[
https://issues.apache.org/jira/browse/HIVE-22412?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
ASF GitHub Bot updated HIVE-22412:
----------------------------------
Labels: pull-request-available (was: )
> StatsUtils throw NPE when explain
> ---------------------------------
>
> Key: HIVE-22412
> URL: https://issues.apache.org/jira/browse/HIVE-22412
> Project: Hive
> Issue Type: Bug
> Components: HiveServer2
> Affects Versions: 1.2.1, 2.0.0, 3.0.0
> Reporter: xiepengjie
> Assignee: xiepengjie
> Priority: Major
> Labels: pull-request-available
> Attachments: HIVE-22412.patch
>
> Time Spent: 10m
> Remaining Estimate: 0h
>
> The demo like this:
> {code:java}
> drop table if exists explain_npe_map;
> drop table if exists explain_npe_array;
> drop table if exists explain_npe_struct;
> create table explain_npe_map ( c1 map<string, string> );
> create table explain_npe_array ( c1 array<string> );
> create table explain_npe_struct ( c1 struct<name:string, age:int> );
> -- error
> set hive.cbo.enable=false;
> explain select c1 from explain_npe_map where c1 is null;
> explain select c1 from explain_npe_array where c1 is null;
> explain select c1 from explain_npe_struct where c1 is null;
> -- correct
> set hive.cbo.enable=true;
> explain select c1 from explain_npe_map where c1 is null;
> explain select c1 from explain_npe_array where c1 is null;
> explain select c1 from explain_npe_struct where c1 is null;{code}
>
> if the conf 'hive.cbo.enable' set false , NPE will be thrown ; otherwise will
> not.
> {code:java}
> hive> drop table if exists explain_npe_map;
> OK
> Time taken: 0.063 seconds
> hive> drop table if exists explain_npe_array;
> OK
> Time taken: 0.035 seconds
> hive> drop table if exists explain_npe_struct;
> OK
> Time taken: 0.015 seconds
> hive>
> > create table explain_npe_map ( c1 map<string, string> );
> OK
> Time taken: 0.584 seconds
> hive> create table explain_npe_array ( c1 array<string> );
> OK
> Time taken: 0.216 seconds
> hive> create table explain_npe_struct ( c1 struct<name:string, age:int> );
> OK
> Time taken: 0.17 seconds
> hive>
> > set hive.cbo.enable=false;
> hive> explain select c1 from explain_npe_map where c1 is null;
> FAILED: NullPointerException null
> hive> explain select c1 from explain_npe_array where c1 is null;
> FAILED: NullPointerException null
> hive> explain select c1 from explain_npe_struct where c1 is null;
> FAILED: RuntimeException Error invoking signature method
> hive>
> > set hive.cbo.enable=true;
> hive> explain select c1 from explain_npe_map where c1 is null;
> OK
> STAGE DEPENDENCIES:
> Stage-0 is a root stageSTAGE PLANS:
> Stage: Stage-0
> Fetch Operator
> limit: -1
> Processor Tree:
> TableScan
> alias: explain_npe_map
> Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column
> stats: NONE
> Filter Operator
> predicate: false (type: boolean)
> Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column
> stats: NONE
> Select Operator
> expressions: c1 (type: map<string,string>)
> outputColumnNames: _col0
> Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL
> Column stats: NONE
> ListSinkTime taken: 1.593 seconds, Fetched: 20 row(s)
> hive> explain select c1 from explain_npe_array where c1 is null;
> OK
> STAGE DEPENDENCIES:
> Stage-0 is a root stageSTAGE PLANS:
> Stage: Stage-0
> Fetch Operator
> limit: -1
> Processor Tree:
> TableScan
> alias: explain_npe_array
> Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column
> stats: NONE
> Filter Operator
> predicate: false (type: boolean)
> Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column
> stats: NONE
> Select Operator
> expressions: c1 (type: array<string>)
> outputColumnNames: _col0
> Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL
> Column stats: NONE
> ListSinkTime taken: 1.969 seconds, Fetched: 20 row(s)
