txt2emoji

#!/usr/bin/env python
# -*- coding: utf-8 -*-

"""
This script converts text to related emojis, injecting context-relevant visual
cues into datasets. It enables the enrichment of text data with corresponding
emojis, enhancing its expressiveness and engagement. 

Before running this script, you need to download the required resources. Just open
up `python` and type:

import nltk
nltk.download('punkt_tab')
"""

import nltk
from nltk.tokenize import word_tokenize
from emoji import EMOJI_DATA
import argparse
from pathlib import Path
import re

# Download required NLTK data (only needed once)
nltk.download('punkt', quiet=True)

def get_emoji_mapping():
    """Create a mapping of words to emojis."""
    emoji_map = {}
    # Group emoji variations together
    emoji_variations = {}
    
    for emoji_char, data in EMOJI_DATA.items():
        base_emoji = data.get('base', emoji_char)  # Get base emoji or use current one
        if base_emoji not in emoji_variations:
            emoji_variations[base_emoji] = set()
        emoji_variations[base_emoji].add(emoji_char)
        
        if 'en' in data:  # If emoji has English description
            words = data['en'].lower().replace('_', ' ').split()
            for word in words:
                if word not in emoji_map:
                    emoji_map[word] = []
                emoji_map[word].append(emoji_char)
    return emoji_map, emoji_variations

def text_to_emojis(text):
    """Convert text to related emojis."""
    # Create emoji mapping and variations
    emoji_map, emoji_variations = get_emoji_mapping()
    
    # Regex pattern to match any token containing numbers
    number_pattern = re.compile(r'.*\d+.*')
    
    # Emojis to exclude
    excluded_emojis = {
        '🔶',
        '⭕',
        '🔷',
        '🔹',
        '🔸',
        '🔺',
        '🔻',
        '🔴',
        '🔵',
        '🔼',
        '🔾',
        '🇵🇬',
        '🀄',
        '🔲',
        '✅'
    }
    
    # Words to exclude from emoji conversion
    excluded_words = {
        '(',
        ')',
        'purple',
        'abdominal',
        'penetration',
        'feral',
        'body',
        'nude',
        'anthro',
        'big',
        'small',
        'the',
        'a',
        'an',
        'and',
        'or',
        'but',
        'if',
        'then',
        'because',
        'as',
        'until',
        'while',
        ',',
        'hi',
        'res',
        'pussy'
        'penetrated',
        'equine',
        'felid',
        'feline',
        'equid',
        'genital',
        'genitals',
        'penetrating',
        'medial',
        'ring',
        'inside',
        'duo',
        'solo',
        'in',
        'hair',
        'andromorph',
        'from',
        'behind',
        'position',
        'pantherine',
        'animal',
        'brown',
        'sub',
        'dom',
        'explicit',
        'black',
        'bulge',
        'dominant',
        'kousen',
        'rendan',
        'genitalia',
        'tan',
        'simple',
        'media',
        'vaginal',
        'red',
        'pecs',   
        'navel',
        'background',
        'pubes',
    }
    
    # Track used emojis and their variations
    used_emojis = set()
    
    # Additional manual mappings for common words
    custom_mappings = {
        'markings': '🏷️',
        'sweat': '💧',
        'toes': '👣',
        'teeth': '🦷',
        'fingering': '👉',
        'blush': '😊',
        'male': '♂️',
        'tiger': '🐯',
        'fluids': '💧',
        'wolf': '🐺',
        'dog': '🐶',
        'female': '♀️',
        'intersex': '⚧️',
        'muscular': '💪',
        'wheelbarrow': '🚜',
        'sex': '💑',
        'size': '📏',
        'difference': '🔢',
        'penis': '🔱',
        'paws': '🐾',
        'pawpads': '🐾',
        'hindpaw': '🐾',
        'fur': '🧥',
        'horse': '🐴',
        #'pussy': '',
        'ejaculation': '💦',
        'cum': '💦',
        'love': '❤️',
        'smaller': '🔽',
        'bigger': '🔼',
        'larger': '🔼',
        'cat': '😺',
        'cats': '😺',
        'dog': '🐶',
        'dogs': '🐶',
        'sun': '☀️',
        'moon': '🌙',
        'star': '⭐',
        'happy': '😊',
        'sad': '😢',
        'angry': '😠',
        'food': '🍔',
        'heart': '❤️',
        'fire': '🔥',
        'hot': '🔥',
        'cold': '❄️',
        'snow': '❄️',
        'rain': '🌧️',
        'smile': '😊',
        'laugh': '😂',
        'cry': '😢',
    }
    
