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

2 files changed, 5 insertions, 4 deletions

diff --git a/lib/Serialization/ASTReaderStmt.cpp b/lib/Serialization/ASTReaderStmt.cpp
index 87912af461..e57ab1937c 100644
--- a/lib/Serialization/ASTReaderStmt.cpp
+++ b/lib/Serialization/ASTReaderStmt.cpp
@@ -372,12 +372,13 @@ void ASTStmtReader::VisitStringLiteral(StringLiteral *E) {
   assert(Record[Idx] == E->getNumConcatenated() &&
          "Wrong number of concatenated tokens!");
   ++Idx;
-  E->Kind = static_cast<StringLiteral::StringKind>(Record[Idx++]);
-  E->IsPascal = Record[Idx++];
+  StringLiteral::StringKind kind =
+        static_cast<StringLiteral::StringKind>(Record[Idx++]);
+  bool isPascal = Record[Idx++];
 
   // Read string data
   llvm::SmallString<16> Str(&Record[Idx], &Record[Idx] + Len);
-  E->setString(Reader.getContext(), Str.str());
+  E->setString(Reader.getContext(), Str.str(), kind, isPascal);
   Idx += Len;
 
   // Read source locations
diff --git a/lib/Serialization/ASTWriterStmt.cpp b/lib/Serialization/ASTWriterStmt.cpp
index 0721c299a1..61570a880a 100644
--- a/lib/Serialization/ASTWriterStmt.cpp
+++ b/lib/Serialization/ASTWriterStmt.cpp
@@ -331,7 +331,7 @@ void ASTStmtWriter::VisitStringLiteral(StringLiteral *E) {
   // StringLiteral. However, we can't do so now because we have no
   // provision for coping with abbreviations when we're jumping around
   // the AST file during deserialization.
-  Record.append(E->getString().begin(), E->getString().end());
+  Record.append(E->getBytes().begin(), E->getBytes().end());
   for (unsigned I = 0, N = E->getNumConcatenated(); I != N; ++I)
     Writer.AddSourceLocation(E->getStrTokenLoc(I), Record);
   Code = serialization::EXPR_STRING_LITERAL;