|
0
|
1 |
/****************************************************************************
|
|
|
2 |
**
|
|
|
3 |
** Copyright (C) 2009 Nokia Corporation and/or its subsidiary(-ies).
|
|
|
4 |
** All rights reserved.
|
|
|
5 |
** Contact: Nokia Corporation (qt-info@nokia.com)
|
|
|
6 |
**
|
|
|
7 |
** This file is part of the QtScript module of the Qt Toolkit.
|
|
|
8 |
**
|
|
|
9 |
** $QT_BEGIN_LICENSE:LGPL$
|
|
|
10 |
** No Commercial Usage
|
|
|
11 |
** This file contains pre-release code and may not be distributed.
|
|
|
12 |
** You may use this file in accordance with the terms and conditions
|
|
|
13 |
** contained in the Technology Preview License Agreement accompanying
|
|
|
14 |
** this package.
|
|
|
15 |
**
|
|
|
16 |
** GNU Lesser General Public License Usage
|
|
|
17 |
** Alternatively, this file may be used under the terms of the GNU Lesser
|
|
|
18 |
** General Public License version 2.1 as published by the Free Software
|
|
|
19 |
** Foundation and appearing in the file LICENSE.LGPL included in the
|
|
|
20 |
** packaging of this file. Please review the following information to
|
|
|
21 |
** ensure the GNU Lesser General Public License version 2.1 requirements
|
|
|
22 |
** will be met: http://www.gnu.org/licenses/old-licenses/lgpl-2.1.html.
|
|
|
23 |
**
|
|
|
24 |
** In addition, as a special exception, Nokia gives you certain additional
|
|
|
25 |
** rights. These rights are described in the Nokia Qt LGPL Exception
|
|
|
26 |
** version 1.1, included in the file LGPL_EXCEPTION.txt in this package.
|
|
|
27 |
**
|
|
|
28 |
** If you have questions regarding the use of this file, please contact
|
|
|
29 |
** Nokia at qt-info@nokia.com.
|
|
|
30 |
**
|
|
|
31 |
**
|
|
|
32 |
**
|
|
|
33 |
**
|
|
|
34 |
**
|
|
|
35 |
**
|
|
|
36 |
**
|
|
|
37 |
**
|
|
|
38 |
** $QT_END_LICENSE$
|
|
|
39 |
**
|
|
|
40 |
****************************************************************************/
|
|
|
41 |
|
|
|
42 |
#include "qscriptlexer_p.h"
|
|
|
43 |
|
|
|
44 |
#include "qscriptgrammar_p.h"
|
|
|
45 |
#include <ctype.h>
|
|
|
46 |
#include <stdlib.h>
|
|
|
47 |
#include <stdio.h>
|
|
|
48 |
#include <string.h>
|
|
|
49 |
|
|
|
50 |
QT_BEGIN_NAMESPACE
|
|
|
51 |
|
|
|
52 |
extern double qstrtod(const char *s00, char const **se, bool *ok);
|
|
|
53 |
|
|
|
54 |
#define shiftWindowsLineBreak() \
|
|
|
55 |
do { \
|
|
|
56 |
if (((current == '\r') && (next1 == '\n')) \
|
|
|
57 |
|| ((current == '\n') && (next1 == '\r'))) { \
|
|
|
58 |
shift(1); \
|
|
|
59 |
} \
|
|
|
60 |
} \
|
|
|
61 |
while (0)
|
|
|
62 |
|
|
|
63 |
typedef double qsreal; // ###
|
|
|
64 |
|
|
|
65 |
namespace QScript {
|
|
|
66 |
extern qsreal integerFromString(const char *buf, int size, int radix);
|
|
|
67 |
}
|
|
|
68 |
|
|
|
69 |
QScript::Lexer::Lexer(QScriptEnginePrivate *eng)
|
|
|
70 |
: driver(eng),
|
|
|
71 |
yylineno(0),
|
|
|
72 |
size8(128), size16(128), restrKeyword(false),
|
|
|
73 |
stackToken(-1), pos(0),
|
|
|
74 |
code(0), length(0),
|
|
|
75 |
bol(true),
|
|
|
76 |
current(0), next1(0), next2(0), next3(0),
|
|
|
77 |
err(NoError),
|
|
|
78 |
check_reserved(true),
|
|
|
79 |
parenthesesState(IgnoreParentheses),
|
|
|
80 |
prohibitAutomaticSemicolon(false)
|
|
|
81 |
{
|
|
|
82 |
// allocate space for read buffers
|
|
|
83 |
buffer8 = new char[size8];
|
|
|
84 |
buffer16 = new QChar[size16];
|
|
|
85 |
pattern = 0;
|
|
|
86 |
flags = 0;
|
|
|
87 |
|
|
|
88 |
}
|
|
|
89 |
|
|
|
90 |
QScript::Lexer::~Lexer()
|
|
|
91 |
{
|
|
|
92 |
delete [] buffer8;
|
|
|
93 |
delete [] buffer16;
|
|
|
94 |
}
|
|
|
95 |
|
|
|
96 |
void QScript::Lexer::setCode(const QString &c, int lineno)
|
|
|
97 |
{
|
|
|
98 |
errmsg = QString();
|
|
|
99 |
yylineno = lineno;
|
|
|
100 |
yycolumn = 1;
|
|
|
101 |
restrKeyword = false;
|
|
|
102 |
delimited = false;
|
|
|
103 |
stackToken = -1;
|
|
|
104 |
pos = 0;
|
|
|
105 |
code = c.unicode();
|
|
|
106 |
length = c.length();
|
|
|
107 |
bol = true;
|
|
|
108 |
|
|
|
109 |
// read first characters
|
|
|
110 |
current = (length > 0) ? code[0].unicode() : 0;
|
|
|
111 |
next1 = (length > 1) ? code[1].unicode() : 0;
|
|
|
112 |
next2 = (length > 2) ? code[2].unicode() : 0;
|
|
|
113 |
next3 = (length > 3) ? code[3].unicode() : 0;
|
|
|
114 |
}
|
|
|
115 |
|
|
|
116 |
void QScript::Lexer::shift(uint p)
|
|
|
117 |
{
|
|
|
118 |
while (p--) {
|
|
|
119 |
++pos;
|
|
|
120 |
++yycolumn;
|
|
|
121 |
current = next1;
|
|
|
122 |
next1 = next2;
|
|
|
123 |
next2 = next3;
|
|
|
124 |
next3 = (pos + 3 < length) ? code[pos+3].unicode() : 0;
|
|
|
125 |
}
|
|
|
126 |
}
|
|
|
127 |
|
|
|
128 |
void QScript::Lexer::setDone(State s)
|
|
|
129 |
{
|
|
|
130 |
state = s;
|
|
|
131 |
done = true;
|
|
|
132 |
}
|
|
|
133 |
|
|
|
134 |
int QScript::Lexer::findReservedWord(const QChar *c, int size) const
|
|
|
135 |
{
|
|
|
136 |
switch (size) {
|
|
|
137 |
case 2: {
|
|
|
138 |
if (c[0] == QLatin1Char('d') && c[1] == QLatin1Char('o'))
|
|
|
139 |
return QScriptGrammar::T_DO;
|
|
|
140 |
else if (c[0] == QLatin1Char('i') && c[1] == QLatin1Char('f'))
|
|
|
141 |
return QScriptGrammar::T_IF;
|
|
|
142 |
else if (c[0] == QLatin1Char('i') && c[1] == QLatin1Char('n'))
|
|
|
143 |
return QScriptGrammar::T_IN;
|
|
|
