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/test/scala/sandcrawler/ScorableFeaturesTest.scala | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'scalding/src/test/scala/sandcrawler/ScorableFeaturesTest.scala') 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