Gopinath created HIVE-27462:
-------------------------------
Summary: hive.create.as.external.legacy does not respect KAFKA
storage handler tables
Key: HIVE-27462
URL: https://issues.apache.org/jira/browse/HIVE-27462
Project: Hive
Issue Type: Bug
Reporter: Gopinath
hive.create.as.external.legacy does not respect KAFKA storage handler tables.
{noformat}
0: jdbc:hive2://host> set hive.create.as.external.legacy=true;
No rows affected (0.063 seconds)
0: jdbc:hive2://host> CREATE TABLE kafka_table
. . . . . . . . . . . . . . . . . . . . . . .> (name string, address
struct<a:string,c:string,e:string>)
. . . . . . . . . . . . . . . . . . . . . . .> STORED BY
'org.apache.hadoop.hive.kafka.KafkaStorageHandler'
. . . . . . . . . . . . . . . . . . . . . . .> TBLPROPERTIES
. . . . . . . . . . . . . . . . . . . . . . .> ("kafka.topic" = "dummytopic1",
"kafka.bootstrap.servers"="local:9092");
INFO : Compiling
command(queryId=hive_20230623094735_fe15596e-0f83-4b55-a528-fe119291f495):
CREATE TABLE kafka_table
(name string, address struct<a:string,c:string,e:string>)
STORED BY 'org.apache.hadoop.hive.kafka.KafkaStorageHandler'
TBLPROPERTIES
("kafka.topic" = "dummytopic1", "kafka.bootstrap.servers"="local:9092")
INFO : Semantic Analysis Completed (retrial = false)
INFO : Created Hive schema: Schema(fieldSchemas:null, properties:null)
INFO : Completed compiling
command(queryId=hive_20230623094735_fe15596e-0f83-4b55-a528-fe119291f495); Time
taken: 0.019 seconds
INFO : Executing
command(queryId=hive_20230623094735_fe15596e-0f83-4b55-a528-fe119291f495):
CREATE TABLE kafka_table
(name string, address struct<a:string,c:string,e:string>)
STORED BY 'org.apache.hadoop.hive.kafka.KafkaStorageHandler'
TBLPROPERTIES
("kafka.topic" = "dummytopic1",
"kafka.bootstrap.servers"="c1757-node4.coelab.cloudera.com:9092")
INFO : Starting task [Stage-0:DDL] in serial mode
ERROR : Failed
org.apache.hadoop.hive.ql.metadata.HiveException:
MetaException(message:org.apache.hadoop.hive.kafka.KafkaStorageHandler supports
only EXTERNAL_TABLE)
at org.apache.hadoop.hive.ql.metadata.Hive.createTable(Hive.java:1363)
at org.apache.hadoop.hive.ql.metadata.Hive.createTable(Hive.java:1368)
at
org.apache.hadoop.hive.ql.ddl.table.create.CreateTableOperation.createTableNonReplaceMode(CreateTableOperation.java:158)
at
org.apache.hadoop.hive.ql.ddl.table.create.CreateTableOperation.execute(CreateTableOperation.java:116)
at org.apache.hadoop.hive.ql.ddl.DDLTask.execute(DDLTask.java:84)
at org.apache.hadoop.hive.ql.exec.Task.executeTask(Task.java:214)
at
org.apache.hadoop.hive.ql.exec.TaskRunner.runSequential(TaskRunner.java:105)
at org.apache.hadoop.hive.ql.Executor.launchTask(Executor.java:354)
at org.apache.hadoop.hive.ql.Executor.launchTasks(Executor.java:327)
at org.apache.hadoop.hive.ql.Executor.runTasks(Executor.java:244)
at org.apache.hadoop.hive.ql.Executor.execute(Executor.java:105)
at org.apache.hadoop.hive.ql.Driver.execute(Driver.java:367)
at org.apache.hadoop.hive.ql.Driver.runInternal(Driver.java:205)
at org.apache.hadoop.hive.ql.Driver.run(Driver.java:154)
at org.apache.hadoop.hive.ql.Driver.run(Driver.java:149)
at org.apache.hadoop.hive.ql.reexec.ReExecDriver.run(ReExecDriver.java:185)
at org.apache.hadoop.hive.ql.reexec.ReExecDriver.run(ReExecDriver.java:228)
at org.apache.hadoop.hive.cli.CliDriver.processLocalCmd(CliDriver.java:257)
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:425)
at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:356)
at
org.apache.hadoop.hive.ql.QTestUtil.executeClientInternal(QTestUtil.java:733)
at org.apache.hadoop.hive.ql.QTestUtil.executeClient(QTestUtil.java:703)
at
org.apache.hadoop.hive.cli.control.CoreCliDriver.runTest(CoreCliDriver.java:115)
at
org.apache.hadoop.hive.cli.control.CliAdapter.runTest(CliAdapter.java:157)
at
org.apache.hadoop.hive.cli.TestMiniLlapCliDriver.testCliDriver(TestMiniLlapCliDriver.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$3.evaluate(ParentRunner.java:306)
at org.junit.runners.ParentRunner.run(ParentRunner.java:413)
at
org.apache.maven.surefire.junit4.JUnit4Provider.execute(JUnit4Provider.java:365)
at
org.apache.maven.surefire.junit4.JUnit4Provider.executeWithRerun(JUnit4Provider.java:273)
at
org.apache.maven.surefire.junit4.JUnit4Provider.executeTestSet(JUnit4Provider.java:238)
at
org.apache.maven.surefire.junit4.JUnit4Provider.invoke(JUnit4Provider.java:159)
at
org.apache.maven.surefire.booter.ForkedBooter.runSuitesInProcess(ForkedBooter.java:377)
at
org.apache.maven.surefire.booter.ForkedBooter.execute(ForkedBooter.java:138)
at org.apache.maven.surefire.booter.ForkedBooter.run(ForkedBooter.java:465)
at org.apache.maven.surefire.booter.ForkedBooter.main(ForkedBooter.java:451)
Caused by:
MetaException(message:org.apache.hadoop.hive.kafka.KafkaStorageHandler supports
only EXTERNAL_TABLE)
at
org.apache.hadoop.hive.kafka.KafkaStorageHandler.preCreateTable(KafkaStorageHandler.java:386)
at
org.apache.hadoop.hive.metastore.HiveMetaStoreClient.createTable(HiveMetaStoreClient.java:1459)
at
org.apache.hadoop.hive.metastore.HiveMetaStoreClient.createTable(HiveMetaStoreClient.java:1435)
at
org.apache.hadoop.hive.metastore.HiveMetaStoreClient.createTable(HiveMetaStoreClient.java:1426)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at
org.apache.hadoop.hive.metastore.RetryingMetaStoreClient.invoke(RetryingMetaStoreClient.java:213)
at com.sun.proxy.$Proxy133.createTable(Unknown Source)
at org.apache.hadoop.hive.ql.metadata.Hive.createTable(Hive.java:1352)
... 65 more{noformat}
The same has been working for HBASE storage handler tables.
