def _detect_encoding_by_bom(
sample: typing.AnyStr,
default: typing.Optional[str] = None) -> typing.Optional[str]:
"""
Detects the encoding of a `sample` string, among various Unicode
variants, by looking at the BOM (Byte Order Mark) as defined in
the `codecs` module.
"""
# JSON always starts with two ASCII characters, so detection is as
# easy as counting the nulls and from their location and count
# determine the encoding. Also detect a BOM, if present.
sample = sample[:4]
if sample in (codecs.BOM_UTF32_LE, codecs.BOM_UTF32_BE):
return 'utf-32' # BOM included
if sample[:3] == codecs.BOM_UTF8:
return 'utf-8-sig' # BOM included, MS style (discouraged)
if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
return 'utf-16' # BOM included
nullcount = sample.count(_null)
if nullcount == 0:
return default
if nullcount == 2:
if sample[::2] == _null2: # 1st and 3rd are null
return 'utf-16-be'
if sample[1::2] == _null2: # 2nd and 4th are null
return 'utf-16-le'
# Did not detect 2 valid UTF-16 ascii-range characters
if nullcount == 3:
if sample[:3] == _null3:
return 'utf-32-be'
if sample[1:] == _null3:
return 'utf-32-le'
# Did not detect a valid UTF-32 ascii-range character
return default
def charCountBiggerEqualThanX(text: typing.AnyStr, cha: typing.AnyStr):
res = text.count(cha)
if debug:
print(res)
return res
