gluttonberg-core 2.5.5 → 2.5.6

data/lib/gluttonberg/content/despamilator/filter/emails.rb

@@ -0,0 +1,49 @@
+module Gluttonberg
+  module Content
+    require 'despamilator/filter'
+
+    module DespamilatorFilter
+
+      class Emails < Despamilator::Filter
+
+        def name
+          'Emails'
+        end
+
+        def description
+          'Detects each emails in a string'
+        end
+
+        def parse subject
+          @email_regex ||= begin
+            email_name_regex  = '[A-Z0-9_\.%\+\-\']+'
+            domain_head_regex = '(?:[A-Z0-9\-]+\.)+'
+            domain_tld_regex  = '(?:[A-Z]{2,4}|museum|travel)'
+            /\A#{email_name_regex}@#{domain_head_regex}#{domain_tld_regex}\z/i
+          end
+
+          comment_email_as_spam = Gluttonberg::Setting.get_setting("comment_email_as_spam")
+          if comment_email_as_spam == "Yes"
+            text = subject.text.strip
+            subject.register_match!({
+             :score => 1.0, :filter => self
+            }) if @email_regex.match(text)
+          end
+
+          comment_number_of_emails_allowed = Gluttonberg::Setting.get_setting("comment_number_of_emails_allowed")
+          if !comment_number_of_emails_allowed.blank? && comment_number_of_emails_allowed.to_i > 0
+            comment_number_of_emails_allowed = comment_number_of_emails_allowed.to_i
+            subject.text.split(/%s/).each do |word|
+              subject.register_match!({
+               :score => (1.0/comment_number_of_emails_allowed), :filter => self
+              }) if @email_regex.match(word)
+            end
+          end
+
+        end
+
+      end
+
+    end
+  end #Content
+end #Gluttonberg

data/lib/gluttonberg/content/despamilator/filter/gtubs_test_filter.rb

@@ -0,0 +1,25 @@
+module Gluttonberg
+  module Content
+    require 'despamilator/filter'
+
+    module DespamilatorFilter
+
+      class GtubsTestFilter < Despamilator::Filter
+
+        def name
+          'GTubs Test Filter'
+        end
+
+        def description
+          'Detects the special test string (Despamilator.gtubs_test_string) and assigns a big score.'
+        end
+
+        def parse subject
+          subject.register_match!({:score => 100, :filter => self}) if subject.text == Despamilator.gtubs_test_string
+        end
+
+      end
+
+    end
+  end #Content
+end #Gluttonberg

data/lib/gluttonberg/content/despamilator/filter/html_tags.rb

@@ -0,0 +1,134 @@
+module Gluttonberg
+  module Content
+
+    module DespamilatorFilter
+
+      class HtmlTags < Despamilator::Filter
+
+        def parse subject
+          text = subject.text.downcase
+
+          html_tags.each do |tag|
+            opening_elements = text.count(/<\s*#{tag}\W/)
+            closing_elements = text.count(/\W#{tag}\s*\/>/)
+
+            if opening_elements > 0 or closing_elements > 0
+              safest_element_count = opening_elements > closing_elements ? opening_elements : closing_elements
+              subject.register_match!({:score => 0.6 * safest_element_count, :filter => self})
+            end
+          end
+        end
+
+        def name
+          'HTML tags'
+        end
+
+        def description
+          'Detects HTML tags in text'
+        end
+
+        def html_tags
+          # make sure these are lowercase, in order to save processing
+          [
+                  '!--',
+                  '!doctype',
+                  'a',
+                  'abbr',
+                  'acronym',
+                  'address',
+                  'applet',
+                  'area',
+                  'b',
+                  'base',
+                  'basefont',
+                  'bdo',
+                  'big',
+                  'blockquote',
+                  'body',
+                  'br',
+                  'button',
+                  'caption',
+                  'center',
+                  'cite',
+                  'code',
+                  'col',
+                  'colgroup',
+                  'dd',
+                  'del',
+                  'dfn',
+                  'dir',
+                  'div',
+                  'dl',
+                  'dt',
+                  'em',
+                  'fieldset',
+                  'font',
+                  'form',
+                  'frame',
+                  'frameset',
+                  'h1',
+                  'h2',
+                  'h3',
+                  'h4',
+                  'h5',
+                  'h6',
+                  'head',
+                  'hr',
+                  'html',
+                  'i',
+                  'iframe',
+                  'img',
+                  'input',
+                  'ins',
+                  'isindex',
+                  'kbd',
+                  'label',
+                  'legend',
+                  'li',
+                  'link',
+                  'map',
+                  'menu',
+                  'meta',
+                  'noframes',
+                  'noscript',
+                  'object',
+                  'ol',
+                  'optgroup',
+                  'option',
+                  'p',
+                  'param',
+                  'pre',
+                  'q',
+                  's',
+                  'samp',
+                  'select',
+                  'small',
+                  'span',
+                  'strike',
+                  'strong',
+                  'style',
+                  'sub',
+                  'sup',
+                  'table',
+                  'tbody',
+                  'td',
+                  'textarea',
+                  'tfoot',
+                  'th',
+                  'thead',
+                  'title',
+                  'tr',
+                  'tt',
+                  'u',
+                  'ul',
+                  'var',
+                  'xmp'
+          ]
+
+        end
+
+      end
+
+    end
+  end #Content
+end #Gluttonberg

