Skip to content

Fix for when Hadoop dataSource inputSpec is specified multiple times. #5790

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
nishantmonu51 merged 1 commit into from
May 22, 2018
Merged

Fix for when Hadoop dataSource inputSpec is specified multiple times. #5790

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 5 additions & 5 deletions indexing-hadoop/src/main/java/io/druid/indexer/HadoopIngestionSpec.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,7 @@
import org.joda.time.Interval;

import java.io.IOException;
import java.util.ArrayList;
import java.util.HashSet;
import java.util.List;
import java.util.Map;
Expand Down Expand Up @@ -150,20 +151,19 @@ public static HadoopIngestionSpec updateSegmentListIfDatasourcePathSpecIsUsed(
String ingestionSpec = "ingestionSpec";

Map<String, Object> pathSpec = spec.getIOConfig().getPathSpec();
Map<String, Object> datasourcePathSpec = null;
List<Map<String, Object>> datasourcePathSpecs = new ArrayList<>();
if (pathSpec.get(type).equals(dataSource)) {
datasourcePathSpec = pathSpec;
datasourcePathSpecs.add(pathSpec);
} else if (pathSpec.get(type).equals(multi)) {
List<Map<String, Object>> childPathSpecs = (List<Map<String, Object>>) pathSpec.get(children);
for (Map<String, Object> childPathSpec : childPathSpecs) {
if (childPathSpec.get(type).equals(dataSource)) {
datasourcePathSpec = childPathSpec;
break;
datasourcePathSpecs.add(childPathSpec);
}
}
}

if (datasourcePathSpec != null) {
for (Map<String, Object> datasourcePathSpec : datasourcePathSpecs) {
Map<String, Object> ingestionSpecMap = (Map<String, Object>) datasourcePathSpec.get(ingestionSpec);
DatasourceIngestionSpec ingestionSpecObj = jsonMapper.convertValue(
ingestionSpecMap,
Expand Down
61 changes: 56 additions & 5 deletions ...c/test/java/io/druid/indexer/HadoopIngestionSpecUpdateDatasourcePathSpecSegmentsTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,9 +51,12 @@
*/
public class HadoopIngestionSpecUpdateDatasourcePathSpecSegmentsTest
{
private final String testDatasource = "test";
private final Interval testDatasourceInterval = Intervals.of("1970/3000");
private final Interval testDatasourceIntervalPartial = Intervals.of("2050/3000");
private static final String testDatasource = "test";
private static final String testDatasource2 = "test2";
private static final Interval testDatasourceInterval = Intervals.of("1970/3000");
private static final Interval testDatasourceInterval2 = Intervals.of("2000/2001");
private static final Interval testDatasourceIntervalPartial = Intervals.of("2050/3000");

private final ObjectMapper jsonMapper;

public HadoopIngestionSpecUpdateDatasourcePathSpecSegmentsTest()
Expand All @@ -67,7 +70,7 @@ public HadoopIngestionSpecUpdateDatasourcePathSpecSegmentsTest()
}

private static final DataSegment SEGMENT = new DataSegment(
"test1",
testDatasource,
Intervals.of("2000/3000"),
"ver",
ImmutableMap.<String, Object>of(
Expand All @@ -81,6 +84,21 @@ public HadoopIngestionSpecUpdateDatasourcePathSpecSegmentsTest()
2
);

private static final DataSegment SEGMENT2 = new DataSegment(
testDatasource2,
Intervals.of("2000/3000"),
"ver2",
ImmutableMap.<String, Object>of(
"type", "local",
"path", "/tmp/index2.zip"
),
ImmutableList.of("host2"),
ImmutableList.of("visited_sum", "unique_hosts"),
NoneShardSpec.instance(),
9,
2
);

@Test
public void testUpdateSegmentListIfDatasourcePathSpecIsUsedWithNoDatasourcePathSpec() throws Exception
{
Expand Down Expand Up @@ -218,6 +236,23 @@ public void testUpdateSegmentListIfDatasourcePathSpecIsUsedWithMultiplePathSpec(
),
null,
false
),
new DatasourcePathSpec(
jsonMapper,
null,
new DatasourceIngestionSpec(
testDatasource2,
testDatasourceInterval2,
null,
null,
null,
null,
null,
false,
null
),
null,
false
)
)
);
Expand All @@ -229,6 +264,10 @@ public void testUpdateSegmentListIfDatasourcePathSpecIsUsedWithMultiplePathSpec(
ImmutableList.of(WindowedDataSegment.of(SEGMENT)),
((DatasourcePathSpec) ((MultiplePathSpec) config.getPathSpec()).getChildren().get(1)).getSegments()
);
Assert.assertEquals(
ImmutableList.of(new WindowedDataSegment(SEGMENT2, testDatasourceInterval2)),
((DatasourcePathSpec) ((MultiplePathSpec) config.getPathSpec()).getChildren().get(2)).getSegments()
);
}

private HadoopDruidIndexerConfig testRunUpdateSegmentListIfDatasourcePathSpecIsUsed(
Expand Down Expand Up @@ -264,9 +303,21 @@ private HadoopDruidIndexerConfig testRunUpdateSegmentListIfDatasourcePathSpecIsU
);

UsedSegmentLister segmentLister = EasyMock.createMock(UsedSegmentLister.class);

EasyMock.expect(
segmentLister.getUsedSegmentsForIntervals(testDatasource, Lists.newArrayList(jobInterval))
segmentLister.getUsedSegmentsForIntervals(
testDatasource,
Lists.newArrayList(jobInterval != null ? jobInterval.overlap(testDatasourceInterval) : null)
)
).andReturn(ImmutableList.of(SEGMENT));

EasyMock.expect(
segmentLister.getUsedSegmentsForIntervals(
testDatasource2,
Lists.newArrayList(jobInterval != null ? jobInterval.overlap(testDatasourceInterval2) : null)
)
).andReturn(ImmutableList.of(SEGMENT2));

EasyMock.replay(segmentLister);

spec = HadoopIngestionSpec.updateSegmentListIfDatasourcePathSpecIsUsed(spec, jsonMapper, segmentLister);
Expand Down