diff options
Diffstat (limited to 'Lib/lib2to3/pgen2')
| -rw-r--r-- | Lib/lib2to3/pgen2/tokenize.py | 19 |
1 files changed, 10 insertions, 9 deletions
diff --git a/Lib/lib2to3/pgen2/tokenize.py b/Lib/lib2to3/pgen2/tokenize.py index 7ae0280..701daf8 100644 --- a/Lib/lib2to3/pgen2/tokenize.py +++ b/Lib/lib2to3/pgen2/tokenize.py @@ -253,14 +253,16 @@ def detect_encoding(readline): in. It detects the encoding from the presence of a utf-8 bom or an encoding - cookie as specified in pep-0263. If both a bom and a cookie are present, - but disagree, a SyntaxError will be raised. If the encoding cookie is an - invalid charset, raise a SyntaxError. + cookie as specified in pep-0263. If both a bom and a cookie are present, but + disagree, a SyntaxError will be raised. If the encoding cookie is an invalid + charset, raise a SyntaxError. Note that if a utf-8 bom is found, + 'utf-8-sig' is returned. If no encoding is specified, then the default of 'utf-8' will be returned. """ bom_found = False encoding = None + default = 'utf-8' def read_or_stop(): try: return readline() @@ -287,17 +289,16 @@ def detect_encoding(readline): if codec.name != 'utf-8': # This behaviour mimics the Python interpreter raise SyntaxError('encoding problem: utf-8') - else: - # Allow it to be properly encoded and decoded. - encoding = 'utf-8-sig' + encoding += '-sig' return encoding first = read_or_stop() if first.startswith(BOM_UTF8): bom_found = True first = first[3:] + default = 'utf-8-sig' if not first: - return 'utf-8', [] + return default, [] encoding = find_cookie(first) if encoding: @@ -305,13 +306,13 @@ def detect_encoding(readline): second = read_or_stop() if not second: - return 'utf-8', [first] + return default, [first] encoding = find_cookie(second) if encoding: return encoding, [first, second] - return 'utf-8', [first, second] + return default, [first, second] def untokenize(iterable): """Transform tokens back into Python source code. |