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



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@226988 91177308-0d34-0410-b5e6-96231b3b80d8

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<char> 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<const char *> &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);

test/Other/Inputs/utf8-bom-response

@@ -0,0 +1 @@
+-help

test/Other/Inputs/utf8-response

@@ -0,0 +1 @@
+-help

test/Other/ResponseFile.ll

@@ -6,6 +6,11 @@
 ; RUN: llvm-as @%t.list2 -o %t.bc
 ; RUN: llvm-nm %t.bc 2>&1 | FileCheck %s
 
+; When the response file begins with UTF8 BOM sequence, we shall remove them.
+; Neither command below should return a "Could not open input file" error.
+; RUN: llvm-as @%S/Inputs/utf8-response > /dev/null
+; RUN: llvm-as @%S/Inputs/utf8-bom-response > /dev/null
+
 ; CHECK: T foobar
 
 define void @foobar() {