despamilator 0.2

data/spec/despamilator_spec.rb

@@ -0,0 +1,15 @@
+require File.dirname(__FILE__) + '/spec_helper.rb'
+
+describe Despamilator do
+  before :each do
+    @dspam = Despamilator.new('this text is absolutely fine')
+  end
+
+  it "should return a zero score for fine text" do
+    @dspam.score.should == 0
+  end
+
+  it "should return no matching filter for fine text" do
+    @dspam.matched_by.should be_empty
+  end
+end

data/spec/filters/html_tags_spec.rb

@@ -0,0 +1,144 @@
+require File.dirname(__FILE__) + '/../spec_helper.rb'
+
+context "HtmlTags" do
+  describe "filtering" do
+    [
+            '!--',
+            '!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'
+    ].each do |script_tag|
+      [script_tag.upcase, script_tag.downcase].each do |script_tag|
+        [
+                "<#{script_tag}",
+                "#{script_tag}/>",
+                "<#{script_tag}/>",
+                "< #{script_tag} ",
+                "#{script_tag} />",
+                "<\n#{script_tag}\n/>",
+                "<\n#{script_tag} ",
+                "#{script_tag}\n/>",
+                "<\r#{script_tag}\r/>"
+        ].each do |script_tag|
+          it "should detect '#{script_tag}'" do
+            dspam = Despamilator.new(script_tag)
+            dspam.score.should == 0.3
+          end
+        end
+      end
+    end
+
+    describe 'attributes' do
+      before :all do
+        @dspam = Despamilator.new('<xmp>').matched_by.first
+      end
+
+      it "should have a name" do
+        @dspam.name.should == 'Detects HTML tags in text'
+      end
+
+      it "should have a description" do
+        @dspam.description.should == 'Searches for various HTML tags'
+      end
+
+      it "should have a filename" do
+        @dspam.filename.should == 'html_tags.rb'
+      end
+    end
+
+    describe 'bug fixes' do
+      it "should detect an h1" do
+        Despamilator.new('<h1>TITLE!!</h1>').score.should == 0.3
+      end
+    end
+  end
+end

data/spec/filters/naughty_q_spec.rb

@@ -0,0 +1,39 @@
+require File.dirname(__FILE__) + '/../spec_helper.rb'
+
+describe "NaughtyQ" do
+  it "should return a score for 1 misplaced q" do
+    dspam = Despamilator.new('qtu')
+    dspam.score.should == 0.2
+  end
+
+  describe 'attributes' do
+    before :each do
+      @filter = Despamilator.new('qtqt').matched_by.first
+    end
+
+    it "should have a filename" do
+      @filter.filename.should == 'naughty_q.rb'
+    end
+
+    it "should have a name" do
+      @filter.name.should == 'Naughty Q'
+    end
+
+    it "should have a description" do
+      @filter.description.should == 'Detects possible misuse of the letter Q (English language)'
+    end
+
+    it "should have a number of matches" do
+      @filter.matches.should == 2
+    end
+
+    it "should have a score" do
+      @filter.score.should == 0.4
+    end
+  end
+
+  it "should score more for 3 misplaced q's" do
+    dspam = Despamilator.new('qtuqsq')
+    dspam.score.to_s.should == 0.4.to_s
+  end
+end

