[
https://issues.apache.org/jira/browse/HIVE-27754?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17770032#comment-17770032
]
Krisztian Kasa commented on HIVE-27754:
---------------------------------------
A simple repro with a query:
{code}
create table t1 (a int);
insert into t1(a) values (1), (2), (NULL);
select * from t1 where 'anything';
{code}
returns
{code}
1
2
NULL
{code}
CBO is failing in this case. From hive.log
{code}
2023-09-28T05:14:55,578 ERROR [08def54d-804f-44fc-8452-c9873eb3a06e Listener at
0.0.0.0/36139] parse.CalcitePlanner: CBO failed, skipping CBO.
org.apache.hadoop.hive.ql.optimizer.calcite.CalciteSemanticException: Filter
expression with non-boolean return type.
at
org.apache.hadoop.hive.ql.parse.CalcitePlanner$CalcitePlannerAction.genFilterRelNode(CalcitePlanner.java:3216)
~[hive-exec-4.0.0-beta-2-SNAPSHOT.jar:4.0.0-beta-2-SNAPSHOT]
at
org.apache.hadoop.hive.ql.parse.CalcitePlanner$CalcitePlannerAction.genFilterRelNode(CalcitePlanner.java:3202)
~[hive-exec-4.0.0-beta-2-SNAPSHOT.jar:4.0.0-beta-2-SNAPSHOT]
at
org.apache.hadoop.hive.ql.parse.CalcitePlanner$CalcitePlannerAction.genFilterRelNode(CalcitePlanner.java:3399)
~[hive-exec-4.0.0-beta-2-SNAPSHOT.jar:4.0.0-beta-2-SNAPSHOT]
at
org.apache.hadoop.hive.ql.parse.CalcitePlanner$CalcitePlannerAction.genFilterLogicalPlan(CalcitePlanner.java:3410)
~[hive-exec-4.0.0-beta-2-SNAPSHOT.jar:4.0.0-beta-2-SNAPSHOT]
at
org.apache.hadoop.hive.ql.parse.CalcitePlanner$CalcitePlannerAction.genLogicalPlan(CalcitePlanner.java:5084)
~[hive-exec-4.0.0-beta-2-SNAPSHOT.jar:4.0.0-beta-2-SNAPSHOT]
at
org.apache.hadoop.hive.ql.parse.CalcitePlanner$CalcitePlannerAction.apply(CalcitePlanner.java:1649)
~[hive-exec-4.0.0-beta-2-SNAPSHOT.jar:4.0.0-beta-2-SNAPSHOT]
at
org.apache.hadoop.hive.ql.parse.CalcitePlanner$CalcitePlannerAction.apply(CalcitePlanner.java:1593)
~[hive-exec-4.0.0-beta-2-SNAPSHOT.jar:4.0.0-beta-2-SNAPSHOT]
at
org.apache.calcite.tools.Frameworks.lambda$withPlanner$0(Frameworks.java:131)
~[hive-exec-4.0.0-beta-2-SNAPSHOT.jar:4.0.0-beta-2-SNAPSHOT]
at
org.apache.calcite.prepare.CalcitePrepareImpl.perform(CalcitePrepareImpl.java:914)
~[hive-exec-4.0.0-beta-2-SNAPSHOT.jar:4.0.0-beta-2-SNAPSHOT]
at org.apache.calcite.tools.Frameworks.withPrepare(Frameworks.java:180)
~[hive-exec-4.0.0-beta-2-SNAPSHOT.jar:4.0.0-beta-2-SNAPSHOT]
at org.apache.calcite.tools.Frameworks.withPlanner(Frameworks.java:126)
~[hive-exec-4.0.0-beta-2-SNAPSHOT.jar:4.0.0-beta-2-SNAPSHOT]
at
org.apache.hadoop.hive.ql.parse.CalcitePlanner.logicalPlan(CalcitePlanner.java:1345)
~[hive-exec-4.0.0-beta-2-SNAPSHOT.jar:4.0.0-beta-2-SNAPSHOT]
at
org.apache.hadoop.hive.ql.parse.CalcitePlanner.genOPTree(CalcitePlanner.java:572)
~[hive-exec-4.0.0-beta-2-SNAPSHOT.jar:4.0.0-beta-2-SNAPSHOT]
at
org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.analyzeInternal(SemanticAnalyzer.java:13023)
~[hive-exec-4.0.0-beta-2-SNAPSHOT.jar:4.0.0-beta-2-SNAPSHOT]
at
