diff options
author | Cheng Hao <hao.cheng@intel.com> | 2015-06-11 14:03:08 -0700 |
---|---|---|
committer | Michael Armbrust <michael@databricks.com> | 2015-06-11 14:03:08 -0700 |
commit | 040f223c5b9ca724c9f2b4abb59c21b3a23720ba (patch) | |
tree | a05325ba5a7ef0fbd58996dfbaa0608bdfe54b2c | |
parent | c8d551d546979e126c91925487e30c353185e3ba (diff) | |
download | spark-040f223c5b9ca724c9f2b4abb59c21b3a23720ba.tar.gz spark-040f223c5b9ca724c9f2b4abb59c21b3a23720ba.tar.bz2 spark-040f223c5b9ca724c9f2b4abb59c21b3a23720ba.zip |
[SPARK-7915] [SQL] Support specifying the column list for target table in CTAS
```
create table t1 (a int, b string) as select key, value from src;
desc t1;
key int NULL
value string NULL
```
Thus Hive doesn't support specifying the column list for target table in CTAS, however, we should either throwing exception explicity, or supporting the this feature, we just pick up the later one, which seems useful and straightforward.
Author: Cheng Hao <hao.cheng@intel.com>
Closes #6458 from chenghao-intel/ctas_column and squashes the following commits:
d1fa9b6 [Cheng Hao] bug in unittest
4e701aa [Cheng Hao] update as feedback
f305ec1 [Cheng Hao] support specifying the column list for target table in CTAS
-rw-r--r-- | sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/CreateTableAsSelect.scala | 16 | ||||
-rw-r--r-- | sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala | 18 |
2 files changed, 30 insertions, 4 deletions
diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/CreateTableAsSelect.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/CreateTableAsSelect.scala index 7d3ec12c4e..87c36a8b61 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/CreateTableAsSelect.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/CreateTableAsSelect.scala @@ -50,17 +50,25 @@ case class CreateTableAsSelect( import org.apache.hadoop.io.Text import org.apache.hadoop.mapred.TextInputFormat - val withSchema = + val withFormat = tableDesc.copy( - schema = - query.output.map(c => - HiveColumn(c.name, HiveMetastoreTypes.toMetastoreType(c.dataType), null)), inputFormat = tableDesc.inputFormat.orElse(Some(classOf[TextInputFormat].getName)), outputFormat = tableDesc.outputFormat .orElse(Some(classOf[HiveIgnoreKeyTextOutputFormat[Text, Text]].getName)), serde = tableDesc.serde.orElse(Some(classOf[LazySimpleSerDe].getName()))) + + val withSchema = if (withFormat.schema.isEmpty) { + // Hive doesn't support specifying the column list for target table in CTAS + // However we don't think SparkSQL should follow that. + tableDesc.copy(schema = + query.output.map(c => + HiveColumn(c.name, HiveMetastoreTypes.toMetastoreType(c.dataType), null))) + } else { + withFormat + } + hiveContext.catalog.client.createTable(withSchema) // Get the Metastore Relation 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 40a35674e4..8bd4900497 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 @@ -360,6 +360,24 @@ class SQLQuerySuite extends QueryTest { } } + test("specifying the column list for CTAS") { + Seq((1, "111111"), (2, "222222")).toDF("key", "value").registerTempTable("mytable1") + + sql("create table gen__tmp(a int, b string) as select key, value from mytable1") + checkAnswer( + sql("SELECT a, b from gen__tmp"), + sql("select key, value from mytable1").collect()) + sql("DROP TABLE gen__tmp") + + sql("create table gen__tmp(a double, b double) as select key, value from mytable1") + checkAnswer( + sql("SELECT a, b from gen__tmp"), + sql("select cast(key as double), cast(value as double) from mytable1").collect()) + sql("DROP TABLE gen__tmp") + + sql("drop table mytable1") + } + test("command substitution") { sql("set tbl=src") checkAnswer( |