Stowage/cpython
2
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-12-08 06:10:17 +00:00
Code Issues Projects Releases Packages Wiki Activity

[3.9] gh-90568: Fix exception type for \N with a named sequence in RE (GH-91665) (GH-91830) (GH-91834)

Browse source 
re.error is now raised instead of TypeError.
(cherry picked from commit 6ccfa31421)
(cherry picked from commit 9c18d783c3)

Co-authored-by: Serhiy Storchaka <storchaka@gmail.com>
This commit is contained in:
Miss Islington (bot) 2022-04-22 11:34:31 -07:00 • committed by GitHub
parent 2f75d43f1e
commit 97d14e1dfb
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
3 changed files with 9 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
Lib/sre_parse.py
View file

@ -330,7 +330,7 @@ def _class_escape(source, escape):
charname = source.getuntil('}', 'character name') charname = source.getuntil('}', 'character name')
try: try:
c = ord(unicodedata.lookup(charname)) c = ord(unicodedata.lookup(charname))
except KeyError: except (KeyError, TypeError):
raise source.error("undefined character name %r" % charname, raise source.error("undefined character name %r" % charname,
len(charname) + len(r'\N{}')) len(charname) + len(r'\N{}'))
return LITERAL, c return LITERAL, c
@ -390,7 +390,7 @@ def _escape(source, escape, state):
charname = source.getuntil('}', 'character name') charname = source.getuntil('}', 'character name')
try: try:
c = ord(unicodedata.lookup(charname)) c = ord(unicodedata.lookup(charname))
except KeyError: except (KeyError, TypeError):
raise source.error("undefined character name %r" % charname, raise source.error("undefined character name %r" % charname,
len(charname) + len(r'\N{}')) len(charname) + len(r'\N{}'))
return LITERAL, c return LITERAL, c

4
Lib/test/test_re.py
View file

@ -753,6 +753,10 @@ def test_named_unicode_escapes(self):
"undefined character name 'SPAM'", 0) "undefined character name 'SPAM'", 0)
self.checkPatternError(r'[\N{SPAM}]', self.checkPatternError(r'[\N{SPAM}]',
"undefined character name 'SPAM'", 1) "undefined character name 'SPAM'", 1)
self.checkPatternError(r'\N{KEYCAP NUMBER SIGN}',
"undefined character name 'KEYCAP NUMBER SIGN'", 0)
self.checkPatternError(r'[\N{KEYCAP NUMBER SIGN}]',
"undefined character name 'KEYCAP NUMBER SIGN'", 1)
self.checkPatternError(br'\N{LESS-THAN SIGN}', r'bad escape \N', 0) self.checkPatternError(br'\N{LESS-THAN SIGN}', r'bad escape \N', 0)
self.checkPatternError(br'[\N{LESS-THAN SIGN}]', r'bad escape \N', 1) self.checkPatternError(br'[\N{LESS-THAN SIGN}]', r'bad escape \N', 1)

3
Misc/NEWS.d/next/Library/2022-04-18-16-31-33.gh-issue-90568.9kiU7o.rst Normal file
View file

@ -0,0 +1,3 @@
Parsing ``\N`` escapes of Unicode Named Character Sequences in a
:mod:`regular expression <re>` raises now :exc:`re.error` instead of
``TypeError``.