Merge pull request #1295 from broadinstitute/rhl_sv_error_output_1194

Correct error messages and error handling in multiple tools

protected/gatk-tools-protected/src/main/java/org/broadinstitute/gatk/tools/walkers/cancer/contamination/ContEst.java

@@ -264,14 +264,14 @@ public class ContEst extends RodWalker<Map<String, Map<String, ContaminationStat
             useSequencingGenotypes = true;
             // if were not using arrays, we need to figure out what samples are what
             for(SAMReaderID id : getToolkit().getReadsDataSource().getReaderIDs()) {
-                if (id.getTags().getPositionalTags().size() == 0)
+                if (id.getTags().getPositionalTags().isEmpty())
                     throw new UserException.BadInput("BAMs must be tagged with " + GENOTYPE_BAM_TAG + " and " + EVAL_BAM_TAG + " when running in array-free mode. Please see the ContEst documentation for more details");
 
                 // now sort out what tags go with what bam
                 for (String tag : id.getTags().getPositionalTags()) {
                     if (GENOTYPE_BAM_TAG.equalsIgnoreCase(tag)) {
                         try {
-                            if (getToolkit().getReadsDataSource().getHeader(id).getReadGroups().size() == 0)
+                            if (getToolkit().getReadsDataSource().getHeader(id).getReadGroups().isEmpty())
                                 throw new RuntimeException("No Read Groups found for Genotyping BAM -- Read Groups are Required in sequencing genotype mode!");
                             genotypeSample = getToolkit().getReadsDataSource().getHeader(id).getReadGroups().get(0).getSample();
                         } catch (NullPointerException npe) {
@@ -279,7 +279,7 @@ public class ContEst extends RodWalker<Map<String, Map<String, ContaminationStat
                         }
                     } else if (EVAL_BAM_TAG.equalsIgnoreCase(tag)) {
                         try {
-                            if (getToolkit().getReadsDataSource().getHeader(id).getReadGroups().size() == 0)
+                            if (getToolkit().getReadsDataSource().getHeader(id).getReadGroups().isEmpty())
                                 throw new RuntimeException("No Read Groups found for Genotyping BAM -- Read Groups are Required in sequencing genotype mode!");
                             evalSample = getToolkit().getReadsDataSource().getHeader(id).getReadGroups().get(0).getSample();
                         } catch (NullPointerException npe) {
@@ -410,7 +410,7 @@ public class ContEst extends RodWalker<Map<String, Map<String, ContaminationStat
                                 namePair.getKey(),
                                 populationsToEvaluate);
 
-                if (results.size() > 0) {
+                if (!results.isEmpty()) {
                     countResults++;
                     stats.put(namePair.getKey(), results);
                 }
@@ -498,7 +498,7 @@ public class ContEst extends RodWalker<Map<String, Map<String, ContaminationStat
     private static Genotype getGenotypeFromArray(RefMetaDataTracker tracker, RodBinding<VariantContext> genotypes, boolean verifiedSampleName, boolean verifySample, String sampleName) {
         // get the truthForSample and the hapmap information for this site; if either are null we can't move forward
         Collection<VariantContext> truths = tracker.getValues(genotypes);
-        if (truths == null || truths.size() == 0) return null;
+        if (truths == null || truths.isEmpty()) return null;
 
         VariantContext truthForSample = truths.iterator().next();
 
@@ -506,7 +506,7 @@ public class ContEst extends RodWalker<Map<String, Map<String, ContaminationStat
         if (!verifiedSampleName && verifySample) {
             if (!truthForSample.getSampleNames().contains(sampleName))
                 throw new UserException.BadInput("The sample name was set to " + sampleName + " but this sample isn't in your genotypes file.  Please Verify your sample name");
-                verifiedSampleName = true;
+            verifiedSampleName = true;
         }
 