    # Tokenize the input text
    tokens = word_tokenize(text.lower())
    
    # Store found emojis with their explanations
    found_emojis = []
    explanations = []
    
    def is_emoji_usable(emoji):
        """Check if emoji or any of its variations have been used."""
        # Find the base emoji
        base_emoji = None
        for base, variations in emoji_variations.items():
            if emoji in variations:
                base_emoji = base
                break
        
        if base_emoji:
            # Check if any variation has been used
            return not any(variation in used_emojis for variation in emoji_variations[base_emoji])
        return emoji not in used_emojis
    
    # Process each token
    for token in tokens:
        # Skip excluded words and anything containing numbers
        if token in excluded_words or number_pattern.match(token):
            continue
            
        # First check custom mappings
        if token in custom_mappings:
            emoji = custom_mappings[token]
            if emoji not in excluded_emojis and is_emoji_usable(emoji):
                found_emojis.append(emoji)
                used_emojis.add(emoji)
                explanations.append(f"'{token}' → {emoji} (custom mapping)")
            #else:
            #    explanations.append(f"'{token}' → (skipped - emoji {emoji} already used)")
            continue
            
        # Then check emoji mapping
        if token in emoji_map:
            found_match = False
            for emoji in emoji_map[token]:
                if emoji not in excluded_emojis and is_emoji_usable(emoji):
                    found_emojis.append(emoji)
                    used_emojis.add(emoji)
                    explanations.append(f"'{token}' → {emoji} (from emoji database)")
                    found_match = True
                    break
            if not found_match:
                available_emojis = [e for e in emoji_map[token] if e not in excluded_emojis]
                #if available_emojis:
                #    explanations.append(f"'{token}' → (skipped - all matching emojis {', '.join(available_emojis)} already used)")
                #else:
                #    explanations.append(f"'{token}' → (skipped - all matching emojis are excluded)")
        else:
            explanations.append(f"'{token}' → (no matching emoji found)")
    
    # Return emojis and explanations
    return ' '.join(found_emojis) if found_emojis else '', explanations

def process_file(file_path):
    """Process a single text file and create corresponding emoji and explanation files."""
    try:
        with open(file_path, 'r', encoding='utf-8') as f:
            text = f.read()
        
        emojis, explanations = text_to_emojis(text)
        
        # Create output filenames
        emoji_file = file_path.with_suffix('.emoji')
        explanation_file = file_path.with_suffix('.emoji.explain')
        
        with open(emoji_file, 'w', encoding='utf-8') as f:
            f.write(emojis)
            
        with open(explanation_file, 'w', encoding='utf-8') as f:
            f.write('\n'.join(explanations))
            
        print(f"Processed: {file_path} → {emoji_file} and {explanation_file}")
    except Exception as e:
        print(f"Error processing {file_path}: {str(e)}")

def main():
    # Set up argument parser
    parser = argparse.ArgumentParser(description='Convert text files to emoji representations')
    parser.add_argument('directory', nargs='?', default='.',
                       help='Directory to process (default: current directory)')
    
    args = parser.parse_args()
    
    # Convert to Path object and resolve to absolute path
    base_dir = Path(args.directory).resolve()
    
    if not base_dir.exists():
        print(f"Error: Directory '{base_dir}' does not exist")
        return
    
    # Find all .txt files in directory and subdirectories
    txt_files = list(base_dir.rglob('*.txt'))
    
    if not txt_files:
        print(f"No .txt files found in {base_dir}")
        return
    
    print(f"Found {len(txt_files)} .txt files to process")
    
    # Process each file
    for file_path in txt_files:
        process_file(file_path)

if __name__ == "__main__":
    main()