[Support] Treat null bytes as separator in windows command line strings

When reading directives from a .drectve section, the directives are
tokenized as a normal windows command line. However in these cases,
link.exe allows the directives to be separated by null bytes, not only by
spaces.

A test case for this change will be added in the lld repo.

Differential Revision: https://reviews.llvm.org/D52014

llvm-svn: 342204

1 files changed, 6 insertions, 2 deletions

diff --git a/llvm/lib/Support/CommandLine.cpp b/llvm/lib/Support/CommandLine.cpp
index a1e659a..b169bb6 100644
--- a/llvm/lib/Support/CommandLine.cpp
+++ b/llvm/lib/Support/CommandLine.cpp
@@ -693,6 +693,10 @@ 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,
@@ -808,7 +812,7 @@ void cl::TokenizeWindowsCommandLine(StringRef Src, StringSaver &Saver,
     // 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);
@@ -832,7 +836,7 @@ void cl::TokenizeWindowsCommandLine(StringRef Src, StringSaver &Saver,
     // 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;