data/spec/filters/numbers_and_words_spec.rb

@@ -0,0 +1,59 @@
+require File.dirname(__FILE__) + '/../spec_helper.rb'
+
+describe "NumbersAndWords" do
+  [1, 4, 10, 100000, '1,000,000', '1st', '2nd', '3rd', '4th', '5th', '6th', '10th', '122nd'].each do |number|
+    it "should return a blank for a #{number}" do
+      dspam = Despamilator.new(number)
+      dspam.score.should == 0
+    end
+  end
+
+  ['wanga x5 mool', '4ghk', 'XTHL9'].each do |string|
+    it "should detect suspicious number word combos such as #{string}" do
+      dspam = Despamilator.new(string)
+      dspam.score.should == 0.1
+    end
+  end
+
+  ['4wanga x5 mool', '4g6hk', 'XT7HL9', '77th8nd'].each do |string|
+    it "should detect multiple suspicious number word combos such as #{string}" do
+      dspam = Despamilator.new(string)
+      dspam.score.should == 0.2
+    end
+  end
+
+  [1, 2, 3, 4, 5, 6].each do |tag_no|
+    header_tag = "h#{tag_no}"
+
+    it "should ignore html header tag #{header_tag}" do
+      dspam = Despamilator.new(header_tag)
+      dspam.score.should == 0
+    end
+  end
+
+  describe 'attributes' do
+    before :each do
+      @filter = Despamilator.new('X5T').matched_by.first
+    end
+
+    it "should have a filename" do
+      @filter.filename.should == 'numbers_and_words.rb'
+    end
+
+    it "should have a name" do
+      @filter.name.should == 'Numbers next to words'
+    end
+
+    it "should have a description" do
+      @filter.description.should == 'Detects unusual number/word combinations'
+    end
+
+    it "should have a number of matches" do
+      @filter.matches.should == 1
+    end
+
+    it "should have a score" do
+      @filter.score.should == 0.1
+    end
+  end
+end

data/spec/filters/script_tag_spec.rb

@@ -0,0 +1,32 @@
+require File.dirname(__FILE__) + '/../spec_helper.rb'
+
+context "ScriptTag" do
+  describe "detecting various script tags" do
+    ['<script type="whatever">', '<script></script>', '</script>', '<script>', "<script\n>"].each do |script_tag|
+      [script_tag.upcase, script_tag.downcase].each do |script_tag|
+        it "should detect '#{script_tag}' of a script tag" do
+          dspam = Despamilator.new(script_tag)
+          dspam.score.should == 1
+        end
+      end
+    end
+  end
+
+  describe 'attributes' do
+    before :all do
+      @dspam = Despamilator.new('<script>').matched_by.first
+    end
+
+    it "should have a name" do
+      @dspam.name.should == 'Detects script tags in text'
+    end
+
+    it "should have a description" do
+      @dspam.description.should == 'Searches for variations for the HTML script tag'
+    end
+
+    it "should have a filename" do
+      @dspam.filename.should == 'script_tag.rb'
+    end
+  end
+end

data/spec/spec.opts

@@ -0,0 +1 @@
+--colour

data/spec/spec_helper.rb

@@ -0,0 +1,10 @@
+begin
+  require 'spec'
+rescue LoadError
+  require 'rubygems' unless ENV['NO_RUBYGEMS']
+  gem 'rspec'
+  require 'spec'
+end
+
+$:.unshift(File.dirname(__FILE__) + '/../lib')
+require 'despamilator'

data/tasks/rspec.rake

@@ -0,0 +1,21 @@
+begin
+  require 'spec'
+rescue LoadError
+  require 'rubygems' unless ENV['NO_RUBYGEMS']
+  require 'spec'
+end
+begin
+  require 'spec/rake/spectask'
+rescue LoadError
+  puts <<-EOS
+To use rspec for testing you must install rspec gem:
+    gem install rspec
+EOS
+  exit(0)
+end
+
+desc "Run the specs under spec/models"
+Spec::Rake::SpecTask.new do |t|
+  t.spec_opts = ['--options', "spec/spec.opts"]
+  t.spec_files = FileList['spec/**/*_spec.rb']
+end

