Allow for hdfs and gcs URI's to be passed to GenomicsDB #5017
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,5 +1,6 @@ | ||
| package org.broadinstitute.hellbender.engine; | ||
|
|
||
| import com.intel.genomicsdb.GenomicsDBUtils; | ||
| import com.intel.genomicsdb.model.GenomicsDBExportConfiguration; | ||
| import com.intel.genomicsdb.reader.GenomicsDBFeatureReader; | ||
| import htsjdk.samtools.SAMSequenceDictionary; | ||
|
|
@@ -27,7 +28,6 @@ | |
| import java.nio.channels.SeekableByteChannel; | ||
| import java.nio.file.Files; | ||
| import java.nio.file.Path; | ||
| import java.util.Iterator; | ||
| import java.util.List; | ||
| import java.util.Optional; | ||
|
|
@@ -62,11 +62,6 @@ | |
| public final class FeatureDataSource<T extends Feature> implements GATKDataSource<T>, AutoCloseable { | ||
| private static final Logger logger = LogManager.getLogger(FeatureDataSource.class); | ||
|
|
||
| /** | ||
| * Feature reader used to retrieve records from our file | ||
| */ | ||
|
|
@@ -260,7 +255,7 @@ public FeatureDataSource(final FeatureInput<T> featureInput, final int queryLook | |
| // a query by interval is attempted. | ||
| this.featureReader = getFeatureReader(featureInput, targetFeatureType, cloudWrapper, cloudIndexWrapper, reference); | ||
|
|
||
| if (IOUtils.isGenomicsDBPath(featureInput.getFeaturePath())) { | ||
| //genomics db uri's have no associated index file to read from, but they do support random access | ||
| this.hasIndex = false; | ||
| this.supportsRandomAccess = true; | ||
|
|
@@ -282,20 +277,13 @@ public FeatureDataSource(final FeatureInput<T> featureInput, final int queryLook | |
| this.queryLookaheadBases = queryLookaheadBases; | ||
| } | ||
|
|
||
|
|
||
| @SuppressWarnings("unchecked") | ||
| private static <T extends Feature> FeatureReader<T> getFeatureReader(final FeatureInput<T> featureInput, final Class<? extends Feature> targetFeatureType, | ||
| final Function<SeekableByteChannel, SeekableByteChannel> cloudWrapper, | ||
| final Function<SeekableByteChannel, SeekableByteChannel> cloudIndexWrapper, | ||
| final Path reference) { | ||
| if (IOUtils.isGenomicsDBPath(featureInput.getFeaturePath())) { | ||
| try { | ||
| if (reference == null) { | ||
| throw new UserException.MissingReference("You must provide a reference if you want to load from GenomicsDB"); | ||
|
|
@@ -364,57 +352,50 @@ private static <T extends Feature> FeatureReader<T> getFeatureReader(final Featu | |
| } | ||
| } | ||
|
|
||
| private static void verifyPathsAreReadable(final String ... paths) { | ||
| for (String path : paths) { | ||
| IOUtils.assertFileIsReadable(IOUtils.getPath(path)); | ||
| } | ||
| } | ||
|
|
||
|
|
||
| private static FeatureReader<VariantContext> getGenomicsDBFeatureReader(final String path, final File reference) { | ||
| final String workspace = IOUtils.getGenomicsDBAbsolutePath(path); | ||
| if (workspace == null) { | ||
| throw new IllegalArgumentException("Trying to create a GenomicsDBReader from non-GenomicsDB input path " + path); | ||
| } else if (Files.notExists(IOUtils.getPath(workspace))) { | ||
| throw new UserException("GenomicsDB workspace " + path + " does not exist"); | ||
| } | ||
|
|
||
|
