1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
|
#ifndef PBD_TOKENIZER
#define PBD_TOKENIZER
#include <iterator>
#include <string>
#include <pbd/whitespace.h>
namespace PBD {
/**
Tokenize string, this should work for standard
strings as well as Glib::ustring. This is a bit of a hack,
there are much better string tokenizing patterns out there.
If strip_whitespace is set to true, tokens will be checked to see
that they still have a length after stripping. If no length, they
are discarded.
*/
template<typename StringType, typename Iter>
unsigned int
tokenize(const StringType& str,
const StringType& delims,
Iter it,
bool strip_whitespace=false)
{
typename StringType::size_type start_pos = 0;
typename StringType::size_type end_pos = 0;
unsigned int token_count = 0;
do {
start_pos = str.find_first_not_of(delims, start_pos);
end_pos = str.find_first_of(delims, start_pos);
if (start_pos != end_pos) {
if (end_pos == str.npos) {
end_pos = str.length();
}
if (strip_whitespace) {
StringType stripped = str.substr(start_pos, end_pos - start_pos);
strip_whitespace_edges (stripped);
if (stripped.length()) {
*it++ = stripped;
}
} else {
*it++ = str.substr(start_pos, end_pos - start_pos);
}
++token_count;
start_pos = str.find_first_not_of(delims, end_pos + 1);
}
} while (start_pos != str.npos);
if (start_pos != str.npos) {
if (strip_whitespace) {
StringType stripped = str.substr(start_pos, str.length() - start_pos);
strip_whitespace_edges (stripped);
if (stripped.length()) {
*it++ = stripped;
}
} else {
*it++ = str.substr(start_pos, str.length() - start_pos);
}
++token_count;
}
return token_count;
}
} // namespace PBD
#endif // PBD_TOKENIZER
|