agoswami0915 opened a new issue, #4600:
URL: https://github.com/apache/iceberg/issues/4600
While running the insert table command [spark.sql("""INSERT INTO
dev.db.iceberg_prefix VALUES (1, "Pizza", "orders")""")] for a table created
with 'write.object-storage.enabled'=true, getting a NullPointerException error.
Table DDL:
spark.sql("""CREATE TABLE dev.db.iceberg_prefix (
id bigint,
data string,
category string)
USING iceberg
OPTIONS (
'write.object-storage.enabled'=true,
'write.data.path'='s3://iceberg-hive-warehouse/warehouse-location')
PARTITIONED BY (category)""")
Error:
An error was encountered:
An error occurred while calling o89.sql.
: java.lang.NullPointerException
at
org.apache.iceberg.LocationProviders.stripTrailingSlash(LocationProviders.java:135)
at
org.apache.iceberg.LocationProviders.access$000(LocationProviders.java:34)
at
org.apache.iceberg.LocationProviders$ObjectStoreLocationProvider.<init>(LocationProviders.java:99)
at
org.apache.iceberg.LocationProviders.locationsFor(LocationProviders.java:65)
at
org.apache.iceberg.hadoop.HadoopTableOperations.locationProvider(HadoopTableOperations.java:182)
at org.apache.iceberg.BaseTable.locationProvider(BaseTable.java:224)
at
org.apache.iceberg.SerializableTable.<init>(SerializableTable.java:78)
at
org.apache.iceberg.SerializableTable.copyOf(SerializableTable.java:91)
at
org.apache.iceberg.spark.source.SparkWrite.createWriterFactory(SparkWrite.java:179)
at
org.apache.iceberg.spark.source.SparkWrite.access$700(SparkWrite.java:92)
at
org.apache.iceberg.spark.source.SparkWrite$BaseBatchWrite.createBatchWriterFactory(SparkWrite.java:233)
at
org.apache.spark.sql.execution.datasources.v2.V2TableWriteExec.writeWithV2(WriteToDataSourceV2Exec.scala:348)
at
org.apache.spark.sql.execution.datasources.v2.V2TableWriteExec.writeWithV2$(WriteToDataSourceV2Exec.scala:336)
at
org.apache.spark.sql.execution.datasources.v2.AppendDataExec.writeWithV2(WriteToDataSourceV2Exec.scala:218)
at
org.apache.spark.sql.execution.datasources.v2.AppendDataExec.run(WriteToDataSourceV2Exec.scala:225)
at
org.apache.spark.sql.execution.datasources.v2.V2CommandExec.result$lzycompute(V2CommandExec.scala:40)
at
org.apache.spark.sql.execution.datasources.v2.V2CommandExec.result(V2CommandExec.scala:40)
at
org.apache.spark.sql.execution.datasources.v2.V2CommandExec.executeCollect(V2CommandExec.scala:46)
at
org.apache.spark.sql.Dataset.$anonfun$logicalPlan$1(Dataset.scala:230)
at
org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:3751)
at
org.apache.spark.sql.catalyst.QueryPlanningTracker$.withTracker(QueryPlanningTracker.scala:107)
at
org.apache.spark.sql.execution.SQLExecution$.withTracker(SQLExecution.scala:232)
at
org.apache.spark.sql.execution.SQLExecution$.executeQuery$1(SQLExecution.scala:110)
at
org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:135)
at
org.apache.spark.sql.catalyst.QueryPlanningTracker$.withTracker(QueryPlanningTracker.scala:107)
at
org.apache.spark.sql.execution.SQLExecution$.withTracker(SQLExecution.scala:232)
at
org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:135)
at
org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:253)
at
org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:134)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:775)
at
org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:68)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3749)
at org.apache.spark.sql.Dataset.<init>(Dataset.scala:230)
at org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:101)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:775)
at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:98)
at
org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:618)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:775)
at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:613)
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 py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:282)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:238)
at java.lang.Thread.run(Thread.java:750)
Traceback (most recent call last):
File "/usr/lib/spark/python/lib/pyspark.zip/pyspark/sql/session.py", line
723, in sql
return DataFrame(self._jsparkSession.sql(sqlQuery), self._wrapped)
File "/usr/lib/spark/python/lib/py4j-0.10.9-src.zip/py4j/java_gateway.py",
line 1305, in __call__
answer, self.gateway_client, self.target_id, self.name)
File "/usr/lib/spark/python/lib/pyspark.zip/pyspark/sql/utils.py", line
111, in deco
return f(*a, **kw)
File "/usr/lib/spark/python/lib/py4j-0.10.9-src.zip/py4j/protocol.py",
line 328, in get_return_value
format(target_id, ".", name), value)
py4j.protocol.Py4JJavaError: An error occurred while calling o89.sql.
