JAL-2546 JAL-2490 efficient lookup of features, correct handling of
authorgmungoc <g.m.carstairs@dundee.ac.uk>
Mon, 22 May 2017 13:06:19 +0000 (14:06 +0100)
committergmungoc <g.m.carstairs@dundee.ac.uk>
Mon, 22 May 2017 13:06:19 +0000 (14:06 +0100)
non-positional features

examples/example.json
src/jalview/io/JSONFile.java
test/jalview/io/JSONFileTest.java

index 5f6e784..5055d04 100644 (file)
@@ -1 +1 @@
-{"seqs":[{"name":"FER_CAPAN/3-34","start":3,"svid":"1.0","end":34,"id":"1665704504","seq":"SVSATMISTSFMPRKPAVTSL-KPIPNVGE--ALF","order":1},{"name":"FER1_SOLLC/3-34","start":3,"svid":"1.0","end":34,"id":"1003594867","seq":"SISGTMISTSFLPRKPAVTSL-KAISNVGE--ALF","order":2},{"name":"Q93XJ9_SOLTU/3-34","start":3,"svid":"1.0","end":34,"id":"1332961135","seq":"SISGTMISTSFLPRKPVVTSL-KAISNVGE--ALF","order":3},{"name":"FER1_PEA/6-37","start":6,"svid":"1.0","end":37,"id":"1335040546","seq":"ALYGTAVSTSFLRTQPMPMSV-TTTKAFSN--GFL","order":4},{"name":"Q7XA98_TRIPR/6-39","start":6,"svid":"1.0","end":39,"id":"1777084554","seq":"ALYGTAVSTSFMRRQPVPMSV-ATTTTTKAFPSGF","order":5},{"name":"FER_TOCH/3-34","start":3,"svid":"1.0","end":34,"id":"823528539","seq":"FILGTMISKSFLFRKPAVTSL-KAISNVGE--ALF","order":6}],"appSettings":{"globalColorScheme":"zappo","webStartUrl":"www.jalview.org/services/launchApp","application":"Jalview","hiddenSeqs":"823528539","showSeqFeatures":"true","version":"2.9","hiddenCols":"32-33;34-34"},"seqGroups":[{"displayText":true,"startRes":21,"groupName":"JGroup:1883305585","endRes":29,"colourText":false,"sequenceRefs":["1003594867","1332961135","1335040546","1777084554"],"svid":"1.0","showNonconserved":false,"colourScheme":"Zappo","displayBoxes":true}],"alignAnnotation":[{"svid":"1.0","annotations":[{"displayCharacter":"","value":0,"secondaryStructure":"\u0000"},{"displayCharacter":"","value":0,"secondaryStructure":"\u0000"},{"displayCharacter":"α","value":0,"secondaryStructure":"H"},{"displayCharacter":"α","value":0,"secondaryStructure":"H"},{"displayCharacter":"α","value":0,"secondaryStructure":"H"},{"displayCharacter":"","value":0,"secondaryStructure":"\u0000"},{"displayCharacter":"","value":0,"secondaryStructure":"\u0000"},{"displayCharacter":"","value":0,"secondaryStructure":"\u0000"},{"displayCharacter":"β","value":0,"secondaryStructure":"E"},{"displayCharacter":"β","value":0,"secondaryStructure":"E"},{"displayCharacter":"β","value":0,"secondaryStructure":"E"},{"displayCharacter":"β","value":0,"secondaryStructure":"E"},{"displayCharacter":"β","value":0,"secondaryStructure":"E"},{"displayCharacter":"β","value":0,"secondaryStructure":"E"},{"displayCharacter":"β","value":0,"secondaryStructure":"E"},{"displayCharacter":"β","value":0,"secondaryStructure":"E"},{"displayCharacter":"","value":0,"secondaryStructure":"\u0000"},{"displayCharacter":"","value":0,"secondaryStructure":"\u0000"},{"displayCharacter":"","value":0,"secondaryStructure":"\u0000"},{"displayCharacter":"","value":0,"secondaryStructure":"\u0000"},{"displayCharacter":"","value":0,"secondaryStructure":"\u0000"},{"displayCharacter":"","value":0,"secondaryStructure":"\u0000"},{"displayCharacter":"","value":0,"secondaryStructure":"\u0000"},{"displayCharacter":"","value":0,"secondaryStructure":"\u0000"},{"displayCharacter":"","value":0,"secondaryStructure":"\u0000"},{"displayCharacter":"","value":0,"secondaryStructure":"\u0000"},{"displayCharacter":"α","value":0,"secondaryStructure":"H"},{"displayCharacter":"α","value":0,"secondaryStructure":"H"},{"displayCharacter":"α","value":0,"secondaryStructure":"H"},{"displayCharacter":"α","value":0,"secondaryStructure":"H"},{"displayCharacter":"α","value":0,"secondaryStructure":"H"},{"displayCharacter":"","value":0,"secondaryStructure":"\u0000"},{"displayCharacter":"","value":0,"secondaryStructure":"\u0000"},{"displayCharacter":"","value":0,"secondaryStructure":"\u0000"},{"displayCharacter":"","value":0,"secondaryStructure":"\u0000"}],"description":"New description","label":"Secondary Structure"}],"svid":"1.0","seqFeatures":[{"fillColor":"#7d1633","score":0,"sequenceRef":"1332961135","featureGroup":"Jalview","svid":"1.0","description":"desciption","xStart":3,"xEnd":13,"type":"feature_x"},{"fillColor":"#7d1633","score":0,"sequenceRef":"1335040546","featureGroup":"Jalview","svid":"1.0","description":"desciption","xStart":3,"xEnd":13,"type":"feature_x"},{"fillColor":"#7d1633","score":0,"sequenceRef":"1777084554","featureGroup":"Jalview","svid":"1.0","description":"desciption","xStart":3,"xEnd":13,"type":"feature_x"}]}
\ No newline at end of file
+{"seqs":[{"name":"FER_CAPAN/3-34","start":3,"svid":"1.0","end":34,"id":"1665704504","seq":"SVSATMISTSFMPRKPAVTSL-KPIPNVGE--ALF","order":1},{"name":"FER1_SOLLC/3-34","start":3,"svid":"1.0","end":34,"id":"1003594867","seq":"SISGTMISTSFLPRKPAVTSL-KAISNVGE--ALF","order":2},{"name":"Q93XJ9_SOLTU/3-34","start":3,"svid":"1.0","end":34,"id":"1332961135","seq":"SISGTMISTSFLPRKPVVTSL-KAISNVGE--ALF","order":3},{"name":"FER1_PEA/6-37","start":6,"svid":"1.0","end":37,"id":"1335040546","seq":"ALYGTAVSTSFLRTQPMPMSV-TTTKAFSN--GFL","order":4},{"name":"Q7XA98_TRIPR/6-39","start":6,"svid":"1.0","end":39,"id":"1777084554","seq":"ALYGTAVSTSFMRRQPVPMSV-ATTTTTKAFPSGF","order":5},{"name":"FER_TOCH/3-34","start":3,"svid":"1.0","end":34,"id":"823528539","seq":"FILGTMISKSFLFRKPAVTSL-KAISNVGE--ALF","order":6}],"appSettings":{"globalColorScheme":"zappo","webStartUrl":"www.jalview.org/services/launchApp","application":"Jalview","hiddenSeqs":"823528539","showSeqFeatures":"true","version":"2.9","hiddenCols":"32-33;34-34"},"seqGroups":[{"displayText":true,"startRes":21,"groupName":"JGroup:1883305585","endRes":29,"colourText":false,"sequenceRefs":["1003594867","1332961135","1335040546","1777084554"],"svid":"1.0","showNonconserved":false,"colourScheme":"Zappo","displayBoxes":true}],"alignAnnotation":[{"svid":"1.0","annotations":[{"displayCharacter":"","value":0,"secondaryStructure":"\u0000"},{"displayCharacter":"","value":0,"secondaryStructure":"\u0000"},{"displayCharacter":"α","value":0,"secondaryStructure":"H"},{"displayCharacter":"α","value":0,"secondaryStructure":"H"},{"displayCharacter":"α","value":0,"secondaryStructure":"H"},{"displayCharacter":"","value":0,"secondaryStructure":"\u0000"},{"displayCharacter":"","value":0,"secondaryStructure":"\u0000"},{"displayCharacter":"","value":0,"secondaryStructure":"\u0000"},{"displayCharacter":"β","value":0,"secondaryStructure":"E"},{"displayCharacter":"β","value":0,"secondaryStructure":"E"},{"displayCharacter":"β","value":0,"secondaryStructure":"E"},{"displayCharacter":"β","value":0,"secondaryStructure":"E"},{"displayCharacter":"β","value":0,"secondaryStructure":"E"},{"displayCharacter":"β","value":0,"secondaryStructure":"E"},{"displayCharacter":"β","value":0,"secondaryStructure":"E"},{"displayCharacter":"β","value":0,"secondaryStructure":"E"},{"displayCharacter":"","value":0,"secondaryStructure":"\u0000"},{"displayCharacter":"","value":0,"secondaryStructure":"\u0000"},{"displayCharacter":"","value":0,"secondaryStructure":"\u0000"},{"displayCharacter":"","value":0,"secondaryStructure":"\u0000"},{"displayCharacter":"","value":0,"secondaryStructure":"\u0000"},{"displayCharacter":"","value":0,"secondaryStructure":"\u0000"},{"displayCharacter":"","value":0,"secondaryStructure":"\u0000"},{"displayCharacter":"","value":0,"secondaryStructure":"\u0000"},{"displayCharacter":"","value":0,"secondaryStructure":"\u0000"},{"displayCharacter":"","value":0,"secondaryStructure":"\u0000"},{"displayCharacter":"α","value":0,"secondaryStructure":"H"},{"displayCharacter":"α","value":0,"secondaryStructure":"H"},{"displayCharacter":"α","value":0,"secondaryStructure":"H"},{"displayCharacter":"α","value":0,"secondaryStructure":"H"},{"displayCharacter":"α","value":0,"secondaryStructure":"H"},{"displayCharacter":"","value":0,"secondaryStructure":"\u0000"},{"displayCharacter":"","value":0,"secondaryStructure":"\u0000"},{"displayCharacter":"","value":0,"secondaryStructure":"\u0000"},{"displayCharacter":"","value":0,"secondaryStructure":"\u0000"}],"description":"New description","label":"Secondary Structure"}],"svid":"1.0","seqFeatures":[{"fillColor":"#7d1633","score":0,"sequenceRef":"1332961135","featureGroup":"Pfam","svid":"1.0","description":"My description","xStart":0,"xEnd":0,"type":"Domain"},{"fillColor":"#7d1633","score":0,"sequenceRef":"1332961135","featureGroup":"Jalview","svid":"1.0","description":"desciption","xStart":3,"xEnd":13,"type":"feature_x"},{"fillColor":"#7d1633","score":0,"sequenceRef":"1335040546","featureGroup":"Jalview","svid":"1.0","description":"desciption","xStart":3,"xEnd":13,"type":"feature_x"},{"fillColor":"#7d1633","score":0,"sequenceRef":"1777084554","featureGroup":"Jalview","svid":"1.0","description":"desciption","xStart":3,"xEnd":13,"type":"feature_x"}]}
\ No newline at end of file
index 8bbbcd1..14574d0 100644 (file)
@@ -51,6 +51,7 @@ import jalview.schemes.ColourSchemeProperty;
 import jalview.schemes.JalviewColourScheme;
 import jalview.schemes.ResidueColourScheme;
 import jalview.util.ColorUtils;
+import jalview.util.Format;
 import jalview.viewmodel.seqfeatures.FeaturesDisplayed;
 