144 |
} break;
|
|
|
145 |
|
|
|
146 |
case 3: {
|
|
|
147 |
if (c[0] == QLatin1Char('f') && c[1] == QLatin1Char('o') && c[2] == QLatin1Char('r'))
|
|
|
148 |
return QScriptGrammar::T_FOR;
|
|
|
149 |
else if (c[0] == QLatin1Char('n') && c[1] == QLatin1Char('e') && c[2] == QLatin1Char('w'))
|
|
|
150 |
return QScriptGrammar::T_NEW;
|
|
|
151 |
else if (c[0] == QLatin1Char('t') && c[1] == QLatin1Char('r') && c[2] == QLatin1Char('y'))
|
|
|
152 |
return QScriptGrammar::T_TRY;
|
|
|
153 |
else if (c[0] == QLatin1Char('v') && c[1] == QLatin1Char('a') && c[2] == QLatin1Char('r'))
|
|
|
154 |
return QScriptGrammar::T_VAR;
|
|
|
155 |
else if (check_reserved) {
|
|
|
156 |
if (c[0] == QLatin1Char('i') && c[1] == QLatin1Char('n') && c[2] == QLatin1Char('t'))
|
|
|
157 |
return QScriptGrammar::T_RESERVED_WORD;
|
|
|
158 |
}
|
|
|
159 |
} break;
|
|
|
160 |
|
|
|
161 |
case 4: {
|
|
|
162 |
if (c[0] == QLatin1Char('c') && c[1] == QLatin1Char('a')
|
|
|
163 |
&& c[2] == QLatin1Char('s') && c[3] == QLatin1Char('e'))
|
|
|
164 |
return QScriptGrammar::T_CASE;
|
|
|
165 |
else if (c[0] == QLatin1Char('e') && c[1] == QLatin1Char('l')
|
|
|
166 |
&& c[2] == QLatin1Char('s') && c[3] == QLatin1Char('e'))
|
|
|
167 |
return QScriptGrammar::T_ELSE;
|
|
|
168 |
else if (c[0] == QLatin1Char('t') && c[1] == QLatin1Char('h')
|
|
|
169 |
&& c[2] == QLatin1Char('i') && c[3] == QLatin1Char('s'))
|
|
|
170 |
return QScriptGrammar::T_THIS;
|
|
|
171 |
else if (c[0] == QLatin1Char('v') && c[1] == QLatin1Char('o')
|
|
|
172 |
&& c[2] == QLatin1Char('i') && c[3] == QLatin1Char('d'))
|
|
|
173 |
return QScriptGrammar::T_VOID;
|
|
|
174 |
else if (c[0] == QLatin1Char('w') && c[1] == QLatin1Char('i')
|
|
|
175 |
&& c[2] == QLatin1Char('t') && c[3] == QLatin1Char('h'))
|
|
|
176 |
return QScriptGrammar::T_WITH;
|
|
|
177 |
else if (c[0] == QLatin1Char('t') && c[1] == QLatin1Char('r')
|
|
|
178 |
&& c[2] == QLatin1Char('u') && c[3] == QLatin1Char('e'))
|
|
|
179 |
return QScriptGrammar::T_TRUE;
|
|
|
180 |
else if (c[0] == QLatin1Char('n') && c[1] == QLatin1Char('u')
|
|
|
181 |
&& c[2] == QLatin1Char('l') && c[3] == QLatin1Char('l'))
|
|
|
182 |
return QScriptGrammar::T_NULL;
|
|
|
183 |
else if (check_reserved) {
|
|
|
184 |
if (c[0] == QLatin1Char('e') && c[1] == QLatin1Char('n')
|
|
|
185 |
&& c[2] == QLatin1Char('u') && c[3] == QLatin1Char('m'))
|
|
|
186 |
return QScriptGrammar::T_RESERVED_WORD;
|
|
|
187 |
else if (c[0] == QLatin1Char('b') && c[1] == QLatin1Char('y')
|
|
|
188 |
&& c[2] == QLatin1Char('t') && c[3] == QLatin1Char('e'))
|
|
|
189 |
return QScriptGrammar::T_RESERVED_WORD;
|
|
|
190 |
else if (c[0] == QLatin1Char('l') && c[1] == QLatin1Char('o')
|
|
|
191 |
&& c[2] == QLatin1Char('n') && c[3] == QLatin1Char('g'))
|
|
|
192 |
return QScriptGrammar::T_RESERVED_WORD;
|
|
|
193 |
else if (c[0] == QLatin1Char('c') && c[1] == QLatin1Char('h')
|
|
|
194 |
&& c[2] == QLatin1Char('a') && c[3] == QLatin1Char('r'))
|
|
|
195 |
return QScriptGrammar::T_RESERVED_WORD;
|
|
|
196 |
else if (c[0] == QLatin1Char('g') && c[1] == QLatin1Char('o')
|
|
|
197 |
&& c[2] == QLatin1Char('t') && c[3] == QLatin1Char('o'))
|
|
|
198 |
return QScriptGrammar::T_RESERVED_WORD;
|
|
|
199 |
}
|
|
|
200 |
} break;
|
|
|
201 |
|
|
|
202 |
case 5: {
|
|
|
203 |
if (c[0] == QLatin1Char('b') && c[1] == QLatin1Char('r')
|
|
|
204 |
&& c[2] == QLatin1Char('e') && c[3] == QLatin1Char('a')
|
|
|
205 |
&& c[4] == QLatin1Char('k'))
|
|
|
206 |
return QScriptGrammar::T_BREAK;
|
|
|
207 |
else if (c[0] == QLatin1Char('c') && c[1] == QLatin1Char('a')
|
|
|
208 |
&& c[2] == QLatin1Char('t') && c[3] == QLatin1Char('c')
|
|
|
209 |
&& c[4] == QLatin1Char('h'))
|
|
|
210 |
return QScriptGrammar::T_CATCH;
|
|
|
211 |
else if (c[0] == QLatin1Char('t') && c[1] == QLatin1Char('h')
|
|
|
212 |
&& c[2] == QLatin1Char('r') && c[3] == QLatin1Char('o')
|
|
|
213 |
&& c[4] == QLatin1Char('w'))
|
|
|
214 |
return QScriptGrammar::T_THROW;
|
|
|
215 |
else if (c[0] == QLatin1Char('w') && c[1] == QLatin1Char('h')
|
|
|
216 |
&& c[2] == QLatin1Char('i') && c[3] == QLatin1Char('l')
|
|
|
217 |
&& c[4] == QLatin1Char('e'))
|
|
|
218 |
return QScriptGrammar::T_WHILE;
|
|
|
219 |
else if (c[0] == QLatin1Char('c') && c[1] == QLatin1Char('o')
|
|
|
220 |
&& c[2] == QLatin1Char('n') && c[3] == QLatin1Char('s')
|
|
|
221 |
&& c[4] == QLatin1Char('t'))
|
|
|
222 |
return QScriptGrammar::T_CONST;
|
|
|
223 |
else if (c[0] == QLatin1Char('f') && c[1] == QLatin1Char('a')
|
|
|
224 |
&& c[2] == QLatin1Char('l') && c[3] == QLatin1Char('s')
|
|
|
225 |
&& c[4] == QLatin1Char('e'))
|
|
|
226 |
return QScriptGrammar::T_FALSE;
|
|
|
227 |
else if (check_reserved) {
|
|
|
228 |
if (c[0] == QLatin1Char('s') && c[1] == QLatin1Char('h')
|
|
|
229 |
&& c[2] == QLatin1Char('o') && c[3] == QLatin1Char('r')
|
|
|
230 |
&& c[4] == QLatin1Char('t'))
|
|
|
231 |
return QScriptGrammar::T_RESERVED_WORD;
|
|
|
232 |
else if (c[0] == QLatin1Char('s') && c[1] == QLatin1Char('u')
|
|
|
233 |
&& c[2] == QLatin1Char('p') && c[3] == QLatin1Char('e')
|
|
|
234 |
&& c[4] == QLatin1Char('r'))
|
|
|
235 |
return QScriptGrammar::T_RESERVED_WORD;
|
|
|
236 |
else if (c[0] == QLatin1Char('f') && c[1] == QLatin1Char('i')
