X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fanalysis%2FAlignmentUtils.java;h=6385fa75076c0ef2d32d715ae67781bcb8126f39;hb=b5d61763044c1d72f06ce0e50da2171422a3774b;hp=2e607c08fff25b96a6aa129d8efccde40fee4c7c;hpb=135d3c8e51d19e221e68134a3cd7290fa9c783a8;p=jalview.git

diff --git a/src/jalview/analysis/AlignmentUtils.java b/src/jalview/analysis/AlignmentUtils.java
index 2e607c0..6385fa7 100644
--- a/src/jalview/analysis/AlignmentUtils.java
+++ b/src/jalview/analysis/AlignmentUtils.java
@@ -1,22 +1,46 @@
+/*
+ * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8.2)
+ * Copyright (C) 2014 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.analysis;
 
+import jalview.datamodel.AlignmentAnnotation;
+import jalview.datamodel.AlignmentI;
+import jalview.datamodel.SequenceI;
+
 import java.util.ArrayList;
 import java.util.List;
 
-import jalview.datamodel.SequenceI;
-import jalview.datamodel.AlignmentI;
-
 /**
- * grab bag of useful alignment manipulation operations
- * Expect these to be refactored elsewhere at some point.
+ * grab bag of useful alignment manipulation operations Expect these to be
+ * refactored elsewhere at some point.
+ * 
  * @author jimp
- *
+ * 
  */
 public class AlignmentUtils
 {
 
   /**
-   * given an existing alignment, create a new alignment including all, or up to flankSize additional symbols from each sequence's dataset sequence
+   * given an existing alignment, create a new alignment including all, or up to
+   * flankSize additional symbols from each sequence's dataset sequence
+   * 
    * @param core
    * @param flankSize
    * @return AlignmentI
@@ -25,67 +49,114 @@ public class AlignmentUtils
   {
     List<SequenceI> sq = new ArrayList<SequenceI>();
     int maxoffset = 0;
-    for (SequenceI s:core.getSequences())
+    for (SequenceI s : core.getSequences())
     {
       SequenceI newSeq = s.deriveSequence();
-      if (newSeq.getStart()>maxoffset)
+      if (newSeq.getStart() > maxoffset
+              && newSeq.getDatasetSequence().getStart() < s.getStart())
       {
         maxoffset = newSeq.getStart();
       }
       sq.add(newSeq);
     }
-    if (flankSize>-1) {
+    if (flankSize > -1)
+    {
       maxoffset = flankSize;
     }
     // now add offset to create a new expanded alignment
-    for (SequenceI s:sq)
+    for (SequenceI s : sq)
     {
       SequenceI ds = s;
-      while (ds.getDatasetSequence()!=null) {
-        ds=ds.getDatasetSequence();
+      while (ds.getDatasetSequence() != null)
+      {
+        ds = ds.getDatasetSequence();
       }
+      int s_end = s.findPosition(s.getStart() + s.getLength());
       // find available flanking residues for sequence
-      int ustream_ds=s.getStart()-ds.getStart(),dstream_ds=ds.getEnd()-s.getEnd();
-      
+      int ustream_ds = s.getStart() - ds.getStart(), dstream_ds = ds
+              .getEnd() - s_end;
+
       // build new flanked sequence
-      
+
       // compute gap padding to start of flanking sequence
-      int offset=maxoffset - ustream_ds;
-      
+      int offset = maxoffset - ustream_ds;
+
       // padding is gapChar x ( maxoffset - min(ustream_ds, flank)
-      if (flankSize>=0) {
-        if (flankSize<ustream_ds)
+      if (flankSize >= 0)
+      {
+        if (flankSize < ustream_ds)
         {
-        // take up to flankSize residues
-        offset = maxoffset-flankSize;
-        ustream_ds = flankSize;
-      }
-        if (flankSize<dstream_ds)
+          // take up to flankSize residues
+          offset = maxoffset - flankSize;
+          ustream_ds = flankSize;
+        }
+        if (flankSize < dstream_ds)
         {
-          dstream_ds=flankSize;
+          dstream_ds = flankSize;
         }
       }
-      char[] upstream = new String(ds.getSequence(s.getStart()-1-ustream_ds, s.getStart()-1)).toLowerCase().toCharArray();
-      char[] downstream = new String(ds.getSequence(s.getEnd()+1,s.getEnd()+1+dstream_ds)).toLowerCase().toCharArray();
-      char[] coreseq=s.getSequence();
-      char[] nseq = new char[offset+upstream.length+downstream.length+coreseq.length]; 
+      char[] upstream = new String(ds.getSequence(s.getStart() - 1
+              - ustream_ds, s.getStart() - 1)).toLowerCase().toCharArray();
+      char[] downstream = new String(ds.getSequence(s_end - 1, s_end + 1
+              + dstream_ds)).toLowerCase().toCharArray();
+      char[] coreseq = s.getSequence();
+      char[] nseq = new char[offset + upstream.length + downstream.length
+              + coreseq.length];
       char c = core.getGapCharacter();
       // TODO could lowercase the flanking regions
-      int p=0;
-      for (; p<offset;p++)
+      int p = 0;
+      for (; p < offset; p++)
       {
         nseq[p] = c;
       }
-//      s.setSequence(new String(upstream).toLowerCase()+new String(coreseq) + new String(downstream).toLowerCase());
+      // s.setSequence(new String(upstream).toLowerCase()+new String(coreseq) +
+      // new String(downstream).toLowerCase());
       System.arraycopy(upstream, 0, nseq, p, upstream.length);
-      System.arraycopy(coreseq, 0, nseq, p+upstream.length, coreseq.length);
-      System.arraycopy(downstream, 0, nseq, p+coreseq.length+upstream.length, downstream.length);
+      System.arraycopy(coreseq, 0, nseq, p + upstream.length,
+              coreseq.length);
+      System.arraycopy(downstream, 0, nseq, p + coreseq.length
+              + upstream.length, downstream.length);
       s.setSequence(new String(nseq));
-      s.setStart(s.getStart()-ustream_ds);
-      s.setEnd(s.getEnd()+downstream.length);
+      s.setStart(s.getStart() - ustream_ds);
+      s.setEnd(s_end + downstream.length);
+    }
+    AlignmentI newAl = new jalview.datamodel.Alignment(
+            sq.toArray(new SequenceI[0]));
+    for (SequenceI s : sq)
+    {
+      if (s.getAnnotation() != null)
+      {
+        for (AlignmentAnnotation aa : s.getAnnotation())
+        {
+          newAl.addAnnotation(aa);
+        }
+      }
     }
-    AlignmentI newAl = new jalview.datamodel.Alignment(sq.toArray(new SequenceI[0]));
     newAl.setDataset(core.getDataset());
     return newAl;
   }
+
+  /**
+   * Returns the index (zero-based position) of a sequence in an alignment, or
+   * -1 if not found.
+   * 
+   * @param al
+   * @param seq
+   * @return
+   */
+  public static int getSequenceIndex(AlignmentI al, SequenceI seq)
+  {
+    int result = -1;
+    int pos = 0;
+    for (SequenceI alSeq : al.getSequences())
+    {
+      if (alSeq == seq)
+      {
+        result = pos;
+        break;
+      }
+      pos++;
+    }
+    return result;
+  }
 }