zzh
/
gatk-3.8
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Updated VCF Reader to parse VCFs according to the VCFv3.3 spec. Column headers are tab separated since sample names might have spaces. 

Updated test files in /humgen/gsa-scr1/GATK_Data/Validation_Data/*.vcf to remove spaces except for when they are supposed to be in the sample name.
Added @Test before VCFReaderTest.testHeaderNoRecords()

git-svn-id: file:///humgen/gsa-scr1/gsa-engineering/svn_contents/trunk@2809 348d0f76-0448-11de-a6fe-93d51630548a
This commit is contained in:
kshakir 2010-02-08 22:55:59 +00:00
parent 935e76daa1
commit fc810a1800
2 changed files with 47 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
java/src/org/broadinstitute/sting/utils/genotype/vcf/VCFReader.java
View File

@ -1,14 +1,27 @@
package org.broadinstitute.sting.utils.genotype.vcf;
import org.broadinstitute.sting.utils.Utils;
import java.io.*;
import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.nio.charset.Charset;
import java.util.*;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.Iterator;
import java.util.LinkedHashSet;
import java.util.List;
import java.util.Map;
import java.util.Set;
import java.util.TreeSet;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import java.util.zip.GZIPInputStream;
import org.broadinstitute.sting.utils.Utils;
/** The VCFReader class, which given a valid vcf file, parses out the header and VCF records */
public class VCFReader implements Iterator<VCFRecord>, Iterable<VCFRecord> {
@ -151,7 +164,7 @@ public class VCFReader implements Iterator<VCFRecord>, Iterable<VCFRecord> {
// iterate over all the passed in strings
for ( String str : headerStrings ) {
if ( !str.startsWith("##") ) {
String[] strings = str.substring(1).split("\\s+");
String[] strings = str.substring(1).split("\t");
// the columns should be in order according to Richard Durbin
int arrayIndex = 0;
for (VCFHeader.HEADER_FIELDS field : VCFHeader.HEADER_FIELDS.values()) {
@ -197,7 +210,7 @@ public class VCFReader implements Iterator<VCFRecord>, Iterable<VCFRecord> {
try {
// things we need to make a VCF record
Map<VCFHeader.HEADER_FIELDS, String> values = new HashMap<VCFHeader.HEADER_FIELDS, String>();
String tokens[] = line.split("\\s+");
String tokens[] = line.split("\t");
// check to ensure that the column count of tokens is right
if (tokens.length != mHeader.getColumnCount()) {

39
java/test/org/broadinstitute/sting/utils/genotype/vcf/VCFReaderTest.java
View File

@ -1,16 +1,24 @@
package org.broadinstitute.sting.utils.genotype.vcf;
import org.broadinstitute.sting.BaseTest;
import org.broadinstitute.sting.utils.fasta.IndexedFastaSequenceFile;
import org.broadinstitute.sting.utils.StingException;
import org.broadinstitute.sting.utils.GenomeLocParser;
import org.broadinstitute.sting.gatk.refdata.RodVCF;
import org.junit.Assert;
import org.junit.Test;
import org.junit.BeforeClass;
import java.io.BufferedReader;
import java.io.File;
import java.io.FileNotFoundException;
import java.io.FileReader;
import java.io.IOException;
import java.util.ArrayList;
import java.util.Iterator;
import java.util.List;
import java.util.Map;
import java.util.Set;
import java.io.*;
import java.util.*;
import org.broadinstitute.sting.BaseTest;
import org.broadinstitute.sting.gatk.refdata.RodVCF;
import org.broadinstitute.sting.utils.GenomeLocParser;
import org.broadinstitute.sting.utils.StingException;
import org.broadinstitute.sting.utils.fasta.IndexedFastaSequenceFile;
import org.junit.Assert;
import org.junit.BeforeClass;
import org.junit.Test;
/** test the VCFReader class test */
public class VCFReaderTest extends BaseTest {
@ -20,6 +28,7 @@ public class VCFReaderTest extends BaseTest {
private static final String VCF_MIXUP_FILE = validationDataLocation + "mixedup.v2.vcf";
private static final File complexFile = new File(validationDataLocation + "complexExample.vcf");
private static final File headerNoRecordsFile = new File(validationDataLocation + "headerNoRecords.vcf");
private static final File headerSampleSpaceFile = new File(validationDataLocation + "headerSampleSpaceFile.vcf");
@BeforeClass
@ -164,7 +173,7 @@ public class VCFReaderTest extends BaseTest {
BufferedReader breader = new BufferedReader(reader);
String line;
while ((line = breader.readLine()) != null) {
String[] pieces = line.split("\\s+");
String[] pieces = line.split("\t");
if (line.contains("##")) {
continue;
@ -340,10 +349,18 @@ public class VCFReaderTest extends BaseTest {
if (reader.hasNext()) Assert.fail("The reader should NOT have a record");
}
@Test
public void testHeaderNoRecords() {
VCFReader reader = new VCFReader(headerNoRecordsFile);
Assert.assertTrue(reader.getHeader().getMetaData() != null);
Assert.assertTrue(!reader.iterator().hasNext());
}
@Test
public void testHeaderSampleSpaceFile() {
VCFReader reader = new VCFReader(headerSampleSpaceFile);
Assert.assertTrue(reader.getHeader().hasGenotypingData());
Assert.assertTrue(reader.getHeader().getGenotypeSamples().size() == 1);
Assert.assertTrue(reader.getHeader().getGenotypeSamples().contains("SAMPLE NAME"));
}
}