/
ReadAndWrite.scala
119 lines (99 loc) · 3.41 KB
/
ReadAndWrite.scala
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
package com.github.pedrovgs.sparkplayground.exercise5
import com.github.pedrovgs.sparkplayground.{Resources, SparkApp}
import com.github.pedrovgs.sparkplayground.exercise5.model.ProtoUser
import com.trueaccord.scalapb.spark._
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.DataFrame
import scala.util.Try
object ReadAndWrite extends SparkApp with Resources {
def readAndWriteText(): Unit = {
val outputFile = "./outputs/capitalizedTextFile.txt"
delete(outputFile)
val capitalizedText = readAndCapitalizeTextFile()
capitalizedText.saveAsTextFile(outputFile)
}
def readAndWriteJson(): Unit = {
val user = readUsersSortedByName()
writeUserAsJson(user)
}
def readAndWriteCSV(): Unit = {
val gameBoySales = readGameBoySales()
writeAsCsv(gameBoySales)
}
def readAndWriteProtocolBuffer(): Unit = {
val protoUsers =
readUsersSortedByName().map(u => ProtoUser(u.name.title, u.name.first, u.name.last))
sqlContext.protoToDataFrame(protoUsers).createOrReplaceTempView("users")
writeAsProtocolBuffer()
}
def readAndWriteObjectFile(): Unit = {
val sales = readGameBoySales()
writeAsObjectFile(sales)
}
def readAndWriteGzipFile(): Unit = {
val firstUser = sparkContext.textFile(getFilePath("/exercise5/users.json.gz"))
val outputFile = "./outputs/users.txt"
delete(outputFile)
firstUser.saveAsTextFile(outputFile)
}
private def writeAsObjectFile(sales: DataFrame) = {
val outputFile = "./outputs/objectFile"
delete(outputFile)
sales.rdd.saveAsObjectFile(outputFile)
}
private def writeAsProtocolBuffer(): Unit = {
val outputFile = "./outputs/protocolBufferUsers"
delete(outputFile)
sqlContext
.sql("SELECT title, first, last FROM users WHERE title = 'mr'")
.write
.save(outputFile)
}
private def writeAsCsv(gameBoySales: DataFrame) = {
val outputFile = "./outputs/gameBoyGamesSales.csv"
delete(outputFile)
gameBoySales.write
.format("com.databricks.spark.csv")
.option("header", "true")
.save(outputFile)
}
private def readGameBoySales(): DataFrame = {
sqlContext.read
.format("com.databricks.spark.csv")
.option("header", "true")
.option("inferSchema", "true")
.load(getFilePath("/exercise5/videoGamesSales.csv"))
.filter(row => row.getAs[String]("Platform") == "GB")
}
private def readAndCapitalizeTextFile(): RDD[String] = {
val resourceFile = getFilePath("/exercise5/textFile.txt")
sparkContext.textFile(resourceFile).flatMap(_.split(" ")).map(line => line.capitalize)
}
private def readUsersSortedByName(): RDD[User] = {
sparkContext
.textFile(getFilePath("/exercise5/users.json"))
.flatMap(line =>
Try {
objectMapper.readValue(line, classOf[User])
}.toOption)
.sortBy(_.name.first, ascending = true, 1)
}
private def writeUserAsJson(userRDD: RDD[User]): Unit = {
val outputFile = getOutputFilePath("/firstUser.json")
delete(outputFile)
userRDD
.map(user => {
objectMapper.writeValueAsString(user)
})
.saveAsTextFile(outputFile)
}
pprint.pprintln("Let's read and write some files!")
readAndWriteText()
readAndWriteJson()
readAndWriteCSV()
readAndWriteProtocolBuffer()
readAndWriteObjectFile()
readAndWriteGzipFile()
pprint.pprintln(
"We are done! Take a look at the ./outputs folder if you want to se the results.")
}