spark-reviews mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From rxin <...@git.apache.org>
Subject [GitHub] spark pull request: [SPARK-13078][SQL] Infrastructure for the inte...
Date Mon, 01 Feb 2016 07:02:32 GMT
Github user rxin commented on a diff in the pull request:

    https://github.com/apache/spark/pull/10982#discussion_r51385263
  
    --- Diff: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/interface.scala
---
    @@ -0,0 +1,172 @@
    +/*
    + * 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.catalog
    +
    +import org.apache.spark.sql.AnalysisException
    +
    +
    +/**
    + * Interface for the system catalog (of columns, partitions, tables, and databases).
    + *
    + * This is only used for non-temporary items, and implementations must be thread-safe
as they
    + * can be accessed in multiple threads.
    + */
    +abstract class Catalog {
    +
    +  // --------------------------------------------------------------------------
    +  // Databases
    +  // --------------------------------------------------------------------------
    +
    +  def createDatabase(dbDefinition: Database, ifNotExists: Boolean): Unit
    +
    +  def dropDatabase(
    +    db: String,
    +    ignoreIfNotExists: Boolean,
    +    cascade: Boolean): Unit
    +
    +  def alterDatabase(db: String, dbDefinition: Database): Unit
    +
    +  def getDatabase(db: String): Database
    +
    +  def listDatabases(): Seq[String]
    +
    +  def listDatabases(pattern: String): Seq[String]
    +
    +  // --------------------------------------------------------------------------
    +  // Tables
    +  // --------------------------------------------------------------------------
    +
    +  def createTable(db: String, tableDefinition: Table, ifNotExists: Boolean): Unit
    +
    +  def dropTable(db: String, table: String, ignoreIfNotExists: Boolean): Unit
    +
    +  def renameTable(db: String, oldName: String, newName: String): Unit
    +
    +  def alterTable(db: String, table: String, tableDefinition: Table): Unit
    +
    +  def getTable(db: String, table: String): Table
    +
    +  def listTables(db: String): Seq[String]
    +
    +  def listTables(db: String, pattern: String): Seq[String]
    +
    +  // --------------------------------------------------------------------------
    +  // Partitions
    +  // --------------------------------------------------------------------------
    +
    +  // TODO: need more functions for partitioning.
    +
    +  def alterPartition(db: String, table: String, part: TablePartition): Unit
    +
    +  def alterPartitions(db: String, table: String, parts: Seq[TablePartition]): Unit
    +
    +  // --------------------------------------------------------------------------
    +  // Functions
    +  // --------------------------------------------------------------------------
    +
    +  def createFunction(db: String, funcDefinition: Function, ifNotExists: Boolean): Unit
    +
    +  def dropFunction(db: String, funcName: String): Unit
    +
    +  def alterFunction(db: String, funcName: String, funcDefinition: Function): Unit
    +
    +  def getFunction(db: String, funcName: String): Function
    +
    +  def listFunctions(db: String, pattern: String): Seq[String]
    +
    +}
    +
    +
    +/**
    + * A function defined in the catalog.
    + *
    + * @param name name of the function
    + * @param className fully qualified class name, e.g. "org.apache.spark.util.MyFunc"
    + */
    +case class Function(
    +  name: String,
    +  className: String
    +)
    +
    +
    +/**
    + * Storage format, used to describe how a partition or a table is stored.
    + */
    +case class StorageFormat(
    +  locationUri: String,
    +  inputFormat: String,
    +  outputFormat: String,
    +  serde: String,
    +  serdeProperties: Map[String, String]
    +)
    +
    +
    +/**
    + * A column in a table.
    + */
    +case class Column(
    +  name: String,
    +  dataType: String,
    +  nullable: Boolean,
    +  comment: String
    +)
    +
    +
    +/**
    + * A partition (Hive style) defined in the catalog.
    + *
    + * @param values values for the partition columns
    + * @param storage storage format of the partition
    + */
    +case class TablePartition(
    +  values: Seq[String],
    +  storage: StorageFormat
    +)
    +
    +
    +/**
    + * A table defined in the catalog.
    + */
    +case class Table(
    --- End diff --
    
    added description.



---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---

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


Mime
View raw message