         GenotypesContext gt = truthForSample.getGenotypes();
@@ -622,6 +622,9 @@ public class ContEst extends RodWalker<Map<String, Map<String, ContaminationStat
 
         for (String pop : pops) {
             PopulationFrequencyInfo info = parsePopulationFrequencyInfo(popVC, pop);
+            if ( info == null )
+                throw new RuntimeException("No population frequency annotation for " + pop + " in " + popVC.toString());
+
             double alleleFreq = info.getMinorAlleleFrequency();
             if (alleleFreq > 0.5) {
                 throw new RuntimeException("Minor allele frequency is greater than 0.5, this is an error; we saw AF of " + alleleFreq);
@@ -708,7 +711,7 @@ public class ContEst extends RodWalker<Map<String, Map<String, ContaminationStat
             }
 
 
-            if (newMap.size() > 0)
+            if (!newMap.isEmpty())
                 cleanedMap.put(entry.getKey(), newMap);
             else
                 out.println("Warning: We're throwing out lane " + entry.getKey() + " since it has fewer than " + minBaseCount +

protected/gatk-tools-protected/src/test/java/org/broadinstitute/gatk/tools/walkers/cancer/contamination/ContEstIntegrationTest.java

@@ -52,6 +52,7 @@
 package org.broadinstitute.gatk.tools.walkers.cancer.contamination;
 
 import org.broadinstitute.gatk.engine.walkers.WalkerTest;
+import org.broadinstitute.gatk.utils.exceptions.UserException;
 import org.testng.annotations.Test;
 
 import java.util.Arrays;
@@ -100,4 +101,17 @@ public class ContEstIntegrationTest extends WalkerTest {
                         " -isr INTERSECTION",md5sums);
         executeTest("testArrayFree",spec);
     }
+
+    @Test(enabled = true)
+    public void testArrayNoPop(){
+        WalkerTest.WalkerTestSpec spec = new WalkerTest.WalkerTestSpec(
+                "-T ContEst" +
+                        " -I:eval " + ContaminatedBamsDirectory + "HCC1143_BL.small.0.05.contaminated.with.SM-612V3.small.0.95.bam" +
+                        " -I:genotype " + NormalBamsDirectory + "SM-612V4.bam" +
+                        " -R " + b37KGReference +
+                        " --popfile " + validationDataLocation + "hg19_population_stratified_af_hapmap_3.3.fixed_no_pop.vcf",
+                        0,
+                UserException.class);
+        executeTest("testArrayNoPop",spec);
+    }
 }

public/gatk-tools-public/src/main/java/org/broadinstitute/gatk/tools/walkers/rnaseq/ASEReadCounter.java

@@ -202,7 +202,7 @@ public class ASEReadCounter extends LocusWalker<String, Integer> {
         final List<VariantContext> VCs =  tracker.getValues(sites, context.getLocation());
         if(VCs != null && VCs.size() > 1)
             throw new UserException("More then one variant context at position: "+contig+":"+position);
-        if(VCs == null || VCs.size() == 0)
+        if(VCs == null || VCs.isEmpty())
             return null;
 
         final VariantContext vc = VCs.get(0);
@@ -211,7 +211,11 @@ public class ASEReadCounter extends LocusWalker<String, Integer> {
             return null;
         }
 
+        if ( vc.getNAlleles() == 1 || vc.getAlternateAllele(0).getBases().length == 0 )
+            throw new UserException("The file of variant sites must contain heterozygous sites and cannot be a GVCF file containing <NON_REF> alleles.");
+
         final char altAllele = (char)vc.getAlternateAllele(0).getBases()[0];
+
         final String siteID = vc.getID();
         final ReadBackedPileup pileup = filterPileup(context.getBasePileup(), countType, includeReadsWithDeletionAtLoci());
 

public/gatk-tools-public/src/main/java/org/broadinstitute/gatk/tools/walkers/variantutils/SelectVariants.java