 import java.awt.Color;
@@ -228,8 +229,7 @@ public class JSONFile extends AlignFile implements ComplexAlignFile
 
       if (exportSettings.isExportFeatures())
       {
-        jsonAlignmentPojo
-                .setSeqFeatures(sequenceFeatureToJsonPojo(sqs, fr));
+        jsonAlignmentPojo.setSeqFeatures(sequenceFeatureToJsonPojo(sqs));
       }
 
       if (exportSettings.isExportGroups() && seqGroups != null
@@ -319,8 +319,8 @@ public class JSONFile extends AlignFile implements ComplexAlignFile
     return hiddenSections;
   }
 
-  public List<SequenceFeaturesPojo> sequenceFeatureToJsonPojo(
-          SequenceI[] sqs, FeatureRenderer fr)
+  protected List<SequenceFeaturesPojo> sequenceFeatureToJsonPojo(
+          SequenceI[] sqs)
   {
     displayedFeatures = (fr == null) ? null : fr.getFeaturesDisplayed();
     List<SequenceFeaturesPojo> sequenceFeaturesPojo = new ArrayList<SequenceFeaturesPojo>();
@@ -331,41 +331,38 @@ public class JSONFile extends AlignFile implements ComplexAlignFile
 
     FeatureColourFinder finder = new FeatureColourFinder(fr);
 
+    String[] visibleFeatureTypes = displayedFeatures == null ? null
+            : displayedFeatures.getVisibleFeatures().toArray(
+                    new String[displayedFeatures.getVisibleFeatureCount()]);
+
     for (SequenceI seq : sqs)
     {
-      SequenceI dataSetSequence = seq.getDatasetSequence();
-      SequenceFeature[] seqFeatures = (dataSetSequence == null) ? null
-              : seq.getDatasetSequence().getSequenceFeatures();
-
-      seqFeatures = (seqFeatures == null) ? seq.getSequenceFeatures()
-              : seqFeatures;
-      if (seqFeatures == null)
-      {
-        continue;
-      }
-
+      /*
+       * get all features currently visible (and any non-positional features)
+       */
+      List<SequenceFeature> seqFeatures = seq.getFeatures().getAllFeatures(
+              visibleFeatureTypes);
       for (SequenceFeature sf : seqFeatures)
       {
-        if (displayedFeatures != null
-                && displayedFeatures.isVisible(sf.getType()))
-        {
-          SequenceFeaturesPojo jsonFeature = new SequenceFeaturesPojo(
-                  String.valueOf(seq.hashCode()));
-
-          String featureColour = (fr == null) ? null : jalview.util.Format
-                  .getHexString(finder.findFeatureColour(Color.white, seq,
-                          seq.findIndex(sf.getBegin())));
-          jsonFeature.setXstart(seq.findIndex(sf.getBegin()) - 1);
-          jsonFeature.setXend(seq.findIndex(sf.getEnd()));
-          jsonFeature.setType(sf.getType());
-          jsonFeature.setDescription(sf.getDescription());
-          jsonFeature.setLinks(sf.links);
-          jsonFeature.setOtherDetails(sf.otherDetails);
-          jsonFeature.setScore(sf.getScore());
-          jsonFeature.setFillColor(featureColour);
-          jsonFeature.setFeatureGroup(sf.getFeatureGroup());
-          sequenceFeaturesPojo.add(jsonFeature);
-        }
+        SequenceFeaturesPojo jsonFeature = new SequenceFeaturesPojo(
+                String.valueOf(seq.hashCode()));
+
+        String featureColour = (fr == null) ? null : Format
+                .getHexString(finder.findFeatureColour(Color.white, seq,
+                        seq.findIndex(sf.getBegin())));
+        int xStart = sf.getBegin() == 0 ? 0
+                : seq.findIndex(sf.getBegin()) - 1;
+        int xEnd = sf.getEnd() == 0 ? 0 : seq.findIndex(sf.getEnd());
+        jsonFeature.setXstart(xStart);
+        jsonFeature.setXend(xEnd);
+        jsonFeature.setType(sf.getType());
+        jsonFeature.setDescription(sf.getDescription());
+        jsonFeature.setLinks(sf.links);
+        jsonFeature.setOtherDetails(sf.otherDetails);
+        jsonFeature.setScore(sf.getScore());
+        jsonFeature.setFillColor(featureColour);
+        jsonFeature.setFeatureGroup(sf.getFeatureGroup());
+        sequenceFeaturesPojo.add(jsonFeature);
       }
     }
     return sequenceFeaturesPojo;
@@ -696,8 +693,14 @@ public class JSONFile extends AlignFile implements ComplexAlignFile
         Float score = Float.valueOf(jsonFeature.get("score").toString());
 
