Major Description
If a user attempts to read Parquet files with mismatched schemas and schema merging is disabled then this may result in a very confusing UnsupportedOperationException and ParquetDecodingException errors from Parquet.
e.g.
Seq(("bcd")).toDF("a").coalesce(1).write.mode("overwrite").parquet(s"$path/") Seq((1)).toDF("a").coalesce(1).write.mode("append").parquet(s"$path/") spark.read.parquet(s"$path/").collect()
Would result in
Caused by: java.lang.UnsupportedOperationException: Unimplemented type: IntegerType at org.apache.spark.sql.execution.datasources.parquet.VectorizedColumnReader.readBinaryBatch(VectorizedColumnReader.java:474) at org.apache.spark.sql.execution.datasources.parquet.VectorizedColumnReader.readBatch(VectorizedColumnReader.java:214) at org.apache.spark.sql.execution.datasources.parquet.VectorizedParquetRecordReader.nextBatch(VectorizedParquetRecordReader.java:261) at org.apache.spark.sql.execution.datasources.parquet.VectorizedParquetRecordReader.nextKeyValue(VectorizedParquetRecordReader.java:159) at org.apache.spark.sql.execution.datasources.RecordReaderIterator.hasNext(RecordReaderIterator.scala:39) at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext(FileScanRDD.scala:106) at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.nextIterator(FileScanRDD.scala:182) at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext(FileScanRDD.scala:106) at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.scan_nextBatch$(Unknown Source) at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source) at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43) at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$11$$anon$1.hasNext(WholeStageCodegenExec.scala:617) at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:253) at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:247) at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:830) at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:830) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324) at org.apache.spark.rdd.RDD.iterator(RDD.scala:288) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87) at org.apache.spark.scheduler.Task.run(Task.scala:109) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:345) 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)
