You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@hive.apache.org by "Krisztian Kasa (Jira)" <ji...@apache.org> on 2021/05/31 14:05:00 UTC
[jira] [Updated] (HIVE-25166) Query with multiple count(distinct
constant) fails
[ https://issues.apache.org/jira/browse/HIVE-25166?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Krisztian Kasa updated HIVE-25166:
----------------------------------
Summary: Query with multiple count(distinct constant) fails (was: Query with multiple count(distinct) fails)
> Query with multiple count(distinct constant) fails
> --------------------------------------------------
>
> Key: HIVE-25166
> URL: https://issues.apache.org/jira/browse/HIVE-25166
> Project: Hive
> Issue Type: Bug
> Components: CBO
> Reporter: Krisztian Kasa
> Assignee: Krisztian Kasa
> Priority: Major
> Labels: pull-request-available
> Time Spent: 10m
> Remaining Estimate: 0h
>
> {code}
> select count(distinct 0), count(distinct null) from alltypes;
> {code}
> {code}
> org.apache.hadoop.hive.ql.parse.SemanticException: Line 0:-1 Expression not in GROUP BY key 'TOK_NULL'
> at org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.genAllExprNodeDesc(SemanticAnalyzer.java:12941)
> at org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.genExprNodeDesc(SemanticAnalyzer.java:12883)
> at org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.genSelectPlan(SemanticAnalyzer.java:4695)
> at org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.genSelectPlan(SemanticAnalyzer.java:4483)
> at org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.genPostGroupByBodyPlan(SemanticAnalyzer.java:10960)
> at org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.genBodyPlan(SemanticAnalyzer.java:10902)
> at org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.genPlan(SemanticAnalyzer.java:11808)
> at org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.genPlan(SemanticAnalyzer.java:11665)
> at org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.genPlan(SemanticAnalyzer.java:11692)
> at org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.genPlan(SemanticAnalyzer.java:11678)
> at org.apache.hadoop.hive.ql.parse.CalcitePlanner.genOPTree(CalcitePlanner.java:618)
> at org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.analyzeInternal(SemanticAnalyzer.java:12505)
> at org.apache.hadoop.hive.ql.parse.CalcitePlanner.analyzeInternal(CalcitePlanner.java:449)
> at org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.analyze(BaseSemanticAnalyzer.java:316)
> at org.apache.hadoop.hive.ql.parse.ExplainSemanticAnalyzer.analyzeInternal(ExplainSemanticAnalyzer.java:175)
> at org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.analyze(BaseSemanticAnalyzer.java:316)
> at org.apache.hadoop.hive.ql.Compiler.analyze(Compiler.java:223)
> at org.apache.hadoop.hive.ql.Compiler.compile(Compiler.java:105)
> at org.apache.hadoop.hive.ql.Driver.compile(Driver.java:492)
> at org.apache.hadoop.hive.ql.Driver.compileInternal(Driver.java:445)
> at org.apache.hadoop.hive.ql.Driver.compileAndRespond(Driver.java:409)
> at org.apache.hadoop.hive.ql.Driver.compileAndRespond(Driver.java:403)
> at org.apache.hadoop.hive.ql.reexec.ReExecDriver.compileAndRespond(ReExecDriver.java:125)
> at org.apache.hadoop.hive.ql.reexec.ReExecDriver.run(ReExecDriver.java:229)
> at org.apache.hadoop.hive.cli.CliDriver.processLocalCmd(CliDriver.java:256)
> at org.apache.hadoop.hive.cli.CliDriver.processCmd1(CliDriver.java:201)
> at org.apache.hadoop.hive.cli.CliDriver.processCmd(CliDriver.java:127)
> at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:422)
> at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:353)
> at org.apache.hadoop.hive.ql.QTestUtil.executeClientInternal(QTestUtil.java:744)
