despamilator 2.0.1 → 2.1

data/despamilator.gemspec

@@ -1,38 +0,0 @@
-# -*- encoding: utf-8 -*-
-
-Gem::Specification.new do |s|
-  s.name = %q{despamilator}
-  s.version = "2.0.1"
-
-  s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
-  s.authors = ["Stephen Hardisty"]
-  s.date = %q{2011-08-11}
-  s.description = %q{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.}
-  s.email = ["moowahaha@hotmail.com"]
-  s.extra_rdoc_files = ["History.txt", "Manifest.txt", "PostInstall.txt", "conf/unusual_characters.txt"]
-  s.files = [".rspec", ".rvmrc", "Gemfile", "Gemfile.lock", "History.txt", "Manifest.txt", "PostInstall.txt", "README.rdoc", "Rakefile", "conf/unusual_characters.txt", "despamilator.gemspec", "lib/despamilator.rb", "lib/despamilator/filter.rb", "lib/despamilator/filter/gtubs_test_filter.rb", "lib/despamilator/filter/html_tags.rb", "lib/despamilator/filter/ip_address_url.rb", "lib/despamilator/filter/long_words.rb", "lib/despamilator/filter/naughty_words.rb", "lib/despamilator/filter/numbers_and_words.rb", "lib/despamilator/filter/script_tag.rb", "lib/despamilator/filter/shouting.rb", "lib/despamilator/filter/square_brackets.rb", "lib/despamilator/filter/trailing_number.rb", "lib/despamilator/filter/unusual_characters.rb", "lib/despamilator/filter/urls.rb", "lib/despamilator/filter_base.rb", "scripts/despamilator_score.rb", "scripts/from_file.rb", "spec/despamilator_spec.rb", "spec/filter_base_spec.rb", "spec/filters/gtubs_test_filter_spec.rb", "spec/filters/html_tags_spec.rb", "spec/filters/ip_address_url_spec.rb", "spec/filters/long_words_spec.rb", "spec/filters/naughty_words_spec.rb", "spec/filters/numbers_and_words_spec.rb", "spec/filters/script_tag_spec.rb", "spec/filters/shouting_spec.rb", "spec/filters/square_brackets_spec.rb", "spec/filters/trailing_number_spec.rb", "spec/filters/unusual_characters_spec.rb", "spec/filters/urls_spec.rb", "spec/helpers/corpus_helper.rb", "spec/helpers/filter_helper.rb", "spec/helpers/spec_helper.rb", "tasks/test.rake"]
-  s.homepage = %q{http://github.com/moowahaha/despamilator}
-  s.post_install_message = %q{PostInstall.txt}
-  s.rdoc_options = ["--main", "README.rdoc"]
-  s.require_paths = ["lib"]
-  s.rubyforge_project = %q{despamilator}
-  s.rubygems_version = %q{1.5.2}
-  s.summary = %q{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}
-
-  if s.respond_to? :specification_version then
-    s.specification_version = 3
-
-    if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
-      s.add_development_dependency(%q<rubyforge>, [">= 2.0.4"])
-      s.add_development_dependency(%q<hoe>, [">= 2.7.0"])
-    else
-      s.add_dependency(%q<rubyforge>, [">= 2.0.4"])
-      s.add_dependency(%q<hoe>, [">= 2.7.0"])
-    end
-  else
-    s.add_dependency(%q<rubyforge>, [">= 2.0.4"])
-    s.add_dependency(%q<hoe>, [">= 2.7.0"])
-  end
-end

