[556] | 1 | /****************************************************************************
|
---|
| 2 | **
|
---|
[846] | 3 | ** Copyright (C) 2011 Nokia Corporation and/or its subsidiary(-ies).
|
---|
[556] | 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 | ** $QT_BEGIN_LICENSE:LGPL-ONLY$
|
---|
| 10 | ** GNU Lesser General Public License Usage
|
---|
| 11 | ** This file may be used under the terms of the GNU Lesser
|
---|
| 12 | ** General Public License version 2.1 as published by the Free Software
|
---|
| 13 | ** Foundation and appearing in the file LICENSE.LGPL included in the
|
---|
| 14 | ** packaging of this file. Please review the following information to
|
---|
| 15 | ** ensure the GNU Lesser General Public License version 2.1 requirements
|
---|
| 16 | ** will be met: http://www.gnu.org/licenses/old-licenses/lgpl-2.1.html.
|
---|
| 17 | **
|
---|
| 18 | ** If you have questions regarding the use of this file, please contact
|
---|
| 19 | ** Nokia at qt-info@nokia.com.
|
---|
| 20 | ** $QT_END_LICENSE$
|
---|
| 21 | **
|
---|
| 22 | ****************************************************************************/
|
---|
| 23 |
|
---|
| 24 | #include "qscriptlexer_p.h"
|
---|
| 25 |
|
---|
| 26 | #include "qscriptgrammar_p.h"
|
---|
| 27 | #include <ctype.h>
|
---|
| 28 | #include <stdlib.h>
|
---|
| 29 | #include <stdio.h>
|
---|
| 30 | #include <string.h>
|
---|
| 31 |
|
---|
| 32 | QT_BEGIN_NAMESPACE
|
---|
| 33 |
|
---|
[846] | 34 | Q_CORE_EXPORT double qstrtod(const char *s00, char const **se, bool *ok);
|
---|
[556] | 35 |
|
---|
| 36 | #define shiftWindowsLineBreak() \
|
---|
| 37 | do { \
|
---|
| 38 | if (((current == '\r') && (next1 == '\n')) \
|
---|
| 39 | || ((current == '\n') && (next1 == '\r'))) { \
|
---|
| 40 | shift(1); \
|
---|
| 41 | } \
|
---|
| 42 | } \
|
---|
| 43 | while (0)
|
---|
| 44 |
|
---|
| 45 | typedef double qsreal; // ###
|
---|
| 46 |
|
---|
| 47 | namespace QScript {
|
---|
| 48 | extern qsreal integerFromString(const char *buf, int size, int radix);
|
---|
| 49 | }
|
---|
| 50 |
|
---|
| 51 | QScript::Lexer::Lexer(QScriptEnginePrivate *eng)
|
---|
| 52 | : driver(eng),
|
---|
| 53 | yylineno(0),
|
---|
| 54 | size8(128), size16(128), restrKeyword(false),
|
---|
| 55 | stackToken(-1), pos(0),
|
---|
| 56 | code(0), length(0),
|
---|
| 57 | bol(true),
|
---|
| 58 | current(0), next1(0), next2(0), next3(0),
|
---|
| 59 | err(NoError),
|
---|
| 60 | check_reserved(true),
|
---|
| 61 | parenthesesState(IgnoreParentheses),
|
---|
| 62 | prohibitAutomaticSemicolon(false)
|
---|
| 63 | {
|
---|
| 64 | // allocate space for read buffers
|
---|
| 65 | buffer8 = new char[size8];
|
---|
| 66 | buffer16 = new QChar[size16];
|
---|
| 67 | pattern = 0;
|
---|
| 68 | flags = 0;
|
---|
| 69 |
|
---|
| 70 | }
|
---|
| 71 |
|
---|
| 72 | QScript::Lexer::~Lexer()
|
---|
| 73 | {
|
---|
| 74 | delete [] buffer8;
|
---|
| 75 | delete [] buffer16;
|
---|
| 76 | }
|
---|
| 77 |
|
---|
| 78 | void QScript::Lexer::setCode(const QString &c, int lineno)
