From 5ada7a5e9747e03e8c3725b1b4d00e2a9f448e9e Mon Sep 17 00:00:00 2001
From: Ed Schouten <ed@80386.nl>
Date: Sun, 29 Sep 2013 07:54:52 +0000
Subject: [PATCH] Add character set related __STDC_* definitions.

Clang uses UTF-16 and UTF-32 for its char16_t's and char32_t's
exclusively. This means that we can define __STDC_UTF_16__ and
__STDC_UTF_32__ unconditionally.

While there, define __STDC_MB_MIGHT_NEQ_WC__ for FreeBSD. FreeBSD's
wchar_t's don't encode characters as ISO-10646; the encoding depends on
the locale used. Because the character set used might not be a superset
of ASCII, we must define __STDC_MB_MIGHT_NEQ_WC__.



git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@191631 91177308-0d34-0410-b5e6-96231b3b80d8
---
 lib/Basic/Targets.cpp             |  5 +++++
 lib/Frontend/InitPreprocessor.cpp |  8 ++++++++
 test/Preprocessor/init.c          | 14 ++++++++++++++
 3 files changed, 27 insertions(+)

diff --git a/lib/Basic/Targets.cpp b/lib/Basic/Targets.cpp
index f1a1454410..3ee9cd48b5 100644
--- a/lib/Basic/Targets.cpp
+++ b/lib/Basic/Targets.cpp
@@ -253,6 +253,11 @@ protected:
     Builder.defineMacro("__KPRINTF_ATTRIBUTE__");
     DefineStd(Builder, "unix", Opts);
     Builder.defineMacro("__ELF__");
+
+    // On FreeBSD, wchar_t contains the number of the code point as
+    // used by the character set of the locale. These character sets are
+    // not necessarily a superset of ASCII.
+    Builder.defineMacro("__STDC_MB_MIGHT_NEQ_WC__", "1");
   }
 public:
   FreeBSDTargetInfo(const llvm::Triple &Triple) : OSTargetInfo<Target>(Triple) {
diff --git a/lib/Frontend/InitPreprocessor.cpp b/lib/Frontend/InitPreprocessor.cpp
index 8703a67a6f..77cf3b38e6 100644
--- a/lib/Frontend/InitPreprocessor.cpp
+++ b/lib/Frontend/InitPreprocessor.cpp
@@ -330,6 +330,14 @@ static void InitializeStandardPredefinedMacros(const TargetInfo &TI,
       Builder.defineMacro("__cplusplus", "199711L");
   }
 
+  // In C11 these are environment macros. In C++11 they are only defined
+  // as part of <cuchar>. To prevent breakage when mixing C and C++
+  // code, define these macros unconditionally. We can define them
+  // unconditionally, as Clang always uses UTF-16 and UTF-32 for 16-bit
+  // and 32-bit character literals.
+  Builder.defineMacro("__STDC_UTF_16__", "1");
+  Builder.defineMacro("__STDC_UTF_32__", "1");
+
   if (LangOpts.ObjC1)
     Builder.defineMacro("__OBJC__");
 
diff --git a/test/Preprocessor/init.c b/test/Preprocessor/init.c
index 38ddaa6a14..ce7ee09abe 100644
--- a/test/Preprocessor/init.c
+++ b/test/Preprocessor/init.c
@@ -49,6 +49,14 @@
 // C99:#define __STRICT_ANSI__ 1
 //
 // 
+// RUN: %clang_cc1 -std=c11 -E -dM < /dev/null | FileCheck -check-prefix C11 %s
+//
+// C11:#define __STDC_UTF_16__ 1
+// C11:#define __STDC_UTF_32__ 1
+// C11:#define __STDC_VERSION__ 201112L
+// C11:#define __STRICT_ANSI__ 1
+//
+// 
 // RUN: %clang_cc1 -E -dM < /dev/null | FileCheck -check-prefix COMMON %s
 //
 // COMMON:#define __CONSTANT_CFSTRINGS__ 1
@@ -2925,6 +2933,12 @@
 // X86_64-LINUX:#define __x86_64 1
 // X86_64-LINUX:#define __x86_64__ 1
 //
+// RUN: %clang_cc1 -E -dM -ffreestanding -triple=x86_64-unknown-freebsd9.1 < /dev/null | FileCheck -check-prefix X86_64-FREEBSD %s
+//
+// X86_64-FREEBSD:#define __FreeBSD__ 9
+// X86_64-FREEBSD:#define __FreeBSD_cc_version 900001
+// X86_64-FREEBSD:#define __STDC_MB_MIGHT_NEQ_WC__ 1
+//
 // RUN: %clang_cc1 -E -dM -ffreestanding -triple=sparc64-none-none < /dev/null | FileCheck -check-prefix SPARCV9 %s
 // SPARCV9:#define __INT64_TYPE__ long int
 // SPARCV9:#define __INTMAX_TYPE__ long int
-- 
2.40.0