[PATCH] D119221: [clang][lexer] Allow u8 character literal prefixes in C2x

[Timm Bäder via Phabricator via cfe-commits]

tbaeder created this revision.
tbaeder added a reviewer: aaron.ballman.
tbaeder requested review of this revision.
Herald added a project: clang.
Herald added a subscriber: cfe-commits.

Implement N2418 for C2x.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D119221

Files:
  clang/lib/Lex/Lexer.cpp
  clang/test/Lexer/utf8-char-literal.cpp


Index: clang/test/Lexer/utf8-char-literal.cpp
===================================================================
--- clang/test/Lexer/utf8-char-literal.cpp
+++ clang/test/Lexer/utf8-char-literal.cpp
@@ -1,5 +1,6 @@
 // RUN: %clang_cc1 -triple x86_64-apple-darwin -std=c++11 -fsyntax-only 
-verify %s
 // RUN: %clang_cc1 -triple x86_64-apple-darwin -std=c11 -x c -fsyntax-only 
-verify %s
+// RUN: %clang_cc1 -triple x86_64-apple-darwin -std=c2x -DC2X -x c 
-fsyntax-only -verify %s
 // RUN: %clang_cc1 -triple x86_64-apple-darwin -std=c++1z -fsyntax-only 
-verify %s
 
 int array0[u'ñ' == u'\xf1'? 1 : -1];
@@ -12,4 +13,12 @@
 char d = u8'\u1234'; // expected-error {{character too large for enclosing 
character literal type}}
 char e = u8'ሴ'; // expected-error {{character too large for enclosing 
character literal type}}
 char f = u8'ab'; // expected-error {{Unicode character literals may not 
contain multiple characters}}
+#elif defined(C2X)
+char a = u8'ñ';             // expected-error {{character too large for 
enclosing character literal type}}
+unsigned char b = u8'\x80'; // ok
+char c = u8'\u0080';        // expected-error {{universal character name 
refers to a control character}}
+char d = u8'\u1234';        // expected-error {{character too large for 
enclosing character literal type}}
+char e = u8'ሴ';             // expected-error {{character too large for 
enclosing character literal type}}
+char f = u8'ab';            // expected-error {{Unicode character literals may 
not contain multiple characters}}
+char g = u8'\x80';          // expected-warning {{implicit conversion from 
'int' to 'char' changes value from 128 to -128}}
 #endif
Index: clang/lib/Lex/Lexer.cpp
===================================================================
--- clang/lib/Lex/Lexer.cpp
+++ clang/lib/Lex/Lexer.cpp
@@ -3459,7 +3459,7 @@
     MIOpt.ReadToken();
     return LexNumericConstant(Result, CurPtr);
 
-  case 'u':   // Identifier (uber) or C11/C++11 UTF-8 or UTF-16 string literal
+  case 'u': // Identifier (uber) or C11/C2x/C++11 UTF-8 or UTF-16 string 
literal
     // Notify MIOpt that we read a non-whitespace/non-comment token.
     MIOpt.ReadToken();
 
@@ -3493,7 +3493,7 @@
                                ConsumeChar(ConsumeChar(CurPtr, SizeTmp, 
Result),
                                            SizeTmp2, Result),
                                tok::utf8_string_literal);
-        if (Char2 == '\'' && LangOpts.CPlusPlus17)
+        if (Char2 == '\'' && (LangOpts.CPlusPlus17 || LangOpts.C2x))
           return LexCharConstant(
               Result, ConsumeChar(ConsumeChar(CurPtr, SizeTmp, Result),
                                   SizeTmp2, Result),



Index: clang/test/Lexer/utf8-char-literal.cpp
===================================================================
--- clang/test/Lexer/utf8-char-literal.cpp
+++ clang/test/Lexer/utf8-char-literal.cpp
@@ -1,5 +1,6 @@
 // RUN: %clang_cc1 -triple x86_64-apple-darwin -std=c++11 -fsyntax-only -verify %s
 // RUN: %clang_cc1 -triple x86_64-apple-darwin -std=c11 -x c -fsyntax-only -verify %s
+// RUN: %clang_cc1 -triple x86_64-apple-darwin -std=c2x -DC2X -x c -fsyntax-only -verify %s
 // RUN: %clang_cc1 -triple x86_64-apple-darwin -std=c++1z -fsyntax-only -verify %s
 
 int array0[u'ñ' == u'\xf1'? 1 : -1];
@@ -12,4 +13,12 @@
 char d = u8'\u1234'; // expected-error {{character too large for enclosing character literal type}}
 char e = u8'ሴ'; // expected-error {{character too large for enclosing character literal type}}
 char f = u8'ab'; // expected-error {{Unicode character literals may not contain multiple characters}}
+#elif defined(C2X)
+char a = u8'ñ';             // expected-error {{character too large for enclosing character literal type}}
+unsigned char b = u8'\x80'; // ok
+char c = u8'\u0080';        // expected-error {{universal character name refers to a control character}}
+char d = u8'\u1234';        // expected-error {{character too large for enclosing character literal type}}
+char e = u8'ሴ';             // expected-error {{character too large for enclosing character literal type}}
+char f = u8'ab';            // expected-error {{Unicode character literals may not contain multiple characters}}
+char g = u8'\x80';          // expected-warning {{implicit conversion from 'int' to 'char' changes value from 128 to -128}}
 #endif
Index: clang/lib/Lex/Lexer.cpp
===================================================================
--- clang/lib/Lex/Lexer.cpp
+++ clang/lib/Lex/Lexer.cpp
@@ -3459,7 +3459,7 @@
     MIOpt.ReadToken();
     return LexNumericConstant(Result, CurPtr);
 
-  case 'u':   // Identifier (uber) or C11/C++11 UTF-8 or UTF-16 string literal
+  case 'u': // Identifier (uber) or C11/C2x/C++11 UTF-8 or UTF-16 string literal
     // Notify MIOpt that we read a non-whitespace/non-comment token.
     MIOpt.ReadToken();
 
@@ -3493,7 +3493,7 @@
                                ConsumeChar(ConsumeChar(CurPtr, SizeTmp, Result),
                                            SizeTmp2, Result),
                                tok::utf8_string_literal);
-        if (Char2 == '\'' && LangOpts.CPlusPlus17)
+        if (Char2 == '\'' && (LangOpts.CPlusPlus17 || LangOpts.C2x))
           return LexCharConstant(
               Result, ConsumeChar(ConsumeChar(CurPtr, SizeTmp, Result),
                                   SizeTmp2, Result),

_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits