bad_word_detector 0.0.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- data/.gitignore +17 -0
- data/Gemfile +4 -0
- data/LICENSE +22 -0
- data/README.md +56 -0
- data/Rakefile +10 -0
- data/bad_word_detector.gemspec +33 -0
- data/bin/bad_word_detector +13 -0
- data/lib/bad_word_detector.rb +200 -0
- data/lib/bad_word_detector/bad_word.rb +30 -0
- data/lib/bad_word_detector/prefix_tree.rb +56 -0
- data/lib/bad_word_detector/rule.rb +35 -0
- data/lib/bad_word_detector/state.rb +41 -0
- data/lib/bad_word_detector/version.rb +3 -0
- data/lib/bad_word_detector/whitelist.rb +33 -0
- data/lib/conf/library.yaml +155 -0
- data/lib/conf/rules.yaml +59 -0
- data/lib/conf/whitelist.yaml +236921 -0
- data/lib/conf/words.yaml +459 -0
- data/test/rules.yaml +63 -0
- data/test/test.rb +26 -0
- data/test/test_bad_word_detector.rb +72 -0
- metadata +110 -0
data/lib/conf/words.yaml
ADDED
@@ -0,0 +1,459 @@
|
|
1
|
+
---
|
2
|
+
- "ahole"
|
3
|
+
- "anus"
|
4
|
+
- "ash0le"
|
5
|
+
- "ash0les"
|
6
|
+
- "asholes"
|
7
|
+
- "ass"
|
8
|
+
- "Ass Monkey"
|
9
|
+
- "Assface"
|
10
|
+
- "assh0le"
|
11
|
+
- "assh0lez"
|
12
|
+
- "asshole"
|
13
|
+
- "assholes"
|
14
|
+
- "assholz"
|
15
|
+
- "asswipe"
|
16
|
+
- "azzhole"
|
17
|
+
- "bassterds"
|
18
|
+
- "bastard"
|
19
|
+
- "bastards"
|
20
|
+
- "bastardz"
|
21
|
+
- "basterds"
|
22
|
+
- "basterdz"
|
23
|
+
- "Biatch"
|
24
|
+
- "bitch"
|
25
|
+
- "bitches"
|
26
|
+
- "Blow Job"
|
27
|
+
- "boffing"
|
28
|
+
- "butthole"
|
29
|
+
- "buttwipe"
|
30
|
+
- "c0ck"
|
31
|
+
- "c0cks"
|
32
|
+
- "c0k"
|
33
|
+
- "Carpet Muncher"
|
34
|
+
- "cawk"
|
35
|
+
- "cawks"
|
36
|
+
- "Clit"
|
37
|
+
- "cnts"
|
38
|
+
- "cntz"
|
39
|
+
- "cock"
|
40
|
+
- "cockhead"
|
41
|
+
- "cock-head"
|
42
|
+
- "cocks"
|
43
|
+
- "CockSucker"
|
44
|
+
- "cock-sucker"
|
45
|
+
- "crap"
|
46
|
+
- "cum"
|
47
|
+
- "cunt"
|
48
|
+
- "cunts"
|
49
|
+
- "cuntz"
|
50
|
+
- "dick"
|
51
|
+
- "dild0"
|
52
|
+
- "dild0s"
|
53
|
+
- "dildo"
|
54
|
+
- "dildos"
|
55
|
+
- "dilld0"
|
56
|
+
- "dilld0s"
|
57
|
+
- "dominatricks"
|
58
|
+
- "dominatrics"
|
59
|
+
- "dominatrix"
|
60
|
+
- "dyke"
|
61
|
+
- "enema"
|
62
|
+
- "f u c k"
|
63
|
+
- "f u c k e r"
|
64
|
+
- "fag"
|
65
|
+
- "fag1t"
|
66
|
+
- "faget"
|
67
|
+
- "fagg1t"
|
68
|
+
- "faggit"
|
69
|
+
- "faggot"
|
70
|
+
- "fagit"
|
71
|
+
- "fags"
|
72
|
+
- "fagz"
|
73
|
+
- "faig"
|
74
|
+
- "faigs"
|
75
|
+
- "fart"
|
76
|
+
- "flipping the bird"
|
77
|
+
- "fuck"
|
78
|
+
- "fucker"
|
79
|
+
- "fuckin"
|
80
|
+
- "fucking"
|
81
|
+
- "fucks"
|
82
|
+
- "Fudge Packer"
|
83
|
+
- "fuk"
|
84
|
+
- "Fukah"
|
85
|