@@ -664,7 +664,7 @@ public class SelectVariants extends RodWalker<Integer, Integer> implements TreeR
                             "Samples entered on command line (through -sf or -sn) that are not present in the VCF.",
                             "A list of these samples:",
                             Utils.join(",", commandLineUniqueSamples),
-                            "To ignore these samples, run with --allowNonOverlappingCommandLineSamples"));
+                            "To ignore these samples, run with --ALLOW_NONOVERLAPPING_COMMAND_LINE_SAMPLES"));
                 }
             }
 

public/gatk-tools-public/src/test/java/org/broadinstitute/gatk/tools/walkers/rnaseq/ASEReadCounterIntegrationTest.java

@@ -26,6 +26,7 @@
 package org.broadinstitute.gatk.tools.walkers.rnaseq;
 
 import org.broadinstitute.gatk.engine.walkers.WalkerTest;
+import org.broadinstitute.gatk.utils.exceptions.UserException;
 import org.testng.annotations.Test;
 
 import java.util.Arrays;
@@ -100,6 +101,14 @@ public class ASEReadCounterIntegrationTest extends WalkerTest {
         executeTest("test high mq with no read passing", spec);
     }
 
+    @Test
+    public void testASEReadCounterNonRef() {
+        WalkerTest.WalkerTestSpec spec = new WalkerTest.WalkerTestSpec(
+                "-T ASEReadCounter -R " + b37KGReference + " -I " + privateTestDir + "NA12878.RNAseq.bam -sites "+privateTestDir +"NA12878.chr20_2444518_2637800.RNAseq.NonRef.vcf -U ALLOW_N_CIGAR_READS", 0,
+                UserException.class);
+        executeTest("test <NON_REF> sites VCF file", spec);
+    }
+
 
 
 

public/gatk-utils/src/main/java/org/broadinstitute/gatk/utils/exceptions/UserException.java

@@ -373,7 +373,7 @@ public class UserException extends ReviewedGATKException {
 
     public static class LexicographicallySortedSequenceDictionary extends UserException {
         public LexicographicallySortedSequenceDictionary(String name, SAMSequenceDictionary dict) {
-            super(String.format("Lexicographically sorted human genome sequence detected in %s. Please see " + HelpConstants.forumPost("discussion/58/companion-utilities-reordersam") + "for more information. Error details: %s contigs = %s",
+            super(String.format("Lexicographically sorted human genome sequence detected in %s. Please see " + HelpConstants.articlePost("1328") + "for more information. Error details: %s contigs = %s",
                     name, name, ReadUtils.prettyPrintSequenceRecords(dict)));
         }
     }

public/gatk-utils/src/main/java/org/broadinstitute/gatk/utils/help/HelpConstants.java

@@ -29,6 +29,7 @@ public class HelpConstants {
 
     public final static String BASE_GATK_URL = "http://www.broadinstitute.org/gatk";
     public final static String GATK_DOCS_URL = BASE_GATK_URL + "/guide/tooldocs/";
+    public final static String GATK_ARTICLE_URL = BASE_GATK_URL + "/guide/article";
     public final static String GATK_FORUM_URL = "http://gatkforums.broadinstitute.org/";
     public final static String GATK_FORUM_API_URL = "https://gatkforums.broadinstitute.org/api/v1/";
 
@@ -61,6 +62,10 @@ public class HelpConstants {
     	return GATK_FORUM_URL + post;
     }
 
+    public static String articlePost(String id) {
+        return GATK_ARTICLE_URL + "?id=" + id;
+    }
+
     /**
      * Go-to developer name codes for tracking and display purposes. Only current team members should be in this list.
      * When someone leaves, their charges should be redistributed. The actual string should be closest to the dev's

public/gatk-utils/src/main/java/org/broadinstitute/gatk/utils/pairhmm/PairHMM.java

@@ -372,7 +372,7 @@ public abstract class PairHMM {
     {
         doProfiling = (numThreads == 1);
         if(numThreads > 1)
-            logger.info("Performance profiling for PairHMM is disabled because HaplotypeCaller is being run with multiple threads (-nct>1) option\nProfiling is enabled only when running in single thread mode\n");
+            logger.info("Performance profiling for PairHMM is disabled because the program is being run with multiple threads (-nct>1) option\nProfiling is enabled only when running in single thread mode\n");
     }
 
     /**