         Sequence seq = seqMap.get(seqRef);
-        int featureBegin = seq.findPosition(begin.intValue());
-        int featureEnd = seq.findPosition(end.intValue()) - 1;
+
+        /*
+         * begin/end of 0 is for a non-positional feature
+         */
+        int featureBegin = begin.intValue() == 0 ? 0 : seq
+                .findPosition(begin.intValue());
+        int featureEnd = end.intValue() == 0 ? 0 : seq.findPosition(end
+                .intValue()) - 1;
 
         SequenceFeature sequenceFeature = new SequenceFeature(type,
                 description, featureBegin, featureEnd, score, featureGrp);
index 2aff5cc..410263c 100644 (file)
@@ -32,6 +32,7 @@ import jalview.datamodel.Sequence;
 import jalview.datamodel.SequenceFeature;
 import jalview.datamodel.SequenceGroup;
 import jalview.datamodel.SequenceI;
+import jalview.datamodel.features.SequenceFeatures;
 import jalview.gui.AlignFrame;
 import jalview.gui.JvOptionPane;
 import jalview.json.binding.biojson.v1.ColourSchemeMapper;
@@ -96,6 +97,10 @@ public class JSONFileTest
   @BeforeTest(alwaysRun = true)
   public void setup() throws Exception
   {
+    /*
+     * construct expected values
+     * nb this have to match the data in examples/example.json
+     */
     // create and add sequences
     Sequence[] seqs = new Sequence[5];
     seqs[0] = new Sequence("FER_CAPAN",
@@ -115,14 +120,18 @@ public class JSONFileTest
 
     // create and add sequence features
     SequenceFeature seqFeature2 = new SequenceFeature("feature_x",
-            "desciption", "status", 6, 15, "Jalview");
+            "description", "status", 6, 15, "Jalview");
     SequenceFeature seqFeature3 = new SequenceFeature("feature_x",
-            "desciption", "status", 9, 18, "Jalview");
+            "description", "status", 9, 18, "Jalview");
     SequenceFeature seqFeature4 = new SequenceFeature("feature_x",
-            "desciption", "status", 9, 18, "Jalview");
+            "description", "status", 9, 18, "Jalview");
+    // non-positional feature:
+    SequenceFeature seqFeature5 = new SequenceFeature("Domain",
+            "My description", "status", 0, 0, "Pfam");
     seqs[2].addSequenceFeature(seqFeature2);
     seqs[3].addSequenceFeature(seqFeature3);
     seqs[4].addSequenceFeature(seqFeature4);
+    seqs[2].addSequenceFeature(seqFeature5);
 
     for (Sequence seq : seqs)
     {
@@ -456,7 +465,7 @@ public class JSONFileTest
     return true;
   }
 
-  public boolean isSeqMatched(SequenceI expectedSeq, SequenceI actualSeq)
+  boolean isSeqMatched(SequenceI expectedSeq, SequenceI actualSeq)
   {
     System.out.println("Testing >>> " + actualSeq.getName());
 
@@ -490,14 +499,19 @@ public class JSONFileTest
             + actualGrp.getStartRes());
     System.out.println(expectedGrp.getEndRes() + " | "
             + actualGrp.getEndRes());
-    System.out.println(expectedGrp.cs + " | " + actualGrp.cs);
+    System.out.println(expectedGrp.cs.getColourScheme() + " | "
+            + actualGrp.cs.getColourScheme());
 
