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
|
/*
* 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.repl
import java.io.File
import scala.tools.nsc.GenericRunnerSettings
import org.apache.spark._
import org.apache.spark.internal.Logging
import org.apache.spark.sql.SparkSession
import org.apache.spark.util.Utils
object Main extends Logging {
initializeLogIfNecessary(true)
val conf = new SparkConf()
val rootDir = conf.getOption("spark.repl.classdir").getOrElse(Utils.getLocalDir(conf))
val outputDir = Utils.createTempDir(root = rootDir, namePrefix = "repl")
var sparkContext: SparkContext = _
var sparkSession: SparkSession = _
// this is a public var because tests reset it.
var interp: SparkILoop = _
private var hasErrors = false
private def scalaOptionError(msg: String): Unit = {
hasErrors = true
Console.err.println(msg)
}
def main(args: Array[String]) {
doMain(args, new SparkILoop)
}
// Visible for testing
private[repl] def doMain(args: Array[String], _interp: SparkILoop): Unit = {
interp = _interp
val jars = conf.getOption("spark.jars")
.map(_.replace(",", File.pathSeparator))
.getOrElse("")
val interpArguments = List(
"-Yrepl-class-based",
"-Yrepl-outdir", s"${outputDir.getAbsolutePath}",
"-classpath", jars
) ++ args.toList
val settings = new GenericRunnerSettings(scalaOptionError)
settings.processArguments(interpArguments, true)
if (!hasErrors) {
interp.process(settings) // Repl starts and goes in loop of R.E.P.L
Option(sparkContext).map(_.stop)
}
}
def createSparkContext(): SparkContext = {
val execUri = System.getenv("SPARK_EXECUTOR_URI")
conf.setIfMissing("spark.app.name", "Spark shell")
// SparkContext will detect this configuration and register it with the RpcEnv's
// file server, setting spark.repl.class.uri to the actual URI for executors to
// use. This is sort of ugly but since executors are started as part of SparkContext
// initialization in certain cases, there's an initialization order issue that prevents
// this from being set after SparkContext is instantiated.
.set("spark.repl.class.outputDir", outputDir.getAbsolutePath())
if (execUri != null) {
conf.set("spark.executor.uri", execUri)
}
if (System.getenv("SPARK_HOME") != null) {
conf.setSparkHome(System.getenv("SPARK_HOME"))
}
sparkContext = new SparkContext(conf)
logInfo("Created spark context..")
Signaling.cancelOnInterrupt(sparkContext)
sparkContext
}
def createSparkSession(): SparkSession = {
if (SparkSession.hiveClassesArePresent) {
sparkSession = SparkSession.builder.enableHiveSupport().getOrCreate()
logInfo("Created Spark session with Hive support")
} else {
sparkSession = SparkSession.builder.getOrCreate()
logInfo("Created Spark session")
}
sparkSession
}
}
|