Spaces:
Running
Running
Update app.py
Browse files
app.py
CHANGED
@@ -13,6 +13,9 @@ class ONNXInferencePipeline:
|
|
13 |
if hf_token is None:
|
14 |
raise ValueError("HF_TOKEN environment variable is not set.")
|
15 |
|
|
|
|
|
|
|
16 |
# Download files from Hugging Face Hub using the token
|
17 |
self.onnx_path = hf_hub_download(repo_id=repo_id, filename="model.onnx", use_auth_token=hf_token)
|
18 |
self.tokenizer_path = hf_hub_download(repo_id=repo_id, filename="train_bpe_tokenizer.json", use_auth_token=hf_token)
|
@@ -33,6 +36,796 @@ class ONNXInferencePipeline:
|
|
33 |
self.providers = ['CUDAExecutionProvider']
|
34 |
self.session.set_providers(self.providers)
|
35 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
36 |
def preprocess(self, text):
|
37 |
encoding = self.tokenizer.encode(text)
|
38 |
ids = encoding.ids[:self.max_len]
|
@@ -40,6 +833,16 @@ class ONNXInferencePipeline:
|
|
40 |
return np.array(ids + padding, dtype=np.int64).reshape(1, -1)
|
41 |
|
42 |
def predict(self, text):
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
43 |
# Preprocess
|
44 |
input_array = self.preprocess(text)
|
45 |
|
@@ -59,7 +862,8 @@ class ONNXInferencePipeline:
|
|
59 |
return {
|
60 |
'label': class_labels[predicted_class],
|
61 |
'confidence': float(probabilities[0][predicted_class]),
|
62 |
-
'probabilities': probabilities[0].tolist()
|
|
|
63 |
}
|
64 |
|
65 |
# Example usage
|
@@ -69,23 +873,27 @@ if __name__ == "__main__":
|
|
69 |
|
70 |
# Example texts for testing
|
71 |
example_texts = [
|
72 |
-
"You're a worthless piece of garbage who should die"
|
|
|
73 |
]
|
74 |
|
75 |
for text in example_texts:
|
76 |
result = pipeline.predict(text)
|
77 |
print(f"Input: {text}")
|
78 |
-
print(f"Prediction: {result['label']}
|
79 |
-
|
|
|
|
|
|
|
80 |
print("-" * 80)
|
81 |
|
82 |
# Define a function for Gradio to use
|
83 |
def gradio_predict(text):
|
84 |
result = pipeline.predict(text)
|
85 |
-
|
86 |
-
f"Prediction: {result['label']}
|
87 |
-
|
88 |
-
|
89 |
|
90 |
# Create a Gradio interface
|
91 |
iface = gr.Interface(
|
@@ -101,17 +909,17 @@ if __name__ == "__main__":
|
|
101 |
),
|
102 |
examples=[
|
103 |
# Explicitly offensive examples
|
104 |
-
"Congrats, you fuckbrain arsehole, you
|
105 |
-
"You
|
106 |
"Your mother should have done better raising such a useless idiot.",
|
107 |
|
108 |
# Neutral or appropriate examples
|
109 |
-
"Hello HR, I hope this message finds you well. I
|
110 |
-
"Thank you for your time and consideration. Please don
|
111 |
-
"The weather today is lovely, and I
|
112 |
|
113 |
# Mixed examples (some offensive, some neutral)
|
114 |
-
"I appreciate your help, but honestly, you
|
115 |
]
|
116 |
)
|
117 |
|
|
|
13 |
if hf_token is None:
|
14 |
raise ValueError("HF_TOKEN environment variable is not set.")
|
15 |
|
16 |
+
# Load banned keywords list
|
17 |
+
self.banned_keywords = self.load_banned_keywords()
|
18 |
+
|
19 |
# Download files from Hugging Face Hub using the token
|
20 |
self.onnx_path = hf_hub_download(repo_id=repo_id, filename="model.onnx", use_auth_token=hf_token)
|
21 |
self.tokenizer_path = hf_hub_download(repo_id=repo_id, filename="train_bpe_tokenizer.json", use_auth_token=hf_token)
|
|
|
36 |
self.providers = ['CUDAExecutionProvider']
|
37 |
self.session.set_providers(self.providers)
|
38 |
|
39 |
+
def load_banned_keywords(self):
|
40 |
+
# Define a list of banned keywords
|
41 |
+
# This can be loaded from a file or defined directly here
|
42 |
+
# For this example, I'm using a shortened list from your document
|
43 |
+
return [
|
44 |
+
# Original banned keywords
|
45 |
+
"fuck", "shit", "bitch", "cunt", "asshole", "faggot", "nigger", "bastard", "damn", "crap",
|
46 |
+
"arse", "bollocks", "cock", "dick", "piss", "wanker", "whore", "slut", "motherfucker", "son of a bitch",
|
47 |
+
"chink", "gook", "kike", "spic", "wog", "coon", "negro", "tar baby", "bimbo", "skank", "hoe", "twat",
|
48 |
+
"pagal", "mad", "bloody", "blood", "tranny", "dyke", "queer", "fudge packer", "muff diver",
|
49 |
+
"retard", "cripple", "spaz", "mongoloid", "idiot", "rocket", "killing", "pistol",
|
50 |
+
"infidel", "heathen", "blasphemy", "heretic", "islam", "religion", "relegious", "ak47",
|
51 |
+
"kill yourself", "go to hell", "rape", "murder", "terrorist", "terror",
|
52 |
+
"pedo", "nazi", "devil", "shithead", "asswipe", "blast", "islamist",
|
53 |
+
"bomb", "poison", "stab", "shoot", "assassinate", "strangle", "torture", "harm", "injure",
|
54 |
+
"terrorism", "extremist", "radical", "suicide", "explosion", "grenade", "weapon", "gun", "rifle",
|
55 |
+
"ammunition", "bombing", "massacre", "genocide",
|
56 |
+
"threaten", "intimidate", "destroy", "obliterate", "exterminate", "eliminate", "annihilate", "violence",
|
57 |
+
"attack", "raid", "ambush", "hostage", "kidnap",
|
58 |
+
"war", "bloodshed", "slaughter", "brutality", "carnage", "vengeance", "revenge", "punish", "execute",
|
59 |
+
"decapitate", "maim", "hell", "poo", "turd",
|
60 |
+
"douche", "dumbass", "jerk", "prick", "scumbag", "screw", "sodomize",
|
61 |
+
"beaner", "camel jockey", "gypsy", "haji", "jap", "paki", "raghead", "sambo", "wetback", "yid",
|
62 |
+
"gold digger", "hooker", "milf", "porn", "prostitute", "sex worker", "thot",
|
63 |
+
"gender bender", "hermaphrodite", "ladyboy", "she-male", "sissy",
|
64 |
+
"blind", "deaf", "dumb", "lame", "psycho", "schizo", "stupid", "buddha fart", "jesus h christ", "pastafarian",
|
65 |
+
"abuse", "behead", "choke", "crucify", "dismember", "electrocute", "gaslight",
|
66 |
+
"hang", "lynch", "smother", "strangle", "taser",
|
67 |
+
"al qaeda", "isis", "taliban", "chemical weapon", "biological weapon", "nuclear bomb", "dirty bomb",
|
68 |
+
"suicide vest", "car bomb", "drone strike",
|
69 |
+
"burn", "castrate", "cutthroat", "gang bang", "gangster", "hitman", "mafia", "mob", "noose",
|
70 |
+
"poison gas", "sniper", "vengeful",
|
71 |
+
"anarchy", "apocalypse", "chaos", "doom", "evil", "hate", "insanity", "madness", "plague", "riot",
|
72 |
+
"slaughterhouse", "zombie", "bund", "gand", "gandu", "chod", "behenchod", "behen chod", "lora", "lund", "loda",
|
73 |
+
# Additional banned keywords from the new list
|
74 |
+
"2g1c", "2 girls 1 cup", "acrotomophilia", "alabama hot pocket", "alaskan pipeline", "anal", "anilingus", "anus",
|
75 |
+
"arsehole", "ass", "assmunch", "auto erotic", "autoerotic", "babeland", "baby batter", "baby juice",
|
76 |
+
"ball gag", "ball gravy", "ball kicking", "ball licking", "ball sack", "ball sucking", "bangbros",
|
77 |
+
"bareback", "barely legal", "barenaked", "bastardo", "bastinado", "bbw", "bdsm", "beaver cleaver", "beaver lips",
|
78 |
+
"bestiality", "bi curious", "big black", "big breasts", "big knockers", "big tits", "bimbos", "birdlock",
|
79 |
+
"black cock", "blonde action", "blonde on blonde action", "blowjob", "blow job", "blow your load",
|
80 |
+
"blue waffle", "blumpkin", "bondage", "boner", "boob", "boobs", "booty call", "brown showers",
|
81 |
+
"brunette action", "bukkake", "bulldyke", "bullet vibe", "bung hole", "bunghole", "busty", "butt",
|
82 |
+
"buttcheeks", "butthole", "camel toe", "camgirl", "camslut", "camwhore", "carpet muncher", "carpetmuncher",
|
83 |
+
"chocolate rosebuds", "circlejerk", "cleveland steamer", "clit", "clitoris", "clover clamps", "clusterfuck",
|
84 |
+
"cocks", "coprolagnia", "coprophilia", "cornhole", "creampie", "cum", "cumming", "cunnilingus",
|
85 |
+
"cunt", "darkie", "date rape", "daterape", "deep throat", "deepthroat", "dendrophilia", "dick", "dildo",
|
86 |
+
"dirty pillows", "dirty sanchez", "doggie style", "doggiestyle", "doggy style", "doggystyle", "dog style",
|
87 |
+
"dolcett", "domination", "dominatrix", "dommes", "donkey punch", "double dong", "double penetration",
|
88 |
+
"dp action", "dry hump", "dvda", "eat my ass", "ecchi", "ejaculation", "erotic", "erotism", "escort",
|
89 |
+
"ethical slut", "eunuch", "faggot", "fecal", "felch", "fellatio", "feltch", "female squirting", "femdom",
|
90 |
+
"figging", "fingerbang", "fingering", "fisting", "foot fetish", "footjob", "frotting", "fuck buttons",
|
91 |
+
"fudge packer", "fudgepacker", "futanari", "gay sex", "genitals", "giant cock", "girl on", "girl on top",
|
92 |
+
"girls gone wild", "goatcx", "goatse", "gokkun", "gold digger", "golden shower", "goo girl", "goodpoop",
|
93 |
+
"gook", "goregasm", "grenade", "grope", "group sex", "gun", "guro", "gypsy", "hand job", "handjob",
|
94 |
+
"hard core", "hardcore", "hentai", "homoerotic", "honkey", "hooker", "hostage", "hot carl",
|
95 |
+
"hot chick", "how to kill", "how to murder", "huge fat", "humping", "jack off", "jail bait", "jailbait",
|
96 |
+
"jap", "jelly donut", "jerk", "jerk off", "jesus h christ", "jigaboo", "jiggaboo", "jiggerboo", "jizz",
|
97 |
+
"juggs", "kidnap", "kike", "kill yourself", "killing", "kinbaku", "kinkster", "kinky", "knobbing",
|
98 |
+
"ladyboy", "leather restraint", "leather straight jacket", "lemon party", "lolita", "lora", "lovemaking",
|
99 |
+
"make me come", "male squirting", "massacre", "masturbate", "menage a trois", "milf", "mob", "motherfucker",
|
100 |
+
"mound of venus", "mr hands", "muff diver", "muffdiving", "murder", "nambla", "nawashi", "nazi", "negro",
|
101 |
+
"nigger", "nimphomania", "nipple", "noose", "nuclear bomb", "obliterate", "pagal", "paki",
|
102 |
+
"pastafarian", "pedo", "piss", "pistol", "plague", "poison", "poison gas", "poo", "porn", "prick",
|
103 |
+
"prostitute", "psycho", "punish", "queer", "radical", "raghead", "raid", "rape", "relegious", "religion",
|
104 |
+
"retard", "revenge", "rifle", "riot", "rocket", "sambo", "schizo", "screw", "scumbag", "sex worker",
|
105 |
+
"she-male", "shit", "shithead", "shoot", "sissy", "skank", "slaughter", "slaughterhouse", "slut",
|
106 |
+
"smother", "sniper", "sodomize", "son of a bitch", "spaz", "spic", "stab", "strangle", "stupid",
|
107 |
+
