diff options
author | Bryan Newbold <bnewbold@archive.org> | 2018-08-15 20:22:04 -0700 |
---|---|---|
committer | Bryan Newbold <bnewbold@archive.org> | 2018-08-15 20:22:04 -0700 |
commit | 419ca3dc053682d688653e9a64eaaf46018fd330 (patch) | |
tree | d65a9fbb6d97957269fdcf53ea51e422d1cb6a08 /scalding/src/main/scala/sandcrawler/ScorableFeatures.scala | |
parent | df341a68459829380f1f01015768acee5642f15b (diff) | |
download | sandcrawler-419ca3dc053682d688653e9a64eaaf46018fd330.tar.gz sandcrawler-419ca3dc053682d688653e9a64eaaf46018fd330.zip |
scorable: test for null strings
Diffstat (limited to 'scalding/src/main/scala/sandcrawler/ScorableFeatures.scala')
-rw-r--r-- | scalding/src/main/scala/sandcrawler/ScorableFeatures.scala | 5 |
1 files changed, 4 insertions, 1 deletions
diff --git a/scalding/src/main/scala/sandcrawler/ScorableFeatures.scala b/scalding/src/main/scala/sandcrawler/ScorableFeatures.scala index 5d6dea0..966fb93 100644 --- a/scalding/src/main/scala/sandcrawler/ScorableFeatures.scala +++ b/scalding/src/main/scala/sandcrawler/ScorableFeatures.scala @@ -6,7 +6,10 @@ import scala.util.parsing.json.JSONObject // with a second ScorableFeatures). class ScorableFeatures(title : String, year: Int = 0, doi : String = "", sha1: String = "") { def toMap() : Map[String, Any] = { - Map("title" -> title, "year" -> year, "doi" -> doi, "sha1" -> sha1) + Map("title" -> (if (title == null) "" else title), + "year" -> year, + "doi" -> (if (doi == null) "" else doi), + "sha1" -> (if (sha1 == null) "" else sha1)) } override def toString() : String = { |