clean-up and fixes to the VCF input

git-svn-id: file:///humgen/gsa-scr1/gsa-engineering/svn_contents/trunk@1849 348d0f76-0448-11de-a6fe-93d51630548a

java/src/org/broadinstitute/sting/utils/genotype/vcf/VCFGenotypeRecord.java

@@ -15,6 +15,9 @@ import java.util.Map;
  *         so they were broken off into their own class
  */
 public class VCFGenotypeRecord {
+    // the symbol for a empty genotype
+    public static final String EMPTY_GENOTYPE = ".";
+
     // what kind of phasing this genotype has
     public enum PHASE {
         UNPHASED, PHASED, PHASED_SWITCH_PROB, UNKNOWN

java/src/org/broadinstitute/sting/utils/genotype/vcf/VCFGenotypeWriterAdapter.java

@@ -54,6 +54,7 @@ public class VCFGenotypeWriterAdapter implements GenotypeWriter {
         // setup the header fields
         hInfo.put("format", "VCRv3.2");
         hInfo.put("source", mSource);
+        hInfo.put("reference", mReferenceName);
 
         // setup the sample names
         mHeader = new VCFHeader(hInfo, sampleNames);

java/src/org/broadinstitute/sting/utils/genotype/vcf/VCFParameters.java

@@ -74,7 +74,7 @@ class VCFParameters {
     }
 
     public String getFormatString() {
-        return Utils.join(";", formatList);
+        return Utils.join(VCFRecord.FORMAT_FIELD_SEPERATOR, formatList);
     }
 
     public List<VCFGenotypeRecord> getGenotypesRecords() {

java/src/org/broadinstitute/sting/utils/genotype/vcf/VCFReader.java

@@ -192,7 +192,8 @@ public class VCFReader implements Iterator<VCFRecord>, Iterable<VCFRecord> {
             List<VCFGenotypeRecord> genotypeRecords = new ArrayList<VCFGenotypeRecord>();
             index++;
             for (String str : mHeader.getGenotypeSamples()) {
-                genotypeRecords.add(getVCFGenotype(str, mFormatString, tokens[index], values.get(VCFHeader.HEADER_FIELDS.ALT).split(","), values.get(VCFHeader.HEADER_FIELDS.REF).charAt(0)));
+                if (!tokens[index].equalsIgnoreCase(VCFGenotypeRecord.EMPTY_GENOTYPE))
+                    genotypeRecords.add(getVCFGenotype(str, mFormatString, tokens[index], values.get(VCFHeader.HEADER_FIELDS.ALT).split(","), values.get(VCFHeader.HEADER_FIELDS.REF).charAt(0)));
                 index++;
             }
             return new VCFRecord(values, mFormatString, genotypeRecords);
@@ -217,6 +218,7 @@ public class VCFReader implements Iterator<VCFRecord>, Iterable<VCFRecord> {
         VCFGenotypeRecord.PHASE phase = VCFGenotypeRecord.PHASE.UNKNOWN;
         List<String> bases = new ArrayList<String>();
         String keyStrings[] = formatString.split(":");
+
         for (String key : keyStrings) {
             String parse;
             int nextDivider;

java/src/org/broadinstitute/sting/utils/genotype/vcf/VCFRecord.java

@@ -7,7 +7,14 @@ import java.util.*;
 
 /** the basic VCF record type */
 public class VCFRecord {
+    // commonly used strings that are in the standard
+    public static final String FORMAT_FIELD_SEPERATOR = ":";
+    public static final String GENOTYPE_FIELD_SEPERATOR = ":";
     public static final String FIELD_SEPERATOR = "\t";
+    public static final String FILTER_CODE_SEPERATOR = ";";
+    public static final String INFO_FIELD_SEPERATOR = ";";
+    public static final String EMPTY_INFO_FIELD = ".";
+    public static final String DOUBLE_PRECISION_FORMAT_STRING = "%.2f";
     // the reference base
     private char mReferenceBase;
     // our contig
@@ -146,10 +153,7 @@ public class VCFRecord {
      */
 
     public boolean hasGenotypeData() {
-        if (mGenotypeFields.size() < 1) {
+        return (mGenotypeFields.size() > 0);
-            return false;
-        }
-        return true;
     }
 
     /** @return the string for the chromosome that this VCF record is associated with */
@@ -321,14 +325,14 @@ public class VCFRecord {
         String alts = "";
         for (String str : this.getAlternateAlleles()) alts += str + ",";
         builder.append((alts.length() > 0) ? alts.substring(0, alts.length() - 1) + FIELD_SEPERATOR : "." + FIELD_SEPERATOR);
-        builder.append(String.format("%.2f",getQual()) + FIELD_SEPERATOR);
+        builder.append(String.format(DOUBLE_PRECISION_FORMAT_STRING,getQual()) + FIELD_SEPERATOR);
-        builder.append(Utils.join(";", getFilteringCodes()) + FIELD_SEPERATOR);
+        builder.append(Utils.join(FILTER_CODE_SEPERATOR, getFilteringCodes()) + FIELD_SEPERATOR);
         String info = "";
         for (String str : this.getInfoValues().keySet()) {
-            if (str.equals("."))
+            if (str.equals(EMPTY_INFO_FIELD))
-                info = ".";
+                info = EMPTY_INFO_FIELD;
             else
-                info += str + "=" + getInfoValues().get(str) + ";";
+                info += str + "=" + getInfoValues().get(str) + INFO_FIELD_SEPERATOR;
         }
 
         if (info.length() > 1) builder.append(info.substring(0, info.length() - 1));
@@ -363,12 +367,12 @@ public class VCFRecord {
                     builder.append(rec.toGenotypeString(this.mAlts));
                 for (String s : rec.getFields().keySet()) {
                     if (rec.getFields().get(s).equals("")) continue;
-                    builder.append(":");
+                    builder.append(GENOTYPE_FIELD_SEPERATOR);
                     builder.append(rec.getFields().get(s));
                 }
                 gMap.remove(genotype);
             } else {
-                builder.append(".");
+                builder.append(VCFGenotypeRecord.EMPTY_GENOTYPE);
             }
         }
         if (gMap.size() != 0) {