我创建了Hive Avro表，并尝试从Pyspark读取它。基本上试图在Pyspark上的此Hive Avro表上运行基本查询，以进行一些分析。
from pyspark import SparkContext
from pyspark.sql import HiveContext
hive_context = HiveContext(sc)
test = hive_context.table("default.test_avro")
test.registerTempTable("test_temp")
hive_context.sql("select * from test_temp").show()
但是，我遇到以下错误。"飞行"是Avro模式中的嵌套记录。
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 0.0 failed 1 times, most recent failure: Lost task 0.0 in stage 0.0 (TID 0, localhost): org.apache.avro.AvroTypeException: Found test.net.flight, expecting union
at org.apache.avro.io.ResolvingDecoder.doAction(ResolvingDecoder.java:292)
at org.apache.avro.io.parsing.Parser.advance(Parser.java:88)
at org.apache.avro.io.ResolvingDecoder.readIndex(ResolvingDecoder.java:267)
at org.apache.avro.generic.GenericDatumReader.read(GenericDatumReader.java:155)
at org.apache.avro.generic.GenericDatumReader.readArray(GenericDatumReader.java:219)
at org.apache.avro.generic.GenericDatumReader.read(GenericDatumReader.java:153)
at org.apache.avro.generic.GenericDatumReader.read(GenericDatumReader.java:155)
at org.apache.avro.generic.GenericDatumReader.readField(GenericDatumReader.java:193)
at org.apache.avro.generic.GenericDatumReader.readRecord(GenericDatumReader.java:183)
at org.apache.avro.generic.GenericDatumReader.read(GenericDatumReader.java:151)
at org.apache.avro.generic.GenericDatumReader.read(GenericDatumReader.java:142)
at org.apache.hadoop.hive.serde2.avro.AvroDeserializer$SchemaReEncoder.reencode(AvroDeserializer.java:111)
at org.apache.hadoop.hive.serde2.avro.AvroDeserializer.deserialize(AvroDeserializer.java:175)
at org.apache.hadoop.hive.serde2.avro.AvroSerDe.deserialize(AvroSerDe.java:201)
at org.apache.spark.sql.hive.HadoopTableReader$$anonfun$fillObject$2.apply(TableReader.scala:381)
at org.apache.spark.sql.hive.HadoopTableReader$$anonfun$fillObject$2.apply(TableReader.scala:380)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$$anon$10.next(Iterator.scala:312)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
at scala.collection.AbstractIterator.to(Iterator.scala:1157)
at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$5.apply(SparkPlan.scala:215)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$5.apply(SparkPlan.scala:215)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1850)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1850)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1283)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1271)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1270)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1270)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697)
at scala.Option.foreach(Option.scala:236)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:697)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1496)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1458)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1447)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:567)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1824)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1837)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1850)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:215)
at org.apache.spark.sql.execution.Limit.executeCollect(basicOperators.scala:207)
at org.apache.spark.sql.DataFrame$$anonfun$collect$1.apply(DataFrame.scala:1385)
at org.apache.spark.sql.DataFrame$$anonfun$collect$1.apply(DataFrame.scala:1385)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:56)
at org.apache.spark.sql.DataFrame.withNewExecutionId(DataFrame.scala:1903)
at org.apache.spark.sql.DataFrame.collect(DataFrame.scala:1384)
at org.apache.spark.sql.DataFrame.head(DataFrame.scala:1314)
at org.apache.spark.sql.DataFrame.take(DataFrame.scala:1377)
at org.apache.spark.sql.DataFrame.showString(DataFrame.scala:178)
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:497)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:231)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:379)
at py4j.Gateway.invoke(Gateway.java:259)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:133)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:207)
at java.lang.Thread.run(Thread.java:745)
Caused by: org.apache.avro.AvroTypeException: Found test.net.flight, expecting union
at org.apache.avro.io.ResolvingDecoder.doAction(ResolvingDecoder.java:292)
at org.apache.avro.io.parsing.Parser.advance(Parser.java:88)
at org.apache.avro.io.ResolvingDecoder.readIndex(ResolvingDecoder.java:267)
at org.apache.avro.generic.GenericDatumReader.read(GenericDatumReader.java:155)
at org.apache.avro.generic.GenericDatumReader.readArray(GenericDatumReader.java:219)
at org.apache.avro.generic.GenericDatumReader.read(GenericDatumReader.java:153)
at org.apache.avro.generic.GenericDatumReader.read(GenericDatumReader.java:155)
at org.apache.avro.generic.GenericDatumReader.readField(GenericDatumReader.java:193)
at org.apache.avro.generic.GenericDatumReader.readRecord(GenericDatumReader.java:183)
at org.apache.avro.generic.GenericDatumReader.read(GenericDatumReader.java:151)
at org.apache.avro.generic.GenericDatumReader.read(GenericDatumReader.java:142)
at org.apache.hadoop.hive.serde2.avro.AvroDeserializer$SchemaReEncoder.reencode(AvroDeserializer.java:111)
at org.apache.hadoop.hive.serde2.avro.AvroDeserializer.deserialize(AvroDeserializer.java:175)
at org.apache.hadoop.hive.serde2.avro.AvroSerDe.deserialize(AvroSerDe.java:201)
at org.apache.spark.sql.hive.HadoopTableReader$$anonfun$fillObject$2.apply(TableReader.scala:381)
at org.apache.spark.sql.hive.HadoopTableReader$$anonfun$fillObject$2.apply(TableReader.scala:380)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$$anon$10.next(Iterator.scala:312)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
at scala.collection.AbstractIterator.to(Iterator.scala:1157)
at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$5.apply(SparkPlan.scala:215)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$5.apply(SparkPlan.scala:215)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1850)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1850)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
... 1 more
有人可以帮我解决这个问题吗？
编辑：这是AVRO架构：
{"namespace": "test",
"type": "record",
"name": "ticket",
"fields":
[
{"name": "name", "type": "string"},
{"name": "date", "type": "string"},
{"name": "carrier", "type": "string", "default": "null"},
{"name": "passengerNumber", "type": "int"},
{"name":"flights",
"default": "null",
"type":{
"type":"array",
"items": {
"name":"flight", "type":"record", "fields":
[
{"name":"orig", "type": "string"},
{"name":"dest", "type": "string"},
]
}
}
}
]
}
我想您的AVSC架构文件不正确。尝试在Hive中阅读，发现您得到同样的例外。如果是相同的，则是模式问题。
如果您有AVRO数据，请尝试使用AVRO-Tool获取架构文件，然后将其放置在您的HDFS/S3位置。
java -jar〜/avro-tools-1.7.4.4.jar getschema #avrofile＃
请以下面的方式尝试：test = hive_context.sql（""从db_name.table_name"选择 *）