diff options
| author | INADA Naoki <methane@users.noreply.github.com> | 2017-10-14 05:21:59 (GMT) |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2017-10-14 05:21:59 (GMT) |
| commit | 7060380d577690a40ebc201c0725076349e977cd (patch) | |
| tree | 792fe8b9f5a18ff8680f13d03ae27b0544e0fce1 /Lib | |
| parent | 6234e9068332f61f935cf13fa5b1a924a99c28b2 (diff) | |
| download | cpython-7060380d577690a40ebc201c0725076349e977cd.zip cpython-7060380d577690a40ebc201c0725076349e977cd.tar.gz cpython-7060380d577690a40ebc201c0725076349e977cd.tar.bz2 | |
bpo-31672: Fix string.Template accidentally matched non-ASCII identifiers (GH-3872)
Pattern `[a-z]` with `IGNORECASE` flag can match to some non-ASCII characters.
Straightforward solution for this is using `IGNORECASE | ASCII` flag.
But users may subclass `Template` and override only `idpattern`. So we want to
avoid changing `Template.flags`.
So this commit uses local flag `-i` for `idpattern` and change `[a-z]` to `[a-zA-Z]`.
(cherry picked from commit b22273ec5d1992b0cbe078b887427ae9977dfb78)
Diffstat (limited to 'Lib')
| -rw-r--r-- | Lib/string.py | 6 | ||||
| -rw-r--r-- | Lib/test/test_string.py | 6 |
2 files changed, 11 insertions, 1 deletions
diff --git a/Lib/string.py b/Lib/string.py index c902007..670c195 100644 --- a/Lib/string.py +++ b/Lib/string.py @@ -78,7 +78,11 @@ class Template(metaclass=_TemplateMetaclass): """A string class for supporting $-substitutions.""" delimiter = '$' - idpattern = r'[_a-z][_a-z0-9]*' + # r'[a-z]' matches to non-ASCII letters when used with IGNORECASE, + # but without ASCII flag. We can't add re.ASCII to flags because of + # backward compatibility. So we use local -i flag and [a-zA-Z] pattern. + # See https://bugs.python.org/issue31672 + idpattern = r'(?-i:[_a-zA-Z][_a-zA-Z0-9]*)' flags = _re.IGNORECASE def __init__(self, template): diff --git a/Lib/test/test_string.py b/Lib/test/test_string.py index 70439f8..8db23e7 100644 --- a/Lib/test/test_string.py +++ b/Lib/test/test_string.py @@ -271,6 +271,12 @@ class TestTemplate(unittest.TestCase): raises(ValueError, s.substitute, dict(who='tim')) s = Template('$who likes $100') raises(ValueError, s.substitute, dict(who='tim')) + # Template.idpattern should match to only ASCII characters. + # https://bugs.python.org/issue31672 + s = Template("$who likes $\u0131") # (DOTLESS I) + raises(ValueError, s.substitute, dict(who='tim')) + s = Template("$who likes $\u0130") # (LATIN CAPITAL LETTER I WITH DOT ABOVE) + raises(ValueError, s.substitute, dict(who='tim')) def test_idpattern_override(self): class PathPattern(Template): |