Skip to content

hll sketch to accept array as input #8619

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

Closed
gipeshka wants to merge 7 commits into from
Closed

hll sketch to accept array as input #8619

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
f928643
8613 hll sketch to accept array as input
gipeshka Oct 2, 2019
48a7dc8
adjust test
gipeshka Oct 2, 2019
8bdc388
adjust cs
gipeshka Oct 2, 2019
5a04e54
fix wrong configuration name
gipeshka Oct 2, 2019
3935574
try to use long 0
gipeshka Oct 2, 2019
a86004f
try it without shadowing
gipeshka Oct 7, 2019
1834ed2
lets use 15
gipeshka Oct 7, 2019
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
6 changes: 6 additions & 0 deletions ...in/java/org/apache/druid/query/aggregation/datasketches/hll/HllSketchBuildAggregator.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -107,6 +107,12 @@ static void updateSketch(final HllSketch sketch, final Object value)
for (String v : list) {
sketch.update(v.toCharArray());
}
} else if (value instanceof String[]) {
// noinspection unchecked
String[] list = (String[]) value;
for (String v : list) {
sketch.update(v.toCharArray());
}
} else if (value instanceof char[]) {
sketch.update((char[]) value);
} else if (value instanceof byte[]) {
Expand Down
74 changes: 74 additions & 0 deletions ...est/java/org/apache/druid/query/aggregation/datasketches/hll/HllSketchAggregatorTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,13 +21,16 @@

import com.fasterxml.jackson.core.JsonProcessingException;
import com.fasterxml.jackson.databind.ObjectMapper;
import com.google.common.collect.ImmutableList;
import com.google.common.collect.ImmutableMap;
import org.apache.druid.java.util.common.granularity.Granularities;
import org.apache.druid.java.util.common.guava.Sequence;
import org.apache.druid.math.expr.ExprMacroTable;
import org.apache.druid.query.aggregation.AggregationTestHelper;
import org.apache.druid.query.groupby.GroupByQueryConfig;
import org.apache.druid.query.groupby.GroupByQueryRunnerTest;
import org.apache.druid.query.groupby.ResultRow;
import org.apache.druid.segment.transform.ExpressionTransform;
import org.junit.Assert;
import org.junit.Rule;
import org.junit.Test;
Expand All @@ -42,6 +45,7 @@
import java.util.Collections;
import java.util.List;
import java.util.Map;
import java.util.stream.Collectors;

@RunWith(Parameterized.class)
public class HllSketchAggregatorTest
Expand Down Expand Up @@ -112,6 +116,34 @@ public void buildSketchesAtIngestionTime() throws Exception
Assert.assertEquals(200, (double) row.get(0), 0.1);
}

@Test
public void buildSketchesAtIngestionTimeMultiValueWithTransformations() throws Exception
{
Sequence<ResultRow> seq = helper.createIndexAndRunQueryOnSegment(
new File(this.getClass().getClassLoader().getResource("hll/hll_raw.tsv").getFile()),
buildParserJson(
Collections.singletonList("dim"),
Arrays.asList("timestamp", "dim", "multiDim", "id"),
ImmutableList.of(
new ExpressionTransform(
"multiDimAppended",
"array_append(multiDim, '15')",
ExprMacroTable.nil()
Copy link
Copy Markdown
Author

@gipeshka gipeshka Oct 21, 2019

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@clintropolis yes, I guess you're right.

However I am still not able to make this test pass. Is there a simple way to run these tests?

Or maybe the issue is evident right away? I haven't found any test with transformations, I suppose this test implementation is flawed.

)
)
),
buildAggregatorJson("HLLSketchBuild", "multiDimAppended", !ROUND),
0, // minTimestamp
Granularities.NONE,
200, // maxRowCount
buildGroupByQueryJson("HLLSketchMerge", "sketch", !ROUND)
);
List<ResultRow> results = seq.toList();
Assert.assertEquals(1, results.size());
ResultRow row = results.get(0);
Assert.assertEquals(15, (double) row.get(0), 0.1);
}

@Test
public void buildSketchesAtQueryTime() throws Exception
{
Expand Down Expand Up @@ -221,6 +253,48 @@ private static String buildParserJson(List<String> dimensions, List<String> colu
return toJson(object);
}

private static String buildParserJson(
List<String> dimensions,
List<String> columns,
List<ExpressionTransform> transforms
)
{
List<Map<String, String>> transformsObjects = transforms.stream().map(transform ->
ImmutableMap.of(
"type", "expression",
"name", transform.getName(),
"expression", transform.getExpression()
)
).collect(Collectors.toList());

Map<String, Object> transformsObject = ImmutableMap.of(
"transforms", transformsObjects
);

Map<String, Object> timestampSpec = ImmutableMap.of(
"column", "timestamp",
"format", "yyyyMMdd"
);
Map<String, Object> dimensionsSpec = ImmutableMap.of(
"dimensions", dimensions,
"dimensionExclusions", Collections.emptyList(),
"spatialDimensions", Collections.emptyList()
);
Map<String, Object> parseSpec = ImmutableMap.of(
"format", "tsv",
"timestampSpec", timestampSpec,
"dimensionsSpec", dimensionsSpec,
"columns", columns,
"listDelimiter", ","
);
Map<String, Object> object = ImmutableMap.of(
"type", "string",
"parseSpec", parseSpec,
"transformSpec", transformsObject
);
return toJson(object);
}

private static String toJson(Object object)
{
final String json;
Expand Down