> hive> explain select c1 from explain_npe_struct where c1 is null;
> OK
> STAGE DEPENDENCIES:
> Stage-0 is a root stageSTAGE PLANS:
> Stage: Stage-0
> Fetch Operator
> limit: -1
> Processor Tree:
> TableScan
> alias: explain_npe_struct
> Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column
> stats: NONE
> Filter Operator
> predicate: false (type: boolean)
> Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column
> stats: NONE
> Select Operator
> expressions: c1 (type: struct<name:string,age:int>)
> outputColumnNames: _col0
> Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL
> Column stats: NONE
> ListSinkTime taken: 2.932 seconds, Fetched: 20 row(s)
> hive>
> {code}
> ms error like:
> for map:
> {code:java}
> java.lang.NullPointerException
> at
> org.apache.hadoop.hive.ql.stats.StatsUtils.getSizeOfMap(StatsUtils.java:1045)
> at
> org.apache.hadoop.hive.ql.stats.StatsUtils.getSizeOfComplexTypes(StatsUtils.java:931)
> at
> org.apache.hadoop.hive.ql.stats.StatsUtils.getAvgColLenOfVariableLengthTypes(StatsUtils.java:869)
> at
> org.apache.hadoop.hive.ql.stats.StatsUtils.estimateRowSizeFromSchema(StatsUtils.java:526)
> at
> org.apache.hadoop.hive.ql.stats.StatsUtils.collectStatistics(StatsUtils.java:223)
> at
> org.apache.hadoop.hive.ql.stats.StatsUtils.collectStatistics(StatsUtils.java:136)
> at
> org.apache.hadoop.hive.ql.stats.StatsUtils.collectStatistics(StatsUtils.java:124)
> at
> org.apache.hadoop.hive.ql.optimizer.stats.annotation.StatsRulesProcFactory$TableScanStatsRule.process(StatsRulesProcFactory.java:111)
> at
> org.apache.hadoop.hive.ql.lib.DefaultRuleDispatcher.dispatch(DefaultRuleDispatcher.java:90)
> at
> org.apache.hadoop.hive.ql.lib.DefaultGraphWalker.dispatchAndReturn(DefaultGraphWalker.java:95)
> at
> org.apache.hadoop.hive.ql.lib.DefaultGraphWalker.dispatch(DefaultGraphWalker.java:79)
> at
> org.apache.hadoop.hive.ql.lib.PreOrderWalker.walk(PreOrderWalker.java:56)
> at
> org.apache.hadoop.hive.ql.lib.DefaultGraphWalker.startWalking(DefaultGraphWalker.java:110)
> at
> org.apache.hadoop.hive.ql.optimizer.stats.annotation.AnnotateWithStatistics.transform(AnnotateWithStatistics.java:78)
> at
> org.apache.hadoop.hive.ql.optimizer.Optimizer.optimize(Optimizer.java:192)
> at
> org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.analyzeInternal(SemanticAnalyzer.java:10205)
> at
> org.apache.hadoop.hive.ql.parse.CalcitePlanner.analyzeInternal(CalcitePlanner.java:210)
> at
> org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.analyze(BaseSemanticAnalyzer.java:227)
> at
> org.apache.hadoop.hive.ql.parse.ExplainSemanticAnalyzer.analyzeInternal(ExplainSemanticAnalyzer.java:74)
> at
> org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.analyze(BaseSemanticAnalyzer.java:227)
> at org.apache.hadoop.hive.ql.Driver.compile(Driver.java:425)
> at org.apache.hadoop.hive.ql.Driver.compile(Driver.java:309)
> at org.apache.hadoop.hive.ql.Driver.compileInternal(Driver.java:1153)
> at org.apache.hadoop.hive.ql.Driver.runInternal(Driver.java:1206)
> at org.apache.hadoop.hive.ql.Driver.run(Driver.java:1082)
> at org.apache.hadoop.hive.ql.Driver.run(Driver.java:1072)
> at
> org.apache.hadoop.hive.cli.CliDriver.processLocalCmd(CliDriver.java:213)
> at org.apache.hadoop.hive.cli.CliDriver.processCmd(CliDriver.java:165)
> at
> org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:376)
> at
> org.apache.hadoop.hive.cli.CliDriver.executeDriver(CliDriver.java:736)
> at org.apache.hadoop.hive.cli.CliDriver.run(CliDriver.java:681)
> at org.apache.hadoop.hive.cli.CliDriver.main(CliDriver.java:621)
> 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.apache.hadoop.util.RunJar.run(RunJar.java:221)
> at org.apache.hadoop.util.RunJar.main(RunJar.java:136){code}
>
> for array:
> {code:java}
> java.lang.NullPointerException
> at
