From: Daniel Dunbar <daniel@zuster.org>
Date: Thu, 23 Jul 2009 23:41:22 +0000 (+0000)
Subject: Output UTF-16 string literals independent of host byte order.
X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=70ee975fad4653fa09f8e77f9a46a7b1f592ef59;p=clang

Output UTF-16 string literals independent of host byte order.
 - Steve, can you take a look at this? It seems like this code should live
   elsewhere, and there is a FIXME about having Sema validates the UTF-8 to
   UTF-16 conversion.


git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@76915 91177308-0d34-0410-b5e6-96231b3b80d8
---

diff --git a/lib/CodeGen/CodeGenModule.cpp b/lib/CodeGen/CodeGenModule.cpp
index 994f60b015..803df31a6f 100644
--- a/lib/CodeGen/CodeGenModule.cpp
+++ b/lib/CodeGen/CodeGenModule.cpp
@@ -1193,6 +1193,7 @@ static void appendFieldAndPadding(CodeGenModule &CGM,
 static llvm::StringMapEntry<llvm::Constant*> &
 GetConstantCFStringEntry(llvm::StringMap<llvm::Constant*> &Map,
                          const StringLiteral *Literal,
+                         bool TargetIsLSB,
                          bool &IsUTF16,
                          unsigned &StringLength) {
   unsigned NumBytes = Literal->getByteLength();
@@ -1223,15 +1224,28 @@ GetConstantCFStringEntry(llvm::StringMap<llvm::Constant*> &Map,
                                                 StringLength));
   }
 
-  // FIXME: Storing UTF-16 in a C string is a hack to test Unicode strings
-  // without doing more surgery to this routine. Since we aren't explicitly
-  // checking for endianness here, it's also a bug (when generating code for
-  // a target that doesn't match the host endianness). Modeling this as an
-  // i16 array is likely the cleanest solution.
+  // ConvertUTF8toUTF16 returns the length in ToPtr.
   StringLength = ToPtr - &ToBuf[0];
+
+  // Render the UTF-16 string into a byte array and convert to the target byte
+  // order.
+  //
+  // FIXME: This isn't something we should need to do here.
+  llvm::SmallString<128> AsBytes;
+  AsBytes.reserve(StringLength * 2);
+  for (unsigned i = 0; i != StringLength; ++i) {
+    unsigned short Val = ToBuf[i];
+    if (TargetIsLSB) {
+      AsBytes.push_back(Val & 0xFF);
+      AsBytes.push_back(Val >> 8);
+    } else {
+      AsBytes.push_back(Val >> 8);
+      AsBytes.push_back(Val & 0xFF);
+    }
+  }
+
   IsUTF16 = true;
-  return Map.GetOrCreateValue(llvm::StringRef((char *)&ToBuf[0], 
-                                              StringLength * 2));
+  return Map.GetOrCreateValue(llvm::StringRef(AsBytes.data(), AsBytes.size()));
 }
 
 llvm::Constant *
@@ -1239,8 +1253,9 @@ CodeGenModule::GetAddrOfConstantCFString(const StringLiteral *Literal) {
   unsigned StringLength = 0;
   bool isUTF16 = false;
   llvm::StringMapEntry<llvm::Constant*> &Entry =
-    GetConstantCFStringEntry(CFConstantStringMap, Literal, isUTF16, 
-                             StringLength);
+    GetConstantCFStringEntry(CFConstantStringMap, Literal, 
+                             getTargetData().isLittleEndian(),
+                             isUTF16, StringLength);
   
   if (llvm::Constant *C = Entry.getValue())
     return C;
diff --git a/test/CodeGen/darwin-string-literals.c b/test/CodeGen/darwin-string-literals.c
index 90662d15e6..2f94d557ca 100644
--- a/test/CodeGen/darwin-string-literals.c
+++ b/test/CodeGen/darwin-string-literals.c
@@ -1,8 +1,14 @@
-// RUN: clang-cc -triple i386-apple-darwin9 -emit-llvm %s -o - | FileCheck %s
+// RUN: clang-cc -triple i386-apple-darwin9 -emit-llvm %s -o - | FileCheck -check-prefix LSB %s
 
-// CHECK: @.str = private constant [8 x i8] c"string0\00"
-// CHECK: @.str1 = private constant [8 x i8] c"string1\00", section "__TEXT,__cstring,cstring_literals"
-// CHECK: @__utf16_string_ = internal global [35 x i8] c"h\00e\00l\00l\00o\00 \00\92! \00\03& \00\90! \00w\00o\00r\00l\00d\00\00", section "__TEXT,__ustring", align 2
+// CHECK-LSB: @.str = private constant [8 x i8] c"string0\00"
+// CHECK-LSB: @.str1 = private constant [8 x i8] c"string1\00", section "__TEXT,__cstring,cstring_literals"
+// CHECK-LSB: @__utf16_string_ = internal global [35 x i8] c"h\00e\00l\00l\00o\00 \00\92! \00\03& \00\90! \00w\00o\00r\00l\00d\00\00", section "__TEXT,__ustring", align 2
+
+// RUN: clang-cc -triple powerpc-apple-darwin9 -emit-llvm %s -o - | FileCheck -check-prefix MSB %s
+
+// CHECK-MSB: @.str = private constant [8 x i8] c"string0\00"
+// CHECK-MSB: @.str1 = private constant [8 x i8] c"string1\00", section "__TEXT,__cstring,cstring_literals"
+// CHECK-MSB: @__utf16_string_ = internal global [35 x i8] c"\00h\00e\00l\00l\00o\00 !\92\00 &\03\00 !\90\00 \00w\00o\00r\00l\00d\00", section "__TEXT,__ustring", align 2
 
 const char *g0 = "string0";
 const void *g1 = __builtin___CFStringMakeConstantString("string1");