[ https://issues.apache.org/jira/browse/SPARK-21534?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16101009#comment-16101009 ]
Hyukjin Kwon commented on SPARK-21534: -------------------------------------- cc [~zasdfgbnm] and [~ueshin], this one looks related with few PRs we reviewed and worked before. This was not reproduced in Python 2.7: {code} >>> spark.createDataFrame(spark.sql("select unhex('') as xx").rdd.map(lambda x: >>> {"abc": x.xx})).show() +---+ |abc| +---+ | []| +---+ {code} but Python 3.6: {code} >>> spark.createDataFrame(spark.sql("select unhex('') as xx").rdd.map(lambda x: >>> {"abc": x.xx})).show() net.razorvine.pickle.PickleException: invalid pickle data for bytearray; expected 1 or 2 args, got 0 at net.razorvine.pickle.objects.ByteArrayConstructor.construct(ByteArrayConstructor.java:20) at net.razorvine.pickle.Unpickler.load_reduce(Unpickler.java:707) at net.razorvine.pickle.Unpickler.dispatch(Unpickler.java:175) at net.razorvine.pickle.Unpickler.load(Unpickler.java:99) at net.razorvine.pickle.Unpickler.loads(Unpickler.java:112) at org.apache.spark.api.python.SerDeUtil$$anonfun$pythonToJava$1$$anonfun$apply$1.apply(SerDeUtil.scala:174) at org.apache.spark.api.python.SerDeUtil$$anonfun$pythonToJava$1$$anonfun$apply$1.apply(SerDeUtil.scala:173) at scala.collection.Iterator$$anon$12.nextCur(Iterator.scala:434) at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:440) at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408) at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408) at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408) at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:231) at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:225) at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:827) at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:827) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) at org.apache.spark.rdd.RDD.iterator(RDD.scala:287) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87) at org.apache.spark.scheduler.Task.run(Task.scala:108) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:341) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) at java.lang.Thread.run(Thread.java:745) {code} > PickleException when creating dataframe from python row with empty bytearray > ---------------------------------------------------------------------------- > > Key: SPARK-21534 > URL: https://issues.apache.org/jira/browse/SPARK-21534 > Project: Spark > Issue Type: Bug > Components: PySpark, SQL > Affects Versions: 2.2.0 > Reporter: Maciej BryĆski > > {code} > spark.createDataFrame(spark.sql("select unhex('') as xx").rdd.map(lambda x: > {"abc": x.xx})).show() > {code} > This code creates exception. It looks like corner-case. > {code} > net.razorvine.pickle.PickleException: invalid pickle data for bytearray; > expected 1 or 2 args, got 0 > at > net.razorvine.pickle.objects.ByteArrayConstructor.construct(ByteArrayConstructor.java:20) > at net.razorvine.pickle.Unpickler.load_reduce(Unpickler.java:707) > at net.razorvine.pickle.Unpickler.dispatch(Unpickler.java:175) > at net.razorvine.pickle.Unpickler.load(Unpickler.java:99) > at net.razorvine.pickle.Unpickler.loads(Unpickler.java:112) > at > org.apache.spark.api.python.SerDeUtil$$anonfun$pythonToJava$1$$anonfun$apply$1.apply(SerDeUtil.scala:152) > at > org.apache.spark.api.python.SerDeUtil$$anonfun$pythonToJava$1$$anonfun$apply$1.apply(SerDeUtil.scala:151) > at scala.collection.Iterator$$anon$12.nextCur(Iterator.scala:434) > at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:440) > at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408) > at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408) > at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:234) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:228) > at > org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:827) > at > org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:827) > at > org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) > at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:287) > at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87) > at org.apache.spark.scheduler.Task.run(Task.scala:108) > at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:335) > at > java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) > at > java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) > at java.lang.Thread.run(Thread.java:748) > Driver stacktrace: > at > org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1499) > at > org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1487) > at > org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1486) > at > scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) > at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48) > at > org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1486) > at > org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:814) > at > org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:814) > at scala.Option.foreach(Option.scala:257) > at > org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:814) > at > org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1714) > at > org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1669) > at > org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1658) > at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48) > at > org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:630) > at org.apache.spark.SparkContext.runJob(SparkContext.scala:2022) > at org.apache.spark.SparkContext.runJob(SparkContext.scala:2043) > at org.apache.spark.SparkContext.runJob(SparkContext.scala:2062) > at > org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:336) > at > org.apache.spark.sql.execution.CollectLimitExec.executeCollect(limit.scala:38) > at > org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$collectFromPlan(Dataset.scala:2853) > at > org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2153) > at > org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2153) > at org.apache.spark.sql.Dataset$$anonfun$55.apply(Dataset.scala:2837) > at > org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:65) > at org.apache.spark.sql.Dataset.withAction(Dataset.scala:2836) > at org.apache.spark.sql.Dataset.head(Dataset.scala:2153) > at org.apache.spark.sql.Dataset.take(Dataset.scala:2366) > at org.apache.spark.sql.Dataset.showString(Dataset.scala:245) > 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:280) > at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) > at py4j.commands.CallCommand.execute(CallCommand.java:79) > at py4j.GatewayConnection.run(GatewayConnection.java:214) > at java.lang.Thread.run(Thread.java:748) > Caused by: net.razorvine.pickle.PickleException: invalid pickle data for > bytearray; expected 1 or 2 args, got 0 > at > net.razorvine.pickle.objects.ByteArrayConstructor.construct(ByteArrayConstructor.java:20) > at net.razorvine.pickle.Unpickler.load_reduce(Unpickler.java:707) > at net.razorvine.pickle.Unpickler.dispatch(Unpickler.java:175) > at net.razorvine.pickle.Unpickler.load(Unpickler.java:99) > at net.razorvine.pickle.Unpickler.loads(Unpickler.java:112) > at > org.apache.spark.api.python.SerDeUtil$$anonfun$pythonToJava$1$$anonfun$apply$1.apply(SerDeUtil.scala:152) > at > org.apache.spark.api.python.SerDeUtil$$anonfun$pythonToJava$1$$anonfun$apply$1.apply(SerDeUtil.scala:151) > at scala.collection.Iterator$$anon$12.nextCur(Iterator.scala:434) > at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:440) > at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408) > at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408) > at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:234) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:228) > at > org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:827) > at > org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:827) > at > org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) > at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:287) > at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87) > at org.apache.spark.scheduler.Task.run(Task.scala:108) > at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:335) > at > java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) > at > java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) > ... 1 more > {code} -- This message was sent by Atlassian JIRA (v6.4.14#64029) --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org