swearjar 1.0.0 → 1.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: cfbc2f8e57099d5a6b9a4c60961977e8bfb542d3
+  data.tar.gz: d176f8879508172566f2582bf29a5d0d6c47d27d
+SHA512:
+  metadata.gz: 2980ee653f0b552d3e822b991041fd91d5e1ae494d9e2823109e67c927b0dbe53ae0e2192397bd5fed38684d78af07c4713f2271a2ebc93cd0538dfe07aa40be
+  data.tar.gz: 4116470e1e7cdb71c5958888833306e20196cbc6f11ddc7e4219a8ebecb7fe8b0375feb50ede7fcdd03635e588002a401de414ca73d64a8cc661a36100639fd2

data/.travis.yml

@@ -0,0 +1,6 @@
+rvm:
+  - ruby-1.9.3
+  - ruby-2.0.0
+  - ruby-2.1
+  - jruby
+sudo: false

data/CHANGELOG.md

@@ -0,0 +1,8 @@
+# Changelog
+
+### v1.1.0 (2016-02-13)
+- Add emoji support
+- Censor middle finger emoji by default
+
+### v1.0.0 (2012-04-02)
+- Detect plurals

data/Gemfile

@@ -1,3 +1,3 @@
-source :rubygems
+source "https://rubygems.org"
 
-gemspec
+gemspec

data/README.md

@@ -0,0 +1,31 @@
+# Swearjar
+
+Simple profanity detection with content analysis.
+
+## Installation
+
+`gem install swearjar`
+
+## Usage
+
+```ruby
+require "swearjar"
+
+sj = Swearjar.default
+
+sj.profane?("jim henson has a massive hard on he is gonna use to fuck everybody")
+# => true
+
+sj.scorecard("jim henson has a massive hard on he is gonna use to fuck everybody")
+# => {:sexual => 2}
+
+sj.censor("jim henson has a massive hard on he is gonna use to fuck everybody")
+# => "jim henson has a massive **** ** he is gonna use to **** everybody"
+```
+
+To load from a custom config file, you can do the following:
+
+```ruby
+# For an example see lib/config/en.yml
+sj = Swearjar.new("my_swears.yml")
+```

data/Rakefile

@@ -1,18 +1,5 @@
 # encoding: utf-8
 
+require "rspec/core/rake_task"
+RSpec::Core::RakeTask.new(:spec)
 task :default => :spec
-
-require 'spec'
-require 'spec/rake/spectask'
-task :spec => 'spec:all'
-namespace(:spec) do
-  Spec::Rake::SpecTask.new(:all) do |t|
-    t.spec_opts ||= []
-    t.spec_opts << "-rubygems"
-    t.spec_opts << "--options" << "spec/spec.opts"
-    t.spec_files = FileList['spec/**/*_spec.rb']
-  end
-end
-
-require 'bundler'
-Bundler::GemHelper.install_tasks

