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
|
/*
* 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
import scala.language.implicitConversions
import scala.reflect.runtime.universe.TypeTag
import org.apache.spark.SparkContext
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.catalyst.analysis._
import org.apache.spark.sql.catalyst.dsl
import org.apache.spark.sql.catalyst.expressions._
import org.apache.spark.sql.catalyst.optimizer.Optimizer
import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan
import org.apache.spark.sql.catalyst.rules.RuleExecutor
import org.apache.spark.sql.execution._
/**
* <span class="badge" style="float: right; background-color: darkblue;">ALPHA COMPONENT</span>
*
* The entry point for running relational queries using Spark. Allows the creation of [[SchemaRDD]]
* objects and the execution of SQL queries.
*
* @groupname userf Spark SQL Functions
* @groupname Ungrouped Support functions for language integrated queries.
*/
class SQLContext(@transient val sparkContext: SparkContext)
extends Logging
with dsl.ExpressionConversions
with Serializable {
self =>
@transient
protected[sql] lazy val catalog: Catalog = new SimpleCatalog
@transient
protected[sql] lazy val analyzer: Analyzer =
new Analyzer(catalog, EmptyFunctionRegistry, caseSensitive = true)
@transient
protected[sql] val optimizer = Optimizer
@transient
protected[sql] val parser = new catalyst.SqlParser
protected[sql] def parseSql(sql: String): LogicalPlan = parser(sql)
protected[sql] def executeSql(sql: String): this.QueryExecution = executePlan(parseSql(sql))
protected[sql] def executePlan(plan: LogicalPlan): this.QueryExecution =
new this.QueryExecution { val logical = plan }
/**
* <span class="badge badge-red" style="float: right;">EXPERIMENTAL</span>
*
* Allows catalyst LogicalPlans to be executed as a SchemaRDD. Note that the LogicalPlan
* interface is considered internal, and thus not guranteed to be stable. As a result, using
* them directly is not reccomended.
*/
implicit def logicalPlanToSparkQuery(plan: LogicalPlan): SchemaRDD = new SchemaRDD(this, plan)
/**
* Creates a SchemaRDD from an RDD of case classes.
*
* @group userf
*/
implicit def createSchemaRDD[A <: Product: TypeTag](rdd: RDD[A]) =
new SchemaRDD(this, SparkLogicalPlan(ExistingRdd.fromProductRdd(rdd)))
/**
* Loads a parequet file, returning the result as a [[SchemaRDD]].
*
* @group userf
*/
def parquetFile(path: String): SchemaRDD =
new SchemaRDD(this, parquet.ParquetRelation("ParquetFile", path))
/**
* Registers the given RDD as a temporary table in the catalog. Temporary tables exist only
* during the lifetime of this instance of SQLContext.
*
* @group userf
*/
def registerRDDAsTable(rdd: SchemaRDD, tableName: String): Unit = {
catalog.registerTable(None, tableName, rdd.logicalPlan)
}
/**
* Executes a SQL query using Spark, returning the result as a SchemaRDD.
*
* @group userf
*/
def sql(sqlText: String): SchemaRDD = {
val result = new SchemaRDD(this, parseSql(sqlText))
// We force query optimization to happen right away instead of letting it happen lazily like
// when using the query DSL. This is so DDL commands behave as expected. This is only
// generates the RDD lineage for DML queries, but do not perform any execution.
result.queryExecution.toRdd
result
}
protected[sql] class SparkPlanner extends SparkStrategies {
val sparkContext = self.sparkContext
val strategies: Seq[Strategy] =
TopK ::
PartialAggregation ::
SparkEquiInnerJoin ::
BasicOperators ::
CartesianProduct ::
BroadcastNestedLoopJoin :: Nil
}
@transient
protected[sql] val planner = new SparkPlanner
/**
* Prepares a planned SparkPlan for execution by binding references to specific ordinals, and
* inserting shuffle operations as needed.
*/
@transient
protected[sql] val prepareForExecution = new RuleExecutor[SparkPlan] {
val batches =
Batch("Add exchange", Once, AddExchange) ::
Batch("Prepare Expressions", Once, new BindReferences[SparkPlan]) :: Nil
}
/**
* The primary workflow for executing relational queries using Spark. Designed to allow easy
* access to the intermediate phases of query execution for developers.
*/
protected abstract class QueryExecution {
def logical: LogicalPlan
lazy val analyzed = analyzer(logical)
lazy val optimizedPlan = optimizer(analyzed)
// TODO: Don't just pick the first one...
lazy val sparkPlan = planner(optimizedPlan).next()
lazy val executedPlan: SparkPlan = prepareForExecution(sparkPlan)
/** Internal version of the RDD. Avoids copies and has no schema */
lazy val toRdd: RDD[Row] = executedPlan.execute()
protected def stringOrError[A](f: => A): String =
try f.toString catch { case e: Throwable => e.toString }
override def toString: String =
s"""== Logical Plan ==
|${stringOrError(analyzed)}
|== Optimized Logical Plan
|${stringOrError(optimizedPlan)}
|== Physical Plan ==
|${stringOrError(executedPlan)}
""".stripMargin.trim
/**
* Runs the query after interposing operators that print the result of each intermediate step.
*/
def debugExec() = DebugQuery(executedPlan).execute().collect()
}
}
|