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
package mobvista.dmp.datasource.toutiao
import java.net.URI
import java.util
import java.util.Base64
import mobvista.dmp.common.CommonSparkJob
import org.apache.commons.cli.Options
import org.apache.hadoop.fs.{FileSystem, Path}
import org.apache.hadoop.io.compress.GzipCodec
import org.apache.spark.sql.SparkSession
/**
* @package: mobvista.dmp.datasource.toutiao
* @author: wangjf
* @date: 2019/2/22
* @time: 下午5:07
* @email: jinfeng.wang@mobvista.com
* @phone: 152-1062-7698
*/
class CheckToutiao extends CommonSparkJob with Serializable {
override protected def run(args: Array[String]): Int = {
val commandLine = commParser.parse(options, args)
if (!checkMustOption(commandLine)) {
printUsage(options)
return 1
} else {
printOptions(commandLine)
}
val input = commandLine.getOptionValue("input")
val output = commandLine.getOptionValue("output")
val spark = SparkSession.builder()
.appName("CheckToutiao")
.config("spark.rdd.compress", "true")
.config("spark.io.compression.codec", "snappy")
.config("spark.sql.orc.filterPushdown", "true")
.config("spark.serializer", "org.apache.spark.serializer.KryoSerializer")
.config("spark.sql.warehouse.dir", "s3://mob-emr-test/spark-warehouse")
.enableHiveSupport()
.getOrCreate()
FileSystem.get(new URI(s"s3://mob-emr-test"), spark.sparkContext.hadoopConfiguration).delete(new Path(output), true)
try {
val sc = spark.sparkContext
val rdd = sc.textFile(input)
.flatMap(v => {
val res = new util.ArrayList[(String, Int)]()
val vs = Base64.getDecoder.decode(v)
val dmpData = DmpDataProto.DmpData.parseFrom(vs)
val dmpDataIter = dmpData.getIdListList.iterator()
while (dmpDataIter.hasNext) {
val tags = dmpDataIter.next().getTagsList.iterator()
while (tags.hasNext) {
res.add((tags.next, 1))
}
}
import scala.collection.JavaConverters._
res.asScala.iterator
})
rdd.reduceByKey(_ + _).sortByKey(true, 1).saveAsTextFile(output, classOf[GzipCodec])
} finally {
if (spark != null) {
spark.stop()
}
}
0
}
override protected def buildOptions(): Options = {
val options = new Options
options.addOption("input", true, "[must] input path")
options.addOption("output", true, "[must] output path ")
options
}
}
object CheckToutiao {
def main(args: Array[String]): Unit = {
new CheckToutiao().run(args)
}
}