Github user HyukjinKwon commented on a diff in the pull request: https://github.com/apache/spark/pull/15835#discussion_r87382447 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFileFormat.scala --- @@ -272,6 +275,83 @@ class ParquetFileFormat true } + override def getSplits(fileIndex: FileIndex, + fileStatus: FileStatus, + filters: Seq[Filter], + schema: StructType, + hadoopConf: Configuration): Seq[FileSplit] = { + if (filters.isEmpty) { + // Return immediately to save FileSystem overhead + super.getSplits(fileIndex, fileStatus, filters, schema, hadoopConf) + } else { + val filePath = fileStatus.getPath + val rootOption: Option[Path] = fileIndex.rootPaths + .find(root => filePath.toString.startsWith(root.toString)) + val metadataOption = rootOption.flatMap(getMetadataForPath(filePath, _, hadoopConf)) + // If the metadata exists, filter the splits. + // Otherwise, fall back to the default implementation. + metadataOption + .map(filterToSplits(fileStatus, _, rootOption.get, filters, schema, hadoopConf)) + .getOrElse(super.getSplits(fileIndex, fileStatus, filters, schema, hadoopConf)) + } + } + + private def filterToSplits(fileStatus: FileStatus, + metadata: ParquetMetadata, + metadataRoot: Path, + filters: Seq[Filter], + schema: StructType, + hadoopConf: Configuration): Seq[FileSplit] = { + val metadataBlocks = metadata.getBlocks + val parquetSchema = metadata.getFileMetaData.getSchema + val filter = FilterCompat.get(filters + .flatMap(ParquetFilters.createFilter(schema, _)) + .reduce(FilterApi.and)) + val filteredMetadata = + RowGroupFilter.filterRowGroups(filter, metadataBlocks, parquetSchema).asScala + filteredMetadata.flatMap(bmd => { --- End diff -- According to https://github.com/databricks/scala-style-guide#anonymous-methods, ```scala filteredMetadata.flatMap { bmd => ... ``` seems encouraged.
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org