data/lib/despamilator/filter_base.rb

@@ -1,82 +0,0 @@
-class Despamilator
-
-#This class is the base class of all the despamilator filters.
-#
-#== EXAMPLE:
-#
-#This example is to detect the letter "a". Put the code in
-#lib/despamilator/filter/detect_letter_a.rb:
-#
-#  require 'despamilator/filter_base'
-#
-#  module DespamilatorFilter
-#
-#    class DetectLetterA < Despamilator::FilterBase
-#
-#      def name
-#        'Detecting the letter A'
-#      end
-#
-#      def description
-#        'Detects the letter "a" in a string for no reason other than a demo'
-#      end
-#
-#      def parse text
-#        if text.downcase.scan(/a/)
-#        # add 0.1 to the score of the text
-#        self.append_score = 0.1
-#      end
-#    end
-#  end
-
-  class FilterBase
-    attr_accessor :text, :score, :matches
-
-    # Constructor for the class.
-
-    def initialize
-      @matches = 0
-      @score = 0
-      @matched = false
-    end
-
-    # Returns the score the filter instance has calculated.
-
-    def score
-      # workaround for a bug in ruby 1.9.2's floats
-      sprintf("%.3f", @score).to_f
-    end
-
-    # The nice description of the filter. Usually no more than a sentence.
-
-    def description
-      raise "No description defined for #{self.class}"
-    end
-
-    # This method parses some text. The score is assigned to the same instance.
-
-    def parse text
-      raise "No parse defined for #{self.class}"
-    end
-
-    # The one or two word name for the filter.
-
-    def name
-      raise "No name defined for #{self.class}"
-    end
-
-    # Boolean. Whether or not the filter matched anything.
-
-    def matched?
-      @score > 0
-    end
-
-    protected
-
-    def append_score= new_score
-      @matches += 1
-      @score += new_score
-    end
-
-  end
-end

data/scripts/despamilator_score.rb

@@ -1,25 +0,0 @@
-#!/usr/bin/env ruby
-
-require File.join(File.dirname(__FILE__), '..', 'lib', 'despamilator')
-require 'zlib'
-
-file = ARGV[0] || raise("Usage: despamilator_spec.rb [filename]")
-
-text = file =~ /\.gz$/i ? Zlib::GzipReader.open(file).read : File.open(file).read
-
-puts "Testing:"
-puts "========================"
-puts text
-puts "========================"
-puts "\n"
-
-dspam = Despamilator.new(text)
-
-puts "Total Score: #{dspam.score}\n\n"
-
-puts "Matched by..." unless dspam.matched_by.empty?
-dspam.matched_by.each do |match|
-  puts "\tFilter: #{match.name}"
-  puts "\tScore:  #{match.score}"
-  puts "\n"
-end

data/scripts/from_file.rb

@@ -1,26 +0,0 @@
-#!/usr/bin/env ruby
-
-require 'cgi'
-
-slots = {};
-
-1.upto(10000) do |i|
-    slots[i] = true
-end
-
-dir = './spec/spam_corpus/'
-
-Dir[dir + '*.gz'].each do |file|
-    slots.delete(file.scan(/\d+/).first.to_i)
-end
-
-slots = slots.keys.sort
-
-File.open(ARGV[0] || raise).each do |line|
-    txt = dir + "#{slots.shift}.txt"
-    File.open(txt, 'w') do |fh|
-        fh.puts CGI.unescapeHTML(line)
-    end
-
-    `gzip #{txt}`
-end

data/spec/despamilator_spec.rb

@@ -1,13 +0,0 @@
-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/filter_base_spec.rb

@@ -1,30 +0,0 @@
-require 'despamilator/filter_base'
-
-class UnimplementedFilter < Despamilator::FilterBase
-end
-
-describe Despamilator::FilterBase do
-  describe "abstract method" do
-
-    before do
-      @filter = UnimplementedFilter.new
-    end
-
-    [
-            ['name', 'No name defined for UnimplementedFilter'],
-            ['description', 'No description defined for UnimplementedFilter'],
-
-    ].each do |method, exception|
-
-      it "should throw an error when the child class has not implemented a '#{method}' method" do
-        -> {@filter.send(method)}.should raise_error(exception)
-      end
-
-    end
-
-    it "should throw an error when the child class has not implemented a 'parse' method" do
-      -> {@filter.parse('abc')}.should raise_error('No parse defined for UnimplementedFilter')
-    end
-
-  end
-end

data/spec/filters/gtubs_test_filter_spec.rb

@@ -1,9 +0,0 @@
-describe DespamilatorFilter::GtubsTestFilter do
-  the_name_should_be 'GTubs Test Filter'
-  the_description_should_be 'Detects the special test string (Despamilator.gtubs_test_string) and assigns a big score.'
-
-  despamilator_should_apply_the_filter_for(Despamilator.gtubs_test_string)
-
-  a_single_match_of(Despamilator.gtubs_test_string, should_score: 100)
-  a_multiple_match_of(Despamilator.gtubs_test_string, should_score: [100, 1.times])
-end