data/lib/gluttonberg/content/despamilator/filter/ip_address_url.rb

@@ -0,0 +1,27 @@
+module Gluttonberg
+  module Content
+    require 'despamilator/filter'
+
+    module DespamilatorFilter
+
+      class IPAddressURL < Despamilator::Filter
+
+        def name
+          'IP Address URL'
+        end
+
+        def description
+          'Detects IP address URLs'
+        end
+
+        def parse subject
+          subject.register_match!({
+              :score => 0.5, :filter => self
+          }) if subject.text.downcase.count(/http:\/\/\d+\.\d+\.\d+\.\d+/) > 0
+        end
+
+      end
+
+    end
+  end #Content
+end #Gluttonberg

data/lib/gluttonberg/content/despamilator/filter/long_words.rb

@@ -0,0 +1,29 @@
+module Gluttonberg
+  module Content
+    require 'despamilator/filter'
+
+    module DespamilatorFilter
+
+      class LongWords < Despamilator::Filter
+
+        def name
+          'Long Words'
+        end
+
+        def description
+          'Detects long and unbroken strings'
+        end
+
+        def parse subject
+          subject.text.without_uris.words.each do |word|
+            subject.register_match!({
+              :score => 0.1, :filter => self
+            }) if word.length > 20
+          end
+        end
+
+      end
+
+    end
+  end #Content
+end #Gluttonberg

data/lib/gluttonberg/content/despamilator/filter/mixed_case.rb

@@ -0,0 +1,25 @@
+module Gluttonberg
+  module Content
+    module DespamilatorFilter
+
+      class MixedCase < Despamilator::Filter
+        def name
+          'Mixed Case String'
+        end
+
+        def description
+          'Detects mixed case strings.'
+        end
+
+        def parse subject
+          text = subject.text.without_uris
+          count = text.remove_and_count!(/[a-z][A-Z]/)
+          count += text.remove_and_count!(/[a-z][A-Z][a-z]/)
+          subject.register_match!({:score => 0.1 * count, :filter => self}) if count > 0
+        end
+
+      end
+
+    end
+  end #Content
+end #Gluttonberg

data/lib/gluttonberg/content/despamilator/filter/naughty_words.rb

@@ -0,0 +1,80 @@
+module Gluttonberg
+  module Content
+    require 'despamilator/filter'
+
+    module DespamilatorFilter
+
+      class NaughtyWords < Despamilator::Filter
+
+        def name
+          'Naughty Words'
+        end
+
+        def description
+          'Detects cheeky words'
+        end
+
+        def parse subject
+          text = subject.text.downcase
+
+          naughty_words.each do |word|
+            subject.register_match!({:score => 0.1, :filter => self}) if text =~ /\b#{word}s?\b/
+          end
+
+          gb_blacklist_settings = Gluttonberg::Setting.get_setting("comment_blacklist")
+          unless gb_blacklist_settings.blank?
+            gb_blacklist_settings_words = gb_blacklist_settings.split(",")
+            gb_blacklist_settings_words.each do |word|
+              subject.register_match!({:score => 1.0, :filter => self}) if text =~ /\b#{word.strip.downcase}s?\b/
+            end
+          end
+        end
+
+        def local_parse subject
+          local_score = 0.0
+          unless subject.blank?
+            text = subject.downcase
+
+            naughty_words.each do |word|
+              local_score += 0.1 if text =~ /\b#{word}s?\b/
+            end
+
+            gb_blacklist_settings = Gluttonberg::Setting.get_setting("comment_blacklist")
+            unless gb_blacklist_settings.blank?
+              gb_blacklist_settings_words = gb_blacklist_settings.split(",")
+              gb_blacklist_settings_words.each do |word|
+                local_score += 1.0 if text.include?(word.strip.downcase)
+              end
+            end
+          end
+          local_score
+        end
+
+        def naughty_words
+          words = %w{
+            underage
+            penis
+            viagra
+            bondage
+            cunt
+            fuck
+            shit
+            dick
+            tits
+            nude
+            dicks
+            shemale
+            dildo
+            porn
+            cock
+            pussy
+            clit
+            preteen
+            lolita
+           }
+        end
+
+      end
+    end
+  end #Content
+end #Gluttonberg