> at org.apache.hadoop.hive.ql.QTestUtil.executeClient(QTestUtil.java:714)
> at org.apache.hadoop.hive.cli.control.CoreCliDriver.runTest(CoreCliDriver.java:170)
> at org.apache.hadoop.hive.cli.control.CliAdapter.runTest(CliAdapter.java:157)
> at org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver(TestMiniLlapLocalCliDriver.java:62)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
> at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:498)
> at org.junit.runners.model.FrameworkMethod$1.runReflectiveCall(FrameworkMethod.java:59)
> at org.junit.internal.runners.model.ReflectiveCallable.run(ReflectiveCallable.java:12)
> at org.junit.runners.model.FrameworkMethod.invokeExplosively(FrameworkMethod.java:56)
> at org.junit.internal.runners.statements.InvokeMethod.evaluate(InvokeMethod.java:17)
> at org.apache.hadoop.hive.cli.control.CliAdapter$2$1.evaluate(CliAdapter.java:135)
> at org.junit.runners.ParentRunner$3.evaluate(ParentRunner.java:306)
> at org.junit.runners.BlockJUnit4ClassRunner$1.evaluate(BlockJUnit4ClassRunner.java:100)
> at org.junit.runners.ParentRunner.runLeaf(ParentRunner.java:366)
> at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:103)
> at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:63)
> at org.junit.runners.ParentRunner$4.run(ParentRunner.java:331)
> at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:79)
> at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:329)
> at org.junit.runners.ParentRunner.access$100(ParentRunner.java:66)
> at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:293)
> at org.junit.runners.ParentRunner.run(ParentRunner.java:413)
> at org.junit.runners.Suite.runChild(Suite.java:128)
> at org.junit.runners.Suite.runChild(Suite.java:27)
> at org.junit.runners.ParentRunner$4.run(ParentRunner.java:331)
> at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:79)
> at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:329)
> at org.junit.runners.ParentRunner.access$100(ParentRunner.java:66)
> at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:293)
> at org.apache.hadoop.hive.cli.control.CliAdapter$1$1.evaluate(CliAdapter.java:95)
> at org.junit.rules.RunRules.evaluate(RunRules.java:20)
> at org.junit.runners.ParentRunner$3.evaluate(ParentRunner.java:306)
> at org.junit.runners.ParentRunner.run(ParentRunner.java:413)
> at org.apache.maven.surefire.junit4.JUnit4Provider.execute(JUnit4Provider.java:365)
> at org.apache.maven.surefire.junit4.JUnit4Provider.executeWithRerun(JUnit4Provider.java:273)
> at org.apache.maven.surefire.junit4.JUnit4Provider.executeTestSet(JUnit4Provider.java:238)
> at org.apache.maven.surefire.junit4.JUnit4Provider.invoke(JUnit4Provider.java:159)
> at org.apache.maven.surefire.booter.ForkedBooter.runSuitesInProcess(ForkedBooter.java:377)
> at org.apache.maven.surefire.booter.ForkedBooter.execute(ForkedBooter.java:138)
> at org.apache.maven.surefire.booter.ForkedBooter.run(ForkedBooter.java:465)
> at org.apache.maven.surefire.booter.ForkedBooter.main(ForkedBooter.java:451)
> {code}
> CBO Plan:
> {code}
> HiveAggregate(group=[{}], agg#0=[count($0)], agg#1=[count($1)])
> HiveProject($f0=[CASE(=($2, 1), 1, null:INTEGER)], $f1=[null:INTEGER])
> HiveAggregate(group=[{0, 1}], GROUPING__ID=[GROUPING__ID()])
> HiveProject($f0=[true], $f1=[true])
> HiveTableScan(table=[[default, alltypes]], table:alias=[alltypes])
> {code}
> Query is rewritten to use an aggregate with one grouping set but later at ASTConverter this aggregate is treated as a simple Group By without grouping sets. However the function GROUPING__ID can only be used when grouping sets are defined.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)