From 2277c2f793a007fa3a347af23fca35f4a3eafeef Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Wed, 15 Aug 2018 22:43:10 -0700 Subject: do strip periods ('.') --- scalding/src/main/scala/sandcrawler/StringUtilities.scala | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'scalding/src/main') diff --git a/scalding/src/main/scala/sandcrawler/StringUtilities.scala b/scalding/src/main/scala/sandcrawler/StringUtilities.scala index 6eeff7e..2745875 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 -- cgit v1.2.3