ryan-johnson-databricks commented on code in PR #40885: URL: https://github.com/apache/spark/pull/40885#discussion_r1173759666
########## sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileFormat.scala: ########## @@ -241,47 +256,74 @@ object FileFormat { FileSourceConstantMetadataStructField(FILE_BLOCK_LENGTH, LongType, nullable = false), FileSourceConstantMetadataStructField(FILE_MODIFICATION_TIME, TimestampType, nullable = false)) + /** + * All [[BASE_METADATA_FIELDS]] require custom extractors because they are derived directly from + * fields of the [[PartitionedFile]], and do have entries in the file's metadata map. + */ + val BASE_METADATA_EXTRACTORS: Map[String, PartitionedFile => Any] = Map( + FILE_PATH -> { pf: PartitionedFile => pf.toPath.toString }, + FILE_NAME -> { pf: PartitionedFile => pf.toPath.getName }, + FILE_SIZE -> { pf: PartitionedFile => pf.fileSize }, + FILE_BLOCK_START -> { pf: PartitionedFile => pf.start }, + FILE_BLOCK_LENGTH -> { pf: PartitionedFile => pf.length }, + // The modificationTime from the file has millisecond granularity, but the TimestampType for + // `file_modification_time` has microsecond granularity. + FILE_MODIFICATION_TIME -> { pf: PartitionedFile => pf.modificationTime * 1000 } + ) + + /** + * Extracts the [[Literal]] value of a file-constant metadata column from a [[PartitionedFile]]. + * + * If an extractor is available, use it. Otherwise, attempt to fetch the value directly from the + * file's metadata map, returning null if not found. + * + * Raw values (including null) are automatically converted to literals as a courtesy. + */ + def getFileConstantMetadataColumnValue( + name: String, + file: PartitionedFile, + metadataExtractors: Map[String, PartitionedFile => Any]): Literal = { + val extractor = metadataExtractors.get(name).getOrElse { + (_: PartitionedFile).otherConstantMetadataColumnValues.get(name).orNull Review Comment: Agreed. I think it's already fixed locally but I didn't push yet in case there were other comments. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org