Description
Unable to use Hive meta-store in pyspark shell. Tried both HiveContext and SparkSession. Both failed. It always uses in-memory catalog.
Method 1: Using SparkSession
>>> from pyspark.sql import SparkSession
>>> spark = SparkSession.builder.enableHiveSupport().getOrCreate()
>>> spark.sql("CREATE TABLE IF NOT EXISTS src (key INT, value STRING)")
DataFrame[]
>>> spark.sql("LOAD DATA LOCAL INPATH 'examples/src/main/resources/kv1.txt' INTO TABLE src")
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/Users/xiaoli/IdeaProjects/sparkDelivery/python/pyspark/sql/session.py", line 494, in sql
return DataFrame(self._jsparkSession.sql(sqlQuery), self._wrapped)
File "/Users/xiaoli/IdeaProjects/sparkDelivery/python/lib/py4j-0.10.1-src.zip/py4j/java_gateway.py", line 933, in __call__
File "/Users/xiaoli/IdeaProjects/sparkDelivery/python/pyspark/sql/utils.py", line 57, in deco
return f(*a, **kw)
File "/Users/xiaoli/IdeaProjects/sparkDelivery/python/lib/py4j-0.10.1-src.zip/py4j/protocol.py", line 312, in get_return_value
py4j.protocol.Py4JJavaError: An error occurred while calling o21.sql.
: java.lang.UnsupportedOperationException: loadTable is not implemented
at org.apache.spark.sql.catalyst.catalog.InMemoryCatalog.loadTable(InMemoryCatalog.scala:297)
at org.apache.spark.sql.catalyst.catalog.SessionCatalog.loadTable(SessionCatalog.scala:280)
at org.apache.spark.sql.execution.command.LoadData.run(tables.scala:263)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:57)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:55)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:69)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:114)
at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:85)
at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:85)
at org.apache.spark.sql.Dataset.<init>(Dataset.scala:187)
at org.apache.spark.sql.Dataset.<init>(Dataset.scala:168)
at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:63)
at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:541)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:237)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:280)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:128)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:211)
at java.lang.Thread.run(Thread.java:745)
Method 2: Using HiveContext:
>>> from pyspark.sql import HiveContext
>>> sqlContext = HiveContext(sc)
>>> sqlContext.sql("CREATE TABLE IF NOT EXISTS src (key INT, value STRING)")
DataFrame[]
>>> sqlContext.sql("LOAD DATA LOCAL INPATH 'examples/src/main/resources/kv1.txt' INTO TABLE src")
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/Users/xiaoli/IdeaProjects/sparkDelivery/python/pyspark/sql/context.py", line 346, in sql
return self.sparkSession.sql(sqlQuery)
File "/Users/xiaoli/IdeaProjects/sparkDelivery/python/pyspark/sql/session.py", line 494, in sql
return DataFrame(self._jsparkSession.sql(sqlQuery), self._wrapped)
File "/Users/xiaoli/IdeaProjects/sparkDelivery/python/lib/py4j-0.10.1-src.zip/py4j/java_gateway.py", line 933, in __call__
File "/Users/xiaoli/IdeaProjects/sparkDelivery/python/pyspark/sql/utils.py", line 57, in deco
return f(*a, **kw)
File "/Users/xiaoli/IdeaProjects/sparkDelivery/python/lib/py4j-0.10.1-src.zip/py4j/protocol.py", line 312, in get_return_value
py4j.protocol.Py4JJavaError: An error occurred while calling o21.sql.
: java.lang.UnsupportedOperationException: loadTable is not implemented
at org.apache.spark.sql.catalyst.catalog.InMemoryCatalog.loadTable(InMemoryCatalog.scala:297)
at org.apache.spark.sql.catalyst.catalog.SessionCatalog.loadTable(SessionCatalog.scala:280)
at org.apache.spark.sql.execution.command.LoadData.run(tables.scala:263)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:57)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:55)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:69)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:114)
at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:85)
at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:85)
at org.apache.spark.sql.Dataset.<init>(Dataset.scala:187)
at org.apache.spark.sql.Dataset.<init>(Dataset.scala:168)
at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:63)
at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:541)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:237)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:280)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:128)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:211)
at java.lang.Thread.run(Thread.java:745)
Attachments
Issue Links
- blocks
-
SPARK-15396
[Spark] [SQL] [DOC] It can't connect hive metastore database
-
- Resolved
-
- relates to
-
SPARK-15345 SparkSession's conf doesn't take effect when there's already an existing SparkContext
-
- Closed
-
- links to
