Open
Description
[X] Bug report.
Description
While trying to parse geoPointInfo, it sample a document by exists query on the geoPoint field. If the geoPoint field on the sample document contains multiple values, for example - array of strings, the type wrongly inferred is GeoPointType.LAT_LON_OBJECT.
Looks like MappingUtils.doParseGeoPointInfo, tries to parse List as LON_LAT_ARRAY if the first element on the array is instance of Double, and on other cases (like in my case, where the first element on the list is instance of String), it will returns the default value - LAT_LON_OBJECT.
The fix should be something like - return the return value of another call of doParseGeoPointInfo with the content of the first list element, if it is not Double.
Steps to reproduce
The "sample" document, returned by client.sampleForFields is:
{
"pickupGeoLocations" : [
"41.123123, -11.123123",
"42.123123, -12.123123",
"44.123123, -13.123123"
]
}
the (wrong) schema I got is:
root
|-- geoLocations: array (nullable = true)
| |-- element: struct (containsNull = true)
| | |-- lat: double (nullable = true)
| | |-- lon: double (nullable = true)
Stacktrace:
Py4JJavaError Traceback (most recent call last)
<ipython-input-59-24d25af437a3> in <module>()
----> 1 df.select('geoLocations').rdd.take(1)
/usr/lib/spark/python/pyspark/rdd.py in take(self, num)
1341
1342 p = range(partsScanned, min(partsScanned + numPartsToTry, totalParts))
-> 1343 res = self.context.runJob(self, takeUpToNumLeft, p)
1344
1345 items += res
/usr/lib/spark/python/pyspark/context.py in runJob(self, rdd, partitionFunc, partitions, allowLocal)
990 # SparkContext#runJob.
991 mappedRDD = rdd.mapPartitions(partitionFunc)
--> 992 port = self._jvm.PythonRDD.runJob(self._jsc.sc(), mappedRDD._jrdd, partitions)
993 return list(_load_from_socket(port, mappedRDD._jrdd_deserializer))
994
/usr/lib/spark/python/lib/py4j-src.zip/py4j/java_gateway.py in __call__(self, *args)
1131 answer = self.gateway_client.send_command(command)
1132 return_value = get_return_value(
-> 1133 answer, self.gateway_client, self.target_id, self.name)
1134
1135 for temp_arg in temp_args:
/usr/lib/spark/python/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()
/usr/lib/spark/python/lib/py4j-src.zip/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
317 raise Py4JJavaError(
318 "An error occurred while calling {0}{1}{2}.\n".
--> 319 format(target_id, ".", name), value)
320 else:
321 raise Py4JError(
Py4JJavaError: An error occurred while calling z:org.apache.spark.api.python.PythonRDD.runJob.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 34.0 failed 4 times, most recent failure: Lost task 0.3 in stage 34.0 (TID 260, ip-192-168-128-21.ec2.internal, executor 5): scala.MatchError: 33.94, -117.72 (of class java.lang.String)
at org.apache.spark.sql.catalyst.CatalystTypeConverters$StructConverter.toCatalystImpl(CatalystTypeConverters.scala:236)
at org.apache.spark.sql.catalyst.CatalystTypeConverters$StructConverter.toCatalystImpl(CatalystTypeConverters.scala:231)
at org.apache.spark.sql.catalyst.CatalystTypeConverters$CatalystTypeConverter.toCatalyst(CatalystTypeConverters.scala:103)
at org.apache.spark.sql.catalyst.CatalystTypeConverters$ArrayConverter$$anonfun$toCatalystImpl$2.apply(CatalystTypeConverters.scala:164)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at scala.collection.Iterator$class.foreach(Iterator.scala:893)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1336)
at scala.collection.IterableLike$class.foreach(IterableLike.scala:72)
at scala.collection.AbstractIterable.foreach(Iterable.scala:54)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
at scala.collection.AbstractTraversable.map(Traversable.scala:104)
at org.apache.spark.sql.catalyst.CatalystTypeConverters$ArrayConverter.toCatalystImpl(CatalystTypeConverters.scala:164)
at org.apache.spark.sql.catalyst.CatalystTypeConverters$ArrayConverter.toCatalystImpl(CatalystTypeConverters.scala:154)
at org.apache.spark.sql.catalyst.CatalystTypeConverters$CatalystTypeConverter.toCatalyst(CatalystTypeConverters.scala:103)
at org.apache.spark.sql.catalyst.CatalystTypeConverters$$anonfun$createToCatalystConverter$2.apply(CatalystTypeConverters.scala:379)
at org.apache.spark.sql.execution.RDDConversions$$anonfun$rowToRowRdd$1$$anonfun$apply$3.apply(ExistingRDD.scala:61)
