l2e_vocab_blacklist 1.0.0 → 1.0.1

Sign up to get free protection for your applications and to get access to all the features.
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA1:
3
- metadata.gz: f2420de5b15e5cb61f0282dc22850555e5be7840
4
- data.tar.gz: 39a4e09483d8ef9de4f94abfc458012b6e5a6988
3
+ metadata.gz: a89b0d6537e66cb74360ab8024cdbafaccfb2d9a
4
+ data.tar.gz: 7ba3879756f5b9b1429904e488150c2c18d807f0
5
5
  SHA512:
6
- metadata.gz: 79526b19533289a180e9a553ffd340ae9e95a5f213f15a5232367084c3fe994140e6c533fddc09cd559dae44f6ddad308ad03f8e94a2eff9395183c79328a4a9
7
- data.tar.gz: f83408fbab1d607675b8077530b86e4c9189a8481819fa18e72bd2f1122601361e14c09392121ef2d707c23cf3e0f939c0274018076003014364f2ed852fa5b0
6
+ metadata.gz: a05b911f2cbdc358f3c083d5c4e890b0d2280e086fb235d59381aff9925adc8d6b6aebcbdc4ddd28a5cacb950ff67e0d2b6dc5c8138f44e7638346bd8d80e731
7
+ data.tar.gz: 48d946379208feb2f10ca1e508a437b18012d186a82fb510eb6c41d2eac2a05eadb74e25fd0e948ecc64e2a8ef4e03ce16d32b5fa004ff3fde1f626f6656cae7
@@ -1,5 +1,36 @@
1
+ require 'active_support/inflector'
2
+
1
3
  class VocabBlacklist
2
- def self.blacklisted?(word)
3
- word == "drat"
4
+ def self.blacklisted?(str)
5
+ # Sanitize string
6
+ str = str.downcase.strip.gsub(CONSIDER_REGEX, '')
7
+
8
+ # Blacklist if any of the words
9
+ str.split(" ").each do |word|
10
+ return true if FULL_WORDS.include?( word )
11
+ end
12
+
13
+ # For compound dirty words
14
+ PHRASES.each do |bad_phrase|
15
+ return true if str.include?(bad_phrase)
16
+ end
17
+
18
+ return GREEDY_DIRTY_WORDS.any?{ |s| str.include?( s ) }
4
19
  end
20
+
21
+ def self.file_to_nomalized_words(file)
22
+ File.read(file).split("\n").reject { |s| s.to_s.strip.empty? }.map(&:downcase).map { |s| s.gsub(CONSIDER_REGEX, '') }
23
+ end
24
+
25
+ def self.words_with_expansions(words)
26
+ words.map { |s| [s, s.pluralize, s.singularize] }.uniq.flatten
27
+ end
28
+
29
+ BLACKLIST_DIR = File.join(File.dirname(__FILE__), 'l2e_vocab_blacklist/blacklists')
30
+ CONSIDER_REGEX = /[^0-9a-z\* ]/i
31
+
32
+ PHRASES = file_to_nomalized_words("#{BLACKLIST_DIR}/full_words.txt").select { |w| w.split(" ").length > 1 }
33
+ FULL_WORDS = file_to_nomalized_words("#{BLACKLIST_DIR}/full_words.txt").reject { |w| w.split(" ").length > 1 }
34
+ GREEDY_DIRTY_WORDS = words_with_expansions(file_to_nomalized_words("#{BLACKLIST_DIR}/greedy_words.txt")).uniq.freeze
35
+
5
36
  end
@@ -0,0 +1,340 @@
1
+ Asshole
2
+ Anal
3
+ Ass
4
+ A-Hole
5
+ Asexual
6
+ Anus
7
+ Aerolia
8
+ Alcohol
9
+ Abortion
10
+ Apeshit
11
+ Aids
12