|
|
|
237 |
&& c[2] == QLatin1Char('n') && c[3] == QLatin1Char('a')
|
|
|
238 |
&& c[4] == QLatin1Char('l'))
|
|
|
239 |
return QScriptGrammar::T_RESERVED_WORD;
|
|
|
240 |
else if (c[0] == QLatin1Char('c') && c[1] == QLatin1Char('l')
|
|
|
241 |
&& c[2] == QLatin1Char('a') && c[3] == QLatin1Char('s')
|
|
|
242 |
&& c[4] == QLatin1Char('s'))
|
|
|
243 |
return QScriptGrammar::T_RESERVED_WORD;
|
|
|
244 |
else if (c[0] == QLatin1Char('f') && c[1] == QLatin1Char('l')
|
|
|
245 |
&& c[2] == QLatin1Char('o') && c[3] == QLatin1Char('a')
|
|
|
246 |
&& c[4] == QLatin1Char('t'))
|
|
|
247 |
return QScriptGrammar::T_RESERVED_WORD;
|
|
|
248 |
}
|
|
|
249 |
} break;
|
|
|
250 |
|
|
|
251 |
case 6: {
|
|
|
252 |
if (c[0] == QLatin1Char('d') && c[1] == QLatin1Char('e')
|
|
|
253 |
&& c[2] == QLatin1Char('l') && c[3] == QLatin1Char('e')
|
|
|
254 |
&& c[4] == QLatin1Char('t') && c[5] == QLatin1Char('e'))
|
|
|
255 |
return QScriptGrammar::T_DELETE;
|
|
|
256 |
else if (c[0] == QLatin1Char('r') && c[1] == QLatin1Char('e')
|
|
|
257 |
&& c[2] == QLatin1Char('t') && c[3] == QLatin1Char('u')
|
|
|
258 |
&& c[4] == QLatin1Char('r') && c[5] == QLatin1Char('n'))
|
|
|
259 |
return QScriptGrammar::T_RETURN;
|
|
|
260 |
else if (c[0] == QLatin1Char('s') && c[1] == QLatin1Char('w')
|
|
|
261 |
&& c[2] == QLatin1Char('i') && c[3] == QLatin1Char('t')
|
|
|
262 |
&& c[4] == QLatin1Char('c') && c[5] == QLatin1Char('h'))
|
|
|
263 |
return QScriptGrammar::T_SWITCH;
|
|
|
264 |
else if (c[0] == QLatin1Char('t') && c[1] == QLatin1Char('y')
|
|
|
265 |
&& c[2] == QLatin1Char('p') && c[3] == QLatin1Char('e')
|
|
|
266 |
&& c[4] == QLatin1Char('o') && c[5] == QLatin1Char('f'))
|
|
|
267 |
return QScriptGrammar::T_TYPEOF;
|
|
|
268 |
else if (check_reserved) {
|
|
|
269 |
if (c[0] == QLatin1Char('e') && c[1] == QLatin1Char('x')
|
|
|
270 |
&& c[2] == QLatin1Char('p') && c[3] == QLatin1Char('o')
|
|
|
271 |
&& c[4] == QLatin1Char('r') && c[5] == QLatin1Char('t'))
|
|
|
272 |
return QScriptGrammar::T_RESERVED_WORD;
|
|
|
273 |
else if (c[0] == QLatin1Char('s') && c[1] == QLatin1Char('t')
|
|
|
274 |
&& c[2] == QLatin1Char('a') && c[3] == QLatin1Char('t')
|
|
|
275 |
&& c[4] == QLatin1Char('i') && c[5] == QLatin1Char('c'))
|
|
|
276 |
return QScriptGrammar::T_RESERVED_WORD;
|
|
|
277 |
else if (c[0] == QLatin1Char('d') && c[1] == QLatin1Char('o')
|
|
|
278 |
&& c[2] == QLatin1Char('u') && c[3] == QLatin1Char('b')
|
|
|
279 |
&& c[4] == QLatin1Char('l') && c[5] == QLatin1Char('e'))
|
|
|
280 |
return QScriptGrammar::T_RESERVED_WORD;
|
|
|
281 |
else if (c[0] == QLatin1Char('i') && c[1] == QLatin1Char('m')
|
|
|
282 |
&& c[2] == QLatin1Char('p') && c[3] == QLatin1Char('o')
|
|
|
283 |
&& c[4] == QLatin1Char('r') && c[5] == QLatin1Char('t'))
|
|
|
284 |
return QScriptGrammar::T_RESERVED_WORD;
|
|
|
285 |
else if (c[0] == QLatin1Char('p') && c[1] == QLatin1Char('u')
|
|
|
286 |
&& c[2] == QLatin1Char('b') && c[3] == QLatin1Char('l')
|
|
|
287 |
&& c[4] == QLatin1Char('i') && c[5] == QLatin1Char('c'))
|
|
|
288 |
return QScriptGrammar::T_RESERVED_WORD;
|
|
|
289 |
else if (c[0] == QLatin1Char('n') && c[1] == QLatin1Char('a')
|
|
|
290 |
&& c[2] == QLatin1Char('t') && c[3] == QLatin1Char('i')
|
|
|
291 |
&& c[4] == QLatin1Char('v') && c[5] == QLatin1Char('e'))
|
|
|
292 |
return QScriptGrammar::T_RESERVED_WORD;
|
|
|
293 |
else if (c[0] == QLatin1Char('t') && c[1] == QLatin1Char('h')
|
|
|
294 |
&& c[2] == QLatin1Char('r') && c[3] == QLatin1Char('o')
|
|
|
295 |
&& c[4] == QLatin1Char('w') && c[5] == QLatin1Char('s'))
|
|
|
296 |
return QScriptGrammar::T_RESERVED_WORD;
|
|
|
297 |
}
|
|
|
298 |
} break;
|
|
|
299 |
|
|
|
300 |
case 7: {
|
|
|
301 |
if (c[0] == QLatin1Char('d') && c[1] == QLatin1Char('e')
|
|
|
302 |
&& c[2] == QLatin1Char('f') && c[3] == QLatin1Char('a')
|
|
|
303 |
&& c[4] == QLatin1Char('u') && c[5] == QLatin1Char('l')
|
|
|
304 |
&& c[6] == QLatin1Char('t'))
|
|
|
305 |
return QScriptGrammar::T_DEFAULT;
|
|
|
306 |
else if (c[0] == QLatin1Char('f') && c[1] == QLatin1Char('i')
|
|
|
307 |
&& c[2] == QLatin1Char('n') && c[3] == QLatin1Char('a')
|
|
|
308 |
&& c[4] == QLatin1Char('l') && c[5] == QLatin1Char('l')
|
|
|
309 |
&& c[6] == QLatin1Char('y'))
|
|
|
310 |
return QScriptGrammar::T_FINALLY;
|
|
|
311 |
else if (check_reserved) {
|
|
|
312 |
if (c[0] == QLatin1Char('b') && c[1] == QLatin1Char('o')
|
|
|
313 |
&& c[2] == QLatin1Char('o') && c[3] == QLatin1Char('l')
|
|
|
314 |
&& c[4] == QLatin1Char('e') && c[5] == QLatin1Char('a')
|
|
|
315 |
&& c[6] == QLatin1Char('n'))
|
|
|
316 |
return QScriptGrammar::T_RESERVED_WORD;
|
|
|
317 |
else if (c[0] == QLatin1Char('e') && c[1] == QLatin1Char('x')
|
|
|
318 |
&& c[2] == QLatin1Char('t') && c[3] == QLatin1Char('e')
|
|
|
319 |
&& c[4] == QLatin1Char('n') && c[5] == QLatin1Char('d')
|
|
|
320 |
&& c[6] == QLatin1Char('s'))
|
|
|
321 |
return QScriptGrammar::T_RESERVED_WORD;
|
|
|
322 |
else if (c[0] == QLatin1Char('p') && c[1] == QLatin1Char('a')
|
|
|
323 |
&& c[2] == QLatin1Char('c') && c[3] == QLatin1Char('k')
|
|
|
324 |
&& c[4] == QLatin1Char('a') && c[5] == QLatin1Char('g')
|
|
|
325 |
&& c[6] == QLatin1Char('e'))
|
|
|
326 |
return QScriptGrammar::T_RESERVED_WORD;
