[
https://issues.apache.org/jira/browse/BEAM-8042?focusedWorklogId=375298&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-375298
]
ASF GitHub Bot logged work on BEAM-8042:
----------------------------------------
Author: ASF GitHub Bot
Created on: 21/Jan/20 23:44
Start Date: 21/Jan/20 23:44
Worklog Time Spent: 10m
Work Description: 11moon11 commented on pull request #10649: [BEAM-8042]
[ZetaSQL] Fix aggregate column reference
URL: https://github.com/apache/beam/pull/10649#discussion_r369303722
##########
File path:
sdks/java/extensions/sql/zetasql/src/test/java/org/apache/beam/sdk/extensions/sql/zetasql/ZetaSQLDialectSpecTest.java
##########
@@ -1347,6 +1347,44 @@ public void testZetaSQLStructFieldAccessInTumble() {
pipeline.run().waitUntilFinish(Duration.standardMinutes(PIPELINE_EXECUTION_WAITTIME_MINUTES));
}
+ @Test
+ public void testAggregateWithAndWithoutColumnRefs() {
+ ZetaSQLQueryPlanner zetaSQLQueryPlanner = new ZetaSQLQueryPlanner(config);
+
+ String sql =
+ "SELECT \n"
+ + " id, \n"
+ + " SUM(has_f1) as f1_count, \n"
+ + " SUM(has_f2) as f2_count, \n"
+ + " SUM(has_f3) as f3_count, \n"
+ + " SUM(has_f4) as f4_count, \n"
+ + " SUM(has_f5) as f5_count, \n"
+ + " COUNT(*) as count, \n"
+ + " SUM(has_f6) as f6_count \n"
+ + "FROM (select 0 as id, 1 as has_f1, 2 as has_f2, 3 as has_f3, 4
as has_f4, 5 as has_f5, 6 as has_f6)\n"
Review comment:
Might want to use named parameters to not rely on hard-coded values.
----------------------------------------------------------------
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:
us...@infra.apache.org
Issue Time Tracking
-------------------
Worklog Id: (was: 375298)
Time Spent: 50m (was: 40m)
> Parsing of aggregate query fails
> --------------------------------
>
> Key: BEAM-8042
> URL: https://issues.apache.org/jira/browse/BEAM-8042
> Project: Beam
> Issue Type: Sub-task
> Components: dsl-sql-zetasql
> Reporter: Rui Wang
> Assignee: Kirill Kozlov
> Priority: Critical
> Time Spent: 50m
> Remaining Estimate: 0h
>
> {code}
> @Rule
> public TestPipeline pipeline =
> TestPipeline.fromOptions(createPipelineOptions());
> private static PipelineOptions createPipelineOptions() {
> BeamSqlPipelineOptions opts =
> PipelineOptionsFactory.create().as(BeamSqlPipelineOptions.class);
> opts.setPlannerName(ZetaSQLQueryPlanner.class.getName());
> return opts;
> }
> @Test
> public void testAggregate() {
> Schema inputSchema = Schema.builder()
> .addByteArrayField("id")
> .addInt64Field("has_f1")
> .addInt64Field("has_f2")
> .addInt64Field("has_f3")
> .addInt64Field("has_f4")
> .addInt64Field("has_f5")
> .addInt64Field("has_f6")
> .build();
> String sql = "SELECT \n" +
> " id, \n" +
> " COUNT(*) as count, \n" +
> " SUM(has_f1) as f1_count, \n" +
> " SUM(has_f2) as f2_count, \n" +
> " SUM(has_f3) as f3_count, \n" +
> " SUM(has_f4) as f4_count, \n" +
> " SUM(has_f5) as f5_count, \n" +
> " SUM(has_f6) as f6_count \n" +
> "FROM PCOLLECTION \n" +
> "GROUP BY id";
> pipeline
> .apply(Create.empty(inputSchema))
> .apply(SqlTransform.query(sql));
> pipeline.run();
> }
> {code}
> {code}
> Caused by: java.lang.RuntimeException: Error while applying rule
> AggregateProjectMergeRule, args
> [rel#553:LogicalAggregate.NONE(input=RelSubset#552,group={0},f1=COUNT(),f2=SUM($2),f3=SUM($3),f4=SUM($4),f5=SUM($5),f6=SUM($6),f7=SUM($7)),
>
> rel#551:LogicalProject.NONE(input=RelSubset#550,key=$0,f1=$1,f2=$2,f3=$3,f4=$4,f5=$5,f6=$6)]
> at
> org.apache.beam.repackaged.sql.org.apache.calcite.plan.volcano.VolcanoRuleCall.onMatch(VolcanoRuleCall.java:232)
> at
> org.apache.beam.repackaged.sql.org.apache.calcite.plan.volcano.VolcanoPlanner.findBestExp(VolcanoPlanner.java:637)
> at
> org.apache.beam.repackaged.sql.org.apache.calcite.tools.Programs$RuleSetProgram.run(Programs.java:340)
> at
> org.apache.beam.sdk.extensions.sql.zetasql.ZetaSQLPlannerImpl.transform(ZetaSQLPlannerImpl.java:168)
> at
> org.apache.beam.sdk.extensions.sql.zetasql.ZetaSQLQueryPlanner.parseQuery(ZetaSQLQueryPlanner.java:99)
> at
> org.apache.beam.sdk.extensions.sql.zetasql.ZetaSQLQueryPlanner.parseQuery(ZetaSQLQueryPlanner.java:87)
> at
> org.apache.beam.sdk.extensions.sql.zetasql.ZetaSQLQueryPlanner.convertToBeamRel(ZetaSQLQueryPlanner.java:66)
> at
> org.apache.beam.sdk.extensions.sql.impl.BeamSqlEnv.parseQuery(BeamSqlEnv.java:104)
> at
> ... 39 more
> Caused by: java.lang.ArrayIndexOutOfBoundsException: 7
> at
> org.apache.beam.repackaged.sql.com.google.common.collect.RegularImmutableList.get(RegularImmutableList.java:58)
> at
> org.apache.beam.repackaged.sql.org.apache.calcite.rel.rules.AggregateProjectMergeRule.apply(AggregateProjectMergeRule.java:96)
> at
> org.apache.beam.repackaged.sql.org.apache.calcite.rel.rules.AggregateProjectMergeRule.onMatch(AggregateProjectMergeRule.java:73)
> at
> org.apache.beam.repackaged.sql.org.apache.calcite.plan.volcano.VolcanoRuleCall.onMatch(VolcanoRuleCall.java:205)
> ... 48 more
> {code}
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