data/lib/config/en.yml

@@ -1,8 +1,16 @@
+---
 regex:
   'hard ons?\b': ["sexual"]
   'jerk off\b': ["sexual"]
   'pissed off\b': ["inappropriate"]
-  'sand nigger': ["discriminatory"]
+  '\w*n[i1]gg[e3]r\w*': ["discriminatory"]
+  '\w*fuck\w*': ["sexual"]
+  '\w*b[i1]tch\w*': ["insult"]
+  '\w*ejaculat\w*': ["sexual"]
+  '\w*damn\w*': ["inappropriate", "blasphemy"]
+  '\w*f[a4]gg[o0]t\w*': ["discriminatory"]
+  '\w*wh[o0]r[e3]\w*': ["insult"]
+  '\w*p[e3]n[i1]s\w*': ["sexual"]
 simple:
   "anus": ["sexual"]
   "arse": ["insult"]
@@ -18,8 +26,6 @@ simple:
   "asscock": ["insult"]
   "asscracker": ["sexual"]
   "assface": ["sexual"]
-  "assfuck": ["sexual"]
-  "assfucker": ["discriminatory"]
   "assgoblin": ["discriminatory"]
   "asshat": ["sexual"]
   "asshead": ["insult"]
@@ -31,9 +37,7 @@ simple:
   "assmonkey": ["insult"]
   "assmunch": ["insult"]
   "assmuncher": ["sexual"]
-  "assnigger": ["discriminatory"]
   "asspirate": ["discriminatory"]
-  "assshit": ["insult"]
   "assshole": ["sexual"]
   "asssucker": ["insult"]
   "asswad": ["sexual"]
@@ -41,31 +45,17 @@ simple:
   "bampot": ["insult"]
   "bastard": ["insult"]
   "beaner": ["discriminatory"]
-  "beastial": ["sexual"]
   "beastiality": ["sexual"]
   "beastility": ["sexual"]
-  "bestial": ["sexual"]
   "bestiality": ["sexual"]
-  "bitch": ["insult"]
-  "bitchass": ["insult"]
-  "bitcher": ["insult"]
-  "bitchin": ["inappropriate"]
-  "bitching": ["inappropriate"]
-  "bitchtit": ["discriminatory"]
-  "bitchy": ["insult"]
   "blow job": ["sexual"]
   "blowjob": ["sexual"]
   "bollocks": ["sexual"]
   "bollox": ["sexual"]
   "boner": ["sexual"]
-  "brotherfucker": ["discriminatory"]
   "bullshit": ["inappropriate"]
-  "bullshit": ["inappropriate"]
-  "bumblefuck": ["discriminatory"]
   "butt plug": ["sexual"]
   "butt-pirate": ["discriminatory"]
-  "buttfucka": ["discriminatory"]
-  "buttfucker": ["discriminatory"]
   "camel toe": ["sexual"]
   "carpetmuncher": ["discriminatory"]
   "chinc": ["discriminatory"]
@@ -74,14 +64,11 @@ simple:
   "chode": ["sexual"]
   "clit": ["sexual"]
   "clitface": ["insult"]
-  "clitfuck": ["sexual"]
-  "clusterfuck": ["inappropriate"]
   "cock": ["sexual"]
   "cockass": "Jerk"
   "cockbite": ["insult"]
   "cockburger": ["insult"]
   "cockface": ["insult"]
-  "cockfucker": ["insult"]
   "cockhead": ["insult"]
   "cockjockey": ["discriminatory"]
   "cockknoker": ["discriminatory"]
@@ -95,16 +82,14 @@ simple:
   "cockshit": ["insult"]
   "cocksmith": ["discriminatory"]
   "cocksmoker": ["discriminatory"]
-  "cocksuck": ["sexual"]
+  "cocksuck": ["sexual", "discriminatory"]
   "cocksucked": ["sexual"]
   "cocksucker": ["discriminatory", "sexual"]
   "cocksucking": ["sexual", "discriminatory"]
-  "cocksucks": ["sexual", "discriminatory"]
   "coochie": ["sexual"]
   "coochy": ["sexual"]
   "coon": ["discriminatory"]
   "cooter": ["sexual"]
-  "cracker": ["discriminatory"]
   "cum": ["sexual"]
   "cumbubble": ["insult"]
   "cumdumpster": ["sexual"]
@@ -118,7 +103,6 @@ simple:
   "cunillingus": ["sexual"]
   "cunnie": ["sexual"]
   "cunnilingus": ["sexual"]
-  "cunnilingus": ["sexual"]
   "cunt": ["insult", "sexual"]
   "cuntface": ["insult"]
   "cunthole": ["sexual"]
@@ -128,19 +112,11 @@ simple:
   "cuntrag": ["insult"]
