You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spark.apache.org by an...@apache.org on 2016/04/14 20:08:19 UTC

spark git commit: [SPARK-14592][SQL] Native support for CREATE TABLE LIKE DDL command

Repository: spark
Updated Branches:
  refs/heads/master c971aee40 -> 28efdd3fd


[SPARK-14592][SQL] Native support for CREATE TABLE LIKE DDL command

## What changes were proposed in this pull request?
JIRA: https://issues.apache.org/jira/browse/SPARK-14592

This patch adds native support for DDL command `CREATE TABLE LIKE`.

The SQL syntax is like:

    CREATE TABLE table_name LIKE existing_table
    CREATE TABLE IF NOT EXISTS table_name LIKE existing_table

## How was this patch tested?
`HiveDDLCommandSuite`. `HiveQuerySuite` already tests `CREATE TABLE LIKE`.

Author: Liang-Chi Hsieh <si...@tw.ibm.com>

This patch had conflicts when merged, resolved by
Committer: Andrew Or <an...@databricks.com>

Closes #12362 from viirya/create-table-like.


Project: http://git-wip-us.apache.org/repos/asf/spark/repo
Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/28efdd3f
Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/28efdd3f
Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/28efdd3f

Branch: refs/heads/master
Commit: 28efdd3fd789fa2ebed5be03b36ca0f682e37669
Parents: c971aee
Author: Liang-Chi Hsieh <si...@tw.ibm.com>
Authored: Thu Apr 14 11:08:08 2016 -0700
Committer: Andrew Or <an...@databricks.com>
Committed: Thu Apr 14 11:08:08 2016 -0700

----------------------------------------------------------------------
 .../apache/spark/sql/catalyst/parser/SqlBase.g4 |  7 ++--
 .../spark/sql/execution/command/tables.scala    | 40 +++++++++++++++++++-
 .../hive/execution/HiveCompatibilitySuite.scala |  4 +-
 .../sql/hive/execution/HiveSqlParser.scala      | 13 ++++++-
 .../spark/sql/hive/HiveDDLCommandSuite.scala    | 24 +++++++++++-
 5 files changed, 79 insertions(+), 9 deletions(-)
----------------------------------------------------------------------


http://git-wip-us.apache.org/repos/asf/spark/blob/28efdd3f/sql/catalyst/src/main/antlr4/org/apache/spark/sql/catalyst/parser/SqlBase.g4
----------------------------------------------------------------------
diff --git a/sql/catalyst/src/main/antlr4/org/apache/spark/sql/catalyst/parser/SqlBase.g4 b/sql/catalyst/src/main/antlr4/org/apache/spark/sql/catalyst/parser/SqlBase.g4
index a937ad1..9cf2dd2 100644
--- a/sql/catalyst/src/main/antlr4/org/apache/spark/sql/catalyst/parser/SqlBase.g4
+++ b/sql/catalyst/src/main/antlr4/org/apache/spark/sql/catalyst/parser/SqlBase.g4
@@ -55,6 +55,8 @@ statement
         rowFormat?  createFileFormat? locationSpec?
         (TBLPROPERTIES tablePropertyList)?
         (AS? query)?                                                   #createTable
+    | CREATE TABLE (IF NOT EXISTS)? target=tableIdentifier
+        LIKE source=tableIdentifier                                    #createTableLike
     | ANALYZE TABLE tableIdentifier partitionSpec? COMPUTE STATISTICS
         (identifier | FOR COLUMNS identifierSeq?)?                     #analyze
     | ALTER (TABLE | VIEW) from=tableIdentifier
@@ -136,10 +138,7 @@ statement
     ;
 
 hiveNativeCommands
-    : createTableHeader LIKE tableIdentifier
-        rowFormat?  createFileFormat? locationSpec?
-        (TBLPROPERTIES tablePropertyList)?
-    | DELETE FROM tableIdentifier (WHERE booleanExpression)?
+    : DELETE FROM tableIdentifier (WHERE booleanExpression)?
     | TRUNCATE TABLE tableIdentifier partitionSpec?
         (COLUMNS identifierList)?
     | SHOW COLUMNS (FROM | IN) tableIdentifier ((FROM|IN) identifier)?

