| 1 | /**************************************************************************** |
| 2 | ** |
| 3 | ** Copyright (C) 2015 The Qt Company Ltd. |
| 4 | ** Contact: http://www.qt.io/licensing/ |
| 5 | ** |
| 6 | ** This file is part of the QtScript module of the Qt Toolkit. |
| 7 | ** |
| 8 | ** $QT_BEGIN_LICENSE:LGPL$ |
| 9 | ** Commercial License Usage |
| 10 | ** Licensees holding valid commercial Qt licenses may use this file in |
| 11 | ** accordance with the commercial license agreement provided with the |
| 12 | ** Software or, alternatively, in accordance with the terms contained in |
| 13 | ** a written agreement between you and The Qt Company. For licensing terms |
| 14 | ** and conditions see https://www.qt.io/terms-conditions. For further |
| 15 | ** information use the contact form at https://www.qt.io/contact-us. |
| 16 | ** |
| 17 | ** GNU Lesser General Public License Usage |
| 18 | ** Alternatively, this file may be used under the terms of the GNU Lesser |
| 19 | ** General Public License version 3 as published by the Free Software |
| 20 | ** Foundation and appearing in the file LICENSE.LGPL3 included in the |
| 21 | ** packaging of this file. Please review the following information to |
| 22 | ** ensure the GNU Lesser General Public License version 3 requirements |
| 23 | ** will be met: https://www.gnu.org/licenses/lgpl-3.0.html. |
| 24 | ** |
| 25 | ** GNU General Public License Usage |
| 26 | ** Alternatively, this file may be used under the terms of the GNU |
| 27 | ** General Public License version 2.0 or (at your option) the GNU General |
| 28 | ** Public license version 3 or any later version approved by the KDE Free |
| 29 | ** Qt Foundation. The licenses are as published by the Free Software |
| 30 | ** Foundation and appearing in the file LICENSE.GPL2 and LICENSE.GPL3 |
| 31 | ** included in the packaging of this file. Please review the following |
| 32 | ** information to ensure the GNU General Public License requirements will |
| 33 | ** be met: https://www.gnu.org/licenses/gpl-2.0.html and |
| 34 | ** https://www.gnu.org/licenses/gpl-3.0.html. |
| 35 | ** |
| 36 | ** $QT_END_LICENSE$ |
| 37 | ** |
| 38 | ****************************************************************************/ |
| 39 | |
| 40 | #include "qscriptlexer_p.h" |
| 41 | |
| 42 | #include "qscriptgrammar_p.h" |
| 43 | #include <ctype.h> |
| 44 | #include <stdlib.h> |
| 45 | #include <stdio.h> |
| 46 | #include <string.h> |
| 47 | |
| 48 | QT_BEGIN_NAMESPACE |
| 49 | |
| 50 | #define shiftWindowsLineBreak() \ |
| 51 | do { \ |
| 52 | if (((current == '\r') && (next1 == '\n')) \ |
| 53 | || ((current == '\n') && (next1 == '\r'))) { \ |
| 54 | shift(1); \ |
| 55 | } \ |
| 56 | } \ |
| 57 | while (0) |
| 58 | |
| 59 | typedef double qsreal; // ### |
| 60 | |
| 61 | namespace QScript { |
| 62 | extern qsreal integerFromString(const char *buf, int size, int radix); |
| 63 | } |
| 64 | |
| 65 | QScript::Lexer::Lexer(QScriptEnginePrivate *eng) |
| 66 | : driver(eng), |
| 67 | yylineno(0), |
| 68 | size8(128), size16(128), restrKeyword(false), |
| 69 | stackToken(-1), pos(0), |
| 70 | code(0), length(0), |
| 71 | bol(true), |
| 72 | current(0), next1(0), next2(0), next3(0), |
| 73 | err(NoError), |
| 74 | check_reserved(true), |
| 75 | parenthesesState(IgnoreParentheses), |
| 76 | prohibitAutomaticSemicolon(false) |
| 77 | { |
| 78 | // allocate space for read buffers |
| 79 | buffer8 = new char[size8]; |
| 80 | buffer16 = new QChar[size16]; |
| 81 | pattern = 0; |
| 82 | flags = 0; |
| 83 | |
| 84 | } |
| 85 | |
| 86 | QScript::Lexer::~Lexer() |
| 87 | { |
| 88 | delete [] buffer8; |
| 89 | delete [] buffer16; |
| 90 | } |
| 91 | |
| 92 | void QScript::Lexer::setCode(const QString &c, int lineno) |
| 93 | { |
| 94 | errmsg = QString(); |
| 95 | yylineno = lineno; |
| 96 | yycolumn = 1; |
| 97 | restrKeyword = false; |
| 98 | delimited = false; |
| 99 | stackToken = -1; |
| 100 | pos = 0; |
| 101 | code = c.unicode(); |
| 102 | length = c.length(); |
| 103 | bol = true; |
| 104 | |
| 105 | // read first characters |
| 106 | current = (length > 0) ? code[0].unicode() : 0; |
| 107 | next1 = (length > 1) ? code[1].unicode() : 0; |
| 108 | next2 = (length > 2) ? code[2].unicode() : 0; |
| 109 | next3 = (length > 3) ? code[3].unicode() : 0; |
| 110 | } |
| 111 | |
| 112 | void QScript::Lexer::shift(uint p) |
| 113 | { |
| 114 | while (p--) { |
| 115 | ++pos; |
| 116 | ++yycolumn; |
| 117 | current = next1; |
| 118 | next1 = next2; |
| 119 | next2 = next3; |
| 120 | next3 = (pos + 3 < length) ? code[pos+3].unicode() : 0; |
| 121 | } |
| 122 | } |
| 123 | |
| 124 | void QScript::Lexer::setDone(State s) |
| 125 | { |
| 126 | state = s; |
| 127 | done = true; |
| 128 | } |
| 129 | |
| 130 | int QScript::Lexer::findReservedWord(const QChar *c, int size) const |
| 131 | { |
| 132 | switch (size) { |
| 133 | case 2: { |
| 134 | if (c[0] == QLatin1Char('d') && c[1] == QLatin1Char('o')) |
| 135 | return QScriptGrammar::T_DO; |
| 136 | else if (c[0] == QLatin1Char('i') && c[1] == QLatin1Char('f')) |
| 137 | return QScriptGrammar::T_IF; |
| 138 | else if (c[0] == QLatin1Char('i') && c[1] == QLatin1Char('n')) |
| 139 | return QScriptGrammar::T_IN; |
| 140 | } break; |
| 141 | |
| 142 | case 3: { |
| 143 | if (c[0] == QLatin1Char('f') && c[1] == QLatin1Char('o') && c[2] == QLatin1Char('r')) |
| 144 | return QScriptGrammar::T_FOR; |
