-
Notifications
You must be signed in to change notification settings - Fork 28.1k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[SPARK-13664][SQL] Add a strategy for planning partitioned and bucketed scans of files #11646
Changes from 6 commits
94cede6
09df4c8
ef6ddaf
9990d41
4f29845
7ad3119
65596df
c1cf71e
35be8d5
4744b97
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,56 @@ | ||
/* | ||
* 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.execution.datasources | ||
|
||
import org.apache.spark.{Partition, TaskContext} | ||
import org.apache.spark.rdd.RDD | ||
import org.apache.spark.sql.SQLContext | ||
import org.apache.spark.sql.catalyst.InternalRow | ||
|
||
/** | ||
* A single file that should be read, along with partition column values that | ||
* need to be prepended to each row. The reading should start at the first | ||
* valid record found after `offset`. | ||
*/ | ||
case class PartitionedFile( | ||
partitionValues: InternalRow, | ||
filePath: String, | ||
start: Long, | ||
length: Long) | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Should this has something about locations? There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Good question. We should add locality information here, but it probably belongs in I'll add a comment that this strategy does not yet take locality into account. |
||
|
||
/** | ||
* A collection of files that should be read as a single task possibly from multiple partitioned | ||
* directories. | ||
* | ||
* IMPLEMENT ME: This is just a placeholder for a future implementation. | ||
*/ | ||
case class FilePartition(val index: Int, files: Seq[PartitionedFile]) extends Partition | ||
|
||
class FileScanRDD( | ||
@transient val sqlContext: SQLContext, | ||
readFunction: (PartitionedFile) => Iterator[InternalRow], | ||
@transient val filePartitions: Seq[FilePartition]) | ||
extends RDD[InternalRow](sqlContext.sparkContext, Nil) { | ||
|
||
|
||
override def compute(split: Partition, context: TaskContext): Iterator[InternalRow] = { | ||
throw new NotImplementedError("Not Implemented Yet") | ||
} | ||
|
||
override protected def getPartitions: Array[Partition] = Array.empty | ||
} |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
offset -> start