http://git-wip-us.apache.org/repos/asf/spark/blob/28efdd3f/sql/core/src/main/scala/org/apache/spark/sql/execution/command/tables.scala
----------------------------------------------------------------------
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/command/tables.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/command/tables.scala
index e315598..0b41985 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/command/tables.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/command/tables.scala
@@ -17,9 +17,45 @@
 
 package org.apache.spark.sql.execution.command
 
-import org.apache.spark.sql.{Row, SQLContext}
+import org.apache.spark.sql.{AnalysisException, Row, SQLContext}
 import org.apache.spark.sql.catalyst.TableIdentifier
-import org.apache.spark.sql.catalyst.catalog.CatalogTable
+import org.apache.spark.sql.catalyst.catalog.{CatalogTable, CatalogTableType}
+
+/**
+ * A command to create a table with the same definition of the given existing table.
+ *
+ * The syntax of using this command in SQL is:
+ * {{{
+ *   CREATE TABLE [IF NOT EXISTS] [db_name.]table_name
+ *   LIKE [other_db_name.]existing_table_name
+ * }}}
+ */
+case class CreateTableLike(
+    targetTable: TableIdentifier,
+    sourceTable: TableIdentifier,
+    ifNotExists: Boolean) extends RunnableCommand {
+
+  override def run(sqlContext: SQLContext): Seq[Row] = {
+    val catalog = sqlContext.sessionState.catalog
+    if (!catalog.tableExists(sourceTable)) {
+      throw new AnalysisException(
+        s"Source table in CREATE TABLE LIKE does not exist: '$sourceTable'")
+    }
+    if (catalog.isTemporaryTable(sourceTable)) {
+      throw new AnalysisException(
+        s"Source table in CREATE TABLE LIKE cannot be temporary: '$sourceTable'")
+    }
+
+    val tableToCreate = catalog.getTableMetadata(sourceTable).copy(
+      identifier = targetTable,
+      tableType = CatalogTableType.MANAGED_TABLE,
+      createTime = System.currentTimeMillis,
+      lastAccessTime = -1).withNewStorage(locationUri = None)
+
+    catalog.createTable(tableToCreate, ifNotExists)
+    Seq.empty[Row]
+  }
+}
 
 
 // TODO: move the rest of the table commands from ddl.scala to this file

http://git-wip-us.apache.org/repos/asf/spark/blob/28efdd3f/sql/hive/compatibility/src/test/scala/org/apache/spark/sql/hive/execution/HiveCompatibilitySuite.scala
----------------------------------------------------------------------
diff --git a/sql/hive/compatibility/src/test/scala/org/apache/spark/sql/hive/execution/HiveCompatibilitySuite.scala b/sql/hive/compatibility/src/test/scala/org/apache/spark/sql/hive/execution/HiveCompatibilitySuite.scala
index a45d180..989e68a 100644
--- a/sql/hive/compatibility/src/test/scala/org/apache/spark/sql/hive/execution/HiveCompatibilitySuite.scala
+++ b/sql/hive/compatibility/src/test/scala/org/apache/spark/sql/hive/execution/HiveCompatibilitySuite.scala
@@ -416,6 +416,9 @@ class HiveCompatibilitySuite extends HiveQueryFileTest with BeforeAndAfter {
     "skewjoinopt18",
     "skewjoinopt9",
 
