encoding.py

import codecs
import locale
import re
import sys
from typing import List, Tuple

BOMS: List[Tuple[bytes, str]] = [
    (codecs.BOM_UTF8, "utf-8"),
    (codecs.BOM_UTF16, "utf-16"),
    (codecs.BOM_UTF16_BE, "utf-16-be"),
    (codecs.BOM_UTF16_LE, "utf-16-le"),
    (codecs.BOM_UTF32, "utf-32"),
    (codecs.BOM_UTF32_BE, "utf-32-be"),
    (codecs.BOM_UTF32_LE, "utf-32-le"),
]

ENCODING_RE = re.compile(rb"coding[:=]\s*([-\w.]+)")


def auto_decode(data: bytes) -> str:
    """Check a bytes string for a BOM to correctly detect the encoding

    Fallback to locale.getpreferredencoding(False) like open() on Python3"""
    for bom, encoding in BOMS:
        if data.startswith(bom):
            return data[len(bom) :].decode(encoding)
    # Lets check the first two lines as in PEP263
    for line in data.split(b"\n")[:2]:
        if line[0:1] == b"#" and ENCODING_RE.search(line):
            result = ENCODING_RE.search(line)
            assert result is not None
            encoding = result.groups()[0].decode("ascii")
            return data.decode(encoding)
    return data.decode(
        locale.getpreferredencoding(False) or sys.getdefaultencoding(),
    )