metadata

@@ -0,0 +1,155 @@
+--- !ruby/object:Gem::Specification 
+name: despamilator
+version: !ruby/object:Gem::Version 
+  prerelease: false
+  segments: 
+  - 0
+  - 2
+  version: "0.2"
+platform: ruby
+authors: 
+- Stephen Hardisty
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2010-03-28 00:00:00 +11:00
+default_executable: 
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: rubyforge
+  prerelease: false
+  requirement: &id001 !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        segments: 
+        - 2
+        - 0
+        - 3
+        version: 2.0.3
+  type: :development
+  version_requirements: *id001
+- !ruby/object:Gem::Dependency 
+  name: gemcutter
+  prerelease: false
+  requirement: &id002 !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        segments: 
+        - 0
+        - 5
+        - 0
+        version: 0.5.0
+  type: :development
+  version_requirements: *id002
+- !ruby/object:Gem::Dependency 
+  name: hoe
+  prerelease: false
+  requirement: &id003 !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        segments: 
+        - 2
+        - 5
+        - 0
+        version: 2.5.0
+  type: :development
+  version_requirements: *id003
+description: |-
+  Despamilator is a plugin based spam detector designed for use on your web forms borne out of two annoyances:
+  Spam being submitted in my web forms AND CAPTCHAS being intrusive. Despamilator will apply
+  some commonly used heuristics from the world of anti-spam to help you decide whether your users are human or machine.
+email: 
+- moowahaha@hotmail.com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: 
+- History.txt
+- Manifest.txt
+- PostInstall.txt
+- pkg/despamilator-0.1/History.txt
+- pkg/despamilator-0.1/Manifest.txt
+- pkg/despamilator-0.1/PostInstall.txt
+files: 
+- History.txt
+- Manifest.txt
+- PostInstall.txt
+- README.rdoc
+- Rakefile
+- despamilator.gemspec
+- lib/despamilator.rb
+- lib/despamilator/filter.rb
+- lib/despamilator/filter/html_tags.rb
+- lib/despamilator/filter/naughty_q.rb
+- lib/despamilator/filter/numbers_and_words.rb
+- lib/despamilator/filter/script_tag.rb
+- lib/despamilator/filter_base.rb
+- pkg/despamilator-0.1.gem
+- pkg/despamilator-0.1.tgz
+- pkg/despamilator-0.1/History.txt
+- pkg/despamilator-0.1/Manifest.txt
+- pkg/despamilator-0.1/PostInstall.txt
+- pkg/despamilator-0.1/README.rdoc
+- pkg/despamilator-0.1/Rakefile
+- pkg/despamilator-0.1/despamilator.gemspec
+- pkg/despamilator-0.1/lib/despamilator.rb
+- pkg/despamilator-0.1/lib/despamilator/filter.rb
+- pkg/despamilator-0.1/lib/despamilator/filter/html_tags.rb
+- pkg/despamilator-0.1/lib/despamilator/filter/naughty_q.rb
+- pkg/despamilator-0.1/lib/despamilator/filter/numbers_and_words.rb
+- pkg/despamilator-0.1/lib/despamilator/filter/script_tag.rb
+- pkg/despamilator-0.1/lib/despamilator/filter_base.rb
+- pkg/despamilator-0.1/spec/despamilator_spec.rb
+- pkg/despamilator-0.1/spec/filters/html_tags_spec.rb
+- pkg/despamilator-0.1/spec/filters/naughty_q_spec.rb
+- pkg/despamilator-0.1/spec/filters/numbers_and_words_spec.rb
+- pkg/despamilator-0.1/spec/filters/script_tag_spec.rb
+- pkg/despamilator-0.1/spec/spec.opts
+- pkg/despamilator-0.1/spec/spec_helper.rb
+- pkg/despamilator-0.1/tasks/rspec.rake
+- spec/despamilator_spec.rb
+- spec/filters/html_tags_spec.rb
+- spec/filters/naughty_q_spec.rb
+- spec/filters/numbers_and_words_spec.rb
+- spec/filters/script_tag_spec.rb
+- spec/spec.opts
+- spec/spec_helper.rb
+- tasks/rspec.rake
+has_rdoc: true
+homepage: http://github.com/moowahaha/despamliator
+licenses: []
+
+post_install_message: PostInstall.txt
+rdoc_options: 
+- --main
+- README.rdoc
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      segments: 
+      - 0
+      version: "0"
+requirements: []
+
+rubyforge_project: despamilator
+rubygems_version: 1.3.6
+signing_key: 
+specification_version: 3
+summary: "Despamilator is a plugin based spam detector designed for use on your web forms borne out of two annoyances: Spam being submitted in my web forms AND CAPTCHAS being intrusive"
+test_files: []
+