   "cuntslut": ["insult"]
   "cyberfuc": ["sexual"]
-  "cyberfuck": ["sexual"]
-  "cyberfucked": ["sexual"]
-  "cyberfucker": ["sexual"]
-  "cyberfucking": ["sexual"]
-  "dago": ["discriminatory"]
-  "damn": ["inappropriate"]
-  "deggo": ["discriminatory"]
+  "dammit": ["inappropriate", "blasphemy"]
   "dick": ["sexual", "insult"]
   "dickbag": ["insult"]
-  "dickbeaters": ["sexual"]
+  "dickbeater": ["sexual"]
   "dickface": ["insult"]
-  "dickfuck": ["insult"]
-  "dickfucker": ["discriminatory"]
   "dickhead": ["insult"]
   "dickhole": ["sexual"]
   "dickjuice": ["sexual"]
@@ -165,26 +141,15 @@ simple:
   "dumass": ["insult"]
   "dumb ass": ["insult"]
   "dumbass": ["insult"]
-  "dumbfuck": ["insult"]
   "dumbshit": ["insult"]
   "dumshit": ["insult"]
   "dyke": ["discriminatory"]
-  "ejaculate": ["sexual"]
-  "ejaculated": ["sexual"]
-  "ejaculates": ["sexual"]
-  "ejaculating": ["sexual"]
-  "ejaculation": ["sexual"]
   "fag": ["discriminatory"]
   "fagbag": ["discriminatory"]
-  "fagfucker": ["discriminatory"]
   "fagging": ["discriminatory"]
   "faggit": ["discriminatory"]
-  "faggot": ["discriminatory"]
-  "faggot": ["discriminatory"]
-  "faggotcock": ["discriminatory"]
-  "faggs": ["discriminatory"]
+  "fagg": ["discriminatory"]
   "fagot": ["discriminatory"]
-  "fags": ["discriminatory"]
   "fagtard": ["discriminatory"]
   "fart": ["inappropriate"]
   "farted": ["inappropriate"]
@@ -193,42 +158,8 @@ simple:
   "fatass": ["insult"]
   "felatio": ["sexual"]
   "fellatio": ["sexual"]
-  "fellatio": ["sexual"]
   "feltch": ["sexual"]
-  "fingerfuck": ["sexual"]
-  "fingerfucked": ["sexual"]
-  "fingerfucker": ["sexual"]
-  "fingerfucking": ["sexual"]
-  "fingerfucks": ["sexual"]
-  "fistfuck": ["sexual"]
-  "fistfucked": ["sexual"]
-  "fistfucker": ["sexual"]
-  "fistfucking": ["sexual"]
   "flamer": ["discriminatory"]
-  "fuck": ["sexual"]
-  "fuckass": ["insult"]
-  "fuckbag": ["insult"]
-  "fuckboy": ["insult"]
-  "fuckbrain": ["insult"]
-  "fuckbutt": ["sexual"]
-  "fucked": ["sexual"]
-  "fucker": ["sexual", "insult"]
-  "fuckersucker": ["insult"]
-  "fuckface": ["insult"]
-  "fuckhead": ["sexual"]
-  "fuckhole": ["insult"]
-  "fuckin": ["sexual"]
-  "fucking": ["sexual"]
-  "fuckme": ["sexual"]
-  "fucknut": ["insult"]
-  "fucknutt": ["insult"]
-  "fuckoff": ["insult"]
-  "fuckstick": ["sexual"]
-  "fucktard": ["insult"]
-  "fuckup": ["insult"]
-  "fuckwad": ["insult"]
-  "fuckwit": ["insult"]
-  "fuckwitt": ["insult"]
   "fudgepacker": ["discriminatory"]
   "fuk": ["sexual"]
   "gangbang": ["sexual"]
@@ -237,15 +168,10 @@ simple:
   "gayass": ["sexual"]
   "gaybob": ["discriminatory"]
   "gaydo": ["discriminatory"]
-  "gayfuck": ["discriminatory"]
-  "gayfuckist": ["discriminatory"]
   "gaylord": ["discriminatory"]
   "gaysex": ["discriminatory"]
   "gaytard": ["discriminatory"]
   "gaywad": ["discriminatory"]
-  "goddamn": ["inappropriate", "blasphemy"]
-  "goddamn": ["inappropriate", "blasphemy"]
-  "goddamnit": ["inappropriate", "blasphemy"]
   "gooch": ["sexual"]
   "gook": ["discriminatory"]
   "gringo": ["discriminatory"]
@@ -254,12 +180,11 @@ simple:
   "hardcoresex": ["sexual"]
   "heeb": ["discriminatory"]
   "hell": ["inappropriate"]
-  "hell": ["inappropriate"]
   "ho": ["discriminatory"]