+    boolean colourSchemeMatches = (expectedGrp.cs.getColourScheme() == null && actualGrp.cs
+            .getColourScheme() == null)
+            || expectedGrp.cs.getColourScheme().getClass()
+                    .equals(actualGrp.cs.getColourScheme().getClass());
     if (expectedGrp.getName().equals(actualGrp.getName())
             && expectedGrp.getColourText() == actualGrp.getColourText()
             && expectedGrp.getDisplayBoxes() == actualGrp.getDisplayBoxes()
             && expectedGrp.getIgnoreGapsConsensus() == actualGrp
                     .getIgnoreGapsConsensus()
-            && (expectedGrp.cs.getClass().equals(actualGrp.cs.getClass()))
+            && colourSchemeMatches
             && expectedGrp.getSequences().size() == actualGrp
                     .getSequences().size()
             && expectedGrp.getStartRes() == actualGrp.getStartRes()
@@ -510,7 +524,6 @@ public class JSONFileTest
 
   private boolean featuresMatched(SequenceI seq1, SequenceI seq2)
   {
-    boolean matched = false;
     try
     {
       if (seq1 == null && seq2 == null)
@@ -518,52 +531,48 @@ public class JSONFileTest
         return true;
       }
 
-      SequenceFeature[] inFeature = seq1.getSequenceFeatures();
-      SequenceFeature[] outFeature = seq2.getSequenceFeatures();
+      List<SequenceFeature> inFeature = seq1.getFeatures().getAllFeatures();
+      List<SequenceFeature> outFeature = seq2.getFeatures()
+              .getAllFeatures();
 
-      if (inFeature == null && outFeature == null)
-      {
-        return true;
-      }
-      else if ((inFeature == null && outFeature != null)
-              || (inFeature != null && outFeature == null))
+      if (inFeature.size() != outFeature.size())
       {
+        System.err.println("Feature count in: " + inFeature.size()
+                + ", out: " + outFeature.size());
         return false;
       }
 
-      int testSize = inFeature.length;
-      int matchedCount = 0;
+      SequenceFeatures.sortFeatures(inFeature, true);
+      SequenceFeatures.sortFeatures(outFeature, true);
+      int i = 0;
       for (SequenceFeature in : inFeature)
       {
-        for (SequenceFeature out : outFeature)
+        SequenceFeature out = outFeature.get(i);
+        System.out.println(out.getType() + " | " + in.getType());
+        System.out.println(out.getBegin() + " | " + in.getBegin());
+        System.out.println(out.getEnd() + " | " + in.getEnd());
+
+        if (in.getBegin() == out.getBegin() && in.getEnd() == out.getEnd()
+                && in.getScore() == out.getScore()
+                && in.getFeatureGroup().equals(out.getFeatureGroup())
+                && in.getType().equals(out.getType()))
         {
-          System.out.println(out.getType() + " | " + in.getType());
-          System.out.println(out.getBegin() + " | " + in.getBegin());
-          System.out.println(out.getEnd() + " | " + in.getEnd());
-
-          if (inFeature.length == outFeature.length
-                  && in.getBegin() == out.getBegin()
-                  && in.getEnd() == out.getEnd()
-                  && in.getScore() == out.getScore()
-                  && in.getFeatureGroup().equals(out.getFeatureGroup())
-                  && in.getType().equals(out.getType()))
-          {
-
-            ++matchedCount;
-          }
         }
-      }
-      System.out.println("matched count >>>>>> " + matchedCount);
-      if (testSize == matchedCount)
-      {
-        matched = true;
+        else
+        {
+          System.err.println("Feature[" + i + "] mismatch, in: "
+                  + in.toString() + ", out: "
+                  + outFeature.get(i).toString());
+          return false;
+        }
+        i++;
       }
     } catch (Exception e)
     {
       e.printStackTrace();
     }
     // System.out.println(">>>>>>>>>>>>>> features matched : " + matched);
-    return matched;
+    return true;
   }
 
   /**
@@ -599,7 +608,7 @@ public class JSONFileTest
     Assert.assertNotNull(newAlignment.getGroups());
     for (SequenceGroup seqGrp : newAlignment.getGroups())
     {
-      SequenceGroup expectedGrp = expectedGrps.get(seqGrp.getName());
+      SequenceGroup expectedGrp = copySg;
       AssertJUnit.assertTrue(
               "Failed SequenceGroup Test for >>> " + seqGrp.getName(),
               isGroupMatched(expectedGrp, seqGrp));