morphys

from morphys import to_unicode, to_bytes # Example 1: Convert a Unicode string to bytes unicode_string = "Hello, world! 👋" encoded_bytes = to_bytes(unicode_string, encoding="utf-8") print(f"Unicode string: {unicode_string}") print(f"Encoded bytes: {encoded_bytes}") # Example 2: Convert bytes back to a Unicode string decoded_string = to_unicode(encoded_bytes, encoding="utf-8") print(f"Decoded string: {decoded_string}") # Example 3: Handling potential non-UTF8 characters (assuming default error handling) # If 'morphys' has smart handling, it might try other encodings or use 'replace'/'ignore' # This example still explicitly uses UTF-8 and shows a common issue if characters are not valid try: latin1_bytes = b'caf\xe9' print(f"\nAttempting to decode latin1 bytes: {latin1_bytes}") decoded_from_latin1 = to_unicode(latin1_bytes, encoding="utf-8", errors="strict") print(f"Decoded with strict UTF-8: {decoded_from_latin1}") except UnicodeDecodeError as e: print(f"Error decoding with strict UTF-8 (expected): {e}") # Using 'replace' error handling for robustness decoded_from_latin1_safe = to_unicode(latin1_bytes, encoding="utf-8", errors="replace") print(f"Decoded with UTF-8 (replace errors): {decoded_from_latin1_safe}")