data/lib/gluttonberg/content/despamilator/filter/no_vowels.rb

@@ -0,0 +1,28 @@
+module Gluttonberg
+  module Content
+    require 'despamilator/filter'
+
+    module DespamilatorFilter
+
+      class NoVowels < Despamilator::Filter
+
+        NO_VOWELS_REGEX = /^[b-df-hj-np-tv-xzB-DF-HJ-NP-TV-XZ]+$/
+
+        def name
+          'No Vowels'
+        end
+
+        def description
+          'Detects things that are all letters but no vowels and separated by spaces'
+        end
+
+        def parse(subject)
+          words = subject.text.split(/\s+/).select{|str| str.match(NO_VOWELS_REGEX)}
+          unless words.empty?
+            subject.register_match!({:score => ((words.length ** 2).to_f / 100) , :filter => self})
+          end
+        end
+      end
+    end
+  end #Content
+end #Gluttonberg

data/lib/gluttonberg/content/despamilator/filter/numbers_and_words.rb

@@ -0,0 +1,55 @@
+module Gluttonberg
+  module Content
+    require 'despamilator/filter'
+
+    module DespamilatorFilter
+
+      class NumbersAndWords < Despamilator::Filter
+
+        def parse subject
+          text = tidy_text(subject)
+
+          [
+                  /\w\d+/,
+                  /\d+\w/,
+                  /\d+($|\b)/
+          ].each do |regexp|
+            matches = text.scan(regexp)
+
+            next if matches.empty?
+
+            matches.each do |to_remove|
+              to_remove = to_remove.to_s
+              text.sub!(to_remove, '') unless to_remove.empty?
+              subject.register_match!({:score => 0.1, :filter => self})
+            end
+          end
+        end
+
+        def name
+          'Numbers next to words'
+        end
+
+        def description
+          'Detects unusual number/word combinations'
+        end
+
+        private
+
+        def tidy_text subject
+          text = subject.text.without_uris
+          text.downcase!
+
+          # strip out "good numbers"
+          text.gsub!(/h[1-6]/, '')
+          text.gsub!(/(^|\b)\d+($|\b)/, '')
+          text.gsub!(/(^|\b)\d+(,|\.)\d+($|\b)/, '')
+          text.gsub!(/(^|\b)\d+(st|nd|rd|th)($|\b)/, '')
+
+          text
+        end
+      end
+
+    end
+  end #Content
+end #Gluttonberg

data/lib/gluttonberg/content/despamilator/filter/obfuscated_urls.rb

@@ -0,0 +1,45 @@
+module Gluttonberg
+  module Content
+    module DespamilatorFilter
+
+      class ObfuscatedURLs < Despamilator::Filter
+        def name
+          'Obfuscated URLs'
+        end
+
+        def description
+          'Finds lame attempts at obfuscating urls.'
+        end
+
+        def parse subject
+          text = subject.text.without_uris.downcase
+          count = find_space_separated_parts text
+          count += find_space_separated_characters text
+
+          # weird maths below is due to some issue with ruby 1.9.2 multiplying floats by 3 (?!)
+          subject.register_match!({:score => (4.0 * count) / 10, :filter => self}) if count > 0
+        end
+
+        private
+
+        def find_space_separated_parts text
+          text.count(/www\s+\w+\s+com/)
+        end
+
+        def find_space_separated_characters text
+          count = 0
+
+          text.split(/[a-z][a-z]/).each do |candidate|
+            candidate.strip!
+            candidate.gsub!(/\s+/, '')
+            count += 1 if candidate =~ /\w{5,}\.\w{2,3}/
+          end
+
+          count
+        end
+
+      end
+
+    end
+  end #Content
+end #Gluttonberg

