diff options
| author | ptmcg <ptmcg@austin.rr.com> | 2022-11-06 16:47:20 -0600 |
|---|---|---|
| committer | ptmcg <ptmcg@austin.rr.com> | 2022-11-06 16:47:20 -0600 |
| commit | 6aef782b6d347db134bafa66004c60b42e42e427 (patch) | |
| tree | 8fb8b4e455a3671f4320e8cf3b85a46d83ed18e4 | |
| parent | 2c648a1acdd0fc6691b682dff1a23ce9b4005090 (diff) | |
| download | pyparsing-git-6aef782b6d347db134bafa66004c60b42e42e427.tar.gz | |
Add Unicode MIDDLE DOT to Latin1.identbodychars
| -rw-r--r-- | CHANGES | 2 | ||||
| -rw-r--r-- | pyparsing/unicode.py | 4 |
2 files changed, 4 insertions, 2 deletions
@@ -60,6 +60,8 @@ help from Devin J. Pohly in structuring the code to enable this peaceful transit debug flag on an expression and all of its sub-expressions. Requested by multimeric in Issue #399. +- Added '·' (Unicode MIDDLE DOT) to the set of Latin1.identbodychars. + - Fixed bug in `Word` when `max=2`. Also added performance enhancement when specifying `exact` argument. Reported in issue #409 by panda-34, nice catch! diff --git a/pyparsing/unicode.py b/pyparsing/unicode.py index c1d469b..9bc5e1d 100644 --- a/pyparsing/unicode.py +++ b/pyparsing/unicode.py @@ -100,13 +100,13 @@ class unicode_set: def identbodychars(cls): """ all characters in this range that are valid identifier body characters, - plus the digits 0-9 + plus the digits 0-9, and · (Unicode MIDDLE DOT) """ return "".join( sorted( set( cls.identchars - + "0123456789" + + "0123456789·" + "".join( [c for c in cls._chars_for_ranges if ("_" + c).isidentifier()] ) |