+
- "Fuken"
|
86
|
+
- "fuker"
|
87
|
+
- "Fukin"
|
88
|
+
- "Fukk"
|
89
|
+
- "Fukkah"
|
90
|
+
- "Fukken"
|
91
|
+
- "Fukker"
|
92
|
+
- "Fukkin"
|
93
|
+
- "g00k"
|
94
|
+
- "gay"
|
95
|
+
- "gayboy"
|
96
|
+
- "gaygirl"
|
97
|
+
- "gays"
|
98
|
+
- "gayz"
|
99
|
+
- "God-damned"
|
100
|
+
- "h00r"
|
101
|
+
- "h0ar"
|
102
|
+
- "h0re"
|
103
|
+
- "hells"
|
104
|
+
- "hoar"
|
105
|
+
- "hoor"
|
106
|
+
- "hoore"
|
107
|
+
- "jackoff"
|
108
|
+
- "jap"
|
109
|
+
- "japs"
|
110
|
+
- "jerk-off"
|
111
|
+
- "jisim"
|
112
|
+
- "jiss"
|
113
|
+
- "jizm"
|
114
|
+
- "jizz"
|
115
|
+
- "knob"
|
116
|
+
- "knobs"
|
117
|
+
- "knobz"
|
118
|
+
- "kunt"
|
119
|
+
- "kunts"
|
120
|
+
- "kuntz"
|
121
|
+
- "Lesbian"
|
122
|
+
- "Lezzian"
|
123
|
+
- "Lipshits"
|
124
|
+
- "Lipshitz"
|
125
|
+
- "masochist"
|
126
|
+
- "masokist"
|
127
|
+
- "massterbait"
|
128
|
+
- "masstrbait"
|
129
|
+
- "masstrbate"
|
130
|
+
- "masterbaiter"
|
131
|
+
- "masterbate"
|
132
|
+
- "masterbates"
|
133
|
+
- "Motha Fucker"
|
134
|
+
- "Motha Fuker"
|
135
|
+
- "Motha Fukkah"
|
136
|
+
- "Motha Fukker"
|
137
|
+
- "Mother Fucker"
|
138
|
+
- "Mother Fukah"
|
139
|
+
- "Mother Fuker"
|
140
|
+
- "Mother Fukkah"
|
141
|
+
- "Mother Fukker"
|
142
|
+
- "mother-fucker"
|
143
|
+
- "Mutha Fucker"
|
144
|
+
- "Mutha Fukah"
|
145
|
+
- "Mutha Fuker"
|
146
|
+
- "Mutha Fukkah"
|
147
|
+
- "Mutha Fukker"
|
148
|
+
- "n1gr"
|
149
|
+
- "nastt"
|
150
|
+
- "nigger;"
|
151
|
+
- "nigur;"
|
152
|
+
- "niiger;"
|
153
|
+
- "niigr;"
|
154
|
+
- "orafis"
|
155
|
+
- "orgasim;"
|
156
|
+
- "orgasm"
|
157
|
+
- "orgasum"
|
158
|
+
- "oriface"
|
159
|
+
- "orifice"
|
160
|
+
- "orifiss"
|
161
|
+
- "packi"
|
162
|
+
- "packie"
|
163
|
+
- "packy"
|
164
|
+
- "paki"
|
165
|
+
- "pakie"
|
166
|
+
- "paky"
|
167
|
+
- "pecker"
|
168
|
+
- "peeenus"
|
169
|
+
- "peeenusss"
|
170
|
+
- "peenus"
|
171
|
+
- "peinus"
|
172
|
+
- "pen1s"
|
173
|
+
- "penas"
|
174
|
+
- "penis"
|
175
|
+
- "penis-breath"
|
176
|
+
- "penus"
|
177
|
+
- "penuus"
|
178
|
+
- "Phuc"
|
179
|
+
- "Phuck"
|
180
|
+
- "Phuk"
|
181
|
+
- "Phuker"
|
182
|
+
- "Phukker"
|
183
|
+
- "polac"
|
184
|
+
- "polack"
|
185
|
+
- "polak"
|
186
|
+
- "Poonani"
|
187
|
+
- "pr1c"
|
188
|
+
- "pr1ck"
|
189
|
+
- "pr1k"
|
190
|
+
- "pusse"
|
191
|
+
- "pussee"
|
192
|
+
- "pussy"
|
193
|
+
- "puuke"
|
194
|
+
- "puuker"
|
195
|
+
- "queer"
|
196
|
+
- "queers"
|
197
|
+
- "queerz"
|
198
|
+
- "qweers"
|
199
|
+
- "qweerz"
|
200
|
+
- "qweir"
|
201
|
+
- "recktum"
|
202
|
+
- "rectum"
|
203
|
+
- "retard"
|
204
|
+
- "sadist"
|
205
|
+
- "scank"
|
206
|
+
- "schlong"
|
207
|
+
- "screwing"
|
208
|
+
- "semen"
|
209
|
+
- "sex"
|
210
|
+
- "sexy"
|
211
|
+
- "Sh!t"
|
212
|
+
- "sh1t"
|
213
|
+
- "sh1ter"
|
214
|
+
- "sh1ts"
|
215
|
+
- "sh1tter"
|
216
|
+
- "sh1tz"
|
217
|
+
- "shit"
|
218
|
+
- "shits"
|
219
|
+
- "shitter"
|
220
|
+
- "Shitty"
|
221
|
+
- "Shity"
|
222
|
+
- "shitz"
|
223
|
+
- "Shyt"
|
224
|
+
- "Shyte"
|
225
|
+
- "Shytty"
|
226
|
+
- "Shyty"
|
227
|
+
- "skanck"
|
228
|
+
- "skank"
|
229
|
+
- "skankee"
|
230
|
+
- "skankey"
|
231
|
+
- "skanks"
|
232
|
+
- "Skanky"
|
233
|
+
- "slut"
|
234
|
+
- "sluts"
|
235
|
+
- "Slutty"
|
236
|
+
- "slutz"
|
237
|
+
- "son-of-a-bitch"
|
238
|
+
- "tit"
|
239
|
+
- "turd"
|
240
|
+
- "va1jina"
|
241
|
+
- "vag1na"
|
242
|
+
- "vagiina"
|
243
|
+
- "vagina"
|
244
|
+
- "vaj1na"
|
245
|
+
- "vajina"
|
246
|
+
- "vullva"
|
247
|
+
- "vulva"
|
248
|
+
- "w0p"
|
249
|
+
- "wh00r"
|
250
|
+
- "wh0re"
|
251
|
+
- "whore"
|
252
|
+
- "xrated"
|
253
|
+
- "xxx"
|
254
|
+
- "b!+ch"
|
255
|
+
- "bitch"
|
256
|
+
- "blowjob"
|
257
|
+
- "clit"
|
258
|
+
- "arschloch"
|
259
|
+
- "fuck"
|
260
|
+
- "shit"
|
261
|
+
- "ass"
|
262
|
+
- "asshole"
|
263
|
+
- "b!tch"
|
264
|
+
- "b17ch"
|
265
|
+
- "b1tch"
|
266
|
+
- "bastard"
|
267
|
+
- "bi+ch"
|
268
|
+
- "boiolas"
|
269
|
+
- "buceta"
|
270
|
+
- "c0ck"
|
271
|
+
- "cawk"
|
272
|
+
- "chink"
|
273
|
+
- "cipa"
|
274
|
+
- "clits"
|
275
|
+
- "cock"
|
276
|
+
- "cum"
|
277
|
+
- "cunt"
|
278
|
+
- "dildo"
|
279
|
+
- "dirsa"
|
280
|
+
- "ejakulate"
|
281
|
+
- "fatass"
|
282
|
+
- "fcuk"
|
283
|
+
- "fuk"
|
284
|
+
- "fux0r"
|
285
|
+
- "hoer"
|
286
|
+
- "hore"
|
287
|
+
- "jism"
|
288
|
+
- "kawk"
|
289
|
+
- "l3itch"
|
290
|
+
- "l3i+ch"
|
291
|
+
- "lesbian"
|
292
|
+
- "masturbate"
|
293
|
+
- "masterbat*"
|
294
|
+
- "masterbat3"
|
295
|
+
- "motherfucker"
|
296
|
+
- "s.o.b."
|
297
|
+
- "mofo"
|
298
|
+
- "nazi"
|
299
|
+
- "nigga"
|
300
|
+
- "nigger"
|
301
|
+
- "nutsack"
|
302
|
+
- "phuck"
|
303
|
+
- "pimpis"
|
304
|
+
- "pusse"
|
305
|
+
- "pussy"
|
306
|
+
- "scrotum"
|
307
|
+
- "sh!t"
|
308
|
+
- "shemale"
|
309
|
+
- "shi+"
|
310
|
+
- "sh!+"
|
311
|
+
- "slut"
|
312
|
+
- "smut"
|
313
|
+
- "teets"
|
314
|
+
- "tits"
|
315
|
+
- "boobs"
|
316
|
+
- "b00bs"
|
317
|
+
- "teez"
|
318
|
+
- "testical"
|
319
|
+
- "testicle"
|
320
|
+
- "titt"
|
321
|
+
- "w00se"
|
322
|
+
- "jackoff"
|
323
|
+
- "wank"
|
324
|
+
- "whoar"
|
325
|
+
- "whore"
|
326
|
+
- "*damn"
|
327
|
+
- "*dyke"
|
328
|
+
- "*fuck*"
|
329
|
+
- "*shit*"
|
330
|
+
- "@$$"
|
331
|
+
- "amcik"
|
332
|
+
- "andskota"
|
333
|
+
- "arse*"
|
334
|
+
