Chris@16: //  (C) Copyright Jeremy Siek 2004 
Chris@16: //  Distributed under the Boost Software License, Version 1.0. (See
Chris@16: //  accompanying file LICENSE_1_0.txt or copy at
Chris@16: //  http://www.boost.org/LICENSE_1_0.txt)
Chris@16: 
Chris@16: #ifndef BOOST_STRINGTOK_HPP
Chris@16: #define BOOST_STRINGTOK_HPP
Chris@16: 
Chris@16: /*
Chris@16:  * stringtok.hpp -- Breaks a string into tokens.  This is an example for lib3.
Chris@16:  *
Chris@16:  * Template function looks like this:
Chris@16:  *
Chris@16:  *    template <typename Container>
Chris@16:  *    void stringtok (Container &l,
Chris@16:  *                    string const &s,
Chris@16:  *                    char const * const ws = " \t\n");
Chris@16:  *
Chris@16:  * A nondestructive version of strtok() that handles its own memory and can
Chris@16:  * be broken up by any character(s).  Does all the work at once rather than
Chris@16:  * in an invocation loop like strtok() requires.
Chris@16:  *
Chris@16:  * Container is any type that supports push_back(a_string), although using
Chris@16:  * list<string> and deque<string> are indicated due to their O(1) push_back.
Chris@16:  * (I prefer deque<> because op[]/at() is available as well.)  The first
Chris@16:  * parameter references an existing Container.
Chris@16:  *
Chris@16:  * s is the string to be tokenized.  From the parameter declaration, it can
Chris@16:  * be seen that s is not affected.  Since references-to-const may refer to
Chris@16:  * temporaries, you could use stringtok(some_container, readline("")) when
Chris@16:  * using the GNU readline library.
Chris@16:  *
Chris@16:  * The final parameter is an array of characters that serve as whitespace.
Chris@16:  * Whitespace characters default to one or more of tab, space, and newline,
Chris@16:  * in any combination.
Chris@16:  *
Chris@16:  * 'l' need not be empty on entry.  On return, 'l' will have the token
Chris@16:  * strings appended.
Chris@16:  *
Chris@16:  *
Chris@16:  * [Example:
Chris@16:  *       list<string>       ls;
Chris@16:  *       stringtok (ls, " this  \t is\t\n  a test  ");
Chris@16:  *       for (list<string>::const_iterator i = ls.begin();
Chris@16:  *            i != ls.end(); ++i)
Chris@16:  *       {
Chris@16:  *            cerr << ':' << (*i) << ":\n";
Chris@16:  *       }
Chris@16:  *
Chris@16:  *  would print
Chris@16:  *       :this:
Chris@16:  *       :is:
Chris@16:  *       :a:
Chris@16:  *       :test:
Chris@16:  * -end example]
Chris@16:  *
Chris@16:  * pedwards@jaj.com  May 1999
Chris@16: */
Chris@16: 
Chris@16: 
Chris@16: #include <string>
Chris@16: #include <cstring>    // for strchr
Chris@16: 
Chris@16: 
Chris@16: /*****************************************************************
Chris@16:  * This is the only part of the implementation that I don't like.
Chris@16:  * It can probably be improved upon by the reader...
Chris@16: */
Chris@16: 
Chris@16:     inline bool
Chris@16:     isws (char c, char const * const wstr)
Chris@16:     {
Chris@16:         using namespace std;
Chris@16:         return (strchr(wstr,c) != NULL);
Chris@16:     }
Chris@16: 
Chris@16: 
Chris@16: namespace boost {
Chris@16: 
Chris@16: /*****************************************************************
Chris@16:  * Simplistic and quite Standard, but a bit slow.  This should be
Chris@16:  * templatized on basic_string instead, or on a more generic StringT
Chris@16:  * that just happens to support ::size_type, .substr(), and so on.
Chris@16:  * I had hoped that "whitespace" would be a trait, but it isn't, so
Chris@16:  * the user must supply it.  Enh, this lets them break up strings on
Chris@16:  * different things easier than traits would anyhow.
Chris@16: */
Chris@16: template <typename Container>
Chris@16: void
Chris@16: stringtok (Container &l, std::string const &s, char const * const ws = " \t\n")
Chris@16: {
Chris@16:   typedef std::string::size_type size_type;
Chris@16:     const size_type  S = s.size();
Chris@16:           size_type  i = 0;
Chris@16: 
Chris@16:     while (i < S) {
Chris@16:         // eat leading whitespace
Chris@16:         while ((i < S) && (isws(s[i],ws)))  ++i;
Chris@16:         if (i == S)  return;  // nothing left but WS
Chris@16: 
Chris@16:         // find end of word
Chris@16:         size_type  j = i+1;
Chris@16:         while ((j < S) && (!isws(s[j],ws)))  ++j;
Chris@16: 
Chris@16:         // add word
Chris@16:         l.push_back(s.substr(i,j-i));
Chris@16: 
Chris@16:         // set up for next loop
Chris@16:         i = j+1;
Chris@16:     }
Chris@16: }
Chris@16: 
Chris@16: 
Chris@16: } // namespace boost
Chris@16: 
Chris@16: #endif // BOOST_STRINGTOK_HPP