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
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
|
/* -*- Mode: C++; tab-width: 2; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
/***************************************************************************
* mltokenizer.cc
*
* Tue Nov 4 08:46:35 CET 2008
* Copyright 2008 Bent Bisballe Nyeng
* deva@aasimon.org
****************************************************************************/
/*
* This file is part of Pracro.
*
* Pracro 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.
*
* Pracro 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 Pracro; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
*/
#include "mltokenizer.h"
static std::string rereplaceescaping(std::string mlvalue)
{
std::string output;
size_t i = 0;
while(i < mlvalue.length()) {
if(mlvalue[i] == '\1') {
output += '{';
i++;
} else if(mlvalue[i] == '\2') {
output += '}';
i++;
} else {
output += mlvalue[i];
i++;
}
}
return output;
}
static std::string replaceescaping(std::string mlvalue)
{
std::string output;
size_t i = 0;
while(i < mlvalue.length()) {
if(i < mlvalue.length() - 1 && mlvalue[i] == '{' && mlvalue[i + 1] == '{') {
output += '\1';
i+=2;
} else if(i < mlvalue.length() - 1 && mlvalue[i] == '}' && mlvalue[i + 1] == '}') {
output += '\2';
i+=2;
} else {
output += mlvalue[i];
i++;
}
}
return output;
}
static std::string gettoken(std::string input, size_t start, std::string term)
{
std::string output;
size_t i = start;
while(i < input.length()) {
size_t j = 0;
while(j < term.length()) {
if(input[i] == term[j]) return output;
j++;
}
output += input[i];
i++;
}
return output;
}
typedef enum {
NAME,
VALUE,
TEXT,
ENDOFITEM,
UNDEFINED
} tokenizerstate_t;
std::vector< mltoken_t > mltokenize(std::string mlvalue)
{
std::vector< mltoken_t > tokens;
mlvalue = replaceescaping(mlvalue);
tokenizerstate_t state = UNDEFINED;
mltoken_t token;
size_t i = 0;
while(i < mlvalue.length()) {
switch(state) {
case NAME:
token.name = gettoken(mlvalue, i, "|");
i += token.name.length() + 1;
token.type = MLTT_VALUE;
token.value = "";
state = VALUE;
break;
case VALUE:
token.value = gettoken(mlvalue, i, "}\n");
i += token.value.length() + 1;
token.value = rereplaceescaping(token.value);
token.type = MLTT_VALUE;
tokens.push_back(token);
state = UNDEFINED;
break;
case TEXT:
if(mlvalue[i] == '$') token.value = "$";
else token.value = gettoken(mlvalue, i, "$\n");
i += token.value.length();
token.value = rereplaceescaping(token.value);
token.type = MLTT_TEXT;
token.name = "";
if(tokens.size() && tokens.back().type == MLTT_TEXT) tokens.back().value += token.value;
else tokens.push_back(token);
state = UNDEFINED;
break;
case ENDOFITEM:
token.value = "\n";
i++;
token.type = MLTT_ENDOFITEM;
token.name = "";
tokens.push_back(token);
state = UNDEFINED;
break;
case UNDEFINED:
switch(mlvalue[i]) {
case '$':
if(i < mlvalue.length() - 1 && mlvalue[i + 1] == '{') { i++; break; } // ignore
else { state = TEXT; break; }
case '{': state = NAME; i++; break;
case '\n': state = ENDOFITEM; break;
default: state = TEXT; break;
}
}
}
if(state != UNDEFINED) {
printf("Oups... missed something in the end!\n");
tokens.push_back(token);
}
return tokens;
}
#ifdef TEST_MLTOKENIZER
int main()
{
std::string mlvalue = "$ab}}c\ndef ${na$me|${{va$lue}}}\n12${34}\n";
std::vector< mltoken_t > tokens = mltokenize(mlvalue);
std::vector< mltoken_t >::iterator i = tokens.begin();
while(i != tokens.end()) {
printf("Token:\n");
printf("\tType: ");
switch(i->type) {
case MLTT_VALUE: printf("VALUE\n"); break;
case MLTT_TEXT: printf("TEXT\n"); break;
case MLTT_ENDOFITEM: printf("ENDOFITEM\n"); break;
case MLTT_UNDEFINED: printf("UNDEFINED\n"); break;
}
printf("\tName: %s\n", i->name.c_str());
printf("\tValue: %s\n", i->value.c_str());
printf("\n");
i++;
}
return 0;
}
#endif
|
