From 7f36a79ee9387b738b83a265d6b30427de35b2df Mon Sep 17 00:00:00 2001 From: Eric Christopher Date: Sat, 9 Apr 2011 00:01:04 +0000 Subject: Eat the UTF-8 BOM at the beginning of a file since it's ignored anyhow. Nom Nom Nom. Patch by Anton Korobeynikov! llvm-svn: 129174 --- clang/lib/Basic/SourceManager.cpp | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'clang/lib/Basic/SourceManager.cpp') diff --git a/clang/lib/Basic/SourceManager.cpp b/clang/lib/Basic/SourceManager.cpp index b6939ec..8262feb 100644 --- a/clang/lib/Basic/SourceManager.cpp +++ b/clang/lib/Basic/SourceManager.cpp @@ -126,13 +126,12 @@ const llvm::MemoryBuffer *ContentCache::getBuffer(Diagnostic &Diag, if (Invalid) *Invalid = true; 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 without a BOM right now. See + // (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. llvm::StringRef BufStr = Buffer.getPointer()->getBuffer(); - const char *BOM = llvm::StringSwitch(BufStr) - .StartsWith("\xEF\xBB\xBF", "UTF-8") + const char *InvalidBOM = llvm::StringSwitch(BufStr) .StartsWith("\xFE\xFF", "UTF-16 (BE)") .StartsWith("\xFF\xFE", "UTF-16 (LE)") .StartsWith("\x00\x00\xFE\xFF", "UTF-32 (BE)") @@ -145,9 +144,9 @@ const llvm::MemoryBuffer *ContentCache::getBuffer(Diagnostic &Diag, .StartsWith("\x84\x31\x95\x33", "GB-18030") .Default(0); - if (BOM) { + if (InvalidBOM) { Diag.Report(Loc, diag::err_unsupported_bom) - << BOM << ContentsEntry->getName(); + << InvalidBOM << ContentsEntry->getName(); Buffer.setInt(Buffer.getInt() | InvalidFlag); } -- cgit v1.1