gemini-profanity-filter 0.1.0

A Python module for detecting and filtering profanity using Google's Gemini API

Gemini Profanity Filter

A Python module for detecting and filtering profanity in text using Google's Gemini API. The module can identify standard and obfuscated profanity across multiple languages.

Features

• Detects standard profanity in multiple languages
• Identifies obfuscated profanity (character substitutions, leetspeak, etc.)
• Handles stretched or repeated characters
• Detects deliberately fragmented words
• Works with mixed case patterns
• Processes context-sensitive profanity
• Language-specific profanity patterns including Cyrillic, Asian scripts, etc.

Installation

pip install gemini-profanity-filter

Usage

from gemini_profanity_filter import ProfanityFilter

# Initialize with your API key
filter = ProfanityFilter(api_key="your_api_key")

# Filter text
result = filter.filter_text("Text to be filtered")

# Access results
if result:
    print(f"Filtered text: {result.filtered_text}")
    print(f"Detected profanity instances: {result.detected_count}")
    
    # Print details about detected instances
    for instance in result.detected_profanity:
        print(f"Original form: {instance.original_form}")
        print(f"Normalized form: {instance.normalized_form}")
        print(f"Detection method: {instance.detection_method}")
        print(f"Confidence score: {instance.confidence_score}")
    
    # Get detected languages
    print(f"Languages detected: {', '.join(result.languages_detected)}")

Requirements

• Python 3.7 or higher
• Google GenerativeAI Python library
• A valid Google Gemini API key

License

MIT