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
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
|
/* ScummVM - Graphic Adventure Engine
*
* ScummVM is the legal property of its developers, whose names
* are too numerous to list here. Please refer to the COPYRIGHT
* file distributed with this source distribution.
*
* 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 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 General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*
*/
#include "common/tokenizer.h"
namespace Common {
StringTokenizer::StringTokenizer(const String &str, const String &delimiters) : _str(str), _delimiters(delimiters) {
reset();
}
void StringTokenizer::reset() {
_tokenBegin = _tokenEnd = 0;
}
bool StringTokenizer::empty() const {
// Search for the next token's start (i.e. the next non-delimiter character)
for (uint i = _tokenEnd; i < _str.size(); i++) {
if (!_delimiters.contains(_str[i]))
return false; // Found a token so the tokenizer is not empty
}
// Didn't find any more tokens so the tokenizer is empty
return true;
}
String StringTokenizer::nextToken() {
// Seek to next token's start (i.e. jump over the delimiters before next token)
for (_tokenBegin = _tokenEnd; _tokenBegin < _str.size() && _delimiters.contains(_str[_tokenBegin]); _tokenBegin++)
;
// Seek to the token's end (i.e. jump over the non-delimiters)
for (_tokenEnd = _tokenBegin; _tokenEnd < _str.size() && !_delimiters.contains(_str[_tokenEnd]); _tokenEnd++)
;
// Return the found token
return String(_str.c_str() + _tokenBegin, _tokenEnd - _tokenBegin);
}
StringArray StringTokenizer::split() {
StringArray res;
while (!empty())
res.push_back(nextToken());
return res;
}
String StringTokenizer::delimitersAtTokenBegin() const {
// First token appears at beginning of the string, or no tokens have been extracted yet
if (_tokenBegin == 0)
return String();
// Iterate backwards until we hit either the previous token, or the beginning of the input string
int delimitersBegin;
for (delimitersBegin = _tokenBegin - 1; delimitersBegin >= 0 && _delimiters.contains(_str[delimitersBegin]); delimitersBegin--)
;
++delimitersBegin;
// Return the delimiters
return String(_str.c_str() + delimitersBegin, _tokenBegin - delimitersBegin);
}
String StringTokenizer::delimitersAtTokenEnd() const {
// Last token appears at end of the string, or no tokens have been extracted yet
if (_tokenEnd == 0 || _tokenEnd == _str.size())
return String();
// Iterate forwards until we hit either the next token, or the end of the input string
uint delimitersEnd;
for (delimitersEnd = _tokenEnd; delimitersEnd < _str.size() && _delimiters.contains(_str[delimitersEnd]); delimitersEnd++)
;
// Return the delimiters
return String(_str.c_str() + _tokenEnd, delimitersEnd - _tokenEnd);
}
U32StringTokenizer::U32StringTokenizer(const U32String &str, const String &delimiters) : _str(str), _delimiters(delimiters) {
reset();
}
void U32StringTokenizer::reset() {
_tokenBegin = _tokenEnd = _str.begin();
}
bool U32StringTokenizer::empty() const {
// Search for the next token's start (i.e. the next non-delimiter character)
for (U32String::const_iterator itr = _tokenEnd; itr != _str.end(); itr++) {
if (!_delimiters.contains(*itr)) {
return false; // Found a token so the tokenizer is not empty
}
}
// Didn't find any more tokens so the tokenizer is empty
return true;
}
U32String U32StringTokenizer::nextToken() {
// Skip delimiters when present at the beginning, to point to the next token
// For example, the below loop will set _tokenBegin & _tokenEnd to 'H' for the string -> "!!--=Hello World"
// And subsequently, skip all delimiters in the beginning of the next word.
_tokenBegin = _tokenEnd;
while (_tokenBegin != _str.end() && _delimiters.contains(*_tokenBegin))
_tokenBegin++;
_tokenEnd = _tokenBegin;
// Loop and advance _tokenEnd until we find a delimiter at the end of a word/string
while (_tokenBegin != _str.end() && _tokenEnd != _str.end()) {
if (_delimiters.contains(*_tokenEnd)) {
return U32String(_tokenBegin, _tokenEnd);
}
_tokenEnd++;
}
// Returning the last word if _tokenBegin iterator isn't at the end.
if (_tokenBegin != _str.end())
return U32String(_tokenBegin, _tokenEnd);
else
return U32String();
}
U32StringArray U32StringTokenizer::split() {
U32StringArray res;
while (!empty())
res.push_back(nextToken());
return res;
}
U32String U32StringTokenizer::delimitersAtTokenBegin() const {
// First token appears at beginning of the string, or no tokens have been extracted yet
if (_tokenBegin == _str.begin())
return U32String();
// Iterate backwards until we hit either the previous token, or the beginning of the input string
U32String::const_iterator delimitersBegin;
for (delimitersBegin = _tokenBegin - 1; delimitersBegin >= _str.begin() && _delimiters.contains(*delimitersBegin); delimitersBegin--)
;
++delimitersBegin;
// Return the delimiters
return U32String(delimitersBegin, _tokenBegin - delimitersBegin);
}
U32String U32StringTokenizer::delimitersAtTokenEnd() const {
// Last token appears at end of the string, or no tokens have been extracted yet
if (_tokenEnd == _str.begin() || _tokenEnd == _str.end())
return String();
// Iterate forwards until we hit either the next token, or the end of the input string
U32String::const_iterator delimitersEnd;
for (delimitersEnd = _tokenEnd; delimitersEnd < _str.end() && _delimiters.contains(*delimitersEnd); delimitersEnd++)
;
// Return the delimiters
return U32String(_tokenEnd, delimitersEnd - _tokenEnd);
}
} // End of namespace Common
|
