+/// * If an odd number of backslashes is followed by a double quote, one
+/// backslash is output for every pair of backslashes, and a double quote is
+/// output for the last pair of backslash-double quote. The double quote is
+/// consumed in this case.
+///
+/// * Otherwise, backslashes are interpreted literally.
+static size_t parseBackslash(StringRef Src, size_t I, SmallString<128> &Token) {
+ size_t E = Src.size();
+ int BackslashCount = 0;
+ // Skip the backslashes.
+ do {
+ ++I;
+ ++BackslashCount;
+ } while (I != E && Src[I] == '\\');
+
+ bool FollowedByDoubleQuote = (I != E && Src[I] == '"');
+ if (FollowedByDoubleQuote) {
+ Token.append(BackslashCount / 2, '\\');
+ if (BackslashCount % 2 == 0)
+ return I - 1;
+ Token.push_back('"');
+ return I;
+ }
+ Token.append(BackslashCount, '\\');
+ return I - 1;
+}
+
+void cl::TokenizeWindowsCommandLine(StringRef Src, StringSaver &Saver,
+ SmallVectorImpl<const char *> &NewArgv) {
+ SmallString<128> Token;
+
+ // This is a small state machine to consume characters until it reaches the
+ // end of the source string.
+ enum { INIT, UNQUOTED, QUOTED } State = INIT;
+ for (size_t I = 0, E = Src.size(); I != E; ++I) {
+ // INIT state indicates that the current input index is at the start of
+ // the string or between tokens.
+ if (State == INIT) {
+ if (isWhitespace(Src[I]))
+ continue;
+ if (Src[I] == '"') {
+ State = QUOTED;
+ continue;
+ }
+ if (Src[I] == '\\') {
+ I = parseBackslash(Src, I, Token);
+ State = UNQUOTED;
+ continue;
+ }
+ Token.push_back(Src[I]);
+ 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(Src[I])) {
+ NewArgv.push_back(Saver.SaveString(Token.c_str()));
+ Token.clear();
+ State = INIT;
+ continue;
+ }
+ if (Src[I] == '"') {
+ State = QUOTED;
+ continue;
+ }
+ if (Src[I] == '\\') {
+ I = parseBackslash(Src, I, Token);
+ continue;
+ }
+ Token.push_back(Src[I]);
+ continue;
+ }
+
+ // QUOTED state means that it's reading a token quoted by double quotes.
+ if (State == QUOTED) {
+ if (Src[I] == '"') {
+ State = UNQUOTED;
+ continue;
+ }
+ if (Src[I] == '\\') {
+ I = parseBackslash(Src, I, Token);
+ continue;
+ }
+ Token.push_back(Src[I]);
+ }
+ }
+ // Append the last token after hitting EOF with no whitespace.
+ if (!Token.empty())
+ NewArgv.push_back(Saver.SaveString(Token.c_str()));
+}
+
+static bool ExpandResponseFile(const char *FName, StringSaver &Saver,
+ TokenizerCallback Tokenizer,
+ SmallVectorImpl<const char *> &NewArgv) {
+ OwningPtr<MemoryBuffer> MemBuf;
+ if (MemoryBuffer::getFile(FName, MemBuf))
+ return false;
+ StringRef Str(MemBuf->getBufferStart(), MemBuf->getBufferSize());
+
+ // If we have a UTF-16 byte order mark, convert to UTF-8 for parsing.
+ ArrayRef<char> BufRef(MemBuf->getBufferStart(), MemBuf->getBufferEnd());
+ std::string UTF8Buf;
+ if (hasUTF16ByteOrderMark(BufRef)) {
+ if (!convertUTF16ToUTF8String(BufRef, UTF8Buf))
+ return false;
+ Str = StringRef(UTF8Buf);
+ }
+
+ // Tokenize the contents into NewArgv.
+ Tokenizer(Str, Saver, NewArgv);
+
+ return true;
+}
+
+/// \brief Expand response files on a command line recursively using the given
+/// StringSaver and tokenization strategy.
+bool cl::ExpandResponseFiles(StringSaver &Saver, TokenizerCallback Tokenizer,
+ SmallVectorImpl<const char *> &Argv) {
+ unsigned RspFiles = 0;
+ bool AllExpanded = false;
+
+ // Don't cache Argv.size() because it can change.
+ for (unsigned I = 0; I != Argv.size(); ) {
+ const char *Arg = Argv[I];
+ if (Arg[0] != '@') {
+ ++I;
+ continue;
+ }
+
+ // If we have too many response files, leave some unexpanded. This avoids
+ // crashing on self-referential response files.
+ if (RspFiles++ > 20)
+ return false;
+
+ // Replace this response file argument with the tokenization of its
+ // contents. Nested response files are expanded in subsequent iterations.
+ // FIXME: If a nested response file uses a relative path, is it relative to
+ // the cwd of the process or the response file?
+ SmallVector<const char *, 0> ExpandedArgv;
+ if (!ExpandResponseFile(Arg + 1, Saver, Tokenizer, ExpandedArgv)) {
+ AllExpanded = false;