Github user cloud-fan commented on a diff in the pull request: https://github.com/apache/spark/pull/21295#discussion_r190252764 --- Diff: sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/SpecificParquetRecordReaderBase.java --- @@ -225,7 +226,8 @@ protected void initialize(String path, List<String> columns) throws IOException this.sparkSchema = new ParquetToSparkSchemaConverter(config).convert(requestedSchema); this.reader = new ParquetFileReader( config, footer.getFileMetaData(), file, blocks, requestedSchema.getColumns()); - for (BlockMetaData block : blocks) { + // use the blocks from the reader in case some do not match filters and will not be read + for (BlockMetaData block : reader.getRowGroups()) { --- End diff -- I think this is an existing issue, does your test case fail on Spark 2.3 too?
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org