org.apache.hadoop.hive.ql.parse.CalcitePlanner.analyzeInternal(CalcitePlanner.java:467)
~[hive-exec-4.0.0-beta-2-SNAPSHOT.jar:4.0.0-beta-2-SNAPSHOT]
at
org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.analyze(BaseSemanticAnalyzer.java:328)
~[hive-exec-4.0.0-beta-2-SNAPSHOT.jar:4.0.0-beta-2-SNAPSHOT]
at
org.apache.hadoop.hive.ql.parse.ExplainSemanticAnalyzer.analyzeInternal(ExplainSemanticAnalyzer.java:180)
~[hive-exec-4.0.0-beta-2-SNAPSHOT.jar:4.0.0-beta-2-SNAPSHOT]
at
org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.analyze(BaseSemanticAnalyzer.java:328)
~[hive-exec-4.0.0-beta-2-SNAPSHOT.jar:4.0.0-beta-2-SNAPSHOT]
at org.apache.hadoop.hive.ql.Compiler.analyze(Compiler.java:224)
~[hive-exec-4.0.0-beta-2-SNAPSHOT.jar:4.0.0-beta-2-SNAPSHOT]
at org.apache.hadoop.hive.ql.Compiler.compile(Compiler.java:107)
~[hive-exec-4.0.0-beta-2-SNAPSHOT.jar:4.0.0-beta-2-SNAPSHOT]
at org.apache.hadoop.hive.ql.Driver.compile(Driver.java:519)
~[hive-exec-4.0.0-beta-2-SNAPSHOT.jar:4.0.0-beta-2-SNAPSHOT]
at org.apache.hadoop.hive.ql.Driver.compileInternal(Driver.java:471)
~[hive-exec-4.0.0-beta-2-SNAPSHOT.jar:4.0.0-beta-2-SNAPSHOT]
at org.apache.hadoop.hive.ql.Driver.compileAndRespond(Driver.java:436)
~[hive-exec-4.0.0-beta-2-SNAPSHOT.jar:4.0.0-beta-2-SNAPSHOT]
at org.apache.hadoop.hive.ql.Driver.compileAndRespond(Driver.java:430)
~[hive-exec-4.0.0-beta-2-SNAPSHOT.jar:4.0.0-beta-2-SNAPSHOT]
at
org.apache.hadoop.hive.ql.reexec.ReExecDriver.compileAndRespond(ReExecDriver.java:121)
~[hive-exec-4.0.0-beta-2-SNAPSHOT.jar:4.0.0-beta-2-SNAPSHOT]
at
org.apache.hadoop.hive.ql.reexec.ReExecDriver.run(ReExecDriver.java:227)
~[hive-exec-4.0.0-beta-2-SNAPSHOT.jar:4.0.0-beta-2-SNAPSHOT]
at
org.apache.hadoop.hive.cli.CliDriver.processLocalCmd(CliDriver.java:257)
~[hive-cli-4.0.0-beta-2-SNAPSHOT.jar:?]
at org.apache.hadoop.hive.cli.CliDriver.processCmd1(CliDriver.java:201)
~[hive-cli-4.0.0-beta-2-SNAPSHOT.jar:?]
at org.apache.hadoop.hive.cli.CliDriver.processCmd(CliDriver.java:127)
~[hive-cli-4.0.0-beta-2-SNAPSHOT.jar:?]
at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:425)
~[hive-cli-4.0.0-beta-2-SNAPSHOT.jar:?]
at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:356)
~[hive-cli-4.0.0-beta-2-SNAPSHOT.jar:?]
at
org.apache.hadoop.hive.ql.QTestUtil.executeClientInternal(QTestUtil.java:733)
~[hive-it-util-4.0.0-beta-2-SNAPSHOT.jar:4.0.0-beta-2-SNAPSHOT]
at
org.apache.hadoop.hive.ql.QTestUtil.executeClient(QTestUtil.java:703)
~[hive-it-util-4.0.0-beta-2-SNAPSHOT.jar:4.0.0-beta-2-SNAPSHOT]
at
org.apache.hadoop.hive.cli.control.CoreCliDriver.runTest(CoreCliDriver.java:115)
~[hive-it-util-4.0.0-beta-2-SNAPSHOT.jar:4.0.0-beta-2-SNAPSHOT]
at
org.apache.hadoop.hive.cli.control.CliAdapter.runTest(CliAdapter.java:157)
~[hive-it-util-4.0.0-beta-2-SNAPSHOT.jar:4.0.0-beta-2-SNAPSHOT]
at
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver(TestMiniLlapLocalCliDriver.java:62)
~[test-classes/:?]
