url_scrubber 0.7.20 → 0.8.0

checksums.yaml

@@ -1,7 +1,15 @@
 ---
-SHA1:
-  metadata.gz: 743040fbabe8b162af5d06665e9d8b076916097a
-  data.tar.gz: 3a620b4a6fff1a137093f2d1fb5be3c6b43ef84f
+!binary "U0hBMQ==":
+  metadata.gz: !binary |-
+    YjU1ZDhmYTczNWEzMDk2MjQ4M2U2NDkzMGNiZmQ1Y2U2YTMxZDk0MQ==
+  data.tar.gz: !binary |-
+    NDE2YzlhOWFjMmU3NWFiNjIzNmE4OTJlYjQ3ZmYwMDExMTJjZGNmMw==
 SHA512:
-  metadata.gz: 1641e258c6f4bccbe75de24bb7132697ed286b2f485cc1ef73ba0576307c15eda16b6e8be11e2cf91386b719c2f476ad04cb4e47a47b433df9e0355166fc5e3f
-  data.tar.gz: 6e290b6607c0363c73a25328f8b217a56789ae90793930a11ca78dbe51676a90e3871d17ef878dc1f936fdc8c5ba2bb28f2cf90749afe3ebf57e52f231e40926
+  metadata.gz: !binary |-
+    MDRlZTJlNzFiOTMwYWFkZWY4YzZiZWM5ZjAxMWVhMzMwZjNmYzg4ZmZkMjc2
+    NGRmZTc0Nzc0NGU4M2MzNTk2NGQ5YzhkODRhYTk1YTU3ZWE5YmY1MDMyMTQ4
+    ZjFiNGI4MTAyMmM0MzQ1Y2Y5NWMyMTYwMmQyZTQyNTE1ZTQ4ZDQ=
+  data.tar.gz: !binary |-
+    MTQ4MDcxMDFlM2QzM2Q2ODAwMWUxOGRhMzg2OTBmMjhiNTEzNmNmYTY5ZDg4
+    NjM4YjhmOGNkMTJmNzQ1ZGQxMDI3ODgxNDc0NGNiN2QyNmExMTk5NzRjOGUy
+    NWMzOWRjNTMwM2YxZjFjYjUzYmMyYjU1YjVkNGNjOWFiMTRkOTE=

data/lib/url_scrubber/version.rb

@@ -1,3 +1,3 @@
 module UrlScrubber
-  VERSION = "0.7.20"
+  VERSION = "0.8.0"
 end

data/lib/url_scrubber.rb

@@ -12,8 +12,8 @@ module UrlScrubber
     return nil unless m
 
     url = m[1]
-    url.sub!(/^https/, 'http')
-    url.sub!(/^htp/, 'http')
+    url.sub!(/^https/i, 'http')
+    url.sub!(/^htp/i, 'http')
     url.sub!(/\/+$/, '')
     url.sub!(/;+$/, '')
     url.sub!('#!/', '')
@@ -23,6 +23,8 @@ module UrlScrubber
     remove_html_tags!(url)
     url = drop_anchor!(special_cases(url))
     url.chomp(',')
+    url.gsub!(/\/+$/, '') # remove any trailing slashes (/) in the resulting URL
+    return url
   end
 
   def self.service_of(url)
@@ -159,7 +161,7 @@ module UrlScrubber
     when :google    then return sc_google_plus(url)
     when :flickr    then return sc_flickr(url)
     when :pinterest then return sc_pinterest(url)
-    when :vimeo      then return sc_vimeo(url)
+    when :vimeo     then return sc_vimeo(url)
     when :yelp      then return sc_yelp(url)
     end
 
@@ -167,7 +169,9 @@ module UrlScrubber
   end
 
   def self.remove_www!(url)
-    url.sub!(%r{://www\d*\.}, '://')
+    # url.sub!(%r{://www\d*\.}, '://')
+    url.sub!(%r{^https?://www?w?\d*\.}i, 'http://')
+    url.sub!(%r{^https?://m\d*\.}i, 'http://')
     url
   end
 
