aboutsummaryrefslogtreecommitdiffstats
path: root/scalding/src/main/scala/sandcrawler/Scorable.scala
diff options
context:
space:
mode:
authorEllen Spertus <ellen.spertus@gmail.com>2018-08-22 12:52:03 -0700
committerEllen Spertus <ellen.spertus@gmail.com>2018-08-22 12:52:03 -0700
commitf54e47ace6dd041e78e10ee25573c6ad3de808eb (patch)
tree21931c4efd9997d69227623aba0cff224907dd44 /scalding/src/main/scala/sandcrawler/Scorable.scala
parentb628b7026ab8e7abf4beeaaad99d831b49578483 (diff)
downloadsandcrawler-f54e47ace6dd041e78e10ee25573c6ad3de808eb.tar.gz
sandcrawler-f54e47ace6dd041e78e10ee25573c6ad3de808eb.zip
Added title length filtering to GrobidScorable
Diffstat (limited to 'scalding/src/main/scala/sandcrawler/Scorable.scala')
-rw-r--r--scalding/src/main/scala/sandcrawler/Scorable.scala1
1 files changed, 1 insertions, 0 deletions
diff --git a/scalding/src/main/scala/sandcrawler/Scorable.scala b/scalding/src/main/scala/sandcrawler/Scorable.scala
index 9b9c633..c704ed9 100644
--- a/scalding/src/main/scala/sandcrawler/Scorable.scala
+++ b/scalding/src/main/scala/sandcrawler/Scorable.scala
@@ -30,6 +30,7 @@ abstract class Scorable {
}
object Scorable {
+ val MaxTitleLength = 255
val NoSlug = "NO SLUG" // Used for slug if title is empty or unparseable
def isValidSlug(slug : String) : Boolean = {