mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-08-22 09:45:06 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 13

Issue #18873: The tokenize module, IDLE, 2to3, and the findnocoding.py script

Browse source 
now detect Python source code encoding only in comment lines.
This commit is contained in:
Serhiy Storchaka 2013-09-16 23:51:56 +03:00
parent 975fce3788
commit dafea85190
9 changed files with 44 additions and 22 deletions
Download patch file Download diff file Expand all files Collapse all files

8
Lib/tokenize.py
View file

@ -31,7 +31,7 @@ from token import *
from codecs import lookup, BOM_UTF8
import collections
from io import TextIOWrapper
cookie_re = re.compile("coding[:=]\s*([-\w.]+)")
cookie_re = re.compile(r'^[ \t\f]*#.*coding[:=][ \t]*([-\w.]+)', re.ASCII)
import token
__all__ = token.__all__ + ["COMMENT", "tokenize", "detect_encoding",
@ -372,10 +372,10 @@ def detect_encoding(readline):
msg = '{} for {!r}'.format(msg, filename)
raise SyntaxError(msg)
matches = cookie_re.findall(line_string)
if not matches:
match = cookie_re.match(line_string)
if not match:
return None
encoding = _get_normal_name(matches[0])
encoding = _get_normal_name(match.group(1))
try:
codec = lookup(encoding)
except LookupError: