diff options
Diffstat (limited to 'clang/lib/Lex/Lexer.cpp')
| -rw-r--r-- | clang/lib/Lex/Lexer.cpp | 14 |
1 files changed, 8 insertions, 6 deletions
diff --git a/clang/lib/Lex/Lexer.cpp b/clang/lib/Lex/Lexer.cpp index 82f65ef..3070407 100644 --- a/clang/lib/Lex/Lexer.cpp +++ b/clang/lib/Lex/Lexer.cpp @@ -3484,9 +3484,14 @@ uint32_t Lexer::tryReadUCN(const char *&StartPtr, const char *SlashLoc, if (LangOpts.AsmPreprocessor) return CodePoint; - // C99 6.4.3p2: A universal character name shall not specify a character whose - // short identifier is less than 00A0 other than 0024 ($), 0040 (@), or - // 0060 (`), nor one in the range D800 through DFFF inclusive.) + // C2x 6.4.3p2: A universal character name shall not designate a code point + // where the hexadecimal value is: + // - in the range D800 through DFFF inclusive; or + // - greater than 10FFFF. + // A universal-character-name outside the c-char-sequence of a character + // constant, or the s-char-sequence of a string-literal shall not designate + // a control character or a character in the basic character set. + // C++11 [lex.charset]p2: If the hexadecimal value for a // universal-character-name corresponds to a surrogate code point (in the // range 0xD800-0xDFFF, inclusive), the program is ill-formed. Additionally, @@ -3496,9 +3501,6 @@ uint32_t Lexer::tryReadUCN(const char *&StartPtr, const char *SlashLoc, // ranges 0x00-0x1F or 0x7F-0x9F, both inclusive) or to a character in the // basic source character set, the program is ill-formed. if (CodePoint < 0xA0) { - if (CodePoint == 0x24 || CodePoint == 0x40 || CodePoint == 0x60) - return CodePoint; - // We don't use isLexingRawMode() here because we need to warn about bad // UCNs even when skipping preprocessing tokens in a #if block. if (Result && PP) { |