@@ -228,21 +232,64 @@ module UrlScrubber
   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
+    
     if url.match("/media/albums") || url.match("/media/set")
+      # puts "media"
       url = url.match('\&') ? url.split('&',2)[0] : url
     elsif url.include?('facebook.com/groups/')
       url = drop_url_query!(url)
+    elsif mdata = url.match(regex1)
+      # puts "regex1"
+      # "http://facebook.com/pages/Command-Canada/1434248516885065/timeline"
+      url = mdata[:url]
+      uname = mdata[:uname]
+      uid = mdata[:uid]
+    elsif mdata = url.match(regex2)
+      # puts "regex2"
+      # "https://www.facebook.com/profile.php?id=100009574328879"
+      url, http_response = check_for_redirection(mdata[:url])
+      uid = mdata[:uid]
+    elsif mdata = url.match(regex2a)
+      # puts "regex2a"
+      # "https://www.facebook.com/profile.php?_rdr=p&id=100009574328879"
+      url = "http://facebook.com/profile.php?id=" + mdata[:uid]
+      url, http_response = check_for_redirection(url)
+      uid = mdata[:uid]
+    elsif mdata = url.match(regex4)
+      # puts "#{url} - #{mdata[:uname]}"
+      # "http://facebook.com/home.php?#!/person.name"
+        url = mdata[:url] + mdata[:uname]
+        url = drop_url_query!(url)
+    elsif mdata = url.match(regex3)
+      # puts "regex3"
+      # "http://facebook.com/TonyMollHomeLoans/timeline"
+      if mdata[:uname] != "pages"
+        url = mdata[:url]
+        uname = mdata[:uname]
+      end
+      url = drop_url_query!(url)
     elsif url.include?("facebook.com/profile.php?id=")
+      # puts "profile.php"
       # these were being truncated, they do redirect, but typically a 301 response is generated 
       # so the url is returned unchanged.  Better than truncation.
       url, http_response = check_for_redirection(url)
     else
-      url.sub!(/facebook\.com\/home\.php[\?#!\/]+/, 'facebook.com/')
+      # puts "else"
       url = drop_url_query!(url)
     end
+    
+    # Due to the redirection check, "https" and "www." can be re-introduced
+    url = url.sub(%r{^https?://www.}i, 'http://')
+    url = url.sub(/\?_rdr.*/, '')
     url
   end
-
+  
   def self.sc_linkedin(url)
 
     url.sub!('linkedin.com/companies/', 'linkedin.com/company/')

data/spec/url_scrubber_spec.rb

@@ -30,6 +30,7 @@ describe UrlScrubber do
       UrlScrubber.scrub('http://www.example.com/page').should eq('http://example.com/page')
     end
 
+
     describe 'with youtube urls' do
       it 'should drop /user/ if it exists' do
         UrlScrubber.scrub('http://youtube.com/user/absolutely').should eq('http://youtube.com/absolutely')
@@ -44,6 +45,7 @@ describe UrlScrubber do
       end
     end
 
+
     describe 'with twitter urls' do
       it 'should drop @ from in front of username' do
         UrlScrubber.scrub('http://twitter.com/@absolutely').should eq('http://twitter.com/absolutely')
@@ -69,6 +71,7 @@ describe UrlScrubber do
       end
     end
 
+
     describe 'with facebook urls' do
       it 'should drop /home.php?#!/ from the beginning of the path' do
         UrlScrubber.scrub('http://facebook.com/home.php?#!/person.name').should eq('http://facebook.com/person.name')
@@ -82,11 +85,176 @@ describe UrlScrubber do
         UrlScrubber.scrub('http://facebook.com/person.name?ref=pb').should eq('http://facebook.com/person.name')
       end
 