| 145 | else if (c[0] == QLatin1Char('n') && c[1] == QLatin1Char('e') && c[2] == QLatin1Char('w')) |
| 146 | return QScriptGrammar::T_NEW; |
| 147 | else if (c[0] == QLatin1Char('t') && c[1] == QLatin1Char('r') && c[2] == QLatin1Char('y')) |
| 148 | return QScriptGrammar::T_TRY; |
| 149 | else if (c[0] == QLatin1Char('v') && c[1] == QLatin1Char('a') && c[2] == QLatin1Char('r')) |
| 150 | return QScriptGrammar::T_VAR; |
| 151 | else if (check_reserved) { |
| 152 | if (c[0] == QLatin1Char('i') && c[1] == QLatin1Char('n') && c[2] == QLatin1Char('t')) |
| 153 | return QScriptGrammar::T_RESERVED_WORD; |
| 154 | } |
| 155 | } break; |
| 156 | |
| 157 | case 4: { |
| 158 | if (c[0] == QLatin1Char('c') && c[1] == QLatin1Char('a') |
| 159 | && c[2] == QLatin1Char('s') && c[3] == QLatin1Char('e')) |
| 160 | return QScriptGrammar::T_CASE; |
| 161 | else if (c[0] == QLatin1Char('e') && c[1] == QLatin1Char('l') |
| 162 | && c[2] == QLatin1Char('s') && c[3] == QLatin1Char('e')) |
| 163 | return QScriptGrammar::T_ELSE; |
| 164 | else if (c[0] == QLatin1Char('t') && c[1] == QLatin1Char('h') |
| 165 | && c[2] == QLatin1Char('i') && c[3] == QLatin1Char('s')) |
| 166 | return QScriptGrammar::T_THIS; |
| 167 | else if (c[0] == QLatin1Char('v') && c[1] == QLatin1Char('o') |
| 168 | && c[2] == QLatin1Char('i') && c[3] == QLatin1Char('d')) |
| 169 | return QScriptGrammar::T_VOID; |
| 170 | else if (c[0] == QLatin1Char('w') && c[1] == QLatin1Char('i') |
| 171 | && c[2] == QLatin1Char('t') && c[3] == QLatin1Char('h')) |
| 172 | return QScriptGrammar::T_WITH; |
| 173 | else if (c[0] == QLatin1Char('t') && c[1] == QLatin1Char('r') |
| 174 | && c[2] == QLatin1Char('u') && c[3] == QLatin1Char('e')) |
| 175 | return QScriptGrammar::T_TRUE; |
| 176 | else if (c[0] == QLatin1Char('n') && c[1] == QLatin1Char('u') |
| 177 | && c[2] == QLatin1Char('l') && c[3] == QLatin1Char('l')) |
| 178 | return QScriptGrammar::T_NULL; |
| 179 | else if (check_reserved) { |
| 180 | if (c[0] == QLatin1Char('e') && c[1] == QLatin1Char('n') |
| 181 | && c[2] == QLatin1Char('u') && c[3] == QLatin1Char('m')) |
| 182 | return QScriptGrammar::T_RESERVED_WORD; |
| 183 | else if (c[0] == QLatin1Char('b') && c[1] == QLatin1Char('y') |
| 184 | && c[2] == QLatin1Char('t') && c[3] == QLatin1Char('e')) |
| 185 | return QScriptGrammar::T_RESERVED_WORD; |
| 186 | else if (c[0] == QLatin1Char('l') && c[1] == QLatin1Char('o') |
| 187 | && c[2] == QLatin1Char('n') && c[3] == QLatin1Char('g')) |
| 188 | return QScriptGrammar::T_RESERVED_WORD; |
| 189 | else if (c[0] == QLatin1Char('c') && c[1] == QLatin1Char('h') |
| 190 | && c[2] == QLatin1Char('a') && c[3] == QLatin1Char('r')) |
| 191 | return QScriptGrammar::T_RESERVED_WORD; |
| 192 | else if (c[0] == QLatin1Char('g') && c[1] == QLatin1Char('o') |
| 193 | && c[2] == QLatin1Char('t') && c[3] == QLatin1Char('o')) |
| 194 | return QScriptGrammar::T_RESERVED_WORD; |
| 195 | } |
| 196 | } break; |
| 197 | |
| 198 | case 5: { |
| 199 | if (c[0] == QLatin1Char('b') && c[1] == QLatin1Char('r') |
| 200 | && c[2] == QLatin1Char('e') && c[3] == QLatin1Char('a') |
| 201 | && c[4] == QLatin1Char('k')) |
| 202 | return QScriptGrammar::T_BREAK; |
| 203 | else if (c[0] == QLatin1Char('c') && c[1] == QLatin1Char('a') |
| 204 | && c[2] == QLatin1Char('t') && c[3] == QLatin1Char('c') |
| 205 | && c[4] == QLatin1Char('h')) |
| 206 | return QScriptGrammar::T_CATCH; |
| 207 | else if (c[0] == QLatin1Char('t') && c[1] == QLatin1Char('h') |
| 208 | && c[2] == QLatin1Char('r') && c[3] == QLatin1Char('o') |
| 209 | && c[4] == QLatin1Char('w')) |
| 210 | return QScriptGrammar::T_THROW; |
| 211 | else if (c[0] == QLatin1Char('w') && c[1] == QLatin1Char('h') |
| 212 | && c[2] == QLatin1Char('i') && c[3] == QLatin1Char('l') |
| 213 | && c[4] == QLatin1Char('e')) |
| 214 | return QScriptGrammar::T_WHILE; |
| 215 | else if (c[0] == QLatin1Char('c') && c[1] == QLatin1Char('o') |
| 216 | && c[2] == QLatin1Char('n') && c[3] == QLatin1Char('s') |
| 217 | && c[4] == QLatin1Char('t')) |
| 218 | return QScriptGrammar::T_CONST; |
| 219 | else if (c[0] == QLatin1Char('f') && c[1] == QLatin1Char('a') |
| 220 | && c[2] == QLatin1Char('l') && c[3] == QLatin1Char('s') |
| 221 | && c[4] == QLatin1Char('e')) |
| 222 | return QScriptGrammar::T_FALSE; |
| 223 | else if (check_reserved) { |
| 224 | if (c[0] == QLatin1Char('s') && c[1] == QLatin1Char('h') |
| 225 | && c[2] == QLatin1Char('o') && c[3] == QLatin1Char('r') |
| 226 | && c[4] == QLatin1Char('t')) |
| 227 | return QScriptGrammar::T_RESERVED_WORD; |
| 228 | else if (c[0] == QLatin1Char('s') && c[1] == QLatin1Char('u') |
| 229 | && c[2] == QLatin1Char('p') && c[3] == QLatin1Char('e') |
| 230 | && c[4] == QLatin1Char('r')) |
| 231 | return QScriptGrammar::T_RESERVED_WORD; |
| 232 | else if (c[0] == QLatin1Char('f') && c[1] == QLatin1Char('i') |
| 233 | && c[2] == QLatin1Char('n') && c[3] == QLatin1Char('a') |
| 234 | && c[4] == QLatin1Char('l')) |
| 235 | return QScriptGrammar::T_RESERVED_WORD; |
| 236 | else if (c[0] == QLatin1Char('c') && c[1] == QLatin1Char('l') |
| 237 | && c[2] == QLatin1Char('a') && c[3] == QLatin1Char('s') |
| 238 | && c[4] == QLatin1Char('s')) |
| 239 | return QScriptGrammar::T_RESERVED_WORD; |
| 240 | else if (c[0] == QLatin1Char('f') && c[1] == QLatin1Char('l') |
| 241 | && c[2] == QLatin1Char('o') && c[3] == QLatin1Char('a') |
| 242 | && c[4] == QLatin1Char('t')) |
| 243 | return QScriptGrammar::T_RESERVED_WORD; |
| 244 | } |
| 245 | } break; |