|
---|
| 79 | {
|
---|
| 80 | errmsg = QString();
|
---|
| 81 | yylineno = lineno;
|
---|
| 82 | yycolumn = 1;
|
---|
| 83 | restrKeyword = false;
|
---|
| 84 | delimited = false;
|
---|
| 85 | stackToken = -1;
|
---|
| 86 | pos = 0;
|
---|
| 87 | code = c.unicode();
|
---|
| 88 | length = c.length();
|
---|
| 89 | bol = true;
|
---|
| 90 |
|
---|
| 91 | // read first characters
|
---|
| 92 | current = (length > 0) ? code[0].unicode() : 0;
|
---|
| 93 | next1 = (length > 1) ? code[1].unicode() : 0;
|
---|
| 94 | next2 = (length > 2) ? code[2].unicode() : 0;
|
---|
| 95 | next3 = (length > 3) ? code[3].unicode() : 0;
|
---|
| 96 | }
|
---|
| 97 |
|
---|
| 98 | void QScript::Lexer::shift(uint p)
|
---|
| 99 | {
|
---|
| 100 | while (p--) {
|
---|
| 101 | ++pos;
|
---|
| 102 | ++yycolumn;
|
---|
| 103 | current = next1;
|
---|
| 104 | next1 = next2;
|
---|
| 105 | next2 = next3;
|
---|
| 106 | next3 = (pos + 3 < length) ? code[pos+3].unicode() : 0;
|
---|
| 107 | }
|
---|
| 108 | }
|
---|
| 109 |
|
---|
| 110 | void QScript::Lexer::setDone(State s)
|
---|
| 111 | {
|
---|
| 112 | state = s;
|
---|
| 113 | done = true;
|
---|
| 114 | }
|
---|
| 115 |
|
---|
| 116 | int QScript::Lexer::findReservedWord(const QChar *c, int size) const
|
---|
| 117 | {
|
---|
| 118 | switch (size) {
|
---|
| 119 | case 2: {
|
---|
| 120 | if (c[0] == QLatin1Char('d') && c[1] == QLatin1Char('o'))
|
---|
| 121 | return QScriptGrammar::T_DO;
|
---|
| 122 | else if (c[0] == QLatin1Char('i') && c[1] == QLatin1Char('f'))
|
---|
| 123 | return QScriptGrammar::T_IF;
|
---|
| 124 | else if (c[0] == QLatin1Char('i') && c[1] == QLatin1Char('n'))
|
---|
| 125 | return QScriptGrammar::T_IN;
|
---|
| 126 | } break;
|
---|
| 127 |
|
---|
| 128 | case 3: {
|
---|
| 129 | if (c[0] == QLatin1Char('f') && c[1] == QLatin1Char('o') && c[2] == QLatin1Char('r'))
|
---|
| 130 | return QScriptGrammar::T_FOR;
|
---|
| 131 | else if (c[0] == QLatin1Char('n') && c[1] == QLatin1Char('e') && c[2] == QLatin1Char('w'))
|
---|
| 132 | return QScriptGrammar::T_NEW;
|
---|
| 133 | else if (c[0] == QLatin1Char('t') && c[1] == QLatin1Char('r') && c[2] == QLatin1Char('y'))
|
---|
| 134 | return QScriptGrammar::T_TRY;
|
---|
| 135 | else if (c[0] == QLatin1Char('v') && c[1] == QLatin1Char('a') && c[2] == QLatin1Char('r'))
|
---|
| 136 | return QScriptGrammar::T_VAR;
|
---|
| 137 | else if (check_reserved) {
|
---|
| 138 | if (c[0] == QLatin1Char('i') && c[1] == QLatin1Char('n') && c[2] == QLatin1Char('t'))
|
---|
| 139 | return QScriptGrammar::T_RESERVED_WORD;
|
---|
| 140 | }
|
---|
| 141 | } break;
|
---|
| 142 |
|
---|
| 143 | case 4: {
|
---|
| 144 | if (c[0] == QLatin1Char('c') && c[1] == QLatin1Char('a')
|
---|
| 145 | && c[2] == QLatin1Char('s') && c[3] == QLatin1Char('e'))
|
---|
| 146 | return QScriptGrammar::T_CASE;
|
---|
| 147 | else if (c[0] == QLatin1Char('e') && c[1] == QLatin1Char('l')
|
---|
| 148 | && c[2] == QLatin1Char('s') && c[3] == QLatin1Char('e'))
|
---|
| 149 | return QScriptGrammar::T_ELSE;
|
---|
| 150 | else if (c[0] == QLatin1Char('t') && c[1] == QLatin1Char('h')
|
---|
| 151 | && c[2] == QLatin1Char('i') && c[3] == QLatin1Char('s'))
|
---|
| 152 | return QScriptGrammar::T_THIS;
|
---|
| 153 | else if (c[0] == QLatin1Char('v') && c[1] == QLatin1Char('o')
|
---|
| 154 | && c[2] == QLatin1Char('i') && c[3] == QLatin1Char('d'))
|
---|
| 155 | return QScriptGrammar::T_VOID;
|
---|
| 156 | else if (c[0] == QLatin1Char('w') && c[1] == QLatin1Char('i')
|
---|
| 157 | && c[2] == QLatin1Char('t') && c[3] == QLatin1Char('h'))
|
---|
| 158 | return QScriptGrammar::T_WITH;
|
---|
| 159 | else if (c[0] == QLatin1Char('t') && c[1] == QLatin1Char('r')
|
---|
| 160 | && c[2] == QLatin1Char('u') && c[3] == QLatin1Char('e'))
|
---|
| 161 | return QScriptGrammar::T_TRUE;
|
---|
| 162 | else if (c[0] == QLatin1Char('n') && c[1] == QLatin1Char('u')
|
---|
| 163 | && c[2] == QLatin1Char('l') && c[3] == QLatin1Char('l'))
|
---|
| 164 | return QScriptGrammar::T_NULL;
|
---|
| 165 | else if (check_reserved) {
|
---|
| 166 | if (c[0] == QLatin1Char('e') && c[1] == QLatin1Char('n')
|
---|
| 167 | && c[2] == QLatin1Char('u') && c[3] == QLatin1Char('m'))
|
---|
| 168 | return QScriptGrammar::T_RESERVED_WORD;
|
---|
| 169 | else if (c[0] == QLatin1Char('b') && c[1] == QLatin1Char('y')
|
---|
| 170 | && c[2] == QLatin1Char('t') && c[3] == QLatin1Char('e'))
|
---|
| 171 | return QScriptGrammar::T_RESERVED_WORD;
|
---|
| 172 | else if (c[0] == QLatin1Char('l') && c[1] == QLatin1Char('o')
|
---|
| 173 | && c[2] == QLatin1Char('n') && c[3] == QLatin1Char('g'))
|
---|
| 174 | return QScriptGrammar::T_RESERVED_WORD;
|
---|
| 175 | else if (c[0] == QLatin1Char('c') && c[1] == QLatin1Char('h')
|
---|
| 176 | && c[2] == QLatin1Char('a') && c[3] == QLatin1Char('r'))
|
---|
| 177 | return QScriptGrammar::T_RESERVED_WORD;
|
---|
| 178 | else if (c[0] == QLatin1Char('g') && c[1] == QLatin1Char('o')
|
---|
| 179 | && c[2] == QLatin1Char('t') && c[3] == QLatin1Char('o'))
|
---|
| 180 | return QScriptGrammar::T_RESERVED_WORD;
|
---|
| 181 | }
|
---|
| 182 | } break;
|
---|
| 183 |
|
---|
| 184 | case 5: {
|
---|
| 185 | if (c[0] == QLatin1Char('b') && c[1] == QLatin1Char('r')
|
---|
| 186 | && c[2] == QLatin1Char('e') && c[3] == QLatin1Char('a')
|
---|
| 187 | && c[4] == QLatin1Char('k'))
|
---|
| 188 | return QScriptGrammar::T_BREAK;
|
---|
| 189 | else if (c[0] == QLatin1Char('c') && c[1] == QLatin1Char('a')
|
---|
| 190 | && c[2] == QLatin1Char('t') && c[3] == QLatin1Char('c')
|
---|
| 191 | && c[4] == QLatin1Char('h'))
|
---|
| 192 | return QScriptGrammar::T_CATCH;
|
---|
| 193 | else if (c[0] == QLatin1Char('t') && c[1] == QLatin1Char('h')
|
---|
| 194 | && c[2] == QLatin1Char('r') && c[3] == QLatin1Char('o')
|
---|
| 195 | && c[4] == QLatin1Char('w'))
|
---|
| 196 | return QScriptGrammar::T_THROW;
|
---|
| 197 | else if (c[0] == QLatin1Char('w') && c[1] == QLatin1Char('h')
|
---|
| 198 | && c[2] == QLatin1Char('i') && c[3] == QLatin1Char('l')
|