+      # Vanity URL
+
+      it 'should not change a good vanity url' do
+        UrlScrubber.scrub('http://facebook.com/TonyMollHomeLoans').should eq('http://facebook.com/TonyMollHomeLoans')
+      end
+
+      it 'should only drop the trailing / on a good vanity url' do
+        UrlScrubber.scrub('http://facebook.com/TonyMollHomeLoans/').should eq('http://facebook.com/TonyMollHomeLoans')
+      end
+
+      it 'should only drop the trailing /about on a good vanity url' do
+        UrlScrubber.scrub('http://facebook.com/TonyMollHomeLoans/about').should eq('http://facebook.com/TonyMollHomeLoans')
+      end
+      
+      it 'should only drop the trailing /timeline on a good vanity url' do
+        UrlScrubber.scrub('http://facebook.com/TonyMollHomeLoans/timeline').should eq('http://facebook.com/TonyMollHomeLoans')
+      end
+
+      it 'should only drop the trailing ?_rdr=p on a good vanity url' do
+        UrlScrubber.scrub('http://facebook.com/TonyMollHomeLoans?_rdr=p').should eq('http://facebook.com/TonyMollHomeLoans')
+      end
+
+      # Vanity URL with period in username
+
+      it 'should not change a good vanity url with a period in username' do
+        UrlScrubber.scrub('http://facebook.com/jim.reischling').should eq('http://facebook.com/jim.reischling')
+      end
+
+      it 'should only drop the trailing / on a good vanity url with a period in username' do
+        UrlScrubber.scrub('http://facebook.com/jim.reischling/').should eq('http://facebook.com/jim.reischling')
+      end
+
+      it 'should only drop the trailing /about on a good vanity url with a period in username' do
+        UrlScrubber.scrub('http://facebook.com/jim.reischling/about').should eq('http://facebook.com/jim.reischling')
+      end
+      
+      it 'should only drop the trailing /timeline on a good vanity url with a period in username' do
+        UrlScrubber.scrub('http://facebook.com/jim.reischling/timeline').should eq('http://facebook.com/jim.reischling')
+      end
+
+      it 'should only drop the trailing ?_rdr on a good vanity url with a period in username' do
+        UrlScrubber.scrub('http://facebook.com/jim.reischling?_rdr').should eq('http://facebook.com/jim.reischling')
+      end
+
+      # Vanity URL with two periods in username
+
+      it 'should not change a good vanity url two periods in username' do
+        UrlScrubber.scrub('http://facebook.com/sam.thwaite.5/').should eq('http://facebook.com/sam.thwaite.5')
+      end
+
+      # V1 Non-Vanity URLs
+
+      it 'should not change a good V1 non-vanity url without UID' do
+        UrlScrubber.scrub('http://facebook.com/pages/Chris-Stopp-NMLS-257248-Alpine-Mortgage-Planning').should eq('http://facebook.com/pages/Chris-Stopp-NMLS-257248-Alpine-Mortgage-Planning')
+      end
+
+      it 'should not change a good V1 non-vanity url without UID with trialing slash' do
+        UrlScrubber.scrub('http://facebook.com/pages/Chris-Stopp-NMLS-257248-Alpine-Mortgage-Planning/').should eq('http://facebook.com/pages/Chris-Stopp-NMLS-257248-Alpine-Mortgage-Planning')
+      end
+
+      it 'should not change a good V1 non-vanity url with UID' do
+        UrlScrubber.scrub('http://facebook.com/pages/Chris-Stopp-NMLS-257248-Alpine-Mortgage-Planning/152622158131521').should eq('http://facebook.com/pages/Chris-Stopp-NMLS-257248-Alpine-Mortgage-Planning/152622158131521')
