequences or sequence colour scheme
      */
     SequenceGroup mappedGroup = new SequenceGroup(sg);
     mappedGroup.cs = mapTo.getGlobalColourScheme();
     mappedGroup.clear();
-    // TODO set width of mapped group
 
+    int minStartCol = -1;
+    int maxEndCol = -1;
+    final int selectionStartRes = sg.getStartRes();
+    final int selectionEndRes = sg.getEndRes();
     for (SequenceI selected : sg.getSequences())
     {
+      /*
+       * Find the widest range of non-gapped positions in the selection range
+       */
+      int firstUngappedPos = selectionStartRes;
+      while (firstUngappedPos <= selectionEndRes
+              && Comparison.isGap(selected.getCharAt(firstUngappedPos)))
+      {
+        firstUngappedPos++;
+      }
+
+      /*
+       * If this sequence is only gaps in the selected range, skip it
+       */
+      if (firstUngappedPos > selectionEndRes)
+      {
+        continue;
+      }
+
+      int lastUngappedPos = selectionEndRes;
+      while (lastUngappedPos >= selectionStartRes
+              && Comparison.isGap(selected.getCharAt(lastUngappedPos)))
+      {
+        lastUngappedPos--;
+      }
+
+      /*
+       * Find the selected start/end residue positions in sequence
+       */
+      int startResiduePos = selected.findPosition(firstUngappedPos);
+      int endResiduePos = selected.findPosition(lastUngappedPos);
+
       for (AlignedCodonFrame acf : codonFrames)
       {
         SequenceI mappedSequence = targetIsNucleotide ? acf
@@ -301,8 +368,39 @@ public final class MappingUtils
         {
           for (SequenceI seq : mapTo.getAlignment().getSequences())
           {
+            int mappedStartResidue = 0;
+            int mappedEndResidue = 0;
             if (seq.getDatasetSequence() == mappedSequence)
             {
+              /*
+               * Found a sequence mapping. Locate the start/end mapped residues.
+               */
+              SearchResults sr = buildSearchResults(selected,
+                      startResiduePos, Collections.singleton(acf));
+              for (Match m : sr.getResults())
+              {
+                mappedStartResidue = m.getStart();
+                mappedEndResidue = m.getEnd();
+              }
+              sr = buildSearchResults(selected, endResiduePos,
+                      Collections.singleton(acf));
+              for (Match m : sr.getResults())
+              {
+                mappedStartResidue = Math.min(mappedStartResidue,
+                        m.getStart());
+                mappedEndResidue = Math.max(mappedEndResidue, m.getEnd());
+              }
+
+              /*
+               * Find the mapped aligned columns, save the range. Note findIndex
+               * returns a base 1 position, SequenceGroup uses base 0
+               */
+              int mappedStartCol = seq.findIndex(mappedStartResidue) - 1;
+              minStartCol = minStartCol == -1 ? mappedStartCol : Math.min(
+                      minStartCol, mappedStartCol);
+              int mappedEndCol = seq.findIndex(mappedEndResidue) - 1;
+              maxEndCol = maxEndCol == -1 ? mappedEndCol : Math.max(
+                      maxEndCol, mappedEndCol);
               mappedGroup.addSequence(seq, false);
               break;
             }
@@ -310,6 +408,8 @@ public final class MappingUtils
         }
       }
     }
+    mappedGroup.setStartRes(minStartCol < 0 ? 0 : minStartCol);
+    mappedGroup.setEndRes(maxEndCol < 0 ? 0 : maxEndCol);
     return mappedGroup;
   }
 
@@ -333,18 +433,19 @@ public final class MappingUtils
     SequenceI[] sortOrder = command.getSequenceOrder(undo);
     List<SequenceI> mappedOrder = new ArrayList<SequenceI>();
     int j = 0;
+
+    /*
+     * Assumption: we are only interested in a cDNA/protein mapping; refactor in
+     * future if we want to support sorting (c)dna as (c)dna or protein as
+     * protein
+     */
+    boolean mappingToNucleotide = mapTo.isNucleotide();
     for (SequenceI seq : sortOrder)
     {
       for (AlignedCodonFrame acf : mappings)
       {
-        /*
-         * Try protein-to-Dna, failing that try dna-to-protein
-         */
-        SequenceI mappedSeq = acf.getDnaForAaSeq(seq);
-        if (mappedSeq == null)
-        {
-          mappedSeq = acf.getAaForDnaSeq(seq);
-        }
+        SequenceI mappedSeq = mappingToNucleotide ? acf.getDnaForAaSeq(seq)
+                : acf.getAaForDnaSeq(seq);
         if (mappedSeq != null)
         {
           for (SequenceI seq2 : mapTo.getSequences())
@@ -414,6 +515,12 @@ public final class MappingUtils
     Set<AlignedCodonFrame> codonFrames = protein.getAlignment()
             .getCodonFrames();
     ColumnSelection mappedColumns = new ColumnSelection();
+
+    if (colsel == null)
+    {
+      return mappedColumns;
+    }
+
     char fromGapChar = mapFrom.getAlignment().getGapCharacter();
 
     // FIXME allow for hidden columns
@@ -542,4 +649,30 @@ public final class MappingUtils
     }
     return result;
   }
+
+  /**
+   * Returns a list of any mappings that are from or to the given (aligned or
+   * dataset) sequence.
+   * 
+   * @param sequence
+   * @param mappings
+   * @return
+   */
+  public static List<AlignedCodonFrame> findMappingsForSequence(
+          SequenceI sequence, Set<AlignedCodonFrame> mappings)
+  {
+    List<AlignedCodonFrame> result = new ArrayList<AlignedCodonFrame>();
+    if (sequence == null || mappings == null)
+    {
+      return result;
+    }
+    for (AlignedCodonFrame mapping : mappings)
+    {
+      if (mapping.involvesSequence(sequence))
+      {
+        result.add(mapping);
+      }
+    }
+    return result;
+  }
 }