   "hoe": ["discriminatory"]
   "homo": ["discriminatory"]
-  "homodumbshit": ["insult"]
   "honkey": ["discriminatory"]
+  "honky": ["discriminatory"]
   "horniest": ["sexual"]
   "horny": ["sexual"]
   "hotsex": ["sexual"]
@@ -282,7 +207,6 @@ simple:
   "kumer": ["sexual"]
   "kummer": ["sexual"]
   "kumming": ["sexual"]
-  "kums": ["sexual"]
   "kunilingus": ["sexual"]
   "kunt": ["sexual"]
   "kyke": ["discriminatory"]
@@ -292,27 +216,11 @@ simple:
   "lust": ["sexual"]
   "lusting": ["sexual"]
   "mcfagget": ["discriminatory"]
-  "mick": ["discriminatory"]
   "minge": ["sexual"]
-  "mothafuck": ["sexual"]
-  "mothafucka": ["sexual", "insult"]
-  "mothafuckaz": ["sexual"]
-  "mothafucked": ["sexual"]
-  "mothafucker": ["sexual", "insult"]
-  "mothafuckin": ["sexual"]
-  "mothafucking": ["sexual"]
-  "mothafucks": ["sexual"]
-  "motherfuck": ["sexual"]
-  "motherfucked": ["sexual"]
-  "motherfucker": ["sexual", "insult"]
-  "motherfuckin": ["sexual"]
-  "motherfucking": ["sexual"]
   "muff": ["sexual"]
   "muffdiver": ["discriminatory", "sexual"]
-  "munging": ["sexual"]
   "negro": ["discriminatory"]
   "nigga": ["discriminatory"]
-  "nigger": ["discriminatory"]
   "niglet": ["discriminatory"]
   "nut sack": ["sexual"]
   "nutsack": ["sexual"]
@@ -322,16 +230,12 @@ simple:
   "panooch": ["sexual"]
   "pecker": ["sexual"]
   "peckerhead": ["insult"]
-  "penis": ["sexual"]
-  "penisfucker": ["discriminatory"]
-  "penispuffer": ["discriminatory"]
   "phonesex": ["sexual"]
   "phuk": ["sexual"]
   "phuked": ["sexual"]
   "phuking": ["sexual"]
   "phukked": ["sexual"]
   "phukking": ["sexual"]
-  "phuks": ["sexual"]
   "phuq": ["sexual"]
   "pis": ["sexual"]
   "pises": ["sexual"]
@@ -341,8 +245,7 @@ simple:
   "piss": ["inappropriate"]
   "pissed": ["inappropriate"]
   "pisser": ["sexual"]
-  "pisses": ["sexual"]
-  "pissflaps": ["sexual"]
+  "pissflap": ["sexual"]
   "pissin": ["sexual"]
   "pissing": ["sexual"]
   "pissoff": ["sexual"]
@@ -357,7 +260,6 @@ simple:
   "porn": ["sexual"]
   "porno": ["sexual"]
   "pornography": ["sexual"]
-  "pornos": ["sexual"]
   "prick": ["sexual"]
   "punanny": ["sexual"]
   "punta": ["insult"]
@@ -374,7 +276,6 @@ simple:
   "renob": ["sexual"]
   "rimjob": ["sexual"]
   "ruski": ["discriminatory"]
-  "sandnigger": ["discriminatory"]
   "schlong": ["sexual"]
   "scrote": ["sexual"]
   "shit": ["sexual", "inappropriate"]
@@ -405,11 +306,8 @@ simple:
   "shiznit": ["inappropriate"]
   "skank": ["insult"]
   "skeet": ["sexual"]
-  "skullfuck": ["sexual"]
-  "slut": ["sexual"]
   "slut": ["discriminatory"]
   "slutbag": ["discriminatory"]
-  "sluts": ["sexual"]
   "smeg": ["inappropriate"]
   "smut": ["sexual"]
   "snatch": ["sexual"]
@@ -421,19 +319,14 @@ simple:
   "testicle": ["sexual"]
   "thundercunt": ["insult"]
   "tit": ["sexual"]
-  "titfuck": ["sexual"]
-  "tittyfuck": ["sexual"]
   "twat": ["sexual"]
   "twatlips": ["insult"]
   "twatwaffle": ["discriminatory"]
-  "unclefucker": ["discriminatory"]
   "va-j-j": ["sexual"]
   "vag": ["sexual"]
   "vagina": ["sexual"]
   "vjayjay": ["sexual"]
   "wank": ["sexual"]
   "wetback": ["discriminatory"]
-  "whore": ["insult"]
-  "whorebag": ["insult"]
-  "whoreface": ["insult"]
-  "wop": ["discriminatory"]
+emoji:
+  "1f595": ["insult"]