---|
| 199 | && c[4] == QLatin1Char('e'))
|
---|
| 200 | return QScriptGrammar::T_WHILE;
|
---|
| 201 | else if (c[0] == QLatin1Char('c') && c[1] == QLatin1Char('o')
|
---|
| 202 | && c[2] == QLatin1Char('n') && c[3] == QLatin1Char('s')
|
---|
| 203 | && c[4] == QLatin1Char('t'))
|
---|
| 204 | return QScriptGrammar::T_CONST;
|
---|
| 205 | else if (c[0] == QLatin1Char('f') && c[1] == QLatin1Char('a')
|
---|
| 206 | && c[2] == QLatin1Char('l') && c[3] == QLatin1Char('s')
|
---|
| 207 | && c[4] == QLatin1Char('e'))
|
---|
| 208 | return QScriptGrammar::T_FALSE;
|
---|
| 209 | else if (check_reserved) {
|
---|
| 210 | if (c[0] == QLatin1Char('s') && c[1] == QLatin1Char('h')
|
---|
| 211 | && c[2] == QLatin1Char('o') && c[3] == QLatin1Char('r')
|
---|
| 212 | && c[4] == QLatin1Char('t'))
|
---|
| 213 | return QScriptGrammar::T_RESERVED_WORD;
|
---|
| 214 | else if (c[0] == QLatin1Char('s') && c[1] == QLatin1Char('u')
|
---|
| 215 | && c[2] == QLatin1Char('p') && c[3] == QLatin1Char('e')
|
---|
| 216 | && c[4] == QLatin1Char('r'))
|
---|
| 217 | return QScriptGrammar::T_RESERVED_WORD;
|
---|
| 218 | else if (c[0] == QLatin1Char('f') && c[1] == QLatin1Char('i')
|
---|
| 219 | && c[2] == QLatin1Char('n') && c[3] == QLatin1Char('a')
|
---|
| 220 | && c[4] == QLatin1Char('l'))
|
---|
| 221 | return QScriptGrammar::T_RESERVED_WORD;
|
---|
| 222 | else if (c[0] == QLatin1Char('c') && c[1] == QLatin1Char('l')
|
---|
| 223 | && c[2] == QLatin1Char('a') && c[3] == QLatin1Char('s')
|
---|
| 224 | && c[4] == QLatin1Char('s'))
|
---|
| 225 | return QScriptGrammar::T_RESERVED_WORD;
|
---|
| 226 | else if (c[0] == QLatin1Char('f') && c[1] == QLatin1Char('l')
|
---|
| 227 | && c[2] == QLatin1Char('o') && c[3] == QLatin1Char('a')
|
---|
| 228 | && c[4] == QLatin1Char('t'))
|
---|
| 229 | return QScriptGrammar::T_RESERVED_WORD;
|
---|
| 230 | }
|
---|
| 231 | } break;
|
---|
| 232 |
|
---|
| 233 | case 6: {
|
---|
| 234 | if (c[0] == QLatin1Char('d') && c[1] == QLatin1Char('e')
|
---|
| 235 | && c[2] == QLatin1Char('l') && c[3] == QLatin1Char('e')
|
---|
| 236 | && c[4] == QLatin1Char('t') && c[5] == QLatin1Char('e'))
|
---|
| 237 | return QScriptGrammar::T_DELETE;
|
---|
| 238 | else if (c[0] == QLatin1Char('r') && c[1] == QLatin1Char('e')
|
---|
| 239 | && c[2] == QLatin1Char('t') && c[3] == QLatin1Char('u')
|
---|
| 240 | && c[4] == QLatin1Char('r') && c[5] == QLatin1Char('n'))
|
---|
| 241 | return QScriptGrammar::T_RETURN;
|
---|
| 242 | else if (c[0] == QLatin1Char('s') && c[1] == QLatin1Char('w')
|
---|
| 243 | && c[2] == QLatin1Char('i') && c[3] == QLatin1Char('t')
|
---|
| 244 | && c[4] == QLatin1Char('c') && c[5] == QLatin1Char('h'))
|
---|
| 245 | return QScriptGrammar::T_SWITCH;
|
---|
| 246 | else if (c[0] == QLatin1Char('t') && c[1] == QLatin1Char('y')
|
---|
| 247 | && c[2] == QLatin1Char('p') && c[3] == QLatin1Char('e')
|
---|
| 248 | && c[4] == QLatin1Char('o') && c[5] == QLatin1Char('f'))
|
---|
| 249 | return QScriptGrammar::T_TYPEOF;
|
---|
