olaky commented on code in PR #39408:
URL: https://github.com/apache/spark/pull/39408#discussion_r1069313774
##########
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/FileMetadataStructSuite.scala:
##########
@@ -677,4 +677,90 @@ class FileMetadataStructSuite extends QueryTest with
SharedSparkSession {
assert(analyzedStruct.fields.forall(!_.nullable),
analyzedStruct.fields.mkString(", "))
assert(executedStruct.fields.forall(!_.nullable),
executedStruct.fields.mkString(", "))
}
+
+ test("SPARK-41896: Filter on row_index and a stored column at the same
time") {
+ withTempPath { dir =>
+ val storedIdName = "stored_id"
+ val storedIdUpperLimitExclusive = 520
+ val rowIndexLowerLimitInclusive = 10
+
+ spark.range(start = 500, end = 600)
+ .toDF(storedIdName)
+ .write
+ .format("parquet")
+ .save(dir.getAbsolutePath)
+
+ // Select stored_id 510 to 519 via a stored_id and row_index filter.
+ val collectedRows = spark.read.load(dir.getAbsolutePath)
+ .select(storedIdName, METADATA_ROW_INDEX)
+ .where(col(storedIdName).lt(lit(storedIdUpperLimitExclusive)))
+ .where(col(METADATA_ROW_INDEX).geq(lit(rowIndexLowerLimitInclusive)))
+ .collect()
+
+ assert(collectedRows.length === 10)
+ assert(collectedRows.forall(_.getLong(0) < storedIdUpperLimitExclusive))
+ assert(collectedRows.forall(_.getLong(1) >= rowIndexLowerLimitInclusive))
+ }
+ }
+
+ test("SPARK-41896: Filter on constant and generated metadata attributes at
the same time") {
+ withTempPath { dir =>
+ val idColumnName = "id"
+ val partitionColumnName = "partition"
+ val numFiles = 4
+ val totalNumRows = 40
+
+ spark.range(end = totalNumRows)
+ .toDF(idColumnName)
+ .withColumn(partitionColumnName, col(idColumnName).mod(lit(numFiles)))
+ .write
+ .partitionBy(partitionColumnName)
+ .format("parquet")
+ .save(dir.getAbsolutePath)
+
+ // Get one file path.
+ val randomTableFilePath = spark.read.load(dir.getAbsolutePath)
+ .select(METADATA_FILE_PATH).collect().head.getString(0)
+
+ val halfTheNumberOfRowsPerFile = totalNumRows / (numFiles * 2)
+ val collectedRows = spark.read.load(dir.getAbsolutePath)
+ .where(col(METADATA_FILE_PATH).equalTo(lit(randomTableFilePath)))
+ .where(col(METADATA_ROW_INDEX).leq(lit(halfTheNumberOfRowsPerFile)))
Review Comment:
I added more asserts here: We select half the columns from one of the files.
What I assert now is that all rows do indeed come from one file and have a row
index lower than halfTheNumberOfRowsPerFile. That proves that the filter is
evaluated if I am not mistaken
--
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]