{noformat}
0: jdbc:hive2://host> CREATE TABLE IF NOT EXISTS pagecounts_hbase (rowkey
STRING, pageviews STRING, bytes STRING)
. . . . . . . . . . . . . . . . . . . . . . .> STORED BY
'org.apache.hadoop.hive.hbase.HBaseStorageHandler'
. . . . . . . . . . . . . . . . . . . . . . .> WITH SERDEPROPERTIES
('hbase.columns.mapping' = ':key,f:c1,f:c2')
. . . . . . . . . . . . . . . . . . . . . . .> TBLPROPERTIES
('hbase.table.name' = 'pagecounts');
INFO : Compiling
command(queryId=hive_20230623093945_0c96e28f-33fb-41a8-b817-534300e768b5):
CREATE TABLE IF NOT EXISTS pagecounts_hbase (rowkey STRING, pageviews STRING,
bytes STRING)
STORED BY 'org.apache.hadoop.hive.hbase.HBaseStorageHandler'
WITH SERDEPROPERTIES ('hbase.columns.mapping' = ':key,f:c1,f:c2')
TBLPROPERTIES ('hbase.table.name' = 'pagecounts')
INFO : Semantic Analysis Completed (retrial = false)
INFO : Created Hive schema: Schema(fieldSchemas:null, properties:null)
INFO : Completed compiling
command(queryId=hive_20230623093945_0c96e28f-33fb-41a8-b817-534300e768b5); Time
taken: 0.059 seconds
INFO : Executing
command(queryId=hive_20230623093945_0c96e28f-33fb-41a8-b817-534300e768b5):
CREATE TABLE IF NOT EXISTS pagecounts_hbase (rowkey STRING, pageviews STRING,
bytes STRING)
STORED BY 'org.apache.hadoop.hive.hbase.HBaseStorageHandler'
WITH SERDEPROPERTIES ('hbase.columns.mapping' = ':key,f:c1,f:c2')
TBLPROPERTIES ('hbase.table.name' = 'pagecounts')
INFO : Starting task [Stage-0:DDL] in serial mode
INFO : Completed executing
command(queryId=hive_20230623093945_0c96e28f-33fb-41a8-b817-534300e768b5); Time
taken: 1.473 seconds
INFO : OK
No rows affected (1.607 seconds)
0: jdbc:hive2://host> show create table pagecounts_hbase;
INFO : Compiling
command(queryId=hive_20230623093957_0a038864-cac5-4b60-a78f-1b0a8c5a04af): show
create table pagecounts_hbase
INFO : Semantic Analysis Completed (retrial = false)
INFO : Created Hive schema:
Schema(fieldSchemas:[FieldSchema(name:createtab_stmt, type:string, comment:from
deserializer)], properties:null)
INFO : Completed compiling
command(queryId=hive_20230623093957_0a038864-cac5-4b60-a78f-1b0a8c5a04af); Time
taken: 0.051 seconds
INFO : Executing
command(queryId=hive_20230623093957_0a038864-cac5-4b60-a78f-1b0a8c5a04af): show
create table pagecounts_hbase
INFO : Starting task [Stage-0:DDL] in serial mode
INFO : Completed executing
command(queryId=hive_20230623093957_0a038864-cac5-4b60-a78f-1b0a8c5a04af); Time
taken: 0.051 seconds
INFO : OK
+----------------------------------------------------+
| createtab_stmt |
+----------------------------------------------------+
| CREATE EXTERNAL TABLE `pagecounts_hbase`( |
| `rowkey` string COMMENT '', |
| `pageviews` string COMMENT '', |
| `bytes` string COMMENT '') |
| ROW FORMAT SERDE |
| 'org.apache.hadoop.hive.hbase.HBaseSerDe' |
| STORED BY |
| 'org.apache.hadoop.hive.hbase.HBaseStorageHandler' |
| WITH SERDEPROPERTIES ( |
| 'hbase.columns.mapping'=':key,f:c1,f:c2', |
| 'serialization.format'='1') |
| TBLPROPERTIES ( |
| 'TRANSLATED_TO_EXTERNAL'='TRUE', |
| 'bucketing_version'='2', |
| 'external.table.purge'='TRUE', |
| 'hbase.table.name'='pagecounts', |
| 'transient_lastDdlTime'='1687513187') |
+----------------------------------------------------+{noformat}
Even after enabling hive.create.as.external.legacy , kafka storage handler
expects EXTERNAL keyword.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)