> org.apache.hadoop.hive.ql.stats.StatsUtils.getSizeOfComplexTypes(StatsUtils.java:1168)
> at
> org.apache.hadoop.hive.ql.stats.StatsUtils.getAvgColLenOf(StatsUtils.java:1132)
> at
> org.apache.hadoop.hive.ql.stats.StatsUtils.estimateRowSizeFromSchema(StatsUtils.java:686)
> at
> org.apache.hadoop.hive.ql.stats.StatsUtils.estimateRowSizeFromSchema(StatsUtils.java:664)
> at
> org.apache.hadoop.hive.ql.stats.StatsUtils.collectStatistics(StatsUtils.java:254)
> at
> org.apache.hadoop.hive.ql.stats.StatsUtils.collectStatistics(StatsUtils.java:162)
> at
> org.apache.hadoop.hive.ql.stats.StatsUtils.collectStatistics(StatsUtils.java:150)
> at
> org.apache.hadoop.hive.ql.optimizer.stats.annotation.StatsRulesProcFactory$TableScanStatsRule.process(StatsRulesProcFactory.java:142)
> 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.lib.LevelOrderWalker.walk(LevelOrderWalker.java:143)
> at
> org.apache.hadoop.hive.ql.lib.LevelOrderWalker.startWalking(LevelOrderWalker.java:122)
> at
> org.apache.hadoop.hive.ql.optimizer.stats.annotation.AnnotateWithStatistics.transform(AnnotateWithStatistics.java:78)
> at
> org.apache.hadoop.hive.ql.optimizer.Optimizer.optimize(Optimizer.java:250)
> at
> org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.analyzeInternal(SemanticAnalyzer.java:12481)
> at
> org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.analyzeInternal(SemanticAnalyzer.java:11824)
> at
> org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.analyze(BaseSemanticAnalyzer.java:285)
> at
> org.apache.hadoop.hive.ql.parse.ExplainSemanticAnalyzer.analyzeInternal(ExplainSemanticAnalyzer.java:166)
> at
> org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.analyze(BaseSemanticAnalyzer.java:285)
> at org.apache.hadoop.hive.ql.Driver.compile(Driver.java:664)
> at org.apache.hadoop.hive.ql.Driver.compileInternal(Driver.java:1854)
> at
> org.apache.hadoop.hive.ql.Driver.compileAndRespond(Driver.java:1801)
> at
> org.apache.hadoop.hive.ql.Driver.compileAndRespond(Driver.java:1796)
> at
> org.apache.hadoop.hive.ql.reexec.ReExecDriver.compileAndRespond(ReExecDriver.java:126)
> at
> org.apache.hadoop.hive.ql.reexec.ReExecDriver.run(ReExecDriver.java:214)
> at
> org.apache.hadoop.hive.cli.CliDriver.processLocalCmd(CliDriver.java:239)
> at org.apache.hadoop.hive.cli.CliDriver.processCmd(CliDriver.java:188)
> at
> org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:402)
> at
> org.apache.hadoop.hive.cli.CliDriver.executeDriver(CliDriver.java:821)
> at org.apache.hadoop.hive.cli.CliDriver.run(CliDriver.java:759)
> at org.apache.hadoop.hive.cli.CliDriver.main(CliDriver.java:683)
> 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.apache.hadoop.util.RunJar.run(RunJar.java:226)
> at org.apache.hadoop.util.RunJar.main(RunJar.java:141)
> {code}
> for struct:
> Maybe correct in branch of master, but i think it is necessary to initialize
> the value of StandardConstantStructObjectInspector
> {code:java}
> //代码占位符
> 2020-06-10T16:40:56,971 ERROR [52839d08-57a7-475f-b87f-8f1410978b8a main]
> ql.Driver: FAILED: RuntimeException Error invoking signature method
> java.lang.RuntimeException: Error invoking signature method
> at
> org.apache.hadoop.hive.ql.optimizer.signature.SignatureUtils$SignatureMapper.write(SignatureUtils.java:76)
> at
> org.apache.hadoop.hive.ql.optimizer.signature.SignatureUtils.write(SignatureUtils.java:40)
> at
> org.apache.hadoop.hive.ql.optimizer.signature.OpSignature.<init>(OpSignature.java:53)
> at
> org.apache.hadoop.hive.ql.optimizer.signature.OpSignature.of(OpSignature.java:57)
> at
> org.apache.hadoop.hive.ql.optimizer.signature.OpTreeSignature.<init>(OpTreeSignature.java:50)
> at
> org.apache.hadoop.hive.ql.optimizer.signature.OpTreeSignature.of(OpTreeSignature.java:63)
> at
