Fix a bug that reports UTF16 (LE) files as UTF32 (LE) ones

[owenpan]

Summary

Also fix a typo for the SCSU byte order mark.

[sammccall]

This looks good, but did you intend to make a new diff? It looks like D61559 didn't land yet.

[owenpan]

This patch fixes clang. I copied the code from here to clang/tools/clang-format/ClangFormat.cpp in D61559 to fix clang-format. I'm not sure if the code here should be moved into a function, though.

cfe/trunk/lib/Basic/SourceManager.cpp

if (getRawBuffer()->getBufferSize() != (size_t)ContentsEntry->getSize()) {
     return Buffer.getPointer();
   }
 
   // If the buffer is valid, check to see if it has a UTF Byte Order Mark
   // (BOM).  We only support UTF-8 with and without a BOM right now.  See
   // http://en.wikipedia.org/wiki/Byte_order_mark for more information.
   StringRef BufStr = Buffer.getPointer()->getBuffer();
   const char *InvalidBOM = llvm::StringSwitch<const char *>(BufStr)
-    .StartsWith("\xFE\xFF", "UTF-16 (BE)")
-    .StartsWith("\xFF\xFE", "UTF-16 (LE)")
     .StartsWith(llvm::StringLiteral::withInnerNUL("\x00\x00\xFE\xFF"),
                                                   "UTF-32 (BE)")
     .StartsWith(llvm::StringLiteral::withInnerNUL("\xFF\xFE\x00\x00"),
                                                   "UTF-32 (LE)")
+    .StartsWith("\xFE\xFF", "UTF-16 (BE)")
+    .StartsWith("\xFF\xFE", "UTF-16 (LE)")
     .StartsWith("\x2B\x2F\x76", "UTF-7")
     .StartsWith("\xF7\x64\x4C", "UTF-1")
     .StartsWith("\xDD\x73\x66\x73", "UTF-EBCDIC")
-    .StartsWith("\x0E\xFE\xFF", "SDSU")
+    .StartsWith("\x0E\xFE\xFF", "SCSU")
     .StartsWith("\xFB\xEE\x28", "BOCU-1")
     .StartsWith("\x84\x31\x95\x33", "GB-18030")
     .Default(nullptr);
 
   if (InvalidBOM) {
     Diag.Report(Loc, diag::err_unsupported_bom)
       << InvalidBOM << ContentsEntry->getName();
     Buffer.setInt(Buffer.getInt() | InvalidFlag);