+static bool isWhitespace(char C) {
+ return strchr(" \t\n\r\f\v", C);
+}
+
+static bool isQuote(char C) {
+ return C == '\"' || C == '\'';
+}
+
+static bool isGNUSpecial(char C) {
+ return strchr("\\\"\' ", C);
+}
+
+void cl::TokenizeGNUCommandLine(StringRef Src, StringSaver &Saver,
+ SmallVectorImpl<const char *> &NewArgv) {
+ SmallString<128> Token;
+ for (size_t I = 0, E = Src.size(); I != E; ++I) {
+ // Consume runs of whitespace.
+ if (Token.empty()) {
+ while (I != E && isWhitespace(Src[I]))
+ ++I;
+ if (I == E) break;
+ }
+
+ // Backslashes can escape backslashes, spaces, and other quotes. Otherwise
+ // they are literal. This makes it much easier to read Windows file paths.
+ if (I + 1 < E && Src[I] == '\\' && isGNUSpecial(Src[I + 1])) {
+ ++I; // Skip the escape.
+ Token.push_back(Src[I]);
+ continue;
+ }
+
+ // Consume a quoted string.
+ if (isQuote(Src[I])) {
+ char Quote = Src[I++];
+ while (I != E && Src[I] != Quote) {
+ // Backslashes are literal, unless they escape a special character.
+ if (Src[I] == '\\' && I + 1 != E && isGNUSpecial(Src[I + 1]))
+ ++I;
+ Token.push_back(Src[I]);
+ ++I;
+ }
+ if (I == E) break;
+ continue;
+ }
+
+ // End the token if this is whitespace.
+ if (isWhitespace(Src[I])) {
+ if (!Token.empty())
+ NewArgv.push_back(Saver.SaveString(Token.c_str()));
+ Token.clear();
+ continue;
+ }
+
+ // This is a normal character. Append it.
+ 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()));
+}
+
+/// Backslashes are interpreted in a rather complicated way in the Windows-style
+/// command line, because backslashes are used both to separate path and to
+/// escape double quote. This method consumes runs of backslashes as well as the
+/// following double quote if it's escaped.
+///
+/// * If an even number of backslashes is followed by a double quote, one
+/// backslash is output for every pair of backslashes, and the last double
+/// quote remains unconsumed. The double quote will later be interpreted as
+/// the start or end of a quoted string in the main loop outside of this
+/// function.