+      end
+
+      it 'should only drop the trailing /about on a good V1 non-vanity url' do
+        UrlScrubber.scrub('http://facebook.com/pages/Chris-Stopp-NMLS-257248-Alpine-Mortgage-Planning/152622158131521/about').should eq('http://facebook.com/pages/Chris-Stopp-NMLS-257248-Alpine-Mortgage-Planning/152622158131521')
+      end
+      
+      it 'should only drop the trailing /info on a good V1 non-vanity url' do
+        UrlScrubber.scrub('http://facebook.com/pages/Chris-Stopp-NMLS-257248-Alpine-Mortgage-Planning/152622158131521/info').should eq('http://facebook.com/pages/Chris-Stopp-NMLS-257248-Alpine-Mortgage-Planning/152622158131521')
+      end
+      
+      it 'should only drop the trailing /timeline on a good V1 non-vanity url' do
+        UrlScrubber.scrub('http://facebook.com/pages/Chris-Stopp-NMLS-257248-Alpine-Mortgage-Planning/152622158131521/timeline').should eq('http://facebook.com/pages/Chris-Stopp-NMLS-257248-Alpine-Mortgage-Planning/152622158131521')
+      end
+
+      it 'should only drop the trailing ?_rdr on a good V1 non-vanity url' do
+        UrlScrubber.scrub('http://facebook.com/pages/Chris-Stopp-NMLS-257248-Alpine-Mortgage-Planning/152622158131521?_rdr').should eq('http://facebook.com/pages/Chris-Stopp-NMLS-257248-Alpine-Mortgage-Planning/152622158131521')
+      end
+
+      # V2 Non-Vanity URLs
+
+      it 'should not change a good V2 non-vanity url without UID' do
+        UrlScrubber.scrub('http://facebook.com/Pinnacle-Capital-Mortgage-Lynette-Lea-Jorden-Reverse-Mortgage-Specialist-702124366560414').should eq('http://facebook.com/Pinnacle-Capital-Mortgage-Lynette-Lea-Jorden-Reverse-Mortgage-Specialist-702124366560414')
+      end
+
+      it 'should not change a good V2 non-vanity url without UID with trialing slash' do
+        UrlScrubber.scrub('http://facebook.com/Pinnacle-Capital-Mortgage-Lynette-Lea-Jorden-Reverse-Mortgage-Specialist-702124366560414/').should eq('http://facebook.com/Pinnacle-Capital-Mortgage-Lynette-Lea-Jorden-Reverse-Mortgage-Specialist-702124366560414')
+      end
+
+      it 'should only drop the trailing /about on a good V2 non-vanity url' do
+        UrlScrubber.scrub('http://facebook.com/Pinnacle-Capital-Mortgage-Lynette-Lea-Jorden-Reverse-Mortgage-Specialist-702124366560414/about').should eq('http://facebook.com/Pinnacle-Capital-Mortgage-Lynette-Lea-Jorden-Reverse-Mortgage-Specialist-702124366560414')
+      end
+      
+      it 'should only drop the trailing /info on a good V2 non-vanity url' do
+        UrlScrubber.scrub('http://facebook.com/Pinnacle-Capital-Mortgage-Lynette-Lea-Jorden-Reverse-Mortgage-Specialist-702124366560414/info').should eq('http://facebook.com/Pinnacle-Capital-Mortgage-Lynette-Lea-Jorden-Reverse-Mortgage-Specialist-702124366560414')
+      end
+      
+      it 'should only drop the trailing /timeline on a good V2 non-vanity url' do
+        UrlScrubber.scrub('http://facebook.com/Pinnacle-Capital-Mortgage-Lynette-Lea-Jorden-Reverse-Mortgage-Specialist-702124366560414/timeline').should eq('http://facebook.com/Pinnacle-Capital-Mortgage-Lynette-Lea-Jorden-Reverse-Mortgage-Specialist-702124366560414')
+      end
+
+      it 'should only drop the trailing ?_rdr on a good V2 non-vanity url' do