| 246 | |
| 247 | case 6: { |
| 248 | if (c[0] == QLatin1Char('d') && c[1] == QLatin1Char('e') |
| 249 | && c[2] == QLatin1Char('l') && c[3] == QLatin1Char('e') |
| 250 | && c[4] == QLatin1Char('t') && c[5] == QLatin1Char('e')) |
| 251 | return QScriptGrammar::T_DELETE; |
| 252 | else if (c[0] == QLatin1Char('r') && c[1] == QLatin1Char('e') |
| 253 | && c[2] == QLatin1Char('t') && c[3] == QLatin1Char('u') |
| 254 | && c[4] == QLatin1Char('r') && c[5] == QLatin1Char('n')) |
| 255 | return QScriptGrammar::T_RETURN; |
| 256 | else if (c[0] == QLatin1Char('s') && c[1] == QLatin1Char('w') |
| 257 | && c[2] == QLatin1Char('i') && c[3] == QLatin1Char('t') |
| 258 | && c[4] == QLatin1Char('c') && c[5] == QLatin1Char('h')) |
| 259 | return QScriptGrammar::T_SWITCH; |
| 260 | else if (c[0] == QLatin1Char('t') && c[1] == QLatin1Char('y') |
| 261 | && c[2] == QLatin1Char('p') && c[3] == QLatin1Char('e') |
| 262 | && c[4] == QLatin1Char('o') && c[5] == QLatin1Char('f')) |
| 263 | return QScriptGrammar::T_TYPEOF; |
| 264 | else if (check_reserved) { |
| 265 | if (c[0] == QLatin1Char('e') && c[1] == QLatin1Char('x') |
| 266 | && c[2] == QLatin1Char('p') && c[3] == QLatin1Char('o') |
| 267 | && c[4] == QLatin1Char('r') && c[5] == QLatin1Char('t')) |
| 268 | return QScriptGrammar::T_RESERVED_WORD; |
| 269 | else if (c[0] == QLatin1Char('s') && c[1] == QLatin1Char('t') |
| 270 | && c[2] == QLatin1Char('a') && c[3] == QLatin1Char('t') |
| 271 | && c[4] == QLatin1Char('i') && c[5] == QLatin1Char('c')) |
| 272 | return QScriptGrammar::T_RESERVED_WORD; |
| 273 | else if (c[0] == QLatin1Char('d') && c[1] == QLatin1Char('o') |
| 274 | && c[2] == QLatin1Char('u') && c[3] == QLatin1Char('b') |
| 275 | && c[4] == QLatin1Char('l') && c[5] == QLatin1Char('e')) |
| 276 | return QScriptGrammar::T_RESERVED_WORD; |
| 277 | else if (c[0] == QLatin1Char('i') && c[1] == QLatin1Char('m') |
| 278 | && c[2] == QLatin1Char('p') && c[3] == QLatin1Char('o') |
| 279 | && c[4] == QLatin1Char('r') && c[5] == QLatin1Char('t')) |
| 280 | return QScriptGrammar::T_RESERVED_WORD; |
| 281 | else if (c[0] == QLatin1Char('p') && c[1] == QLatin1Char('u') |
| 282 | && c[2] == QLatin1Char('b') && c[3] == QLatin1Char('l') |
| 283 | && c[4] == QLatin1Char('i') && c[5] == QLatin1Char('c')) |
| 284 | return QScriptGrammar::T_RESERVED_WORD; |
| 285 | else if (c[0] == QLatin1Char('n') && c[1] == QLatin1Char('a') |
| 286 | && c[2] == QLatin1Char('t') && c[3] == QLatin1Char('i') |
| 287 | && c[4] == QLatin1Char('v') && c[5] == QLatin1Char('e')) |
| 288 | return QScriptGrammar::T_RESERVED_WORD; |
| 289 | else if (c[0] == QLatin1Char('t') && c[1] == QLatin1Char('h') |
| 290 | && c[2] == QLatin1Char('r') && c[3] == QLatin1Char('o') |
| 291 | && c[4] == QLatin1Char('w') && c[5] == QLatin1Char('s')) |
| 292 | return QScriptGrammar::T_RESERVED_WORD; |
| 293 | } |
| 294 | } break; |
| 295 | |
| 296 | case 7: { |
| 297 | if (c[0] == QLatin1Char('d') && c[1] == QLatin1Char('e') |
| 298 | && c[2] == QLatin1Char('f') && c[3] == QLatin1Char('a') |
| 299 | && c[4] == QLatin1Char('u') && c[5] == QLatin1Char('l') |
| 300 | && c[6] == QLatin1Char('t')) |
| 301 | return QScriptGrammar::T_DEFAULT; |
| 302 | else if (c[0] == QLatin1Char('f') && c[1] == QLatin1Char('i') |
| 303 | && c[2] == QLatin1Char('n') && c[3] == QLatin1Char('a') |
| 304 | && c[4] == QLatin1Char('l') && c[5] == QLatin1Char('l') |
| 305 | && c[6] == QLatin1Char('y')) |
| 306 | return QScriptGrammar::T_FINALLY; |
| 307 | else if (check_reserved) { |
| 308 | if (c[0] == QLatin1Char('b') && c[1] == QLatin1Char('o') |
| 309 | && c[2] == QLatin1Char('o') && c[3] == QLatin1Char('l') |
| 310 | && c[4] == QLatin1Char('e') && c[5] == QLatin1Char('a') |
| 311 | && c[6] == QLatin1Char('n')) |
| 312 | return QScriptGrammar::T_RESERVED_WORD; |
| 313 | else if (c[0] == QLatin1Char('e') && c[1] == QLatin1Char('x') |
| 314 | && c[2] == QLatin1Char('t') && c[3] == QLatin1Char('e') |
| 315 | && c[4] == QLatin1Char('n') && c[5] == QLatin1Char('d') |
| 316 | && c[6] == QLatin1Char('s')) |
| 317 | return QScriptGrammar::T_RESERVED_WORD; |
| 318 | else if (c[0] == QLatin1Char('p') && c[1] == QLatin1Char('a') |
| 319 | && c[2] == QLatin1Char('c') && c[3] == QLatin1Char('k') |
| 320 | && c[4] == QLatin1Char('a') && c[5] == QLatin1Char('g') |
| 321 | && c[6] == QLatin1Char('e')) |
| 322 | return QScriptGrammar::T_RESERVED_WORD; |
| 323 | else if (c[0] == QLatin1Char('p') && c[1] == QLatin1Char('r') |
| 324 | && c[2] == QLatin1Char('i') && c[3] == QLatin1Char('v') |
| 325 | && c[4] == QLatin1Char('a') && c[5] == QLatin1Char('t') |
| 326 | && c[6] == QLatin1Char('e')) |
| 327 | return QScriptGrammar::T_RESERVED_WORD; |
| 328 | } |
| 329 | } break; |
| 330 | |
| 331 | case 8: { |
| 332 | if (c[0] == QLatin1Char('c') && c[1] == QLatin1Char('o') |
| 333 | && c[2] == QLatin1Char('n') && c[3] == QLatin1Char('t') |
| 334 | && c[4] == QLatin1Char('i') && c[5] == QLatin1Char('n') |
| 335 | && c[6] == QLatin1Char('u') && c[7] == QLatin1Char('e')) |
| 336 | return QScriptGrammar::T_CONTINUE; |
| 337 | else if (c[0] == QLatin1Char('f') && c[1] == QLatin1Char('u') |
| 338 | && c[2] == QLatin1Char('n') && c[3] == QLatin1Char('c') |
| 339 | && c[4] == QLatin1Char('t') && c[5] == QLatin1Char('i') |
| 340 | && c[6] == QLatin1Char('o') && c[7] == QLatin1Char('n')) |
| 341 | return QScriptGrammar::T_FUNCTION; |
| 342 | else if (c[0] == QLatin1Char('d') && c[1] == QLatin1Char('e') |
