East-Asian Mojibake Encoding Detection (Manual) / 亂碼轉換 / 乱码转换 / 文字化け変換

encoding_detection.py

ENCODINGS = {
    # Japanese
    'shift_jis': "Shift-JIS",
    'iso2022_jp': "ISO 2022 JP",
    # Chinese
    'big5': "Big5",
    'gbk': "GBK",
    'gb2312': "GB 2312",
    'gb18030': "GB 18030",
    # Korean
    "euc_kr": "EUC-KR",
    "iso2022_kr": "ISO 2022 KR",
    "johab": "Johab",
    "cp949": "UHC",
    # Unicode Transformation Format
    'utf_8': "UTF-8",
}

def try_decode(text: bytes, without: str):
    for encoding, encoding_name in ENCODINGS.items():
        if encoding == without:
            continue
        try:
            decoded = text.decode(encoding, 'replace')
            yield (encoding, encoding_name, decoded)
        except UnicodeDecodeError as e:
            continue

def pprint_hex(byte_str: bytes):
    return ' '.join(["%02X" % x for x in byte_str])

def try_encode(text: str, without: str):
    for encoding, encoding_name in ENCODINGS.items():
        if encoding == without:
            continue
        try:
            encoded = text.encode(encoding)
            yield (encoding, encoding_name, encoded)
        except UnicodeEncodeError as e:
            continue

def main():
    C = input()
    encoding_name_maxlen = len(max(ENCODINGS.values(), key=len))
    
    for encoding, encoding_name, encoded in try_encode(C, ""):
        print(f"Success! Encoded into { encoding_name } = ‘{pprint_hex(encoded)}’")
        for _, encoding_name_decode, decoded in try_decode(encoded, encoding):
            print(f"-- Decoded from {encoding_name_decode.ljust(encoding_name_maxlen)}: {decoded}")

if __name__ == "__main__":
    main()