+        UrlScrubber.scrub('http://facebook.com/Pinnacle-Capital-Mortgage-Lynette-Lea-Jorden-Reverse-Mortgage-Specialist-702124366560414?_rdr').should eq('http://facebook.com/Pinnacle-Capital-Mortgage-Lynette-Lea-Jorden-Reverse-Mortgage-Specialist-702124366560414')
+      end
+
+      it 'should only drop the trailing app_267091300008193 on a good Vanity url' do
+        UrlScrubber.scrub('http://facebook.com/theloansisters/app_267091300008193').should eq('http://facebook.com/theloansisters')
+      end
+
+      it 'should handle profile URL with shorter UID' do
+        UrlScrubber.scrub('http://www.facebook.com/profile.php?id=1165522415').should eq('http://facebook.com/profile.php?id=1165522415')
+      end
+
+      it 'should handle profile URL with longer UID' do
+        UrlScrubber.scrub('http://www.facebook.com/profile.php?id=100004113611106').should eq('http://facebook.com/profile.php?id=100004113611106')
+      end
+
+      it 'should handle profile URL with longer UID and https' do
+        UrlScrubber.scrub('https://www.facebook.com/profile.php?id=100000735668376').should eq('http://facebook.com/profile.php?id=100000735668376')
+      end
+
+      it 'should handle profile URL with fref' do
+        UrlScrubber.scrub('https://www.facebook.com/profile.php?id=100007058896205&fref=ts').should eq('http://facebook.com/profile.php?id=100007058896205')
+      end
+
+      it 'should handle profile URL with &_rdr' do
+        UrlScrubber.scrub('https://www.facebook.com/profile.php?id=100008623904282&_rdr').should eq('http://facebook.com/profile.php?id=100008623904282')
+      end
+
+      it 'should handle profile URL with _rdr=p&' do
+        UrlScrubber.scrub('https://www.facebook.com/profile.php?_rdr=p&id=100009574328879').should eq('http://facebook.com/profile.php?id=100009574328879')
+      end
+      
+      it 'should handle uppercase HTTP' do
+        UrlScrubber.scrub('HTTP://facebook.com/TonyMollHomeLoans').should eq('http://facebook.com/TonyMollHomeLoans')
+      end
+
+      it 'should handle uppercase HTTPS' do
+        UrlScrubber.scrub('HTTPS://facebook.com/TonyMollHomeLoans').should eq('http://facebook.com/TonyMollHomeLoans')
+      end
+
+      it 'should handle ww.' do
+        UrlScrubber.scrub('http://ww.facebook.com/TonyMollHomeLoans').should eq('http://facebook.com/TonyMollHomeLoans')
+      end
+
+      it 'should handle ww1.' do
+        UrlScrubber.scrub('http://ww1.facebook.com/TonyMollHomeLoans').should eq('http://facebook.com/TonyMollHomeLoans')
+      end
+
+      it 'should handle www1.' do
+        UrlScrubber.scrub('http://ww1.facebook.com/TonyMollHomeLoans').should eq('http://facebook.com/TonyMollHomeLoans')
+      end
+
+      it 'should handle wwww.' do
+        UrlScrubber.scrub('http://wwww.facebook.com/TonyMollHomeLoans').should eq('http://facebook.com/TonyMollHomeLoans')
+      end
+
+      it 'should handle mobile urls (m.)' do
+        UrlScrubber.scrub('http://m.facebook.com/TonyMollHomeLoans').should eq('http://facebook.com/TonyMollHomeLoans')
+      end
+
       it 'should not kick in for a non-facebook url' do
         UrlScrubber.scrub('http://example.com/home.php?#!/person.name').should_not eq('http://example.com/person.name')
       end
     end
 
