Output UTF-8-encoded characters as identifier characters into assembly

by default.

This is a behaviour configurable in the MCAsmInfo. I've decided to turn
it on by default in (possibly optimistic) hopes that most assemblers are
reasonably sane. If this proves a problem, switching to default seems
reasonable.

I'm not sure if this is the opportune place to test, but it seemed good
to make sure it was tested somewhere.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154235 91177308-0d34-0410-b5e6-96231b3b80d8

4 files changed, 19 insertions, 4 deletions

diff --git a/include/llvm/MC/MCAsmInfo.h b/include/llvm/MC/MCAsmInfo.h
index 095ca14c1b..0f67c99371 100644
--- a/include/llvm/MC/MCAsmInfo.h
+++ b/include/llvm/MC/MCAsmInfo.h
@@ -143,6 +143,10 @@ namespace llvm {
     /// symbol names.  This defaults to true.
     bool AllowPeriodsInName;
 
+    /// AllowUTF8 - This is true if the assembler accepts UTF-8 input.
+    // FIXME: Make this a more general encoding setting?
+    bool AllowUTF8;
+
     //===--- Data Emission Directives -------------------------------------===//
 
     /// ZeroDirective - this should be set to the directive used to get some
@@ -485,6 +489,9 @@ namespace llvm {
     bool doesAllowPeriodsInName() const {
       return AllowPeriodsInName;
     }
+    bool doesAllowUTF8() const {
+      return AllowUTF8;
+    }
     const char *getZeroDirective() const {
       return ZeroDirective;
     }
diff --git a/lib/MC/MCAsmInfo.cpp b/lib/MC/MCAsmInfo.cpp
index 582d21fe90..8286c1dfea 100644
--- a/lib/MC/MCAsmInfo.cpp
+++ b/lib/MC/MCAsmInfo.cpp
@@ -49,6 +49,7 @@ MCAsmInfo::MCAsmInfo() {
   AllowQuotesInName = false;
   AllowNameToStartWithDigit = false;
   AllowPeriodsInName = true;
+  AllowUTF8 = true;
   ZeroDirective = "\t.zero\t";
   AsciiDirective = "\t.ascii\t";
   AscizDirective = "\t.asciz\t";
diff --git a/lib/Target/Mangler.cpp b/lib/Target/Mangler.cpp
index 53ad155f37..786a0c5ed1 100644
--- a/lib/Target/Mangler.cpp
+++ b/lib/Target/Mangler.cpp
@@ -22,12 +22,13 @@
 #include "llvm/ADT/Twine.h"
 using namespace llvm;
 
-static bool isAcceptableChar(char C, bool AllowPeriod) {
+static bool isAcceptableChar(char C, bool AllowPeriod, bool AllowUTF8) {
   if ((C < 'a' || C > 'z') &&
       (C < 'A' || C > 'Z') &&
       (C < '0' || C > '9') &&
       C != '_' && C != '$' && C != '@' &&
-      !(AllowPeriod && C == '.'))
+      !(AllowPeriod && C == '.') &&
+      !(AllowUTF8 && (C & 0x80)))
     return false;
   return true;
 }
@@ -56,8 +57,9 @@ static bool NameNeedsEscaping(StringRef Str, const MCAsmInfo &MAI) {
   // If any of the characters in the string is an unacceptable character, force
   // quotes.
   bool AllowPeriod = MAI.doesAllowPeriodsInName();
+  bool AllowUTF8 = MAI.doesAllowUTF8();
   for (unsigned i = 0, e = Str.size(); i != e; ++i)
-    if (!isAcceptableChar(Str[i], AllowPeriod))
+    if (!isAcceptableChar(Str[i], AllowPeriod, AllowUTF8))
       return true;
   return false;
 }
@@ -74,8 +76,9 @@ static void appendMangledName(SmallVectorImpl<char> &OutName, StringRef Str,
   }
 
   bool AllowPeriod = MAI.doesAllowPeriodsInName();
+  bool AllowUTF8 = MAI.doesAllowUTF8();
   for (unsigned i = 0, e = Str.size(); i != e; ++i) {
-    if (!isAcceptableChar(Str[i], AllowPeriod))
+    if (!isAcceptableChar(Str[i], AllowPeriod, AllowUTF8))
       MangleLetter(OutName, Str[i]);
     else
       OutName.push_back(Str[i]);
diff --git a/test/CodeGen/X86/utf8.ll b/test/CodeGen/X86/utf8.ll
new file mode 100644
index 0000000000..8a75c2ebce
--- /dev/null
+++ b/test/CodeGen/X86/utf8.ll
@@ -0,0 +1,4 @@
+; RUN: llc < %s -march=x86 | FileCheck %s
+
+; CHECK: "iΔ",4,4
+@"i\CE\94" = common global i32 0, align 4