blog/BigData-Notes
2
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

spark-streaming-flume

Browse Source
This commit is contained in:
罗祥
2019-05-23 17:20:37 +08:00
parent cbc7c485a8
commit 485ddabe55
4 changed files with 4 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
code/spark/spark-streaming-flume/src/main/scala/com/heibaiying/flume/PullBasedWordCount.scala
View File

@@ -18,9 +18,8 @@ object PullBasedWordCount {
// 1.获取输入流
val flumeStream = FlumeUtils.createPollingStream(ssc, "hadoop001", 8888)
// 2.词频统计
flumeStream.map(line => new String(line.event.getBody.array()).trim)
.flatMap(_.split(" ")).map((_, 1)).reduceByKey(_ + _).print()
// 2.打印输入流中的数据
flumeStream.map(line => new String(line.event.getBody.array()).trim).print()
ssc.start()
ssc.awaitTermination()

5
code/spark/spark-streaming-flume/src/main/scala/com/heibaiying/flume/PushBasedWordCount.scala
View File

@@ -19,9 +19,8 @@ object PushBasedWordCount {
// 1.获取输入流
val flumeStream = FlumeUtils.createStream(ssc, "hadoop001", 8888)
// 2.词频统计
flumeStream.map(line => new String(line.event.getBody.array()).trim)
.flatMap(_.split(" ")).map((_, 1)).reduceByKey(_ + _).print()
// 2.打印输入流的数据
flumeStream.map(line => new String(line.event.getBody.array()).trim).print()
ssc.start()
ssc.awaitTermination()