[
https://issues.apache.org/jira/browse/BEAM-7013?focusedWorklogId=310111&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-310111
]
ASF GitHub Bot logged work on BEAM-7013:
----------------------------------------
Author: ASF GitHub Bot
Created on: 10/Sep/19 20:53
Start Date: 10/Sep/19 20:53
Worklog Time Spent: 10m
Work Description: zfraa commented on pull request #9519: [BEAM-7013] Use
a 0-length byte array to represent empty sketch in HllCount
URL: https://github.com/apache/beam/pull/9519#discussion_r322957148
##########
File path:
sdks/java/extensions/zetasketch/src/test/java/org/apache/beam/sdk/extensions/zetasketch/HllCountTest.java
##########
@@ -302,12 +304,53 @@ public void testMergePartialGlobally_SingletonInput() {
@Test
@Category(NeedsRunner.class)
- public void testMergePartialGlobally_EmptyInput() {
+ public void testMergePartialGlobally_SingletonInputEmptySketch() {
PCollection<byte[]> result =
- p.apply(Create.empty(TypeDescriptor.of(byte[].class)))
+
p.apply(Create.of(EMPTY_SKETCH)).apply(HllCount.MergePartial.globally());
+
+ PAssert.thatSingleton(result).isEqualTo(EMPTY_SKETCH);
+ p.run();
+ }
+
+ @Test
+ @Category(NeedsRunner.class)
+ public void testMergePartialGlobally_MergeWithEmptySketch() {
+ PCollection<byte[]> result =
+ p.apply(Create.of(LONGS_SKETCH,
EMPTY_SKETCH)).apply(HllCount.MergePartial.globally());
+
+ PAssert.thatSingleton(result).isEqualTo(LONGS_SKETCH);
+ p.run();
+ }
+
+ @Test
+ @Category(NeedsRunner.class)
+ public void testMergePartialGlobally_MergeMultipleEmptySketches() {
+ PCollection<byte[]> result =
+ p.apply(Create.of(EMPTY_SKETCH,
EMPTY_SKETCH)).apply(HllCount.MergePartial.globally());
+
+ PAssert.thatSingleton(result).isEqualTo(EMPTY_SKETCH);
+ p.run();
+ }
+
+ @Test
+ @Category(NeedsRunner.class)
+ public void testMergePartialGlobally_MergeWithSketchOfEmptySet() {
+ PCollection<byte[]> result =
+ p.apply(Create.of(LONGS_SKETCH, LONGS_SKETCH_OF_EMPTY_SET))
+ .apply(HllCount.MergePartial.globally());
+
+ PAssert.thatSingleton(result).isEqualTo(LONGS_SKETCH);
+ p.run();
+ }
+
+ @Test
+ @Category(NeedsRunner.class)
+ public void testMergePartialGlobally_MergeEmptySketchWithSketchOfEmptySet() {
+ PCollection<byte[]> result =
+ p.apply(Create.of(EMPTY_SKETCH, LONGS_SKETCH_OF_EMPTY_SET))
.apply(HllCount.MergePartial.globally());
- PAssert.that(result).empty();
+ PAssert.thatSingleton(result).isEqualTo(LONGS_SKETCH_OF_EMPTY_SET);
Review comment:
Good point, SG.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
Issue Time Tracking
-------------------
Worklog Id: (was: 310111)
Time Spent: 34h (was: 33h 50m)
> A new count distinct transform based on BigQuery compatible HyperLogLog++
> implementation
> ----------------------------------------------------------------------------------------
>
> Key: BEAM-7013
> URL: https://issues.apache.org/jira/browse/BEAM-7013
> Project: Beam
> Issue Type: New Feature
> Components: extensions-java-sketching, sdk-java-core
> Reporter: Yueyang Qiu
> Assignee: Yueyang Qiu
> Priority: Major
> Fix For: 2.16.0
>
> Time Spent: 34h
> Remaining Estimate: 0h
>
--
This message was sent by Atlassian Jira
(v8.3.2#803003)