data/lib/swearjar.rb

@@ -1,63 +1,89 @@
 require 'yaml'
-require 'fuzzy_hash'
 
 class Swearjar
-
   def self.default
-    from_language
+    from_language('en')
   end
 
-  def self.from_language(language = 'en')
+  def self.from_language(language)
     new(File.join(File.dirname(__FILE__), 'config', "#{language}.yml"))
   end
 
-  attr_reader :tester, :hash
-
   def initialize(file = nil)
-    @tester = FuzzyHash.new
     @hash = {}
+    @regexs = {}
     load_file(file) if file
   end
 
+  def profane?(string)
+    string = string.to_s
+    scan(string) {|_word, test| return true if test }
+    false
+  end
+
+  def scorecard(string)
+    string = string.to_s
+    scorecard = {}
+    scan(string) do |_word, test|
+      next unless test
+      test.each do |type|
+        scorecard[type] = 0 unless scorecard.key?(type)
+        scorecard[type] += 1
+      end
+    end
+    scorecard
+  end
+
+  def censor(string)
+    censored_string = string.to_s.dup
+    scan(string) do |word, test|
+      next unless test
+      replacement = block_given? ? yield(word) : word.gsub(/\S/, '*')
+      censored_string.gsub!(word, replacement)
+    end
+    censored_string
+  end
+
+  private
+
   def load_file(file)
     data = YAML.load_file(file)
 
     data['regex'].each do |pattern, type|
-      @tester[Regexp.new(pattern)] = type
+      @regexs[Regexp.new(pattern, "i")] = type
     end if data['regex']
 
     data['simple'].each do |test, type|
       @hash[test] = type
     end if data['simple']
+
+    data['emoji'].each do |unicode, type|
+      char = [unicode.hex].pack("U")
+      @hash[char] = type
+    end if data['emoji']
   end
 
+  WORD_REGEX = /\b[a-zA-Z-]+\b/
+
+  # https://github.com/franklsf95/ruby-emoji-regex
+  EMOJI_REGEX = /[\u{00A9}\u{00AE}\u{203C}\u{2049}\u{2122}\u{2139}\u{2194}-\u{2199}\u{21A9}-\u{21AA}\u{231A}-\u{231B}\u{2328}\u{23CF}\u{23E9}-\u{23F3}\u{23F8}-\u{23FA}\u{24C2}\u{25AA}-\u{25AB}\u{25B6}\u{25C0}\u{25FB}-\u{25FE}\u{2600}-\u{2604}\u{260E}\u{2611}\u{2614}-\u{2615}\u{2618}\u{261D}\u{2620}\u{2622}-\u{2623}\u{2626}\u{262A}\u{262E}-\u{262F}\u{2638}-\u{263A}\u{2648}-\u{2653}\u{2660}\u{2663}\u{2665}-\u{2666}\u{2668}\u{267B}\u{267F}\u{2692}-\u{2694}\u{2696}-\u{2697}\u{2699}\u{269B}-\u{269C}\u{26A0}-\u{26A1}\u{26AA}-\u{26AB}\u{26B0}-\u{26B1}\u{26BD}-\u{26BE}\u{26C4}-\u{26C5}\u{26C8}\u{26CE}-\u{26CF}\u{26D1}\u{26D3}-\u{26D4}\u{26E9}-\u{26EA}\u{26F0}-\u{26F5}\u{26F7}-\u{26FA}\u{26FD}\u{2702}\u{2705}\u{2708}-\u{270D}\u{270F}\u{2712}\u{2714}\u{2716}\u{271D}\u{2721}\u{2728}\u{2733}-\u{2734}\u{2744}\u{2747}\u{274C}\u{274E}\u{2753}-\u{2755}\u{2757}\u{2763}-\u{2764}\u{2795}-\u{2797}\u{27A1}\u{27B0}\u{27BF}\u{2934}-\u{2935}\u{2B05}-\u{2B07}\u{2B1B}-\u{2B1C}\u{2B50}\u{2B55}\u{3030}\u{303D}\u{3297}\u{3299}\u{1F004}\u{1F0CF}\u{1F170}-\u{1F171}\u{1F17E}-\u{1F17F}\u{1F18E}\u{1F191}-\u{1F19A}\u{1F201}-\u{1F202}\u{1F21A}\u{1F22F}\u{1F232}-\u{1F23A}\u{1F250}-\u{1F251}\u{1F300}-\u{1F321}\u{1F324}-\u{1F393}\u{1F396}-\u{1F397}\u{1F399}-\u{1F39B}\u{1F39E}-\u{1F3F0}\u{1F3F3}-\u{1F3F5}\u{1F3F7}-\u{1F4FD}\u{1F4FF}-\u{1F53D}\u{1F549}-\u{1F54E}\u{1F550}-\u{1F567}\u{1F56F}-\u{1F570}\u{1F573}-\u{1F579}\u{1F587}\u{1F58A}-\u{1F58D}\u{1F590}\u{1F595}-\u{1F596}\u{1F5A5}\u{1F5A8}\u{1F5B1}-\u{1F5B2}\u{1F5BC}\u{1F5C2}-\u{1F5C4}\u{1F5D1}-\u{1F5D3}\u{1F5DC}-\u{1F5DE}\u{1F5E1}\u{1F5E3}\u{1F5EF}\u{1F5F3}\u{1F5FA}-\u{1F64F}\u{1F680}-\u{1F6C5}\u{1F6CB}-\u{1F6D0}\u{1F6E0}-\u{1F6E5}\u{1F6E9}\u{1F6EB}-\u{1F6EC}\u{1F6F0}\u{1F6F3}\u{1F910}-\u{1F918}\u{1F980}-\u{1F984}\u{1F9C0}]/
+
   def scan(string, &block)
-    string = string.to_s
-    string.scan(/\b[a-zA-Z-]+\b/) do |word|
-      block.call(word, hash[word.downcase] || hash[word.downcase.gsub(/e?s$/,'')] )
+    string.scan(WORD_REGEX) do |word|
+      block.call(word,
+        @hash[word.downcase] ||
+        @hash[word.downcase.gsub(/s\z/,'')] ||
+        @hash[word.downcase.gsub(/es\z/,'')])
     end
-    if match = tester.match_with_result(string)
-      block.call(match.last, match.first)
-    end
-  end
 
