[LLD] [COFF] Allow embedded directives to be separated by null bytes

[mstorsjo]

Summary

The PE spec says that they will be separated by spaces, but link.exe handles it just fine if they are separated by null bytes as well.

Since these directives are parsed and split by TokenizeWindowsCommandLine, this function needs to learn to treat null bytes as separators - this patch makes that unconditional, but at worst we might need to make it an optional feature, only used when parsing .drectve.

[ruiu]

LGTM

llvm/trunk/lib/Support/CommandLine.cpp

static bool EatsUnboundedNumberOfValues(const Option *O) {
   return O->getNumOccurrencesFlag() == cl::ZeroOrMore ||
          O->getNumOccurrencesFlag() == cl::OneOrMore;
 }
 
 static bool isWhitespace(char C) {
   return C == ' ' || C == '\t' || C == '\r' || C == '\n';
 }
 
+static bool isWhitespaceOrNull(char C) {
+  return isWhitespace(C) || C == '\0';
+}
+
 static bool isQuote(char C) { return C == '\"' || C == '\''; }
 
 void cl::TokenizeGNUCommandLine(StringRef Src, StringSaver &Saver,
                                 SmallVectorImpl<const char *> &NewArgv,
                                 bool MarkEOLs) {
   SmallString<128> Token;
   for (size_t I = 0, E = Src.size(); I != E; ++I) {
     // Consume runs of whitespace.
void cl::TokenizeWindowsCommandLine(StringRef Src, StringSaver &Saver,
   // end of the source string.
   enum { INIT, UNQUOTED, QUOTED } State = INIT;
   for (size_t I = 0, E = Src.size(); I != E; ++I) {
     char C = Src[I];
 
     // INIT state indicates that the current input index is at the start of
     // the string or between tokens.
     if (State == INIT) {
-      if (isWhitespace(C)) {
+      if (isWhitespaceOrNull(C)) {
         // Mark the end of lines in response files
         if (MarkEOLs && C == '\n')
           NewArgv.push_back(nullptr);
         continue;
       }
       if (C == '"') {
         State = QUOTED;
         continue;
       }
       if (C == '\\') {
         I = parseBackslash(Src, I, Token);
         State = UNQUOTED;
         continue;
       }
       Token.push_back(C);
       State = UNQUOTED;
       continue;
     }
 
     // UNQUOTED state means that it's reading a token not quoted by double
     // quotes.
     if (State == UNQUOTED) {
       // Whitespace means the end of the token.
-      if (isWhitespace(C)) {
+      if (isWhitespaceOrNull(C)) {
         NewArgv.push_back(Saver.save(StringRef(Token)).data());
         Token.clear();
         State = INIT;
         // Mark the end of lines in response files
         if (MarkEOLs && C == '\n')
           NewArgv.push_back(nullptr);
         continue;
       }