spark-sql的warn

20/06/10 16:31:38 WARN parquet.CorruptStatistics: Ignoring statistics because created_by could not be parsed (see PARQUET-251): parquet-mr
org.apache.parquet.VersionParser$VersionParseException: Could not parse created_by: parquet-mr using format: (.+) version ((.*) )?\(build ?(.*)\)
	at org.apache.parquet.VersionParser.parse(VersionParser.java:112)
	at org.apache.parquet.CorruptStatistics.shouldIgnoreStatistics(CorruptStatistics.java:60)
	at org.apache.parquet.format.converter.ParquetMetadataConverter.fromParquetStatistics(ParquetMetadataConverter.java:263)
	at org.apache.parquet.format.converter.ParquetMetadataConverter.fromParquetMetadata(ParquetMetadataConverter.java:567)
	at org.apache.parquet.format.converter.ParquetMetadataConverter.readParquetMetadata(ParquetMetadataConverter.java:544)
	at org.apache.parquet.hadoop.ParquetFileReader.readFooter(ParquetFileReader.java:431)
	at org.apache.parquet.hadoop.ParquetFileReader.readFooter(ParquetFileReader.java:386)
	at org.apache.spark.sql.execution.datasources.parquet.SpecificParquetRecordReaderBase.initialize(SpecificParquetRecordReaderBase.java:107)
	at org.apache.spark.sql.execution.datasources.parquet.VectorizedParquetRecordReader.initialize(VectorizedParquetRecordReader.java:109)
	at org.apache.spark.sql.execution.datasources.parquet.ParquetFileFormat$$anonfun$buildReader$1.apply(ParquetFileFormat.scala:381)
	at org.apache.spark.sql.execution.datasources.parquet.ParquetFileFormat$$anonfun$buildReader$1.apply(ParquetFileFormat.scala:355)
	at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.nextIterator(FileScanRDD.scala:168)
	at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext(FileScanRDD.scala:109)
	at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.scan_nextBatch$(Unknown Source)
	at org.apache.spark.sql.catalyst.expressions.GeneratedClass$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:377)
	at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:439)
	at scala.collection.Iterator$JoinIterator.hasNext(Iterator.scala:211)
	at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
	at org.apache.spark.sql.catalyst.expressions.GeneratedClass$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:377)
	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$25.apply(RDD.scala:827)
	at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
	at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
	at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
	at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
	at org.apache.spark.scheduler.Task.run(Task.scala:99)
	at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:322)
	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)