"suicide", "suicide vest", "taliban", "tar baby", "taser", "terror", "terrorism", "terrorist", "thot",
|
108 |
+
"threaten", "torture", "tranny", "turd", "twat", "vengeance", "vengeful", "violence", "wanker",
|
109 |
+
"war", "weapon", "wetback", "whore", "wog", "yid", "zombie",
|
110 |
+
# Additional variations for "stupid"
|
111 |
+
"stupid", "sstupid", "stupidd", "stuupid", "stuppidd", "sttupid", "stupiid", "sttuppid",
|
112 |
+
# Additional variations for "idiot"
|
113 |
+
"idiot", "idiott", "idioot", "idit", "id0t",
|
114 |
+
# Additional variations for "fuck"
|
115 |
+
"fuck", "f*ck", "f**ck", "fck", "fukk", "fucc", "f u c k",
|
116 |
+
# Additional variations for "shit"
|
117 |
+
"shit", "sh1t", "sh!t", "sht", "shiit",
|
118 |
+
# Additional variations for "bitch"
|
119 |
+
"bitch", "btch", "b1tch", "biatch", "b*tch",
|
120 |
+
# Additional variations for "asshole"
|
121 |
+
"asshole", "ashole", "asshol", "a$$hole", "a**hole",
|
122 |
+
# Additional variations for "dumb"
|
123 |
+
"dumb", "dumm", "dum", "dumbass", "dumass",
|
124 |
+
# Additional variations for "faggot"
|
125 |
+
"faggot", "fag", "fagg0t", "faaggot",
|
126 |
+
# Additional variations for "nigger"
|
127 |
+
"nigger", "nigga", "niggar", "niggah", "n*gger",
|
128 |
+
# Additional variations for "cunt"
|
129 |
+
"cunt", "c*nt", "c0nt",
|
130 |
+
# Additional variations for "whore"
|
131 |
+
"whore", "wh0re", "w*h*re", "whoore",
|
132 |
+
# Additional variations for "slut"
|
133 |
+
"slut", "sluut", "sllut", "slutty", "slu*t",
|
134 |
+
# Additional variations for "bastard"
|
135 |
+
"bastard", "basturd", "bastrd", "bastar",
|
136 |
+
# Additional variations for "dick"
|
137 |
+
"dick", "d1ck", "d!ck", "dicc", "d!k",
|
138 |
+
# Additional variations for "cock"
|
139 |
+
"cock", "c0ck", "c*ck",
|
140 |
+
# Additional variations for "ass"
|
141 |
+
"ass", "a$$", "azz", "a s s", "a$$s", "a55",
|
142 |
+
# Additional banned keywords from extended lists
|
143 |
+
"wop", "dago", "cracker", "mick", "libtard",
|
144 |
+
"asshat", "dickhead", "fuckhead", "fuckwit", "shithead", "dumbfuck", "jackass",
|
145 |
+
"assclown", "dickwad", "scumbucket", "prickface", "cocknose", "pissflap",
|
146 |
+
"cocksucker", "cum dumpster", "cum guzzler", "cum slut", "suck my dick", "suck my cock",
|
147 |
+
"pussy-whipped", "whorebag", "snowflake", "chav", "Karen", "fascist", "chod", "fukr", "idiott",
|
148 |
+
# New keywords from the additional list
|
149 |
+
"16+", "18+", "a$$", "alcohol", "amerifag",
|
150 |
+
"assault", "b!tch", "bstard", "burn yourself", "c!nt", "christfucker", "cnt", "cocaine",
|
151 |
+
"cracker", "creep", "cut yourself", "d!ck", "die in a hole", "die now", "dipshit", "drink bleach",
|
152 |
+
"drop dead", "dumbfuck", "dyke", "explosion", "fag", "fck", "fuck off", "fucker", "fucking idiot",
|
153 |
+
"fuk", "genocide", "get drunk", "go hang yourself", "gook", "gypsy", "handjob", "heroin",
|
154 |
+
"ho", "hymie", "i will ban you", "i will bomb the place", "i will fuck you", "i will kill you",
|
155 |
+
"jew", "jewboy", "kike", "kill", "kill yourself", "loser", "marijuana", "massacre", "meth",
|
156 |
+
"molest", "moslemfucker", "murder", "naked", "obongo", "orgy", "overdose", "p0rn", "penis",
|
157 |
+
"perv", "pervert", "rape", "rape you", "rat poison", "retard", "s3x", "sandnigger",
|
158 |
+
"screw you", "scumbag", "secks", "self-harm", "sex offender", "sexual predator", "sx",
|
159 |
+
"take pills", "terrorist", "tits", "tranny", "twat", "vag", "vagina", "vodka", "x", "xxx",
|
160 |
+
"you will get raped", "you're a piece of shit", "you're banned forever", "you're crazy",
|
161 |
+
"you're hallucinating", "you're such a cunt", "you're worthless",
|
162 |
+
# New Sexually Explicit keywords and variations
|
163 |
+
"p0rn", "nu|)e", "nud3", "5ex", "$ex", "s3x", "hardc0re", "h@rdcore", "hardcor3", "#ardcore",
|
164 |
+
"har|)core", "hard(ore", "h4rdcore", "adu1t", "adul7", "adu|t", "@dult", "adult", "4dult",
|
165 |
+
"a|)ult", "erot1c", "erot|c", "erot!c", "ero7ic", "eroti(", "er0tic", "3rotic", "str!p",
|
166 |
+
"s7rip", "str1p", "$trip", "strip", "str|p", "5trip", "c@mgirl", "camg|rl", "camg1rl",
|
167 |
+
"(amgirl", "cam9irl", "c4mgirl", "camgir1", "camgir|", "camg!rl", "feti$h", "fet1sh", "feti5h",
|
168 |
+
"fetis#", "f3tish", "fe7ish", "fetish", "fet!sh", "fet|sh",
|
169 |
+
"orgy", "or9y", "0rgy", "3scort", "escor7", "e$cort", "es(ort", "esc0rt", "e5cort", "escort",
|
170 |
+
"#ookup", "h00kup", "hookup", "8dsm", "bd5m", "bd$m", "bdsm", "b|)sm", "masturbat3", "m@sturb@te",
|
171 |
+
"ma$turbate", "m4sturb4te", "ma5turbate", "mas7urba7e", "mastur8ate",
|
172 |
+
"inc3st", "|ncest", "in(est", "ince$t", "ince5t", "!ncest", "inces7", "1ncest",
|
173 |
+
"ta8oo", "tab00", "t@boo", "taboo", "t4boo", "7aboo",
|
174 |
+
"blowjob", "bl0wj0b", "8lowjo8", "b|owjob", "b1owjob", "cumsh0t", "cums#ot", "cum5hot",
|
175 |
+
"cumshot", "cum$hot", "(umshot", "cumsho7", "deepthr0at", "deept#roat", "d33pthroat",
|
176 |
+
"deepthro@t", "deepthro4t", "|)eepthroat", "deep7hroa7",
|
177 |
+
# New Sexual Harassment keywords and variations
|
178 |
+
"perv", "p3rv", "(reep", "creep", "cr33p", "mo1est", "molest", "mole$t", "m0lest",
|
179 |
+
"mo|est", "mol3st", "moles7", "mole5t", "gr0pe", "9rope", "grop3", "grope", "h@r@ss",
|
180 |
+
"harass", "hara55", "h4r4ss", "#arass", "hara$$", "c4tc4ll", "ca7call", "catca11",
|
181 |
+
"catca||", "c@tc@ll", "(at(all", "catcall", "pre|)ator", "pred4tor", "pred@tor", "preda7or",
|
182 |
+
"pr3dator", "predat0r", "predator", "sta1ker", "st@lker", "stalk3r", "$talker", "st4lker",
|
183 |
+
"s7alker", "5talker", "stalker", "sta|ker", "m1sogyn1st", "misogynis7", "misogynist",
|
184 |
+
"m|sogyn|st", "m!sogyn!st", "mi$ogyni$t", "miso9ynist", "mis0gynist", "mi5ogyni5t",
|
185 |
+
"exp0se", "expose", "3xpos3", "expo$e", "expo5e",
|
186 |
+
# New Dangerous Content keywords and variations
|
187 |
+
"b0mb", "8om8", "k!ll", "k1ll", "ki||", "ki11", "k|ll", "kill", "atta(k", "a77ack",
|
188 |
+
"@tt@ck", "4tt4ck", "terr0r", "t3rror", "7error", "shoo7", "sh00t", "$hoot", "5hoot",
|
189 |
+
"s#oot", "$tab", "st4b", "st@b", "5tab", "sta8", "s7ab", "exp|osive", "expl0sive",
|
190 |
+
"explosive", "3xplosiv3", "explos!ve", "explos1ve", "explo5ive", "explos|ve", "explo$ive",
|
191 |
+
"exp1osive", "assass|nate", "assassinat3", "assass!nate", "assass1nate", "a55a55inate",
|
192 |
+
"assassina7e", "assassinate", "@ss@ssin@te", "4ss4ssin4te", "a$$a$$inate", "massacr3",
|
193 |
+
"massa(re", "ma$$acre", "m4ss4cre", "m@ss@cre", "ma55acre", "massacre", "$uicide",
|
194 |
+
"suicide", "su1c1de", "suicid3", "su|c|de", "sui(ide", "suici|)e", "5uicide", "su!c!de",
|
195 |
+
"#omicide", "hom!c!de", "hom|c|de", "homicid3", "homicide", "h0micide", "homi(ide",
|
196 |
+
"homici|)e", "hom1c1de", "7or7ure", "torture", "tortur3", "t0rture", "ra|)ical", "r4dic4l",
|
197 |
+
"rad1cal", "radica1", "radica|", "rad!cal", "rad|cal", "radical", "radi(al", "r@dic@l",
|
198 |
+
"beheadin9", "8eheading", "behea|)ing", "b3h3ading", "behead|ng", "beheading", "behead!ng",
|
199 |
+
"be#eading", "behe4ding", "behe@ding", "behead1ng", "extrem|st", "extrem!st", "3xtr3mist",
|
200 |
+
"extremi$t", "ex7remis7", "extremist", "extrem1st", "extremi5t", "r|ot", "r1ot", "rio7",
|
201 |
+
"r!ot", "ri0t", "traff|ck|ng", "tr@fficking", "traff!ck!ng", "traff1ck1ng", "7rafficking",
|
202 |
+
"tr4fficking", "traffi(king", "trafficking", "traffickin9", "k|dnap", "ki|)nap", "kidn@p",
|
203 |
+
"kidn4p", "k!dnap", "k1dnap", "arson", "ar5on", "ar$on", "4rson", "ars0n",
|
204 |
+
# New Harmful Content keywords and variations
|
205 |
+
"s3lf-harm", "se|f-harm", "self-h4rm", "self-h@rm", "5elf-harm", "self-#arm", "$elf-harm",
|
206 |
+
"se1f-harm", "self-harm", "cutting", "cuttin9", "cutt!ng", "(utting", "cutt1ng", "cu77ing",
|
207 |
+
"cutt|ng", "burn1ng", "burnin9", "burn!ng", "8urning", "burn|ng", "burning",
|
208 |
+
"pa!n", "p4in", "p@in", "pain", "pa1n", "pa|n", "s7arva7ion", "5tarvation",
|
209 |
+
"st4rv4tion", "starvat1on", "starvat!on", "starvation", "starvat|on", "starvati0n",
|
210 |
+
"$tarvation", "st@rv@tion", "overdose", "0verd0se", "ov3rdos3", "over|)ose", "overdo5e",
|
211 |
+
"overdo$e", "|)epresse|)", "d3pr3ss3d", "depre55ed", "depressed", "depre$$ed", "d|e",
|
212 |
+
"die", "d!e", "di3", "|)ie", "d1e", "jump", "hang", "#ang", "h4ng", "han9", "h@ng",
|
213 |
+
"poison", "po!son", "p0is0n", "poi5on", "poi$on", "po1son", "po|son", "(hloroform", "chloroform",
|
214 |
+
"ch|oroform", "ch1oroform", "c#loroform", "chl0r0f0rm", "drug abu5e", "dru9 abuse", "drug abuse",
|
215 |
+
"|)rug abuse", "drug abu$e", "drug 4buse", "drug abus3", "drug @buse", "drug a8use", "@ddict",
|
216 |
+
"4ddict", "add!ct", "addict", "a|)|)ict", "addic7", "add1ct", "add|ct", "addi(t", "opioid",
|
217 |
+
"0pi0id", "op1o1d", "op|o|d", "opioi|)", "op!o!d", "fentanyl", "f3ntanyl", "fentany|",
|
218 |
+
"fen7anyl", "fent@nyl", "fent4nyl", "fentany1", "meth", "met#", "m3th", "me7h", "coca1ne",
|
219 |
+
"cocain3", "cocaine", "coc4ine", "(o(aine", "coc@ine", "coca!ne", "coca|ne", "c0caine",
|
220 |
+
"h3roin", "her0in", "heroin", "#eroin", "hero|n", "hero!n", "hero1n",
|
221 |
+
# New Hate Speech keywords and variations
|
222 |
+
"n@zi", "naz1", "naz!", "nazi", "na2i", "naz|", "n4zi", "kkk", "suprema(y", "$upremacy",
|
223 |
+
"suprem4cy", "suprem@cy", "supr3macy", "5upremacy", "supremacy", "gen0cide", "genoc1de",
|
224 |
+
"genoci|)e", "genocide", "genoc|de", "geno(ide", "9enocide", "g3nocid3", "genoc!de", "big0t",
|
225 |
+
"bigot", "b|got", "bi9ot", "bigo7", "b!got", "8igot", "b1got", "#omop#obe", "homophobe",
|
226 |
+
"homophob3", "homopho8e", "h0m0ph0be", "xenophobe", "xenopho8e", "xenop#obe", "x3nophob3",
|
227 |
+
"xen0ph0be", "antifa", "bootlicker", "tankie", "baiter", "griefer", "kek", "pepe", "zoomer",
|
228 |
+
# New Slang Abuses & Offensive Insults
|
229 |
+
"bit(h", "8itch", "b|tch", "b1tch", "bi7ch", "bastar|", "b@st@rd", "ba5tard", "bas7ard",
