0016-MSVC-Compatibility.patch

diff --git a/clang/include/clang/Basic/SourceManager.h b/clang/include/clang/Basic/SourceManager.h
index cc29c24f5a35..c8e44dd40593 100644
--- a/clang/include/clang/Basic/SourceManager.h
+++ b/clang/include/clang/Basic/SourceManager.h
@@ -259,6 +259,12 @@ public:
   // If BufStr has an invalid BOM, returns the BOM name; otherwise, returns
   // nullptr
   static const char *getInvalidBOM(StringRef BufStr);
+
+  // Check buffer is UTF16
+  static bool checkBufUTF16(StringRef BufStr);
+
+   // Check buffer is UTF32
+  static bool checkBufUTF32(StringRef BufStr);
 };
 
 // Assert that the \c ContentCache objects will always be 8-byte aligned so
diff --git a/clang/lib/Basic/SourceManager.cpp b/clang/lib/Basic/SourceManager.cpp
index ec3e35595bb7..6419442b0c86 100644
--- a/clang/lib/Basic/SourceManager.cpp
+++ b/clang/lib/Basic/SourceManager.cpp
@@ -33,6 +33,7 @@
 #include "llvm/Support/MemoryBuffer.h"
 #include "llvm/Support/Path.h"
 #include "llvm/Support/raw_ostream.h"
+#include "llvm/Support/ConvertUTF.h"
 #include <algorithm>
 #include <cassert>
 #include <cstddef>
@@ -98,6 +99,33 @@ const char *ContentCache::getInvalidBOM(StringRef BufStr) {
   return InvalidBOM;
 }
 
+// Check buffer is UTF16
+bool ContentCache::checkBufUTF16(StringRef BufStr) {
+    const char *Result = llvm::StringSwitch<const char *>(BufStr)
+                             .StartsWith("\xFE\xFF", "UTF-16 (BE)")
+                             .StartsWith("\xFF\xFE", "UTF-16 (LE)")
+                             .Default(nullptr);
+    if (Result) {
+        return true;
+    }
+    return false;
+}
+
+// Check buffer is UTF32
+bool ContentCache::checkBufUTF32(StringRef BufStr) {
+    const char *Result =
+        llvm::StringSwitch<const char *>(BufStr)
+            .StartsWith(llvm::StringLiteral::withInnerNUL("\x00\x00\xFE\xFF"),
+                        "UTF-32 (BE)")
+            .StartsWith(llvm::StringLiteral::withInnerNUL("\xFF\xFE\x00\x00"),
+                        "UTF-32 (LE)")
+            .Default(nullptr);
+    if (Result) {
+        return true;
+    }
+    return false;
+}
+
 llvm::Optional<llvm::MemoryBufferRef>
 ContentCache::getBufferOrNone(DiagnosticsEngine &Diag, FileManager &FM,
                               SourceLocation Loc) const {
@@ -175,6 +203,21 @@ ContentCache::getBufferOrNone(DiagnosticsEngine &Diag, FileManager &FM,
   // http://en.wikipedia.org/wiki/Byte_order_mark for more information.
   StringRef BufStr = Buffer->getBuffer();
   const char *InvalidBOM = getInvalidBOM(BufStr);
+  
+  // [MSVC Compatibility] Trying to convert UTF16 to UTF8.
+  if (InvalidBOM && checkBufUTF16(BufStr)) {
+    std::string StrUtf8;
+    if (llvm::convertUTF16ToUTF8String(
+            llvm::makeArrayRef(BufStr.data(), BufStr.size()), StrUtf8)) {
+      char *NewBuf = new char[StrUtf8.size() + 4]{0};
+      memcpy(NewBuf, StrUtf8.data(), StrUtf8.size());
+      Buffer->BufferStart = NewBuf;
+      Buffer->BufferEnd = NewBuf + StrUtf8.size();
+      BufStr = Buffer->getBuffer();
+      // Verify it again.
+      InvalidBOM = getInvalidBOM(BufStr);
+    }
+  }
 
   if (InvalidBOM) {
     Diag.Report(Loc, diag::err_unsupported_bom)
diff --git a/llvm/include/llvm/Support/MemoryBuffer.h b/llvm/include/llvm/Support/MemoryBuffer.h
index 6385805eba1d..7add4aa3d9a7 100644
--- a/llvm/include/llvm/Support/MemoryBuffer.h
+++ b/llvm/include/llvm/Support/MemoryBuffer.h
@@ -48,6 +48,8 @@ using file_t = int;
 /// reading when they encounter a '\0' than to continually check the file
 /// position to see if it has reached the end of the file.
 class MemoryBuffer {
+// hack it
+public:
   const char *BufferStart; // Start of the buffer.
   const char *BufferEnd;   // End of the buffer.