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
|
/*
* 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.api.r
import java.io.{ByteArrayInputStream, ByteArrayOutputStream, DataInputStream, DataOutputStream}
import org.apache.spark.api.java.{JavaRDD, JavaSparkContext}
import org.apache.spark.api.r.SerDe
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.catalyst.expressions.{Alias, Expression, NamedExpression}
import org.apache.spark.sql.types._
import org.apache.spark.sql.{Column, DataFrame, GroupedData, Row, SQLContext, SaveMode}
private[r] object SQLUtils {
def createSQLContext(jsc: JavaSparkContext): SQLContext = {
new SQLContext(jsc)
}
def getJavaSparkContext(sqlCtx: SQLContext): JavaSparkContext = {
new JavaSparkContext(sqlCtx.sparkContext)
}
def toSeq[T](arr: Array[T]): Seq[T] = {
arr.toSeq
}
def createStructType(fields : Seq[StructField]): StructType = {
StructType(fields)
}
def getSQLDataType(dataType: String): DataType = {
dataType match {
case "byte" => org.apache.spark.sql.types.ByteType
case "integer" => org.apache.spark.sql.types.IntegerType
case "float" => org.apache.spark.sql.types.FloatType
case "double" => org.apache.spark.sql.types.DoubleType
case "numeric" => org.apache.spark.sql.types.DoubleType
case "character" => org.apache.spark.sql.types.StringType
case "string" => org.apache.spark.sql.types.StringType
case "binary" => org.apache.spark.sql.types.BinaryType
case "raw" => org.apache.spark.sql.types.BinaryType
case "logical" => org.apache.spark.sql.types.BooleanType
case "boolean" => org.apache.spark.sql.types.BooleanType
case "timestamp" => org.apache.spark.sql.types.TimestampType
case "date" => org.apache.spark.sql.types.DateType
case _ => throw new IllegalArgumentException(s"Invaid type $dataType")
}
}
def createStructField(name: String, dataType: String, nullable: Boolean): StructField = {
val dtObj = getSQLDataType(dataType)
StructField(name, dtObj, nullable)
}
def createDF(rdd: RDD[Array[Byte]], schema: StructType, sqlContext: SQLContext): DataFrame = {
val num = schema.fields.size
val rowRDD = rdd.map(bytesToRow(_, schema))
sqlContext.createDataFrame(rowRDD, schema)
}
def dfToRowRDD(df: DataFrame): JavaRDD[Array[Byte]] = {
df.map(r => rowToRBytes(r))
}
private[this] def doConversion(data: Object, dataType: DataType): Object = {
data match {
case d: java.lang.Double if dataType == FloatType =>
new java.lang.Float(d)
case _ => data
}
}
private[this] def bytesToRow(bytes: Array[Byte], schema: StructType): Row = {
val bis = new ByteArrayInputStream(bytes)
val dis = new DataInputStream(bis)
val num = SerDe.readInt(dis)
Row.fromSeq((0 until num).map { i =>
doConversion(SerDe.readObject(dis), schema.fields(i).dataType)
}.toSeq)
}
private[this] def rowToRBytes(row: Row): Array[Byte] = {
val bos = new ByteArrayOutputStream()
val dos = new DataOutputStream(bos)
val cols = (0 until row.length).map(row(_).asInstanceOf[Object]).toArray
SerDe.writeObject(dos, cols)
bos.toByteArray()
}
def dfToCols(df: DataFrame): Array[Array[Any]] = {
// localDF is Array[Row]
val localDF = df.collect()
val numCols = df.columns.length
// result is Array[Array[Any]]
(0 until numCols).map { colIdx =>
localDF.map { row =>
row(colIdx)
}
}.toArray
}
def saveMode(mode: String): SaveMode = {
mode match {
case "append" => SaveMode.Append
case "overwrite" => SaveMode.Overwrite
case "error" => SaveMode.ErrorIfExists
case "ignore" => SaveMode.Ignore
}
}
def loadDF(
sqlContext: SQLContext,
source: String,
options: java.util.Map[String, String]): DataFrame = {
sqlContext.read.format(source).options(options).load()
}
def loadDF(
sqlContext: SQLContext,
source: String,
schema: StructType,
options: java.util.Map[String, String]): DataFrame = {
sqlContext.read.format(source).schema(schema).options(options).load()
}
}
|
