msh-console/library/stringtoargcargv.cpp

/** stringtoargcargv.cpp -- Parsing a string to std::vector<string>

  Copyright (C) 2011 Bernhard Eder

  This software is provided 'as-is', without any express or implied
  warranty.  In no event will the authors be held liable for any damages
  arising from the use of this software.

  Permission is granted to anyone to use this software for any purpose,
  including commercial applications, and to alter it and redistribute it
  freely, subject to the following restrictions:

  1. The origin of this software must not be misrepresented; you must not
   claim that you wrote the original software. If you use this software
   in a product, an acknowledgment in the product documentation would be
   appreciated but is not required.
  2. Altered source versions must be plainly marked as such, and must not be
   misrepresented as being the original software.
  3. This notice may not be removed or altered from any source distribution.

  Bernhard Eder blog_at_bbgen.net

*/

///The code is modified for the null-termination of argv

#include "stringtoargcargv.h"

namespace StringToArgcArgv{

    static inline bool _isQuote(char c);
    static inline bool _isEscape(char c);
    static inline bool _isPipe(char c);
    static inline bool _isWhitespace(char c);

    void vectorToArgcArgv(const std::vector<std::string>& args, int* argc, char*** argv){
        *argv = new char*[args.size()+1]();
        int i=0;
        for(std::vector<std::string>::const_iterator it = args.begin();
          it != args.end();
          ++it, ++i){
            std::string arg = *it;
            (*argv)[i] = new char[arg.length()+1]();
            std::strcpy((*argv)[i], arg.c_str());
        }
        (*argv)[i]=NULL;
        *argc = args.size();
    }

    void stringToArgcArgv(const std::string& str, int* argc, char*** argv){
        return vectorToArgcArgv(parseStringToVector(str),argc,argv);
    }

    void freeString(int& argc, char**& argv){
        for(int i=0; i<argc; i++){
            delete[] argv[i];
        }
        delete[] argv;
    }

    std::vector<std::string> parseStringToVector(const std::string& args)
    {
      std::stringstream ain(args);    // used to iterate over input string
      ain >> std::noskipws;           // do not skip white spaces
      std::vector<std::string> oargs; // output list of arguments

      std::stringstream currentArg("");
      currentArg >> std::noskipws;

      // current state
      enum State {
        InArg,      // currently scanning an argument
        InArgQuote, // currently scanning an argument (which started with quotes)
        OutOfArg    // currently not scanning an argument
      };
      State currentState = OutOfArg;

      char currentQuoteChar = '\0'; // to distinguish between ' and " quotations
                                    // this allows to use "foo'bar"

      char c;
      while(!ain.eof() && (ain >> c)) { // iterate char by char

        if(_isQuote(c)) {
          switch(currentState) {
            case OutOfArg:
              currentArg.str(std::string());
            case InArg:
              currentState = InArgQuote;
              currentQuoteChar = c;
              break;

            case InArgQuote:
              if(c == currentQuoteChar)
                currentState = InArg;
              else
                currentArg << c;
              break;
          }

        }
        else if(_isWhitespace(c) || _isPipe(c)) {
            switch(currentState) {
            case InArg:
                oargs.push_back(currentArg.str());
                if(_isPipe(c)) oargs.push_back("|");
                currentState = OutOfArg;
                break;
            case InArgQuote:
                currentArg << c;
                break;
            case OutOfArg:
                if(_isPipe(c)) oargs.push_back("|");
                    // nothing
                    break;
                }
        }
        else if(_isEscape(c)) {
          switch(currentState) {
            case OutOfArg:
              currentArg.str(std::string());
              currentState = InArg;
            case InArg:
            case InArgQuote:
              if(ain.eof())
              {
    #ifdef WIN32
                // Windows doesn't care about an escape character at the end.
                // It just adds \ to the arg.
                currentArg << c;
    #else
                throw(std::runtime_error("Found Escape Character at end of file."));
    #endif
              }
              else
              {
    #ifdef WIN32
                // Windows only escapes the " character.
                // Every other character is just printed and the \ is added itself.
                char c1 = c;
                ain >> c;
                if(c != '\"')
                  currentArg << c1; // only ignore \ when next char is "
                ain.unget();
    #else
                ain >> c;
                currentArg << c;
    #endif
              }
              break;
          }
        }
        else {
          switch(currentState) {
            case InArg:
            case InArgQuote:
              currentArg << c;
              break;

            case OutOfArg:
              currentArg.str(std::string());
              currentArg << c;
              currentState = InArg;
              break;
          }
        }
      }

      if(currentState == InArg)
        oargs.push_back(currentArg.str());
      else if(currentState == InArgQuote)
        throw(std::runtime_error("Starting quote has no ending quote."));

      return oargs;
    }

    static inline bool _isQuote(char c){
      if(c == '\"')
        return true;
      else if(c == '\'')
        return true;

      return false;
    }

    static inline bool _isEscape(char c){
      if(c == '\\')
        return true;

      return false;
    }

    static inline bool _isWhitespace(char c){
      if(c == ' ')
        return true;
      else if(c == '\t')
        return true;

      return false;
    }

    static inline bool _isPipe(char c){
      if(c == '|') return true;
      return false;
    }
}