wr_vocab_blacklist 0.0.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 83cba9b3f2d5a661c2a4106ba948db0b8da5913e523a50b282495686ad06d744
+  data.tar.gz: d02403de8157e30b1cf4d868b9f274f536ea4b131c6aef2bddaf6b9a8520a872
+SHA512:
+  metadata.gz: 158019d306ff7b712cd77a1ce5f2ef37644938e0a6a12ed53818a3e45b4b12c399997fa7f81099473c050d39676c47b17d466756092da29a52177e914a5d141c
+  data.tar.gz: 67934a1895f260bfd39b6b8b30cc32adc045576f0be1222d22669a5489941a83eae3ade1ac6b639a3cf0ed8cb813ccfc863d09c09a6e955a8849d995860a8d15

data/README.md

@@ -0,0 +1,24 @@
+L2E Vocab Blacklist
+==================
+
+Detect words and partial-words that shouldn't be used on Learn2Earn's website
+
+To be expanded to allow for different classes of banned words so
+administrators may loosen or expand restrictions, or so we can be more
+permissive with older students.
+
+Use:
+```
+gem 'l2e_vocab_blacklist'
+```
+
+### To update and publish the gem
+
+1. Merge pull requests, pull to local master
+2. Run tests: `bundle exec rspec spec/l2e_vocab_blacklist_spec.rb`
+3. Increase the gem version and date in `l2e_vocab_blacklist.gemspec`
+4. Run `gem build l2e_vocab_blacklist.gemspec`
+5. Remove the old `.gem` file
+6. Push the new gem with: `gem push l2e_vocab_blacklist-X.X.X.gem` substituting in the gem version
+  1. You may need to sign in on the CLI to push the gem. Talk to Greg about this.
+7. Commit and push your changes