|
230 |
+
"ba$tard", "b4st4rd", "8astard", "assho1e", "assho|e", "a$$hole", "ass#ole", "asshol3", "4sshole",
|
231 |
+
"a55hole", "assh0le", "pr1ck", "pr|ck", "pr!ck", "prick", "|)umbass", "dumba55", "dumb4ss",
|
232 |
+
"dumba$$", "dum8ass", "dumb@ss", "retar|", "r3tard", "re7ard", "ret@rd", "ret4rd", "|)ipshit",
|
233 |
+
"d|psh|t", "dipshi7", "dip5hit", "dips#it", "d!psh!t", "dipshit", "dip$hit", "d1psh1t",
|
234 |
+
"j@ck@ss", "wank3r", "w@nker", "w4nker", "tw4t", "tw@t", "7wa7", "shi7head", "shithe@d",
|
235 |
+
"shith3ad", "5hithead", "s#it#ead", "sh!thead", "sh1thead", "shithea|", "shithe4d", "$hithead",
|
236 |
+
# New General Abuses
|
237 |
+
"|d|ot", "idi0t", "1d1ot", "idio7", "idiot", "i|)iot", "!d!ot", "m0r0n", "moron", "lo5er",
|
238 |
+
"|oser", "1oser", "loser", "l0ser", "los3r", "5cum", "s(um", "$cum", "worthl3ss", "wort#less",
|
239 |
+
"worth|ess", "worthle$$", "wor7hless", "worthless", "worthle55", "worth1ess", "w0rthless",
|
240 |
+
# New additional keywords from your latest list
|
241 |
+
"16+", "18+", "alcohol", "amerifag", "assault", "b!tch", "bstard", "burn yourself", "c!nt",
|
242 |
+
"christfucker", "cnt", "cocaine", "creep", "cut yourself", "die in a hole", "die now", "dipshit",
|
243 |
+
"drink bleach", "drop dead", "dumbfuck", "fuck off", "fucker", "fucking idiot", "genocide",
|
244 |
+
"get drunk", "go hang yourself", "gook", "hymie", "i will ban you", "i will bomb the place",
|
245 |
+
"i will fuck you", "i will kill you", "jew", "jewboy", "kike", "kill", "kill yourself",
|
246 |
+
"loser", "marijuana", "massacre", "meth", "molest", "moslemfucker", "murder", "naked", "obongo",
|
247 |
+
"overdose", "penis", "perv", "pervert", "rape you", "rat poison", "s3x", "sandnigger",
|
248 |
+
"screw you", "secks", "self-harm", "sex offender", "sexual predator", "sx", "take pills",
|
249 |
+
"terrorist", "tits", "tranny", "twat", "vag", "vagina", "vodka", "x", "xxx",
|
250 |
+
"you will get raped", "you're a piece of shit", "you're banned forever", "you're crazy",
|
251 |
+
"you're hallucinating", "you're such a cunt", "you're worthless",
|
252 |
+
# New Sexually Explicit keywords and variations
|
253 |
+
"p0rn", "nu|)e", "nud3", "5ex", "$ex", "s3x", "hardc0re", "h@rdcore", "hardcor3", "#ardcore",
|
254 |
+
"har|)core", "hard(ore", "h4rdcore", "adu1t", "adul7", "adu|t", "@dult", "adult", "4dult",
|
255 |
+
"a|)ult", "erot1c", "erot|c", "erot!c", "ero7ic", "eroti(", "er0tic", "3rotic", "str!p",
|
256 |
+
"s7rip", "str1p", "$trip", "strip", "str|p", "5trip", "c@mgirl", "camg|rl", "camg1rl",
|
257 |
+
"(amgirl", "cam9irl", "c4mgirl", "camgir1", "camgir|", "camg!rl", "feti$h", "fet1sh", "feti5h",
|
258 |
+
"fetis#", "f3tish", "fe7ish", "fetish", "fet!sh", "fet|sh",
|
259 |
+
# New Sexual Harassment keywords and variations
|
260 |
+
"perv", "p3rv", "(reep", "creep", "cr33p", "mo1est", "molest", "mole$t", "m0lest",
|
261 |
+
"mo|est", "mol3st", "moles7", "mole5t", "gr0pe", "9rope", "grop3", "grope", "h@r@ss",
|
262 |
+
"harass", "hara55", "h4r4ss", "#arass", "hara$$", "c4tc4ll", "ca7call", "catca11",
|
263 |
+
"catca||", "c@tc@ll", "(at(all", "catcall", "pre|)ator", "pred4tor", "pred@tor", "preda7or",
|
264 |
+
"pr3dator", "predat0r", "predator", "sta1ker", "st@lker", "stalk3r", "$talker", "st4lker",
|
265 |
+
"s7alker", "5talker", "stalker", "sta|ker", "m1sogyn1st", "misogynis7", "misogynist", "m|sogyn|st",
|
266 |
+
"m!sogyn!st", "mi$ogyni$t", "miso9ynist", "mis0gynist", "mi5ogyni5t",
|
267 |
+
"exp0se", "expose", "3xpos3", "expo$e", "expo5e",
|
268 |
+
# New Dangerous Content keywords and variations
|
269 |
+
"b0mb", "8om8", "k!ll", "k1ll", "ki||", "ki11", "k|ll", "kill", "atta(k", "a77ack",
|
270 |
+
"@tt@ck", "4tt4ck", "terr0r", "t3rror", "7error", "shoo7", "sh00t", "$hoot", "5hoot",
|
271 |
+
"s#oot", "$tab", "st4b", "st@b", "5tab", "sta8", "s7ab", "exp|osive", "expl0sive",
|
272 |
+
"explosive", "3xplosiv3", "explos!ve", "explos1ve", "explo5ive", "explos|ve", "explo$ive",
|
273 |
+
"exp1osive", "assass|nate", "assassinat3", "assass!nate", "assass1nate", "a55a55inate",
|
274 |
+
"assassina7e", "assassinate", "@ss@ssin@te", "4ss4ssin4te", "a$$a$$inate", "massacr3",
|
275 |
+
"massa(re", "ma$$acre", "m4ss4cre", "m@ss@cre", "ma55acre", "massacre", "$uicide", "suicide",
|
276 |
+
"su1c1de", "suicid3", "su|c|de", "sui(ide", "suici|)e", "5uicide", "su!c!de", "#omicide",
|
277 |
+
"hom!c!de", "hom|c|de", "homicid3", "homicide", "h0micide", "homi(ide", "homici|)e", "hom1c1de",
|
278 |
+
"7or7ure", "torture", "tortur3", "t0rture", "ra|)ical", "r4dic4l", "rad1cal", "radica1",
|
279 |
+
"radica|", "rad!cal", "rad|cal", "radical", "radi(al", "r@dic@l", "beheadin9",
|
280 |
+
"8eheading", "behea|)ing", "b3h3ading", "behead|ng", "beheading", "behead!ng",
|
281 |
+
"be#eading", "behe4ding", "behe@ding", "behead1ng", "extrem|st", "extrem!st", "3xtr3mist",
|
282 |
+
"extremi$t", "ex7remis7", "extremist", "extrem1st", "extremi5t", "r|ot", "r1ot", "rio7",
|
283 |
+
"r!ot", "ri0t", "traff|ck|ng", "tr@fficking", "traff!ck!ng", "traff1ck1ng", "7rafficking",
|
284 |
+
"tr4fficking", "traffi(king", "trafficking", "traffickin9", "k|dnap", "ki|)nap", "kidn@p",
|
285 |
+
"kidn4p", "k!dnap", "k1dnap", "arson", "ar5on", "ar$on", "4rson", "ars0n",
|
286 |
+
# New Harmful Content keywords and variations
|
287 |
+
"s3lf-harm", "se|f-harm", "self-h4rm", "self-h@rm", "5elf-harm", "self-#arm", "$elf-harm",
|
288 |
+
"se1f-harm", "self-harm", "cutting", "cuttin9", "cutt!ng", "(utting", "cutt1ng", "cu77ing",
|
289 |
+
"cutt|ng", "burn1ng", "burnin9", "burn!ng", "8urning", "burn|ng", "burning",
|
290 |
+
"pa!n", "p4in", "p@in", "pain", "pa1n", "pa|n", "s7arva7ion", "5tarvation",
|
291 |
+
"st4rv4tion", "starvat1on", "starvat!on", "starvation", "starvat|on", "starvati0n",
|
292 |
+
"$tarvation", "st@rv@tion", "overdose", "0verd0se", "ov3rdos3", "over|)ose", "overdo5e",
|
293 |
+
"overdo$e", "|)epresse|)", "d3pr3ss3d", "depre55ed", "depressed", "depre$$ed", "d|e",
|
294 |
+
"die", "d!e", "di3", "|)ie", "d1e", "jump", "hang", "#ang", "h4ng", "han9", "h@ng",
|
295 |
+
"poison", "po!son", "p0is0n", "poi5on", "poi$on", "po1son", "po|son", "(hloroform", "chloroform",
|
296 |
+
"ch|oroform", "ch1oroform", "c#loroform", "chl0r0f0rm", "drug abu5e", "dru9 abuse", "drug abuse",
|
297 |
+
"|)rug abuse", "drug abu$e", "drug 4buse", "drug abus3", "drug @buse", "drug a8use", "@ddict",
|
298 |
+
"4ddict", "add!ct", "addict", "a|)|)ict", "addic7", "add1ct", "add|ct", "addi(t", "opioid",
|
299 |
+
"0pi0id", "op1o1d", "op|o|d", "opioi|)", "op!o!d", "fentanyl", "f3ntanyl", "fentany|",
|
300 |
+
"fen7anyl", "fent@nyl", "fent4nyl", "fentany1", "meth", "met#", "m3th", "me7h", "coca1ne",
|
301 |
+
"cocain3", "cocaine", "coc4ine", "(o(aine", "coc@ine", "coca!ne", "coca|ne", "c0caine",
|
302 |
+
"h3roin", "her0in", "heroin", "#eroin", "hero|n", "hero!n", "hero1n",
|
303 |
+
# New Hate Speech keywords and variations
|
304 |
+
"n@zi", "naz1", "naz!", "nazi", "na2i", "naz|", "n4zi", "kkk", "suprema(y", "$upremacy",
|
305 |
+
"suprem4cy", "suprem@cy", "supr3macy", "5upremacy", "supremacy", "gen0cide", "genoc1de",
|
306 |
+
"genoci|)e", "genocide", "genoc|de", "geno(ide", "9enocide", "g3nocid3", "genoc!de", "big0t",
|
307 |
+
"bigot", "b|got", "bi9ot", "bigo7", "b!got", "8igot", "b1got", "#omop#obe", "homophobe",
|
308 |
+
"homophob3", "homopho8e", "h0m0ph0be", "xenophobe", "xenopho8e", "xenop#obe", "x3nophob3",
|
309 |
+
"xen0ph0be", "antifa", "bootlicker", "tankie", "baiter", "griefer", "kek", "pepe", "zoomer",
|
310 |
+
# New Slang Abuses & Offensive Insults
|
311 |
+
"bit(h", "8itch", "b|tch", "b1tch", "bi7ch", "bastar|", "b@st@rd", "ba5tard", "bas7ard",
|
312 |
+
"ba$tard", "b4st4rd", "8astard", "assho1e", "assho|e", "a$$hole", "ass#ole", "asshol3", "4sshole",
|
313 |
+
"a55hole", "assh0le", "pr1ck", "pr|ck", "pr!ck", "prick", "|)umbass", "dumba55", "dumb4ss",
|
314 |
+
"dumba$$", "dum8ass", "dumb@ss", "retar|", "r3tard", "re7ard", "ret@rd", "ret4rd", "|)ipshit",
|
315 |
+
"d|psh|t", "dipshi7", "dip5hit", "dips#it", "d!psh!t", "dipshit", "dip$hit", "d1psh1t",
|
316 |
+
"j@ck@ss", "wank3r", "w@nker", "w4nker", "tw4t", "tw@t", "7wa7", "shi7head", "shithe@d",
|
317 |
+
"shith3ad", "5hithead", "s#it#ead", "sh!thead", "sh1thead", "shithea|", "shithe4d", "$hithead",
|
318 |
+
# New General Abuses
|
319 |
+
"|d|ot", "idi0t", "1d1ot", "idio7", "idiot", "i|)iot", "!d!ot", "m0r0n", "moron", "lo5er",
|
320 |
+
"|oser", "1oser", "loser", "l0ser", "los3r", "5cum", "s(um", "$cum", "worthl3ss", "wort#less",
|
321 |
+
"worth|ess", "worthle$$", "wor7hless", "worthless", "worthle55", "worth1ess", "w0rthless",
|
322 |
+
# Additional new keywords from the latest list
|
323 |
+
"16+", "18+", "alcohol", "amerifag", "assault", "b!tch", "bstard", "burn yourself", "c!nt",
|
324 |
+
"christfucker", "cnt", "cocaine", "creep", "cut yourself", "die in a hole", "die now", "dipshit",
|
325 |
+
"drink bleach", "drop dead", "dumbfuck", "fuck off", "fucker", "fucking idiot", "fuk", "get drunk",
|
326 |
+
"go hang yourself", "hymie", "i will ban you", "i will bomb the place", "i will fuck you",
|
327 |
+
"i will kill you", "jew", "jewboy", "moslemfucker", "marijuana", "meth", "molest", "naked",
|
328 |
+
"obongo", "overdose", "perv", "pervert", "rape you", "rat poison", "screw you", "secks",
|
329 |
+
"self-harm", "sex offender", "sexual predator", "sx", "take pills", "terrorist", "tits", "twat",
|
330 |
+
"vag", "vodka", "x", "you will get raped", "you're a piece of shit", "you're banned forever",
|
331 |
+
"you're crazy", "you're hallucinating", "you're such a cunt", "you're worthless",
|
332 |
+
# New Sexually Explicit keywords and variations (second block)
|
333 |
+
"p0rn", "nu|)e", "nud3", "5ex", "$ex", "s3x", "xxx", "hardc0re", "h@rdcore", "hardcor3", "#ardcore",
|
334 |
+
"har|)core", "hard(ore", "h4rdcore", "adu1t", "adul7", "adu|t", "@dult", "adult", "4dult",
|
335 |
+
