Implement P0482R2, support for char8_t type.

This is not yet part of any C++ working draft, and so is controlled by the flag
-fchar8_t rather than a -std= flag. (The GCC implementation is controlled by a
flag with the same name.)

This implementation is experimental, and will be removed or revised
substantially to match the proposal as it makes its way through the C++
committee.


git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@331244 91177308-0d34-0410-b5e6-96231b3b80d8

4 files changed, 16 insertions, 0 deletions

diff --git a/include/clang/Basic/DiagnosticSemaKinds.td b/include/clang/Basic/DiagnosticSemaKinds.td
index cb3f606cc1..4410c32469 100644
--- a/include/clang/Basic/DiagnosticSemaKinds.td
+++ b/include/clang/Basic/DiagnosticSemaKinds.td
@@ -2421,6 +2421,9 @@ def err_template_different_associated_constraints : Error<
 def warn_cxx98_compat_unicode_type : Warning<
   "'%0' type specifier is incompatible with C++98">,
   InGroup<CXX98Compat>, DefaultIgnore;
+def warn_cxx17_compat_unicode_type : Warning<
+  "'char8_t' type specifier is incompatible with C++ standards before C++20">,
+  InGroup<CXXPre2aCompat>, DefaultIgnore;
 
 // __make_integer_seq
 def err_integer_sequence_negative_length : Error<
@@ -5822,6 +5825,13 @@ def err_array_init_wide_string_into_char : Error<
   "initializing char array with wide string literal">;
 def err_array_init_incompat_wide_string_into_wchar : Error<
   "initializing wide char array with incompatible wide string literal">;
+def err_array_init_plain_string_into_char8_t : Error<
+  "initializing 'char8_t' array with plain string literal">;
+def note_array_init_plain_string_into_char8_t : Note<
+  "add 'u8' prefix to form a 'char8_t' string literal">;
+def err_array_init_utf8_string_into_char : Error<
+  "initialization of char array with UTF-8 string literal is not permitted "
+  "by '-fchar8_t'">;
 def err_array_init_different_type : Error<
   "cannot initialize array %diff{of type $ with array of type $|"
   "with different type of array}0,1">;
diff --git a/include/clang/Basic/LangOptions.def b/include/clang/Basic/LangOptions.def
index 87173c8d54..f868110719 100644
--- a/include/clang/Basic/LangOptions.def
+++ b/include/clang/Basic/LangOptions.def
@@ -106,6 +106,7 @@ LANGOPT(LineComment       , 1, 0, "'//' comments")
 LANGOPT(Bool              , 1, 0, "bool, true, and false keywords")
 LANGOPT(Half              , 1, 0, "half keyword")
 LANGOPT(WChar             , 1, CPlusPlus, "wchar_t keyword")
+LANGOPT(Char8             , 1, 0, "char8_t keyword")
 LANGOPT(DeclSpecKeyword   , 1, 0, "__declspec keyword")
 BENIGN_LANGOPT(DollarIdents   , 1, 1, "'$' in identifiers")
 BENIGN_LANGOPT(AsmPreprocessor, 1, 0, "preprocessor in asm mode")
diff --git a/include/clang/Basic/Specifiers.h b/include/clang/Basic/Specifiers.h
index 377534baab..d17e5a8145 100644
--- a/include/clang/Basic/Specifiers.h
+++ b/include/clang/Basic/Specifiers.h
@@ -47,6 +47,7 @@ namespace clang {
     TST_void,
     TST_char,
     TST_wchar,        // C++ wchar_t
+    TST_char8,        // C++20 char8_t (proposed)
     TST_char16,       // C++11 char16_t
     TST_char32,       // C++11 char32_t
     TST_int,
diff --git a/include/clang/Basic/TokenKinds.def b/include/clang/Basic/TokenKinds.def
index f18e06f5b7..6bf945b785 100644
--- a/include/clang/Basic/TokenKinds.def
+++ b/include/clang/Basic/TokenKinds.def
@@ -260,6 +260,7 @@ PUNCTUATOR(caretcaret,            "^^")
 //   BOOLSUPPORT - This is a keyword if 'bool' is a built-in type
 //   HALFSUPPORT - This is a keyword if 'half' is a built-in type
 //   WCHARSUPPORT - This is a keyword if 'wchar_t' is a built-in type
+//   CHAR8SUPPORT - This is a keyword if 'char8_t' is a built-in type
 //
 KEYWORD(auto                        , KEYALL)
 KEYWORD(break                       , KEYALL)
@@ -380,6 +381,9 @@ KEYWORD(co_yield                    , KEYCOROUTINES)
 MODULES_KEYWORD(module)
 MODULES_KEYWORD(import)
 
+// C++ char8_t proposal
+KEYWORD(char8_t                     , CHAR8SUPPORT)
+
 // C11 Extension
 KEYWORD(_Float16                    , KEYALL)