From 7087760028cb55b8290783fc8c28958108f00f36 Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Wed, 22 Aug 2018 12:59:17 -0700 Subject: add more punctuation characters to slug filter --- scalding/src/main/scala/sandcrawler/StringUtilities.scala | 2 +- scalding/src/test/scala/sandcrawler/ScorableFeaturesTest.scala | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'scalding') 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 diff --git a/scalding/src/test/scala/sandcrawler/ScorableFeaturesTest.scala b/scalding/src/test/scala/sandcrawler/ScorableFeaturesTest.scala index 9459749..d742384 100644 --- a/scalding/src/test/scala/sandcrawler/ScorableFeaturesTest.scala +++ b/scalding/src/test/scala/sandcrawler/ScorableFeaturesTest.scala @@ -49,7 +49,7 @@ class ScorableFeaturesTest extends FlatSpec with Matchers { } it should "strip special characters" in { - titleToSlug(":;!',|\"\'`.#?!-@*/\\=+~%$^{}()[]<>-_") shouldBe Scorable.NoSlug + titleToSlug(":;!',|\"\'`.#?!-@*/\\=+~%$^{}()[]<>-_’·“”‘’“”«»「」") shouldBe Scorable.NoSlug // TODO: titleToSlug("©™₨№…") shouldBe Scorable.NoSlug // TODO: titleToSlug("πµΣσ") shouldBe Scorable.NoSlug } -- cgit v1.2.3