data/lib/gluttonberg/content/despamilator/filter/prices.rb

@@ -0,0 +1,23 @@
+module Gluttonberg
+  module Content
+    module DespamilatorFilter
+
+      class Prices < Despamilator::Filter
+        def name
+          'Prices'
+        end
+
+        def description
+          'Detects prices in text.'
+        end
+
+        def parse subject
+          price_count = subject.text.count(/\$\s*\d+/)
+          subject.register_match!({:score => 0.075 * price_count, :filter => self}) if price_count > 0
+        end
+
+      end
+
+    end
+  end #Content
+end #Gluttonberg

data/lib/gluttonberg/content/despamilator/filter/script_tag.rb

@@ -0,0 +1,25 @@
+module Gluttonberg
+  module Content
+    require 'despamilator/filter'
+
+    module DespamilatorFilter
+
+      class ScriptTag < Despamilator::Filter
+
+        def parse subject
+          subject.register_match!({:score => 1, :filter => self}) if subject.text.downcase.match(/<\/?script(>|\s+|\n|\r)/)
+        end
+
+        def name
+          'Script tag'
+        end
+
+        def description
+          'Searches for variations for the HTML script tag'
+        end
+
+      end
+
+    end
+  end #Content
+end #Gluttonberg

data/lib/gluttonberg/content/despamilator/filter/shouting.rb

@@ -0,0 +1,38 @@
+module Gluttonberg
+  module Content
+    require 'despamilator/filter'
+
+    module DespamilatorFilter
+
+      class Shouting < Despamilator::Filter
+
+        def name
+          'Shouting'
+        end
+
+        def description
+          'Detects and scores shouting (all caps)'
+        end
+
+        def parse subject
+          # strip HTML
+          text = subject.text.gsub(/<\/?[^>]*>/, "")
+
+          return if text.length < 20
+
+          uppercased = text.scan(/[A-Z][A-Z]+/).join.length
+          lowercased = text.count(/[a-z]/)
+
+          if uppercased > 0
+            subject.register_match!({
+                :score => (uppercased.to_f / (uppercased + lowercased)) * 0.5,
+                :filter => self
+            })
+          end
+        end
+
+      end
+
+    end
+  end #Content
+end #Gluttonberg

data/lib/gluttonberg/content/despamilator/filter/spammy_tlds.rb

@@ -0,0 +1,26 @@
+module Gluttonberg
+  module Content
+    require 'despamilator/filter'
+
+    module DespamilatorFilter
+
+      class SpammyTLDs < Despamilator::Filter
+
+        def name
+          'Spammy TLDs'
+        end
+
+        def description
+          'Detects TLDs that are more commonly associated with spam.'
+        end
+
+        def parse subject
+          matches = subject.text.count(/\w{5,}\.(info|biz|xxx)\b/)
+          subject.register_match!({:score => 0.05 * matches, :filter => self}) if matches > 0
+        end
+
+      end
+
+    end
+  end #Content
+end #Gluttonberg

data/lib/gluttonberg/content/despamilator/filter/square_brackets.rb

@@ -0,0 +1,27 @@
+module Gluttonberg
+  module Content
+    require 'despamilator/filter'
+
+    module DespamilatorFilter
+
+      class SquareBrackets < Despamilator::Filter
+
+        def name
+          'Square Brackets'
+        end
+
+        def description
+          'Detects each square bracket in a string'
+        end
+
+        def parse subject
+          subject.text.downcase.scan(/(\[|\])/).each do |match|
+            subject.register_match!({:score => 0.05, :filter => self})
+          end
+        end
+
+      end
+
+    end
+  end #Content
+end #Gluttonberg

data/lib/gluttonberg/content/despamilator/filter/trailing_number.rb

@@ -0,0 +1,25 @@
+module Gluttonberg
+  module Content
+    require 'despamilator/filter'
+
+    module DespamilatorFilter
+
+      class TrailingNumber < Despamilator::Filter
+
+        def name
+          'Trailing Number'
+        end
+
+        def description
+          'Detects a trailing cache busting number'
+        end
+
+        def parse subject
+          subject.register_match!({:score => 0.1, :filter => self}) if subject.text.without_uris =~ /\b\d+\s*$/
+        end
+
+      end
+
+    end
+  end #Content
+end #Gluttonberg