Created
December 9, 2022 01:00
-
-
Save erich-truveta/f30d77441186a8c30c5f22f9c44bf59f to your computer and use it in GitHub Desktop.
java.io.IOException: can not read class org.apache.parquet.format.PageHeader: Unrecognized type 0
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| "22/12/08 22:10:28 INFO FileScanRDD: Reading File path: abfss://REDACTED/part-00375-74c76941-8b11-4873-86d6-80444390017d-c000.snappy.parquet, range: 0-87836085, partition values: [empty row]" | |
| "22/12/08 22:10:28 ERROR Executor: Exception in task 365.0 in stage 2865.0 (TID 117118)" | |
| "org.apache.spark.sql.execution.QueryExecutionException: Encountered error while reading file abfss://REDACTED/part-00364-ff7615b7-4a38-4aa7-aa39-3c4ee58483e7-c000.snappy.parquet. Details: " | |
| " at org.apache.spark.sql.errors.QueryExecutionErrors$.cannotReadFilesError(QueryExecutionErrors.scala:731)" | |
| " at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.nextIterator(FileScanRDD.scala:283)" | |
| " at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext(FileScanRDD.scala:116)" | |
| " at org.apache.spark.sql.execution.FileSourceScanExec$$anon$1.hasNext(DataSourceScanExec.scala:554)" | |
| " at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.columnartorow_nextBatch_0$(Unknown Source)" | |
| " at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)" | |
| " at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)" | |
| " at org.apache.spark.sql.execution.WholeStageCodegenExec$$anon$1.hasNext(WholeStageCodegenExec.scala:760)" | |
| " at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)" | |
| " at org.apache.spark.shuffle.sort.BypassMergeSortShuffleWriter.write(BypassMergeSortShuffleWriter.java:140)" | |
| " at org.apache.spark.shuffle.ShuffleWriteProcessor.write(ShuffleWriteProcessor.scala:59)" | |
| " at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:99)" | |
| " at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:52)" | |
| " at org.apache.spark.scheduler.Task.run(Task.scala:136)" | |
| " at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:548)" | |
| " at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1504)" | |
| " at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:551)" | |
| " 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:829)" | |
| "Caused by: java.io.IOException: can not read class org.apache.parquet.format.PageHeader: Unrecognized type 0" | |
| " at org.apache.parquet.format.Util.read(Util.java:365)" | |
| " at org.apache.parquet.format.Util.readPageHeader(Util.java:132)" | |
| " at org.apache.parquet.hadoop.ParquetFileReader$Chunk.readPageHeader(ParquetFileReader.java:1382)" | |
| " at org.apache.parquet.hadoop.ParquetFileReader$Chunk.readAllPages(ParquetFileReader.java:1429)" | |
| " at org.apache.parquet.hadoop.ParquetFileReader$Chunk.readAllPages(ParquetFileReader.java:1402)" | |
| " at org.apache.parquet.hadoop.ParquetFileReader.readChunkPages(ParquetFileReader.java:1023)" | |
| " at org.apache.parquet.hadoop.ParquetFileReader.readNextRowGroup(ParquetFileReader.java:928)" | |
| " at org.apache.parquet.hadoop.ParquetFileReader.readNextFilteredRowGroup(ParquetFileReader.java:972)" | |
| " at org.apache.spark.sql.execution.datasources.parquet.SpecificParquetRecordReaderBase$ParquetRowGroupReaderImpl.readNextRowGroup(SpecificParquetRecordReaderBase.java:266)" | |
| " at org.apache.spark.sql.execution.datasources.parquet.VectorizedParquetRecordReader.checkEndOfRowGroup(VectorizedParquetRecordReader.java:388)" | |
| " at org.apache.spark.sql.execution.datasources.parquet.VectorizedParquetRecordReader.nextBatch(VectorizedParquetRecordReader.java:309)" | |
| " at org.apache.spark.sql.execution.datasources.parquet.VectorizedParquetRecordReader.nextKeyValue(VectorizedParquetRecordReader.java:212)" | |
| " 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:116)" | |
| " at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.nextIterator(FileScanRDD.scala:274)" | |
| " ... 18 more" | |
| "Caused by: shaded.parquet.org.apache.thrift.protocol.TProtocolException: Unrecognized type 0" | |
| " at shaded.parquet.org.apache.thrift.protocol.TProtocolUtil.skip(TProtocolUtil.java:144)" | |
| " at shaded.parquet.org.apache.thrift.protocol.TProtocolUtil.skip(TProtocolUtil.java:130)" | |
| " at shaded.parquet.org.apache.thrift.protocol.TProtocolUtil.skip(TProtocolUtil.java:60)" | |
| " at org.apache.parquet.format.PageHeader$PageHeaderStandardScheme.read(PageHeader.java:1078)" | |
| " at org.apache.parquet.format.PageHeader$PageHeaderStandardScheme.read(PageHeader.java:1019)" | |
| " at org.apache.parquet.format.PageHeader.read(PageHeader.java:896)" | |
| " at org.apache.parquet.format.Util.read(Util.java:362)" | |
| " ... 32 more" |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment