diff options
| author | nyamatongwe <devnull@localhost> | 2008-10-09 22:05:43 +0000 |
|---|---|---|
| committer | nyamatongwe <devnull@localhost> | 2008-10-09 22:05:43 +0000 |
| commit | 8723b946e90e0d793a24adf62d0b453e15e086a1 (patch) | |
| tree | a66bb1c0bab9c499ad4c1a7c7a38d38c1b6f4441 | |
| parent | 3751deea7b3fca18e67f60556b7369810f75ac23 (diff) | |
| download | scintilla-mirror-8723b946e90e0d793a24adf62d0b453e15e086a1.tar.gz | |
Fix for #2153429 by Jason Oster. UTF-8 text could be chopped up.
| -rw-r--r-- | src/LexCSS.cxx | 7 |
1 files changed, 6 insertions, 1 deletions
diff --git a/src/LexCSS.cxx b/src/LexCSS.cxx index f6757c46f..3b139cdcd 100644 --- a/src/LexCSS.cxx +++ b/src/LexCSS.cxx @@ -28,7 +28,12 @@ using namespace Scintilla; static inline bool IsAWordChar(const unsigned int ch) { - return (isalnum(ch) || ch == '-' || ch == '_' || ch >= 161); // _ is not in fact correct CSS word-character + /* FIXME: + * The CSS spec allows "ISO 10646 characters U+00A1 and higher" to be treated as word chars. + * Unfortunately, we are only getting string bytes here, and not full unicode characters. We cannot guarantee + * that our byte is between U+0080 - U+00A0 (to return false), so we have to allow all characters U+0080 and higher + */ + return ch >= 0x80 || isalnum(ch) || ch == '-' || ch == '_'; } inline bool IsCssOperator(const int ch) { |