|
|
|
327 |
else if (c[0] == QLatin1Char('p') && c[1] == QLatin1Char('r')
|
|
|
328 |
&& c[2] == QLatin1Char('i') && c[3] == QLatin1Char('v')
|
|
|
329 |
&& c[4] == QLatin1Char('a') && c[5] == QLatin1Char('t')
|
|
|
330 |
&& c[6] == QLatin1Char('e'))
|
|
|
331 |
return QScriptGrammar::T_RESERVED_WORD;
|
|
|
332 |
}
|
|
|
333 |
} break;
|
|
|
334 |
|
|
|
335 |
case 8: {
|
|
|
336 |
if (c[0] == QLatin1Char('c') && c[1] == QLatin1Char('o')
|
|
|
337 |
&& c[2] == QLatin1Char('n') && c[3] == QLatin1Char('t')
|
|
|
338 |
&& c[4] == QLatin1Char('i') && c[5] == QLatin1Char('n')
|
|
|
339 |
&& c[6] == QLatin1Char('u') && c[7] == QLatin1Char('e'))
|
|
|
340 |
return QScriptGrammar::T_CONTINUE;
|
|
|
341 |
else if (c[0] == QLatin1Char('f') && c[1] == QLatin1Char('u')
|
|
|
342 |
&& c[2] == QLatin1Char('n') && c[3] == QLatin1Char('c')
|
|
|
343 |
&& c[4] == QLatin1Char('t') && c[5] == QLatin1Char('i')
|
|
|
344 |
&& c[6] == QLatin1Char('o') && c[7] == QLatin1Char('n'))
|
|
|
345 |
return QScriptGrammar::T_FUNCTION;
|
|
|
346 |
else if (c[0] == QLatin1Char('d') && c[1] == QLatin1Char('e')
|
|
|
347 |
&& c[2] == QLatin1Char('b') && c[3] == QLatin1Char('u')
|
|
|
348 |
&& c[4] == QLatin1Char('g') && c[5] == QLatin1Char('g')
|
|
|
349 |
&& c[6] == QLatin1Char('e') && c[7] == QLatin1Char('r'))
|
|
|
350 |
return QScriptGrammar::T_DEBUGGER;
|
|
|
351 |
else if (check_reserved) {
|
|
|
352 |
if (c[0] == QLatin1Char('a') && c[1] == QLatin1Char('b')
|
|
|
353 |
&& c[2] == QLatin1Char('s') && c[3] == QLatin1Char('t')
|
|
|
354 |
&& c[4] == QLatin1Char('r') && c[5] == QLatin1Char('a')
|
|
|
355 |
&& c[6] == QLatin1Char('c') && c[7] == QLatin1Char('t'))
|
|
|
356 |
return QScriptGrammar::T_RESERVED_WORD;
|
|
|
357 |
else if (c[0] == QLatin1Char('v') && c[1] == QLatin1Char('o')
|
|
|
358 |
&& c[2] == QLatin1Char('l') && c[3] == QLatin1Char('a')
|
|
|
359 |
&& c[4] == QLatin1Char('t') && c[5] == QLatin1Char('i')
|
|
|
360 |
&& c[6] == QLatin1Char('l') && c[7] == QLatin1Char('e'))
|
|
|
361 |
return QScriptGrammar::T_RESERVED_WORD;
|
|
|
362 |
}
|
|
|
363 |
} break;
|
|
|
364 |
|
|
|
365 |
case 9: {
|
|
|
366 |
if (check_reserved) {
|
|
|
367 |
if (c[0] == QLatin1Char('i') && c[1] == QLatin1Char('n')
|
|
|
368 |
&& c[2] == QLatin1Char('t') && c[3] == QLatin1Char('e')
|
|
|
369 |
&& c[4] == QLatin1Char('r') && c[5] == QLatin1Char('f')
|
|
|
370 |
&& c[6] == QLatin1Char('a') && c[7] == QLatin1Char('c')
|
|
|
371 |
&& c[8] == QLatin1Char('e'))
|
|
|
372 |
return QScriptGrammar::T_RESERVED_WORD;
|
|
|
373 |
else if (c[0] == QLatin1Char('t') && c[1] == QLatin1Char('r')
|
|
|
374 |
&& c[2] == QLatin1Char('a') && c[3] == QLatin1Char('n')
|
|
|
375 |
&& c[4] == QLatin1Char('s') && c[5] == QLatin1Char('i')
|
|
|
376 |
&& c[6] == QLatin1Char('e') && c[7] == QLatin1Char('n')
|
|
|
377 |
&& c[8] == QLatin1Char('t'))
|
|
|
378 |
return QScriptGrammar::T_RESERVED_WORD;
|
|
|
379 |
else if (c[0] == QLatin1Char('p') && c[1] == QLatin1Char('r')
|
|
|
380 |
&& c[2] == QLatin1Char('o') && c[3] == QLatin1Char('t')
|
|
|
381 |
&& c[4] == QLatin1Char('e') && c[5] == QLatin1Char('c')
|
|
|
382 |
&& c[6] == QLatin1Char('t') && c[7] == QLatin1Char('e')
|
|
|
383 |
&& c[8] == QLatin1Char('d'))
|
|
|
384 |
return QScriptGrammar::T_RESERVED_WORD;
|
|
|
385 |
}
|
|
|
386 |
} break;
|
|
|
387 |
|
|
|
388 |
case 10: {
|
|
|
389 |
if (c[0] == QLatin1Char('i') && c[1] == QLatin1Char('n')
|
|
|
390 |
&& c[2] == QLatin1Char('s') && c[3] == QLatin1Char('t')
|
|
|
391 |
&& c[4] == QLatin1Char('a') && c[5] == QLatin1Char('n')
|
|
|
392 |
&& c[6] == QLatin1Char('c') && c[7] == QLatin1Char('e')
|
|
|
393 |
&& c[8] == QLatin1Char('o') && c[9] == QLatin1Char('f'))
|
|
|
394 |
return QScriptGrammar::T_INSTANCEOF;
|
|
|
395 |
else if (check_reserved) {
|
|
|
396 |
if (c[0] == QLatin1Char('i') && c[1] == QLatin1Char('m')
|
|
|
397 |
&& c[2] == QLatin1Char('p') && c[3] == QLatin1Char('l')
|
|
|
398 |
&& c[4] == QLatin1Char('e') && c[5] == QLatin1Char('m')
|
|
|
399 |
&& c[6] == QLatin1Char('e') && c[7] == QLatin1Char('n')
|
|
|
400 |
&& c[8] == QLatin1Char('t') && c[9] == QLatin1Char('s'))
|
|
|
401 |
return QScriptGrammar::T_RESERVED_WORD;
|
|
|
402 |
}
|
|
|
403 |
} break;
|
|
|
404 |
|
|
|
405 |
case 12: {
|
|
|
406 |
if (check_reserved) {
|
|
|
407 |
if (c[0] == QLatin1Char('s') && c[1] == QLatin1Char('y')
|
|
|
408 |
&& c[2] == QLatin1Char('n') && c[3] == QLatin1Char('c')
|
|
|
409 |
&& c[4] == QLatin1Char('h') && c[5] == QLatin1Char('r')
|
|
|
410 |
&& c[6] == QLatin1Char('o') && c[7] == QLatin1Char('n')
|
|
|
411 |
&& c[8] == QLatin1Char('i') && c[9] == QLatin1Char('z')
|
|
|
412 |
&& c[10] == QLatin1Char('e') && c[11] == QLatin1Char('d'))
|
|
|
413 |
return QScriptGrammar::T_RESERVED_WORD;
|
|
|
414 |
}
|
|
|
415 |
} break;
|
|
|
416 |
|
|
|
417 |
} // switch
|
|
|
418 |
|
|
|
419 |
return -1;
|
|
|
420 |
}
|
|
|
421 |
|
|
|
422 |
int QScript::Lexer::lex()
|
|
|
423 |
{
|
|
|
424 |
int token = 0;
|
|
|
425 |
state = Start;
|
|
|
426 |
ushort stringType = 0; // either single or double quotes
|
|
|
427 |
pos8 = pos16 = 0;
|
|
|
428 |
done = false;
|
|
|
429 |
terminator = false;
|
|
|
430 |
|
|
|
431 |
// did we push a token on the stack previously ?
