Fix the representation of wide strings in the AST and IR so that it uses the native representation of integers for the elements. This fixes a bunch of nastiness involving
treating wide strings as a series of bytes.
Patch by Seth Cantrell.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@143417 91177308-0d34-0410-b5e6-96231b3b80d8
diff --git a/lib/AST/Expr.cpp b/lib/AST/Expr.cpp
index 96a8125..3239973 100644
--- a/lib/AST/Expr.cpp
+++ b/lib/AST/Expr.cpp
@@ -29,6 +29,7 @@
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/raw_ostream.h"
#include <algorithm>
+#include <cstring>
using namespace clang;
/// isKnownToHaveBooleanValue - Return true if this is an integer expression
@@ -482,6 +483,29 @@
return V.convertToDouble();
}
+int StringLiteral::mapCharByteWidth(TargetInfo const &target,StringKind k) {
+ int CharByteWidth;
+ switch(k) {
+ case Ascii:
+ case UTF8:
+ CharByteWidth = target.getCharWidth();
+ break;
+ case Wide:
+ CharByteWidth = target.getWCharWidth();
+ break;
+ case UTF16:
+ CharByteWidth = target.getChar16Width();
+ break;
+ case UTF32:
+ CharByteWidth = target.getChar32Width();
+ }
+ assert((CharByteWidth & 7) == 0 && "Assumes character size is byte multiple");
+ CharByteWidth /= 8;
+ assert((CharByteWidth==1 || CharByteWidth==2 || CharByteWidth==4)
+ && "character byte widths supported are 1, 2, and 4 only");
+ return CharByteWidth;
+}
+
StringLiteral *StringLiteral::Create(ASTContext &C, StringRef Str,
StringKind Kind, bool Pascal, QualType Ty,
const SourceLocation *Loc,
@@ -494,12 +518,8 @@
StringLiteral *SL = new (Mem) StringLiteral(Ty);
// OPTIMIZE: could allocate this appended to the StringLiteral.
- char *AStrData = new (C, 1) char[Str.size()];
- memcpy(AStrData, Str.data(), Str.size());
- SL->StrData = AStrData;
- SL->ByteLength = Str.size();
- SL->Kind = Kind;
- SL->IsPascal = Pascal;
+ SL->setString(C,Str,Kind,Pascal);
+
SL->TokLocs[0] = Loc[0];
SL->NumConcatenated = NumStrs;
@@ -513,17 +533,46 @@
sizeof(SourceLocation)*(NumStrs-1),
llvm::alignOf<StringLiteral>());
StringLiteral *SL = new (Mem) StringLiteral(QualType());
- SL->StrData = 0;
- SL->ByteLength = 0;
+ SL->CharByteWidth = 0;
+ SL->Length = 0;
SL->NumConcatenated = NumStrs;
return SL;
}
-void StringLiteral::setString(ASTContext &C, StringRef Str) {
- char *AStrData = new (C, 1) char[Str.size()];
- memcpy(AStrData, Str.data(), Str.size());
- StrData = AStrData;
- ByteLength = Str.size();
+void StringLiteral::setString(ASTContext &C, StringRef Str,
+ StringKind Kind, bool IsPascal) {
+ //FIXME: we assume that the string data comes from a target that uses the same
+ // code unit size and endianess for the type of string.
+ this->Kind = Kind;
+ this->IsPascal = IsPascal;
+
+ CharByteWidth = mapCharByteWidth(C.getTargetInfo(),Kind);
+ assert((Str.size()%CharByteWidth == 0)
+ && "size of data must be multiple of CharByteWidth");
+ Length = Str.size()/CharByteWidth;
+
+ switch(CharByteWidth) {
+ case 1: {
+ char *AStrData = new (C) char[Length];
+ std::memcpy(AStrData,Str.data(),Str.size());
+ StrData.asChar = AStrData;
+ break;
+ }
+ case 2: {
+ uint16_t *AStrData = new (C) uint16_t[Length];
+ std::memcpy(AStrData,Str.data(),Str.size());
+ StrData.asUInt16 = AStrData;
+ break;
+ }
+ case 4: {
+ uint32_t *AStrData = new (C) uint32_t[Length];
+ std::memcpy(AStrData,Str.data(),Str.size());
+ StrData.asUInt32 = AStrData;
+ break;
+ }
+ default:
+ assert(false && "unsupported CharByteWidth");
+ }
}
/// getLocationOfByte - Return a source location that points to the specified