aboutsummaryrefslogtreecommitdiffstats
path: root/scalding/src/main/scala/sandcrawler/CrossrefScorable.scala
diff options
context:
space:
mode:
authorBryan Newbold <bnewbold@archive.org>2018-08-15 20:22:04 -0700
committerBryan Newbold <bnewbold@archive.org>2018-08-15 20:22:04 -0700
commit419ca3dc053682d688653e9a64eaaf46018fd330 (patch)
treed65a9fbb6d97957269fdcf53ea51e422d1cb6a08 /scalding/src/main/scala/sandcrawler/CrossrefScorable.scala
parentdf341a68459829380f1f01015768acee5642f15b (diff)
downloadsandcrawler-419ca3dc053682d688653e9a64eaaf46018fd330.tar.gz
sandcrawler-419ca3dc053682d688653e9a64eaaf46018fd330.zip
scorable: test for null strings
Diffstat (limited to 'scalding/src/main/scala/sandcrawler/CrossrefScorable.scala')
-rw-r--r--scalding/src/main/scala/sandcrawler/CrossrefScorable.scala1
1 files changed, 1 insertions, 0 deletions
diff --git a/scalding/src/main/scala/sandcrawler/CrossrefScorable.scala b/scalding/src/main/scala/sandcrawler/CrossrefScorable.scala
index 4897b1c..ff8201a 100644
--- a/scalding/src/main/scala/sandcrawler/CrossrefScorable.scala
+++ b/scalding/src/main/scala/sandcrawler/CrossrefScorable.scala
@@ -34,6 +34,7 @@ object CrossrefScorable {
if (titles.isEmpty || titles == null || doi.isEmpty || doi == null) {
new MapFeatures(Scorable.NoSlug, json)
} else {
+ // bnewbold: not checking that titles(0) is non-null/non-empty; case would be, in JSON, "title": [ null ]
val sf : ScorableFeatures = new ScorableFeatures(title=titles(0), doi=doi)
new MapFeatures(sf.toSlug, sf.toString)
}