| 343 | && c[2] == QLatin1Char('b') && c[3] == QLatin1Char('u') |
| 344 | && c[4] == QLatin1Char('g') && c[5] == QLatin1Char('g') |
| 345 | && c[6] == QLatin1Char('e') && c[7] == QLatin1Char('r')) |
| 346 | return QScriptGrammar::T_DEBUGGER; |
| 347 | else if (check_reserved) { |
| 348 | if (c[0] == QLatin1Char('a') && c[1] == QLatin1Char('b') |
| 349 | && c[2] == QLatin1Char('s') && c[3] == QLatin1Char('t') |
| 350 | && c[4] == QLatin1Char('r') && c[5] == QLatin1Char('a') |
| 351 | && c[6] == QLatin1Char('c') && c[7] == QLatin1Char('t')) |
| 352 | return QScriptGrammar::T_RESERVED_WORD; |
| 353 | else if (c[0] == QLatin1Char('v') && c[1] == QLatin1Char('o') |
| 354 | && c[2] == QLatin1Char('l') && c[3] == QLatin1Char('a') |
| 355 | && c[4] == QLatin1Char('t') && c[5] == QLatin1Char('i') |
| 356 | && c[6] == QLatin1Char('l') && c[7] == QLatin1Char('e')) |
| 357 | return QScriptGrammar::T_RESERVED_WORD; |
| 358 | } |
| 359 | } break; |
| 360 | |
| 361 | case 9: { |
| 362 | if (check_reserved) { |
| 363 | if (c[0] == QLatin1Char('i') && c[1] == QLatin1Char('n') |
| 364 | && c[2] == QLatin1Char('t') && c[3] == QLatin1Char('e') |
| 365 | && c[4] == QLatin1Char('r') && c[5] == QLatin1Char('f') |
| 366 | && c[6] == QLatin1Char('a') && c[7] == QLatin1Char('c') |
| 367 | && c[8] == QLatin1Char('e')) |
| 368 | return QScriptGrammar::T_RESERVED_WORD; |
| 369 | else if (c[0] == QLatin1Char('t') && c[1] == QLatin1Char('r') |
| 370 | && c[2] == QLatin1Char('a') && c[3] == QLatin1Char('n') |
| 371 | && c[4] == QLatin1Char('s') && c[5] == QLatin1Char('i') |
| 372 | && c[6] == QLatin1Char('e') && c[7] == QLatin1Char('n') |
| 373 | && c[8] == QLatin1Char('t')) |
| 374 | return QScriptGrammar::T_RESERVED_WORD; |
| 375 | else if (c[0] == QLatin1Char('p') && c[1] == QLatin1Char('r') |
| 376 | && c[2] == QLatin1Char('o') && c[3] == QLatin1Char('t') |
| 377 | && c[4] == QLatin1Char('e') && c[5] == QLatin1Char('c') |
| 378 | && c[6] == QLatin1Char('t') && c[7] == QLatin1Char('e') |
| 379 | && c[8] == QLatin1Char('d')) |
| 380 | return QScriptGrammar::T_RESERVED_WORD; |
| 381 | } |
| 382 | } break; |
| 383 | |
| 384 | case 10: { |
| 385 | if (c[0] == QLatin1Char('i') && c[1] == QLatin1Char('n') |
| 386 | && c[2] == QLatin1Char('s') && c[3] == QLatin1Char('t') |
| 387 | && c[4] == QLatin1Char('a') && c[5] == QLatin1Char('n') |
| 388 | && c[6] == QLatin1Char('c') && c[7] == QLatin1Char('e') |
| 389 | && c[8] == QLatin1Char('o') && c[9] == QLatin1Char('f')) |
| 390 | return QScriptGrammar::T_INSTANCEOF; |
| 391 | else if (check_reserved) { |
| 392 | if (c[0] == QLatin1Char('i') && c[1] == QLatin1Char('m') |
| 393 | && c[2] == QLatin1Char('p') && c[3] == QLatin1Char('l') |
| 394 | && c[4] == QLatin1Char('e') && c[5] == QLatin1Char('m') |
| 395 | && c[6] == QLatin1Char('e') && c[7] == QLatin1Char('n') |
| 396 | && c[8] == QLatin1Char('t') && c[9] == QLatin1Char('s')) |
| 397 | return QScriptGrammar::T_RESERVED_WORD; |
| 398 | } |
| 399 | } break; |
| 400 | |
| 401 | case 12: { |
| 402 | if (check_reserved) { |
| 403 | if (c[0] == QLatin1Char('s') && c[1] == QLatin1Char('y') |
| 404 | && c[2] == QLatin1Char('n') && c[3] == QLatin1Char('c') |
| 405 | && c[4] == QLatin1Char('h') && c[5] == QLatin1Char('r') |
| 406 | && c[6] == QLatin1Char('o') && c[7] == QLatin1Char('n') |
| 407 | && c[8] == QLatin1Char('i') && c[9] == QLatin1Char('z') |
| 408 | && c[10] == QLatin1Char('e') && c[11] == QLatin1Char('d')) |
| 409 | return QScriptGrammar::T_RESERVED_WORD; |
| 410 | } |
| 411 | } break; |
| 412 | |
| 413 | } // switch |
| 414 | |
| 415 | return -1; |
| 416 | } |
| 417 | |
| 418 | int QScript::Lexer::lex() |
| 419 | { |
| 420 | int token = 0; |
| 421 | state = Start; |
| 422 | ushort stringType = 0; // either single or double quotes |
| 423 | pos8 = pos16 = 0; |
| 424 | done = false; |
| 425 | terminator = false; |
| 426 | |
| 427 | // did we push a token on the stack previously ? |
| 428 | // (after an automatic semicolon insertion) |
| 429 | if (stackToken >= 0) { |
| 430 | setDone(Other); |
| 431 | token = stackToken; |
| 432 | stackToken = -1; |
| 433 | } |
| 434 | |
| 435 | while (!done) { |
| 436 | switch (state) { |
| 437 | case Start: |
| 438 | if (isWhiteSpace()) { |
| 439 | // do nothing |
| 440 | } else if (current == '/' && next1 == '/') { |
| 441 | recordStartPos(); |
| 442 | shift(p: 1); |
| 443 | state = InSingleLineComment; |
| 444 | } else if (current == '/' && next1 == '*') { |
| 445 | recordStartPos(); |
| 446 | shift(p: 1); |
| 447 | state = InMultiLineComment; |
| 448 | } else if (current == 0) { |
| 449 | syncProhibitAutomaticSemicolon(); |
| 450 | if (!terminator && !delimited && !prohibitAutomaticSemicolon) { |
| 451 | // automatic semicolon insertion if program incomplete |
| 452 | token = QScriptGrammar::T_SEMICOLON; |
| 453 | stackToken = 0; |
| 454 | setDone(Other); |
| 455 | } else { |
| 456 | setDone(Eof); |
| 457 | } |
| 458 | } else if (isLineTerminator()) { |
| 459 | shiftWindowsLineBreak(); |
| 460 | yylineno++; |
| 461 | yycolumn = 0; |
| 462 | bol = true; |
| 463 | terminator = true; |
| 464 | syncProhibitAutomaticSemicolon(); |
| 465 | if (restrKeyword) { |
| 466 | token = QScriptGrammar::T_SEMICOLON; |
| 467 | setDone(Other); |
| 468 | } |
| 469 | } else if (current == '"' || current == '\'') { |
| 470 | recordStartPos(); |
| 471 | state = InString; |
| 472 | stringType = current; |
| 473 | } else if (isIdentLetter(c: current)) { |
| 474 | recordStartPos(); |
| 475 | record16(c: current); |
| 476 | state = InIdentifier; |
| 477 | } else if (current == '0') { |
| 478 | recordStartPos(); |
| 479 | record8(c: current); |
| 480 | state = InNum0; |
| 481 | } else if (isDecimalDigit(c: current)) { |
| 482 | recordStartPos(); |
| 483 | record8(c: current); |
| 484 | state = InNum; |
| 485 | } else if (current == '.' && isDecimalDigit(c: next1)) { |
| 486 | recordStartPos(); |
| 487 | record8(c: current); |
| 488 | state = InDecimal; |
| 489 | } else { |
| 490 | recordStartPos(); |
| 491 | token = matchPunctuator(c1: current, c2: next1, c3: next2, c4: next3); |
| 492 | if (token != -1) { |
| 493 | if (terminator && !delimited && !prohibitAutomaticSemicolon |
| 494 | && (token == QScriptGrammar::T_PLUS_PLUS |
| 495 | || token == QScriptGrammar::T_MINUS_MINUS)) { |
| 496 | // automatic semicolon insertion |
| 497 | stackToken = token; |
| 498 | token = QScriptGrammar::T_SEMICOLON; |
| 499 | } |
| 500 | setDone(Other); |
| 501 | } |
| 502 | else { |
| 503 | setDone(Bad); |
| 504 | err = IllegalCharacter; |
| 505 | errmsg = QLatin1String("Illegal character" ); |
| 506 | } |
| 507 | } |
| 508 | break; |
| 509 | case InString: |
| 510 | if (current == stringType) { |
| 511 | shift(p: 1); |
| 512 | setDone(String); |
| 513 | } else if (current == 0 || isLineTerminator()) { |
| 514 | setDone(Bad); |
| 515 | err = UnclosedStringLiteral; |
| 516 | errmsg = QLatin1String("Unclosed string at end of line" ); |
| 517 | } else if (current == '\\') { |
| 518 | state = InEscapeSequence; |
| 519 | } else { |
| 520 | record16(c: current); |
| 521 | } |
| 522 | break; |
| 523 | // Escape Sequences inside of strings |
| 524 | case InEscapeSequence: |
| 525 | if (isOctalDigit(c: current)) { |
| 526 | if (current >= '0' && current <= '3' && |
| 527 | isOctalDigit(c: next1) && isOctalDigit(c: next2)) { |
| 528 | record16(c: convertOctal(c1: current, c2: next1, c3: next2)); |
| 529 | shift(p: 2); |
| 530 | state = InString; |
| 531 | } else if (isOctalDigit(c: current) && |
| 532 | isOctalDigit(c: next1)) { |
| 533 | record16(c: convertOctal(c1: '0', c2: current, c3: next1)); |
| 534 | shift(p: 1); |
| 535 | state = InString; |
| 536 | } else if (isOctalDigit(c: current)) { |
| 537 | record16(c: convertOctal(c1: '0', c2: '0', c3: current)); |
| 538 | state = InString; |
| 539 | } else { |
| 540 | setDone(Bad); |
| 541 | err = IllegalEscapeSequence; |
| 542 | errmsg = QLatin1String("Illegal escape squence" ); |
| 543 | } |
| 544 | } else if (current == 'x') |
| 545 | state = InHexEscape; |
| 546 | else if (current == 'u') |
| 547 | state = InUnicodeEscape; |
| 548 | else { |
| 549 | if (isLineTerminator()) { |
| 550 | shiftWindowsLineBreak(); |
| 551 | yylineno++; |
| 552 | yycolumn = 0; |
| 553 | bol = true; |
| 554 | } else { |
| 555 | record16(c: singleEscape(c: current)); |
| 556 | } |
| 557 | state = InString; |
| 558 | } |
| 559 | break; |
| 560 | case InHexEscape: |
| 561 | if (isHexDigit(c: current) && isHexDigit(c: next1)) { |
| 562 | state = InString; |
| 563 | record16(c: QLatin1Char(convertHex(c1: current, c2: next1))); |
| 564 | shift(p: 1); |
| 565 | } else if (current == stringType) { |
| 566 | record16(c: QLatin1Char('x')); |
| 567 | shift(p: 1); |
| 568 | setDone(String); |
| 569 | } else { |
| 570 | record16(c: QLatin1Char('x')); |
| 571 | record16(c: current); |
| 572 | state = InString; |
| 573 | } |
| 574 | break; |
| 575 | case InUnicodeEscape: |
| 576 | if (isHexDigit(c: current) && isHexDigit(c: next1) && |
| 577 | isHexDigit(c: next2) && isHexDigit(c: next3)) { |
| 578 | record16(c: convertUnicode(c1: current, c2: next1, c3: next2, c4: next3)); |
| 579 | shift(p: 3); |
| 580 | state = InString; |
| 581 | } else if (current == stringType) { |
| 582 | record16(c: QLatin1Char('u')); |
| 583 | shift(p: 1); |
| 584 | setDone(String); |
| 585 | } else { |
| 586 | setDone(Bad); |
| 587 | err = IllegalUnicodeEscapeSequence; |
| 588 | errmsg = QLatin1String("Illegal unicode escape sequence" ); |
| 589 | } |
| 590 | break; |
| 591 | case InSingleLineComment: |
| 592 | if (isLineTerminator()) { |
| 593 | shiftWindowsLineBreak(); |
| 594 | yylineno++; |
| 595 | yycolumn = 0; |
| 596 | terminator = true; |
| 597 | bol = true; |
| 598 | if (restrKeyword) { |
| 599 | token = QScriptGrammar::T_SEMICOLON; |
| 600 | setDone(Other); |
| 601 | } else |
| 602 | state = Start; |
| 603 | } else if (current == 0) { |
| 604 | setDone(Eof); |
| 605 | } |
| 606 | break; |
| 607 | case InMultiLineComment: |
| 608 | if (current == 0) { |
| 609 | setDone(Bad); |
| 610 | err = UnclosedComment; |
| 611 | errmsg = QLatin1String("Unclosed comment at end of file" ); |
| 612 | } else if (isLineTerminator()) { |
| 613 | shiftWindowsLineBreak(); |
| 614 | yylineno++; |
| 615 | } else if (current == '*' && next1 == '/') { |
| 616 | state = Start; |
| 617 | shift(p: 1); |
| 618 | } |
| 619 | break; |
| 620 | case InIdentifier: |
| 621 | if (isIdentLetter(c: current) || isDecimalDigit(c: current)) { |
| 622 | record16(c: current); |
| 623 | break; |
| 624 | } |
| 625 | setDone(Identifier); |
| 626 | break; |
| 627 | case InNum0: |
| 628 | if (current == 'x' || current == 'X') { |
| 629 | record8(c: current); |
| 630 | state = InHex; |
| 631 | } else if (current == '.') { |
| 632 | record8(c: current); |
| 633 | state = InDecimal; |
| 634 | } else if (current == 'e' || current == 'E') { |
| 635 | record8(c: current); |
| 636 | state = InExponentIndicator; |
| 637 | } else if (isOctalDigit(c: current)) { |
| 638 | record8(c: current); |
| 639 | state = InOctal; |
| 640 | } else if (isDecimalDigit(c: current)) { |
| 641 | record8(c: current); |
| 642 | state = InDecimal; |
| 643 | } else { |
| 644 | setDone(Number); |
| 645 | } |
| 646 | break; |
| 647 | case InHex: |
| 648 | if (isHexDigit(c: current)) |
| 649 | record8(c: current); |
| 650 | else |
| 651 | setDone(Hex); |
| 652 | break; |
| 653 | case InOctal: |
| 654 | if (isOctalDigit(c: current)) { |
| 655 | record8(c: current); |
| 656 | } else if (isDecimalDigit(c: current)) { |
| 657 | record8(c: current); |
| 658 | state = InDecimal; |
| 659 | } else { |
| 660 | setDone(Octal); |
| 661 | } |
| 662 | break; |
| 663 | case InNum: |
| 664 | if (isDecimalDigit(c: current)) { |
| 665 | record8(c: current); |
| 666 | } else if (current == '.') { |
| 667 | record8(c: current); |
| 668 | state = InDecimal; |
| 669 | } else if (current == 'e' || current == 'E') { |
| 670 | record8(c: current); |
| 671 | state = InExponentIndicator; |
| 672 | } else { |
| 673 | setDone(Number); |
| 674 | } |
| 675 | break; |
| 676 | case InDecimal: |
| 677 | if (isDecimalDigit(c: current)) { |
| 678 | record8(c: current); |
| 679 | } else if (current == 'e' || current == 'E') { |
| 680 | record8(c: current); |
| 681 | state = InExponentIndicator; |
| 682 | } else { |
| 683 | setDone(Number); |
| 684 | } |
| 685 | break; |
| 686 | case InExponentIndicator: |
| 687 | if (current == '+' || current == '-') { |
| 688 | record8(c: current); |
| 689 | } else if (isDecimalDigit(c: current)) { |
| 690 | record8(c: current); |
| 691 | state = InExponent; |
| 692 | } else { |
| 693 | setDone(Bad); |
| 694 | err = IllegalExponentIndicator; |
| 695 | errmsg = QLatin1String("Illegal syntax for exponential number" ); |
| 696 | } |
| 697 | break; |
| 698 | case InExponent: |
| 699 | if (isDecimalDigit(c: current)) { |
| 700 | record8(c: current); |
| 701 | } else { |
| 702 | setDone(Number); |
| 703 | } |
| 704 | break; |
| 705 | default: |
| 706 | Q_ASSERT_X(0, "Lexer::lex" , "Unhandled state in switch statement" ); |
| 707 | } |
| 708 | |
| 709 | // move on to the next character |
| 710 | if (!done) |
| 711 | shift(p: 1); |
| 712 | if (state != Start && state != InSingleLineComment) |
| 713 | bol = false; |
| 714 | } |
| 715 | |
| 716 | // no identifiers allowed directly after numeric literal, e.g. "3in" is bad |
| 717 | if ((state == Number || state == Octal || state == Hex) |
| 718 | && isIdentLetter(c: current)) { |
| 719 | state = Bad; |
| 720 | err = IllegalIdentifier; |
| 721 | errmsg = QLatin1String("Identifier cannot start with numeric literal" ); |
| 722 | } |
| 723 | |
| 724 | // terminate string |
| 725 | buffer8[pos8] = '\0'; |
| 726 | |
| 727 | double dval = 0; |
| 728 | if (state == Number) { |
| 729 | dval = QByteArray::fromRawData(buffer8, size: pos8).toDouble(); |
| 730 | } else if (state == Hex) { // scan hex numbers |
| 731 | dval = QScript::integerFromString(buf: buffer8, size: pos8, radix: 16); |
| 732 | state = Number; |
| 733 | } else if (state == Octal) { // scan octal number |
| 734 | dval = QScript::integerFromString(buf: buffer8, size: pos8, radix: 8); |
| 735 | state = Number; |
| 736 | } |
| 737 | |
| 738 | restrKeyword = false; |
| 739 | delimited = false; |
| 740 | |
| 741 | switch (parenthesesState) { |
| 742 | case IgnoreParentheses: |
| 743 | break; |
| 744 | case CountParentheses: |
| 745 | if (token == QScriptGrammar::T_RPAREN) { |
| 746 | --parenthesesCount; |
| 747 | if (parenthesesCount == 0) |
| 748 | parenthesesState = BalancedParentheses; |
| 749 | } else if (token == QScriptGrammar::T_LPAREN) { |
| 750 | ++parenthesesCount; |
| 751 | } |
| 752 | break; |
| 753 | case BalancedParentheses: |
| 754 | parenthesesState = IgnoreParentheses; |
| 755 | break; |
| 756 | } |
| 757 | |
| 758 | switch (state) { |
| 759 | case Eof: |
| 760 | return 0; |
| 761 | case Other: |
| 762 | if(token == QScriptGrammar::T_RBRACE || token == QScriptGrammar::T_SEMICOLON) |
| 763 | delimited = true; |
| 764 | return token; |
| 765 | case Identifier: |
| 766 | if ((token = findReservedWord(c: buffer16, size: pos16)) < 0) { |
| 767 | /* TODO: close leak on parse error. same holds true for String */ |
| 768 | if (driver) { |
| 769 | Q_ASSERT_X(false, Q_FUNC_INFO, "not implemented" ); |
| 770 | qsyylval.ustr = 0; // driver->intern(buffer16, pos16); |
| 771 | } else |
| 772 | qsyylval.ustr = 0; |
| 773 | return QScriptGrammar::T_IDENTIFIER; |
| 774 | } |
| 775 | if (token == QScriptGrammar::T_CONTINUE || token == QScriptGrammar::T_BREAK |
| 776 | || token == QScriptGrammar::T_RETURN || token == QScriptGrammar::T_THROW) { |
| 777 | restrKeyword = true; |
| 778 | } else if (token == QScriptGrammar::T_IF || token == QScriptGrammar::T_FOR |
| 779 | || token == QScriptGrammar::T_WHILE || token == QScriptGrammar::T_WITH) { |
| 780 | parenthesesState = CountParentheses; |
| 781 | parenthesesCount = 0; |
| 782 | } else if (token == QScriptGrammar::T_DO) { |
| 783 | parenthesesState = BalancedParentheses; |
| 784 | } |
| 785 | return token; |
| 786 | case String: |
| 787 | if (driver) { |
| 788 | Q_ASSERT_X(false, Q_FUNC_INFO, "not implemented" ); |
| 789 | qsyylval.ustr = 0; // driver->intern(buffer16, pos16); |
| 790 | } else |
| 791 | qsyylval.ustr = 0; |
| 792 | return QScriptGrammar::T_STRING_LITERAL; |
