Repository: spark Updated Branches: refs/heads/master c8d551d54 -> 040f223c5
[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.ch...@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 Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/040f223c Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/040f223c Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/040f223c Branch: refs/heads/master Commit: 040f223c5b9ca724c9f2b4abb59c21b3a23720ba Parents: c8d551d Author: Cheng Hao <hao.ch...@intel.com> Authored: Thu Jun 11 14:03:08 2015 -0700 Committer: Michael Armbrust <mich...@databricks.com> Committed: Thu Jun 11 14:03:08 2015 -0700 ---------------------------------------------------------------------- .../sql/hive/execution/CreateTableAsSelect.scala | 16 ++++++++++++---- .../spark/sql/hive/execution/SQLQuerySuite.scala | 18 ++++++++++++++++++ 2 files changed, 30 insertions(+), 4 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/040f223c/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/CreateTableAsSelect.scala ---------------------------------------------------------------------- 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 7d3ec12..87c36a8 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 http://git-wip-us.apache.org/repos/asf/spark/blob/040f223c/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala ---------------------------------------------------------------------- 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 40a3567..8bd4900 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( --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org