- "assrammer"
|
335
|
+
- "ayir"
|
336
|
+
- "bi7ch"
|
337
|
+
- "bitch*"
|
338
|
+
- "bollock*"
|
339
|
+
- "breasts"
|
340
|
+
- "butt-pirate"
|
341
|
+
- "cabron"
|
342
|
+
- "cazzo"
|
343
|
+
- "chraa"
|
344
|
+
- "chuj"
|
345
|
+
- "Cock*"
|
346
|
+
- "cunt*"
|
347
|
+
- "d4mn"
|
348
|
+
- "daygo"
|
349
|
+
- "dego"
|
350
|
+
- "dick*"
|
351
|
+
- "dike*"
|
352
|
+
- "dupa"
|
353
|
+
- "dziwka"
|
354
|
+
- "ejackulate"
|
355
|
+
- "Ekrem*"
|
356
|
+
- "Ekto"
|
357
|
+
- "enculer"
|
358
|
+
- "faen"
|
359
|
+
- "fag*"
|
360
|
+
- "fanculo"
|
361
|
+
- "fanny"
|
362
|
+
- "feces"
|
363
|
+
- "feg"
|
364
|
+
- "Felcher"
|
365
|
+
- "ficken"
|
366
|
+
- "fitt*"
|
367
|
+
- "Flikker"
|
368
|
+
- "foreskin"
|
369
|
+
- "Fotze"
|
370
|
+
- "Fu(*"
|
371
|
+
- "fuk*"
|
372
|
+
- "futkretzn"
|
373
|
+
- "gay"
|
374
|
+
- "gook"
|
375
|
+
- "guiena"
|
376
|
+
- "h0r"
|
377
|
+
- "h4x0r"
|
378
|
+
- "hell"
|
379
|
+
- "helvete"
|
380
|
+
- "hoer*"
|
381
|
+
- "honkey"
|
382
|
+
- "Huevon"
|
383
|
+
- "hui"
|
384
|
+
- "injun"
|
385
|
+
- "jizz"
|
386
|
+
- "kanker*"
|
387
|
+
- "kike"
|
388
|
+
- "klootzak"
|
389
|
+
- "kraut"
|
390
|
+
- "knulle"
|
391
|
+
- "kuk"
|
392
|
+
- "kuksuger"
|
393
|
+
- "Kurac"
|
394
|
+
- "kurwa"
|
395
|
+
- "kusi*"
|
396
|
+
- "kyrpa*"
|
397
|
+
- "lesbo"
|
398
|
+
- "mamhoon"
|
399
|
+
- "masturbat*"
|
400
|
+
- "merd*"
|
401
|
+
- "mibun"
|
402
|
+
- "monkleigh"
|
403
|
+
- "mouliewop"
|
404
|
+
- "muie"
|
405
|
+
- "mulkku"
|
406
|
+
- "muschi"
|
407
|
+
- "nazis"
|
408
|
+
- "nepesaurio"
|
409
|
+
- "nigger*"
|
410
|
+
- "orospu"
|
411
|
+
- "paska*"
|
412
|
+
- "perse"
|
413
|
+
- "picka"
|
414
|
+
- "pierdol*"
|
415
|
+
- "pillu*"
|
416
|
+
- "pimmel"
|
417
|
+
- "piss*"
|
418
|
+
- "pizda"
|
419
|
+
- "poontsee"
|
420
|
+
- "poop"
|
421
|
+
- "porn"
|
422
|
+
- "p0rn"
|
423
|
+
- "pr0n"
|
424
|
+
- "preteen"
|
425
|
+
- "pula"
|
426
|
+
- "pule"
|
427
|
+
- "puta"
|
428
|
+
- "puto"
|
429
|
+
- "qahbeh"
|
430
|
+
- "queef*"
|
431
|
+
- "rautenberg"
|
432
|
+
- "schaffer"
|
433
|
+
- "scheiss*"
|
434
|
+
- "schlampe"
|
435
|
+
- "schmuck"
|
436
|
+
- "screw"
|
437
|
+
- "sh!t*"
|
438
|
+
- "sharmuta"
|
439
|
+
- "sharmute"
|
440
|
+
- "shipal"
|
441
|
+
- "shiz"
|
442
|
+
- "skribz"
|
443
|
+
- "skurwysyn"
|
444
|
+
- "sphencter"
|
445
|
+
- "spic"
|
446
|
+
- "spierdalaj"
|
447
|
+
- "splooge"
|
448
|
+
- "suka"
|
449
|
+
- "b00b*"
|
450
|
+
- "testicle*"
|
451
|
+
- "titt*"
|
452
|
+
- "twat"
|
453
|
+
- "vittu"
|
454
|
+
- "wank*"
|
455
|
+
- "wetback*"
|
456
|
+
- "wichser"
|
457
|
+
- "wop*"
|
458
|
+
- "yed"
|
459
|
+
- "zabourah"
|