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
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
|
// This file is part of PUMA.
// Copyright (C) 1999-2003 The PUMA developer team.
//
// This program is free software; you can redistribute it and/or
// modify it under the terms of the GNU General Public License as
// published by the Free Software Foundation; either version 2 of
// the License, or (at your option) any later version.
//
// This program is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
// GNU General Public License for more details.
//
// You should have received a copy of the GNU General Public
// License along with this program; if not, write to the Free
// Software Foundation, Inc., 59 Temple Place, Suite 330, Boston,
// MA 02111-1307 USA
#include "Puma/SimpleParser.h"
namespace Puma {
string SimpleParser::strip (const string &str) {
if (str[0] == '"' && str[str.length () - 1] == '"')
return str.substr (1, str.length () - 2);
return str;
}
string::size_type SimpleParser::findBeginOfNextToken (const string& line, const string& delimiters, string::size_type pos) {
bool escaped = false;
string::size_type lastPos = string::npos;
if (pos != string::npos) {
for (string::size_type i = pos; i < line.length() && lastPos == string::npos; i++) {
char c = line[i];
if (delimiters.find(c) == string::npos) {
lastPos = escaped ? i-1 : i;
}
if (c == '\\') {
escaped = ! escaped;
} else {
escaped = false;
}
}
}
return lastPos;
}
string::size_type SimpleParser::findEndOfNextToken (const string& line, const string& delimiters, string::size_type lastPos) {
bool in_string = false, escaped = false;
string::size_type endpos = line.length();
if (lastPos != string::npos) {
for (string::size_type i = lastPos; i < line.length(); i++) {
char c = line[i];
if (! in_string && delimiters.find(c) != string::npos) {
endpos = i;
break;
}
if (! escaped && c == '"') {
in_string = ! in_string;
}
if (c == '\\') {
escaped = ! escaped;
} else {
escaped = false;
}
}
}
return endpos;
}
string::size_type SimpleParser::next (const string& line, const string& delimiters, string::size_type pos, string::size_type& lastPos) {
// find begin of next token
lastPos = findBeginOfNextToken(line, delimiters, pos);
// find end of the token
return findEndOfNextToken(line, delimiters, lastPos);
}
int SimpleParser::tokenize (const std::string& line, std::vector<std::string>& words, const std::string& delimiters) {
int res = 0;
string::size_type pos = 0, lastPos = 0;
// get first token position
pos = next (line, delimiters, 0, lastPos);
// while not at the end of the line
while (pos != string::npos && lastPos != string::npos) {
// get current token
string token = line.substr (lastPos, pos-lastPos);
// add current token to vector
words.push_back (token);
res++;
// get next token position
pos = next (line, delimiters, pos, lastPos);
}
return res;
}
} // namespace Puma
|