(b'\xff\xfe', 'utf-16-le'),
(b'\xfe\xff', 'utf-16-be'),
]
+
+ encoding = 'utf-8'
for bom, enc in BOMS:
- if first_bytes.startswith(bom):
- s = first_bytes[len(bom):].decode(enc, 'replace')
- break
- else:
- s = first_bytes.decode('utf-8', 'replace')
+ while first_bytes.startswith(bom):
+ encoding, first_bytes = enc, first_bytes[len(bom):]
- return re.match(r'^\s*<', s)
+ return re.match(r'^\s*<', first_bytes.decode(encoding, 'replace'))
def determine_protocol(info_dict):