From f4a3d45e38f18278bbdb7cc32486ded50f76d54b Mon Sep 17 00:00:00 2001 From: Cheng Lian Date: Tue, 21 Jun 2016 11:58:33 -0700 Subject: [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 Closes #13810 from liancheng/spark-16037-follow-up-tests. --- .../spark/sql/hive/InsertIntoHiveTableSuite.scala | 48 ++++++++++++++++++++++ 1 file changed, 48 insertions(+) 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 46432512ba..d9ce1c3dc1 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) + } + } } -- cgit v1.2.3