aboutsummaryrefslogtreecommitdiffstats
path: root/scalding/src/main/scala/sandcrawler/StringUtilities.scala
diff options
context:
space:
mode:
Diffstat (limited to 'scalding/src/main/scala/sandcrawler/StringUtilities.scala')
-rw-r--r--scalding/src/main/scala/sandcrawler/StringUtilities.scala2
1 files changed, 1 insertions, 1 deletions
diff --git a/scalding/src/main/scala/sandcrawler/StringUtilities.scala b/scalding/src/main/scala/sandcrawler/StringUtilities.scala
index 2745875..e03b60d 100644
--- a/scalding/src/main/scala/sandcrawler/StringUtilities.scala
+++ b/scalding/src/main/scala/sandcrawler/StringUtilities.scala
@@ -36,7 +36,7 @@ object StringUtilities {
// Source: https://stackoverflow.com/a/30076541/631051
def removePunctuation(s: String) : String = {
- s.replaceAll("""[\p{Punct}]""", "")
+ s.replaceAll("""[\p{Punct}’·“”‘’“”«»「」]""", "")
}
// Adapted from: https://stackoverflow.com/a/16018452/631051