| 250 | else if (check_reserved) {
|
---|
| 251 | if (c[0] == QLatin1Char('e') && c[1] == QLatin1Char('x')
|
---|
| 252 | && c[2] == QLatin1Char('p') && c[3] == QLatin1Char('o')
|
---|
| 253 | && c[4] == QLatin1Char('r') && c[5] == QLatin1Char('t'))
|
---|
| 254 | return QScriptGrammar::T_RESERVED_WORD;
|
---|
| 255 | else if (c[0] == QLatin1Char('s') && c[1] == QLatin1Char('t')
|
---|
| 256 | && c[2] == QLatin1Char('a') && c[3] == QLatin1Char('t')
|
---|
| 257 | && c[4] == QLatin1Char('i') && c[5] == QLatin1Char('c'))
|
---|
| 258 | return QScriptGrammar::T_RESERVED_WORD;
|
---|
| 259 | else if (c[0] == QLatin1Char('d') && c[1] == QLatin1Char('o')
|
---|
| 260 | && c[2] == QLatin1Char('u') && c[3] == QLatin1Char('b')
|
---|
| 261 | && c[4] == QLatin1Char('l') && c[5] == QLatin1Char('e'))
|
---|
| 262 | return QScriptGrammar::T_RESERVED_WORD;
|
---|
| 263 | else if (c[0] == QLatin1Char('i') && c[1] == QLatin1Char('m')
|
---|
| 264 | && c[2] == QLatin1Char('p') && c[3] == QLatin1Char('o')
|
---|
| 265 | && c[4] == QLatin1Char('r') && c[5] == QLatin1Char('t'))
|
---|
| 266 | return QScriptGrammar::T_RESERVED_WORD;
|
---|
| 267 | else if (c[0] == QLatin1Char('p') && c[1] == QLatin1Char('u')
|
---|
| 268 | && c[2] == QLatin1Char('b') && c[3] == QLatin1Char('l')
|
---|
| 269 | && c[4] == QLatin1Char('i') && c[5] == QLatin1Char('c'))
|
---|
| 270 | return QScriptGrammar::T_RESERVED_WORD;
|
---|
| 271 | else if (c[0] == QLatin1Char('n') && c[1] == QLatin1Char('a')
|
---|
| 272 | && c[2] == QLatin1Char('t') && c[3] == QLatin1Char('i')
|
---|
| 273 | && c[4] == QLatin1Char('v') && c[5] == QLatin1Char('e'))
|
---|
| 274 | return QScriptGrammar::T_RESERVED_WORD;
|
---|
| 275 | else if (c[0] == QLatin1Char('t') && c[1] == QLatin1Char('h')
|
---|
| 276 | && c[2] == QLatin1Char('r') && c[3] == QLatin1Char('o')
|
---|
| 277 | && c[4] == QLatin1Char('w') && c[5] == QLatin1Char('s'))
|
---|
| 278 | return QScriptGrammar::T_RESERVED_WORD;
|
---|
| 279 | }
|
---|
| 280 | } break;
|
---|
| 281 |
|
---|
| 282 | case 7: {
|
---|
| 283 | if (c[0] == QLatin1Char('d') && c[1] == QLatin1Char('e')
|
---|
| 284 | && c[2] == QLatin1Char('f') && c[3] == QLatin1Char('a')
|
---|
| 285 | && c[4] == QLatin1Char('u') && c[5] == QLatin1Char('l')
|
---|
| 286 | && c[6] == QLatin1Char('t'))
|
---|
| 287 | return QScriptGrammar::T_DEFAULT;
|
---|
| 288 | else if (c[0] == QLatin1Char('f') && c[1] == QLatin1Char('i')
|
---|
| 289 | && c[2] == QLatin1Char('n') && c[3] == QLatin1Char('a')
|
---|
| 290 | && c[4] == QLatin1Char('l') && c[5] == QLatin1Char('l')
|
---|
| 291 | && c[6] == QLatin1Char('y'))
|
---|
| 292 | return QScriptGrammar::T_FINALLY;
|
---|
| 293 | else if (check_reserved) {
|
---|
| 294 | if (c[0] == QLatin1Char('b') && c[1] == QLatin1Char('o')
|
---|
| 295 | && c[2] == QLatin1Char('o') && c[3] == QLatin1Char('l')
|
---|
| 296 | && c[4] == QLatin1Char('e') && c[5] == QLatin1Char('a')
|
---|
| 297 | && c[6] == QLatin1Char('n'))
|
---|
| 298 | return QScriptGrammar::T_RESERVED_WORD;
|
---|