+ Abstinence
13
+ Addict
14
+ Arrested
15
+ Amphetamine
16
+ Butt
17
+ Bugger
18
+ Bunghole
19
+ Butthole
20
+ Blowjob
21
+ BJ
22
+ Bastard
23
+ Boob
24
+ Boobies
25
+ Breasts
26
+ Bong
27
+ Beer
28
+ Bisexual
29
+ Beefcake
30
+ Busty
31
+ Bullshit
32
+ Bra
33
+ Brazzer
34
+ Beaner
35
+ Bulging
36
+ Barbiturates
37
+ Cartel
38
+ Codeine
39
+ Cunt
40
+ Corset
41
+ Cum
42
+ Cumming
43
+ Clitoris
44
+ Cock
45
+ Cocksucking
46
+ Cocksucker
47
+ Cockblock
48
+ Cocaine
49
+ Cornholing
50
+ Chink
51
+ Chino
52
+ Crip
53
+ Crack
54
+ Cleavage
55
+ Cunnilingus
56
+ Chronic
57
+ Circumcision
58
+ Circumcised
59
+ Cigarette
60
+ Cig
61
+ ChoMo
62
+ Chulo
63
+ Coolie
64
+ Chlamydia
65
+ Condon
66
+ Cumshot
67
+ Cervix
68
+ Contraception
69
+ Cannabis
70
+ Crap
71
+ Dildo
72
+ Dick
73
+ Dicking
74
+ Damn
75
+ Dyke
76
+ Dipshit
77
+ Daterape
78
+ Douche
79
+ Dingleberry
80
+ Dooms
81
+ Doobie
82
+ Diarrhea
83
+ Dimbad
84
+ Doggy Style
85
+ Drag Queen
86
+ Deep Throat
87
+ Deepthroat
88
+ Dental Dam
89
+ DMT
90
+ Diaphragm
91
+ Eat out
92
+ Ecstasy
93
+ Ejaculate
94
+ Ejaculation
95
+ Exhibitionism
96
+ Fag
97
+ Faggot
98
+ Fisting
99
+ Foreskin
100
+ Fetish
101
+ Fetus
102
+ Fetal
103
+ Grundle
104
+ Gimp
105
+ Gonorrhea
106
+ G-spot
107
+ g spot
108
+ Gigolo
109
+ Gook
110
+ Gay
111
+ Gang Bang
112
+ Gape
113
+ Golden Shower
114
+ Genital
115
+ Gin
116
+ Harlot
117
+ Hangover
118
+ Hungover
119
+ Herpes
120
+ Hook Up
121
+ Hookah
122
+ Hooker
123
+ Harem
124
+ Heroin
125
+ Heroina
126
+ Hick
127
+ Hickey
128
+ Hickie
129
+ Hard On
130
+ Hand Job
131
+ Handjob
132
+ Homosexual
133
+ Heterosexual
134
+ Hiv
135
+ Homicide
136
+ Hallucinate
137
+ Hallucination
138
+ Hallucinating
139
+ Hallucinogen
140
+ Huff
141
+ Huffing
142
+ Hump
143
+ Illicit
144
+ Intercourse
145
+ Joint
146
+ Jackass
147
+ Jigga
148
+ Jap
149
+ Jerkoff
150
+ Jerk Off
151
+ Jerk It
152
+ Juicy
153
+ Kyke
154
+ Kook
155
+ Kunt
156
+ Knocked Up
157
+ KKK
158
+ Lust
159
+ Lustful
160
+ Labia
161
+ Lesbian
162
+ Lesbo
163
+ Lover
164
+ Licking
165
+ Lube
166
+ Lubricant
167
+ Lubrication
168
+ Lithium
169
+ LSD
170
+ Mofo
171
+ Milf
172
+ Meth
173
+ Methamphetamine
174
+ Morphine
175
+ Marijuana
176
+ Mary Jane
177
+ Merk
178
+ Molest
179
+ Missionary
180
+ Masturbate
181
+ Masturbation
182
+ Money Shot
183
+ Murder
184
+ Moneyshot
185
+ Mali
186
+ Moron
187
+ Menstruation
188
+ MDMA
189
+ Nigga
190
+ Nipple
191
+ Nips
192
+ Nignog
193
+ Niptip
194
+ Nicotine
195
+ Narcotic
196
+ Nookie
197
+ Nooky
198
+ Nude
199
+ Nudist
200
+ Nudity
201
+ Naked