data/lib/l2e_vocab_blacklist/blacklists/full_words.csv

@@ -0,0 +1,282 @@
+50 Shades of Gray,15
+50 Shades of Grey,15
+A-Hole,10
+Anal,5
+Anus,5
+Apeshit,15
+Ass,15
+Asshole,10
+B*tch,15
+Badass,15
+Bad-ass,15
+Barbiturates,5
+Bastard,10
+Beaner,15
+Beastiality,15
+Bisexual,5
+BJ,15
+Blowjob,15
+Boner,15
+Boob,10
+Boobs,10
+Boobies,15
+Brazzer,15
+Breasts,5
+Bugger,15
+Bullshit,15
+Bunghole,15
+Busty,5
+Butthole,15
+C*ck,15
+C*cksucker,15
+C*nt,15
+Cannabis,5
+Cervix,5
+Chink,15
+Chino,15
+Chlamydia,10
+ChoMo,15
+Chulo,5
+Cleavage,5
+Clitoris,15
+Cocaine,5
+Cock,15
+Cockblock,15
+Cocksucker,15
+Cocksucking,15
+Codeine,5
+Condom,15
+Coolie,15
+Cornholing,15
+Cr*p,15
+Crap,10
+Crip,10
+Cum,15
+Cumming,15
+Cumshot,15
+Cumslut,15
+Cum-slut,15
+Cunnilingus,15
+Cunt,15
+Damn,5
+Daterape,10
+Deep Throat,15
+Deepthroat,15
+Dental Dam,15
+Dick,15
+Dicking,15
+Dildo,15
+Dingleberry,15
+Dipshit,15
+DMT,15
+Doggy Style,15
+Doobie,15
+Douche,15
+Drag Queen,5
+Dyke,15
+Ejaculate,10
+Ejaculation,10
+Erotic,15
+Erotica,15
+Erection,15
+F*ck,15
+F*cker,15
+F**k,15
+F**ker,15
+F*@k,15
+F*@ker,15
+F*#k,15
+F*#ker,15
+F*?k,15
+F*?ker,15
+F*ck, 15
+F*cking, 15
+Fu*k
+Fag,15
+Faggot,15
+Fetal,5
+Fetish,10
+Fifty Shades of Gray,15
+Fifty Shades of Grey,15
+Fisting,15
+Foreskin,10
+g spot,15
+G-spot,15
+Gang Bang,15
+Genital,10
+Genitals,10
+Gigolo,5
+Gimp,5
+Golden Shower,15
+Gonorrhea,5
+Gook,15
+Grundle,15
+Hallucinogen,5
+Hand Job,15
+Handjob,15
+Hangover,10
+Hard On,5
+Harem,5
+Harlot,10
+Heroin,5
+Heroina,5
+Herpes,10
+Hick,5
+Hickey,5
+Hickie,5
+Hooker,10
+Horny,15
+Huff,10
+Huffing,10
+Hump,15
+Humping,15
+Hungover,10
+Intercourse,5
+Jackass,15
+Jap,15
+Jerk It,15
+Jerk Off,15
+Jerkoff,15
+Jigga,15
+Joint,10
+Kickass,15
+Kick-ass,15
+Kunt,15
+Kyke,15
+Labia,10
+Lesbo,15
+LSD,10
+Lube,15
+Lubricant,10
+Lubrication,5
+Lust,5
+Lustful,5
+Marijuana,10
+Masturbate,10
+Masturbating,10
+Masturbation,10
+MDMA,15
+Merk,15
+Meth,10
+Methamphetamine,10
+Milf,15
+Mofo,15
+Money Shot,15
+Moneyshot,15
+Moron,5
+Motherf*cker,15
+Narcotic,5
+Nigga,15
+Nignog,15
+Nips,15
+Niptip,15
+Nookie,15
+Nooky,15
+Nude,10
+Opiates,5
+Opium,5
+Oral sex,15
+Orgasm,15
+Orgasmic,15
+Orgy,10
+Ovaries,5
+Oxy,15
+Oxycodone,10
+P*ss,15
+Panties,10
+Penile,5
+Penis,10
+Playboy,10
+Porn,15
+Pornograph,15
+Preggers,15
+Promiscuity, 15
+Prostitute,10
+Prostitution,10
+Pussy,15
+Queef,15
+Racy,10
+Rape,5
+Rapist,10
+Raunchy,10
+Rim Job,15
+Rimjob,15
+Rohypnol,10
+Roofie,10
+S&M,15
+S/M,15
+Salvia,15
+Sangria,5
+Schlong,15
+Scrotum,15
+Seduce,10
+Seduced,10
+Seducing,10
+Seductress,10
+Sex,10
+Sexier,10
+Sexiest,10
+Sexing,10
+Sexting,10
+Sexual,10
+Sexy,10
+Sh*t,15
+Shank,15
+Shit,15
+Shitter,15
+Shitting,15
+Shitty,15
+Shmegma,15
+Shrooms,15
+Slut,15
+Snorting,10
+Sperm,10
+Spermicide,10
+Splooge,15
+STD,10
+Strip tease,15
+Stripper,10
+Sucker,10
+Suicide,5
+Syphilis,10
+T*t,15
+Testes,10
+Testicle,10
+Testicular,10
+THC,15
+Thong,10
+Threesome,15
+Tit,10
+Tittie,15
+Titty,15
+Tranny,15
+Turd,15
+Twerk,15
+Uncensored,10
+Urethra,10
+Urine,5
+Uterus,5
+Vag,15
+Vagina,10
+Vagina,10
+Vamp,5
+Viagra,15
+Vicodin,10
+Vulva,5
+Wanker,15
+Weiner,10
+Wetback,15
+Wet dream,10
+Whack Off,15
+Whisky,5
+Whitie,15
+Whity,15
+Whore,10
+Whorehouse,10
+Whoring,10
+Wiener,10
+Wigger,15
+X Rated,10
+XX,10
+XXX,10
+Zipperhead,15

