sunchao commented on a change in pull request #33350:
URL: https://github.com/apache/spark/pull/33350#discussion_r671463471
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/PruneFileSourcePartitionsSuite.scala
##########
@@ -42,35 +43,27 @@ class PruneFileSourcePartitionsSuite extends
PrunePartitionSuiteBase {
test("PruneFileSourcePartitions should not change the output of
LogicalRelation") {
withTable("test") {
- withTempDir { dir =>
- sql(
- s"""
- |CREATE EXTERNAL TABLE test(i int)
- |PARTITIONED BY (p int)
- |STORED AS parquet
- |LOCATION '${dir.toURI}'""".stripMargin)
-
- val tableMeta = spark.sharedState.externalCatalog.getTable("default",
"test")
- val catalogFileIndex = new CatalogFileIndex(spark, tableMeta, 0)
-
- val dataSchema = StructType(tableMeta.schema.filterNot { f =>
- tableMeta.partitionColumnNames.contains(f.name)
- })
- val relation = HadoopFsRelation(
- location = catalogFileIndex,
- partitionSchema = tableMeta.partitionSchema,
- dataSchema = dataSchema,
- bucketSpec = None,
- fileFormat = new ParquetFileFormat(),
- options = Map.empty)(sparkSession = spark)
-
- val logicalRelation = LogicalRelation(relation, tableMeta)
- val query = Project(Seq(Symbol("i"), Symbol("p")),
- Filter(Symbol("p") === 1, logicalRelation)).analyze
-
- val optimized = Optimize.execute(query)
- assert(optimized.missingInput.isEmpty)
- }
+ spark.range(10).selectExpr("id", "id % 3 as
p").write.partitionBy("p").saveAsTable("test")
Review comment:
Thanks @dongjoon-hyun . I found it now. However I'm not sure whether
this matters for the test though: what it does is just 1) register table
metadata in the catalog, 2) create a `LogicalRelation` wrapping a
`HadoopFsRelation` which has the data and partition schema from the step 1),
and 3) feed it into the rule `PruneFileSourcePartitions` and see if the
`LogicalRelation`'s `expectedOutputAttributes` is properly set. Seems this is
irrelevant to what SerDe it is using?
--
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