|
|
|
432 |
// (after an automatic semicolon insertion)
|
|
|
433 |
if (stackToken >= 0) {
|
|
|
434 |
setDone(Other);
|
|
|
435 |
token = stackToken;
|
|
|
436 |
stackToken = -1;
|
|
|
437 |
}
|
|
|
438 |
|
|
|
439 |
while (!done) {
|
|
|
440 |
switch (state) {
|
|
|
441 |
case Start:
|
|
|
442 |
if (isWhiteSpace()) {
|
|
|
443 |
// do nothing
|
|
|
444 |
} else if (current == '/' && next1 == '/') {
|
|
|
445 |
recordStartPos();
|
|
|
446 |
shift(1);
|
|
|
447 |
state = InSingleLineComment;
|
|
|
448 |
} else if (current == '/' && next1 == '*') {
|
|
|
449 |
recordStartPos();
|
|
|
450 |
shift(1);
|
|
|
451 |
state = InMultiLineComment;
|
|
|
452 |
} else if (current == 0) {
|
|
|
453 |
syncProhibitAutomaticSemicolon();
|
|
|
454 |
if (!terminator && !delimited && !prohibitAutomaticSemicolon) {
|
|
|
455 |
// automatic semicolon insertion if program incomplete
|
|
|
456 |
token = QScriptGrammar::T_SEMICOLON;
|
|
|
457 |
stackToken = 0;
|
|
|
458 |
setDone(Other);
|
|
|
459 |
} else {
|
|
|
460 |
setDone(Eof);
|
|
|
461 |
}
|
|
|
462 |
} else if (isLineTerminator()) {
|
|
|
463 |
shiftWindowsLineBreak();
|
|
|
464 |
yylineno++;
|
|
|
465 |
yycolumn = 0;
|
|
|
466 |
bol = true;
|
|
|
467 |
terminator = true;
|
|
|
468 |
syncProhibitAutomaticSemicolon();
|
|
|
469 |
if (restrKeyword) {
|
|
|
470 |
token = QScriptGrammar::T_SEMICOLON;
|
|
|
471 |
setDone(Other);
|
|
|
472 |
}
|
|
|
473 |
} else if (current == '"' || current == '\'') {
|
|
|
474 |
recordStartPos();
|
|
|
475 |
state = InString;
|
|
|
476 |
stringType = current;
|
|
|
477 |
} else if (isIdentLetter(current)) {
|
|
|
478 |
recordStartPos();
|
|
|
479 |
record16(current);
|
|
|
480 |
state = InIdentifier;
|
|
|
481 |
} else if (current == '0') {
|
|
|
482 |
recordStartPos();
|
|
|
483 |
record8(current);
|
|
|
484 |
state = InNum0;
|
|
|
485 |
} else if (isDecimalDigit(current)) {
|
|
|
486 |
recordStartPos();
|
|
|
487 |
record8(current);
|
|
|
488 |
state = InNum;
|
|
|
489 |
} else if (current == '.' && isDecimalDigit(next1)) {
|
|
|
490 |
recordStartPos();
|
|
|
491 |
record8(current);
|
|
|
492 |
state = InDecimal;
|
|
|
493 |
} else {
|
|
|
494 |
recordStartPos();
|
|
|
495 |
token = matchPunctuator(current, next1, next2, next3);
|
|
|
496 |
if (token != -1) {
|
|
|
497 |
if (terminator && !delimited && !prohibitAutomaticSemicolon
|
|
|
498 |
&& (token == QScriptGrammar::T_PLUS_PLUS
|
|
|
499 |
|| token == QScriptGrammar::T_MINUS_MINUS)) {
|
|
|
500 |
// automatic semicolon insertion
|
|
|
501 |
stackToken = token;
|
|
|
502 |
token = QScriptGrammar::T_SEMICOLON;
|
|
|
503 |
}
|
|
|
504 |
setDone(Other);
|
|
|
505 |
}
|
|
|
506 |
else {
|
|
|
507 |
setDone(Bad);
|
|
|
508 |
err = IllegalCharacter;
|
|
|
509 |
errmsg = QLatin1String("Illegal character");
|
|
|
510 |
}
|
|
|
511 |
}
|
|
|
512 |
break;
|
|
|
513 |
case InString:
|
|
|
514 |
if (current == stringType) {
|
|
|
515 |
shift(1);
|
|
|
516 |
setDone(String);
|
|
|
517 |
} else if (current == 0 || isLineTerminator()) {
|
|
|
518 |
setDone(Bad);
|
|
|
519 |
err = UnclosedStringLiteral;
|
|
|
520 |
errmsg = QLatin1String("Unclosed string at end of line");
|
|
|
521 |
} else if (current == '\\') {
|
|
|
522 |
state = InEscapeSequence;
|
|
|
523 |
} else {
|
|
|
524 |
record16(current);
|
|
|
525 |
}
|
|
|
526 |
break;
|
|
|
527 |
// Escape Sequences inside of strings
|
|
|
528 |
case InEscapeSequence:
|
|
|
529 |
if (isOctalDigit(current)) {
|
|
|
530 |
if (current >= '0' && current <= '3' &&
|
|
|
531 |
isOctalDigit(next1) && isOctalDigit(next2)) {
|
|
|
532 |
record16(convertOctal(current, next1, next2));
|
|
|
533 |
shift(2);
|
|
|
534 |
state = InString;
|
|
|
535 |
} else if (isOctalDigit(current) &&
|
|
|
536 |
isOctalDigit(next1)) {
|
|
|
537 |
record16(convertOctal('0', current, next1));
|
|
|
538 |
shift(1);
|
|
|
539 |
state = InString;
|
|
|
540 |
} else if (isOctalDigit(current)) {
|
|
|
541 |
record16(convertOctal('0', '0', current));
|
|
|
542 |
state = InString;
|
|
|
543 |
} else {
|
|
|
544 |
setDone(Bad);
|
|
|
545 |
err = IllegalEscapeSequence;
|
|
|
546 |
errmsg = QLatin1String("Illegal escape squence");
|
|
|
547 |
}
|
|
|
548 |
} else if (current == 'x')
|
|
|
549 |
state = InHexEscape;
|
|
|
550 |
else if (current == 'u')
|
|
|
551 |
state = InUnicodeEscape;
|
|
|
552 |
else {
|
|
|
553 |
if (isLineTerminator()) {
|
|
|
554 |
shiftWindowsLineBreak();
|
|
|
555 |
yylineno++;
|
|
|
556 |
yycolumn = 0;
|
|
|
557 |
bol = true;
|
|
|
558 |
} else {
|
|
|
559 |
record16(singleEscape(current));
|
|
|
560 |
}
|
|
|
561 |
state = InString;
|
|
|
562 |
}
|
|
|
563 |
break;
|
|
|
564 |
case InHexEscape:
|
|
|
565 |
if (isHexDigit(current) && isHexDigit(next1)) {
|
|
|
566 |
state = InString;
|
|
|
567 |
record16(QLatin1Char(convertHex(current, next1)));
|
|
|
568 |
shift(1);
|
|
|
569 |
} else if (current == stringType) {
|
|
|
570 |
record16(QLatin1Char('x'));
|
|
|
571 |
shift(1);
|
|
|
572 |
setDone(String);
|
|
|
573 |
} else {
|
|
|
574 |
record16(QLatin1Char('x'));
|
|
|
575 |
record16(current);
|
|
|
576 |
state = InString;
|
|
|
577 |
}
|
|
|
578 |
break;
|
|
|
579 |
case InUnicodeEscape:
|
|
|
580 |
if (isHexDigit(current) && isHexDigit(next1) &&
|
|
|
581 |
isHexDigit(next2) && isHexDigit(next3)) {
|
|
|
582 |
record16(convertUnicode(current, next1, next2, next3));
|
|
|
583 |
shift(3);
|
|
|
584 |
state = InString;
|
|
|
585 |
} else if (current == stringType) {
|
|
|
586 |
record16(QLatin1Char('u'));
|
|
|
587 |
shift(1);
|
|
|
588 |
setDone(String);
|
|
|
589 |
} else {
|
|
|
590 |
setDone(Bad);
|
|
|
591 |
err = IllegalUnicodeEscapeSequence;
|
|
|
592 |
errmsg = QLatin1String("Illegal unicode escape sequence");
|
|
|
593 |
}
|
|
|
594 |
break;
|
|
|
595 |
case InSingleLineComment:
|
|
|
596 |
if (isLineTerminator()) {
|
|
|
597 |
shiftWindowsLineBreak();
|
|
|
598 |
yylineno++;
|
|
|
599 |
yycolumn = 0;
|
|
|
600 |
terminator = true;
|
|
|
601 |
bol = true;
|
|
|
602 |
if (restrKeyword) {
|
|
|
603 |
token = QScriptGrammar::T_SEMICOLON;
|
|
|
604 |
setDone(Other);
|
|
|
605 |
} else
|
|
|
606 |
state = Start;
|
|
|
607 |
} else if (current == 0) {
|
|
|
608 |
setDone(Eof);
|
|
|
609 |
}
|
|
|
610 |
break;
|
|
|
611 |
case InMultiLineComment:
|
|
|
612 |
if (current == 0) {
|
|
|
613 |
setDone(Bad);
|
|
|
614 |
err = UnclosedComment;
|
|
|
615 |
errmsg = QLatin1String("Unclosed comment at end of file");
|
|
|
616 |
} else if (isLineTerminator()) {
|
|
|
617 |
shiftWindowsLineBreak();
|
|
|
618 |
yylineno++;
|
|
|
619 |
} else if (current == '*' && next1 == '/') {
|
|
|
620 |
state = Start;
|
|
|
621 |
shift(1);
|
|
|
622 |
}
|
|
|
623 |
break;
|
|
|
624 |
case InIdentifier:
|
|
|
625 |
if (isIdentLetter(current) || isDecimalDigit(current)) {
|
|
|
626 |
record16(current);
|
|
|
627 |
break;
|
|
|
628 |
}
|
|
|
629 |
setDone(Identifier);
|
|
|
630 |
break;
|
|
|
631 |
case InNum0:
|
|
|
632 |
if (current == 'x' || current == 'X') {
|
|
|
633 |
record8(current);
|
|
|
634 |
state = InHex;
|
|
|
635 |
} else if (current == '.') {
|
|
|
636 |
record8(current);
|
|
|
637 |
state = InDecimal;
|
|
|
638 |
} else if (current == 'e' || current == 'E') {
|
|
|
639 |
record8(current);
|
|
|
640 |
state = InExponentIndicator;
|
|
|
641 |
} else if (isOctalDigit(current)) {
|
|
|
642 |
record8(current);
|
|
|
643 |
state = InOctal;
|
|
|
644 |
} else if (isDecimalDigit(current)) {
|
|
|
645 |
record8(current);
|
|
|
646 |
state = InDecimal;
|
|
|
647 |
} else {
|
|
|
648 |
setDone(Number);
|
|
|
649 |
}
|
|
|
650 |
break;
|
|
|
651 |
case InHex:
|
|
|
652 |
if (isHexDigit(current))
|
|
|
653 |
record8(current);
|
|
|
654 |
else
|
|
|
655 |
setDone(Hex);
|
|
|
656 |
break;
|
|
|
657 |
case InOctal:
|
|
|
658 |
if (isOctalDigit(current)) {
|
|
|
659 |
record8(current);
|
|
|
660 |
} else if (isDecimalDigit(current)) {
|
|
|
661 |
record8(current);
|
|
|
662 |
state = InDecimal;
|
|
|
663 |
} else {
|
|
|
664 |
setDone(Octal);
|
|
|
665 |
}
|
|
|
666 |
break;
|
|
|
667 |
case InNum:
|
|
|
668 |
if (isDecimalDigit(current)) {
|
|
|
669 |
record8(current);
|
|
|
670 |
} else if (current == '.') {
|
|
|
671 |
record8(current);
|
|
|
672 |
state = InDecimal;
|
|
|
673 |
} else if (current == 'e' || current == 'E') {
|
|
|
674 |
record8(current);
|
|
|
675 |
state = InExponentIndicator;
|
|
|
676 |
} else {
|
|
|
677 |
setDone(Number);
|
|
|
678 |
}
|
|
|
679 |
break;
|
|
|
680 |
case InDecimal:
|
|
|
681 |
if (isDecimalDigit(current)) {
|
|
|
682 |
record8(current);
|
|
|
683 |
} else if (current == 'e' || current == 'E') {
|
|
|
684 |
record8(current);
|
|
|
685 |
state = InExponentIndicator;
|
|
|
686 |
} else {
|
|
|
687 |
setDone(Number);
|
|
|
688 |
}
|
|
|
689 |
break;
|
|
|
690 |
case InExponentIndicator:
|
|
|
691 |
if (current == '+' || current == '-') {
|
|
|
692 |
record8(current);
|
|
|
693 |
} else if (isDecimalDigit(current)) {
|
|
|
694 |
record8(current);
|
|
|
695 |
state = InExponent;
|
|
|
696 |
} else {
|
|
|
697 |
setDone(Bad);
|
|
|
698 |
err = IllegalExponentIndicator;
|
|
|
699 |
errmsg = QLatin1String("Illegal syntax for exponential number");
|
|
|
700 |
}
|
|
|
701 |
break;
|
|
|
702 |
case InExponent:
|
|
|
703 |
if (isDecimalDigit(current)) {
|
|
|
704 |
record8(current);
|
|
|
705 |
} else {
|
|
|
706 |
setDone(Number);
|
|
|
707 |
}
|
|
|
708 |
break;
|
|
|
709 |
default:
|
|
|
710 |
Q_ASSERT_X(0, "Lexer::lex", "Unhandled state in switch statement");
|
|
|
711 |
}
|
|
|
712 |
|
|
|
713 |
// move on to the next character
|
|
|
714 |
if (!done)
|
|
|
715 |
shift(1);
|
|
|
716 |
if (state != Start && state != InSingleLineComment)
|
|
|
717 |
bol = false;
|
|
|
718 |
}
|
|
|
719 |
|
|
|
720 |
// no identifiers allowed directly after numeric literal, e.g. "3in" is bad
|
|
|
721 |
if ((state == Number || state == Octal || state == Hex)
|
|
|
722 |
&& isIdentLetter(current)) {
|
|
|
723 |
state = Bad;
|
|
|
724 |
err = IllegalIdentifier;
|
|
|
725 |
errmsg = QLatin1String("Identifier cannot start with numeric literal");
|
|
|
726 |
}
|
|
|
727 |
|
|
|
728 |
// terminate string
|
|
|
729 |
buffer8[pos8] = '\0';
|
|
|
730 |
|
|
|
731 |
double dval = 0;
|
|
|
732 |
if (state == Number) {
|
|
|
733 |
dval = qstrtod(buffer8, 0, 0);
|
|
|
734 |
} else if (state == Hex) { // scan hex numbers
|
|
|
735 |
dval = QScript::integerFromString(buffer8, pos8, 16);
|
|
|
736 |
state = Number;
|
|
|
737 |
} else if (state == Octal) { // scan octal number
|
|
|
738 |
dval = QScript::integerFromString(buffer8, pos8, 8);
|
|
|
739 |
state = Number;
|
|
|
740 |
}
|
|
|
741 |
|
|
|
742 |
restrKeyword = false;
|
|
|
743 |
delimited = false;
|
|
|
744 |
|
|
|
745 |
switch (parenthesesState) {
|
|
|
746 |
case IgnoreParentheses:
|
|
|
747 |
break;
|
|
|
748 |
case CountParentheses:
|
|
|
749 |
if (token == QScriptGrammar::T_RPAREN) {
|
|
|
750 |
--parenthesesCount;
|
|
|
751 |
if (parenthesesCount == 0)
|
|
|
752 |
parenthesesState = BalancedParentheses;
|
|
|
753 |
} else if (token == QScriptGrammar::T_LPAREN) {
|
|
|
754 |
++parenthesesCount;
|
|
|
755 |
}
|
|
|
756 |
break;
|
|
|
757 |
case BalancedParentheses:
|
|
|
758 |
parenthesesState = IgnoreParentheses;
|
|
|
759 |
break;
|
|
|
760 |
}
|
|
|
761 |
|
|
|
762 |
switch (state) {
|
|
|
763 |
case Eof:
|
|
|
764 |
return 0;
|
|
|
765 |
case Other:
|
|
|
766 |
if(token == QScriptGrammar::T_RBRACE || token == QScriptGrammar::T_SEMICOLON)
|
|
|
767 |
delimited = true;
|
|
|
768 |
return token;
|
|
|
769 |
case Identifier:
|
|
|
770 |
if ((token = findReservedWord(buffer16, pos16)) < 0) {
|
|
|
771 |
/* TODO: close leak on parse error. same holds true for String */
|
|
|
772 |
if (driver) {
|
|
|
773 |
Q_ASSERT_X(false, Q_FUNC_INFO, "not implemented");
|
|
|
774 |
qsyylval.ustr = 0; // driver->intern(buffer16, pos16);
|
|
|
775 |
} else
|
|
|
776 |
qsyylval.ustr = 0;
|
|
|
777 |
return QScriptGrammar::T_IDENTIFIER;
|
|
|
778 |
}
|
|
|
779 |
if (token == QScriptGrammar::T_CONTINUE || token == QScriptGrammar::T_BREAK
|
|
|
780 |
|| token == QScriptGrammar::T_RETURN || token == QScriptGrammar::T_THROW) {
|
|
|
781 |
restrKeyword = true;
|
|
|
782 |
} else if (token == QScriptGrammar::T_IF || token == QScriptGrammar::T_FOR
|
|
|
783 |
|| token == QScriptGrammar::T_WHILE || token == QScriptGrammar::T_WITH) {
|
|
|
784 |
parenthesesState = CountParentheses;
|
|
|
785 |
parenthesesCount = 0;
|
|
|
786 |
} else if (token == QScriptGrammar::T_DO) {
|
|
|
787 |
parenthesesState = BalancedParentheses;
|
|
|
788 |
}
|
|
|
789 |
return token;
|
|
|
790 |
case String:
|
|
|
791 |
if (driver) {
|
|
|
792 |
Q_ASSERT_X(false, Q_FUNC_INFO, "not implemented");
|
|
|
793 |
qsyylval.ustr = 0; // driver->intern(buffer16, pos16);
|
|
|
794 |
} else
|
|
|
795 |
qsyylval.ustr = 0;
|
|
|
796 |
return QScriptGrammar::T_STRING_LITERAL;
|
|
|
797 |
case Number:
|
|
|
798 |
qsyylval.dval = dval;
|
|
|
799 |
return QScriptGrammar::T_NUMERIC_LITERAL;
|
|
|
800 |
case Bad:
|
|
|
801 |
return -1;
|
|
|
802 |
default:
|
|
|
803 |
Q_ASSERT(!"unhandled numeration value in switch");
|
|
|
804 |
return -1;
|
|
|
805 |
}
|
|
|
806 |
}
|
|
|
807 |
|
|
|
808 |
bool QScript::Lexer::isWhiteSpace() const
|
|
|
809 |
{
|
|
|
810 |
return (current == ' ' || current == '\t' ||
|
|
|
811 |
current == 0x0b || current == 0x0c);
|
|
|
812 |
}
|
|
|
813 |
|
|
|
814 |
bool QScript::Lexer::isLineTerminator() const
|
|
|
815 |
{
|
|
|
816 |
return (current == '\n' || current == '\r');
|
|
|
817 |
}
|
|
|
818 |
|
|
|
819 |
bool QScript::Lexer::isIdentLetter(ushort c)
|
|
|
820 |
{
|
|
|
821 |
/* TODO: allow other legitimate unicode chars */
|
|
|
822 |
return ((c >= 'a' && c <= 'z')
|
|
|
823 |
|| (c >= 'A' && c <= 'Z')
|
|
|
824 |
|| c == '$'
|
|
|
825 |
|| c == '_');
|
|
|
826 |
}
|
|
|
827 |
|
|
|
828 |
bool QScript::Lexer::isDecimalDigit(ushort c)
|
|
|
829 |
{
|
|
|
830 |
return (c >= '0' && c <= '9');
|
|
|
831 |
}
|
|
|
832 |
|
|
|
833 |
bool QScript::Lexer::isHexDigit(ushort c) const
|
|
|
834 |
{
|
|
|
835 |
return ((c >= '0' && c <= '9')
|
|
|
836 |
|| (c >= 'a' && c <= 'f')
|
|
|
837 |
|| (c >= 'A' && c <= 'F'));
|
|
|
838 |
}
|
|
|
839 |
|
|
|
840 |
bool QScript::Lexer::isOctalDigit(ushort c) const
|
|
|
841 |
{
|
|
|
842 |
return (c >= '0' && c <= '7');
|
|
|
843 |
}
|
|
|
844 |
|
|
|
845 |
int QScript::Lexer::matchPunctuator(ushort c1, ushort c2,
|
|
|
846 |
ushort c3, ushort c4)
|
|
|
847 |
{
|
|
|
848 |
if (c1 == '>' && c2 == '>' && c3 == '>' && c4 == '=') {
|
|
|
849 |
shift(4);
|
|
|
850 |
return QScriptGrammar::T_GT_GT_GT_EQ;
|
|
|
851 |
} else if (c1 == '=' && c2 == '=' && c3 == '=') {
|
|
|
852 |
shift(3);
|
|
|
853 |
return QScriptGrammar::T_EQ_EQ_EQ;
|
|
|
854 |
} else if (c1 == '!' && c2 == '=' && c3 == '=') {
|
|
|
855 |
shift(3);
|
|
|
856 |
return QScriptGrammar::T_NOT_EQ_EQ;
|
|
|
857 |
} else if (c1 == '>' && c2 == '>' && c3 == '>') {
|
|
|
858 |
shift(3);
|
|
|
859 |
return QScriptGrammar::T_GT_GT_GT;
|
|
|
860 |
} else if (c1 == '<' && c2 == '<' && c3 == '=') {
|
|
|
861 |
shift(3);
|
|
|
862 |
return QScriptGrammar::T_LT_LT_EQ;
|
|
|
863 |
} else if (c1 == '>' && c2 == '>' && c3 == '=') {
|
|
|
864 |
shift(3);
|
|
|
865 |
return QScriptGrammar::T_GT_GT_EQ;
|
|
|
866 |
} else if (c1 == '<' && c2 == '=') {
|
|
|
867 |
shift(2);
|
|
|
868 |
return QScriptGrammar::T_LE;
|
|
|
869 |
} else if (c1 == '>' && c2 == '=') {
|
|
|
870 |
shift(2);
|
|
|
871 |
return QScriptGrammar::T_GE;
|
|
|
872 |
} else if (c1 == '!' && c2 == '=') {
|
|
|
873 |
shift(2);
|
|
|
874 |
return QScriptGrammar::T_NOT_EQ;
|
|
|
875 |
} else if (c1 == '+' && c2 == '+') {
|
|
|
876 |
shift(2);
|
|
|
877 |
return QScriptGrammar::T_PLUS_PLUS;
|
|
|
878 |
} else if (c1 == '-' && c2 == '-') {
|
|
|
879 |
shift(2);
|
|
|
880 |
return QScriptGrammar::T_MINUS_MINUS;
|
|
|
881 |
} else if (c1 == '=' && c2 == '=') {
|
|
|
882 |
shift(2);
|
|
|
883 |
return QScriptGrammar::T_EQ_EQ;
|
|
|
884 |
} else if (c1 == '+' && c2 == '=') {
|
|
|
885 |
shift(2);
|
|
|
886 |
return QScriptGrammar::T_PLUS_EQ;
|
|
|
887 |
} else if (c1 == '-' && c2 == '=') {
|
|
|
888 |
shift(2);
|
|
|
889 |
return QScriptGrammar::T_MINUS_EQ;
|
|
|
890 |
} else if (c1 == '*' && c2 == '=') {
|
|
|
891 |
shift(2);
|
|
|
892 |
return QScriptGrammar::T_STAR_EQ;
|
|
|
893 |
} else if (c1 == '/' && c2 == '=') {
|
|
|
894 |
shift(2);
|
|
|
895 |
return QScriptGrammar::T_DIVIDE_EQ;
|
|
|
896 |
} else if (c1 == '&' && c2 == '=') {
|
|
|
897 |
shift(2);
|
|
|
898 |
return QScriptGrammar::T_AND_EQ;
|
|
|
899 |
} else if (c1 == '^' && c2 == '=') {
|
|
|
900 |
shift(2);
|
|
|
901 |
return QScriptGrammar::T_XOR_EQ;
|
|
|
902 |
} else if (c1 == '%' && c2 == '=') {
|
|
|
903 |
shift(2);
|
|
|
904 |
return QScriptGrammar::T_REMAINDER_EQ;
|
|
|
905 |
} else if (c1 == '|' && c2 == '=') {
|
|
|
906 |
shift(2);
|
|
|
907 |
return QScriptGrammar::T_OR_EQ;
|
|
|
908 |
} else if (c1 == '<' && c2 == '<') {
|
|
|
909 |
shift(2);
|
|
|
910 |
return QScriptGrammar::T_LT_LT;
|
|
|
911 |
} else if (c1 == '>' && c2 == '>') {
|
|
|
912 |
shift(2);
|
|
|
913 |
return QScriptGrammar::T_GT_GT;
|
|
|
914 |
} else if (c1 == '&' && c2 == '&') {
|
|
|
915 |
shift(2);
|
|
|
916 |
return QScriptGrammar::T_AND_AND;
|
|
|
917 |
} else if (c1 == '|' && c2 == '|') {
|
|
|
918 |
shift(2);
|
|
|
919 |
return QScriptGrammar::T_OR_OR;
|
|
|
920 |
}
|
|
|
921 |
|
|
|
922 |
switch(c1) {
|
|
|
923 |
case '=': shift(1); return QScriptGrammar::T_EQ;
|
|
|
924 |
case '>': shift(1); return QScriptGrammar::T_GT;
|
|
|
925 |
case '<': shift(1); return QScriptGrammar::T_LT;
|
|
|
926 |
case ',': shift(1); return QScriptGrammar::T_COMMA;
|
|
|
927 |
case '!': shift(1); return QScriptGrammar::T_NOT;
|
|
|
928 |
case '~': shift(1); return QScriptGrammar::T_TILDE;
|
|
|
929 |
case '?': shift(1); return QScriptGrammar::T_QUESTION;
|
|
|
930 |
case ':': shift(1); return QScriptGrammar::T_COLON;
|
|
|
931 |
case '.': shift(1); return QScriptGrammar::T_DOT;
|
|
|
932 |
case '+': shift(1); return QScriptGrammar::T_PLUS;
|
|
|
933 |
case '-': shift(1); return QScriptGrammar::T_MINUS;
|
|
|
934 |
case '*': shift(1); return QScriptGrammar::T_STAR;
|
|
|
935 |
case '/': shift(1); return QScriptGrammar::T_DIVIDE_;
|
|
|
936 |
case '&': shift(1); return QScriptGrammar::T_AND;
|
|
|
937 |
case '|': shift(1); return QScriptGrammar::T_OR;
|
|
|
938 |
case '^': shift(1); return QScriptGrammar::T_XOR;
|
|
|
939 |
case '%': shift(1); return QScriptGrammar::T_REMAINDER;
|
|
|
940 |
case '(': shift(1); return QScriptGrammar::T_LPAREN;
|
|
|
941 |
case ')': shift(1); return QScriptGrammar::T_RPAREN;
|
|
|
942 |
case '{': shift(1); return QScriptGrammar::T_LBRACE;
|
|
|
943 |
case '}': shift(1); return QScriptGrammar::T_RBRACE;
|
|
|
944 |
case '[': shift(1); return QScriptGrammar::T_LBRACKET;
|
|
|
945 |
case ']': shift(1); return QScriptGrammar::T_RBRACKET;
|
|
|
946 |
case ';': shift(1); return QScriptGrammar::T_SEMICOLON;
|
|
|
947 |
|
|
|
948 |
default: return -1;
|
|
|
949 |
}
|
|
|
950 |
}
|
|
|
951 |
|
|
|
952 |
ushort QScript::Lexer::singleEscape(ushort c) const
|
|
|
953 |
{
|
|
|
954 |
switch(c) {
|
|
|
955 |
case 'b':
|
|
|
956 |
return 0x08;
|
|
|
957 |
case 't':
|
|
|
958 |
return 0x09;
|
|
|
959 |
case 'n':
|
|
|
960 |
return 0x0A;
|
|
|
961 |
case 'v':
|
|
|
962 |
return 0x0B;
|
|
|
963 |
case 'f':
|
|
|
964 |
return 0x0C;
|
|
|
965 |
case 'r':
|
|
|
966 |
return 0x0D;
|
|
|
967 |
case '"':
|
|
|
968 |
return 0x22;
|
|
|
969 |
case '\'':
|
|
|
970 |
return 0x27;
|
|
|
971 |
case '\\':
|
|
|
972 |
return 0x5C;
|
|
|
973 |
default:
|
|
|
974 |
return c;
|
|
|
975 |
}
|
|
|
976 |
}
|
|
|
977 |
|
|
|
978 |
ushort QScript::Lexer::convertOctal(ushort c1, ushort c2,
|
|
|
979 |
ushort c3) const
|
|
|
980 |
{
|
|
|
981 |
return ((c1 - '0') * 64 + (c2 - '0') * 8 + c3 - '0');
|
|
|
982 |
}
|
|
|
983 |
|
|
|
984 |
unsigned char QScript::Lexer::convertHex(ushort c)
|
|
|
985 |
{
|
|
|
986 |
if (c >= '0' && c <= '9')
|
|
|
987 |
return (c - '0');
|
|
|
988 |
else if (c >= 'a' && c <= 'f')
|
|
|
989 |
return (c - 'a' + 10);
|
|
|
990 |
else
|
|
|
991 |
return (c - 'A' + 10);
|
|
|
992 |
}
|
|
|
993 |
|
|
|
994 |
unsigned char QScript::Lexer::convertHex(ushort c1, ushort c2)
|
|
|
995 |
{
|
|
|
996 |
return ((convertHex(c1) << 4) + convertHex(c2));
|
|
|
997 |
}
|
|
|
998 |
|
|
|
999 |
QChar QScript::Lexer::convertUnicode(ushort c1, ushort c2,
|
|
|
1000 |
ushort c3, ushort c4)
|
|
|
1001 |
{
|
|
|
1002 |
return QChar((convertHex(c3) << 4) + convertHex(c4),
|
|
|
1003 |
(convertHex(c1) << 4) + convertHex(c2));
|
|
|
1004 |
}
|
|
|
1005 |
|
|
|
1006 |
void QScript::Lexer::record8(ushort c)
|
|
|
1007 |
{
|
|
|
1008 |
Q_ASSERT(c <= 0xff);
|
|
|
1009 |
|
|
|
1010 |
// enlarge buffer if full
|
|
|
1011 |
if (pos8 >= size8 - 1) {
|
|
|
1012 |
char *tmp = new char[2 * size8];
|
|
|
1013 |
memcpy(tmp, buffer8, size8 * sizeof(char));
|
|
|
1014 |
delete [] buffer8;
|
|
|
1015 |
buffer8 = tmp;
|
|
|
1016 |
size8 *= 2;
|
|
|
1017 |
}
|
|
|
1018 |
|
|
|
1019 |
buffer8[pos8++] = (char) c;
|
|
|
1020 |
}
|
|
|
1021 |
|
|
|
1022 |
void QScript::Lexer::record16(QChar c)
|
|
|
1023 |
{
|
|
|
1024 |
// enlarge buffer if full
|
|
|
1025 |
if (pos16 >= size16 - 1) {
|
|
|
1026 |
QChar *tmp = new QChar[2 * size16];
|
|
|
1027 |
memcpy(tmp, buffer16, size16 * sizeof(QChar));
|
|
|
1028 |
delete [] buffer16;
|
|
|
1029 |
buffer16 = tmp;
|
|
|
1030 |
size16 *= 2;
|
|
|
1031 |
}
|
|
|
1032 |
|
|
|
1033 |
buffer16[pos16++] = c;
|
|
|
1034 |
}
|
|
|
1035 |
|
|
|
1036 |
void QScript::Lexer::recordStartPos()
|
|
|
1037 |
{
|
|
|
1038 |
startlineno = yylineno;
|
|
|
1039 |
startcolumn = yycolumn;
|
|
|
1040 |
}
|
|
|
1041 |
|
|
|
1042 |
bool QScript::Lexer::scanRegExp(RegExpBodyPrefix prefix)
|
|
|
1043 |
{
|
|
|
1044 |
pos16 = 0;
|
|
|
1045 |
bool lastWasEscape = false;
|
|
|
1046 |
|
|
|
1047 |
if (prefix == EqualPrefix)
|
|
|
1048 |
record16(QLatin1Char('='));
|
|
|
1049 |
|
|
|
1050 |
while (1) {
|
|
|
1051 |
if (isLineTerminator() || current == 0) {
|
|
|
1052 |
errmsg = QLatin1String("Unterminated regular expression literal");
|
|
|
1053 |
return false;
|
|
|
1054 |
}
|
|
|
1055 |
else if (current != '/' || lastWasEscape == true)
|
|
|
1056 |
{
|
|
|
1057 |
record16(current);
|
|
|
1058 |
lastWasEscape = !lastWasEscape && (current == '\\');
|
|
|
1059 |
}
|
|
|
1060 |
else {
|
|
|
1061 |
if (driver) {
|
|
|
1062 |
Q_ASSERT_X(false, Q_FUNC_INFO, "not implemented");
|
|
|
1063 |
pattern = 0; // driver->intern(buffer16, pos16);
|
|
|
1064 |
} else
|
|
|
1065 |
pattern = 0;
|
|
|
1066 |
pos16 = 0;
|
|
|
1067 |
shift(1);
|
|
|
1068 |
break;
|
|
|
1069 |
}
|
|
|
1070 |
shift(1);
|
|
|
1071 |
}
|
|
|
1072 |
|
|
|
1073 |
flags = 0;
|
|
|
1074 |
while (isIdentLetter(current)) {
|
|
|
1075 |
// current version was remade from this line:
|
|
|
1076 |
//int flag = QScript::Ecma::RegExp::flagFromChar(current);
|
|
|
1077 |
//code was "inlined" because it was only one call to this function
|
|
|
1078 |
int flag;
|
|
|
1079 |
switch (current) {
|
|
|
1080 |
case 'g': flag = 0x01; break;
|
|
|
1081 |
case 'm': flag = 0x02; break;
|
|
|
1082 |
case 'i': flag = 0x04; break;
|
|
|
1083 |
default: flag = 0;
|
|
|
1084 |
}
|
|
|
1085 |
if (flag == 0) {
|
|
|
1086 |
errmsg = QString::fromLatin1("Invalid regular expression flag '%0'")
|
|
|
1087 |
.arg(QChar(current));
|
|
|
1088 |
return false;
|
|
|
1089 |
}
|
|
|
1090 |
flags |= flag;
|
|
|
1091 |
record16(current);
|
|
|
1092 |
shift(1);
|
|
|
1093 |
}
|
|
|
1094 |
|
|
|
1095 |
return true;
|
|
|
1096 |
}
|
|
|
1097 |
|
|
|
1098 |
void QScript::Lexer::syncProhibitAutomaticSemicolon()
|
|
|
1099 |
{
|
|
|
1100 |
if (parenthesesState == BalancedParentheses) {
|
|
|
1101 |
// we have seen something like "if (foo)", which means we should
|
|
|
1102 |
// never insert an automatic semicolon at this point, since it would
|
|
|
1103 |
// then be expanded into an empty statement (ECMA-262 7.9.1)
|
|
|
1104 |
prohibitAutomaticSemicolon = true;
|
|
|
1105 |
parenthesesState = IgnoreParentheses;
|
|
|
1106 |
} else {
|
|
|
1107 |
prohibitAutomaticSemicolon = false;
|
|
|
1108 |
}
|
|
|
1109 |
}
|
|
|
1110 |
|
|
|
1111 |
QT_END_NAMESPACE
|