-
Notifications
You must be signed in to change notification settings - Fork 703
/
QueryTest.scala
178 lines (154 loc) · 6.53 KB
/
QueryTest.scala
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
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
/*
* 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.test.util
import java.util.{Locale, TimeZone}
import scala.collection.JavaConverters._
import org.apache.spark.sql.{DataFrame, Row, SQLContext}
import org.apache.spark.sql.catalyst.plans._
import org.apache.spark.sql.catalyst.util._
import org.apache.spark.sql.test.TestQueryExecutor
import org.apache.carbondata.common.logging.LogServiceFactory
import org.apache.carbondata.core.constants.CarbonCommonConstants
import org.apache.carbondata.core.util.CarbonProperties
class QueryTest extends PlanTest {
val LOGGER = LogServiceFactory.getLogService(this.getClass.getCanonicalName)
// Timezone is fixed to America/Los_Angeles for those timezone sensitive tests (timestamp_*)
TimeZone.setDefault(TimeZone.getTimeZone("America/Los_Angeles"))
// Add Locale setting
Locale.setDefault(Locale.US)
/**
* Runs the plan and makes sure the answer contains all of the keywords, or the
* none of keywords are listed in the answer
* @param df the [[DataFrame]] to be executed
* @param exists true for make sure the keywords are listed in the output, otherwise
* to make sure none of the keyword are not listed in the output
* @param keywords keyword in string array
*/
def checkExistence(df: DataFrame, exists: Boolean, keywords: String*) {
val outputs = df.collect().map(_.mkString).mkString
for (key <- keywords) {
if (exists) {
assert(outputs.contains(key), s"Failed for $df ($key doesn't exist in result)")
} else {
assert(!outputs.contains(key), s"Failed for $df ($key existed in the result)")
}
}
}
/**
* Runs the plan and counts the keyword in the answer
* @param df the [[DataFrame]] to be executed
* @param count expected count
* @param keyword keyword to search
*/
def checkExistenceCount(df: DataFrame, count: Long, keyword: String): Unit = {
val outputs = df.collect().map(_.mkString).mkString
assert(outputs.sliding(keyword.length).count(_ == keyword) === count)
}
def sqlTest(sqlString: String, expectedAnswer: Seq[Row])(implicit sqlContext: SQLContext) {
test(sqlString) {
checkAnswer(sqlContext.sql(sqlString), expectedAnswer)
}
}
/**
* Runs the plan and makes sure the answer matches the expected result.
* @param df the [[DataFrame]] to be executed
* @param expectedAnswer the expected result in a [[Seq]] of [[Row]]s.
*/
protected def checkAnswer(df: DataFrame, expectedAnswer: Seq[Row]): Unit = {
QueryTest.checkAnswer(df, expectedAnswer) match {
case Some(errorMessage) => fail(errorMessage)
case None =>
}
}
protected def checkAnswer(df: DataFrame, expectedAnswer: Row): Unit = {
checkAnswer(df, Seq(expectedAnswer))
}
protected def checkAnswer(df: DataFrame, expectedAnswer: DataFrame): Unit = {
checkAnswer(df, expectedAnswer.collect())
}
def sql(sqlText: String): DataFrame = TestQueryExecutor.INSTANCE.sql(sqlText)
val sqlContext: SQLContext = TestQueryExecutor.INSTANCE.sqlContext
lazy val storeLocation = CarbonProperties.getInstance().
getProperty(CarbonCommonConstants.STORE_LOCATION)
val resourcesPath = TestQueryExecutor.resourcesPath
val metastoredb = TestQueryExecutor.metastoredb
val integrationPath = TestQueryExecutor.integrationPath
val dblocation = TestQueryExecutor.location
}
object QueryTest {
def checkAnswer(df: DataFrame, expectedAnswer: java.util.List[Row]): String = {
checkAnswer(df, expectedAnswer.asScala) match {
case Some(errorMessage) => errorMessage
case None => null
}
}
/**
* Runs the plan and makes sure the answer matches the expected result.
* If there was exception during the execution or the contents of the DataFrame does not
* match the expected result, an error message will be returned. Otherwise, a [[None]] will
* be returned.
* @param df the [[DataFrame]] to be executed
* @param expectedAnswer the expected result in a [[Seq]] of [[Row]]s.
*/
def checkAnswer(df: DataFrame, expectedAnswer: Seq[Row]): Option[String] = {
val isSorted = df.logicalPlan.collect { case s: logical.Sort => s }.nonEmpty
def prepareAnswer(answer: Seq[Row]): Seq[Row] = {
// Converts data to types that we can do equality comparison using Scala collections.
// For BigDecimal type, the Scala type has a better definition of equality test (similar to
// Java's java.math.BigDecimal.compareTo).
// For binary arrays, we convert it to Seq to avoid of calling java.util.Arrays.equals for
// equality test.
val converted: Seq[Row] = answer.map { s =>
Row.fromSeq(s.toSeq.map {
case d: java.math.BigDecimal => BigDecimal(d)
case b: Array[Byte] => b.toSeq
case o => o
})
}
if (!isSorted) converted.sortBy(_.toString()) else converted
}
val sparkAnswer = try df.collect().toSeq catch {
case e: Exception =>
val errorMessage =
s"""
|Exception thrown while executing query:
|${df.queryExecution}
|== Exception ==
|$e
|${org.apache.spark.sql.catalyst.util.stackTraceToString(e)}
""".stripMargin
return Some(errorMessage)
}
if (prepareAnswer(expectedAnswer) != prepareAnswer(sparkAnswer)) {
val errorMessage =
s"""
|Results do not match for query:
|${df.queryExecution}
|== Results ==
|${
sideBySide(
s"== Correct Answer - ${expectedAnswer.size} ==" +:
prepareAnswer(expectedAnswer).map(_.toString()),
s"== Spark Answer - ${sparkAnswer.size} ==" +:
prepareAnswer(sparkAnswer).map(_.toString())).mkString("\n")
}
""".stripMargin
return Some(errorMessage)
}
return None
}
}