> org.apache.hadoop.hive.ql.optimizer.signature.OpTreeSignatureFactory$CachedFactory.lambda$getSignature$0(OpTreeSignatureFactory.java:62)
> at java.util.Map.computeIfAbsent(Map.java:957)
> at
> org.apache.hadoop.hive.ql.optimizer.signature.OpTreeSignatureFactory$CachedFactory.getSignature(OpTreeSignatureFactory.java:62)
> at
> org.apache.hadoop.hive.ql.plan.mapper.PlanMapper.getSignatureOf(PlanMapper.java:265)
> at
> org.apache.hadoop.hive.ql.optimizer.stats.annotation.StatsRulesProcFactory.applyRuntimeStats(StatsRulesProcFactory.java:2666)
> at
> org.apache.hadoop.hive.ql.optimizer.stats.annotation.StatsRulesProcFactory.access$000(StatsRulesProcFactory.java:116)
> at
> org.apache.hadoop.hive.ql.optimizer.stats.annotation.StatsRulesProcFactory$SelectStatsRule.process(StatsRulesProcFactory.java:211)
> 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.lib.LevelOrderWalker.walk(LevelOrderWalker.java:143)
> at
> org.apache.hadoop.hive.ql.lib.LevelOrderWalker.startWalking(LevelOrderWalker.java:122)
> at
> org.apache.hadoop.hive.ql.optimizer.stats.annotation.AnnotateWithStatistics.transform(AnnotateWithStatistics.java:78)
> at
> org.apache.hadoop.hive.ql.optimizer.Optimizer.optimize(Optimizer.java:250)
> at
> org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.analyzeInternal(SemanticAnalyzer.java:12481)
> at
> org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.analyzeInternal(SemanticAnalyzer.java:11824)
> at
> org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.analyze(BaseSemanticAnalyzer.java:285)
> at
> org.apache.hadoop.hive.ql.parse.ExplainSemanticAnalyzer.analyzeInternal(ExplainSemanticAnalyzer.java:166)
> at
> org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.analyze(BaseSemanticAnalyzer.java:285)
> at org.apache.hadoop.hive.ql.Driver.compile(Driver.java:664)
> at org.apache.hadoop.hive.ql.Driver.compileInternal(Driver.java:1854)
> at
> org.apache.hadoop.hive.ql.Driver.compileAndRespond(Driver.java:1801)
> at
> org.apache.hadoop.hive.ql.Driver.compileAndRespond(Driver.java:1796)
> at
> org.apache.hadoop.hive.ql.reexec.ReExecDriver.compileAndRespond(ReExecDriver.java:126)
> at
> org.apache.hadoop.hive.ql.reexec.ReExecDriver.run(ReExecDriver.java:214)
> at
> org.apache.hadoop.hive.cli.CliDriver.processLocalCmd(CliDriver.java:239)
> at org.apache.hadoop.hive.cli.CliDriver.processCmd(CliDriver.java:188)
> at
> org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:402)
> at
> org.apache.hadoop.hive.cli.CliDriver.executeDriver(CliDriver.java:821)
> at org.apache.hadoop.hive.cli.CliDriver.run(CliDriver.java:759)
> at org.apache.hadoop.hive.cli.CliDriver.main(CliDriver.java:683)
> 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.apache.hadoop.util.RunJar.run(RunJar.java:226)
> at org.apache.hadoop.util.RunJar.main(RunJar.java:141)
> Caused by: java.lang.reflect.InvocationTargetException
> 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.apache.hadoop.hive.ql.optimizer.signature.SignatureUtils$SignatureMapper.write(SignatureUtils.java:73)
> ... 42 more
> Caused by: java.lang.NullPointerException
> at
> org.apache.hadoop.hive.ql.plan.ExprNodeConstantDesc.getExprString(ExprNodeConstantDesc.java:158)
> at
> org.apache.hadoop.hive.ql.plan.ExprNodeDesc.getExprString(ExprNodeDesc.java:90)
> at
> org.apache.hadoop.hive.ql.plan.PlanUtils.addExprToStringBuffer(PlanUtils.java:1104)
> at
> org.apache.hadoop.hive.ql.plan.PlanUtils.getExprListString(PlanUtils.java:1092)
> at
> org.apache.hadoop.hive.ql.plan.PlanUtils.getExprListString(PlanUtils.java:1075)
> at
> org.apache.hadoop.hive.ql.plan.SelectDesc.getColListString(SelectDesc.java:79)
> ... 47 more
> {code}
>
> We can fix it by initializing value for StandardConstantMapObjectInspector,
> StandardConstantListObjectInspector and StandardConstantStructObjectInspector.
>
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
