From a8cf495a1592f9d2deddd1c39ce57e81dcc426e5 Mon Sep 17 00:00:00 2001 From: Yunzhong Gao Date: Sat, 24 Jan 2015 04:23:08 +0000 Subject: If we see UTF-8 BOM sequence at the beginning of a response file, we shall remove these bytes before parsing. Phabricator Revision: http://reviews.llvm.org/D7156 llvm-svn: 226988 --- llvm/lib/Support/CommandLine.cpp | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'llvm/lib/Support/CommandLine.cpp') diff --git a/llvm/lib/Support/CommandLine.cpp b/llvm/lib/Support/CommandLine.cpp index a774421b26c..b4e32257a01 100644 --- a/llvm/lib/Support/CommandLine.cpp +++ b/llvm/lib/Support/CommandLine.cpp @@ -655,6 +655,13 @@ void cl::TokenizeWindowsCommandLine(StringRef Src, StringSaver &Saver, NewArgv.push_back(nullptr); } +// It is called byte order marker but the UTF-8 BOM is actually not affected +// by the host system's endianness. +static bool hasUTF8ByteOrderMark(ArrayRef S) { + return (S.size() >= 3 && + S[0] == '\xef' && S[1] == '\xbb' && S[2] == '\xbf'); +} + static bool ExpandResponseFile(const char *FName, StringSaver &Saver, TokenizerCallback Tokenizer, SmallVectorImpl &NewArgv, @@ -674,6 +681,11 @@ static bool ExpandResponseFile(const char *FName, StringSaver &Saver, return false; Str = StringRef(UTF8Buf); } + // If we see UTF-8 BOM sequence at the beginning of a file, we shall remove + // these bytes before parsing. + // Reference: http://en.wikipedia.org/wiki/UTF-8#Byte_order_mark + else if (hasUTF8ByteOrderMark(BufRef)) + Str = StringRef(BufRef.data() + 3, BufRef.size() - 3); // Tokenize the contents into NewArgv. Tokenizer(Str, Saver, NewArgv, MarkEOLs); -- cgit v1.2.3