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
|
/*
* 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.rdd
import java.io.PrintWriter
import java.util.StringTokenizer
import scala.collection.Map
import scala.collection.JavaConversions._
import scala.collection.mutable.ArrayBuffer
import scala.io.Source
import org.apache.spark.{SparkEnv, Partition, TaskContext}
import org.apache.spark.broadcast.Broadcast
/**
* An RDD that pipes the contents of each parent partition through an external command
* (printing them one per line) and returns the output as a collection of strings.
*/
class PipedRDD[T: ClassManifest](
prev: RDD[T],
command: Seq[String],
envVars: Map[String, String],
printPipeContext: (String => Unit) => Unit,
printRDDElement: (T, String => Unit) => Unit)
extends RDD[String](prev) {
// Similar to Runtime.exec(), if we are given a single string, split it into words
// using a standard StringTokenizer (i.e. by spaces)
def this(
prev: RDD[T],
command: String,
envVars: Map[String, String] = Map(),
printPipeContext: (String => Unit) => Unit = null,
printRDDElement: (T, String => Unit) => Unit = null) =
this(prev, PipedRDD.tokenize(command), envVars, printPipeContext, printRDDElement)
override def getPartitions: Array[Partition] = firstParent[T].partitions
override def compute(split: Partition, context: TaskContext): Iterator[String] = {
val pb = new ProcessBuilder(command)
// Add the environmental variables to the process.
val currentEnvVars = pb.environment()
envVars.foreach { case (variable, value) => currentEnvVars.put(variable, value) }
val proc = pb.start()
val env = SparkEnv.get
// Start a thread to print the process's stderr to ours
new Thread("stderr reader for " + command) {
override def run() {
for (line <- Source.fromInputStream(proc.getErrorStream).getLines) {
System.err.println(line)
}
}
}.start()
// Start a thread to feed the process input from our parent's iterator
new Thread("stdin writer for " + command) {
override def run() {
SparkEnv.set(env)
val out = new PrintWriter(proc.getOutputStream)
// input the pipe context firstly
if (printPipeContext != null) {
printPipeContext(out.println(_))
}
for (elem <- firstParent[T].iterator(split, context)) {
if (printRDDElement != null) {
printRDDElement(elem, out.println(_))
} else {
out.println(elem)
}
}
out.close()
}
}.start()
// Return an iterator that read lines from the process's stdout
val lines = Source.fromInputStream(proc.getInputStream).getLines
return new Iterator[String] {
def next() = lines.next()
def hasNext = {
if (lines.hasNext) {
true
} else {
val exitStatus = proc.waitFor()
if (exitStatus != 0) {
throw new Exception("Subprocess exited with status " + exitStatus)
}
false
}
}
}
}
}
object PipedRDD {
// Split a string into words using a standard StringTokenizer
def tokenize(command: String): Seq[String] = {
val buf = new ArrayBuffer[String]
val tok = new StringTokenizer(command)
while(tok.hasMoreElements) {
buf += tok.nextToken()
}
buf
}
}
|