-  def profane?(string)
-    string = string.to_s
-    scan(string) {|word, test| return true if !test.nil?}
-    return false
-  end
-
-  def scorecard(string)
-    string = string.to_s
-    scorecard = {}
-    scan(string) {|word, test| test.each { |type| scorecard.key?(type) ? scorecard[type] += 1 : scorecard[type] = 1} if test}
-    scorecard
-  end
+    string.scan(EMOJI_REGEX) do |emoji_char|
+      block.call(emoji_char, @hash[emoji_char])
+    end
 
-  def censor(string)
-    censored_string = string.to_s.dup
-    scan(string) {|word, test| censored_string.gsub!(word, block_given? ? yield(word) : word.gsub(/\S/, '*')) if test}
-    censored_string
+    @regexs.each do |regex, type|
+      string.scan(regex) do |word|
+        block.call(word, type)
+      end
+    end
   end
-
-end
+end

data/lib/swearjar/version.rb

@@ -1,3 +1,3 @@
 class Swearjar
-  VERSION = '1.0.0'
-end
+  VERSION = '1.1.0'
+end

data/spec/data/swear.yml

@@ -1,2 +1,3 @@
+---
 simple:
   "python": ["sexual"]

data/spec/swearjar_spec.rb

@@ -1,48 +1,87 @@
+# encoding: UTF-8
 require 'spec_helper'
 
 describe Swearjar do
-
   it "should detect dirty words" do
-    Swearjar.default.profane?('fuck you jim henson').should be_true
+    expect(Swearjar.default.profane?('jackass chan')).to be_truthy
   end
 
   it "should detect dirty words regardless of case" do
-    Swearjar.default.profane?('FuCk you jim henson').should be_true
+    expect(Swearjar.default.profane?('JACKASS CHAN')).to be_truthy
   end
 
   it "should not detect non-dirty words" do
-    Swearjar.default.profane?('i love you jim henson').should be_false
+    expect(Swearjar.default.profane?('I love Jackie Chan movies')).to be_falsey
   end
 
   it "should give us a scorecard" do
-    Swearjar.default.scorecard('fuck you jim henson').should == {'sexual'=>1}
+    expect(Swearjar.default.scorecard('honky jim henson')).to eq({'discriminatory'=>1})
   end
 
   it "should detect multiword" do
-    Swearjar.default.scorecard('jim henson has a hard on').should == {'sexual'=>1}
+    expect(Swearjar.default.scorecard('jim henson has a hard on')).to eq({'sexual'=>1})
   end
 
   it "should detect multiword plurals" do
-    Swearjar.default.scorecard('jim henson has a hard ons').should == {'sexual'=>1}
+    expect(Swearjar.default.scorecard('jim henson has a hard ons')).to eq({'sexual'=>1})
   end
 
