c21 commented on a change in pull request #34575:
URL: https://github.com/apache/spark/pull/34575#discussion_r773674207
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileScanRDD.scala
##########
@@ -103,6 +115,101 @@ class FileScanRDD(
context.killTaskIfInterrupted()
(currentIterator != null && currentIterator.hasNext) || nextIterator()
}
+
+ ///////////////////////////
+ // FILE METADATA METHODS //
+ ///////////////////////////
+
+ // a metadata internal row, will only be updated when the current file
is changed
+ val metadataRow: InternalRow = new
GenericInternalRow(metadataColumns.length)
+
+ // an unsafe projection to convert a joined internal row to an unsafe row
+ private lazy val projection = {
+ val joinedExpressions =
+ readDataSchema.fields.map(_.dataType) ++
metadataColumns.map(_.dataType)
+ UnsafeProjection.create(joinedExpressions)
+ }
+
+ /**
+ * For each partitioned file, metadata columns for each record in the
file are exactly same.
+ * Only update metadata row when `currentFile` is changed.
+ */
+ private def updateMetadataRow(): Unit = {
+ if (metadataColumns.nonEmpty && currentFile != null) {
+ val path = new Path(currentFile.filePath)
+ metadataColumns.zipWithIndex.foreach { case (attr, i) =>
+ attr.name match {
+ case FILE_PATH => metadataRow.update(i,
UTF8String.fromString(path.toString))
+ case FILE_NAME => metadataRow.update(i,
UTF8String.fromString(path.getName))
+ case FILE_SIZE => metadataRow.update(i, currentFile.fileSize)
+ case FILE_MODIFICATION_TIME =>
+ // the modificationTime from the file is in millisecond,
+ // while internally, the TimestampType is stored in microsecond
+ metadataRow.update(i, currentFile.modificationTime * 1000L)
+ }
+ }
+ }
+ }
+
+ /**
+ * Create a writable column vector containing all required metadata
columns
+ */
+ private def createMetadataColumnVector(c: ColumnarBatch):
Array[WritableColumnVector] = {
+ val path = new Path(currentFile.filePath)
+ val filePathBytes = path.toString.getBytes
+ val fileNameBytes = path.getName.getBytes
+ var rowId = 0
+ metadataColumns.map(_.name).map {
Review comment:
Yeah I agree, it's not a huge issue as it's per batch not per row. But
also think it's not hard to organize code as the most efficient way.
--
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]
