url_scrubber 0.8.5 → 0.8.6

checksums.yaml

@@ -1,15 +1,15 @@
 ---
 !binary "U0hBMQ==":
   metadata.gz: !binary |-
-    MWNkMWE5MDM0ZTliMzg1NDcwN2Y5Zjg4Mzc1ZWE4MWY1ZmVlMWUwMQ==
+    MDM4ZTYzMzA2NTRjNzhjOTI2MjI4MGI3MDdlZjIzYjZmYjQ4ZDUwOA==
   data.tar.gz: !binary |-
-    ZTg4Y2ZkNTU2NWZjMjhmYjczZGM4OTQ3MWRmYjNkMDc5ZDMxMTJmNg==
+    NDczYzkxOTc4OGFkNmQzNTI2M2E4Y2E0MGM2NmRhZmQwNWRmZDYwNw==
 SHA512:
   metadata.gz: !binary |-
-    ZWM2M2VlZWM5N2UyMmFhODU4NmE0MjAwYWZiMzk1OTBkODA3ZDQ4NzA2ZWRj
-    Mzc0ZTk2MjY5YTA2YzVjY2NiY2RjMWEyZTQyZjc3NzFlNzE4YTU3YWRhZTQy
-    NWE3MDBlNzc5YTM4NDEzNjYwYzJiMjUxYjY3MDRjZjUzNzc1NTA=
+    MmMxY2U0ZmMwMDYyZjUwYjQ4YjI3OTU2NDZiZjgzYTZhZDY5ODQ3ZTAzM2E4
+    NTNkNWM0NWMwNTcyYTkwMDlkYzk2MzkyMDY1NjYzMTNlODg0Y2FhYWIxNmUy
+    ZDgwMjUxNDI3YTk5ZTQ2MTdjZWJkNzcxZGViMzYyZTBjYTI5NDY=
   data.tar.gz: !binary |-
-    NGQ2ZDQ3NjUwY2RlOGYxMzljNDMyMTU0ZWJmZGRkN2YwMmJjNmIwMzY4OGQ4
-    NWU0NmE5OGE3Mjk4NTgxNDk1M2E2YzdkNTVmNTEwMzQ1NDEzOGY2NmZjMzA2
-    ZTMzNzUwNDIyMWM5YzIzMjg2NTJhMGRlMWNkMWE5NTdiN2E5ZGI=
+    ZDRkYjJmNjY2ZWQ5N2IxNzE2MWYxNGNmODJhNDJmNjc0OTkyZjIzOTYxMzMx
+    NGVkZjE4MTYzN2E4OWE2MTNhMDUzOGFiMWY1Mzg1MmNkNWUyNWQyNjlhYjE0
+    M2NmYjY2ZDg3MzAxOTNkZTZmZTQ0NDFlY2FmODVjOWI1OTEyYzA=

data/Gemfile

@@ -1,4 +1,6 @@
 source "http://rubygems.org"
 
 # Specify your gem's dependencies in url_scrubber.gemspec
-gemspec
+gemspec
+
+gem 'domainatrix'

data/lib/url_scrubber/version.rb

@@ -1,3 +1,3 @@
 module UrlScrubber
-  VERSION = "0.8.5"
+  VERSION = "0.8.6"
 end

data/lib/url_scrubber.rb

@@ -5,6 +5,7 @@ require 'uri'
 USER_AGENT = 'Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_3; en-us) AppleWebKit/534.1+ (KHTML, like Gecko) Version/5.0 Safari/533.16'
 
 module UrlScrubber
+
   def self.scrub(url)
     url = url.clone # don't modify the original argument
     
@@ -27,6 +28,7 @@ module UrlScrubber
     return url
   end
 
+
   def self.service_of(url)
     
     domain_match = url.match(%r{https?://([^/]+)})
@@ -66,6 +68,7 @@ module UrlScrubber
     :other
   end  
 
+
   def self.ideal_form?(url)
     url = scrub(url)
     return false unless url
@@ -100,23 +103,27 @@ module UrlScrubber
       true
     end
   end
-  
+
+
   def self.linkedin_company_url?(url)
     url = scrub(url)
     return false unless url
     return url.include?('http://linkedin.com/company/')
   end
+
   
   def self.linkedin_personal_url?(url)
     url = scrub(url)
     return false unless url
     return url.include?('http://linkedin.com/in/') || url.include?('http://linkedin.com/pub/') 
   end
+
   
   def self.find_identity_from_url(url)
     UrlScrubber.scrub(url).split("/").last unless url.nil?
   end
 
+
   def self.find_linkedin_identity_from_url(url)
     return nil if url.nil?
     scrubbed_url = scrub(url) 
@@ -135,6 +142,7 @@ module UrlScrubber
     end
   end
 
+
   # Requirements:
   # 1.  must have http/https scheme
   # 2.  no "@" in any of the passed in url string
@@ -146,14 +154,34 @@ module UrlScrubber
     rescue URI::InvalidURIError
     false
   end
+
+
+  def self.maps_to_public_url(url)
+    scrubbed = scrub(url)
+    parsed = URI.parse(url) or return nil
+    host = Domainatrix.parse(parsed.host)
+    if host.domain == "facebook" && host.subdomain == "business"
+      public_url = scrubbed.sub("http://business.facebook.com", "http://facebook.com")
+    elsif host.domain == "google" && host.subdomain == "business"
+      public_url = scrubbed.sub("http://business.google.com", "http://plus.google.com")
+    else
+      public_url = nil
+    end
+    public_url
+  end
+
   
