mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-07-29 14:15:07 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 9

[3.13] gh-126505: Fix bugs in compiling case-insensitive character classes (GH-126557) (GH-126689)

Browse source 
* upper-case non-BMP character was ignored
* the ASCII flag was ignored when matching a character range whose
  upper bound is beyond the BMP region
(cherry picked from commit 819830f34a)

Co-authored-by: Serhiy Storchaka <storchaka@gmail.com>
This commit is contained in:
Miss Islington (bot) 2024-11-11 17:54:57 +01:00 • committed by GitHub
parent fc10908f7d
commit 7db6d4282f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 73 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

23
Lib/re/_compiler.py
View file

@ -248,11 +248,11 @@ def _optimize_charset(charset, iscased=None, fixup=None, fixes=None):
while True:
try:
if op is LITERAL:
if fixup:
lo = fixup(av)
charmap[lo] = 1
if fixes and lo in fixes:
for k in fixes[lo]:
if fixup: # IGNORECASE and not LOCALE
av = fixup(av)
charmap[av] = 1
if fixes and av in fixes:
for k in fixes[av]:
charmap[k] = 1
if not hascased and iscased(av):
hascased = True
@ -260,7 +260,7 @@ def _optimize_charset(charset, iscased=None, fixup=None, fixes=None):
charmap[av] = 1
elif op is RANGE:
r = range(av[0], av[1]+1)
if fixup:
if fixup: # IGNORECASE and not LOCALE
if fixes:
for i in map(fixup, r):
charmap[i] = 1
@ -287,8 +287,7 @@ def _optimize_charset(charset, iscased=None, fixup=None, fixes=None):
# Character set contains non-BMP character codes.
# For range, all BMP characters in the range are already
# proceeded.
if fixup:
hascased = True
if fixup: # IGNORECASE and not LOCALE
# For now, IN_UNI_IGNORE+LITERAL and
# IN_UNI_IGNORE+RANGE_UNI_IGNORE work for all non-BMP
# characters, because two characters (at least one of
@ -299,7 +298,13 @@ def _optimize_charset(charset, iscased=None, fixup=None, fixes=None):
# Also, both c.lower() and c.lower().upper() are single
# characters for every non-BMP character.
if op is RANGE:
op = RANGE_UNI_IGNORE
if fixes: # not ASCII
op = RANGE_UNI_IGNORE
hascased = True
else:
assert op is LITERAL
if not hascased and iscased(av):
hascased = True
tail.append((op, av))
break