data/spec/filters/html_tags_spec.rb

@@ -1,129 +0,0 @@
-describe DespamilatorFilter::HtmlTags do
-
-  the_name_should_be 'HTML tags'
-  the_description_should_be 'Detects HTML tags in text'
-
-  despamilator_should_apply_the_filter_for('<xmp>')
-
-  a_single_match_of('<xmp>', should_score: 0.6)
-  a_multiple_match_of('<h1></h1> <h2></h2>', should_score: [1.2, 2.times])
-
-  [
-          '!--',
-          '!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} />",
-              "<\n#{script_tag}\n/>",
-              "<\n#{script_tag} >",
-              "<#{script_tag}\n/>",
-              "<\r#{script_tag}\r/>"
-      ].each do |tag|
-        it "should detect '#{tag}'" do
-          dspam = DespamilatorFilter::HtmlTags.new
-          dspam.parse(tag)
-          dspam.score.should == 0.6
-        end
-
-      end
-
-    end
-
-  end
-
-end

data/spec/filters/ip_address_url_spec.rb

@@ -1,11 +0,0 @@
-describe DespamilatorFilter::IPAddressURL do
-
-  the_name_should_be 'IP Address URL'
-  the_description_should_be 'Detects IP address URLs'
-
-  despamilator_should_apply_the_filter_for('http://12.34.56.78/')
-
-  a_single_match_of('http://12.34.56.78/', should_score: 0.5)
-  a_multiple_match_of('http://12.34.56.78/ http://98.76.54.32/', should_score: [0.5, 1.times])
-
-end

data/spec/filters/long_words_spec.rb

@@ -1,11 +0,0 @@
-describe DespamilatorFilter::LongWords do
-
-  the_name_should_be 'Long Words'
-  the_description_should_be 'Detects long and unbroken strings'
-
-  despamilator_should_apply_the_filter_for('honorificabilitudinitatibus')
-
-  a_single_match_of('honorificabilitudinitatibus', should_score: 0.1)
-  a_multiple_match_of('honorificabilitudinitatibus antidisestablishmentarianism', should_score: [0.2, 2.times])
-
-end

data/spec/filters/naughty_words_spec.rb

@@ -1,11 +0,0 @@
-describe DespamilatorFilter::NaughtyWords do
-
-  the_name_should_be 'Naughty Words'
-  the_description_should_be 'Detects cheeky words'
-
-  despamilator_should_apply_the_filter_for('bondage')
-
-  a_single_match_of('bondage', should_score: 0.1)
-  a_multiple_match_of('viagra penis', should_score: [0.2, 2.times])
-
-end

data/spec/filters/numbers_and_words_spec.rb

@@ -1,34 +0,0 @@
-describe DespamilatorFilter::NumbersAndWords do
-
-  the_name_should_be 'Numbers next to words'
-  the_description_should_be 'Detects unusual number/word combinations'
-
-  despamilator_should_apply_the_filter_for('X5T')
-
-  a_single_match_of('X5T', should_score: 0.1)
-  a_multiple_match_of('4g6hk', should_score: [0.2, 2.times])
-
-  describe 'exceptions' do
-    before :all do
-      @filter = DespamilatorFilter::NumbersAndWords.new
-    end
-
-    [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
-        @filter.parse(number.to_s)
-        @filter.score.should == 0
-      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
-        @filter.parse(header_tag)
-        @filter.score.should == 0
-      end
-    end
-
-  end
-
-end

data/spec/filters/script_tag_spec.rb

@@ -1,22 +0,0 @@
-describe DespamilatorFilter::ScriptTag do
-
-  the_name_should_be 'Script tag'
-  the_description_should_be 'Searches for variations for the HTML script tag'
-
-  despamilator_should_apply_the_filter_for('<script>')
-
-  a_single_match_of('<script>', should_score: 1)
-  a_multiple_match_of('<script></script> <script></script>', should_score: [1, 1.times])
-
-  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
-
-end