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

Detect unreasonably large allele strings (>2^16) and throw an error 

-- samtools can emit alleles where the ref is 42M Ns and this caused the GATK (via tribble) to hang in several places.
-- Tribble was updated so we actually could read the line properly (rev. to 51 here).
-- Still the parsing algorithms in the GATK aren't happy with such a long allele.  Instead of optimizing the code around an improper use case I put in a limit of 2^16 bp for any allele, and throw a meaningful exception when encountered.
This commit is contained in:
Mark DePristo 2012-01-16 14:07:42 -05:00
parent 816dcf9616
commit f2b0575dee
3 changed files with 12 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
public/java/src/org/broadinstitute/sting/utils/codecs/vcf/AbstractVCFCodec.java
View File

@ -18,6 +18,7 @@ import java.util.zip.GZIPInputStream;
public abstract class AbstractVCFCodec implements FeatureCodec, NameAwareCodec {
public final static int MAX_EXPLICIT_ALLELE_SIZE = (int)Math.pow(2, 16);
protected final static Logger log = Logger.getLogger(VCFCodec.class);
protected final static int NUM_STANDARD_FIELDS = 8; // INFO is the 8th column
@ -252,7 +253,7 @@ public abstract class AbstractVCFCodec implements FeatureCodec, NameAwareCodec {
// if we have don't have a header, or we have a header with no genotyping data check that we have eight columns. Otherwise check that we have nine (normal colummns + genotyping data)
if (( (header == null || !header.hasGenotypingData()) && nParts != NUM_STANDARD_FIELDS) ||
(header != null && header.hasGenotypingData() && nParts != (NUM_STANDARD_FIELDS + 1)) )
(header != null && header.hasGenotypingData() && nParts != (NUM_STANDARD_FIELDS + 1)) )
throw new UserException.MalformedVCF("there aren't enough columns for line " + line + " (we expected " + (header == null ? NUM_STANDARD_FIELDS : NUM_STANDARD_FIELDS + 1) +
" tokens, and saw " + nParts + " )", lineNo);
@ -518,8 +519,11 @@ public abstract class AbstractVCFCodec implements FeatureCodec, NameAwareCodec {
* @param lineNo the line number for this record
*/
private static void checkAllele(String allele, boolean isRef, int lineNo) {
if ( allele == null || allele.length() == 0 )
generateException("Empty alleles are not permitted in VCF records", lineNo);
if ( allele == null || allele.length() == 0 )
generateException("Empty alleles are not permitted in VCF records", lineNo);
if ( allele.length() > MAX_EXPLICIT_ALLELE_SIZE )
generateException(String.format("Allele detected with length %d, exceeding max size %d. Please remove this from the VCF file before continuing", allele.length(), MAX_EXPLICIT_ALLELE_SIZE), lineNo);
if ( isSymbolicAllele(allele) ) {
if ( isRef ) {
@ -572,12 +576,13 @@ public abstract class AbstractVCFCodec implements FeatureCodec, NameAwareCodec {
public static int computeForwardClipping(List<Allele> unclippedAlleles, String ref) {
boolean clipping = true;
final byte ref0 = ref.getBytes()[0];
for ( Allele a : unclippedAlleles ) {
if ( a.isSymbolic() )
continue;
if ( a.length() < 1 || (a.getBases()[0] != ref.getBytes()[0]) ) {
if ( a.length() < 1 || (a.getBases()[0] != ref0) ) {
clipping = false;
break;
}
@ -589,6 +594,7 @@ public abstract class AbstractVCFCodec implements FeatureCodec, NameAwareCodec {
protected static int computeReverseClipping(List<Allele> unclippedAlleles, String ref, int forwardClipping, int lineNo) {
int clipping = 0;
boolean stillClipping = true;
final byte[] refBytes = ref.getBytes();
while ( stillClipping ) {
for ( Allele a : unclippedAlleles ) {
@ -604,7 +610,7 @@ public abstract class AbstractVCFCodec implements FeatureCodec, NameAwareCodec {
stillClipping = false;
else if ( ref.length() == clipping )
generateException("bad alleles encountered", lineNo);
else if ( a.getBases()[a.length()-clipping-1] != ref.getBytes()[ref.length()-clipping-1] )
else if ( a.getBases()[a.length()-clipping-1] != refBytes[ref.length()-clipping-1] )
stillClipping = false;
}
if ( stillClipping )

BIN
settings/repository/org.broad/tribble-46.jar → settings/repository/org.broad/tribble-51.jar
View File

Binary file not shown.

2
settings/repository/org.broad/tribble-46.xml → settings/repository/org.broad/tribble-51.xml
View File

@ -1,3 +1,3 @@
<ivy-module version="1.0">
<info organisation="org.broad" module="tribble" revision="46" status="integration" />
<info organisation="org.broad" module="tribble" revision="51" status="integration" />
</ivy-module>