blob: 4043b3928f113019d6235c6f76136a6c066338a4 (
plain)
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
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
|
/*
* Tokenizer.cpp
*
* Copyright (C) 2008 Matthias Schiffer <matthias@gamezock.de>
*
* This program is free software: you can redistribute it and/or modify it
* under the terms of the GNU Lesser General Public License as published by the
* Free Software Foundation, either version 3 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 Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public License along
* with this program. If not, see <http://www.gnu.org/licenses/>.
*/
#include "Tokenizer.h"
namespace Mad {
namespace Core {
const std::string Tokenizer::delimiters = " \t\n\"'\\";
std::vector<std::string> Tokenizer::split(const std::string &str) {
std::vector<std::string> ret;
for(size_t s = 0; s < str.length();) {
size_t index = str.find_first_of(delimiters, s);
size_t length = (index == std::string::npos) ? std::string::npos : index-s;
ret.push_back(str.substr(s, length));
if(index != std::string::npos) {
size_t index2 = str.find_first_not_of(delimiters, index);
length = (index2 == std::string::npos) ? std::string::npos : index2-index;
ret.push_back(str.substr(index, length));
if(index2 != std::string::npos)
s = index2;
else
break;
}
else
break;
}
return ret;
}
bool Tokenizer::tokenize(const std::string &str, std::vector<std::string> &out) {
std::vector<std::string> splitString = split(str);
bool singleQuotes = false, doubleQuotes = false, escape = false;
std::string token;
bool forceToken = false;
out.clear();
for(std::vector<std::string>::iterator s = splitString.begin(); s != splitString.end(); ++s) {
token += *s;
escape = false;
if(++s == splitString.end())
break;
for(std::string::iterator c = s->begin(); c != s->end(); ++c) {
if(*c == '\n' && escape) {
escape = false;
if(doubleQuotes)
continue;
}
if(escape || (singleQuotes && *c != '\'')) {
token += *c;
escape = false;
continue;
}
switch(*c) {
case ' ':
case '\t':
case '\n':
if(doubleQuotes) {
token += *c;
}
else {
if(!token.empty() || forceToken) {
out.push_back(token);
token.clear();
forceToken = false;
}
}
break;
case '"':
doubleQuotes = !doubleQuotes;
forceToken = true;
break;
case '\'':
if(doubleQuotes) {
token += *c;
}
else {
singleQuotes = !singleQuotes;
forceToken = true;
}
break;
case '\\':
escape = true;
}
}
}
if(!token.empty() || forceToken)
out.push_back(token);
return !(singleQuotes || doubleQuotes || escape);
}
}
}
|