| 793 | case Number: |
| 794 | qsyylval.dval = dval; |
| 795 | return QScriptGrammar::T_NUMERIC_LITERAL; |
| 796 | case Bad: |
| 797 | return -1; |
| 798 | default: |
| 799 | Q_ASSERT(!"unhandled numeration value in switch" ); |
| 800 | return -1; |
| 801 | } |
| 802 | } |
| 803 | |
| 804 | bool QScript::Lexer::isWhiteSpace() const |
| 805 | { |
| 806 | return (current == ' ' || current == '\t' || |
| 807 | current == 0x0b || current == 0x0c); |
| 808 | } |
| 809 | |
| 810 | bool QScript::Lexer::isLineTerminator() const |
| 811 | { |
| 812 | return (current == '\n' || current == '\r'); |
| 813 | } |
| 814 | |
| 815 | bool QScript::Lexer::isIdentLetter(ushort c) |
| 816 | { |
| 817 | /* TODO: allow other legitimate unicode chars */ |
| 818 | return ((c >= 'a' && c <= 'z') |
| 819 | || (c >= 'A' && c <= 'Z') |
| 820 | || c == '$' |
| 821 | || c == '_'); |
| 822 | } |
| 823 | |
| 824 | bool QScript::Lexer::isDecimalDigit(ushort c) |
| 825 | { |
| 826 | return (c >= '0' && c <= '9'); |
| 827 | } |
| 828 | |
| 829 | bool QScript::Lexer::isHexDigit(ushort c) const |
| 830 | { |
| 831 | return ((c >= '0' && c <= '9') |
| 832 | || (c >= 'a' && c <= 'f') |
| 833 | || (c >= 'A' && c <= 'F')); |
| 834 | } |
| 835 | |
| 836 | bool QScript::Lexer::isOctalDigit(ushort c) const |
| 837 | { |
| 838 | return (c >= '0' && c <= '7'); |
| 839 | } |
| 840 | |
| 841 | int QScript::Lexer::matchPunctuator(ushort c1, ushort c2, |
| 842 | ushort c3, ushort c4) |
| 843 | { |
| 844 | if (c1 == '>' && c2 == '>' && c3 == '>' && c4 == '=') { |
| 845 | shift(p: 4); |
| 846 | return QScriptGrammar::T_GT_GT_GT_EQ; |
| 847 | } else if (c1 == '=' && c2 == '=' && c3 == '=') { |
| 848 | shift(p: 3); |
| 849 | return QScriptGrammar::T_EQ_EQ_EQ; |
| 850 | } else if (c1 == '!' && c2 == '=' && c3 == '=') { |
| 851 | shift(p: 3); |
| 852 | return QScriptGrammar::T_NOT_EQ_EQ; |
| 853 | } else if (c1 == '>' && c2 == '>' && c3 == '>') { |
| 854 | shift(p: 3); |
| 855 | return QScriptGrammar::T_GT_GT_GT; |
| 856 | } else if (c1 == '<' && c2 == '<' && c3 == '=') { |
| 857 | shift(p: 3); |
| 858 | return QScriptGrammar::T_LT_LT_EQ; |
| 859 | } else if (c1 == '>' && c2 == '>' && c3 == '=') { |
| 860 | shift(p: 3); |
| 861 | return QScriptGrammar::T_GT_GT_EQ; |
| 862 | } else if (c1 == '<' && c2 == '=') { |
| 863 | shift(p: 2); |
| 864 | return QScriptGrammar::T_LE; |
| 865 | } else if (c1 == '>' && c2 == '=') { |
| 866 | shift(p: 2); |
| 867 | return QScriptGrammar::T_GE; |
| 868 | } else if (c1 == '!' && c2 == '=') { |
| 869 | shift(p: 2); |
| 870 | return QScriptGrammar::T_NOT_EQ; |
| 871 | } else if (c1 == '+' && c2 == '+') { |
| 872 | shift(p: 2); |
| 873 | return QScriptGrammar::T_PLUS_PLUS; |
| 874 | } else if (c1 == '-' && c2 == '-') { |
| 875 | shift(p: 2); |
| 876 | return QScriptGrammar::T_MINUS_MINUS; |
| 877 | } else if (c1 == '=' && c2 == '=') { |
| 878 | shift(p: 2); |
| 879 | return QScriptGrammar::T_EQ_EQ; |
| 880 | } else if (c1 == '+' && c2 == '=') { |
| 881 | shift(p: 2); |
| 882 | return QScriptGrammar::T_PLUS_EQ; |
| 883 | } else if (c1 == '-' && c2 == '=') { |
| 884 | shift(p: 2); |
| 885 | return QScriptGrammar::T_MINUS_EQ; |
| 886 | } else if (c1 == '*' && c2 == '=') { |
| 887 | shift(p: 2); |
| 888 | return QScriptGrammar::T_STAR_EQ; |
| 889 | } else if (c1 == '/' && c2 == '=') { |
| 890 | shift(p: 2); |
| 891 | return QScriptGrammar::T_DIVIDE_EQ; |
| 892 | } else if (c1 == '&' && c2 == '=') { |
| 893 | shift(p: 2); |
| 894 | return QScriptGrammar::T_AND_EQ; |
| 895 | } else if (c1 == '^' && c2 == '=') { |
| 896 | shift(p: 2); |
| 897 | return QScriptGrammar::T_XOR_EQ; |
| 898 | } else if (c1 == '%' && c2 == '=') { |
| 899 | shift(p: 2); |
| 900 | return QScriptGrammar::T_REMAINDER_EQ; |
| 901 | } else if (c1 == '|' && c2 == '=') { |
| 902 | shift(p: 2); |
| 903 | return QScriptGrammar::T_OR_EQ; |
| 904 | } else if (c1 == '<' && c2 == '<') { |
| 905 | shift(p: 2); |
| 906 | return QScriptGrammar::T_LT_LT; |
| 907 | } else if (c1 == '>' && c2 == '>') { |
| 908 | shift(p: 2); |
| 909 | return QScriptGrammar::T_GT_GT; |
| 910 | } else if (c1 == '&' && c2 == '&') { |
| 911 | shift(p: 2); |
| 912 | return QScriptGrammar::T_AND_AND; |
| 913 | } else if (c1 == '|' && c2 == '|') { |
| 914 | shift(p: 2); |
| 915 | return QScriptGrammar::T_OR_OR; |
| 916 | } |
| 917 | |
| 918 | switch(c1) { |
| 919 | case '=': shift(p: 1); return QScriptGrammar::T_EQ; |
| 920 | case '>': shift(p: 1); return QScriptGrammar::T_GT; |
| 921 | case '<': shift(p: 1); return QScriptGrammar::T_LT; |
| 922 | case ',': shift(p: 1); return QScriptGrammar::T_COMMA; |
| 923 | case '!': shift(p: 1); return QScriptGrammar::T_NOT; |
| 924 | case '~': shift(p: 1); return QScriptGrammar::T_TILDE; |
| 925 | case '?': shift(p: 1); return QScriptGrammar::T_QUESTION; |
| 926 | case ':': shift(p: 1); return QScriptGrammar::T_COLON; |
| 927 | case '.': shift(p: 1); return QScriptGrammar::T_DOT; |
| 928 | case '+': shift(p: 1); return QScriptGrammar::T_PLUS; |
| 929 | case '-': shift(p: 1); return QScriptGrammar::T_MINUS; |
| 930 | case '*': shift(p: 1); return QScriptGrammar::T_STAR; |
| 931 | case '/': shift(p: 1); return QScriptGrammar::T_DIVIDE_; |
| 932 | case '&': shift(p: 1); return QScriptGrammar::T_AND; |
| 933 | case '|': shift(p: 1); return QScriptGrammar::T_OR; |
| 934 | case '^': shift(p: 1); return QScriptGrammar::T_XOR; |
| 935 | case '%': shift(p: 1); return QScriptGrammar::T_REMAINDER; |
