1 // (C) Copyright Jeremy Siek 2004
2 // Distributed under the Boost Software License, Version 1.0. (See
3 // accompanying file LICENSE_1_0.txt or copy at
4 // http://www.boost.org/LICENSE_1_0.txt)
5
6 #ifndef BOOST_STRINGTOK_HPP
7 #define BOOST_STRINGTOK_HPP
8
9 /*
10 * stringtok.hpp -- Breaks a string into tokens. This is an example for lib3.
11 *
12 * Template function looks like this:
13 *
14 * template <typename Container>
15 * void stringtok (Container &l,
16 * string const &s,
17 * char const * const ws = " \t\n");
18 *
19 * A nondestructive version of strtok() that handles its own memory and can
20 * be broken up by any character(s). Does all the work at once rather than
21 * in an invocation loop like strtok() requires.
22 *
23 * Container is any type that supports push_back(a_string), although using
24 * list<string> and deque<string> are indicated due to their O(1) push_back.
25 * (I prefer deque<> because op[]/at() is available as well.) The first
26 * parameter references an existing Container.
27 *
28 * s is the string to be tokenized. From the parameter declaration, it can
29 * be seen that s is not affected. Since references-to-const may refer to
30 * temporaries, you could use stringtok(some_container, readline("")) when
31 * using the GNU readline library.
32 *
33 * The final parameter is an array of characters that serve as whitespace.
34 * Whitespace characters default to one or more of tab, space, and newline,
35 * in any combination.
36 *
37 * 'l' need not be empty on entry. On return, 'l' will have the token
38 * strings appended.
39 *
40 *
41 * [Example:
42 * list<string> ls;
43 * stringtok (ls, " this \t is\t\n a test ");
44 * for (list<string>::const_iterator i = ls.begin();
45 * i != ls.end(); ++i)
46 * {
47 * cerr << ':' << (*i) << ":\n";
48 * }
49 *
50 * would print
51 * :this:
52 * :is:
53 * :a:
54 * :test:
55 * -end example]
56 *
57 * pedwards@jaj.com May 1999
58 */
59
60
61 #include <string>
62 #include <cstring> // for strchr
63
64
65 /*****************************************************************
66 * This is the only part of the implementation that I don't like.
67 * It can probably be improved upon by the reader...
68 */
69
70 inline bool
isws(char c,char const * const wstr)71 isws (char c, char const * const wstr)
72 {
73 using namespace std;
74 return (strchr(wstr,c) != NULL);
75 }
76
77
78 namespace boost {
79
80 /*****************************************************************
81 * Simplistic and quite Standard, but a bit slow. This should be
82 * templatized on basic_string instead, or on a more generic StringT
83 * that just happens to support ::size_type, .substr(), and so on.
84 * I had hoped that "whitespace" would be a trait, but it isn't, so
85 * the user must supply it. Enh, this lets them break up strings on
86 * different things easier than traits would anyhow.
87 */
88 template <typename Container>
89 void
stringtok(Container & l,std::string const & s,char const * const ws=" \\t\\n")90 stringtok (Container &l, std::string const &s, char const * const ws = " \t\n")
91 {
92 typedef std::string::size_type size_type;
93 const size_type S = s.size();
94 size_type i = 0;
95
96 while (i < S) {
97 // eat leading whitespace
98 while ((i < S) && (isws(s[i],ws))) ++i;
99 if (i == S) return; // nothing left but WS
100
101 // find end of word
102 size_type j = i+1;
103 while ((j < S) && (!isws(s[j],ws))) ++j;
104
105 // add word
106 l.push_back(s.substr(i,j-i));
107
108 // set up for next loop
109 i = j+1;
110 }
111 }
112
113
114 } // namespace boost
115
116 #endif // BOOST_STRINGTOK_HPP
117