"""
content_moderator.py
--------------------
A tiny, dependency‑free content‑moderation utility.
Features
--------
* Detects profanity, slurs and adult‑content keywords (both EN & PT).
* Returns:
- a boolean flag (is_clean)
- a list of detected offensive tokens
- a "sanitized" version of the original text (optional)
* Configurable: you can extend the word‑lists, adjust sensitivity,
or replace the simple regex engine with a custom matcher.
Usage example
-------------
>>> from content_moderator import moderate
>>> text = "Esse cara é um babalu e fala merda pra criança."
>>> clean, hits, safe = moderate(text, return_cleaned=True)
>>> print(clean) # False
>>> print(hits) # ['babalu', 'merda']
>>> print(safe) # "Esse cara é um ***** e fala ***** pra criança."
"""
import re
from typing import List, Tuple, Optional
# ----------------------------------------------------------------------
# 1️⃣ WORD LISTS
# ----------------------------------------------------------------------
# The lists below are deliberately short; you can expand them as needed.
# They contain the most common profanity/sexually‑explicit terms in English
# and Portuguese. All entries are lower‑cased for case‑insensitive matching.
EN_PROFANITY =
"fuck", "shit", "bitch", "cunt", "asshole", "dick", "pussy",
"cum", "blowjob", "nigger", "fag", "slut", "whore"
PT_PROFANITY =
"porra", "caralho", "buceta", "pinto", "cu", "filho da puta",
"merda", "baba", "babalu", "bengala", "idiota", "piranha",
"viado", "sacanagem"
# Combine them for a single lookup set.
OFFENSIVE_WORDS = PT_PROFANITY
# ----------------------------------------------------------------------
# 2️⃣ REGEX PRE‑COMPILATION
# ----------------------------------------------------------------------
# Build a regex that matches any whole word from the set.
# \b – word boundary
# re.IGNORECASE – case‑insensitive
# re.UNICODE – proper handling of accented characters
_WORD_PATTERN = re.compile(
r"\b(" + "|".join(map(re.escape, OFFENSIVE_WORDS)) + r")\b",
flags=re.IGNORECASE | re.UNICODE,
)
# ----------------------------------------------------------------------
# 3️⃣ CORE FUNCTION
# ----------------------------------------------------------------------
def moderate(
text: str,
*,
return_hits: bool = True,
return_cleaned: bool = False,
mask_char: str = "*"
) -> Tuple[bool, Optional[List[str]], Optional[str]]:
"""
Scan *text* for offensive words.
Parameters
----------
text : str
The raw user‑generated content.
return_hits : bool, optional
If True, the function also returns a list with the matched words.
return_cleaned : bool, optional
If True, returns a sanitized version where each detected token
is replaced by ``mask_char`` repeated to the same length.
mask_char : str, optional
The character used for masking (default "*").
Returns
-------
is_clean : bool
``True`` if no offensive token was found.
hits : list[str] | None
List of detected words (lower‑cased). ``None`` when *return_hits=False*.
cleaned_text : str | None
Masked version of the original text. ``None`` when
*return_cleaned=False*.
Example
-------
>>> moderate("Oi, seu babalu!", return_cleaned=True)
(False, ['babalu'], 'Oi, seu ******!')
"""
# 1️⃣ Find all matches (case‑insensitive)
matches = _WORD_PATTERN.findall(text)
# Normalise to lower‑case for the output list
hits = [m.lower() for m in matches] if return_hits else None
# 2️⃣ Build a sanitized version if requested
cleaned = None
if return_cleaned:
def _mask(match: re.Match) -> str:
return mask_char * len(match.group(0))
cleaned = _WORD_PATTERN.sub(_mask, text)
# 3️⃣ Determine overall cleanliness
is_clean = len(matches) == 0
return is_clean, hits, cleaned
# ----------------------------------------------------------------------
# 4️⃣ QUICK DEMO (runs when executed directly)
# ----------------------------------------------------------------------
if __name__ == "__main__":
demo_sentences = [
"Esse cara é um babalu e fala merda pra criança.",
"What a beautiful day! No bad words here.",
"You are such a bitch!",
"Fala, bambambú! (just a nonsense word)",
]
for s in demo_sentences:
clean, hits, safe = moderate(s, return_cleaned=True)
print("\nOriginal :", s)
print("Is clean? :", clean)
if hits:
print("Detected :", ", ".join(hits))
if safe:
print("Sanitized :", safe)
However, I can offer some general information that might be helpful:
Given the potential cultural and specific references, if you're looking for detailed information on these topics, I recommend checking reputable sources or specific platforms that specialize in Brazilian entertainment, culture, or media. This could include news websites, cultural blogs, or official channels that produce or discuss such content. brasileirinhas kid bengala e musa babalu full
Kid Bengala Musa Babalu are associated with a specific period in the Brazilian adult entertainment industry, particularly through the production company Brasileirinhas. This era was marked by an effort to professionalize adult media in Brazil, moving toward higher production values and feature-length narratives. """ content_moderator
Clovis Basilio dos Santos, known professionally as Kid Bengala, became a well-known figure in Brazil, transcending the adult industry to appear in mainstream television, comedy programs, and public life. His persona often leaned into a mix of physical performance and a distinctive public image that made him a recognizable name in Brazilian pop culture during the early 2000s. However, I can offer some general information that
Musa Babalu was frequently cast alongside him during this time. Their collaborations were central to the marketing strategy of Brasileirinhas, which sought to create high-profile "star" pairings to compete with international adult film markets. These productions often focused on specific genres that were commercially successful at the time and helped establish the studio as a dominant force in South American adult media.
The visibility of these performers reflects a broader trend in Brazilian media during the late 90s and 2000s, where adult industry figures often crossed over into general celebrity circles, appearing at major events like Carnival. This period is often studied by media historians interested in the intersection of adult entertainment, commercial marketing, and mainstream celebrity culture in Brazil. While the content itself remains intended for adult audiences, the professional trajectory of these individuals illustrates the growth and evolution of the private entertainment sector in the country.
| Situation | Integration steps |
|-----------|-------------------|
| A web‑app (Flask/Django/FastAPI) | Import moderate in the request‑handling view, call it on incoming POST data, reject or auto‑sanitize before persisting. |
| A Discord / Telegram bot | Run moderate(message.content) for each incoming message; if is_clean is False, delete the message or warn the user. |
| A mobile game chat | Call the function on each chat packet server‑side; only forward the sanitized version to other players. |
| A classroom‑learning platform | Use return_cleaned=True to automatically hide profanity while still storing the original for moderation logs. |
def load_wordlists(json_path: str) -> None:
import json
with open(json_path, "r", encoding="utf-8") as fp:
data = json.load(fp) # "en": [...], "pt": [...]
global OFFENSIVE_WORDS, _WORD_PATTERN
OFFENSIVE_WORDS = w.lower() for w in data["en"] + data["pt"]
_WORD_PATTERN = re.compile(
r"\b(" + "|".join(map(re.escape, OFFENSIVE_WORDS)) + r")\b",
flags=re.IGNORECASE | re.UNICODE,
)