mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-08-27 12:16:04 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 8

#2834: Change re module semantics, so that str and bytes mixing is forbidden,

Browse source 
and str (unicode) patterns get full unicode matching by default. The re.ASCII
flag is also introduced to ask for ASCII matching instead.
This commit is contained in:
Antoine Pitrou 2008-08-19 17:56:33 +00:00
parent 3ad7ba10a2
commit fd036451bf
37 changed files with 280 additions and 163 deletions
Download patch file Download diff file Expand all files Collapse all files

14
Lib/sre_parse.py
View file

@ -64,6 +64,7 @@ FLAGS = {
"s": SRE_FLAG_DOTALL,
"x": SRE_FLAG_VERBOSE,
# extensions
"a": SRE_FLAG_ASCII,
"t": SRE_FLAG_TEMPLATE,
"u": SRE_FLAG_UNICODE,
}
@ -672,6 +673,18 @@ def _parse(source, state):
return subpattern
def fix_flags(src, flags):
# Check and fix flags according to the type of pattern (str or bytes)
if isinstance(src, str):
if not flags & SRE_FLAG_ASCII:
flags |= SRE_FLAG_UNICODE
elif flags & SRE_FLAG_UNICODE:
raise ValueError("ASCII and UNICODE flags are incompatible")
else:
if flags & SRE_FLAG_UNICODE:
raise ValueError("can't use UNICODE flag with a bytes pattern")
return flags
def parse(str, flags=0, pattern=None):
# parse 're' pattern into list of (opcode, argument) tuples
@ -683,6 +696,7 @@ def parse(str, flags=0, pattern=None):
pattern.str = str
p = _parse_sub(source, pattern, 0)
p.pattern.flags = fix_flags(str, p.pattern.flags)
tail = source.get()
if tail == ")":