-
Notifications
You must be signed in to change notification settings - Fork 28.2k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
[SPARK-13080][SQL] Implement new Catalog API using Hive
## What changes were proposed in this pull request? This is a step towards merging `SQLContext` and `HiveContext`. A new internal Catalog API was introduced in #10982 and extended in #11069. This patch introduces an implementation of this API using `HiveClient`, an existing interface to Hive. It also extends `HiveClient` with additional calls to Hive that are needed to complete the catalog implementation. *Where should I start reviewing?* The new catalog introduced is `HiveCatalog`. This class is relatively simple because it just calls `HiveClientImpl`, where most of the new logic is. I would not start with `HiveClient`, `HiveQl`, or `HiveMetastoreCatalog`, which are modified mainly because of a refactor. *Why is this patch so big?* I had to refactor HiveClient to remove an intermediate representation of databases, tables, partitions etc. After this refactor `CatalogTable` convert directly to and from `HiveTable` (etc.). Otherwise we would have to first convert `CatalogTable` to the intermediate representation and then convert that to HiveTable, which is messy. The new class hierarchy is as follows: ``` org.apache.spark.sql.catalyst.catalog.Catalog - org.apache.spark.sql.catalyst.catalog.InMemoryCatalog - org.apache.spark.sql.hive.HiveCatalog ``` Note that, as of this patch, none of these classes are currently used anywhere yet. This will come in the future before the Spark 2.0 release. ## How was the this patch tested? All existing unit tests, and HiveCatalogSuite that extends CatalogTestCases. Author: Andrew Or <andrew@databricks.com> Author: Reynold Xin <rxin@databricks.com> Closes #11293 from rxin/hive-catalog.
- Loading branch information
Showing
21 changed files
with
1,483 additions
and
700 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
52 changes: 52 additions & 0 deletions
52
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/NoSuchItemException.scala
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,52 @@ | ||
/* | ||
* Licensed to the Apache Software Foundation (ASF) under one or more | ||
* contributor license agreements. See the NOTICE file distributed with | ||
* this work for additional information regarding copyright ownership. | ||
* The ASF licenses this file to You under the Apache License, Version 2.0 | ||
* (the "License"); you may not use this file except in compliance with | ||
* the License. You may obtain a copy of the License at | ||
* | ||
* http://www.apache.org/licenses/LICENSE-2.0 | ||
* | ||
* Unless required by applicable law or agreed to in writing, software | ||
* distributed under the License is distributed on an "AS IS" BASIS, | ||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
* See the License for the specific language governing permissions and | ||
* limitations under the License. | ||
*/ | ||
|
||
package org.apache.spark.sql.catalyst.analysis | ||
|
||
import org.apache.spark.sql.catalyst.catalog.Catalog.TablePartitionSpec | ||
|
||
|
||
/** | ||
* Thrown by a catalog when an item cannot be found. The analyzer will rethrow the exception | ||
* as an [[org.apache.spark.sql.AnalysisException]] with the correct position information. | ||
*/ | ||
abstract class NoSuchItemException extends Exception { | ||
override def getMessage: String | ||
} | ||
|
||
class NoSuchDatabaseException(db: String) extends NoSuchItemException { | ||
override def getMessage: String = s"Database $db not found" | ||
} | ||
|
||
class NoSuchTableException(db: String, table: String) extends NoSuchItemException { | ||
override def getMessage: String = s"Table $table not found in database $db" | ||
} | ||
|
||
class NoSuchPartitionException( | ||
db: String, | ||
table: String, | ||
spec: TablePartitionSpec) | ||
extends NoSuchItemException { | ||
|
||
override def getMessage: String = { | ||
s"Partition not found in table $table database $db:\n" + spec.mkString("\n") | ||
} | ||
} | ||
|
||
class NoSuchFunctionException(db: String, func: String) extends NoSuchItemException { | ||
override def getMessage: String = s"Function $func not found in database $db" | ||
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.