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
|
/*
* 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.jdbc
import scala.collection.mutable.ArrayBuffer
import java.sql.DriverManager
import org.apache.spark.Partition
import org.apache.spark.sql.SQLContext
import org.apache.spark.sql.sources._
/**
* Data corresponding to one partition of a JDBCRDD.
*/
private[sql] case class JDBCPartition(whereClause: String, idx: Int) extends Partition {
override def index: Int = idx
}
/**
* Instructions on how to partition the table among workers.
*/
private[sql] case class JDBCPartitioningInfo(
column: String,
lowerBound: Long,
upperBound: Long,
numPartitions: Int)
private[sql] object JDBCRelation {
/**
* Given a partitioning schematic (a column of integral type, a number of
* partitions, and upper and lower bounds on the column's value), generate
* WHERE clauses for each partition so that each row in the table appears
* exactly once. The parameters minValue and maxValue are advisory in that
* incorrect values may cause the partitioning to be poor, but no data
* will fail to be represented.
*/
def columnPartition(partitioning: JDBCPartitioningInfo): Array[Partition] = {
if (partitioning == null) return Array[Partition](JDBCPartition(null, 0))
val numPartitions = partitioning.numPartitions
val column = partitioning.column
if (numPartitions == 1) return Array[Partition](JDBCPartition(null, 0))
// Overflow and silliness can happen if you subtract then divide.
// Here we get a little roundoff, but that's (hopefully) OK.
val stride: Long = (partitioning.upperBound / numPartitions
- partitioning.lowerBound / numPartitions)
var i: Int = 0
var currentValue: Long = partitioning.lowerBound
var ans = new ArrayBuffer[Partition]()
while (i < numPartitions) {
val lowerBound = if (i != 0) s"$column >= $currentValue" else null
currentValue += stride
val upperBound = if (i != numPartitions - 1) s"$column < $currentValue" else null
val whereClause =
if (upperBound == null) {
lowerBound
} else if (lowerBound == null) {
upperBound
} else {
s"$lowerBound AND $upperBound"
}
ans += JDBCPartition(whereClause, i)
i = i + 1
}
ans.toArray
}
}
private[sql] class DefaultSource extends RelationProvider {
/** Returns a new base relation with the given parameters. */
override def createRelation(
sqlContext: SQLContext,
parameters: Map[String, String]): BaseRelation = {
val url = parameters.getOrElse("url", sys.error("Option 'url' not specified"))
val driver = parameters.getOrElse("driver", null)
val table = parameters.getOrElse("dbtable", sys.error("Option 'dbtable' not specified"))
val partitionColumn = parameters.getOrElse("partitionColumn", null)
val lowerBound = parameters.getOrElse("lowerBound", null)
val upperBound = parameters.getOrElse("upperBound", null)
val numPartitions = parameters.getOrElse("numPartitions", null)
if (driver != null) Class.forName(driver)
if (partitionColumn != null
&& (lowerBound == null || upperBound == null || numPartitions == null)) {
sys.error("Partitioning incompletely specified")
}
val partitionInfo = if (partitionColumn == null) {
null
} else {
JDBCPartitioningInfo(
partitionColumn,
lowerBound.toLong,
upperBound.toLong,
numPartitions.toInt)
}
val parts = JDBCRelation.columnPartition(partitionInfo)
JDBCRelation(url, table, parts)(sqlContext)
}
}
private[sql] case class JDBCRelation(
url: String,
table: String,
parts: Array[Partition])(@transient val sqlContext: SQLContext)
extends PrunedFilteredScan {
override val schema = JDBCRDD.resolveTable(url, table)
override def buildScan(requiredColumns: Array[String], filters: Array[Filter]) = {
val driver: String = DriverManager.getDriver(url).getClass.getCanonicalName
JDBCRDD.scanTable(
sqlContext.sparkContext,
schema,
driver,
url,
table,
requiredColumns,
filters,
parts)
}
}
|