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
|
/*
* 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.plans
import org.apache.spark.SparkFunSuite
import org.apache.spark.sql.catalyst.expressions._
import org.apache.spark.sql.catalyst.expressions.aggregate.AggregateExpression
import org.apache.spark.sql.catalyst.plans.logical.{Filter, LogicalPlan, OneRowRelation, Sample}
import org.apache.spark.sql.catalyst.util._
/**
* Provides helper methods for comparing plans.
*/
abstract class PlanTest extends SparkFunSuite with PredicateHelper {
/**
* Since attribute references are given globally unique ids during analysis,
* we must normalize them to check if two different queries are identical.
*/
protected def normalizeExprIds(plan: LogicalPlan) = {
plan transformAllExpressions {
case s: ScalarSubquery =>
ScalarSubquery(s.query, ExprId(0))
case a: AttributeReference =>
AttributeReference(a.name, a.dataType, a.nullable)(exprId = ExprId(0))
case a: Alias =>
Alias(a.child, a.name)(exprId = ExprId(0))
case ae: AggregateExpression =>
ae.copy(resultId = ExprId(0))
}
}
/**
* Normalizes plans:
* - Filter the filter conditions that appear in a plan. For instance,
* ((expr 1 && expr 2) && expr 3), (expr 1 && expr 2 && expr 3), (expr 3 && (expr 1 && expr 2)
* etc., will all now be equivalent.
* - Sample the seed will replaced by 0L.
*/
private def normalizePlan(plan: LogicalPlan): LogicalPlan = {
plan transform {
case filter @ Filter(condition: Expression, child: LogicalPlan) =>
Filter(splitConjunctivePredicates(condition).sortBy(_.hashCode()).reduce(And), child)
case sample: Sample =>
sample.copy(seed = 0L)(true)
}
}
/** Fails the test if the two plans do not match */
protected def comparePlans(plan1: LogicalPlan, plan2: LogicalPlan) {
val normalized1 = normalizePlan(normalizeExprIds(plan1))
val normalized2 = normalizePlan(normalizeExprIds(plan2))
if (normalized1 != normalized2) {
fail(
s"""
|== FAIL: Plans do not match ===
|${sideBySide(normalized1.treeString, normalized2.treeString).mkString("\n")}
""".stripMargin)
}
}
/** Fails the test if the two expressions do not match */
protected def compareExpressions(e1: Expression, e2: Expression): Unit = {
comparePlans(Filter(e1, OneRowRelation), Filter(e2, OneRowRelation))
}
}
|