There was a problem hiding this comment. Instead of This way, the URIs will at least be legal... There was a problem hiding this comment. For the URI schemes, would you consider gendb://, gendb.gs:// gendb.hdfs://, etc.? There was a problem hiding this comment. If a period in the scheme is legal, then these would be fine. I'd check to make sure that Java's URI, URL, and There was a problem hiding this comment. Yes, URI and Path recognize period in their schemes. |
||
| final String callsetJson = IOUtils.appendPathToDir(workspace, GenomicsDBConstants.DEFAULT_CALLSETMAP_FILE_NAME); | ||
| final String vidmapJson = IOUtils.appendPathToDir(workspace, GenomicsDBConstants.DEFAULT_VIDMAP_FILE_NAME); | ||
| final String vcfHeader = IOUtils.appendPathToDir(workspace, GenomicsDBConstants.DEFAULT_VCFHEADER_FILE_NAME); | ||
|
There was a problem hiding this comment. Are the |
||
|
|
||
| verifyPathsAreReadable(callsetJson, vidmapJson, vcfHeader); | ||
|
|
||
| try { | ||
| final GenomicsDBExportConfiguration.ExportConfiguration exportConfigurationBuilder = | ||
| createExportConfiguration(reference, workspace, callsetJson, vidmapJson, vcfHeader); | ||
| return new GenomicsDBFeatureReader<>(exportConfigurationBuilder, new BCF2Codec(), Optional.empty()); | ||
| } catch (final IOException e) { | ||
| throw new UserException("Couldn't create GenomicsDBFeatureReader", e); | ||
| } | ||
| } | ||
|
|
||
| private static GenomicsDBExportConfiguration.ExportConfiguration createExportConfiguration(final File reference, final String workspace, | ||
| final String callsetJson, final String vidmapJson, | ||
| final String vcfHeader) { | ||
| GenomicsDBExportConfiguration.ExportConfiguration.Builder exportConfigurationBuilder = | ||
| GenomicsDBExportConfiguration.ExportConfiguration.newBuilder() | ||
| .setWorkspace(workspace) | ||
| .setReferenceGenome(reference.getAbsolutePath()) | ||
| .setVidMappingFile(vidmapJson) | ||
|
There was a problem hiding this comment. Are these guaranteed to be absolute at this point? (the previous code enforced this) There was a problem hiding this comment. I have made sure that all these paths are absolute in the changed code where we are allowing for gendb://, gendb.hdfs:// and gendb.gs:// schemes. |
||
| .setCallsetMappingFile(callsetJson) | ||
| .setVcfHeaderFilename(vcfHeader) | ||
| .setProduceGTField(false) | ||
| .setProduceGTWithMinPLValueForSpanningDeletions(false) | ||
| .setSitesOnlyQuery(false) | ||
| .setMaxDiploidAltAllelesThatCanBeGenotyped(GenotypeLikelihoods.MAX_DIPLOID_ALT_ALLELES_THAT_CAN_BE_GENOTYPED); | ||
|
|
||
| // For the multi-interval support, we create multiple arrays (directories) in a single workspace - | ||
| // one per interval. So, if you wish to import intervals ("chr1", [ 1, 100M ]) and ("chr2", [ 1, 100M ]), | ||
|
|
@@ -429,7 +410,7 @@ private static GenomicsDBExportConfiguration.ExportConfiguration createExportCon | |
| // will be backward compatible with respect to reads. Hence, if a directory named genomicsdb_array is found, | ||
| // the array name is passed to the GenomicsDBFeatureReader otherwise the array names are generated from the | ||
| // directory entries. | ||
| if (GenomicsDBUtils.isGenomicsDBArray(workspace.toString(), GenomicsDBConstants.DEFAULT_ARRAY_NAME)) { | ||
| exportConfigurationBuilder.setArrayName(GenomicsDBConstants.DEFAULT_ARRAY_NAME); | ||
| } else { | ||
| exportConfigurationBuilder.setGenerateArrayNameFromPartitionBounds(true); | ||
|
|
||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Move this method to
IOUtilsas well.