data/lib/l2e_vocab_blacklist/blacklists/greedy_words.txt

@@ -0,0 +1,4 @@
+fuck
+bitch
+nigger
+**

data/lib/l2e_vocab_blacklist/blacklists/whitelist.csv

@@ -0,0 +1 @@
+moby dick,5

data/lib/l2e_vocab_blacklist.rb

@@ -0,0 +1,115 @@
+require 'active_support/inflector'
+require 'csv'  
+
+class VocabBlacklist
+
+	# Returns true or false, check to see if the string is on the blacklist
+	def self.blacklisted?(str, age = "0")
+		# Sanitize string
+		str = str.downcase.strip
+
+		whitelisted_phrases = self.whitelist_matches(str)
+
+		# Blacklist if any of the words 
+		str.split(/[ -]/).each do |word|
+			word = word.gsub(CONSIDER_REGEX, "")
+
+			if check_full_words_csv(word, age)
+
+				is_whitelisted = whitelisted_phrases.any? do |phrase|
+					phrase.include?(word)
+				end
+				if !is_whitelisted
+					return true
+				end
+			end
+		end
+		# For compound dirty words
+		PHRASES.each do |bad_phrase|
+			return true if str.include?(bad_phrase)
+		end
+		
+		return GREEDY_WORDS.any? { |s| str.include?(s) }
+	end
+
+	def self.whitelist_matches(text)
+		text = text.downcase.strip.gsub(CONSIDER_REGEX, "")
+		WHITELIST.select do |whitelist_phrase|
+			text.include?(whitelist_phrase)
+		end
+
+	end
+
+	def self.censor(str, age = "0", replace_with = "*")
+		PHRASES.each do |bad_phrase|
+			# match number of characters for any replace_with that is 1 character
+			if replace_with.length == 1
+				str.gsub!(/#{ bad_phrase }/i, replace_with * bad_phrase.length)
+			else
+				str.gsub!(/#{ bad_phrase }/i, replace_with)
+			end
+		end
+
+		whitelisted_phrases = self.whitelist_matches(str)
+
+		str.split(/ /).map do |working_word|
+			working_word.split(/-/).map do |sub_working_word|
+				word = sub_working_word.downcase.gsub(CONSIDER_REGEX, "")
+
+				is_whitelisted = whitelisted_phrases.any? do |phrase|
+					phrase.include?(word)
+				end
+
+				if !is_whitelisted
+					if check_full_words_csv(word, age)
+						# match number of characters for any replace_with that is 1 character
+						if replace_with.length == 1
+							sub_working_word.gsub!(/#{ word }/i, replace_with * word.length)
+						else
+							sub_working_word.gsub!(/#{ word }/i, replace_with)
+						end
+					end
+
+					if GREEDY_WORDS.any? { |w| word.include?(w) }
+						# match number of characters for any replace_with that is 1 character
+						if replace_with.length == 1
+							sub_working_word = replace_with * sub_working_word.length
+						else
+							sub_working_word = replace_with
+						end
+					end
+				end
+
+				sub_working_word
+			end.join("-")
+		end.join(" ")
+	end
+
+	def self.file_to_normalized_words(file)
+		CSV.parse(File.read(file)).map(&:first).reject { |s| s.to_s.strip.empty? }.map(&:downcase).map { |s| s.gsub(CONSIDER_REGEX, "") }
+	end
+
+	def self.words_with_expansions(words)
+		words.map { |s| [s, s.pluralize, s.singularize] }.uniq.flatten
+	end
+
+	BLACKLIST_DIR = File.join(File.dirname(__FILE__), 'l2e_vocab_blacklist/blacklists')
+	CONSIDER_REGEX = /[^0-9a-z\* ]/i
+
+	PHRASES = file_to_normalized_words("#{BLACKLIST_DIR}/full_words.csv").select { |w| w.split(" ").length > 1 }
+	FULL_WORDS = file_to_normalized_words("#{BLACKLIST_DIR}/full_words.csv").reject { |w| w.split(" ").length > 1 }
+	GREEDY_WORDS = words_with_expansions(file_to_normalized_words("#{BLACKLIST_DIR}/greedy_words.txt")).uniq.freeze
+	WHITELIST = file_to_normalized_words("#{BLACKLIST_DIR}/whitelist.csv").uniq.freeze
+
+	FULL_WORDS_CSV = CSV.parse(File.read("#{BLACKLIST_DIR}/full_words.csv"))
+
+	private
+
+		def self.check_full_words_csv(word, age)
+			FULL_WORDS_CSV.each do |row|
+				return true	 if row[1].to_i >= age.to_i && row[0].downcase == word.downcase
+			end
+			return false
+		end
+
+end

metadata

@@ -0,0 +1,55 @@
+--- !ruby/object:Gem::Specification
+name: wr_vocab_blacklist
+version: !ruby/object:Gem::Version
+  version: 0.0.0
+platform: ruby
+authors:
+- Greg Sherrid
+- Gilles Ferone
+- Kevin Schroeder
+- Matt Schleifman
+- Whooo's Reading by Learn2Earn
+autorequire:
+bindir: bin
+cert_chain: []
+date: 2022-03-15 00:00:00.000000000 Z
+dependencies: []
+description: Detect words and partial-words that shouldn't be used on Whooo's Reading
+  website
+email:
+- kevin@whooosreading.org
+- gilles@whooosreading.org
+- matt@whooosreading.org
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- README.md
+- lib/l2e_vocab_blacklist.rb
+- lib/l2e_vocab_blacklist/blacklists/full_words.csv
+- lib/l2e_vocab_blacklist/blacklists/greedy_words.txt
+- lib/l2e_vocab_blacklist/blacklists/whitelist.csv
+homepage: https://github.com/whooosreading/l2e_vocab_blacklist
+licenses:
+- All rights reserved, for now
+metadata: {}
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.2.3
+signing_key:
+specification_version: 4
+summary: Whooo's Reading Vocab Blacklist
+test_files: []