202
+ Negro
203
+ Nazi
204
+ Orgasm
205
+ Orgasmic
206
+ Orgy
207
+ Opiates
208
+ Opium
209
+ Ovaries
210
+ Oral
211
+ Oxy
212
+ Oxycodone
213
+ Penis
214
+ Private Parts
215
+ Pee
216
+ Penile
217
+ Preggers
218
+ Pregnant
219
+ Pregnancy
220
+ Prostitute
221
+ Prostitution
222
+ Porn
223
+ Pornograph
224
+ Panties
225
+ Pussy
226
+ Playboy
227
+ Queer
228
+ Queef
229
+ Rape
230
+ Raper
231
+ Rapist
232
+ Roofie
233
+ Rohypnol
234
+ Raunchy
235
+ Rimjob
236
+ Rim Job
237
+ Racist
238
+ Racism
239
+ Racy
240
+ Retard
241
+ Rum
242
+ Slut
243
+ Smoke
244
+ Shit
245
+ Shitty
246
+ Shrooms
247
+ Shitter
248
+ Shitting
249
+ Shmegma
250
+ Suck
251
+ Sucker
252
+ Snort
253
+ Snorting
254
+ Scat
255
+ Syphilis
256
+ Sperm
257
+ Spermicide
258
+ Shoplift
259
+ Shoplifting
260
+ Squirt
261
+ Squirting
262
+ Sex
263
+ Sexy
264
+ Sexual
265
+ Sexist
266
+ Sexism
267
+ Sexing
268
+ Salvia
269
+ Sangria
270
+ Steroids
271
+ STD
272
+ Splooge
273
+ Suicide
274
+ Shank
275
+ Schlong
276
+ Scrotum
277
+ Tranny
278
+ Transvestite
279
+ Testes
280
+ Testicle
281
+ Testicular
282
+ Transexual
283
+ Transgender
284
+ Transgendered
285
+ Trafficking
286
+ Tobacco
287
+ Twerk
288
+ Throbbing
289
+ Tit
290
+ Tittie
291
+ Titty
292
+ Turd
293
+ Tequila
294
+ THC
295
+ Unmentionables
296
+ Urethra
297
+ Urine
298
+ Ureter
299
+ Uterus
300
+ Underage
301
+ Vulva
302
+ Vagina
303
+ Vagina
304
+ Viagra
305
+ Vag
306
+ Vamp
307
+ Vicodin
308
+ Whisky
309
+ Whore
310
+ Whorehouse
311
+ Whoring
312
+ Wanker
313
+ Weiner
314
+ Wiener
315
+ Whity
316
+ Whitie
317
+ Wetback
318
+ Wigger
319
+ Whack Off
320
+ Weed
321
+ X Rated
322
+ XX
323
+ XXX
324
+ Yank
325
+ Zipperhead
326
+ F*ck
327
+ F*cker
328
+ Sh*t
329
+ Cr*p
330
+ C*nt
331
+ B*tch
332
+ P*ss
333
+ C*ck
334
+ C*cksucker
335
+ Motherf*cker
336
+ T*t
337
+ 50 Shades of Grey
338
+ 50 Shades of Gray
339
+ Fifty Shades of Grey
340
+ Fifty Shades of Gray
@@ -0,0 +1,3 @@
1
+ fuck
2
+ bitch
3
+ nigger
metadata CHANGED
@@ -1,7 +1,7 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: l2e_vocab_blacklist
3
3
  version: !ruby/object:Gem::Version
4
- version: 1.0.0
4
+ version: 1.0.1
5
5
  platform: ruby
6
6
  authors:
7
7
  - Greg Sherrid
@@ -20,6 +20,8 @@ extra_rdoc_files: []
20
20
  files:
21
21
  - README.md
22
22
  - lib/l2e_vocab_blacklist.rb
23
+ - lib/l2e_vocab_blacklist/blacklists/full_words.txt
24
+ - lib/l2e_vocab_blacklist/blacklists/greedy_words.txt
23
25
  homepage: https://github.com/gregsherrid/l2e_vocab_blacklist
24
26
  licenses:
25
27
  - All rights reserved, for now