"a|)ult", "erot1c", "erot|c", "erot!c", "ero7ic", "eroti(", "er0tic", "3rotic", "str!p",
|
336 |
+
"s7rip", "str1p", "$trip", "strip", "str|p", "5trip", "c@mgirl", "camg|rl", "camg1rl",
|
337 |
+
"(amgirl", "cam9irl", "c4mgirl", "camgir1", "camgir|", "camg!rl", "feti$h", "fet1sh", "feti5h",
|
338 |
+
"fetis#", "f3tish", "fe7ish", "fetish", "fet!sh", "fet|sh",
|
339 |
+
# New Sexual Harassment keywords and variations (second block)
|
340 |
+
"perv", "p3rv", "(reep", "creep", "cr33p", "mo1est", "molest", "mole$t", "m0lest",
|
341 |
+
"mo|est", "mol3st", "moles7", "mole5t", "gr0pe", "9rope", "grop3", "grope", "h@r@ss",
|
342 |
+
"harass", "hara55", "h4r4ss", "#arass", "hara$$", "c4tc4ll", "ca7call", "catca11", "catca||",
|
343 |
+
"c@tc@ll", "(at(all", "catcall", "pre|)ator", "pred4tor", "pred@tor", "preda7or", "pr3dator",
|
344 |
+
"predat0r", "predator", "sta1ker", "st@lker", "stalk3r", "$talker", "st4lker", "s7alker",
|
345 |
+
"5talker", "stalker", "sta|ker", "m1sogyn1st", "misogynis7", "misogynist", "m|sogyn|st",
|
346 |
+
"m!sogyn!st", "mi$ogyni$t", "miso9ynist", "mis0gynist", "mi5ogyni5t", "exp0se", "expose",
|
347 |
+
"3xpos3", "expo$e", "expo5e",
|
348 |
+
# New Dangerous Content keywords and variations (second block)
|
349 |
+
"b0mb", "8om8", "k!ll", "k1ll", "ki||", "ki11", "k|ll", "kill", "atta(k", "a77ack",
|
350 |
+
"@tt@ck", "4tt4ck", "terr0r", "t3rror", "7error", "shoo7", "sh00t", "$hoot", "5hoot",
|
351 |
+
"s#oot", "$tab", "st4b", "st@b", "5tab", "sta8", "s7ab", "exp|osive", "expl0sive",
|
352 |
+
"explosive", "3xplosiv3", "explos!ve", "explos1ve", "explo5ive", "explos|ve", "explo$ive",
|
353 |
+
"exp1osive", "assass|nate", "assassinat3", "assass!nate", "assass1nate", "a55a55inate",
|
354 |
+
"assassina7e", "assassinate", "@ss@ssin@te", "4ss4ssin4te", "a$$a$$inate", "massacr3", "massa(re",
|
355 |
+
"ma$$acre", "m4ss4cre", "m@ss@cre", "ma55acre", "massacre", "$uicide", "suicide", "su1c1de",
|
356 |
+
"suicid3", "su|c|de", "sui(ide", "suici|)e", "5uicide", "su!c!de", "#omicide", "hom!c!de",
|
357 |
+
"hom|c|de", "homicid3", "homicide", "h0micide", "homi(ide", "homici|)e", "hom1c1de", "7or7ure",
|
358 |
+
"torture", "tortur3", "t0rture", "ra|)ical", "r4dic4l", "rad1cal", "radica1", "radica|",
|
359 |
+
"rad!cal", "rad|cal", "radical", "radi(al", "r@dic@l", "beheadin9", "8eheading",
|
360 |
+
"behea|)ing", "b3h3ading", "behead|ng", "beheading", "behead!ng", "be#eading", "behe4ding",
|
361 |
+
"behe@ding", "behead1ng", "extrem|st", "extrem!st", "3xtr3mist", "extremi$t", "ex7remis7",
|
362 |
+
"extremist", "extrem1st", "extremi5t", "r|ot", "r1ot", "rio7", "r!ot", "ri0t", "traff|ck|ng",
|
363 |
+
"tr@fficking", "traff!ck!ng", "traff1ck1ng", "7rafficking", "tr4fficking", "traffi(king",
|
364 |
+
"trafficking", "traffickin9", "k|dnap", "ki|)nap", "kidn@p", "kidn4p", "k!dnap", "k1dnap",
|
365 |
+
"arson", "ar5on", "ar$on", "4rson", "ars0n",
|
366 |
+
# New Harmful Content keywords and variations (second block)
|
367 |
+
"s3lf-harm", "se|f-harm", "self-h4rm", "self-h@rm", "5elf-harm", "self-#arm", "$elf-harm",
|
368 |
+
"se1f-harm", "self-harm", "cutting", "cuttin9", "cutt!ng", "(utting", "cutt1ng", "cu77ing",
|
369 |
+
"cutt|ng", "burn1ng", "burnin9", "burn!ng", "8urning", "burn|ng", "burning", "pa!n",
|
370 |
+
"p4in", "p@in", "pain", "pa1n", "pa|n", "s7arva7ion", "5tarvation", "st4rv4tion", "starvat1on",
|
371 |
+
"starvat!on", "starvation", "starvat|on", "starvati0n", "$tarvation", "st@rv@tion", "overdose",
|
372 |
+
"0verd0se", "ov3rdos3", "over|)ose", "overdo5e", "overdo$e", "|)epresse|)", "d3pr3ss3d",
|
373 |
+
"depre55ed", "depressed", "depre$$ed", "d|e", "die", "d!e", "di3", "|)ie", "d1e", "jump",
|
374 |
+
"hang", "#ang", "h4ng", "han9", "h@ng", "poison", "po!son", "p0is0n", "poi5on", "poi$on",
|
375 |
+
"po1son", "po|son", "(hloroform", "chloroform", "ch|oroform", "ch1oroform", "c#loroform",
|
376 |
+
"chl0r0f0rm", "drug abu5e", "dru9 abuse", "drug abuse", "|)rug abuse", "drug abu$e", "drug 4buse",
|
377 |
+
"drug abus3", "drug @buse", "drug a8use", "@ddict", "4ddict", "add!ct", "addict", "a|)|)ict",
|
378 |
+
"addic7", "add1ct", "add|ct", "addi(t", "opioid", "0pi0id", "op1o1d", "op|o|d", "opioi|)",
|
379 |
+
"op!o!d", "fentanyl", "f3ntanyl", "fentany|", "fen7anyl", "fent@nyl", "fent4nyl", "fentany1",
|
380 |
+
"meth", "met#", "m3th", "me7h", "coca1ne", "cocain3", "cocaine", "coc4ine", "(o(aine",
|
381 |
+
"coc@ine", "coca!ne", "coca|ne", "c0caine", "h3roin", "her0in", "heroin", "#eroin", "hero|n",
|
382 |
+
"hero!n", "hero1n",
|
383 |
+
# New Hate Speech keywords and variations (second block)
|
384 |
+
"n@zi", "naz1", "naz!", "nazi", "na2i", "naz|", "n4zi", "kkk", "suprema(y", "$upremacy",
|
385 |
+
"suprem4cy", "suprem@cy", "supr3macy", "5upremacy", "supremacy", "gen0cide", "genoc1de",
|
386 |
+
"genoci|)e", "genocide", "genoc|de", "geno(ide", "9enocide", "g3nocid3", "genoc!de",
|
387 |
+
"big0t", "bigot", "b|got", "bi9ot", "bigo7", "b!got", "8igot", "b1got", "#omop#obe", "homophobe",
|
388 |
+
"homophob3", "homopho8e", "h0m0ph0be", "xenophobe", "xenopho8e", "xenop#obe", "x3nophob3",
|
389 |
+
"xen0ph0be", "antifa", "bootlicker", "tankie", "baiter", "griefer", "kek", "pepe", "zoomer",
|
390 |
+
# New Slang Abuses & Offensive Insults (second block)
|
391 |
+
"bit(h", "8itch", "b|tch", "b1tch", "bi7ch", "bastar|", "b@st@rd", "ba5tard", "bas7ard",
|
392 |
+
"ba$tard", "b4st4rd", "8astard", "assho1e", "assho|e", "a$$hole", "ass#ole", "asshol3",
|
393 |
+
"4sshole", "a55hole", "assh0le", "pr1ck", "pr|ck", "pr!ck", "prick", "|)umbass", "dumba55",
|
394 |
+
"dumb4ss", "dumba$$", "dum8ass", "dumb@ss", "retar|", "r3tard", "re7ard", "ret@rd", "ret4rd",
|
395 |
+
"|)ipshit", "d|psh|t", "dipshi7", "dip5hit", "dips#it", "d!psh!t", "dipshit", "dip$hit",
|
396 |
+
"d1psh1t", "j@ck@ss", "wank3r", "w@nker", "w4nker", "tw4t", "tw@t", "7wa7", "shi7head",
|
397 |
+
"shithe@d", "shith3ad", "5hithead", "s#it#ead", "sh!thead", "sh1thead", "shithea|", "shithe4d",
|
398 |
+
"$hithead",
|
399 |
+
# New General Abuses (second block)
|
400 |
+
"|d|ot", "idi0t", "1d1ot", "idio7", "idiot", "i|)iot", "!d!ot", "m0r0n", "moron", "lo5er",
|
401 |
+
"|oser", "1oser", "loser", "l0ser", "los3r", "5cum", "s(um", "$cum", "worthl3ss", "wort#less",
|
402 |
+
"worth|ess", "worthle$$", "wor7hless", "worthless", "worthle55", "worth1ess", "w0rthless",
|
403 |
+
# Additional new keywords from the latest list
|
404 |
+
"16+", "18+", "alcohol", "amerifag", "assault", "b!tch", "bstard", "burn yourself", "c!nt",
|
405 |
+
"christfucker", "cnt", "cocaine", "creep", "cut yourself", "die in a hole", "die now", "dipshit",
|
406 |
+
"drink bleach", "drop dead", "dumbfuck", "fuck off", "fucker", "fucking idiot", "fuk", "get drunk",
|
407 |
+
"go hang yourself", "hymie", "i will ban you", "i will bomb the place", "i will fuck you",
|
408 |
+
"i will kill you", "jew", "jewboy", "moslemfucker", "marijuana", "massacre", "meth", "molest",
|
409 |
+
"naked", "obongo", "overdose", "penis", "perv", "pervert", "rape you", "rat poison", "s3x",
|
410 |
+
"sandnigger", "screw you", "secks", "self-harm", "sex offender", "sexual predator", "sx",
|
411 |
+
"take pills", "terrorist", "tits", "tranny", "twat", "vag", "vagina", "vodka", "x", "xxx",
|
412 |
+
"you will get raped", "you're a piece of shit", "you're banned forever", "you're crazy",
|
413 |
+
"you're hallucinating", "you're such a cunt", "you're worthless",
|
414 |
+
# New Sexually Explicit keywords and variations (second block)
|
415 |
+
"p0rn", "nu|)e", "nud3", "5ex", "$ex", "s3x", "xxx", "hardc0re", "h@rdcore", "hardcor3", "#ardcore",
|
416 |
+
"har|)core", "hard(ore", "h4rdcore", "adu1t", "adul7", "adu|t", "@dult", "adult", "4dult",
|
417 |
+
"a|)ult", "erot1c", "erot|c", "erot!c", "ero7ic", "eroti(", "er0tic", "3rotic", "str!p",
|
418 |
+
"s7rip", "str1p", "$trip", "strip", "str|p", "5trip", "c@mgirl", "camg|rl", "camg1rl",
|
419 |
+
"(amgirl", "cam9irl", "c4mgirl", "camgir1", "camgir|", "camg!rl", "feti$h", "fet1sh", "feti5h",
|
420 |
+
"fetis#", "f3tish", "fe7ish", "fetish", "fet!sh", "fet|sh",
|
421 |
+
# New Sexual Harassment keywords and variations (second block)
|
422 |
+
"perv", "p3rv", "(reep", "creep", "cr33p", "mo1est", "molest", "mole$t", "m0lest",
|
423 |
+
"mo|est", "mol3st", "moles7", "mole5t", "gr0pe", "9rope", "grop3", "grope", "h@r@ss",
|
424 |
+
"harass", "hara55", "h4r4ss", "#arass", "hara$$", "c4tc4ll", "ca7call", "catca11", "catca||",
|
425 |
+
"c@tc@ll", "(at(all", "catcall", "pre|)ator", "pred4tor", "pred@tor", "preda7or", "pr3dator",
|
426 |
+
"predat0r", "predator", "sta1ker", "st@lker", "stalk3r", "$talker", "st4lker", "s7alker",
|
427 |
+
"5talker", "stalker", "sta|ker", "m1sogyn1st", "misogynis7", "misogynist", "m|sogyn|st",
|
428 |
+
"m!sogyn!st", "mi$ogyni$t", "miso9ynist", "mis0gynist", "mi5ogyni5t", "exp0se", "expose",
|
429 |
+
"3xpos3", "expo$e", "expo5e",
|
430 |
+
# New Dangerous Content keywords and variations (second block)
|
431 |
+
"b0mb", "8om8", "k!ll", "k1ll", "ki||", "ki11", "k|ll", "kill", "atta(k", "a77ack",
|
432 |
+
"@tt@ck", "4tt4ck", "terr0r", "t3rror", "7error", "shoo7", "sh00t", "$hoot", "5hoot",
|
433 |
+
"s#oot", "$tab", "st4b", "st@b", "5tab", "sta8", "s7ab", "exp|osive", "expl0sive",
|
434 |
+
"explosive", "3xplosiv3", "explos!ve", "explos1ve", "explo5ive", "explos|ve", "explo$ive",
|
435 |
+
"exp1osive", "assass|nate", "assassinat3", "assass!nate", "assass1nate", "a55a55inate",
|
436 |
+
"assassina7e", "assassinate", "@ss@ssin@te", "4ss4ssin4te", "a$$a$$inate", "massacr3", "massa(re",
|
437 |
+
"ma$$acre", "m4ss4cre", "m@ss@cre", "ma55acre", "massacre", "$uicide", "suicide", "su1c1de",
|
438 |
+
"suicid3", "su|c|de", "sui(ide", "suici|)e", "5uicide", "su!c!de", "#omicide", "hom!c!de",
|
439 |
+
"hom|c|de", "homicid3", "homicide", "h0micide", "homi(ide", "homici|)e", "hom1c1de", "7or7ure",
|
440 |
+
"torture", "tortur3", "t0rture", "ra|)ical", "r4dic4l", "rad1cal", "radica1", "radica|",