   it "should detect simple dirty plurals" do
-    Swearjar.default.profane?('jim henson had two dicks').should be_true
-    Swearjar.default.profane?('jim henson has two asses').should be_true
+    expect(Swearjar.default.profane?('jim henson had two dicks')).to be_truthy
+    expect(Swearjar.default.profane?('jim henson has two asses')).to be_truthy
   end
 
   it "should censor a string" do
-    Swearjar.default.censor('jim henson has a massive hard on he is gonna use to fuck everybody').should == 'jim henson has a massive **** ** he is gonna use to **** everybody'
+    expect(Swearjar.default.censor('jim henson has a massive hard on he is gonna use to fuck everybody')).to eq('jim henson has a massive **** ** he is gonna use to **** everybody')
   end
 
   it "should not do much when given a non-string" do
-    Swearjar.default.profane?(nil).should be_false
+    expect(Swearjar.default.profane?(nil)).to be_falsey
+  end
+
+  it "doesn't mark an empty string as profane" do
+    expect(Swearjar.default.profane?("")).to be_falsey
   end
 
   it "should allow you to load a new yaml file" do
-    sj = Swearjar.new
-    sj.load_file(File.expand_path('../data/swear.yml', __FILE__))
-    sj.censor("Python is the best language!").should == "****** is the best language!"
+    sj = Swearjar.new(File.expand_path('../data/swear.yml', __FILE__))
+    expect(sj.censor("Python is the best language!")).to eq("****** is the best language!")
+  end
+
+  it "detects multiple entries" do
+    expect(Swearjar.default.scorecard("cunts cunts cunts")).to eq({"insult" => 3, "sexual" => 3})
+    expect(Swearjar.default.scorecard("damn damnit dammit")).to eq({"inappropriate" => 3, "blasphemy" => 3})
+  end
+
+  it "detects plurals of words ending in 'e'" do
+    expect(Swearjar.default.profane?("asspirates")).to be_truthy
+  end
+
+  it "detects profane emojis" do
+    expect(Swearjar.default.profane?("🖕")).to be_truthy
+  end
+
+  it "detects profane emojis with skin tone" do
+    expect(Swearjar.default.profane?("🖕🏾")).to be_truthy
+  end
+
+  it "censors profane emojis" do
+    expect(Swearjar.default.censor("Fuck you🖕 🖕🖕")).to eq("**** you* **")
+  end
+
+  it "censors with regular expression matching" do
+    expect(Swearjar.default.censor("foonIgg3rbar foo nigger")).to eq("************ foo ******")
   end
 
-end
+  it "censors with a mix of normal and regular expression matches" do
+    expect(Swearjar.default.censor("fagfaggot faggotfag")).to eq("********* *********")
+  end
+
+  it "detects scorecard with regular expression matching" do
+    expect(Swearjar.default.scorecard("foonIgg3rbar foo nigger")).to eq({"discriminatory" => 2})
+  end
+
+  xit "doesn't substitute simple words when they occur later as substrings" do
+    expect(Swearjar.default.censor("anus janus")).to eq("**** janus")
+  end
+end

data/swearjar.gemspec

@@ -10,7 +10,7 @@ Gem::Specification.new do |s|
   s.summary = "Put another nickel in the swearjar. Simple profanity detection with content analysis"
   s.description = "#{s.summary}."
   s.email = %q{joshbuddy@gmail.com}
-  s.extra_rdoc_files = ['README.rdoc']
+  s.extra_rdoc_files = ['README.md']
   s.files = `git ls-files`.split("\n")
   s.homepage = %q{http://github.com/joshbuddy/swearjar}
   s.rdoc_options = ["--charset=UTF-8"]
@@ -20,18 +20,8 @@ Gem::Specification.new do |s|
   s.rubyforge_project = 'swearjar'
 
