[ https://issues.apache.org/jira/browse/HIVE-17379?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Sharanya Santhanam updated HIVE-17379: -------------------------------------- Description: Sample Query : with tableAAlias as ( select a, count(z) as acount from tableA groupBy a ) select a.a, b.b from tableB as b JOIN tableAAlias a on a.a=b.a where a.acount > 10 FAILED: NullPointerException null java.lang.NullPointerException at org.apache.hadoop.hive.ql.optimizer.ColumnPrunerProcFactory$ColumnPrunerFilterProc.process(ColumnPrunerProcFactory.java:103) at org.apache.hadoop.hive.ql.lib.DefaultRuleDispatcher.dispatch(DefaultRuleDispatcher.java:90) at org.apache.hadoop.hive.ql.lib.DefaultGraphWalker.dispatchAndReturn(DefaultGraphWalker.java:105) at org.apache.hadoop.hive.ql.lib.DefaultGraphWalker.dispatch(DefaultGraphWalker.java:89) at org.apache.hadoop.hive.ql.optimizer.ColumnPruner$ColumnPrunerWalker.walk(ColumnPruner.java:176) at org.apache.hadoop.hive.ql.lib.DefaultGraphWalker.startWalking(DefaultGraphWalker.java:120) at org.apache.hadoop.hive.ql.optimizer.ColumnPruner.transform(ColumnPruner.java:136) at org.apache.hadoop.hive.ql.optimizer.Optimizer.optimize(Optimizer.java:246) at org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.analyzeInternal(SemanticAnalyzer.java:11149) at org.apache.hadoop.hive.ql.parse.CalcitePlanner.analyzeInternal(CalcitePlanner.java:246) at org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.analyze(BaseSemanticAnalyzer.java:264) at org.apache.hadoop.hive.ql.parse.ExplainSemanticAnalyzer.analyzeInternal(ExplainSemanticAnalyzer.java:80) at org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.analyze(BaseSemanticAnalyzer.java:264) at org.apache.hadoop.hive.ql.Driver.compile(Driver.java:490) at org.apache.hadoop.hive.ql.Driver.compileInternal(Driver.java:1270) at org.apache.hadoop.hive.ql.Driver.runInternal(Driver.java:1412) at org.apache.hadoop.hive.ql.Driver.run(Driver.java:1199) at org.apache.hadoop.hive.ql.Driver.run(Driver.java:1189) at org.apache.hadoop.hive.cli.CliDriver.processLocalCmd(CliDriver.java:265) at org.apache.hadoop.hive.cli.CliDriver.processCmd(CliDriver.java:210) at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:444) at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:376) at org.apache.hadoop.hive.cli.CliDriver.processReader(CliDriver.java:474) at org.apache.hadoop.hive.cli.CliDriver.processFile(CliDriver.java:514) at org.apache.hadoop.hive.cli.CliDriver.executeDriver(CliDriver.java:882) at org.apache.hadoop.hive.cli.CliDriver.run(CliDriver.java:836) at org.apache.hadoop.hive.cli.CliDriver.main(CliDriver.java:732) at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) at java.lang.reflect.Method.invoke(Method.java:606) at org.apache.hadoop.util.RunJar.run(RunJar.java:223) at org.apache.hadoop.util.RunJar.main(RunJar.java:136) The above Query Succeeds if it is modified as : select a.a, b.b , *a.acount* from tableB as b JOIN tableAAlias a on a.a=b.a where a.acount > 10 Please Note the original query worked on hive1.2 & breaks on Hive2.1.1 was: Sample Query : with tableAAlias as ( select a, count(*) as acount from tableA groupBy a ) select a.a, b.b from tableB as b JOIN tableAAlias a on a.a=b.a where a.acount > 10 FAILED: NullPointerException null java.lang.NullPointerException at org.apache.hadoop.hive.ql.optimizer.ColumnPrunerProcFactory$ColumnPrunerFilterProc.process(ColumnPrunerProcFactory.java:103) at org.apache.hadoop.hive.ql.lib.DefaultRuleDispatcher.dispatch(DefaultRuleDispatcher.java:90) at org.apache.hadoop.hive.ql.lib.DefaultGraphWalker.dispatchAndReturn(DefaultGraphWalker.java:105) at org.apache.hadoop.hive.ql.lib.DefaultGraphWalker.dispatch(DefaultGraphWalker.java:89) at org.apache.hadoop.hive.ql.optimizer.ColumnPruner$ColumnPrunerWalker.walk(ColumnPruner.java:176) at org.apache.hadoop.hive.ql.lib.DefaultGraphWalker.startWalking(DefaultGraphWalker.java:120) at org.apache.hadoop.hive.ql.optimizer.ColumnPruner.transform(ColumnPruner.java:136) at org.apache.hadoop.hive.ql.optimizer.Optimizer.optimize(Optimizer.java:246) at org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.analyzeInternal(SemanticAnalyzer.java:11149) at org.apache.hadoop.hive.ql.parse.CalcitePlanner.analyzeInternal(CalcitePlanner.java:246) at org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.analyze(BaseSemanticAnalyzer.java:264) at org.apache.hadoop.hive.ql.parse.ExplainSemanticAnalyzer.analyzeInternal(ExplainSemanticAnalyzer.java:80) at org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.analyze(BaseSemanticAnalyzer.java:264) at org.apache.hadoop.hive.ql.Driver.compile(Driver.java:490) at org.apache.hadoop.hive.ql.Driver.compileInternal(Driver.java:1270) at org.apache.hadoop.hive.ql.Driver.runInternal(Driver.java:1412) at