+
+    # LinkedIn
+
     describe 'with linkedin urls' do
       it 'should change /companies/ to /company/' do
         UrlScrubber.scrub('http://linkedin.com/companies/1337').should eq('http://linkedin.com/company/1337')
@@ -136,7 +304,9 @@ describe UrlScrubber do
     end
 
     describe 'with slideshare urls' do
-      pending
+      skip "is not implemented yet" do
+        # pending
+      end
     end
 
     describe 'with flickr urls' do
@@ -174,7 +344,9 @@ describe UrlScrubber do
     end
 
     describe 'with vimeo urls' do
-      pending
+      skip "is not implemented yet" do
+        # pending
+      end
     end
     
     describe 'with instagram urls' do
@@ -242,7 +414,7 @@ describe UrlScrubber do
     end
     
     it 'returns :tumblr for Tumblr urls' do
-      UrlScrubber.service_of('http://cisco.tumblr.com).should eq :tumblr
+      UrlScrubber.service_of('http://cisco.tumblr.com').should eq :tumblr
     end
     
     it 'returns :other for other urls' do
@@ -258,132 +430,132 @@ describe UrlScrubber do
 
     describe 'for youtube' do
       it 'returns true for apparent channel urls' do
-        UrlScrubber.ideal_form?('http://youtube.com/absolutely').should be_true
+        UrlScrubber.ideal_form?('http://youtube.com/absolutely').should be_truthy
       end
 
       it 'returns false for videos' do
-        UrlScrubber.ideal_form?('http://youtube.com/watch?v=vRGMAW1wzQ8').should be_false
+        UrlScrubber.ideal_form?('http://youtube.com/watch?v=vRGMAW1wzQ8').should be_falsey
       end
     end
 
     describe 'for twitter' do
       it 'returns true for apparent user urls' do
-        UrlScrubber.ideal_form?('http://twitter.com/absolutely').should be_true
+        UrlScrubber.ideal_form?('http://twitter.com/absolutely').should be_truthy
       end
 
       it 'returns false for other pages' do
-        UrlScrubber.ideal_form?('http://twitter.com/').should be_false
+        UrlScrubber.ideal_form?('http://twitter.com/').should be_falsey
       end
     end
 
     describe 'for facebook' do
       it 'returns true for apparent user urls' do
-        UrlScrubber.ideal_form?('http://facebook.com/person.name').should be_true
-        UrlScrubber.ideal_form?('http://facebook.com/profile.php?id=543123521').should be_true
+        UrlScrubber.ideal_form?('http://facebook.com/person.name').should be_truthy
+        UrlScrubber.ideal_form?('http://facebook.com/profile.php?id=543123521').should be_truthy
       end
 
       it 'returns false for other urls' do
-        UrlScrubber.ideal_form?('http://facebook.com/').should be_false
+        UrlScrubber.ideal_form?('http://facebook.com/').should be_falsey
       end
     end
 
     describe 'for linkedin' do
       it 'returns true for apparent company urls' do
-        UrlScrubber.ideal_form?('http://linkedin.com/company/1337').should be_true
-        UrlScrubber.ideal_form?('http://www.linkedin.com/profile/view?id=12341324').should be_true
-        UrlScrubber.ideal_form?('http://linkedin.com/company/brand-name').should be_true
+        UrlScrubber.ideal_form?('http://linkedin.com/company/1337').should be_truthy
+        UrlScrubber.ideal_form?('http://www.linkedin.com/profile/view?id=12341324').should be_truthy
+        UrlScrubber.ideal_form?('http://linkedin.com/company/brand-name').should be_truthy
       end
 
       it 'returns false for other urls' do
-        UrlScrubber.ideal_form?('http://linkedin.com/jobs/c-Cisco').should be_false
+        UrlScrubber.ideal_form?('http://linkedin.com/jobs/c-Cisco').should be_falsey
       end
     end
 
     describe 'for google plus' do
       it 'returns true for apparent person urls' do
-        UrlScrubber.ideal_form?('http://plus.google.com/+SomeName').should be_true
-        UrlScrubber.ideal_form?('http://plus.google.com/u/0/b/111111111111111111111').should be_true
-        UrlScrubber.ideal_form?('https://plus.google.com/u/0/5432123454135/posts').should be_true
+        UrlScrubber.ideal_form?('http://plus.google.com/+SomeName').should be_truthy
+        UrlScrubber.ideal_form?('http://plus.google.com/u/0/b/111111111111111111111').should be_truthy
+        UrlScrubber.ideal_form?('https://plus.google.com/u/0/5432123454135/posts').should be_truthy
       end
 
       it 'returns false for other urls' do
-        UrlScrubber.ideal_form?('http://plus.google.com/').should be_false
+        UrlScrubber.ideal_form?('http://plus.google.com/').should be_falsey
       end
     end
 
     describe 'for slideshare' do
       it 'returns true for apparent user urls' do
-        UrlScrubber.ideal_form?('http://slideshare.net/absolutely').should be_true
+        UrlScrubber.ideal_form?('http://slideshare.net/absolutely').should be_truthy
       end
 
