[
https://issues.apache.org/jira/browse/HUDI-3946?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Danny Chen resolved HUDI-3946.
------------------------------
> Validate option path in flink hudi sink
> ---------------------------------------
>
> Key: HUDI-3946
> URL: https://issues.apache.org/jira/browse/HUDI-3946
> Project: Apache Hudi
> Issue Type: Improvement
> Components: flink
> Reporter: Ruguo Yu
> Priority: Minor
> Labels: pull-request-available
> Fix For: 0.11.0, 0.11.1
>
>
> We should do a non-null check on option 'path'[{color:#ff0000}*1*{color}] in
> flink hudi sink so that flink can expose the 'path' problem as early as
> possible, instead of throwing the error[{color:#FF0000}*2*{color}] at runtime.
> [{color:#ff0000}*1*{color}]
> {code:java}
> CREATE TABLE t1(
> uuid VARCHAR(20) PRIMARY KEY NOT ENFORCED,
> name VARCHAR(10),
> age INT,
> ts TIMESTAMP(3),
> `partition` VARCHAR(20)
> )
> PARTITIONED BY (`partition`)
> WITH (
> 'connector' = 'hudi',
> 'path' = '${path}'
> );
> INSERT INTO t1 VALUES
> ('id1','Danny',23,TIMESTAMP '1970-01-01 00:00:01','par1'),
> ('id2','Stephen',33,TIMESTAMP '1970-01-01 00:00:02','par1'),
> ('id3','Julian',53,TIMESTAMP '1970-01-01 00:00:03','par2'),
> ('id4','Fabian',31,TIMESTAMP '1970-01-01 00:00:04','par2'),
> ('id5','Sophia',18,TIMESTAMP '1970-01-01 00:00:05','par3'),
> ('id6','Emma',20,TIMESTAMP '1970-01-01 00:00:06','par3'),
> ('id7','Bob',44,TIMESTAMP '1970-01-01 00:00:07','par4'),
> ('id8','Han',56,TIMESTAMP '1970-01-01 00:00:08','par4'); {code}
> [{color:#ff0000}*2*{color}]
> {code:java}
> Caused by: java.lang.IllegalArgumentException: Can not create a Path from a
> null string
> at org.apache.hadoop.fs.Path.checkPathArg(Path.java:122)
> ~[hadoop-common-2.7.6.jar:?]
> at org.apache.hadoop.fs.Path.<init>(Path.java:134)
> ~[hadoop-common-2.7.6.jar:?]
> at org.apache.hudi.common.fs.FSUtils.getFs(FSUtils.java:103)
> ~[hudi-flink1.14-bundle_2.11-0.11.0-rc1.jar:0.11.0-rc1]
> at
> org.apache.hudi.util.StreamerUtil.tableExists(StreamerUtil.java:289)
> ~[hudi-flink1.14-bundle_2.11-0.11.0-rc1.jar:0.11.0-rc1]
> at
> org.apache.hudi.util.StreamerUtil.initTableIfNotExists(StreamerUtil.java:258)
> ~[hudi-flink1.14-bundle_2.11-0.11.0-rc1.jar:0.11.0-rc1]
> at
> org.apache.hudi.sink.StreamWriteOperatorCoordinator.start(StreamWriteOperatorCoordinator.java:172)
> ~[hudi-flink1.14-bundle_2.11-0.11.0-rc1.jar:0.11.0-rc1]
> at
> org.apache.flink.runtime.operators.coordination.OperatorCoordinatorHolder.start(OperatorCoordinatorHolder.java:194)
> ~[flink-dist_2.11-1.14.2.jar:1.14.2]
> at
> org.apache.flink.runtime.scheduler.DefaultOperatorCoordinatorHandler.startAllOperatorCoordinators(DefaultOperatorCoordinatorHandler.java:85)
> ~[flink-dist_2.11-1.14.2.jar:1.14.2]
> at
> org.apache.flink.runtime.scheduler.SchedulerBase.startScheduling(SchedulerBase.java:584)
> ~[flink-dist_2.11-1.14.2.jar:1.14.2]
> at
> org.apache.flink.runtime.jobmaster.JobMaster.startScheduling(JobMaster.java:965)
> ~[flink-dist_2.11-1.14.2.jar:1.14.2]
> at
> org.apache.flink.runtime.jobmaster.JobMaster.startJobExecution(JobMaster.java:882)
> ~[flink-dist_2.11-1.14.2.jar:1.14.2]
> at
> org.apache.flink.runtime.jobmaster.JobMaster.onStart(JobMaster.java:389)
> ~[flink-dist_2.11-1.14.2.jar:1.14.2]
> at
> org.apache.flink.runtime.rpc.RpcEndpoint.internalCallOnStart(RpcEndpoint.java:181)
> ~[flink-dist_2.11-1.14.2.jar:1.14.2]
> at
> org.apache.flink.runtime.rpc.akka.AkkaRpcActor$StoppedState.lambda$start$0(AkkaRpcActor.java:624)
> ~[flink-rpc-akka_a8af7b4c-9c0c-4ac4-a1b1-1690068e50df.jar:1.14.2]
> at
> org.apache.flink.runtime.concurrent.akka.ClassLoadingUtils.runWithContextClassLoader(ClassLoadingUtils.java:68)
> ~[flink-rpc-akka_a8af7b4c-9c0c-4ac4-a1b1-1690068e50df.jar:1.14.2]
> at
> org.apache.flink.runtime.rpc.akka.AkkaRpcActor$StoppedState.start(AkkaRpcActor.java:623)
> ~[flink-rpc-akka_a8af7b4c-9c0c-4ac4-a1b1-1690068e50df.jar:1.14.2]
> ... 20 more {code}
--
This message was sent by Atlassian Jira
(v8.20.7#820007)
