[
https://issues.apache.org/jira/browse/SPARK-32081?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Hyukjin Kwon updated SPARK-32081:
---------------------------------
Priority: Major (was: Blocker)
> facing Invalid UTF-32 character v2.4.5 running pyspark
> ------------------------------------------------------
>
> Key: SPARK-32081
> URL: https://issues.apache.org/jira/browse/SPARK-32081
> Project: Spark
> Issue Type: Bug
> Components: EC2
> Affects Versions: 2.4.5
> Reporter: Yaniv Kempler
> Priority: Major
>
> facing Invalid UTF-32 character while reading json files
>
> Py4JJavaError Traceback (most recent call last) <timed exec> in <module>
> ~/.local/lib/python3.6/site-packages/pyspark/sql/readwriter.py in json(self,
> path, schema, primitivesAsString, prefersDecimal, allowComments,
> allowUnquotedFieldNames, allowSingleQuotes, allowNumericLeadingZero,
> allowBackslashEscapingAnyCharacter, mode, columnNameOfCorruptRecord,
> dateFormat, timestampFormat, multiLine, allowUnquotedControlChars, lineSep,
> samplingRatio, dropFieldIfAllNull, encoding) 284 keyed._bypass_serializer =
> True 285 jrdd = keyed._jrdd.map(self._spark._jvm.BytesToString()) --> 286
> return self._df(self._jreader.json(jrdd)) 287 else: 288 raise
> TypeError("path can be only string, list or RDD")
> ~/.local/lib/python3.6/site-packages/py4j/java_gateway.py in __call__(self,
> *args) 1255 answer = self.gateway_client.send_command(command) 1256
> return_value = get_return_value( -> 1257 answer, self.gateway_client,
> self.target_id, self.name) 1258 1259 for temp_arg in temp_args:
> ~/.local/lib/python3.6/site-packages/pyspark/sql/utils.py in deco(*a, **kw)
> 61 def deco(*a, **kw): 62 try: ---> 63 return f(*a, **kw) 64 except
> py4j.protocol.Py4JJavaError as e: 65 s = e.java_exception.toString()
> ~/.local/lib/python3.6/site-packages/py4j/protocol.py in
> get_return_value(answer, gateway_client, target_id, name) 326 raise
> Py4JJavaError( 327 "An error occurred while calling \{0}{1}\{2}.\n". --> 328
> format(target_id, ".", name), value) 329 else: 330 raise Py4JError(
> Py4JJavaError: An error occurred while calling o67.json. :
> org.apache.spark.SparkException: Job aborted due to stage failure: Task 546
> in stage 0.0 failed 4 times, most recent failure: Lost task 546.3 in stage
> 0.0 (TID 642, 172.31.30.196, executor 1): java.io.CharConversionException:
> Invalid UTF-32 character 0x1000000(above 10ffff) at char #206, byte #827) at
> com.fasterxml.jackson.core.io.UTF32Reader.reportInvalid(UTF32Reader.java:189)
> at com.fasterxml.jackson.core.io.UTF32Reader.read(UTF32Reader.java:150) at
> com.fasterxml.jackson.core.json.ReaderBasedJsonParser.loadMore(ReaderBasedJsonParser.java:153)
> at
> com.fasterxml.jackson.core.json.ReaderBasedJsonParser._skipWSOrEnd(ReaderBasedJsonParser.java:2017)
> at
> com.fasterxml.jackson.core.json.ReaderBasedJsonParser.nextToken(ReaderBasedJsonParser.java:577)
> at
> org.apache.spark.sql.catalyst.json.JsonInferSchema$$anonfun$1$$anonfun$apply$1$$anonfun$apply$3.apply(JsonInferSchema.scala:56)
> at
> org.apache.spark.sql.catalyst.json.JsonInferSchema$$anonfun$1$$anonfun$apply$1$$anonfun$apply$3.apply(JsonInferSchema.scala:55)
> at org.apache.spark.util.Utils$.tryWithResource(Utils.scala:2543) at
> org.apache.spark.sql.catalyst.json.JsonInferSchema$$anonfun$1$$anonfun$apply$1.apply(JsonInferSchema.scala:55)
> at
> org.apache.spark.sql.catalyst.json.JsonInferSchema$$anonfun$1$$anonfun$apply$1.apply(JsonInferSchema.scala:53)
> at scala.collection.Iterator$$anon$12.nextCur(Iterator.scala:435) at
> scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:441) at
> scala.collection.Iterator$class.foreach(Iterator.scala:891) at
> scala.collection.AbstractIterator.foreach(Iterator.scala:1334) at
> scala.collection.TraversableOnce$class.reduceLeft(TraversableOnce.scala:185)
> at scala.collection.AbstractIterator.reduceLeft(Iterator.scala:1334) at
> scala.collection.TraversableOnce$class.reduceLeftOption(TraversableOnce.scala:203)
> at scala.collection.AbstractIterator.reduceLeftOption(Iterator.scala:1334)
> at
> scala.collection.TraversableOnce$class.reduceOption(TraversableOnce.scala:210)
> at scala.collection.AbstractIterator.reduceOption(Iterator.scala:1334) at
> org.apache.spark.sql.catalyst.json.JsonInferSchema$$anonfun$1.apply(JsonInferSchema.scala:70)
> at
> org.apache.spark.sql.catalyst.json.JsonInferSchema$$anonfun$1.apply(JsonInferSchema.scala:50)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$23.apply(RDD.scala:823)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$23.apply(RDD.scala:823)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:346) at
> org.apache.spark.rdd.RDD.iterator(RDD.scala:310) at
> org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90) at
> org.apache.spark.scheduler.Task.run(Task.scala:123) at
> org.apache.spark.executor.Executor$TaskRunner$$anonfun$10.apply(Executor.scala:408)
> at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1360) at
> org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:414) at
> java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1128)
> at
> java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:628)
> at java.base/java.lang.Thread.run(Thread.java:834) Driver stacktrace: at
> org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1891)
> at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1879)
> at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1878)