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
~[?:1.8.0_301]
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
~[?:1.8.0_301]
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
~[?:1.8.0_301]
at java.lang.reflect.Method.invoke(Method.java:498) ~[?:1.8.0_301]
at
org.junit.runners.model.FrameworkMethod$1.runReflectiveCall(FrameworkMethod.java:59)
~[junit-4.13.2.jar:4.13.2]
at
org.junit.internal.runners.model.ReflectiveCallable.run(ReflectiveCallable.java:12)
~[junit-4.13.2.jar:4.13.2]
at
org.junit.runners.model.FrameworkMethod.invokeExplosively(FrameworkMethod.java:56)
~[junit-4.13.2.jar:4.13.2]
at
org.junit.internal.runners.statements.InvokeMethod.evaluate(InvokeMethod.java:17)
~[junit-4.13.2.jar:4.13.2]
at
org.apache.hadoop.hive.cli.control.CliAdapter$2$1.evaluate(CliAdapter.java:135)
~[hive-it-util-4.0.0-beta-2-SNAPSHOT.jar:4.0.0-beta-2-SNAPSHOT]
at org.junit.runners.ParentRunner$3.evaluate(ParentRunner.java:306)
~[junit-4.13.2.jar:4.13.2]
at
org.junit.runners.BlockJUnit4ClassRunner$1.evaluate(BlockJUnit4ClassRunner.java:100)
~[junit-4.13.2.jar:4.13.2]
at org.junit.runners.ParentRunner.runLeaf(ParentRunner.java:366)
~[junit-4.13.2.jar:4.13.2]
at
org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:103)
~[junit-4.13.2.jar:4.13.2]
at
org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:63)
~[junit-4.13.2.jar:4.13.2]
at org.junit.runners.ParentRunner$4.run(ParentRunner.java:331)
~[junit-4.13.2.jar:4.13.2]
at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:79)
~[junit-4.13.2.jar:4.13.2]
at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:329)
~[junit-4.13.2.jar:4.13.2]
at org.junit.runners.ParentRunner.access$100(ParentRunner.java:66)
~[junit-4.13.2.jar:4.13.2]
at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:293)
~[junit-4.13.2.jar:4.13.2]
at org.junit.runners.ParentRunner.run(ParentRunner.java:413)
~[junit-4.13.2.jar:4.13.2]
at org.junit.runners.Suite.runChild(Suite.java:128)
~[junit-4.13.2.jar:4.13.2]
at org.junit.runners.Suite.runChild(Suite.java:27)
~[junit-4.13.2.jar:4.13.2]
at org.junit.runners.ParentRunner$4.run(ParentRunner.java:331)
~[junit-4.13.2.jar:4.13.2]
at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:79)
~[junit-4.13.2.jar:4.13.2]
at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:329)
~[junit-4.13.2.jar:4.13.2]
at org.junit.runners.ParentRunner.access$100(ParentRunner.java:66)
~[junit-4.13.2.jar:4.13.2]
at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:293)
~[junit-4.13.2.jar:4.13.2]
at
org.apache.hadoop.hive.cli.control.CliAdapter$1$1.evaluate(CliAdapter.java:95)
~[hive-it-util-4.0.0-beta-2-SNAPSHOT.jar:4.0.0-beta-2-SNAPSHOT]
at org.junit.rules.RunRules.evaluate(RunRules.java:20)
~[junit-4.13.2.jar:4.13.2]
at org.junit.runners.ParentRunner$3.evaluate(ParentRunner.java:306)
~[junit-4.13.2.jar:4.13.2]
at org.junit.runners.ParentRunner.run(ParentRunner.java:413)
~[junit-4.13.2.jar:4.13.2]
at
org.apache.maven.surefire.junit4.JUnit4Provider.execute(JUnit4Provider.java:365)
~[surefire-junit4-3.0.0-M4.jar:3.0.0-M4]
at
org.apache.maven.surefire.junit4.JUnit4Provider.executeWithRerun(JUnit4Provider.java:273)
~[surefire-junit4-3.0.0-M4.jar:3.0.0-M4]
at
org.apache.maven.surefire.junit4.JUnit4Provider.executeTestSet(JUnit4Provider.java:238)
~[surefire-junit4-3.0.0-M4.jar:3.0.0-M4]
at
org.apache.maven.surefire.junit4.JUnit4Provider.invoke(JUnit4Provider.java:159)
~[surefire-junit4-3.0.0-M4.jar:3.0.0-M4]
at
org.apache.maven.surefire.booter.ForkedBooter.runSuitesInProcess(ForkedBooter.java:377)
~[surefire-booter-3.0.0-M4.jar:3.0.0-M4]
at
org.apache.maven.surefire.booter.ForkedBooter.execute(ForkedBooter.java:138)
~[surefire-booter-3.0.0-M4.jar:3.0.0-M4]
at
org.apache.maven.surefire.booter.ForkedBooter.run(ForkedBooter.java:465)
~[surefire-booter-3.0.0-M4.jar:3.0.0-M4]
at
org.apache.maven.surefire.booter.ForkedBooter.main(ForkedBooter.java:451)
~[surefire-booter-3.0.0-M4.jar:3.0.0-M4]
{code}
So Calcite does not support non-boolean filter expression and the non-cbo path
treats string literal as true.
