Viewing file:  encoding.py (1.14 KB) -rw-r--r--
Select action/file-type:
 (+) |  (+) |  (+) | Code (+) | Session (+) |  (+) | SDB (+) |  (+) |  (+) |  (+) |  (+) |  (+) |
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(br"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(),
)
|