-
Notifications
You must be signed in to change notification settings - Fork 97
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
storage: Define start-stop row scan for deleting files from archive t…
…able. #TASK-6756
- Loading branch information
Showing
5 changed files
with
119 additions
and
2 deletions.
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
42 changes: 42 additions & 0 deletions
42
.../java/org/opencb/opencga/storage/hadoop/variant/archive/ArchiveDeleteHBaseColumnTask.java
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 |
---|---|---|
@@ -0,0 +1,42 @@ | ||
package org.opencb.opencga.storage.hadoop.variant.archive; | ||
|
||
import org.apache.hadoop.conf.Configuration; | ||
import org.apache.hadoop.hbase.util.Bytes; | ||
import org.apache.hadoop.hbase.util.Pair; | ||
import org.opencb.commons.datastore.core.ObjectMap; | ||
import org.opencb.opencga.storage.hadoop.utils.DeleteHBaseColumnDriver; | ||
|
||
import java.util.ArrayList; | ||
import java.util.HashSet; | ||
import java.util.List; | ||
import java.util.Set; | ||
|
||
public class ArchiveDeleteHBaseColumnTask extends DeleteHBaseColumnDriver.DeleteHBaseColumnTask { | ||
|
||
public static final String FILE_BATCHES_WITH_FILES_TO_DELETE_FROM_ARCHIVE_INDEX = "fileBatchesWithFilesToDeleteFromArchiveIndex"; | ||
|
||
public static void configureTask(ObjectMap options, List<Integer> fileIds) { | ||
ArchiveRowKeyFactory keyFactory = new ArchiveRowKeyFactory(options); | ||
Set<Integer> fileBatchesSet = new HashSet<>(); | ||
for (Integer fileId : fileIds) { | ||
fileBatchesSet.add(keyFactory.getFileBatch(fileId)); | ||
} | ||
List<Integer> fileBatches = new ArrayList<>(fileBatchesSet); | ||
fileBatches.sort(Integer::compareTo); | ||
options.put(DeleteHBaseColumnDriver.DELETE_HBASE_COLUMN_TASK_CLASS, ArchiveDeleteHBaseColumnTask.class.getName()); | ||
options.put(ArchiveDeleteHBaseColumnTask.FILE_BATCHES_WITH_FILES_TO_DELETE_FROM_ARCHIVE_INDEX, fileBatches); | ||
} | ||
|
||
@Override | ||
public List<Pair<byte[], byte[]>> getRegionsToDelete(Configuration configuration) { | ||
int[] fileBatches = configuration.getInts(FILE_BATCHES_WITH_FILES_TO_DELETE_FROM_ARCHIVE_INDEX); | ||
List<Pair<byte[], byte[]>> regions = new ArrayList<>(); | ||
ArchiveRowKeyFactory archiveRowKeyFactory = new ArchiveRowKeyFactory(configuration); | ||
for (int fileBatch : fileBatches) { | ||
regions.add(new Pair<>( | ||
Bytes.toBytes(archiveRowKeyFactory.generateBlockIdFromBatch(fileBatch)), | ||
Bytes.toBytes(archiveRowKeyFactory.generateBlockIdFromBatch(fileBatch + 1)))); | ||
} | ||
return regions; | ||
} | ||
} |
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
59 changes: 59 additions & 0 deletions
59
...a/org/opencb/opencga/storage/hadoop/variant/archive/ArchiveDeleteHBaseColumnTaskTest.java
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 |
---|---|---|
@@ -0,0 +1,59 @@ | ||
package org.opencb.opencga.storage.hadoop.variant.archive; | ||
|
||
import org.apache.hadoop.conf.Configuration; | ||
import org.apache.hadoop.hbase.util.Bytes; | ||
import org.apache.hadoop.hbase.util.Pair; | ||
import org.junit.Assert; | ||
import org.junit.Test; | ||
import org.opencb.commons.datastore.core.ObjectMap; | ||
|
||
import java.util.Arrays; | ||
import java.util.List; | ||
|
||
import static org.junit.Assert.assertArrayEquals; | ||
import static org.junit.Assert.assertEquals; | ||
import static org.opencb.opencga.storage.hadoop.variant.archive.ArchiveDeleteHBaseColumnTask.*; | ||
|
||
public class ArchiveDeleteHBaseColumnTaskTest { | ||
|
||
private ArchiveDeleteHBaseColumnTask task; | ||
|
||
@Test | ||
public void testConfigureTask() { | ||
ObjectMap options = new ObjectMap(); | ||
task = new ArchiveDeleteHBaseColumnTask(); | ||
configureTask(options, Arrays.asList(1, 2, 3)); | ||
assertEquals(Arrays.asList(0), options.getAsIntegerList(FILE_BATCHES_WITH_FILES_TO_DELETE_FROM_ARCHIVE_INDEX)); | ||
List<Pair<byte[], byte[]>> regionsToDelete = task.getRegionsToDelete(toConf(options)); | ||
assertEquals(1, regionsToDelete.size()); | ||
|
||
assertArrayEquals(Bytes.toBytes("00000_"), regionsToDelete.get(0).getFirst()); | ||
assertArrayEquals(Bytes.toBytes("00001_"), regionsToDelete.get(0).getSecond()); | ||
} | ||
|
||
@Test | ||
public void testConfigureTaskMultiRegions() { | ||
ObjectMap options = new ObjectMap(); | ||
task = new ArchiveDeleteHBaseColumnTask(); | ||
configureTask(options, Arrays.asList(5300, 6053, 9032)); | ||
assertEquals(Arrays.asList(5, 6, 9), options.getAsIntegerList(FILE_BATCHES_WITH_FILES_TO_DELETE_FROM_ARCHIVE_INDEX)); | ||
List<Pair<byte[], byte[]>> regionsToDelete = task.getRegionsToDelete(toConf(options)); | ||
assertEquals(3, regionsToDelete.size()); | ||
|
||
assertArrayEquals(Bytes.toBytes("00005_"), regionsToDelete.get(0).getFirst()); | ||
assertArrayEquals(Bytes.toBytes("00006_"), regionsToDelete.get(0).getSecond()); | ||
assertArrayEquals(Bytes.toBytes("00006_"), regionsToDelete.get(1).getFirst()); | ||
assertArrayEquals(Bytes.toBytes("00007_"), regionsToDelete.get(1).getSecond()); | ||
assertArrayEquals(Bytes.toBytes("00009_"), regionsToDelete.get(2).getFirst()); | ||
assertArrayEquals(Bytes.toBytes("00010_"), regionsToDelete.get(2).getSecond()); | ||
} | ||
|
||
private static Configuration toConf(ObjectMap options) { | ||
Configuration conf = new Configuration(); | ||
for (String key : options.keySet()) { | ||
conf.set(key, options.getString(key)); | ||
} | ||
return conf; | ||
} | ||
|
||
} |