at org.apache.spark.sql.execution.RDDConversions$$anonfun$rowToRowRdd$1$$anonfun$apply$3.apply(ExistingRDD.scala:58)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:409)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$8$$anon$1.hasNext(WholeStageCodegenExec.scala:395)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at org.apache.spark.api.python.SerDeUtil$AutoBatchedPickler.hasNext(SerDeUtil.scala:117)
at scala.collection.Iterator$class.foreach(Iterator.scala:893)
at org.apache.spark.api.python.SerDeUtil$AutoBatchedPickler.foreach(SerDeUtil.scala:112)
at org.apache.spark.api.python.PythonRDD$.writeIteratorToStream(PythonRDD.scala:518)
at org.apache.spark.api.python.PythonRunner$WriterThread$$anonfun$run$3.apply(PythonRDD.scala:333)
at org.apache.spark.util.Utils$.logUncaughtExceptions(Utils.scala:1948)
at org.apache.spark.api.python.PythonRunner$WriterThread.run(PythonRDD.scala:269)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1708)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1696)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1695)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1695)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:855)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:855)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:855)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1923)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1878)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1867)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:671)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2029)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2050)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2069)
at org.apache.spark.api.python.PythonRDD$.runJob(PythonRDD.scala:455)
at org.apache.spark.api.python.PythonRDD.runJob(PythonRDD.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:280)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:214)
at java.lang.Thread.run(Thread.java:748)
Caused by: scala.MatchError: 33.94, -117.72 (of class java.lang.String)
at org.apache.spark.sql.catalyst.CatalystTypeConverters$StructConverter.toCatalystImpl(CatalystTypeConverters.scala:236)
at org.apache.spark.sql.catalyst.CatalystTypeConverters$StructConverter.toCatalystImpl(CatalystTypeConverters.scala:231)
at org.apache.spark.sql.catalyst.CatalystTypeConverters$CatalystTypeConverter.toCatalyst(CatalystTypeConverters.scala:103)
at org.apache.spark.sql.catalyst.CatalystTypeConverters$ArrayConverter$$anonfun$toCatalystImpl$2.apply(CatalystTypeConverters.scala:164)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at scala.collection.Iterator$class.foreach(Iterator.scala:893)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1336)
at scala.collection.IterableLike$class.foreach(IterableLike.scala:72)
at scala.collection.AbstractIterable.foreach(Iterable.scala:54)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
at scala.collection.AbstractTraversable.map(Traversable.scala:104)
at org.apache.spark.sql.catalyst.CatalystTypeConverters$ArrayConverter.toCatalystImpl(CatalystTypeConverters.scala:164)
at org.apache.spark.sql.catalyst.CatalystTypeConverters$ArrayConverter.toCatalystImpl(CatalystTypeConverters.scala:154)
at org.apache.spark.sql.catalyst.CatalystTypeConverters$CatalystTypeConverter.toCatalyst(CatalystTypeConverters.scala:103)
at org.apache.spark.sql.catalyst.CatalystTypeConverters$$anonfun$createToCatalystConverter$2.apply(CatalystTypeConverters.scala:379)
at org.apache.spark.sql.execution.RDDConversions$$anonfun$rowToRowRdd$1$$anonfun$apply$3.apply(ExistingRDD.scala:61)
at org.apache.spark.sql.execution.RDDConversions$$anonfun$rowToRowRdd$1$$anonfun$apply$3.apply(ExistingRDD.scala:58)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:409)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$8$$anon$1.hasNext(WholeStageCodegenExec.scala:395)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at org.apache.spark.api.python.SerDeUtil$AutoBatchedPickler.hasNext(SerDeUtil.scala:117)
at scala.collection.Iterator$class.foreach(Iterator.scala:893)
at org.apache.spark.api.python.SerDeUtil$AutoBatchedPickler.foreach(SerDeUtil.scala:112)
at org.apache.spark.api.python.PythonRDD$.writeIteratorToStream(PythonRDD.scala:518)
at org.apache.spark.api.python.PythonRunner$WriterThread$$anonfun$run$3.apply(PythonRDD.scala:333)
at org.apache.spark.util.Utils$.logUncaughtExceptions(Utils.scala:1948)
at org.apache.spark.api.python.PythonRunner$WriterThread.run(PythonRDD.scala:269)