|
441 |
+
"rad!cal", "rad|cal", "radical", "radi(al", "r@dic@l", "beheadin9", "8eheading",
|
442 |
+
"behea|)ing", "b3h3ading", "behead|ng", "beheading", "behead!ng", "be#eading", "behe4ding",
|
443 |
+
"behe@ding", "behead1ng", "extrem|st", "extrem!st", "3xtr3mist", "extremi$t", "ex7remis7",
|
444 |
+
"extremist", "extrem1st", "extremi5t", "r|ot", "r1ot", "rio7", "r!ot", "ri0t", "traff|ck|ng",
|
445 |
+
"tr@fficking", "traff!ck!ng", "traff1ck1ng", "7rafficking", "tr4fficking", "traffi(king",
|
446 |
+
"trafficking", "traffickin9", "k|dnap", "ki|)nap", "kidn@p", "kidn4p", "k!dnap", "k1dnap",
|
447 |
+
"arson", "ar5on", "ar$on", "4rson", "ars0n",
|
448 |
+
# New Harmful Content keywords and variations (second block)
|
449 |
+
"s3lf-harm", "se|f-harm", "self-h4rm", "self-h@rm", "5elf-harm", "self-#arm", "$elf-harm",
|
450 |
+
"se1f-harm", "self-harm", "cutting", "cuttin9", "cutt!ng", "(utting", "cutt1ng", "cu77ing",
|
451 |
+
"cutt|ng", "burn1ng", "burnin9", "burn!ng", "8urning", "burn|ng", "burning", "pa!n",
|
452 |
+
"p4in", "p@in", "pain", "pa1n", "pa|n", "s7arva7ion", "5tarvation", "st4rv4tion", "starvat1on",
|
453 |
+
"starvat!on", "starvation", "starvat|on", "starvati0n", "$tarvation", "st@rv@tion", "overdose",
|
454 |
+
"0verd0se", "ov3rdos3", "over|)ose", "overdo5e", "overdo$e", "|)epresse|)", "d3pr3ss3d",
|
455 |
+
"depre55ed", "depressed", "depre$$ed", "d|e", "die", "d!e", "di3", "|)ie", "d1e", "jump",
|
456 |
+
"hang", "#ang", "h4ng", "han9", "h@ng", "poison", "po!son", "p0is0n", "poi5on", "poi$on",
|
457 |
+
"po1son", "po|son", "(hloroform", "chloroform", "ch|oroform", "ch1oroform", "c#loroform",
|
458 |
+
"chl0r0f0rm", "drug abu5e", "dru9 abuse", "drug abuse", "|)rug abuse", "drug abu$e", "drug 4buse",
|
459 |
+
"drug abus3", "drug @buse", "drug a8use", "@ddict", "4ddict", "add!ct", "addict", "a|)|)ict",
|
460 |
+
"addic7", "add1ct", "add|ct", "addi(t", "opioid", "0pi0id", "op1o1d", "op|o|d", "opioi|)",
|
461 |
+
"op!o!d", "fentanyl", "f3ntanyl", "fentany|", "fen7anyl", "fent@nyl", "fent4nyl", "fentany1",
|
462 |
+
"meth", "met#", "m3th", "me7h", "coca1ne", "cocain3", "cocaine", "coc4ine", "(o(aine",
|
463 |
+
"coc@ine", "coca!ne", "coca|ne", "c0caine", "h3roin", "her0in", "heroin", "#eroin", "hero|n",
|
464 |
+
"hero!n", "hero1n",
|
465 |
+
# New Hate Speech keywords and variations (second block)
|
466 |
+
"n@zi", "naz1", "naz!", "nazi", "na2i", "naz|", "n4zi", "kkk", "suprema(y", "$upremacy",
|
467 |
+
"suprem4cy", "suprem@cy", "supr3macy", "5upremacy", "supremacy", "gen0cide", "genoc1de",
|
468 |
+
"genoci|)e", "genocide", "genoc|de", "geno(ide", "9enocide", "g3nocid3", "genoc!de", "big0t",
|
469 |
+
"bigot", "b|got", "bi9ot", "bigo7", "b!got", "8igot", "b1got", "#omop#obe", "homophobe",
|
470 |
+
"homophob3", "homopho8e", "h0m0ph0be", "xenophobe", "xenopho8e", "xenop#obe", "x3nophob3",
|
471 |
+
"xen0ph0be", "antifa", "bootlicker", "tankie", "baiter", "griefer", "kek", "pepe", "zoomer",
|
472 |
+
# New Slang Abuses & Offensive Insults (second block)
|
473 |
+
"bit(h", "8itch", "b|tch", "b1tch", "bi7ch", "bastar|", "b@st@rd", "ba5tard", "bas7ard",
|
474 |
+
"ba$tard", "b4st4rd", "8astard", "assho1e", "assho|e", "a$$hole", "ass#ole", "asshol3", "4sshole",
|
475 |
+
"a55hole", "assh0le", "pr1ck", "pr|ck", "pr!ck", "prick", "|)umbass", "dumba55", "dumb4ss",
|
476 |
+
"dumba$$", "dum8ass", "dumb@ss", "retar|", "r3tard", "re7ard", "ret@rd", "ret4rd", "|)ipshit",
|
477 |
+
"d|psh|t", "dipshi7", "dip5hit", "dips#it", "d!psh!t", "dipshit", "dip$hit", "d1psh1t", "j@ck@ss",
|
478 |
+
"wank3r", "w@nker", "w4nker", "tw4t", "tw@t", "7wa7", "shi7head", "shithe@d", "shith3ad",
|
479 |
+
"5hithead", "s#it#ead", "sh!thead", "sh1thead", "shithea|", "shithe4d", "$hithead",
|
480 |
+
# New General Abuses (second block)
|
481 |
+
"|d|ot", "idi0t", "1d1ot", "idio7", "idiot", "i|)iot", "!d!ot", "m0r0n", "moron", "lo5er",
|
482 |
+
"|oser", "1oser", "loser", "l0ser", "los3r", "5cum", "s(um", "$cum", "worthl3ss", "wort#less",
|
483 |
+
"worth|ess", "worthle$$", "wor7hless", "worthless", "worthle55", "worth1ess", "w0rthless",
|
484 |
+
# Additional new keywords from the latest list
|
485 |
+
"16+", "18+", "alcohol", "amerifag", "assault", "b!tch", "bstard", "burn yourself", "c!nt",
|
486 |
+
"christfucker", "cnt", "cocaine", "creep", "cut yourself", "die in a hole", "die now", "dipshit",
|
487 |
+
"drink bleach", "drop dead", "dumbfuck", "fuck off", "fucker", "fucking idiot", "fuk", "get drunk",
|
488 |
+
"go hang yourself", "hymie", "i will ban you", "i will bomb the place", "i will fuck you",
|
489 |
+
"i will kill you", "jew", "jewboy", "moslemfucker", "marijuana", "massacre", "meth", "molest",
|
490 |
+
"naked", "obongo", "overdose", "penis", "perv", "pervert", "rape you", "rat poison", "s3x",
|
491 |
+
"sandnigger", "screw you", "secks", "self-harm", "sex offender", "sexual predator", "sx",
|
492 |
+
"take pills", "terrorist", "tits", "tranny", "twat", "vag", "vagina", "vodka", "x", "xxx",
|
493 |
+
"you will get raped", "you're a piece of shit", "you're banned forever", "you're crazy",
|
494 |
+
"you're hallucinating", "you're such a cunt", "you're worthless",
|
495 |
+
# New Sexually Explicit keywords and variations (second block)
|
496 |
+
"p0rn", "nu|)e", "nud3", "5ex", "$ex", "s3x", "xxx", "hardc0re", "h@rdcore", "hardcor3", "#ardcore",
|
497 |
+
"har|)core", "hard(ore", "h4rdcore", "adu1t", "adul7", "adu|t", "@dult", "adult", "4dult",
|
498 |
+
"a|)ult", "erot1c", "erot|c", "erot!c", "ero7ic", "eroti(", "er0tic", "3rotic", "str!p",
|
499 |
+
"s7rip", "str1p", "$trip", "strip", "str|p", "5trip", "c@mgirl", "camg|rl", "camg1rl",
|
500 |
+
"(amgirl", "cam9irl", "c4mgirl", "camgir1", "camgir|", "camg!rl", "feti$h", "fet1sh", "feti5h",
|
501 |
+
"fetis#", "f3tish", "fe7ish", "fetish", "fet!sh", "fet|sh",
|
502 |
+
# New Sexual Harassment keywords and variations (second block)
|
503 |
+
"perv", "p3rv", "(reep", "creep", "cr33p", "mo1est", "molest", "mole$t", "m0lest",
|
504 |
+
"mo|est", "mol3st", "moles7", "mole5t", "gr0pe", "9rope", "grop3", "grope", "h@r@ss",
|
505 |
+
"harass", "hara55", "h4r4ss", "#arass", "hara$$", "c4tc4ll", "ca7call", "catca11", "catca||",
|
506 |
+
"c@tc@ll", "(at(all", "catcall", "pre|)ator", "pred4tor", "pred@tor", "preda7or", "pr3dator",
|
507 |
+
"predat0r", "predator", "sta1ker", "st@lker", "stalk3r", "$talker", "st4lker", "s7alker",
|
508 |
+
"5talker", "stalker", "sta|ker", "m1sogyn1st", "misogynis7", "misogynist", "m|sogyn|st",
|
509 |
+
"m!sogyn!st", "mi$ogyni$t", "miso9ynist", "mis0gynist", "mi5ogyni5t", "exp0se", "expose",
|
510 |
+
"3xpos3", "expo$e", "expo5e",
|
511 |
+
# New Dangerous Content keywords and variations (second block)
|
512 |
+
"b0mb", "8om8", "k!ll", "k1ll", "ki||", "ki11", "k|ll", "kill", "atta(k", "a77ack",
|
513 |
+
"@tt@ck", "4tt4ck", "terr0r", "t3rror", "7error", "shoo7", "sh00t", "$hoot", "5hoot",
|
514 |
+
"s#oot", "$tab", "st4b", "st@b", "5tab", "sta8", "s7ab", "exp|osive", "expl0sive",
|
515 |
+
"explosive", "3xplosiv3", "explos!ve", "explos1ve", "explo5ive", "explos|ve", "explo$ive",
|
516 |
+
"exp1osive", "assass|nate", "assassinat3", "assass!nate", "assass1nate", "a55a55inate",
|
517 |
+
"assassina7e", "assassinate", "@ss@ssin@te", "4ss4ssin4te", "a$$a$$inate", "massacr3", "massa(re",
|
518 |
+
"ma$$acre", "m4ss4cre", "m@ss@cre", "ma55acre", "massacre", "$uicide", "suicide", "su1c1de",
|
519 |
+
"suicid3", "su|c|de", "sui(ide", "suici|)e", "5uicide", "su!c!de", "#omicide", "hom!c!de",
|
520 |
+
"hom|c|de", "homicid3", "homicide", "h0micide", "homi(ide", "homici|)e", "hom1c1de", "7or7ure",
|
521 |
+
"torture", "tortur3", "t0rture", "ra|)ical", "r4dic4l", "rad1cal", "radica1", "radica|",
|
522 |
+
"rad!cal", "rad|cal", "radical", "radi(al", "r@dic@l", "beheadin9", "8eheading",
|
523 |
+
"behea|)ing", "b3h3ading", "behead|ng", "beheading", "behead!ng", "be#eading", "behe4ding",
|
524 |
+
"behe@ding", "behead1ng", "extrem|st", "extrem!st", "3xtr3mist", "extremi$t", "ex7remis7",
|
525 |
+
"extremist", "extrem1st", "extremi5t", "r|ot", "r1ot", "rio7", "r!ot", "ri0t", "traff|ck|ng",
|
526 |
+
"tr@fficking", "traff!ck!ng", "traff1ck1ng", "7rafficking", "tr4fficking", "traffi(king",
|
527 |
+
"trafficking", "traffickin9", "k|dnap", "ki|)nap", "kidn@p", "kidn4p", "k!dnap", "k1dnap",
|
528 |
+
"arson", "ar5on", "ar$on", "4rson", "ars0n",
|
529 |
+
# New Harmful Content keywords and variations (third block)
|
530 |
+
"s3lf-harm", "se|f-harm", "self-h4rm", "self-h@rm", "5elf-harm", "self-#arm", "$elf-harm",
|
531 |
+
"se1f-harm", "self-harm", "cutting", "cuttin9", "cutt!ng", "(utting", "cutt1ng", "cu77ing",
|
532 |
+
"cutt|ng", "burn1ng", "burnin9", "burn!ng", "8urning", "burn|ng", "burning", "pa!n",
|
533 |
+
"p4in", "p@in", "pain", "pa1n", "pa|n", "s7arva7ion", "5tarvation", "st4rv4tion", "starvat1on",
|
534 |
+
"starvat!on", "starvation", "starvat|on", "starvati0n", "$tarvation", "st@rv@tion", "overdose",
|
535 |
+
"0verd0se", "ov3rdos3", "over|)ose", "overdo5e", "overdo$e", "|)epresse|)", "d3pr3ss3d",
|
536 |
+
"depre55ed", "depressed", "depre$$ed", "d|e", "die", "d!e", "di3", "|)ie", "d1e", "jump",
|
537 |
+
"hang", "#ang", "h4ng", "han9", "h@ng", "poison", "po!son", "p0is0n", "poi5on", "poi$on",
|
538 |
+
"po1son", "po|son", "(hloroform", "chloroform", "ch|oroform", "ch1oroform", "c#loroform",
|
539 |
+
"chl0r0f0rm", "drug abu5e", "dru9 abuse", "drug abuse", "|)rug abuse", "drug abu$e", "drug 4buse",
|
540 |
+
"drug abus3", "drug @buse", "drug a8use", "@ddict", "4ddict", "add!ct", "addict", "a|)|)ict",
|
541 |
+
"addic7", "add1ct", "add|ct", "addi(t", "opioid", "0pi0id", "op1o1d", "op|o|d", "opioi|)",
|
542 |
+
"op!o!d", "fentanyl", "f3ntanyl", "fentany|", "fen7anyl", "fent@nyl", "fent4nyl", "fentany1",
|
543 |
+
"meth", "met#", "m3th", "me7h", "coca1ne", "cocain3", "cocaine", "coc4ine", "(o(aine",
|
544 |
+
"coc@ine", "coca!ne", "coca|ne", "c0caine", "h3roin", "her0in", "heroin", "#eroin", "hero|n",
