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
72
73
74
75
76
77
78
79
80
81
82
|
#include "rl_str_proc.hh"
using namespace std;
/**
*
**/
StrProc::StrProc(const string &in_str, const string &token)
{
string tmp = in_str;
//convert tabs to spaces
uint32_t pos = 0;
string tabtospace = " ";
string::iterator iter = tmp.begin();
while ((pos = tmp.find("\t", pos)) != string::npos) {
tmp.replace(pos, 1, tabtospace);
pos += tabtospace.length();
}
//remove the cr
pos = tmp.find("\n");
if (pos != string::npos) {
tmp.replace(pos, 1, "");
}
//now handle the case of the multiple length token
//note that we are using the '~' as a token internally
uint32_t start = 0, end;
while ((start = tmp.find(token, start)) != string::npos) {
tmp.replace(start, token.length(), "~");
}
while ((start = tmp.find_first_not_of("~")) != string::npos) {
tmp = tmp.substr(start, tmp.length() - start);
end = tmp.find_first_of("~");
_str_coll.push_back(tmp.substr(0, end));
tmp = tmp.substr(end+1, tmp.length() - end-1);
if (end == string::npos) {
break;
}
}
}
/**
*
**/
string
StrProc::get(int i)
{
if (uint32_t(i) >= _str_coll.size()) {
return string("");
}
return _str_coll[i];
}
/**
*
**/
string
StrProc::get(int start, int end)
{
if (uint32_t(start) >= _str_coll.size()) {
return string("");
}
string tmp;
for (int i = start; (i < end) && (uint32_t(i) < _str_coll.size()); ++i) {
tmp += _str_coll[i] + " ";
}
return tmp.substr(0,tmp.length()-1);
}
/**
*
**/
vector<string>
StrProc::get()
{
return _str_coll;
}
|