+  ################################################################################
   private
+  ################################################################################
+
 
   def self.downcase_domain(url)
     domain_match = url.match(%r{http://[^/]+}i)
     domain_match[0].downcase + domain_match.post_match
   end
 
+
   def self.special_cases(url)
     #puts "special_cases"
     case service_of(url)
@@ -171,6 +199,7 @@ module UrlScrubber
     url
   end
 
+
   def self.remove_www!(url)
     # url.sub!(%r{://www\d*\.}, '://')
     url.sub!(%r{^https?://www?w?\d*\.}i, 'http://')
@@ -179,27 +208,32 @@ module UrlScrubber
     url
   end
 
+
   def self.remove_html_tags!(url)
     url.gsub!(/<\/?[^>]+>/, '')
     url
   end
 
+
   def self.drop_url_ampersand!(url)
     url.sub!(/\&.*$/, '')
     url
   end
+
   
   def self.drop_url_query!(url)
     url.sub!(/\?.*$/, '')
     url
   end
 
+
   def self.drop_anchor!(url)
     #puts "drop anchor"
     url.sub!(/#.*$/, '')
     url
   end
 
+
   def self.sc_youtube(url)
     # We need to allow the /user version of the URL due to how YouTube allows users to have their own URL
     # which is not separate channel with it's own customUrl.
@@ -208,6 +242,7 @@ module UrlScrubber
     url
   end
 
+
   def self.sc_vimeo(url)
     if url.include?('vimeo.com/groups/') 
       groups_partition = url.partition('vimeo.com/groups/')
@@ -222,6 +257,7 @@ module UrlScrubber
     url
   end
 
+
   def self.sc_twitter(url)
     url.sub!('twitter.com/@', 'twitter.com/')
 
@@ -238,13 +274,14 @@ module UrlScrubber
     url
   end
 
+
   def self.sc_facebook(url)
     #puts "sc_facebook: #{url}"
-    regex1 = /^(?<url>(https?:\/\/)(www\.)?facebook\.com\/(pages\/)*(?<uname>.*)[\/-](?<uid>[0-9]+))($|\/|\/(about|timeline|info|app_)?)/i
-    regex2 = /^(?<url>(https?:\/\/)(www\.)?facebook\.com\/profile.php\?id=(?<uid>[0-9]+))($|\/|\/.*|&.*)/i
-    regex2a = /^(?<url>(https?:\/\/)(www\.)?facebook\.com\/profile.php\?_rdr=p&id=(?<uid>[0-9]+))($|\/|\/.*|&.*)/i
-    regex3 = /^(?<url>(https?:\/\/)(www\.)?facebook\.com\/(?<uname>[^\?\/]*))($|\/$|\/(about|timeline|info|app_.*)?)/i
-    regex4 = /^(?<url>(https?:\/\/)(www\.)?facebook\.com\/)(?<php>home.php\?([#!]+\/)*)(?<uname>.*)/i
+    regex1 = /^(?<url>(https?:\/\/)((www|business)\.)?facebook\.com\/(pages\/)*(?<uname>.*)[\/-](?<uid>[0-9]+))($|\/|\/(about|timeline|info|app_)?)/i
+    regex2 = /^(?<url>(https?:\/\/)((www|business)\.)?facebook\.com\/profile.php\?id=(?<uid>[0-9]+))($|\/|\/.*|&.*)/i
+    regex2a = /^(?<url>(https?:\/\/)((www|business)\.)?facebook\.com\/profile.php\?_rdr=p&id=(?<uid>[0-9]+))($|\/|\/.*|&.*)/i
+    regex3 = /^(?<url>(https?:\/\/)((www|business)\.)?facebook\.com\/(?<uname>[^\?\/]*))($|\/$|\/(about|timeline|info|app_.*)?)/i
+    regex4 = /^(?<url>(https?:\/\/)((www|business)\.)?facebook\.com\/)(?<php>home.php\?([#!]+\/)*)(?<uname>.*)/i
     
     if url.match("/media/albums") || url.match("/media/set")
       # puts "media"
@@ -296,7 +333,8 @@ module UrlScrubber
     url = url.sub(/\?_rdr.*/, '')
     url
   end
-  
+
+
   def self.sc_linkedin(url)
 
     url.sub!('linkedin.com/companies/', 'linkedin.com/company/')
@@ -320,6 +358,7 @@ module UrlScrubber
     url
   end
 
+
   def self.sc_google_plus(url)
     url.sub!('com/u/0/b/', 'com/')
     url.sub!('com/u/0/', 'com/')
@@ -335,6 +374,7 @@ module UrlScrubber
     community_page ? "http://plus.google.com/communities/#{path_match[1]}" : "http://plus.google.com/#{path_match[1]}"
   end
 
+
   def self.sc_flickr(url)
     if url.include?('flickr.com/groups/') 
       groups_partition = url.partition('flickr.com/groups/')
@@ -354,14 +394,17 @@ module UrlScrubber
     "http://flickr.com/#{user_match[2]}"
   end
 
+
   def self.sc_pinterest(url)
     url
   end
 
+
   def self.sc_yelp(url)
     url
   end
   
+
   def self.check_for_facebook_redirection(uri_str, limit = 5)
     #puts "check_for_facebook_redirection called! uri=#{uri_str}, limit=#{limit.to_s}"
     # finds any redirects   intended for facebook URLs only!!!!

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: url_scrubber
 version: !ruby/object:Gem::Version
-  version: 0.8.5
+  version: 0.8.6
 platform: ruby
 authors:
 - Colin Langton
@@ -11,7 +11,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-12-08 00:00:00.000000000 Z
+date: 2016-12-10 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec