CCPUScriptLexer.cpp
9.35 KB
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
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
/****************************************************************************
Copyright (C) 2013 Henry van Merode. All rights reserved.
Copyright (c) 2015-2016 Chukong Technologies Inc.
Copyright (c) 2017-2018 Xiamen Yaji Software Co., Ltd.
http://www.cocos2d-x.org
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in
all copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
THE SOFTWARE.
****************************************************************************/
#include "CCPUScriptLexer.h"
NS_CC_BEGIN
PUScriptLexer::PUScriptLexer()
{
}
PUScriptLexer::~PUScriptLexer()
{
}
void PUScriptLexer::openLexer(const std::string &str,const std::string &source,PUScriptTokenList& tokens)
{
enum{ READY = 0, COMMENT, MULTICOMMENT, WORD, QUOTE, VAR, POSSIBLECOMMENT };
const wchar_t varopener = '$', quote = '\"', slash = '/', backslash = '\\', openbrace = '{', closebrace = '}', colon = ':', star = '*', cr = '\r', lf = '\n';
char c = 0, lastc = 0;
std::string lexeme;
unsigned int line = 1, state = READY, lastQuote = 0;
// ScriptTokenListPtr tokens(OGRE_NEW_T(ScriptTokenList, MEMCATEGORY_GENERAL)(), SPFM_DELETE_T);
//
// Iterate over the input
std::string::const_iterator i = str.begin(), end = str.end();
while(i != end)
{
lastc = c;
c = *i;
if(c == quote)
lastQuote = line;
switch(state)
{
case READY:
if(c == slash && lastc == slash)
{
// Comment start, clear out the lexeme
lexeme = "";
state = COMMENT;
}
else if(c == star && lastc == slash)
{
lexeme = "";
state = MULTICOMMENT;
}
else if(c == quote)
{
// Clear out the lexeme ready to be filled with quotes!
lexeme = c;
state = QUOTE;
}
else if(c == varopener)
{
// Set up to read in a variable
lexeme = c;
state = VAR;
}
else if(isNewline(c))
{
lexeme = c;
setToken(lexeme, line, source, &tokens);
}
else if(!isWhitespace(c))
{
lexeme = c;
if(c == slash)
state = POSSIBLECOMMENT;
else
state = WORD;
}
break;
case COMMENT:
// This newline happens to be ignored automatically
if(isNewline(c))
state = READY;
break;
case MULTICOMMENT:
if(c == slash && lastc == star)
state = READY;
break;
case POSSIBLECOMMENT:
if(c == slash && lastc == slash)
{
lexeme = "";
state = COMMENT;
break;
}
else if(c == star && lastc == slash)
{
lexeme = "";
state = MULTICOMMENT;
break;
}
else
{
state = WORD;
}
case WORD:
if(isNewline(c))
{
setToken(lexeme, line, source, &tokens);
lexeme = c;
setToken(lexeme, line, source, &tokens);
state = READY;
}
else if(isWhitespace(c))
{
setToken(lexeme, line, source, &tokens);
state = READY;
}
else if(c == openbrace || c == closebrace || c == colon)
{
setToken(lexeme, line, source, &tokens);
lexeme = c;
setToken(lexeme, line, source, &tokens);
state = READY;
}
else
{
lexeme += c;
}
break;
case QUOTE:
if(c != backslash)
{
// Allow embedded quotes with escaping
if(c == quote && lastc == backslash)
{
lexeme += c;
}
else if(c == quote)
{
lexeme += c;
setToken(lexeme, line, source, &tokens);
state = READY;
}
else
{
// Backtrack here and allow a backslash normally within the quote
if(lastc == backslash)
lexeme = lexeme + "\\" + c;
else
lexeme += c;
}
}
break;
case VAR:
if(isNewline(c))
{
setToken(lexeme, line, source, &tokens);
lexeme = c;
setToken(lexeme, line, source, &tokens);
state = READY;
}
else if(isWhitespace(c))
{
setToken(lexeme, line, source, &tokens);
state = READY;
}
else if(c == openbrace || c == closebrace || c == colon)
{
setToken(lexeme, line, source, &tokens);
lexeme = c;
setToken(lexeme, line, source, &tokens);
state = READY;
}
else
{
lexeme += c;
}
break;
}
// Separate check for newlines just to track line numbers
if(c == cr || (c == lf && lastc != cr))
line++;
++i;
}
// Check for valid exit states
if(state == WORD || state == VAR)
{
if(!lexeme.empty())
setToken(lexeme, line, source, &tokens);
}
else
{
if(state == QUOTE)
{
printf("Exception\n");
// OGRE_EXCEPT(Exception::ERR_INVALID_STATE,
// Ogre::String("no matching \" found for \" at line ") +
// Ogre::StringConverter::toString(lastQuote),
// "ScriptLexer::tokenize");
}
}
}
void PUScriptLexer::setToken(const std::string &lexeme, int line, const std::string &source, PUScriptTokenList *tokens)
{
const char openBracket = '{', closeBracket = '}', colon = ':',
quote = '\"', var = '$';
PUScriptToken* token = new (std::nothrow) PUScriptToken;
token->lexeme = lexeme;
token->line = line;
token->file = source;
bool ignore = false;
// Check the user token map first
if(lexeme.size() == 1 && isNewline(lexeme[0]))
{
token->type = TID_NEWLINE;
if(!tokens->empty() && tokens->back()->type == TID_NEWLINE){
ignore = true;
delete token;
}
}
else if(lexeme.size() == 1 && lexeme[0] == openBracket)
token->type = TID_LBRACKET;
else if(lexeme.size() == 1 && lexeme[0] == closeBracket)
token->type = TID_RBRACKET;
else if(lexeme.size() == 1 && lexeme[0] == colon)
token->type = TID_COLON;
else if(lexeme[0] == var)
token->type = TID_VARIABLE;
else
{
// This is either a non-zero length phrase or quoted phrase
if(lexeme.size() >= 2 && lexeme[0] == quote && lexeme[lexeme.size() - 1] == quote)
{
token->type = TID_QUOTE;
}
else
{
token->type = TID_WORD;
}
}
if(!ignore)
tokens->push_back(token);
}
bool PUScriptLexer::isWhitespace(char c) const
{
return c == ' ' || c == '\r' || c == '\t';
}
bool PUScriptLexer::isNewline(char c) const
{
return c == '\n' || c == '\r';
}
NS_CC_END