You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spark.apache.org by yh...@apache.org on 2016/06/21 18:58:37 UTC
spark git commit: [SPARK-16037][SQL] Follow-up: add
DataFrameWriter.insertInto() test cases for by position resolution
Repository: spark
Updated Branches:
refs/heads/master b76e35537 -> f4a3d45e3
[SPARK-16037][SQL] Follow-up: add DataFrameWriter.insertInto() test cases for by position resolution
## What changes were proposed in this pull request?
This PR migrates some test cases introduced in #12313 as a follow-up of #13754 and #13766. These test cases cover `DataFrameWriter.insertInto()`, while the former two only cover SQL `INSERT` statements.
Note that the `testPartitionedTable` utility method tests both Hive SerDe tables and data source tables.
## How was this patch tested?
N/A
Author: Cheng Lian <li...@databricks.com>
Closes #13810 from liancheng/spark-16037-follow-up-tests.
Project: http://git-wip-us.apache.org/repos/asf/spark/repo
Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/f4a3d45e
Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/f4a3d45e
Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/f4a3d45e
Branch: refs/heads/master
Commit: f4a3d45e38f18278bbdb7cc32486ded50f76d54b
Parents: b76e355
Author: Cheng Lian <li...@databricks.com>
Authored: Tue Jun 21 11:58:33 2016 -0700
Committer: Yin Huai <yh...@databricks.com>
Committed: Tue Jun 21 11:58:33 2016 -0700
----------------------------------------------------------------------
.../sql/hive/InsertIntoHiveTableSuite.scala | 48 ++++++++++++++++++++
1 file changed, 48 insertions(+)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/spark/blob/f4a3d45e/sql/hive/src/test/scala/org/apache/spark/sql/hive/InsertIntoHiveTableSuite.scala
----------------------------------------------------------------------
diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/InsertIntoHiveTableSuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/InsertIntoHiveTableSuite.scala
index 4643251..d9ce1c3 100644
--- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/InsertIntoHiveTableSuite.scala
+++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/InsertIntoHiveTableSuite.scala
@@ -469,4 +469,52 @@ class InsertIntoHiveTableSuite extends QueryTest with TestHiveSingleton with Bef
)
}
}
+
+ testPartitionedTable("insertInto() should match columns by position and ignore column names") {
+ tableName =>
+ withSQLConf("hive.exec.dynamic.partition.mode" -> "nonstrict") {
+ // Columns `df.c` and `df.d` are resolved by position, and thus mapped to partition columns
+ // `b` and `c` of the target table.
+ val df = Seq((1, 2, 3, 4)).toDF("a", "b", "c", "d")
+ df.write.insertInto(tableName)
+
+ checkAnswer(
+ sql(s"SELECT a, b, c, d FROM $tableName"),
+ Row(1, 3, 4, 2)
+ )
+ }
+ }
+
+ testPartitionedTable("insertInto() should match unnamed columns by position") {
+ tableName =>
+ withSQLConf("hive.exec.dynamic.partition.mode" -> "nonstrict") {
+ // Columns `c + 1` and `d + 1` are resolved by position, and thus mapped to partition
+ // columns `b` and `c` of the target table.
+ val df = Seq((1, 2, 3, 4)).toDF("a", "b", "c", "d")
+ df.select('a + 1, 'b + 1, 'c + 1, 'd + 1).write.insertInto(tableName)
+
+ checkAnswer(
+ sql(s"SELECT a, b, c, d FROM $tableName"),
+ Row(2, 4, 5, 3)
+ )
+ }
+ }
+
+ testPartitionedTable("insertInto() should reject missing columns") {
+ tableName =>
+ sql("CREATE TABLE t (a INT, b INT)")
+
+ intercept[AnalysisException] {
+ spark.table("t").write.insertInto(tableName)
+ }
+ }
+
+ testPartitionedTable("insertInto() should reject extra columns") {
+ tableName =>
+ sql("CREATE TABLE t (a INT, b INT, c INT, d INT, e INT)")
+
+ intercept[AnalysisException] {
+ spark.table("t").write.insertInto(tableName)
+ }
+ }
}
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org