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
diff --git a/lib/Target/Mangler.cpp b/lib/Target/Mangler.cpp
index 53ad155..786a0c5 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 @@
// 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 @@
}
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]);