|
545 |
+
"hero!n", "hero1n",
|
546 |
+
# New Hate Speech keywords and variations (third block)
|
547 |
+
"n@zi", "naz1", "naz!", "nazi", "na2i", "naz|", "n4zi", "kkk", "suprema(y", "$upremacy",
|
548 |
+
"suprem4cy", "suprem@cy", "supr3macy", "5upremacy", "supremacy", "gen0cide", "genoc1de",
|
549 |
+
"genoci|)e", "genocide", "genoc|de", "geno(ide", "9enocide", "g3nocid3", "genoc!de", "big0t",
|
550 |
+
"bigot", "b|got", "bi9ot", "bigo7", "b!got", "8igot", "b1got", "#omop#obe", "homophobe",
|
551 |
+
"homophob3", "homopho8e", "h0m0ph0be", "xenophobe", "xenopho8e", "xenop#obe", "x3nophob3",
|
552 |
+
"xen0ph0be", "antifa", "bootlicker", "tankie", "baiter", "griefer", "kek", "pepe", "zoomer",
|
553 |
+
# New Slang Abuses & Offensive Insults (third block)
|
554 |
+
"bit(h", "8itch", "b|tch", "b1tch", "bi7ch", "bastar|", "b@st@rd", "ba5tard", "bas7ard",
|
555 |
+
"ba$tard", "b4st4rd", "8astard", "assho1e", "assho|e", "a$$hole", "ass#ole", "asshol3", "4sshole",
|
556 |
+
"a55hole", "assh0le", "pr1ck", "pr|ck", "pr!ck", "prick", "|)umbass", "dumba55", "dumb4ss",
|
557 |
+
"dumba$$", "dum8ass", "dumb@ss", "retar|", "r3tard", "re7ard", "ret@rd", "ret4rd", "|)ipshit",
|
558 |
+
"d|psh|t", "dipshi7", "dip5hit", "dips#it", "d!psh!t", "dipshit", "dip$hit", "d1psh1t", "j@ck@ss",
|
559 |
+
"wank3r", "w@nker", "w4nker", "tw4t", "tw@t", "7wa7", "shi7head", "shithe@d", "shith3ad",
|
560 |
+
"5hithead", "s#it#ead", "sh!thead", "sh1thead", "shithea|", "shithe4d", "$hithead",
|
561 |
+
# New General Abuses (third block)
|
562 |
+
"|d|ot", "idi0t", "1d1ot", "idio7", "idiot", "i|)iot", "!d!ot", "m0r0n", "moron", "lo5er",
|
563 |
+
"|oser", "1oser", "loser", "l0ser", "los3r", "5cum", "s(um", "$cum", "worthl3ss", "wort#less",
|
564 |
+
"worth|ess", "worthle$$", "wor7hless", "worthless", "worthle55", "worth1ess", "w0rthless",
|
565 |
+
# Additional new keywords from the latest list (General Abusive Language)
|
566 |
+
"16+", "18+", "alcohol", "amerifag", "assault", "b!tch", "bstard", "burn yourself", "c!nt",
|
567 |
+
"christfucker", "cnt", "cocaine", "creep", "cut yourself", "die in a hole", "die now", "dipshit",
|
568 |
+
"drink bleach", "drop dead", "dumbfuck", "fuck off", "fucker", "fucking idiot", "fuk", "get drunk",
|
569 |
+
"go hang yourself", "hymie", "i will ban you", "i will bomb the place", "i will fuck you",
|
570 |
+
"i will kill you", "jew", "jewboy", "moslemfucker", "marijuana", "massacre", "meth", "molest",
|
571 |
+
"naked", "obongo", "overdose", "penis", "perv", "pervert", "rape you", "rat poison", "s3x",
|
572 |
+
"sandnigger", "screw you", "secks", "self-harm", "sex offender", "sexual predator", "sx",
|
573 |
+
"take pills", "terrorist", "tits", "tranny", "twat", "vag", "vagina", "vodka", "x", "xxx",
|
574 |
+
"you will get raped", "you're a piece of shit", "you're banned forever", "you're crazy",
|
575 |
+
"you're hallucinating", "you're such a cunt", "you're worthless",
|
576 |
+
# New Sexually Explicit keywords and variations (third block)
|
577 |
+
"p0rn", "nu|)e", "nud3", "5ex", "$ex", "s3x", "xxx", "hardc0re", "h@rdcore", "hardcor3", "#ardcore",
|
578 |
+
"har|)core", "hard(ore", "h4rdcore", "adu1t", "adul7", "adu|t", "@dult", "adult", "4dult",
|
579 |
+
"a|)ult", "erot1c", "erot|c", "erot!c", "ero7ic", "eroti(", "er0tic", "3rotic", "str!p",
|
580 |
+
"s7rip", "str1p", "$trip", "strip", "str|p", "5trip", "c@mgirl", "camg|rl", "camg1rl",
|
581 |
+
"(amgirl", "cam9irl", "c4mgirl", "camgir1", "camgir|", "camg!rl", "feti$h", "fet1sh", "feti5h",
|
582 |
+
"fetis#", "f3tish", "fe7ish", "fetish", "fet!sh", "fet|sh",
|
583 |
+
# New Sexual Harassment keywords and variations (third block)
|
584 |
+
"perv", "p3rv", "(reep", "creep", "cr33p", "mo1est", "molest", "mole$t", "m0lest",
|
585 |
+
"mo|est", "mol3st", "moles7", "mole5t", "gr0pe", "9rope", "grop3", "grope", "h@r@ss",
|
586 |
+
"harass", "hara55", "h4r4ss", "#arass", "hara$$", "c4tc4ll", "ca7call", "catca11", "catca||",
|
587 |
+
"c@tc@ll", "(at(all", "catcall", "pre|)ator", "pred4tor", "pred@tor", "preda7or", "pr3dator",
|
588 |
+
"predat0r", "predator", "sta1ker", "st@lker", "stalk3r", "$talker", "st4lker", "s7alker",
|
589 |
+
"5talker", "stalker", "sta|ker", "m1sogyn1st", "misogynis7", "misogynist", "m|sogyn|st",
|
590 |
+
"m!sogyn!st", "mi$ogyni$t", "miso9ynist", "mis0gynist", "mi5ogyni5t", "exp0se", "expose",
|
591 |
+
"3xpos3", "expo$e", "expo5e",
|
592 |
+
# New Dangerous Content keywords and variations (third block)
|
593 |
+
"b0mb", "8om8", "k!ll", "k1ll", "ki||", "ki11", "k|ll", "kill", "atta(k", "a77ack",
|
594 |
+
"@tt@ck", "4tt4ck", "terr0r", "t3rror", "7error", "shoo7", "sh00t", "$hoot", "5hoot",
|
595 |
+
"s#oot", "$tab", "st4b", "st@b", "5tab", "sta8", "s7ab", "exp|osive", "expl0sive",
|
596 |
+
"explosive", "3xplosiv3", "explos!ve", "explos1ve", "explo5ive", "explos|ve", "explo$ive",
|
597 |
+
"exp1osive", "assass|nate", "assassinat3", "assass!nate", "assass1nate", "a55a55inate",
|
598 |
+
"assassina7e", "assassinate", "@ss@ssin@te", "4ss4ssin4te", "a$$a$$inate", "massacr3", "massa(re",
|
599 |
+
"ma$$acre", "m4ss4cre", "m@ss@cre", "ma55acre", "massacre", "$uicide", "suicide", "su1c1de",
|
600 |
+
"suicid3", "su|c|de", "sui(ide", "suici|)e", "5uicide", "su!c!de", "#omicide", "hom!c!de",
|
601 |
+
"hom|c|de", "homicid3", "homicide", "h0micide", "homi(ide", "homici|)e", "hom1c1de", "7or7ure",
|
602 |
+
"torture", "tortur3", "t0rture", "ra|)ical", "r4dic4l", "rad1cal", "radica1", "radica|",
|
603 |
+
"rad!cal", "rad|cal", "radical", "radi(al", "r@dic@l", "beheadin9", "8eheading",
|
604 |
+
"behea|)ing", "b3h3ading", "behead|ng", "beheading", "behead!ng", "be#eading", "behe4ding",
|
605 |
+
"behe@ding", "behead1ng", "extrem|st", "extrem!st", "3xtr3mist", "extremi$t", "ex7remis7",
|
606 |
+
"extremist", "extrem1st", "extremi5t", "r|ot", "r1ot", "rio7", "r!ot", "ri0t", "traff|ck|ng",
|
607 |
+
"tr@fficking", "traff!ck!ng", "traff1ck1ng", "7rafficking", "tr4fficking", "traffi(king",
|
608 |
+
"trafficking", "traffickin9", "k|dnap", "ki|)nap", "kidn@p", "kidn4p", "k!dnap", "k1dnap",
|
609 |
+
"arson", "ar5on", "ar$on", "4rson", "ars0n",
|
610 |
+
# New Harmful Content keywords and variations (fourth block)
|
611 |
+
"s3lf-harm", "se|f-harm", "self-h4rm", "self-h@rm", "5elf-harm", "self-#arm", "$elf-harm",
|
612 |
+
"se1f-harm", "self-harm", "cutting", "cuttin9", "cutt!ng", "(utting", "cutt1ng", "cu77ing",
|
613 |
+
"cutt|ng", "burn1ng", "burnin9", "burn!ng", "8urning", "burn|ng", "burning", "pa!n",
|
614 |
+
"p4in", "p@in", "pain", "pa1n", "pa|n", "s7arva7ion", "5starvation", "st4rv4tion", "starvat1on",
|
615 |
+
"starvat!on", "starvation", "starvat|on", "starvati0n", "$tarvation", "st@rv@tion", "overdose",
|
616 |
+
"0verd0se", "ov3rdos3", "over|)ose", "overdo5e", "overdo$e", "|)epresse|)", "d3pr3ss3d",
|
617 |
+
"depre55ed", "depressed", "depre$$ed", "d|e", "die", "d!e", "di3", "|)ie", "d1e", "jump",
|
618 |
+
"hang", "#ang", "h4ng", "han9", "h@ng", "poison", "po!son", "p0is0n", "poi5on", "poi$on",
|
619 |
+
"po1son", "po|son", "(hloroform", "chloroform", "ch|oroform", "ch1oroform", "c#loroform",
|
620 |
+
"chl0r0f0rm", "drug abu5e", "dru9 abuse", "drug abuse", "|)rug abuse", "drug abu$e", "drug 4buse",
|
621 |
+
"drug abus3", "drug @buse", "drug a8use", "@ddict", "4ddict", "add!ct", "addict", "a|)|)ict",
|
622 |
+
"addic7", "add1ct", "add|ct", "addi(t", "opioid", "0pi0id", "op1o1d", "op|o|d", "opioi|)",
|
623 |
+
"op!o!d", "fentanyl", "f3ntanyl", "fentany|", "fen7anyl", "fent@nyl", "fent4nyl", "fentany1",
|
624 |
+
"meth", "met#", "m3th", "me7h", "coca1ne", "cocain3", "cocaine", "coc4ine", "(o(aine",
|
625 |
+
"coc@ine", "coca!ne", "coca|ne", "c0caine", "h3roin", "her0in", "heroin", "#eroin", "hero|n",
|
626 |
+
"hero!n", "hero1n",
|
627 |
+
# New Hate Speech keywords and variations (fourth block)
|
628 |
+
"n@zi", "naz1", "naz!", "nazi", "na2i", "naz|", "n4zi", "kkk", "suprema(y", "$upremacy",
|
629 |
+
"suprem4cy", "suprem@cy", "supr3macy", "5upremacy", "supremacy", "gen0cide", "genoc1de",
|
630 |
+
"genoci|)e", "genocide", "genoc|de", "geno(ide", "9enocide", "g3nocid3", "genoc!de", "big0t",
|
631 |
+
"bigot", "b|got", "bi9ot", "bigo7", "b!got", "8igot", "b1got", "#omop#obe", "homophobe",
|
632 |
+
"homophob3", "homopho8e", "h0m0ph0be", "xenophobe", "xenopho8e", "xenop#obe", "x3nophob3",
|
633 |
+
"xen0ph0be", "antifa", "bootlicker", "tankie", "baiter", "griefer", "kek", "pepe", "zoomer",
|
634 |
+
# New Slang Abuses & Offensive Insults (fourth block)
|
635 |
+
"bit(h", "8itch", "b|tch", "b1tch", "bi7ch", "bastar|", "b@st@rd", "ba5tard", "bas7ard",
|
636 |
+
"ba$tard", "b4st4rd", "8astard", "assho1e", "assho|e", "a$$hole", "ass#ole", "asshol3", "4sshole",
|
637 |
+
"a55hole", "assh0le", "pr1ck", "pr|ck", "pr!ck", "prick", "|)umbass", "dumba55", "dumb4ss",
|
638 |
+
"dumba$$", "dum8ass", "dumb@ss", "retar|", "r3tard", "re7ard", "ret@rd", "ret4rd", "|)ipshit",
|
639 |
+
"d|psh|t", "dipshi7", "dip5hit", "dips#it", "d!psh!t", "dipshit", "dip$hit", "d1psh1t", "j@ck@ss",
|
640 |
+
"wank3r", "w@nker", "w4nker", "tw4t", "tw@t", "7wa7", "shi7head", "shithe@d", "shith3ad",
|
641 |
+
"5hithead", "s#it#ead", "sh!thead", "sh1thead", "shithea|", "shithe4d", "$hithead",
|
642 |
+
# New General Abuses (fourth block)
|
643 |
+
"|d|ot", "idi0t", "1d1ot", "idio7", "idiot", "i|)iot", "!d!ot", "m0r0n", "moron", "lo5er",
|
644 |
+
"|oser", "1oser", "loser", "l0ser", "los3r", "5cum", "s(um", "$cum", "worthl3ss", "wort#less",
|
645 |
+
"worth|ess", "worthle$$", "wor7hless", "worthless", "worthle55", "worth1ess", "w0rthless",
|
646 |
+
# Additional new keywords from the latest list (General Abusive Language)
|
647 |
+
"16+", "18+", "alcohol", "amerifag", "assault", "b!tch", "bstard", "burn yourself", "c!nt",
|
648 |
+
"christfucker", "cnt", "cocaine", "creep", "cut yourself", "die in a hole", "die now", "dipshit",
|
649 |
+
