Discourse/discourse
Discourse/discourse
2
0
Fork 0
mirror of https://github.com/discourse/discourse.git synced 2025-09-06 10:50:21 +08:00
Code Packages Activity Actions 9

correct specs, ensure crawler layout only applies to html

Browse source
This commit is contained in:
Sam 2018-01-16 16:28:11 +11:00
parent 7b562d2f46
commit d7657d8e47
3 changed files with 16 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

12
lib/crawler_detection.rb
View file

@ -1,16 +1,24 @@
module CrawlerDetection
def self.to_matcher(string)
def self.to_matcher(string, type: nil)
escaped = string.split('|').map { |agent| Regexp.escape(agent) }.join('|')
if type == :real && Rails.env == "test"
# we need this bypass so we properly render views
escaped << "|Rails Testing"
end
Regexp.new(escaped, Regexp::IGNORECASE)
end
def self.crawler?(user_agent)
return true if user_agent.nil?
# this is done to avoid regenerating regexes
@non_crawler_matchers ||= {}
@matchers ||= {}
possibly_real = (@non_crawler_matchers[SiteSetting.non_crawler_user_agents] ||= to_matcher(SiteSetting.non_crawler_user_agents))
possibly_real = (@non_crawler_matchers[SiteSetting.non_crawler_user_agents] ||= to_matcher(SiteSetting.non_crawler_user_agents, type: :real))
if user_agent.match?(possibly_real)
known_bots = (@matchers[SiteSetting.crawler_user_agents] ||= to_matcher(SiteSetting.crawler_user_agents))