> Query Filter with OR condition updates every record in the table
> ----------------------------------------------------------------
>
> Key: HIVE-27754
> URL: https://issues.apache.org/jira/browse/HIVE-27754
> Project: Hive
> Issue Type: Bug
> Reporter: Simhadri Govindappa
> Assignee: Simhadri Govindappa
> Priority: Major
>
>
> {noformat}
> UPDATE customers_man SET customer_id=22 WHERE last_name='Pierce' OR 'Taylor'
> ;{noformat}
> After the above statement, all the records are updated. The condition
> {{'Taylor'}} is a constant string, and it will always evaluate to true
> because it's a non-empty string. So, effectively, {{UPDATE}} statement is
> updating all rows in the {{customers_man.}}
> {{}}
> {{Repro: }}
> {noformat}
> create table customers_man (customer_id bigint, first_name string)
> PARTITIONED BY (last_name string) STORED AS orc TBLPROPERTIES
> ('transactional'='true');
> insert into customers_man values(1, "Joanna", "Pierce"),(1, "Sharon",
> "Taylor"), (2, "Joanna", "Silver"), (2, "Bob", "Silver"), (2, "Susan",
> "Morrison") ,(2, "Jake", "Donnel") , (3, "Blake", "Burr"), (3, "Trudy",
> "Johnson"), (3, "Trudy", "Henderson");
> select * from customers_man;
>
> +----------------------------+---------------------------+--------------------------+
> | customers_man.customer_id | customers_man.first_name |
> customers_man.last_name |
>
> +----------------------------+---------------------------+--------------------------+
> | 3 | Blake | Burr
> |
> | 2 | Jake | Donnel
> |
> | 3 | Trudy | Henderson
> |
> | 3 | Trudy | Johnson
> |
> | 2 | Susan | Morrison
> |
> | 1 | Joanna | Pierce
> |
> | 2 | Joanna | Silver
> |
> | 2 | Bob | Silver
> |
> | 1 | Sharon | Taylor
> |
>
> +----------------------------+---------------------------+--------------------------+
> UPDATE customers_man SET customer_id=22 WHERE last_name='Pierce' OR
> last_name='Taylor' ;
> select * from customers_man;
>
> +----------------------------+---------------------------+--------------------------+
> | customers_man.customer_id | customers_man.first_name |
> customers_man.last_name |
>
> +----------------------------+---------------------------+--------------------------+
> | 3 | Blake | Burr
> |
> | 2 | Jake | Donnel
> |
> | 3 | Trudy | Henderson
> |
> | 3 | Trudy | Johnson
> |
> | 2 | Susan | Morrison
> |
> | 22 | Joanna | Pierce
> |
> | 2 | Joanna | Silver
> |
> | 2 | Bob | Silver
> |
> | 22 | Sharon | Taylor
> |
>
> +----------------------------+---------------------------+--------------------------+
> UPDATE customers_man SET customer_id=22 WHERE last_name='Pierce' OR
> 'Taylor' ;
> select * from customers_man;
>
> +----------------------------+---------------------------+--------------------------+
> | customers_man.customer_id | customers_man.first_name |
> customers_man.last_name |
>
> +----------------------------+---------------------------+--------------------------+
> | 22 | Blake | Burr
> |
> | 22 | Jake | Donnel
> |
> | 22 | Trudy | Henderson
> |
> | 22 | Trudy | Johnson
> |
> | 22 | Susan | Morrison
> |
> | 22 | Joanna | Pierce
> |
> | 22 | Joanna | Silver
> |
> | 22 | Bob | Silver
> |
> | 22 | Sharon | Taylor
> |
>
> +----------------------------+---------------------------+--------------------------+
> --- simpler repro
> UPDATE customers_man SET customer_id=23 WHERE true;
> select * from customers_man;
> +----------------------------+---------------------------+--------------------------+
> | customers_man.customer_id | customers_man.first_name |
> customers_man.last_name |
> +----------------------------+---------------------------+--------------------------+
> | 23 | Blake | Burr
> |
> | 23 | Jake | Donnel
> |
> | 23 | Trudy | Henderson
> |
> | 23 | Trudy | Johnson
> |
> | 23 | Susan | Morrison
> |
> | 23 | Joanna | Pierce
> |
> | 23 | Joanna | Silver
> |
> | 23 | Bob | Silver
> |
> | 23 | Sharon | Taylor
> |
> +----------------------------+---------------------------+--------------------------+{noformat}
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
