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