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
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
|
/*
* 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.joins
import org.apache.spark.sql.{DataFrame, Row}
import org.apache.spark.sql.catalyst.expressions.{And, Expression, LessThan}
import org.apache.spark.sql.catalyst.planning.ExtractEquiJoinKeys
import org.apache.spark.sql.catalyst.plans.{Inner, LeftSemi}
import org.apache.spark.sql.catalyst.plans.logical.Join
import org.apache.spark.sql.execution.{SparkPlan, SparkPlanTest}
import org.apache.spark.sql.execution.exchange.EnsureRequirements
import org.apache.spark.sql.internal.SQLConf
import org.apache.spark.sql.test.SharedSQLContext
import org.apache.spark.sql.types.{DoubleType, IntegerType, StructType}
class SemiJoinSuite extends SparkPlanTest with SharedSQLContext {
private lazy val left = sqlContext.createDataFrame(
sparkContext.parallelize(Seq(
Row(1, 2.0),
Row(1, 2.0),
Row(2, 1.0),
Row(2, 1.0),
Row(3, 3.0),
Row(null, null),
Row(null, 5.0),
Row(6, null)
)), new StructType().add("a", IntegerType).add("b", DoubleType))
private lazy val right = sqlContext.createDataFrame(
sparkContext.parallelize(Seq(
Row(2, 3.0),
Row(2, 3.0),
Row(3, 2.0),
Row(4, 1.0),
Row(null, null),
Row(null, 5.0),
Row(6, null)
)), new StructType().add("c", IntegerType).add("d", DoubleType))
private lazy val condition = {
And((left.col("a") === right.col("c")).expr,
LessThan(left.col("b").expr, right.col("d").expr))
}
// Note: the input dataframes and expression must be evaluated lazily because
// the SQLContext should be used only within a test to keep SQL tests stable
private def testLeftSemiJoin(
testName: String,
leftRows: => DataFrame,
rightRows: => DataFrame,
condition: => Expression,
expectedAnswer: Seq[Product]): Unit = {
def extractJoinParts(): Option[ExtractEquiJoinKeys.ReturnType] = {
val join = Join(leftRows.logicalPlan, rightRows.logicalPlan, Inner, Some(condition))
ExtractEquiJoinKeys.unapply(join)
}
test(s"$testName using ShuffledHashJoin") {
extractJoinParts().foreach { case (joinType, leftKeys, rightKeys, boundCondition, _, _) =>
withSQLConf(SQLConf.SHUFFLE_PARTITIONS.key -> "1") {
checkAnswer2(leftRows, rightRows, (left: SparkPlan, right: SparkPlan) =>
EnsureRequirements(left.sqlContext.sessionState.conf).apply(
ShuffledHashJoin(
leftKeys, rightKeys, LeftSemi, BuildRight, boundCondition, left, right)),
expectedAnswer.map(Row.fromTuple),
sortAnswers = true)
}
}
}
test(s"$testName using BroadcastHashJoin") {
extractJoinParts().foreach { case (joinType, leftKeys, rightKeys, boundCondition, _, _) =>
withSQLConf(SQLConf.SHUFFLE_PARTITIONS.key -> "1") {
checkAnswer2(leftRows, rightRows, (left: SparkPlan, right: SparkPlan) =>
BroadcastHashJoin(
leftKeys, rightKeys, LeftSemi, BuildRight, boundCondition, left, right),
expectedAnswer.map(Row.fromTuple),
sortAnswers = true)
}
}
}
test(s"$testName using BroadcastNestedLoopJoin build left") {
withSQLConf(SQLConf.SHUFFLE_PARTITIONS.key -> "1") {
checkAnswer2(leftRows, rightRows, (left: SparkPlan, right: SparkPlan) =>
BroadcastNestedLoopJoin(left, right, BuildLeft, LeftSemi, Some(condition)),
expectedAnswer.map(Row.fromTuple),
sortAnswers = true)
}
}
test(s"$testName using BroadcastNestedLoopJoin build right") {
withSQLConf(SQLConf.SHUFFLE_PARTITIONS.key -> "1") {
checkAnswer2(leftRows, rightRows, (left: SparkPlan, right: SparkPlan) =>
BroadcastNestedLoopJoin(left, right, BuildRight, LeftSemi, Some(condition)),
expectedAnswer.map(Row.fromTuple),
sortAnswers = true)
}
}
}
testLeftSemiJoin(
"basic test",
left,
right,
condition,
Seq(
(2, 1.0),
(2, 1.0)
)
)
}
|