У меня есть простой блок кода для записи, а затем чтения данных в формате Avro. Поскольку Avro lib уже встроена в Spark 2.4.x,
Запись файлов Avro прошла успешно, и файлы создаются в HDFS. Однако, исключение AbstractMethodError выбрасывается при чтении файлов. Кто-нибудь может поделиться со мной светом?
Я использовал внутреннюю библиотеку Spark, добавив пакет org.apache.spark: spark-avro_2.11: 2.4.1 в моем интерпретаторе Spark для нод Zeppelin.
Мой простой кодовый блок:
%pyspark
test_rows = [ Row(file_name = "test-guangzhou1", topic='camera1', timestamp=1, msg="Test1"), Row(file_name = "test-guangzhou1", topic='camera1', timestamp=2, msg="Test2"), Row(file_name = "test-guangzhou3", topic='camera3', timestamp=3, msg="Test3"), Row(file_name = "test-guangzhou1", topic='camera1', timestamp=4, msg="Test4") ]
test_df = spark.createDataFrame(test_rows)
test_df.write.format("avro")
.mode('overwrite').save("hdfs:///tmp/bag_parser279181359_3")
loaded_df = spark.read.format("avro").load('hdfs:///tmp/bag_parser279181359_3')
loaded_df.show()
Сообщение об ошибке, которое я увидел:
Py4JJavaError: An error occurred while calling o701.collectToPython.
: java.lang.AbstractMethodError
at org.apache.spark.sql.execution.FileSourceScanExec.inputRDD$lzycompute(DataSourceScanExec.scala:337)
at org.apache.spark.sql.execution.FileSourceScanExec.inputRDD(DataSourceScanExec.scala:331)
at org.apache.spark.sql.execution.FileSourceScanExec.inputRDDs(DataSourceScanExec.scala:357)
at org.apache.spark.sql.execution.WholeStageCodegenExec.doExecute(WholeStageCodegenExec.scala:627)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:137)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:133)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:161)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:158)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:133)
at org.apache.spark.sql.execution.SparkPlan.getByteArrayRdd(SparkPlan.scala:289)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:381)
at org.apache.spark.sql.execution.CollectLimitExec.executeCollect(limit.scala:38)
at org.apache.spark.sql.Dataset$$anonfun$collectToPython$1.apply(Dataset.scala:3259)
at org.apache.spark.sql.Dataset$$anonfun$collectToPython$1.apply(Dataset.scala:3256)
at org.apache.spark.sql.Dataset$$anonfun$53.apply(Dataset.scala:3373)
at org.apache.spark.sql.execution.SQLExecution$$anonfun$withNewExecutionId$1.apply(SQLExecution.scala:79)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:144)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:74)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3367)
at org.apache.spark.sql.Dataset.collectToPython(Dataset.scala:3256)
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:748)
(<class 'py4j.protocol.Py4JJavaError'>, Py4JJavaError(u'An error occurred while calling o701.collectToPython.\n', JavaObject id=o702), <traceback object at 0x7fc031b5c878>)