       it 'returns false for other urls' do
-        UrlScrubber.ideal_form?('http://slideshare.net/absolutely/how-to-create-great-slides-for-presentations').should be_false
+        UrlScrubber.ideal_form?('http://slideshare.net/absolutely/how-to-create-great-slides-for-presentations').should be_falsey
       end
     end
 
     describe 'for flickr' do
       it 'returns true for apparent user urls' do
-        UrlScrubber.ideal_form?('http://flickr.com/username').should be_true
+        UrlScrubber.ideal_form?('http://flickr.com/username').should be_truthy
       end
 
       it 'returns false for other urls' do
-        UrlScrubber.ideal_form?('http://flickr.com/').should be_false
+        UrlScrubber.ideal_form?('http://flickr.com/').should be_falsey
       end
     end
 
     describe 'for pinterest' do
       it 'returns true for apparent user urls' do
-        UrlScrubber.ideal_form?('http://pinterest.com/username').should be_true
+        UrlScrubber.ideal_form?('http://pinterest.com/username').should be_truthy
       end
 
       it 'returns false for other urls' do
-        UrlScrubber.ideal_form?('http://pinterest.com/pin/532412513451524').should be_false
+        UrlScrubber.ideal_form?('http://pinterest.com/pin/532412513451524').should be_falsey
       end
     end
 
     describe 'for yelp' do
       it 'returns true for apparent business urls' do
-        UrlScrubber.ideal_form?('http://yelp.com/very-important-business').should be_true
+        UrlScrubber.ideal_form?('http://yelp.com/very-important-business').should be_truthy
       end
 
       it 'returns false for other urls' do
-        UrlScrubber.ideal_form?('http://yelp.com/user_details?userid=Aheunaobuh-huoanuhbAU').should be_false
+        UrlScrubber.ideal_form?('http://yelp.com/user_details?userid=Aheunaobuh-huoanuhbAU').should be_falsey
       end
     end
 
     describe 'for vimeo' do
       it 'returns true for apparent user urls' do
-        UrlScrubber.ideal_form?('http://vimeo.com/absolutely').should be_true
+        UrlScrubber.ideal_form?('http://vimeo.com/absolutely').should be_truthy
       end
 
       it 'returns false for video urls' do
-        UrlScrubber.ideal_form?('http://vimeo.com/45453874578').should be_false
+        UrlScrubber.ideal_form?('http://vimeo.com/45453874578').should be_falsey
       end
     end
 
     describe 'for instagram' do
       it 'returns true for apparent user urls' do
-        UrlScrubber.ideal_form?('http://instagram.com/username').should be_true
+        UrlScrubber.ideal_form?('http://instagram.com/username').should be_truthy
       end
 
       it 'returns false for other urls' do
-        UrlScrubber.ideal_form?('http://instagram.com/532513451524').should be_false
+        UrlScrubber.ideal_form?('http://instagram.com/532513451524').should be_falsey
       end
     end
 
     describe 'for tumblr' do
       it 'returns true for apparent business urls' do
-        UrlScrubber.ideal_form?('http://cisco.tumblr.com').should be_true
+        UrlScrubber.ideal_form?('http://cisco.tumblr.com').should be_truthy
       end
 
       it 'returns false for user urls' do
-        UrlScrubber.ideal_form?('http://tumblr.com/joe').should be_false
+        UrlScrubber.ideal_form?('http://tumblr.com/joe').should be_falsey
       end
     end
 
     describe 'for other sites' do
       it 'returns true for any other site, really' do
-        UrlScrubber.ideal_form?('http://example.com/absolutely/anything').should be_true
+        UrlScrubber.ideal_form?('http://example.com/absolutely/anything').should be_truthy
       end
     end
   end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: url_scrubber
 version: !ruby/object:Gem::Version
-  version: 0.7.20
+  version: 0.8.0
 platform: ruby
 authors:
 - Colin Langton
@@ -11,7 +11,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-06-12 00:00:00.000000000 Z
+date: 2016-04-08 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec
@@ -124,7 +124,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.1.10
+rubygems_version: 2.4.8
 signing_key: 
 specification_version: 4
 summary: Clean up URLs.