"drink bleach", "drop dead", "dumbfuck", "fuck off", "fucker", "fucking idiot", "fuk", "get drunk",
|
650 |
+
"go hang yourself", "hymie", "i will ban you", "i will bomb the place", "i will fuck you",
|
651 |
+
"i will kill you", "jew", "jewboy", "moslemfucker", "marijuana", "massacre", "meth", "molest",
|
652 |
+
"naked", "obongo", "overdose", "penis", "perv", "pervert", "rape you", "rat poison", "s3x",
|
653 |
+
"sandnigger", "screw you", "secks", "self-harm", "sex offender", "sexual predator", "sx",
|
654 |
+
"take pills", "terrorist", "tits", "tranny", "twat", "vag", "vagina", "vodka", "x", "xxx",
|
655 |
+
"you will get raped", "you're a piece of shit", "you're banned forever", "you're crazy",
|
656 |
+
"you're hallucinating", "you're such a cunt", "you're worthless",
|
657 |
+
# New Sexually Explicit keywords and variations (fourth block)
|
658 |
+
"p0rn", "nu|)e", "nud3", "5ex", "$ex", "s3x", "xxx", "hardc0re", "h@rdcore", "hardcor3", "#ardcore",
|
659 |
+
"har|)core", "hard(ore", "h4rdcore", "adu1t", "adul7", "adu|t", "@dult", "adult", "4dult",
|
660 |
+
"a|)ult", "erot1c", "erot|c", "erot!c", "ero7ic", "eroti(", "er0tic", "3rotic", "str!p",
|
661 |
+
"s7rip", "str1p", "$trip", "strip", "str|p", "5trip", "c@mgirl", "camg|rl", "camg1rl",
|
662 |
+
"(amgirl", "cam9irl", "c4mgirl", "camgir1", "camgir|", "camg!rl", "feti$h", "fet1sh", "feti5h",
|
663 |
+
"fetis#", "f3tish", "fe7ish", "fetish", "fet!sh", "fet|sh",
|
664 |
+
# New Sexual Harassment keywords and variations (fourth block)
|
665 |
+
"perv", "p3rv", "(reep", "creep", "cr33p", "mo1est", "molest", "mole$t", "m0lest",
|
666 |
+
"mo|est", "mol3st", "moles7", "mole5t", "gr0pe", "9rope", "grop3", "grope", "h@r@ss",
|
667 |
+
"harass", "hara55", "h4r4ss", "#arass", "hara$$", "c4tc4ll", "ca7call", "catca11", "catca||",
|
668 |
+
"c@tc@ll", "(at(all", "catcall", "pre|)ator", "pred4tor", "pred@tor", "preda7or", "pr3dator",
|
669 |
+
"predat0r", "predator", "sta1ker", "st@lker", "stalk3r", "$talker", "st4lker", "s7alker",
|
670 |
+
"5talker", "stalker", "sta|ker", "m1sogyn1st", "misogynis7", "misogynist", "m|sogyn|st",
|
671 |
+
"m!sogyn!st", "mi$ogyni$t", "miso9ynist", "mis0gynist", "mi5ogyni5t", "exp0se", "expose",
|
672 |
+
"3xpos3", "expo$e", "expo5e",
|
673 |
+
# New Dangerous Content keywords and variations (fourth block)
|
674 |
+
"b0mb", "8om8", "k!ll", "k1ll", "ki||", "ki11", "k|ll", "kill", "atta(k", "a77ack",
|
675 |
+
"@tt@ck", "4tt4ck", "terr0r", "t3rror", "7error", "shoo7", "sh00t", "$hoot", "5hoot",
|
676 |
+
"s#oot", "$tab", "st4b", "st@b", "5tab", "sta8", "s7ab", "exp|osive", "expl0sive",
|
677 |
+
"explosive", "3xplosiv3", "explos!ve", "explos1ve", "explo5ive", "explos|ve", "explo$ive",
|
678 |
+
"exp1osive", "assass|nate", "assassinat3", "assass!nate", "assass1nate", "a55a55inate",
|
679 |
+
"assassina7e", "assassinate", "@ss@ssin@te", "4ss4ssin4te", "a$$a$$inate", "massacr3", "massa(re",
|
680 |
+
"ma$$acre", "m4ss4cre", "m@ss@cre", "ma55acre", "massacre", "$uicide", "suicide", "su1c1de",
|
681 |
+
"suicid3", "su|c|de", "sui(ide", "suici|)e", "5uicide", "su!c!de", "#omicide", "hom!c!de",
|
682 |
+
"hom|c|de", "homicid3", "homicide", "h0micide", "homi(ide", "homici|)e", "hom1c1de", "7or7ure",
|
683 |
+
"torture", "tortur3", "t0rture", "ra|)ical", "r4dic4l", "rad1cal", "radica1", "radica|",
|
684 |
+
"rad!cal", "rad|cal", "radical", "radi(al", "r@dic@l", "beheadin9", "8eheading",
|
685 |
+
"behea|)ing", "b3h3ading", "behead|ng", "beheading", "behead!ng", "be#eading", "behe4ding",
|
686 |
+
"behe@ding", "behead1ng", "extrem|st", "extrem!st", "3xtr3mist", "extremi$t", "ex7remis7",
|
687 |
+
"extremist", "extrem1st", "extremi5t", "r|ot", "r1ot", "rio7", "r!ot", "ri0t", "traff|ck|ng",
|
688 |
+
"tr@fficking", "traff!ck!ng", "traff1ck1ng", "7rafficking", "tr4fficking", "traffi(king",
|
689 |
+
"trafficking", "traffickin9", "k|dnap", "ki|)nap", "kidn@p", "kidn4p", "k!dnap", "k1dnap",
|
690 |
+
"arson", "ar5on", "ar$on", "4rson", "ars0n",
|
691 |
+
# New Harmful Content keywords and variations (fifth block)
|
692 |
+
"s3lf-harm", "se|f-harm", "self-h4rm", "self-h@rm", "5elf-harm", "self-#arm", "$elf-harm",
|
693 |
+
"se1f-harm", "self-harm", "cutting", "cuttin9", "cutt!ng", "(utting", "cutt1ng", "cu77ing",
|
694 |
+
"cutt|ng", "burn1ng", "burnin9", "burn!ng", "8urning", "burn|ng", "burning", "pa!n",
|
695 |
+
"p4in", "p@in", "pain", "pa1n", "pa|n", "s7arva7ion", "5starvation", "st4rv4tion", "starvat1on",
|
696 |
+
"starvat!on", "starvation", "starvat|on", "starvati0n", "$tarvation", "st@rv@tion", "overdose",
|
697 |
+
"0verd0se", "ov3rdos3", "over|)ose", "overdo5e", "overdo$e", "|)epresse|)", "d3pr3ss3d",
|
698 |
+
"depre55ed", "depressed", "depre$$ed", "d|e", "die", "d!e", "di3", "|)ie", "d1e", "jump",
|
699 |
+
"hang", "#ang", "h4ng", "han9", "h@ng", "poison", "po!son", "p0is0n", "poi5on", "poi$on",
|
700 |
+
"po1son", "po|son", "(hloroform", "chloroform", "ch|oroform", "ch1oroform", "c#loroform",
|
701 |
+
"chl0r0f0rm", "drug abu5e", "dru9 abuse", "drug abuse", "|)rug abuse", "drug abu$e", "drug 4buse",
|
702 |
+
"drug abus3", "drug @buse", "drug a8use", "@ddict", "4ddict", "add!ct", "addict", "a|)|)ict",
|
703 |
+
"addic7", "add1ct", "add|ct", "addi(t", "opioid", "0pi0id", "op1o1d", "op|o|d", "opioi|)",
|
704 |
+
"op!o!d", "fentanyl", "f3ntanyl", "fentany|", "fen7anyl", "fent@nyl", "fent4nyl", "fentany1",
|
705 |
+
"meth", "met#", "m3th", "me7h", "coca1ne", "cocain3", "cocaine", "coc4ine", "(o(aine",
|
706 |
+
"coc@ine", "coca!ne", "coca|ne", "c0caine", "h3roin", "her0in", "heroin", "#eroin", "hero|n",
|
707 |
+
"hero!n", "hero1n",
|
708 |
+
# New Hate Speech keywords and variations (fifth block)
|
709 |
+
"n@zi", "naz1", "naz!", "nazi", "na2i", "naz|", "n4zi", "kkk", "suprema(y", "$upremacy",
|
710 |
+
"suprem4cy", "suprem@cy", "supr3macy", "5upremacy", "supremacy", "gen0cide", "genoc1de",
|
711 |
+
"genoci|)e", "genocide", "genoc|de", "geno(ide", "9enocide", "g3nocid3", "genoc!de", "big0t",
|
712 |
+
"bigot", "b|got", "bi9ot", "bigo7", "b!got", "8igot", "b1got", "#omop#obe", "homophobe",
|
713 |
+
"homophob3", "homopho8e", "h0m0ph0be", "xenophobe", "xenopho8e", "xenop#obe", "x3nophob3",
|
714 |
+
"xen0ph0be", "antifa", "bootlicker", "tankie", "baiter", "griefer", "kek", "pepe", "zoomer",
|
715 |
+
# New Slang Abuses & Offensive Insults (fifth block)
|
716 |
+
"bit(h", "8itch", "b|tch", "b1tch", "bi7ch", "bastar|", "b@st@rd", "ba5tard", "bas7ard",
|
717 |
+
"ba$tard", "b4st4rd", "8astard", "assho1e", "assho|e", "a$$hole", "ass#ole", "asshol3", "4sshole",
|
718 |
+
"a55hole", "assh0le", "pr1ck", "pr|ck", "pr!ck", "prick", "|)umbass", "dumba55", "dumb4ss",
|
719 |
+
"dumba$$", "dum8ass", "dumb@ss", "retar|", "r3tard", "re7ard", "ret@rd", "ret4rd", "|)ipshit",
|
720 |
+
"d|psh|t", "dipshi7", "dip5hit", "dips#it", "d!psh!t", "dipshit", "dip$hit", "d1psh1t", "j@ck@ss",
|
721 |
+
"wank3r", "w@nker", "w4nker", "tw4t", "tw@t", "7wa7", "shi7head", "shithe@d", "shith3ad",
|
722 |
+
"5hithead", "s#it#ead", "sh!thead", "sh1thead", "shithea|", "shithe4d", "$hithead",
|
723 |
+
# New General Abuses (fifth block)
|
724 |
+
"|d|ot", "idi0t", "1d1ot", "idio7", "idiot", "i|)iot", "!d!ot", "m0r0n", "moron", "lo5er",
|
725 |
+
"|oser", "1oser", "loser", "l0ser", "los3r", "5cum", "s(um", "$cum", "worthl3ss", "wort#less",
|
726 |
+
"worth|ess", "worthle$$", "wor7hless", "worthless", "worthle55", "worth1ess", "w0rthless",
|
727 |
+
# Additional new keywords from the latest list (General Abusive Language)
|
728 |
+
"16+", "18+", "alcohol", "amerifag", "assault", "b!tch", "bstard", "burn yourself", "c!nt",
|
729 |
+
"christfucker", "cnt", "cocaine", "creep", "cut yourself", "die in a hole", "die now", "dipshit",
|
730 |
+
"drink bleach", "drop dead", "dumbfuck", "fuck off", "fucker", "fucking idiot", "fuk", "get drunk",
|
731 |
+
"go hang yourself", "hymie", "i will ban you", "i will bomb the place", "i will fuck you",
|
732 |
+
"i will kill you", "jew", "jewboy", "moslemfucker", "marijuana", "massacre", "meth", "molest",
|
733 |
+
"naked", "obongo", "overdose", "penis", "perv", "pervert", "rape you", "rat poison", "s3x",
|
734 |
+
"sandnigger", "screw you", "secks", "self-harm", "sex offender", "sexual predator", "sx",
|
735 |
+
"take pills", "terrorist", "tits", "tranny", "twat", "vag", "vagina", "vodka", "x", "xxx",
|
736 |
+
"you will get raped", "you're a piece of shit", "you're banned forever", "you're crazy",
|
737 |
+
"you're hallucinating", "you're such a cunt", "you're worthless",
|
738 |
+
# New Sexually Explicit keywords and variations (fifth block)
|
739 |
+
"p0rn", "nu|)e", "nud3", "5ex", "$ex", "s3x", "xxx", "hardc0re", "h@rdcore", "hardcor3", "#ardcore",
|
740 |
+
"har|)core", "hard(ore", "h4rdcore", "adu1t", "adul7", "adu|t", "@dult", "adult", "4dult",
|
741 |
+
"a|)ult", "erot1c", "erot|c", "erot!c", "ero7ic", "eroti(", "er0tic", "3rotic", "str!p",
|
742 |
+
"s7rip", "str1p", "$trip", "strip", "str|p", "5trip", "c@mgirl", "camg|rl", "camg1rl",
|
743 |
+
"(amgirl", "cam9irl", "c4mgirl", "camgir1", "camgir|", "camg!rl", "feti$h", "fet1sh", "feti5h",
|
744 |
+
"fetis#", "f3tish", "fe7ish", "fetish", "fet!sh", "fet|sh",
|
745 |
+
# New Sexual Harassment keywords and variations (fifth block)
|
746 |
+
"perv", "p3rv", "(reep", "creep", "cr33p", "mo1est", "molest", "mole$t", "m0lest",
|
747 |
+
"mo|est", "mol3st", "moles7", "mole5t", "gr0pe", "9rope", "grop3", "grope", "h@r@ss",
|
748 |
+
"harass", "hara55", "h4r4ss", "#arass", "hara$$", "c4tc4ll", "ca7call", "catca11", "catca||",
|
749 |
+
"c@tc@ll", "(at(all", "catcall", "pre|)ator", "pred4tor", "pred@tor", "preda7or", "pr3dator",
|
750 |
+
"predat0r", "predator", "sta1ker", "st@lker", "stalk3r", "$talker", "st4lker", "s7alker",
|
751 |
+
"5talker", "stalker", "sta|ker", "m1sogyn1st", "misogynis7", "misogynist", "m|sogyn|st",
|
752 |
+
"m!sogyn!st", "mi$ogyni$t", "miso9ynist", "mis0gynist", "mi5ogyni5t", "exp0se", "expose",
|
753 |
+
