X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fio%2Fvcf%2FVCFLoader.java;h=dadb5324c0436963e83721334a62213d2acbf693;hb=41b0e9331ac71787c1280aa1d809f54c575fbf97;hp=168f1c6499bfcaf4a1d9bd437bb5afe4dc9eeda5;hpb=006890b02106eb31841e6e84d75f1027434823e0;p=jalview.git

diff --git a/src/jalview/io/vcf/VCFLoader.java b/src/jalview/io/vcf/VCFLoader.java
index 168f1c6..dadb532 100644
--- a/src/jalview/io/vcf/VCFLoader.java
+++ b/src/jalview/io/vcf/VCFLoader.java
@@ -1,25 +1,26 @@
+/*
+ * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
+ * Copyright (C) $$Year-Rel$$ 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.io.vcf;
 
-import jalview.analysis.Dna;
-import jalview.api.AlignViewControllerGuiI;
-import jalview.bin.Cache;
-import jalview.datamodel.DBRefEntry;
-import jalview.datamodel.GeneLociI;
-import jalview.datamodel.Mapping;
-import jalview.datamodel.SequenceFeature;
-import jalview.datamodel.SequenceI;
-import jalview.datamodel.features.FeatureAttributeType;
-import jalview.datamodel.features.FeatureSource;
-import jalview.datamodel.features.FeatureSources;
-import jalview.ext.ensembl.EnsemblMap;
-import jalview.ext.htsjdk.HtsContigDb;
-import jalview.ext.htsjdk.VCFReader;
-import jalview.io.gff.Gff3Helper;
-import jalview.io.gff.SequenceOntologyI;
-import jalview.util.MapList;
-import jalview.util.MappingUtils;
-import jalview.util.MessageManager;
-import jalview.util.StringUtils;
+import java.util.Locale;
 
 import java.io.File;
 import java.io.IOException;
@@ -47,6 +48,26 @@ import htsjdk.variant.vcf.VCFHeaderLine;
 import htsjdk.variant.vcf.VCFHeaderLineCount;
 import htsjdk.variant.vcf.VCFHeaderLineType;
 import htsjdk.variant.vcf.VCFInfoHeaderLine;
+import jalview.analysis.Dna;
+import jalview.api.AlignViewControllerGuiI;
+import jalview.bin.Cache;
+import jalview.datamodel.DBRefEntry;
+import jalview.datamodel.GeneLociI;
+import jalview.datamodel.Mapping;
+import jalview.datamodel.SequenceFeature;
+import jalview.datamodel.SequenceI;
+import jalview.datamodel.features.FeatureAttributeType;
+import jalview.datamodel.features.FeatureSource;
+import jalview.datamodel.features.FeatureSources;
+import jalview.ext.ensembl.EnsemblMap;
+import jalview.ext.htsjdk.HtsContigDb;
+import jalview.ext.htsjdk.VCFReader;
+import jalview.io.gff.Gff3Helper;
+import jalview.io.gff.SequenceOntologyI;
+import jalview.util.MapList;
+import jalview.util.MappingUtils;
+import jalview.util.MessageManager;
+import jalview.util.StringUtils;
 
 /**
  * A class to read VCF data (using the htsjdk) and add variants as sequence
@@ -412,7 +433,7 @@ public class VCFLoader
               + DEFAULT_REFERENCE + ":" + DEFAULT_SPECIES);
       reference = DEFAULT_REFERENCE; // default to GRCh37 if not specified
     }
-    reference = reference.toLowerCase();
+    reference = reference.toLowerCase(Locale.ROOT);
 
     /*
      * for a non-human species, or other assembly identifier,
@@ -427,7 +448,7 @@ public class VCFLoader
       String[] tokens = token.split("=");
       if (tokens.length == 2)
       {
-        if (reference.contains(tokens[0].trim().toLowerCase()))
+        if (reference.contains(tokens[0].trim().toLowerCase(Locale.ROOT)))
         {
           vcfAssembly = tokens[1].trim();
           break;
@@ -444,7 +465,7 @@ public class VCFLoader
         String[] tokens = token.split("=");
         if (tokens.length == 2)
         {
-          if (reference.contains(tokens[0].trim().toLowerCase()))
+          if (reference.contains(tokens[0].trim().toLowerCase(Locale.ROOT)))
           {
             vcfSpecies = tokens[1].trim();
             break;
@@ -549,7 +570,7 @@ public class VCFLoader
   {
     for (Pattern p : filters)
     {
-      if (p.matcher(id.toUpperCase()).matches())
+      if (p.matcher(id.toUpperCase(Locale.ROOT)).matches())
       {
         return true;
       }
@@ -643,7 +664,7 @@ public class VCFLoader
     {
       try
       {
-      patterns.add(Pattern.compile(token.toUpperCase()));
+      patterns.add(Pattern.compile(token.toUpperCase(Locale.ROOT)));
       } catch (PatternSyntaxException e)
       {
         System.err.println("Invalid pattern ignored: " + token);
@@ -654,7 +675,6 @@ public class VCFLoader
 
   /**
    * Transfers VCF features to sequences to which this sequence has a mapping.
-   * If the mapping is 3:1, computes peptide variants from nucleotide variants.
    * 
    * @param seq
    */
@@ -877,12 +897,19 @@ public class VCFLoader
           int[] featureRange = map.map.locateInFrom(variant.getStart(),
                   variant.getEnd());
 
+          /*
+           * only take features whose range is fully mappable to sequence positions
+           */
           if (featureRange != null)
           {
             int featureStart = Math.min(featureRange[0], featureRange[1]);
             int featureEnd = Math.max(featureRange[0], featureRange[1]);
-            count += addAlleleFeatures(seq, variant, featureStart,
-                    featureEnd, forwardStrand);
+            if (featureEnd - featureStart == variant.getEnd()
+                    - variant.getStart())
+            {
+              count += addAlleleFeatures(seq, variant, featureStart,
+                      featureEnd, forwardStrand);
+            }
           }
         }
         variants.close();
@@ -892,7 +919,7 @@ public class VCFLoader
          * RuntimeException throwable by htsjdk
          */
         String msg = String.format("Error reading VCF for %s:%d-%d: %s ",
-                map.chromosome, vcfStart, vcfEnd);
+                map.chromosome, vcfStart, vcfEnd,e.getLocalizedMessage());
         Cache.log.error(msg);
       }
     }
@@ -1008,7 +1035,7 @@ public class VCFLoader
      */
     String consequence = getConsequenceForAlleleAndFeature(variant, CSQ_FIELD,
             altAlleleIndex, csqAlleleFieldIndex,
-            csqAlleleNumberFieldIndex, seq.getName().toLowerCase(),
+            csqAlleleNumberFieldIndex, seq.getName().toLowerCase(Locale.ROOT),
             csqFeatureFieldIndex);
 
     /*
@@ -1201,7 +1228,7 @@ public class VCFLoader
       {
         String featureIdentifier = csqFields[featureFieldIndex];
         if (featureIdentifier.length() > 4
-                && seqName.indexOf(featureIdentifier.toLowerCase()) > -1)
+                && seqName.indexOf(featureIdentifier.toLowerCase(Locale.ROOT)) > -1)
         {
           /*
            * feature (transcript) matched - now check for allele match