blob: 6598fa381aa3d9aab7baf521c9c277740c2c6a27 (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
|
/*
* 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
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.catalyst.InternalRow
import org.apache.spark.sql.catalyst.expressions.{Attribute, UnsafeProjection}
import org.apache.spark.sql.execution.metric.SQLMetrics
/**
* Physical plan node for scanning data from a local collection.
*/
case class LocalTableScanExec(
output: Seq[Attribute],
rows: Seq[InternalRow]) extends LeafExecNode {
override lazy val metrics = Map(
"numOutputRows" -> SQLMetrics.createMetric(sparkContext, "number of output rows"))
private val unsafeRows: Array[InternalRow] = {
if (rows.isEmpty) {
Array.empty
} else {
val proj = UnsafeProjection.create(output, output)
rows.map(r => proj(r).copy()).toArray
}
}
private lazy val numParallelism: Int = math.min(math.max(unsafeRows.length, 1),
sqlContext.sparkContext.defaultParallelism)
private lazy val rdd = sqlContext.sparkContext.parallelize(unsafeRows, numParallelism)
protected override def doExecute(): RDD[InternalRow] = {
val numOutputRows = longMetric("numOutputRows")
rdd.map { r =>
numOutputRows += 1
r
}
}
override protected def stringArgs: Iterator[Any] = {
if (rows.isEmpty) {
Iterator("<empty>", output)
} else {
Iterator(output)
}
}
override def executeCollect(): Array[InternalRow] = {
unsafeRows
}
override def executeTake(limit: Int): Array[InternalRow] = {
unsafeRows.take(limit)
}
}
|
