diff options
author | Ellen Spertus <ellen.spertus@gmail.com> | 2018-08-07 10:28:48 -0700 |
---|---|---|
committer | Ellen Spertus <ellen.spertus@gmail.com> | 2018-08-07 10:28:48 -0700 |
commit | 4981a98358aae098714d2266404f7b167993bf0c (patch) | |
tree | e045e4ee2eca6517f02750bb8e5a2e5f60fe277e /scalding/src/main/scala/sandcrawler/ScoreJob.scala | |
parent | dddb7ed410bdd542ca12756d3e97aca6beea5532 (diff) | |
download | sandcrawler-4981a98358aae098714d2266404f7b167993bf0c.tar.gz sandcrawler-4981a98358aae098714d2266404f7b167993bf0c.zip |
Minor refactoring. Added test.
Diffstat (limited to 'scalding/src/main/scala/sandcrawler/ScoreJob.scala')
-rw-r--r-- | scalding/src/main/scala/sandcrawler/ScoreJob.scala | 4 |
1 files changed, 3 insertions, 1 deletions
diff --git a/scalding/src/main/scala/sandcrawler/ScoreJob.scala b/scalding/src/main/scala/sandcrawler/ScoreJob.scala index 22cc9e9..e6a5dc1 100644 --- a/scalding/src/main/scala/sandcrawler/ScoreJob.scala +++ b/scalding/src/main/scala/sandcrawler/ScoreJob.scala @@ -17,7 +17,9 @@ class ScoreJob(args: Args, sc1 : Scorable, sc2 : Scorable)(implicit flowDef : Fl pipe1.join(pipe2).map { entry => val (slug : String, (features1 : ReduceFeatures, features2 : ReduceFeatures)) = entry - Scorable.computeOutput(features1, features2) + new ReduceOutput(Scorable.computeSimilarity(features1, features2), + features1.json, + features2.json) } .write(TypedTsv[ReduceOutput](args("output"))) } |