+    // This test tries to create a table like with TBLPROPERTIES clause, which we don't support.
+    "create_like_tbl_props",
+
     // Index commands are not supported
     "drop_index",
     "drop_index_removes_partition_dirs",
@@ -537,7 +540,6 @@ class HiveCompatibilitySuite extends HiveQueryFileTest with BeforeAndAfter {
     "count",
     "cp_mj_rc",
     "create_insert_outputformat",
-    "create_like_tbl_props",
     "create_nested_type",
     "create_struct_table",
     "create_view_translate",

http://git-wip-us.apache.org/repos/asf/spark/blob/28efdd3f/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveSqlParser.scala
----------------------------------------------------------------------
diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveSqlParser.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveSqlParser.scala
index 8c70707..a97b65e 100644
--- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveSqlParser.scala
+++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveSqlParser.scala
@@ -31,8 +31,10 @@ import org.apache.spark.sql.catalyst.parser._
 import org.apache.spark.sql.catalyst.parser.SqlBaseParser._
 import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan
 import org.apache.spark.sql.execution.SparkSqlAstBuilder
-import org.apache.spark.sql.execution.command.CreateTable
+import org.apache.spark.sql.execution.command.{CreateTable, CreateTableLike}
 import org.apache.spark.sql.hive.{CreateTableAsSelect => CTAS, CreateViewAsSelect => CreateView, HiveSerDe}
+import org.apache.spark.sql.hive.{HiveGenericUDTF, HiveMetastoreTypes, HiveSerDe}
+import org.apache.spark.sql.hive.HiveShim.HiveFunctionWrapper
 
 /**
  * Concrete parser for HiveQl statements.
@@ -232,6 +234,15 @@ class HiveSqlAstBuilder extends SparkSqlAstBuilder {
   }
 
   /**
+   * Create a [[CreateTableLike]] command.
+   */
+  override def visitCreateTableLike(ctx: CreateTableLikeContext): LogicalPlan = withOrigin(ctx) {
+    val targetTable = visitTableIdentifier(ctx.target)
+    val sourceTable = visitTableIdentifier(ctx.source)
+    CreateTableLike(targetTable, sourceTable, ctx.EXISTS != null)
+  }
+
+  /**
    * Create or replace a view. This creates a [[CreateViewAsSelect]] command.
    *
    * For example:

http://git-wip-us.apache.org/repos/asf/spark/blob/28efdd3f/sql/hive/src/test/scala/org/apache/spark/sql/hive/HiveDDLCommandSuite.scala
----------------------------------------------------------------------
diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/HiveDDLCommandSuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/HiveDDLCommandSuite.scala
index b87f035..110c6d1 100644
--- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/HiveDDLCommandSuite.scala
+++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/HiveDDLCommandSuite.scala
@@ -29,7 +29,7 @@ import org.apache.spark.sql.catalyst.expressions.JsonTuple
 import org.apache.spark.sql.catalyst.parser.ParseException
 import org.apache.spark.sql.catalyst.plans.PlanTest
 import org.apache.spark.sql.catalyst.plans.logical.{Generate, ScriptTransformation}
-import org.apache.spark.sql.execution.command.CreateTable
+import org.apache.spark.sql.execution.command.{CreateTable, CreateTableLike}
 import org.apache.spark.sql.hive.execution.{HiveNativeCommand, HiveSqlParser}
 
 class HiveDDLCommandSuite extends PlanTest {
@@ -557,4 +557,26 @@ class HiveDDLCommandSuite extends PlanTest {
     assertUnsupported("MSCK REPAIR TABLE tab1")
   }
 
+  test("create table like") {
+    val v1 = "CREATE TABLE table1 LIKE table2"
+    val (target, source, exists) = parser.parsePlan(v1).collect {
+      case CreateTableLike(t, s, allowExisting) => (t, s, allowExisting)
+    }.head
+    assert(exists == false)
+    assert(target.database.isEmpty)
+    assert(target.table == "table1")
+    assert(source.database.isEmpty)
+    assert(source.table == "table2")
+
+    val v2 = "CREATE TABLE IF NOT EXISTS table1 LIKE table2"
+    val (target2, source2, exists2) = parser.parsePlan(v2).collect {
+      case CreateTableLike(t, s, allowExisting) => (t, s, allowExisting)
+    }.head
+    assert(exists2)
+    assert(target2.database.isEmpty)
+    assert(target2.table == "table1")
+    assert(source2.database.isEmpty)
+    assert(source2.table == "table2")
+  }
+
 }


---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org