diff options
-rw-r--r-- | Doc/library/string.rst | 14 | ||||
-rw-r--r-- | Lib/string.py | 6 | ||||
-rw-r--r-- | Lib/test/test_string.py | 6 | ||||
-rw-r--r-- | Misc/NEWS.d/next/Library/2017-10-12-02-47-16.bpo-31672.DaOkVd.rst | 2 |
4 files changed, 25 insertions, 3 deletions
diff --git a/Doc/library/string.rst b/Doc/library/string.rst index a0977b6461..7a9fcc38bb 100644 --- a/Doc/library/string.rst +++ b/Doc/library/string.rst @@ -746,8 +746,18 @@ to parse template strings. To do this, you can override these class attributes: * *idpattern* -- This is the regular expression describing the pattern for non-braced placeholders (the braces will be added automatically as - appropriate). The default value is the regular expression - ``[_a-z][_a-z0-9]*``. + appropriate). The default value is the regular expression + ``(?-i:[_a-zA-Z][_a-zA-Z0-9]*)``. + + .. note:: + + Since default *flags* is ``re.IGNORECASE``, pattern ``[a-z]`` can match + with some non-ASCII characters. That's why we use local ``-i`` flag here. + + While *flags* is kept to ``re.IGNORECASE`` for backward compatibility, + you can override it to ``0`` or ``re.IGNORECASE | re.ASCII`` when + subclassing. + * *flags* -- The regular expression flags that will be applied when compiling the regular expression used for recognizing substitutions. The default value diff --git a/Lib/string.py b/Lib/string.py index c902007643..670c1951a8 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 70439f85c8..8db23e76c1 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): diff --git a/Misc/NEWS.d/next/Library/2017-10-12-02-47-16.bpo-31672.DaOkVd.rst b/Misc/NEWS.d/next/Library/2017-10-12-02-47-16.bpo-31672.DaOkVd.rst new file mode 100644 index 0000000000..b8de1f3b1d --- /dev/null +++ b/Misc/NEWS.d/next/Library/2017-10-12-02-47-16.bpo-31672.DaOkVd.rst @@ -0,0 +1,2 @@ +``idpattern`` in ``string.Template`` matched some non-ASCII characters. Now +it uses ``-i`` regular expression local flag to avoid non-ASCII characters. |