aboutsummaryrefslogtreecommitdiffstats
path: root/scalding/src/main/scala/sandcrawler/GrobidScorableDumpJob.scala
diff options
context:
space:
mode:
Diffstat (limited to 'scalding/src/main/scala/sandcrawler/GrobidScorableDumpJob.scala')
-rw-r--r--scalding/src/main/scala/sandcrawler/GrobidScorableDumpJob.scala1
1 files changed, 0 insertions, 1 deletions
diff --git a/scalding/src/main/scala/sandcrawler/GrobidScorableDumpJob.scala b/scalding/src/main/scala/sandcrawler/GrobidScorableDumpJob.scala
index f4e84fe..19b257f 100644
--- a/scalding/src/main/scala/sandcrawler/GrobidScorableDumpJob.scala
+++ b/scalding/src/main/scala/sandcrawler/GrobidScorableDumpJob.scala
@@ -45,7 +45,6 @@ class GrobidScorableDumpJob(args: Args) extends JobBase(args) {
validGrobidRows.inc
entry
}
- // XXX: this groupBy after the map?
.groupBy { case MapFeatures(slug, json) => slug }
.map { tuple =>
val (slug : String, features : MapFeatures) = tuple