org.apache.hadoop.hive.ql.Driver.run(Driver.java:1199) at org.apache.hadoop.hive.ql.Driver.run(Driver.java:1189) at org.apache.hadoop.hive.cli.CliDriver.processLocalCmd(CliDriver.java:265) at org.apache.hadoop.hive.cli.CliDriver.processCmd(CliDriver.java:210) at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:444) at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:376) at org.apache.hadoop.hive.cli.CliDriver.processReader(CliDriver.java:474) at org.apache.hadoop.hive.cli.CliDriver.processFile(CliDriver.java:514) at org.apache.hadoop.hive.cli.CliDriver.executeDriver(CliDriver.java:882) at org.apache.hadoop.hive.cli.CliDriver.run(CliDriver.java:836) at org.apache.hadoop.hive.cli.CliDriver.main(CliDriver.java:732) at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) at java.lang.reflect.Method.invoke(Method.java:606) at org.apache.hadoop.util.RunJar.run(RunJar.java:223) at org.apache.hadoop.util.RunJar.main(RunJar.java:136) The above Query Succeeds if it is modified as : select a.a, b.b , *a.acount* from tableB as b JOIN tableAAlias a on a.a=b.a where a.acount > 10 Please Note the original query worked on hive1.2 & breaks on Hive2.1.1 > Null Pointer Exception in WHERE clause when using aggregate function as a > filter > ---------------------------------------------------------------------------------- > > Key: HIVE-17379 > URL: https://issues.apache.org/jira/browse/HIVE-17379 > Project: Hive > Issue Type: Bug > Components: Query Processor > Affects Versions: 2.1.1 > Reporter: Sharanya Santhanam > > Sample Query : > with tableAAlias as ( > select a, count(z) as acount > from tableA > groupBy a > ) > select a.a, b.b > from tableB as b JOIN > tableAAlias a > on a.a=b.a > where a.acount > 10 > FAILED: NullPointerException null > java.lang.NullPointerException > at > org.apache.hadoop.hive.ql.optimizer.ColumnPrunerProcFactory$ColumnPrunerFilterProc.process(ColumnPrunerProcFactory.java:103) > at > org.apache.hadoop.hive.ql.lib.DefaultRuleDispatcher.dispatch(DefaultRuleDispatcher.java:90) > at > org.apache.hadoop.hive.ql.lib.DefaultGraphWalker.dispatchAndReturn(DefaultGraphWalker.java:105) > at > org.apache.hadoop.hive.ql.lib.DefaultGraphWalker.dispatch(DefaultGraphWalker.java:89) > at > org.apache.hadoop.hive.ql.optimizer.ColumnPruner$ColumnPrunerWalker.walk(ColumnPruner.java:176) > at > org.apache.hadoop.hive.ql.lib.DefaultGraphWalker.startWalking(DefaultGraphWalker.java:120) > at > org.apache.hadoop.hive.ql.optimizer.ColumnPruner.transform(ColumnPruner.java:136) > at org.apache.hadoop.hive.ql.optimizer.Optimizer.optimize(Optimizer.java:246) > at > org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.analyzeInternal(SemanticAnalyzer.java:11149) > at > org.apache.hadoop.hive.ql.parse.CalcitePlanner.analyzeInternal(CalcitePlanner.java:246) > at > org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.analyze(BaseSemanticAnalyzer.java:264) > at > org.apache.hadoop.hive.ql.parse.ExplainSemanticAnalyzer.analyzeInternal(ExplainSemanticAnalyzer.java:80) > at > org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.analyze(BaseSemanticAnalyzer.java:264) > at org.apache.hadoop.hive.ql.Driver.compile(Driver.java:490) > at org.apache.hadoop.hive.ql.Driver.compileInternal(Driver.java:1270) > at org.apache.hadoop.hive.ql.Driver.runInternal(Driver.java:1412) > at org.apache.hadoop.hive.ql.Driver.run(Driver.java:1199) > at org.apache.hadoop.hive.ql.Driver.run(Driver.java:1189) > at org.apache.hadoop.hive.cli.CliDriver.processLocalCmd(CliDriver.java:265) > at org.apache.hadoop.hive.cli.CliDriver.processCmd(CliDriver.java:210) > at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:444) > at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:376) > at org.apache.hadoop.hive.cli.CliDriver.processReader(CliDriver.java:474) > at org.apache.hadoop.hive.cli.CliDriver.processFile(CliDriver.java:514) > at org.apache.hadoop.hive.cli.CliDriver.executeDriver(CliDriver.java:882) > at org.apache.hadoop.hive.cli.CliDriver.run(CliDriver.java:836) > at org.apache.hadoop.hive.cli.CliDriver.main(CliDriver.java:732) > at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) > at > sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57) > at > sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) > at java.lang.reflect.Method.invoke(Method.java:606) > at org.apache.hadoop.util.RunJar.run(RunJar.java:223) > at org.apache.hadoop.util.RunJar.main(RunJar.java:136) > The above Query Succeeds if it is modified as : > select a.a, b.b , *a.acount* > from tableB as b JOIN > tableAAlias a > on a.a=b.a > where a.acount > 10 > Please Note the original query worked on hive1.2 & breaks on Hive2.1.1 -- This message was sent by Atlassian JIRA (v6.4.14#64029)