diff options
Diffstat (limited to 'scalding/src/main/scala/example/WordCountJob.scala')
-rw-r--r-- | scalding/src/main/scala/example/WordCountJob.scala | 12 |
1 files changed, 12 insertions, 0 deletions
diff --git a/scalding/src/main/scala/example/WordCountJob.scala b/scalding/src/main/scala/example/WordCountJob.scala new file mode 100644 index 0000000..0e63fed --- /dev/null +++ b/scalding/src/main/scala/example/WordCountJob.scala @@ -0,0 +1,12 @@ +package example + +import com.twitter.scalding._ + +class WordCountJob(args: Args) extends Job(args) { + TypedPipe.from(TextLine(args("input"))) + .flatMap { line => line.split("\\s+") } + .map { word => (word, 1L) } + .sumByKey + // The compiler will enforce the type coming out of the sumByKey is the same as the type we have for our sink + .write(TypedTsv[(String, Long)](args("output"))) +} |