"3xpos3", "expo$e", "expo5e",
|
754 |
+
# New Dangerous Content keywords and variations (fifth block)
|
755 |
+
"b0mb", "8om8", "k!ll", "k1ll", "ki||", "ki11", "k|ll", "kill", "atta(k", "a77ack",
|
756 |
+
"@tt@ck", "4tt4ck", "terr0r", "t3rror", "7error", "shoo7", "sh00t", "$hoot", "5hoot",
|
757 |
+
"s#oot", "$tab", "st4b", "st@b", "5tab", "sta8", "s7ab", "exp|osive", "expl0sive",
|
758 |
+
"explosive", "3xplosiv3", "explos!ve", "explos1ve", "explo5ive", "explos|ve", "explo$ive",
|
759 |
+
"exp1osive", "assass|nate", "assassinat3", "assass!nate", "assass1nate", "a55a55inate",
|
760 |
+
"assassina7e", "assassinate", "@ss@ssin@te", "4ss4ssin4te", "a$$a$$inate", "massacr3", "massa(re",
|
761 |
+
"ma$$acre", "m4ss4cre", "m@ss@cre", "ma55acre", "massacre", "$uicide", "suicide", "su1c1de",
|
762 |
+
"suicid3", "su|c|de", "sui(ide", "suici|)e", "5uicide", "su!c!de", "#omicide", "hom!c!de",
|
763 |
+
"hom|c|de", "homicid3", "homicide", "h0micide", "homi(ide", "homici|)e", "hom1c1de", "7or7ure",
|
764 |
+
"torture", "tortur3", "t0rture", "ra|)ical", "r4dic4l", "rad1cal", "radica1", "radica|",
|
765 |
+
"rad!cal", "rad|cal", "radical", "radi(al", "r@dic@l", "beheadin9", "8eheading",
|
766 |
+
"behea|)ing", "b3h3ading", "behead|ng", "beheading", "behead!ng", "be#eading", "behe4ding",
|
767 |
+
"behe@ding", "behead1ng", "extrem|st", "extrem!st", "3xtr3mist", "extremi$t", "ex7remis7",
|
768 |
+
"extremist", "extrem1st", "extremi5t", "r|ot", "r1ot", "rio7", "r!ot", "ri0t", "traff|ck|ng",
|
769 |
+
"tr@fficking", "traff!ck!ng", "traff1ck1ng", "7rafficking", "tr4fficking", "traffi(king",
|
770 |
+
"trafficking", "traffickin9", "k|dnap", "ki|)nap", "kidn@p", "kidn4p", "k!dnap", "k1dnap",
|
771 |
+
"arson", "ar5on", "ar$on", "4rson", "ars0n",
|
772 |
+
# New Harmful Content keywords and variations (sixth block)
|
773 |
+
"s3lf-harm", "se|f-harm", "self-h4rm", "self-h@rm", "5elf-harm", "self-#arm", "$elf-harm",
|
774 |
+
"se1f-harm", "self-harm", "cutting", "cuttin9", "cutt!ng", "(utting", "cutt1ng", "cu77ing",
|
775 |
+
"cutt|ng", "burn1ng", "burnin9", "burn!ng", "8urning", "burn|ng", "burning", "pa!n",
|
776 |
+
"p4in", "p@in", "pain", "pa1n", "pa|n", "s7arva7ion", "5starvation", "st4rv4tion", "starvat1on",
|
777 |
+
"starvat!on", "starvation", "starvat|on", "starvati0n", "$tarvation", "st@rv@tion", "overdose",
|
778 |
+
"0verd0se", "ov3rdos3", "over|)ose", "overdo5e", "overdo$e", "|)epresse|)", "d3pr3ss3d",
|
779 |
+
"depre55ed", "depressed", "depre$$ed", "d|e", "die", "d!e", "di3", "|)ie", "d1e", "jump",
|
780 |
+
"hang", "#ang", "h4ng", "han9", "h@ng", "poison", "po!son", "p0is0n", "poi5on", "poi$on",
|
781 |
+
"po1son", "po|son", "(hloroform", "chloroform", "ch|oroform", "ch1oroform", "c#loroform",
|
782 |
+
"chl0r0f0rm", "drug abu5e", "dru9 abuse", "drug abuse", "|)rug abuse", "drug abu$e", "drug 4buse",
|
783 |
+
"drug abus3", "drug @buse", "drug a8use", "@ddict", "4ddict", "add!ct", "addict", "a|)|)ict",
|
784 |
+
"addic7", "add1ct", "add|ct", "addi(t", "opioid", "0pi0id", "op1o1d", "op|o|d", "opioi|)",
|
785 |
+
"op!o!d", "fentanyl", "f3ntanyl", "fentany|", "fen7anyl", "fent@nyl", "fent4nyl", "fentany1",
|
786 |
+
"meth", "met#", "m3th", "me7h", "coca1ne", "cocain3", "cocaine", "coc4ine", "(o(aine",
|
787 |
+
"coc@ine", "coca!ne", "coca|ne", "c0caine", "h3roin", "her0in", "heroin", "#eroin", "hero|n",
|
788 |
+
"hero!n", "hero1n",
|
789 |
+
# New Hate Speech keywords and variations (sixth block)
|
790 |
+
"n@zi", "naz1", "naz!", "nazi", "na2i", "naz|", "n4zi", "kkk", "suprema(y", "$upremacy",
|
791 |
+
"suprem4cy", "suprem@cy", "supr3macy", "5upremacy", "supremacy", "gen0cide", "genoc1de",
|
792 |
+
"genoci|)e", "genocide", "genoc|de", "geno(ide", "9enocide", "g3nocid3", "genoc!de", "big0t",
|
793 |
+
"bigot", "b|got", "bi9ot", "bigo7", "b!got", "8igot", "b1got", "#omop#obe", "homophobe",
|
794 |
+
"homophob3", "homopho8e", "h0m0ph0be", "xenophobe", "xenopho8e", "xenop#obe", "x3nophob3",
|
795 |
+
"xen0ph0be", "antifa", "bootlicker", "tankie", "baiter", "griefer", "kek", "pepe", "zoomer",
|
796 |
+
# New Slang Abuses & Offensive Insults (sixth block)
|
797 |
+
"bit(h", "8itch", "b|tch", "b1tch", "bi7ch", "bastar|", "b@st@rd", "ba5tard", "bas7ard",
|
798 |
+
"ba$tard", "b4st4rd", "8astard", "assho1e", "assho|e", "a$$hole", "ass#ole", "asshol3", "4sshole",
|
799 |
+
"a55hole", "assh0le", "pr1ck", "pr|ck", "pr!ck", "prick", "|)umbass", "dumba55", "dumb4ss",
|
800 |
+
"dumba$$", "dum8ass", "dumb@ss", "retar|", "r3tard", "re7ard", "ret@rd", "ret4rd", "|)ipshit",
|
801 |
+
"d|psh|t", "dipshi7", "dip5hit", "dips#it", "d!psh!t", "dipshit", "dip$hit", "d1psh1t", "j@ck@ss",
|
802 |
+
"wank3r", "w@nker", "w4nker", "tw4t", "tw@t", "7wa7", "shi7head", "shithe@d", "shith3ad",
|
803 |
+
"5hithead", "s#it#ead", "sh!thead", "sh1thead", "shithea|", "shithe4d", "$hithead",
|
804 |
+
# New General Abuses (sixth block)
|
805 |
+
"|d|ot", "idi0t", "1d1ot", "idio7", "idiot", "i|)iot", "!d!ot", "m0r0n", "moron", "lo5er",
|
806 |
+
"|oser", "1oser", "loser", "l0ser", "los3r", "5cum", "s(um", "$cum", "worthl3ss", "wort#less",
|
807 |
+
"worth|ess", "worthle$$", "wor7hless", "worthless", "worthle55", "worth1ess", "w0rthless",
|
808 |
+
# Additional new keywords from the latest list (General Abusive Language)
|
809 |
+
"16+", "18+", "alcohol", "amerifag", "assault", "b!tch", "bstard", "burn yourself", "c!nt",
|
810 |
+
"christfucker", "cnt", "cocaine", "creep", "cut yourself", "die in a hole", "die now", "dipshit",
|
811 |
+
"drink bleach", "drop dead", "dumbfuck", "fuck off", "fucker", "fucking idiot", "fuk", "get drunk",
|
812 |
+
"go hang yourself", "hymie", "i will ban you", "i will bomb the place", "i will fuck you",
|
813 |
+
"i will kill you", "jew", "jewboy", "moslemfucker", "marijuana", "massacre", "meth", "molest",
|
814 |
+
"naked", "obongo", "overdose", "penis", "perv", "pervert", "rape you", "rat poison", "s3x",
|
815 |
+
"sandnigger", "screw you", "secks", "self-harm", "sex offender", "sexual predator", "sx",
|
816 |
+
"take pills", "terrorist", "tits", "tranny", "twat", "vag", "vagina", "vodka", "x", "xxx",
|
817 |
+
"you will get raped", "you're a piece of shit", "you're banned forever", "you're crazy",
|
818 |
+
"you're hallucinating", "you're such a cunt", "you're worthless"
|
819 |
+
]
|
820 |
+
|
821 |
+
def contains_banned_keyword(self, text):
|
822 |
+
"""Check if the input text contains any banned keywords."""
|
823 |
+
text_lower = text.lower()
|
824 |
+
for keyword in self.banned_keywords:
|
825 |
+
if keyword in text_lower:
|
826 |
+
return True
|
827 |
+
return False
|
828 |
+
|
829 |
def preprocess(self, text):
|
830 |
encoding = self.tokenizer.encode(text)
|
831 |
ids = encoding.ids[:self.max_len]
|
|
|
833 |
return np.array(ids + padding, dtype=np.int64).reshape(1, -1)
|
834 |
|
835 |
def predict(self, text):
|
836 |
+
# First check if the text contains any banned keywords
|
837 |
+
if self.contains_banned_keyword(text):
|
838 |
+
return {
|
839 |
+
'label': 'Inappropriate Content',
|
840 |
+
'confidence': 1.0,
|
841 |
+
'probabilities': [1.0, 0.0], # Assuming [inappropriate, appropriate]
|
842 |
+
'keyword_matched': True # Flag to indicate keyword match
|
843 |
+
}
|
844 |
+
|
845 |
+
# If no banned keywords, proceed with model prediction
|
846 |
# Preprocess
|
847 |
input_array = self.preprocess(text)
|
848 |
|
|
|
862 |
return {
|
863 |
'label': class_labels[predicted_class],
|
864 |
'confidence': float(probabilities[0][predicted_class]),
|
865 |
+
'probabilities': probabilities[0].tolist(),
|
866 |
+
'keyword_matched': False # Flag to indicate model prediction
|
867 |
}
|
868 |
|
869 |
# Example usage
|
|
|
873 |
|
874 |
# Example texts for testing
|
875 |
example_texts = [
|
876 |
+
"You're a worthless piece of garbage who should die",
|
877 |
+
"Hello, how are you doing today?"
|
878 |
]
|
879 |
|
880 |
for text in example_texts:
|
881 |
result = pipeline.predict(text)
|
882 |
print(f"Input: {text}")
|
883 |
+
print(f"Prediction: {result['label']}")
|
884 |
+
if result['keyword_matched']:
|
885 |
+
print("(Detected by keyword filter)")
|
886 |
+
else:
|
887 |
+
print(f"Confidence: {result['confidence']:.2%}")
|
888 |
print("-" * 80)
|
889 |
|
890 |
# Define a function for Gradio to use
|
891 |
def gradio_predict(text):
|
892 |
result = pipeline.predict(text)
|
893 |
+
if result['keyword_matched']:
|
894 |
+
return f"Prediction: {result['label']} (Detected by keyword filter)"
|
895 |
+
else:
|
896 |
+
return f"Prediction: {result['label']} (Confidence: {result['confidence']:.2%})"
|
897 |
|
898 |
# Create a Gradio interface
|
899 |
iface = gr.Interface(
|
|
|
909 |
),
|
910 |
examples=[
|
911 |
# Explicitly offensive examples
|
912 |
+
"Congrats, you fuckbrain arsehole, you've outdone yourself in stupidity. A real cock-up of a human—should we clap for your bollocks-faced greatness or just pity you?",
|
913 |
+
"You're a mad bastard, but I'd still grab a beer with you! Fuck around all you like, you cockheaded legend—your arsehole antics are bloody brilliant.",
|
914 |
"Your mother should have done better raising such a useless idiot.",
|
915 |
|
916 |
# Neutral or appropriate examples
|
917 |
+
"Hello HR, I hope this message finds you well. I'm writing to express my gratitude for the opportunity to interview for the Financial Analyst position last week. It was a pleasure to meet you and learn more about the role and your team.",
|
918 |
+
"Thank you for your time and consideration. Please don't hesitate to reach out if you need additional information—I'd be happy to discuss further. Looking forward to hearing from you soon!",
|
919 |
+
"The weather today is lovely, and I'm looking forward to a productive day at work.",
|
920 |
|
921 |
# Mixed examples (some offensive, some neutral)
|
922 |
+
"I appreciate your help, but honestly, you're such a clueless idiot sometimes. Still, thanks for trying."
|
923 |
]
|
924 |
)
|
925 |
|