> at
> scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
> at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48) at
> org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1878)
> at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:927)
> at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:927)
> at scala.Option.foreach(Option.scala:257) at
> org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:927)
> at
> org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2112)
> at
> org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2061)
> at
> org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2050)
> at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49) at
> org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:738) at
> org.apache.spark.SparkContext.runJob(SparkContext.scala:2061) at
> org.apache.spark.SparkContext.runJob(SparkContext.scala:2158) at
> org.apache.spark.sql.catalyst.json.JsonInferSchema$.infer(JsonInferSchema.scala:83)
> at
> org.apache.spark.sql.execution.datasources.json.TextInputJsonDataSource$$anonfun$inferFromDataset$1.apply(JsonDataSource.scala:109)
> at
> org.apache.spark.sql.execution.datasources.json.TextInputJsonDataSource$$anonfun$inferFromDataset$1.apply(JsonDataSource.scala:109)
> at
> org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:127)
> at
> org.apache.spark.sql.execution.datasources.json.TextInputJsonDataSource$.inferFromDataset(JsonDataSource.scala:108)
> at
> org.apache.spark.sql.DataFrameReader$$anonfun$2.apply(DataFrameReader.scala:440)
> at
> org.apache.spark.sql.DataFrameReader$$anonfun$2.apply(DataFrameReader.scala:440)
> at scala.Option.getOrElse(Option.scala:121) at
> org.apache.spark.sql.DataFrameReader.json(DataFrameReader.scala:439) at
> org.apache.spark.sql.DataFrameReader.json(DataFrameReader.scala:420) at
> org.apache.spark.sql.DataFrameReader.json(DataFrameReader.scala:406) at
> sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at
> sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
> at
> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:498) at
> py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) at
> py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357) at
> py4j.Gateway.invoke(Gateway.java:282) at
> py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) at
> py4j.commands.CallCommand.execute(CallCommand.java:79) at
> py4j.GatewayConnection.run(GatewayConnection.java:238) at
> java.lang.Thread.run(Thread.java:748) Caused by:
> java.io.CharConversionException: Invalid UTF-32 character 0x1000000(above
> 10ffff) at char #206, byte #827) at
> com.fasterxml.jackson.core.io.UTF32Reader.reportInvalid(UTF32Reader.java:189)
> at com.fasterxml.jackson.core.io.UTF32Reader.read(UTF32Reader.java:150) at
> com.fasterxml.jackson.core.json.ReaderBasedJsonParser.loadMore(ReaderBasedJsonParser.java:153)
> at
> com.fasterxml.jackson.core.json.ReaderBasedJsonParser._skipWSOrEnd(ReaderBasedJsonParser.java:2017)
> at
> com.fasterxml.jackson.core.json.ReaderBasedJsonParser.nextToken(ReaderBasedJsonParser.java:577)
> at
> org.apache.spark.sql.catalyst.json.JsonInferSchema$$anonfun$1$$anonfun$apply$1$$anonfun$apply$3.apply(JsonInferSchema.scala:56)
> at
> org.apache.spark.sql.catalyst.json.JsonInferSchema$$anonfun$1$$anonfun$apply$1$$anonfun$apply$3.apply(JsonInferSchema.scala:55)
> at org.apache.spark.util.Utils$.tryWithResource(Utils.scala:2543) at
> org.apache.spark.sql.catalyst.json.JsonInferSchema$$anonfun$1$$anonfun$apply$1.apply(JsonInferSchema.scala:55)
> at
> org.apache.spark.sql.catalyst.json.JsonInferSchema$$anonfun$1$$anonfun$apply$1.apply(JsonInferSchema.scala:53)
> at scala.collection.Iterator$$anon$12.nextCur(Iterator.scala:435) at
> scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:441) at
> scala.collection.Iterator$class.foreach(Iterator.scala:891) at
> scala.collection.AbstractIterator.foreach(Iterator.scala:1334) at
> scala.collection.TraversableOnce$class.reduceLeft(TraversableOnce.scala:185)
> at scala.collection.AbstractIterator.reduceLeft(Iterator.scala:1334) at
> scala.collection.TraversableOnce$class.reduceLeftOption(TraversableOnce.scala:203)
> at scala.collection.AbstractIterator.reduceLeftOption(Iterator.scala:1334)
> at
> scala.collection.TraversableOnce$class.reduceOption(TraversableOnce.scala:210)
> at scala.collection.AbstractIterator.reduceOption(Iterator.scala:1334) at
> org.apache.spark.sql.catalyst.json.JsonInferSchema$$anonfun$1.apply(JsonInferSchema.scala:70)
> at
> org.apache.spark.sql.catalyst.json.JsonInferSchema$$anonfun$1.apply(JsonInferSchema.scala:50)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$23.apply(RDD.scala:823)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$23.apply(RDD.scala:823)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:346) at
> org.apache.spark.rdd.RDD.iterator(RDD.scala:310) at
> org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90) at
> org.apache.spark.scheduler.Task.run(Task.scala:123) at
> org.apache.spark.executor.Executor$TaskRunner$$anonfun$10.apply(Executor.scala:408)
> at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1360) at
> org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:414) at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1128)
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:628)
> at java.lang.Thread.run(Thread.java:834)
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
