diff options
author | gatorsmile <gatorsmile@gmail.com> | 2016-08-08 22:26:44 +0800 |
---|---|---|
committer | Wenchen Fan <wenchen@databricks.com> | 2016-08-08 22:26:44 +0800 |
commit | ab126909ce381842dbb057d480a1f9bee1b4f38e (patch) | |
tree | 1e1c774ca8bc45e82be2f392ed4dee4b32e23adf /sql/hive | |
parent | 94a9d11ed1f61205af8067bf17d14dc93935ddf8 (diff) | |
download | spark-ab126909ce381842dbb057d480a1f9bee1b4f38e.tar.gz spark-ab126909ce381842dbb057d480a1f9bee1b4f38e.tar.bz2 spark-ab126909ce381842dbb057d480a1f9bee1b4f38e.zip |
[SPARK-16457][SQL] Fix Wrong Messages when CTAS with a Partition By Clause
#### What changes were proposed in this pull request?
When doing a CTAS with a Partition By clause, we got a wrong error message.
For example,
```SQL
CREATE TABLE gen__tmp
PARTITIONED BY (key string)
AS SELECT key, value FROM mytable1
```
The error message we get now is like
```
Operation not allowed: Schema may not be specified in a Create Table As Select (CTAS) statement(line 2, pos 0)
```
However, based on the code, the message we should get is like
```
Operation not allowed: A Create Table As Select (CTAS) statement is not allowed to create a partitioned table using Hive's file formats. Please use the syntax of "CREATE TABLE tableName USING dataSource OPTIONS (...) PARTITIONED BY ...\" to create a partitioned table through a CTAS statement.(line 2, pos 0)
```
Currently, partitioning columns is part of the schema. This PR fixes the bug by changing the detection orders.
#### How was this patch tested?
Added test cases.
Author: gatorsmile <gatorsmile@gmail.com>
Closes #14113 from gatorsmile/ctas.
Diffstat (limited to 'sql/hive')
-rw-r--r-- | sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala | 36 |
1 files changed, 26 insertions, 10 deletions
diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala index cba6aa53f1..b659325a62 100644 --- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala +++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala @@ -642,19 +642,35 @@ class SQLQuerySuite extends QueryTest with SQLTestUtils with TestHiveSingleton { } test("specifying the column list for CTAS") { - Seq((1, "111111"), (2, "222222")).toDF("key", "value").createOrReplaceTempView("mytable1") + withTempView("mytable1") { + Seq((1, "111111"), (2, "222222")).toDF("key", "value").createOrReplaceTempView("mytable1") + withTable("gen__tmp") { + sql("create table gen__tmp as select key as a, value as b from mytable1") + checkAnswer( + sql("SELECT a, b from gen__tmp"), + sql("select key, value from mytable1").collect()) + } - sql("create table gen__tmp as select key as a, value as b from mytable1") - checkAnswer( - sql("SELECT a, b from gen__tmp"), - sql("select key, value from mytable1").collect()) - sql("DROP TABLE gen__tmp") + withTable("gen__tmp") { + val e = intercept[AnalysisException] { + sql("create table gen__tmp(a int, b string) as select key, value from mytable1") + }.getMessage + assert(e.contains("Schema may not be specified in a Create Table As Select (CTAS)")) + } - intercept[AnalysisException] { - sql("create table gen__tmp(a int, b string) as select key, value from mytable1") + withTable("gen__tmp") { + val e = intercept[AnalysisException] { + sql( + """ + |CREATE TABLE gen__tmp + |PARTITIONED BY (key string) + |AS SELECT key, value FROM mytable1 + """.stripMargin) + }.getMessage + assert(e.contains("A Create Table As Select (CTAS) statement is not allowed to " + + "create a partitioned table using Hive's file formats")) + } } - - sql("drop table mytable1") } test("command substitution") { |