From 2eef73e8fef1cfdc3641be71860f9ee46e3db58e Mon Sep 17 00:00:00 2001 From: BrokenEagle Date: Fri, 10 Jan 2020 14:49:48 +0000 Subject: [PATCH 1/2] Add additional Twitter hashtag - It was mentioned on issue #4047 but was forgotten to be included --- app/logical/sources/strategies/twitter.rb | 1 + 1 file changed, 1 insertion(+) diff --git a/app/logical/sources/strategies/twitter.rb b/app/logical/sources/strategies/twitter.rb index a90d260a6..259184677 100644 --- a/app/logical/sources/strategies/twitter.rb +++ b/app/logical/sources/strategies/twitter.rb @@ -21,6 +21,7 @@ module Sources::Strategies # the pattern to avoid creating empty strings. COMMON_TAG_REGEXES = [ /(? Date: Fri, 10 Jan 2020 15:27:57 +0000 Subject: [PATCH 2/2] Use more efficient use of regexes for Twitter hashtag normalization --- app/logical/sources/strategies/twitter.rb | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/app/logical/sources/strategies/twitter.rb b/app/logical/sources/strategies/twitter.rb index 259184677..d8280f193 100644 --- a/app/logical/sources/strategies/twitter.rb +++ b/app/logical/sources/strategies/twitter.rb @@ -139,8 +139,9 @@ module Sources::Strategies def normalize_tag(tag) COMMON_TAG_REGEXES.each do |rg| - if tag.match(rg) - return tag.gsub(rg,"") + norm_tag = tag.gsub(rg,"") + if norm_tag != tag + return norm_tag end end tag