From ffee4f1cefb0dfd8d9145ee3be82c6f7b799870b Mon Sep 17 00:00:00 2001
From: Cheng Lian <lian@databricks.com>
Date: Fri, 10 Mar 2017 15:19:32 -0800
Subject: [PATCH] [SPARK-19905][SQL] Bring back Dataset.inputFiles for Hive
SerDe tables
## What changes were proposed in this pull request?
`Dataset.inputFiles` works by matching `FileRelation`s in the query plan. In Spark 2.1, Hive SerDe tables are represented by `MetastoreRelation`, which inherits from `FileRelation`. However, in Spark 2.2, Hive SerDe tables are now represented by `CatalogRelation`, which doesn't inherit from `FileRelation` anymore, due to the unification of Hive SerDe tables and data source tables. This change breaks `Dataset.inputFiles` for Hive SerDe tables.
This PR tries to fix this issue by explicitly matching `CatalogRelation`s that are Hive SerDe tables in `Dataset.inputFiles`. Note that we can't make `CatalogRelation` inherit from `FileRelation` since not all `CatalogRelation`s are file based (e.g., JDBC data source tables).
## How was this patch tested?
New test case added in `HiveDDLSuite`.
Author: Cheng Lian <lian@databricks.com>
Closes #17247 from liancheng/spark-19905-hive-table-input-files.
---
.../src/main/scala/org/apache/spark/sql/Dataset.scala | 3 +++
.../spark/sql/hive/execution/HiveDDLSuite.scala | 11 +++++++++++
2 files changed, 14 insertions(+)
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala b/sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala
index 0a4d3a93a0..520663f624 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala
@@ -36,6 +36,7 @@ import org.apache.spark.broadcast.Broadcast
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.catalyst._
import org.apache.spark.sql.catalyst.analysis._
+import org.apache.spark.sql.catalyst.catalog.CatalogRelation
import org.apache.spark.sql.catalyst.encoders._
import org.apache.spark.sql.catalyst.expressions._
import org.apache.spark.sql.catalyst.expressions.aggregate._
@@ -2734,6 +2735,8 @@ class Dataset[T] private[sql](
fsBasedRelation.inputFiles
case fr: FileRelation =>
fr.inputFiles
+ case r: CatalogRelation if DDLUtils.isHiveTable(r.tableMeta) =>
+ r.tableMeta.storage.locationUri.map(_.toString).toArray
}.flatten
files.toSet.toArray
}
diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveDDLSuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveDDLSuite.scala
index 23aea24697..79ad156c55 100644
--- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveDDLSuite.scala
+++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveDDLSuite.scala
@@ -1865,4 +1865,15 @@ class HiveDDLSuite
}
}
}
+
+ test("SPARK-19905: Hive SerDe table input paths") {
+ withTable("spark_19905") {
+ withTempView("spark_19905_view") {
+ spark.range(10).createOrReplaceTempView("spark_19905_view")
+ sql("CREATE TABLE spark_19905 STORED AS RCFILE AS SELECT * FROM spark_19905_view")
+ assert(spark.table("spark_19905").inputFiles.nonEmpty)
+ assert(sql("SELECT input_file_name() FROM spark_19905").count() > 0)
+ }
+ }
+ }
}
--
GitLab