我尝试使用 pyspark 和 hive 读取 hive ACID ORC 表转储文件。 转储文件架构如下。
struct<
operation: int,
originalTransaction: bigInt,
bucket: int,
rowId: bigInt,
currentTransaction: bigInt,
row: struct<...>
>
尝试使用版本 > 3.0 的 pyspark 时，但无法读取行列。 如果我用数据框保存兽人数据并尝试读取“行”列，则会发生错误。
# Create SparkSession
spark = SparkSession.builder \
.appName("Read Hive ACID ORC File") \
.enableHiveSupport() \
.getOrCreate()
# Hive ACID ORC path
orc_file_path = "hdfs://~~"
# read ORC file
df = spark.read.format("orc").load(orc_file_path)
df.show(truncate=False, n=5)
# error occurred here!
df.select('row').show()
Py4JJavaError: An error occurred while calling o285.showString.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 15.0 failed 4 times, most recent failure: Lost task 0.3 in stage 15.0 (TID 39) (ac3d0x2011.bdp.bdata.ai executor 1): java.lang.ArrayIndexOutOfBoundsException: 1
at org.apache.orc.impl.TreeReaderFactory$StructTreeReader.nextBatch(TreeReaderFactory.java:2055)
at org.apache.orc.impl.RecordReaderImpl.nextBatch(RecordReaderImpl.java:1324)
at org.apache.spark.sql.execution.datasources.orc.OrcColumnarBatchReader.nextBatch(OrcColumnarBatchReader.java:196)
at org.apache.spark.sql.execution.datasources.orc.OrcColumnarBatchReader.nextKeyValue(OrcColumnarBatchReader.java:99)
at org.apache.spark.sql.execution.datasources.RecordReaderIterator.hasNext(RecordReaderIterator.scala:37)
at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext(FileScanRDD.scala:93)
at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.nextIterator(FileScanRDD.scala:173)
at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext(FileScanRDD.scala:93)
at org.apache.spark.sql.execution.FileSourceScanExec$$anon$1.hasNext(DataSourceScanExec.scala:503)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.columnartorow_nextBatch_0$(Unknown Source)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenExec$$anon$1.hasNext(WholeStageCodegenExec.scala:755)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:345)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:898)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:898)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:131)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:497)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1439)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:500)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2258)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2207)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2206)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2206)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1079)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1079)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1079)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2445)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2387)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2376)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:868)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2196)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2217)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2236)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:472)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:425)
at org.apache.spark.sql.execution.CollectLimitExec.executeCollect(limit.scala:47)
at org.apache.spark.sql.Dataset.collectFromPlan(Dataset.scala:3696)
at org.apache.spark.sql.Dataset.$anonfun$head$1(Dataset.scala:2722)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:3687)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:103)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:163)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:90)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:775)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3685)
at org.apache.spark.sql.Dataset.head(Dataset.scala:2722)
at org.apache.spark.sql.Dataset.take(Dataset.scala:2929)
at org.apache.spark.sql.Dataset.getRows(Dataset.scala:301)
at org.apache.spark.sql.Dataset.showString(Dataset.scala:338)
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:745)
Caused by: java.lang.ArrayIndexOutOfBoundsException: 1
at org.apache.orc.impl.TreeReaderFactory$StructTreeReader.nextBatch(TreeReaderFactory.java:2055)
at org.apache.orc.impl.RecordReaderImpl.nextBatch(RecordReaderImpl.java:1324)
at org.apache.spark.sql.execution.datasources.orc.OrcColumnarBatchReader.nextBatch(OrcColumnarBatchReader.java:196)
at org.apache.spark.sql.execution.datasources.orc.OrcColumnarBatchReader.nextKeyValue(OrcColumnarBatchReader.java:99)
at org.apache.spark.sql.execution.datasources.RecordReaderIterator.hasNext(RecordReaderIterator.scala:37)
at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext(FileScanRDD.scala:93)
at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.nextIterator(FileScanRDD.scala:173)
at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext(FileScanRDD.scala:93)
at org.apache.spark.sql.execution.FileSourceScanExec$$anon$1.hasNext(DataSourceScanExec.scala:503)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.columnartorow_nextBatch_0$(Unknown Source)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenExec$$anon$1.hasNext(WholeStageCodegenExec.scala:755)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:345)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:898)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:898)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:131)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:497)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1439)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:500)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
... 1 more
(<class 'py4j.protocol.Py4JJavaError'>, Py4JJavaError('An error occurred while calling o285.showString.\n', JavaObject id=o286), <traceback object at 0x7f5464fe0108>)
如果我使用如下架构定义外部配置单元表，
CREATE EXTERNAL TABLE IF NOT EXISTS fdp__db_ec_tmp_test.payment_type_filter_file_full
(
operation INT,
originaltransaction BIGINT,
bucket INT,
rowid BIGINT,
currenttransaction BIGINT,
`row` STRUCT<id: INT, value: STRING>
)
STORED AS ORC
LOCATION '{HDFS_LOCATION}'
;
java.io.IOException: org.apache.orc.impl.SchemaEvolution$IllegalEvolutionException: ORC does not support type conversion from file type string (12) to reader type struct<id: int, value: string>(12)
感谢您提前的帮助！！！！