aboutsummaryrefslogtreecommitdiff
path: root/lib/Lex
diff options
context:
space:
mode:
authorRichard Smith <richard-llvm@metafoo.co.uk>2013-03-09 23:56:02 +0000
committerRichard Smith <richard-llvm@metafoo.co.uk>2013-03-09 23:56:02 +0000
commit0093e12513c5c896434915d5e9126f51b780aa61 (patch)
tree4ba4f0eaf849ce25a1e9b23f1876f4a5c4201a9a /lib/Lex
parent0b91cc47a5642de2e1f567fe0f29420acdcdebbe (diff)
When lexing in C11 mode, accept unicode character and string literals, per C11
6.4.4.4/1 and 6.4.5/1. git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@176780 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'lib/Lex')
-rw-r--r--lib/Lex/Lexer.cpp22
1 files changed, 13 insertions, 9 deletions
diff --git a/lib/Lex/Lexer.cpp b/lib/Lex/Lexer.cpp
index e18953d448..e6cc8b929c 100644
--- a/lib/Lex/Lexer.cpp
+++ b/lib/Lex/Lexer.cpp
@@ -1629,7 +1629,8 @@ void Lexer::LexStringLiteral(Token &Result, const char *CurPtr,
if (!isLexingRawMode() &&
(Kind == tok::utf8_string_literal ||
Kind == tok::utf16_string_literal ||
- Kind == tok::utf32_string_literal))
+ Kind == tok::utf32_string_literal) &&
+ getLangOpts().CPlusPlus)
Diag(BufferPtr, diag::warn_cxx98_compat_unicode_literal);
char C = getAndAdvanceChar(CurPtr, Result);
@@ -1794,7 +1795,8 @@ void Lexer::LexCharConstant(Token &Result, const char *CurPtr,
const char *NulCharacter = 0; // Does this character contain the \0 character?
if (!isLexingRawMode() &&
- (Kind == tok::utf16_char_constant || Kind == tok::utf32_char_constant))
+ (Kind == tok::utf16_char_constant || Kind == tok::utf32_char_constant) &&
+ getLangOpts().CPlusPlus)
Diag(BufferPtr, diag::warn_cxx98_compat_unicode_literal);
char C = getAndAdvanceChar(CurPtr, Result);
@@ -2848,11 +2850,11 @@ LexNextToken:
MIOpt.ReadToken();
return LexNumericConstant(Result, CurPtr);
- case 'u': // Identifier (uber) or C++0x UTF-8 or UTF-16 string literal
+ case 'u': // Identifier (uber) or C11/C++11 UTF-8 or UTF-16 string literal
// Notify MIOpt that we read a non-whitespace/non-comment token.
MIOpt.ReadToken();
- if (LangOpts.CPlusPlus11) {
+ if (LangOpts.CPlusPlus11 || LangOpts.C11) {
Char = getCharAndSize(CurPtr, SizeTmp);
// UTF-16 string literal
@@ -2866,7 +2868,8 @@ LexNextToken:
tok::utf16_char_constant);
// UTF-16 raw string literal
- if (Char == 'R' && getCharAndSize(CurPtr + SizeTmp, SizeTmp2) == '"')
+ if (Char == 'R' && LangOpts.CPlusPlus11 &&
+ getCharAndSize(CurPtr + SizeTmp, SizeTmp2) == '"')
return LexRawStringLiteral(Result,
ConsumeChar(ConsumeChar(CurPtr, SizeTmp, Result),
SizeTmp2, Result),
@@ -2882,7 +2885,7 @@ LexNextToken:
SizeTmp2, Result),
tok::utf8_string_literal);
- if (Char2 == 'R') {
+ if (Char2 == 'R' && LangOpts.CPlusPlus11) {
unsigned SizeTmp3;
char Char3 = getCharAndSize(CurPtr + SizeTmp + SizeTmp2, SizeTmp3);
// UTF-8 raw string literal
@@ -2900,11 +2903,11 @@ LexNextToken:
// treat u like the start of an identifier.
return LexIdentifier(Result, CurPtr);
- case 'U': // Identifier (Uber) or C++0x UTF-32 string literal
+ case 'U': // Identifier (Uber) or C11/C++11 UTF-32 string literal
// Notify MIOpt that we read a non-whitespace/non-comment token.
MIOpt.ReadToken();
- if (LangOpts.CPlusPlus11) {
+ if (LangOpts.CPlusPlus11 || LangOpts.C11) {
Char = getCharAndSize(CurPtr, SizeTmp);
// UTF-32 string literal
@@ -2918,7 +2921,8 @@ LexNextToken:
tok::utf32_char_constant);
// UTF-32 raw string literal
- if (Char == 'R' && getCharAndSize(CurPtr + SizeTmp, SizeTmp2) == '"')
+ if (Char == 'R' && LangOpts.CPlusPlus11 &&
+ getCharAndSize(CurPtr + SizeTmp, SizeTmp2) == '"')
return LexRawStringLiteral(Result,
ConsumeChar(ConsumeChar(CurPtr, SizeTmp, Result),
SizeTmp2, Result),