| 936 | case '(': shift(p: 1); return QScriptGrammar::T_LPAREN; |
| 937 | case ')': shift(p: 1); return QScriptGrammar::T_RPAREN; |
| 938 | case '{': shift(p: 1); return QScriptGrammar::T_LBRACE; |
| 939 | case '}': shift(p: 1); return QScriptGrammar::T_RBRACE; |
| 940 | case '[': shift(p: 1); return QScriptGrammar::T_LBRACKET; |
| 941 | case ']': shift(p: 1); return QScriptGrammar::T_RBRACKET; |
| 942 | case ';': shift(p: 1); return QScriptGrammar::T_SEMICOLON; |
| 943 | |
| 944 | default: return -1; |
| 945 | } |
| 946 | } |
| 947 | |
| 948 | ushort QScript::Lexer::singleEscape(ushort c) const |
| 949 | { |
| 950 | switch(c) { |
| 951 | case 'b': |
| 952 | return 0x08; |
| 953 | case 't': |
| 954 | return 0x09; |
| 955 | case 'n': |
| 956 | return 0x0A; |
| 957 | case 'v': |
| 958 | return 0x0B; |
| 959 | case 'f': |
| 960 | return 0x0C; |
| 961 | case 'r': |
| 962 | return 0x0D; |
| 963 | case '"': |
| 964 | return 0x22; |
| 965 | case '\'': |
| 966 | return 0x27; |
| 967 | case '\\': |
| 968 | return 0x5C; |
| 969 | default: |
| 970 | return c; |
| 971 | } |
| 972 | } |
| 973 | |
| 974 | ushort QScript::Lexer::convertOctal(ushort c1, ushort c2, |
| 975 | ushort c3) const |
| 976 | { |
| 977 | return ((c1 - '0') * 64 + (c2 - '0') * 8 + c3 - '0'); |
| 978 | } |
| 979 | |
| 980 | unsigned char QScript::Lexer::convertHex(ushort c) |
| 981 | { |
| 982 | if (c >= '0' && c <= '9') |
| 983 | return (c - '0'); |
| 984 | else if (c >= 'a' && c <= 'f') |
| 985 | return (c - 'a' + 10); |
| 986 | else |
| 987 | return (c - 'A' + 10); |
| 988 | } |
| 989 | |
| 990 | unsigned char QScript::Lexer::convertHex(ushort c1, ushort c2) |
| 991 | { |
| 992 | return ((convertHex(c: c1) << 4) + convertHex(c: c2)); |
| 993 | } |
| 994 | |
| 995 | QChar QScript::Lexer::convertUnicode(ushort c1, ushort c2, |
| 996 | ushort c3, ushort c4) |
| 997 | { |
| 998 | return QChar((convertHex(c: c3) << 4) + convertHex(c: c4), |
| 999 | (convertHex(c: c1) << 4) + convertHex(c: c2)); |
| 1000 | } |
| 1001 | |
| 1002 | void QScript::Lexer::record8(ushort c) |
| 1003 | { |
| 1004 | Q_ASSERT(c <= 0xff); |
| 1005 | |
| 1006 | // enlarge buffer if full |
| 1007 | if (pos8 >= size8 - 1) { |
| 1008 | char *tmp = new char[2 * size8]; |
| 1009 | memcpy(dest: tmp, src: buffer8, n: size8 * sizeof(char)); |
| 1010 | delete [] buffer8; |
| 1011 | buffer8 = tmp; |
| 1012 | size8 *= 2; |
| 1013 | } |
| 1014 | |
| 1015 | buffer8[pos8++] = (char) c; |
| 1016 | } |
| 1017 | |
| 1018 | void QScript::Lexer::record16(QChar c) |
| 1019 | { |
| 1020 | // enlarge buffer if full |
| 1021 | if (pos16 >= size16 - 1) { |
| 1022 | QChar *tmp = new QChar[2 * size16]; |
| 1023 | memcpy(dest: tmp, src: buffer16, n: size16 * sizeof(QChar)); |
| 1024 | delete [] buffer16; |
| 1025 | buffer16 = tmp; |
| 1026 | size16 *= 2; |
| 1027 | } |
| 1028 | |
| 1029 | buffer16[pos16++] = c; |
| 1030 | } |
| 1031 | |
| 1032 | void QScript::Lexer::recordStartPos() |
| 1033 | { |
| 1034 | startlineno = yylineno; |
| 1035 | startcolumn = yycolumn; |
| 1036 | } |
| 1037 | |
| 1038 | bool QScript::Lexer::scanRegExp(RegExpBodyPrefix prefix) |
| 1039 | { |
| 1040 | pos16 = 0; |
| 1041 | bool lastWasEscape = false; |
| 1042 | |
| 1043 | if (prefix == EqualPrefix) |
| 1044 | record16(c: QLatin1Char('=')); |
| 1045 | |
| 1046 | while (1) { |
| 1047 | if (isLineTerminator() || current == 0) { |
| 1048 | errmsg = QLatin1String("Unterminated regular expression literal" ); |
| 1049 | return false; |
| 1050 | } |
| 1051 | else if (current != '/' || lastWasEscape == true) |
| 1052 | { |
| 1053 | record16(c: current); |
| 1054 | lastWasEscape = !lastWasEscape && (current == '\\'); |
| 1055 | } |
| 1056 | else { |
| 1057 | if (driver) { |
| 1058 | Q_ASSERT_X(false, Q_FUNC_INFO, "not implemented" ); |
| 1059 | pattern = 0; // driver->intern(buffer16, pos16); |
| 1060 | } else |
| 1061 | pattern = 0; |
| 1062 | pos16 = 0; |
| 1063 | shift(p: 1); |
| 1064 | break; |
| 1065 | } |
| 1066 | shift(p: 1); |
| 1067 | } |
| 1068 | |
| 1069 | flags = 0; |
| 1070 | while (isIdentLetter(c: current)) { |
| 1071 | // current version was remade from this line: |
| 1072 | //int flag = QScript::Ecma::RegExp::flagFromChar(current); |
| 1073 | //code was "inlined" because it was only one call to this function |
| 1074 | int flag; |
| 1075 | switch (current) { |
| 1076 | case 'g': flag = 0x01; break; |
| 1077 | case 'm': flag = 0x02; break; |
| 1078 | case 'i': flag = 0x04; break; |
| 1079 | default: flag = 0; |
| 1080 | } |
| 1081 | if (flag == 0) { |
| 1082 | errmsg = QString::fromLatin1(str: "Invalid regular expression flag '%0'" ) |
| 1083 | .arg(a: QChar(current)); |
| 1084 | return false; |
| 1085 | } |
| 1086 | flags |= flag; |
| 1087 | record16(c: current); |
| 1088 | shift(p: 1); |
| 1089 | } |
| 1090 | |
| 1091 | return true; |
| 1092 | } |
| 1093 | |
| 1094 | void QScript::Lexer::syncProhibitAutomaticSemicolon() |
| 1095 | { |
| 1096 | if (parenthesesState == BalancedParentheses) { |
| 1097 | // we have seen something like "if (foo)", which means we should |
| 1098 | // never insert an automatic semicolon at this point, since it would |
| 1099 | // then be expanded into an empty statement (ECMA-262 7.9.1) |
| 1100 | prohibitAutomaticSemicolon = true; |
| 1101 | parenthesesState = IgnoreParentheses; |
| 1102 | } else { |
| 1103 | prohibitAutomaticSemicolon = false; |
| 1104 | } |
| 1105 | } |
| 1106 | |
| 1107 | QT_END_NAMESPACE |
| 1108 | |