ala commented on code in PR #37228:
URL: https://github.com/apache/spark/pull/37228#discussion_r928848361
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileFormat.scala:
##########
@@ -182,18 +188,25 @@ object FileFormat {
val FILE_MODIFICATION_TIME = "file_modification_time"
+ val ROW_INDEX = "row_index"
+
+ // A name for a temporary column that holds row indexes computed by the file
format reader
+ // until they can be placed in the _metadata struct.
+ val ROW_INDEX_TEMPORARY_COLUMN_NAME = s"_tmp_metadata_$ROW_INDEX"
+
val METADATA_NAME = "_metadata"
- // supported metadata struct fields for hadoop fs relation
- val METADATA_STRUCT: StructType = new StructType()
- .add(StructField(FILE_PATH, StringType))
- .add(StructField(FILE_NAME, StringType))
- .add(StructField(FILE_SIZE, LongType))
- .add(StructField(FILE_MODIFICATION_TIME, TimestampType))
+ /** Schema of metadata struct that can be produced by every file format. */
+ def getBaseFileMetadataCol: StructType = new StructType()
+ .add(StructField(FileFormat.FILE_PATH, StringType))
+ .add(StructField(FileFormat.FILE_NAME, StringType))
+ .add(StructField(FileFormat.FILE_SIZE, LongType))
+ .add(StructField(FileFormat.FILE_MODIFICATION_TIME, TimestampType))
- // create a file metadata struct col
- def createFileMetadataCol: AttributeReference =
- FileSourceMetadataAttribute(METADATA_NAME, METADATA_STRUCT)
+ /** Create a file metadata struct column containing fields supported by
every format. */
+ def createBaseFileMetadataCol: AttributeReference = {
Review Comment:
Done.
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
