#!/usr/bin/env python3
"""
Decoder for Paul Butler's emoji steganography method
Usage: python3 decoder.py "🥜[encoded-text]"
"""

import sys

def variation_selector_to_byte(char):
    """Convert a variation selector character back to its byte value"""
    code = ord(char)
    
    # Original variation selectors (VS1-VS16): U+FE00 to U+FE0F
    if 0xFE00 <= code <= 0xFE0F:
        return code - 0xFE00
    # Supplementary variation selectors (VS17-VS256): U+E0100 to U+E01EF  
    elif 0xE0100 <= code <= 0xE01EF:
        return code - 0xE0100 + 16
    else:
        return None

def decode_emoji_text(encoded_text):
    """Decode hidden text from emoji with variation selectors"""
    bytes_data = []
    found_variation_selector = False
    
    for char in encoded_text:
        byte_val = variation_selector_to_byte(char)
        if byte_val is not None:
            bytes_data.append(byte_val)
            found_variation_selector = True
        elif found_variation_selector:
            # Stop when we hit a non-variation selector after finding some
            break
    
    try:
        return bytes(bytes_data).decode('utf-8')
    except UnicodeDecodeError:
        return f"Raw bytes: {bytes_data}"

if __name__ == "__main__":
    if len(sys.argv) < 2 or len(sys.argv) > 3:
        print("Usage: python3 decoder.py '<encoded-emoji-text>' [output-file]")
        print("  If no output file specified, uses 'decoded_output.txt'")
        sys.exit(1)
    
    encoded = sys.argv[1]
    output_file = sys.argv[2] if len(sys.argv) == 3 else "decoded_output.txt"
    
    decoded = decode_emoji_text(encoded)
    
    # Write results to file
    with open(output_file, 'w', encoding='utf-8') as f:
        f.write("=== EMOJI STEGANOGRAPHY DECODER RESULTS ===\n\n")
        f.write(f"Encoded text: {encoded}\n\n")
        f.write(f"Decoded result:\n{decoded}\n\n")
        
        # Unicode breakdown
        f.write("=== CHARACTER ANALYSIS ===\n")
        for i, char in enumerate(encoded):
            code = ord(char)
            vs_byte = variation_selector_to_byte(char)
            if vs_byte is not None:
                printable_char = chr(vs_byte) if 32 <= vs_byte <= 126 else f'\\x{vs_byte:02x}'
                f.write(f"  {i:3d}: U+{code:04X} -> byte {vs_byte:3d} ('{printable_char}')\n")
            else:
                f.write(f"  {i:3d}: U+{code:04X} '{char}' (base character)\n")
    
    print(f"✓ Decoding complete! Results saved to: {output_file}")
    print(f"✓ Decoded {len([c for c in encoded if variation_selector_to_byte(c) is not None])} hidden bytes")
    print(f"✓ Preview: {decoded[:100]}{'...' if len(decoded) > 100 else ''}")