You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spark.apache.org by li...@apache.org on 2016/11/22 23:10:59 UTC
spark git commit: [SPARK-16803][SQL] SaveAsTable does not work when
target table is a Hive serde table
Repository: spark
Updated Branches:
refs/heads/master 2fd101b2f -> 9c42d4a76
[SPARK-16803][SQL] SaveAsTable does not work when target table is a Hive serde table
### What changes were proposed in this pull request?
In Spark 2.0, `SaveAsTable` does not work when the target table is a Hive serde table, but Spark 1.6 works.
**Spark 1.6**
``` Scala
scala> sql("create table sample.sample stored as SEQUENCEFILE as select 1 as key, 'abc' as value")
res2: org.apache.spark.sql.DataFrame = []
scala> val df = sql("select key, value as value from sample.sample")
df: org.apache.spark.sql.DataFrame = [key: int, value: string]
scala> df.write.mode("append").saveAsTable("sample.sample")
scala> sql("select * from sample.sample").show()
+---+-----+
|key|value|
+---+-----+
| 1| abc|
| 1| abc|
+---+-----+
```
**Spark 2.0**
``` Scala
scala> df.write.mode("append").saveAsTable("sample.sample")
org.apache.spark.sql.AnalysisException: Saving data in MetastoreRelation sample, sample
is not supported.;
```
So far, we do not plan to support it in Spark 2.1 due to the risk. Spark 1.6 works because it internally uses insertInto. But, if we change it back it will break the semantic of saveAsTable (this method uses by-name resolution instead of using by-position resolution used by insertInto). More extra changes are needed to support `hive` as a `format` in DataFrameWriter.
Instead, users should use insertInto API. This PR corrects the error messages. Users can understand how to bypass it before we support it in a separate PR.
### How was this patch tested?
Test cases are added
Author: gatorsmile <ga...@gmail.com>
Closes #15926 from gatorsmile/saveAsTableFix5.
Project: http://git-wip-us.apache.org/repos/asf/spark/repo
Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/9c42d4a7
Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/9c42d4a7
Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/9c42d4a7
Branch: refs/heads/master
Commit: 9c42d4a76ca8046fcca2e20067f2aa461977e65a
Parents: 2fd101b
Author: gatorsmile <ga...@gmail.com>
Authored: Tue Nov 22 15:10:49 2016 -0800
Committer: gatorsmile <ga...@gmail.com>
Committed: Tue Nov 22 15:10:49 2016 -0800
----------------------------------------------------------------------
.../command/createDataSourceTables.scala | 4 ++++
.../sql/hive/MetastoreDataSourcesSuite.scala | 20 ++++++++++++++++++++
2 files changed, 24 insertions(+)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/spark/blob/9c42d4a7/sql/core/src/main/scala/org/apache/spark/sql/execution/command/createDataSourceTables.scala
----------------------------------------------------------------------
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/command/createDataSourceTables.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/command/createDataSourceTables.scala
index 7e16e43..add732c 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/command/createDataSourceTables.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/command/createDataSourceTables.scala
@@ -175,6 +175,10 @@ case class CreateDataSourceTableAsSelectCommand(
existingSchema = Some(l.schema)
case s: SimpleCatalogRelation if DDLUtils.isDatasourceTable(s.metadata) =>
existingSchema = Some(s.metadata.schema)
+ case c: CatalogRelation if c.catalogTable.provider == Some(DDLUtils.HIVE_PROVIDER) =>
+ throw new AnalysisException("Saving data in the Hive serde table " +
+ s"${c.catalogTable.identifier} is not supported yet. Please use the " +
+ "insertInto() API as an alternative..")
case o =>
throw new AnalysisException(s"Saving data in ${o.toString} is not supported.")
}
http://git-wip-us.apache.org/repos/asf/spark/blob/9c42d4a7/sql/hive/src/test/scala/org/apache/spark/sql/hive/MetastoreDataSourcesSuite.scala
----------------------------------------------------------------------
diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/MetastoreDataSourcesSuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/MetastoreDataSourcesSuite.scala
index 4ab1a54..c7cc75f 100644
--- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/MetastoreDataSourcesSuite.scala
+++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/MetastoreDataSourcesSuite.scala
@@ -413,6 +413,26 @@ class MetastoreDataSourcesSuite extends QueryTest with SQLTestUtils with TestHiv
}
}
+ test("saveAsTable(CTAS) using append and insertInto when the target table is Hive serde") {
+ val tableName = "tab1"
+ withTable(tableName) {
+ sql(s"CREATE TABLE $tableName STORED AS SEQUENCEFILE AS SELECT 1 AS key, 'abc' AS value")
+
+ val df = sql(s"SELECT key, value FROM $tableName")
+ val e = intercept[AnalysisException] {
+ df.write.mode(SaveMode.Append).saveAsTable(tableName)
+ }.getMessage
+ assert(e.contains("Saving data in the Hive serde table `default`.`tab1` is not supported " +
+ "yet. Please use the insertInto() API as an alternative."))
+
+ df.write.insertInto(tableName)
+ checkAnswer(
+ sql(s"SELECT * FROM $tableName"),
+ Row(1, "abc") :: Row(1, "abc") :: Nil
+ )
+ }
+ }
+
test("SPARK-5839 HiveMetastoreCatalog does not recognize table aliases of data source tables.") {
withTable("savedJsonTable") {
// Save the df as a managed table (by not specifying the path).
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org