: java.lang.NullPointerException
at
org.apache.iceberg.LocationProviders.stripTrailingSlash(LocationProviders.java:135)
at
org.apache.iceberg.LocationProviders.access$000(LocationProviders.java:34)
at
org.apache.iceberg.LocationProviders$ObjectStoreLocationProvider.<init>(LocationProviders.java:99)
at
org.apache.iceberg.LocationProviders.locationsFor(LocationProviders.java:65)
at
org.apache.iceberg.hadoop.HadoopTableOperations.locationProvider(HadoopTableOperations.java:182)
at org.apache.iceberg.BaseTable.locationProvider(BaseTable.java:224)
at
org.apache.iceberg.SerializableTable.<init>(SerializableTable.java:78)
at
org.apache.iceberg.SerializableTable.copyOf(SerializableTable.java:91)
at
org.apache.iceberg.spark.source.SparkWrite.createWriterFactory(SparkWrite.java:179)
at
org.apache.iceberg.spark.source.SparkWrite.access$700(SparkWrite.java:92)
at
org.apache.iceberg.spark.source.SparkWrite$BaseBatchWrite.createBatchWriterFactory(SparkWrite.java:233)
at
org.apache.spark.sql.execution.datasources.v2.V2TableWriteExec.writeWithV2(WriteToDataSourceV2Exec.scala:348)
at
org.apache.spark.sql.execution.datasources.v2.V2TableWriteExec.writeWithV2$(WriteToDataSourceV2Exec.scala:336)
at
org.apache.spark.sql.execution.datasources.v2.AppendDataExec.writeWithV2(WriteToDataSourceV2Exec.scala:218)
at
org.apache.spark.sql.execution.datasources.v2.AppendDataExec.run(WriteToDataSourceV2Exec.scala:225)
at
org.apache.spark.sql.execution.datasources.v2.V2CommandExec.result$lzycompute(V2CommandExec.scala:40)
at
org.apache.spark.sql.execution.datasources.v2.V2CommandExec.result(V2CommandExec.scala:40)
at
org.apache.spark.sql.execution.datasources.v2.V2CommandExec.executeCollect(V2CommandExec.scala:46)
at
org.apache.spark.sql.Dataset.$anonfun$logicalPlan$1(Dataset.scala:230)
at
org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:3751)
at
org.apache.spark.sql.catalyst.QueryPlanningTracker$.withTracker(QueryPlanningTracker.scala:107)
at
org.apache.spark.sql.execution.SQLExecution$.withTracker(SQLExecution.scala:232)
at
org.apache.spark.sql.execution.SQLExecution$.executeQuery$1(SQLExecution.scala:110)
at
org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:135)
at
org.apache.spark.sql.catalyst.QueryPlanningTracker$.withTracker(QueryPlanningTracker.scala:107)
at
org.apache.spark.sql.execution.SQLExecution$.withTracker(SQLExecution.scala:232)
at
org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:135)
at
org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:253)
at
org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:134)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:775)
at
org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:68)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3749)
at org.apache.spark.sql.Dataset.<init>(Dataset.scala:230)
at org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:101)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:775)
at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:98)
at
org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:618)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:775)
at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:613)
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 py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:282)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:238)
at java.lang.Thread.run(Thread.java:750)
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