   # dependencies
-  s.add_runtime_dependency 'fuzzyhash',   '~> 0.0.11'
-  s.add_development_dependency 'rake',    '~> 0.8.7'
-  s.add_development_dependency 'rspec',   '~> 1.3.0'
-
-  if s.respond_to? :specification_version then
-    current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
-    s.specification_version = 3
-
-    if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
-    else
-    end
-  else
-  end
+  s.add_development_dependency 'rake',    '~> 10.5'
+  s.add_development_dependency 'rspec',   '~> 3.4'
+  s.add_development_dependency 'pry',   '~> 0.10'
 end
 

metadata

@@ -1,99 +1,105 @@
 --- !ruby/object:Gem::Specification
 name: swearjar
 version: !ruby/object:Gem::Version
-  version: 1.0.0
-  prerelease: 
+  version: 1.1.0
 platform: ruby
 authors:
 - Joshua Hull
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-04-03 00:00:00.000000000 Z
+date: 2016-02-14 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
-  name: fuzzyhash
-  requirement: &70251065583700 !ruby/object:Gem::Requirement
-    none: false
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.0.11
-  type: :runtime
+        version: '10.5'
+  type: :development
   prerelease: false
-  version_requirements: *70251065583700
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.5'
 - !ruby/object:Gem::Dependency
-  name: rake
-  requirement: &70251065583240 !ruby/object:Gem::Requirement
-    none: false
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.8.7
+        version: '3.4'
   type: :development
   prerelease: false
-  version_requirements: *70251065583240
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.4'
 - !ruby/object:Gem::Dependency
-  name: rspec
-  requirement: &70251065582780 !ruby/object:Gem::Requirement
-    none: false
+  name: pry
+  requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.3.0
+        version: '0.10'
   type: :development
   prerelease: false
-  version_requirements: *70251065582780
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.10'
 description: Put another nickel in the swearjar. Simple profanity detection with content
   analysis.
 email: joshbuddy@gmail.com
 executables: []
 extensions: []
 extra_rdoc_files:
-- README.rdoc
+- README.md
 files:
-- .gitignore
+- ".gitignore"
+- ".travis.yml"
+- CHANGELOG.md
 - Gemfile
-- README.rdoc
+- README.md
 - Rakefile
 - lib/config/en.yml
 - lib/swearjar.rb
-- lib/swearjar/tester.rb
 - lib/swearjar/version.rb
 - spec/data/swear.yml
-- spec/spec.opts
 - spec/spec_helper.rb
 - spec/swearjar_spec.rb
 - swearjar.gemspec
 homepage: http://github.com/joshbuddy/swearjar
 licenses: []
+metadata: {}
 post_install_message: 
 rdoc_options:
-- --charset=UTF-8
+- "--charset=UTF-8"
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
 rubyforge_project: swearjar
-rubygems_version: 1.8.11
+rubygems_version: 2.2.3
 signing_key: 
-specification_version: 3
+specification_version: 4
 summary: Put another nickel in the swearjar. Simple profanity detection with content
   analysis
 test_files:
 - spec/data/swear.yml
-- spec/spec.opts
 - spec/spec_helper.rb
 - spec/swearjar_spec.rb
 has_rdoc: 

data/README.rdoc

@@ -1,28 +0,0 @@
-= Swearjar
-
-Simple profanity detection with content analysis.
-
-== Installation
-
-gem install swearjar
-
-== Usage
-
-  require 'swearjar'
-
-  Swearjar.default.profane?('jim henson has a massive hard on he is gonna use to fuck everybody')
-  << true
-
-  Swearjar.default.scorecard('jim henson has a massive hard on he is gonna use to fuck everybody')
-  << {:sexual => 2}
-
-  Swearjar.default.censor('jim henson has a massive hard on he is gonna use to fuck everybody')
-  << 'jim henson has a massive **** ** he is gonna use to **** everybody'
-
-To load from a custom yaml file, you can do the following
-
-  sj = Swearjar.new
-  sj.load_file('my_yaml.yml')
-
-The YAML file can have two sections, `simple` and `regex`. For an example, see `lib/config/en.yml`.
-

data/lib/swearjar/tester.rb

@@ -1,32 +0,0 @@
-require 'yaml'
-require 'fuzzy_hash'
-require 'bloomfilter'
-
-class Swearjar
-  class Tester
-
-    def initialize(config_file)
-      data = YAML.load_file
-
-      @tester = FuzzyHash.new
-
-      data['regex'].each do |pattern, type|
-        @tester[Regexp.new(pattern)] = type
-      end
-
-      data['simple'].each do |test, type|
-        @tester[test] = type
-      end
-
-    end
-
-    def scan(string, &block)
-      string.scan(/\b[\b]+\b/, &block)
-    end
-
-    def profane?(string)
-      scan(string) {|w| return true}
-    end
-
-  end
-end

data/spec/spec.opts

@@ -1,7 +0,0 @@
---colour
---format
-specdoc
---loadby
-mtime
---reverse
---backtrace