| 299 | else if (c[0] == QLatin1Char('e') && c[1] == QLatin1Char('x')
|
---|
| 300 | && c[2] == QLatin1Char('t') && c[3] == QLatin1Char('e')
|
---|
| 301 | && c[4] == QLatin1Char('n') && c[5] == QLatin1Char('d')
|
---|
| 302 | && c[6] == QLatin1Char('s'))
|
---|
| 303 | return QScriptGrammar::T_RESERVED_WORD;
|
---|
| 304 | else if (c[0] == QLatin1Char('p') && c[1] == QLatin1Char('a')
|
---|
| 305 | && c[2] == QLatin1Char('c') && c[3] == QLatin1Char('k')
|
---|
| 306 | && c[4] == QLatin1Char('a') && c[5] == QLatin1Char('g')
|
---|
| 307 | && c[6] == QLatin1Char('e'))
|
---|
| 308 | return QScriptGrammar::T_RESERVED_WORD;
|
---|
| 309 | else if (c[0] == QLatin1Char('p') && c[1] == QLatin1Char('r')
|
---|
| 310 | && c[2] == QLatin1Char('i') && c[3] == QLatin1Char('v')
|
---|
| 311 | && c[4] == QLatin1Char('a') && c[5] == QLatin1Char('t')
|
---|
| 312 | && c[6] == QLatin1Char('e'))
|
---|
| 313 | return QScriptGrammar::T_RESERVED_WORD;
|
---|
| 314 | }
|
---|
| 315 | } break;
|
---|
| 316 |
|
---|
| 317 | case 8: {
|
---|
| 318 | if (c[0] == QLatin1Char('c') && c[1] == QLatin1Char('o')
|
---|
| 319 | && c[2] == QLatin1Char('n') && c[3] == QLatin1Char('t')
|
---|
| 320 | && c[4] == QLatin1Char('i') && c[5] == QLatin1Char('n')
|
---|
| 321 | && c[6] == QLatin1Char('u') && c[7] == QLatin1Char('e'))
|
---|
| 322 | return QScriptGrammar::T_CONTINUE;
|
---|
| 323 | else if (c[0] == QLatin1Char('f') && c[1] == QLatin1Char('u')
|
---|
| 324 | && c[2] == QLatin1Char('n') && c[3] == QLatin1Char('c')
|
---|
| 325 | && c[4] == QLatin1Char('t') && c[5] == QLatin1Char('i')
|
---|
| 326 | && c[6] == QLatin1Char('o') && c[7] == QLatin1Char('n'))
|
---|
| 327 | return QScriptGrammar::T_FUNCTION;
|
---|
| 328 | else if (c[0] == QLatin1Char('d') && c[1] == QLatin1Char('e')
|
---|
| 329 | && c[2] == QLatin1Char('b') && c[3] == QLatin1Char('u')
|
---|
| 330 | && c[4] == QLatin1Char('g') && c[5] == QLatin1Char('g')
|
---|
| 331 | && c[6] == QLatin1Char('e') && c[7] == QLatin1Char('r'))
|
---|
| 332 | return QScriptGrammar::T_DEBUGGER;
|
---|
| 333 | else if (check_reserved) {
|
---|
| 334 | if (c[0] == QLatin1Char('a') && c[1] == QLatin1Char('b')
|
---|
| 335 | && c[2] == QLatin1Char('s') && c[3] == QLatin1Char('t')
|
---|
| 336 | && c[4] == QLatin1Char('r') && c[5] == QLatin1Char('a')
|
---|
| 337 | && c[6] == QLatin1Char('c') && c[7] == QLatin1Char('t'))
|
---|
| 338 | return QScriptGrammar::T_RESERVED_WORD;
|
---|
| 339 | else if (c[0] == QLatin1Char('v') && c[1] == QLatin1Char('o')
|
---|
| 340 | && c[2] == QLatin1Char('l') && c[3] == QLatin1Char('a')
|
---|
| 341 | && c[4] == QLatin1Char('t') && c[5] == QLatin1Char('i')
|
---|
| 342 | && c[6] == QLatin1Char('l') && c[7] == QLatin1Char('e'))
|
---|
| 343 | return QScriptGrammar::T_RESERVED_WORD;
|
---|
| 344 | }
|
---|
| 345 | } break;
|
---|
| 346 |
|
---|
| 347 | case 9: {
|
---|
| 348 | if (check_reserved) {
|
---|
| 349 | if (c[0] == QLatin1Char('i') && c[1] == QLatin1Char('n')
|
---|
| 350 | && c[2] == QLatin1Char('t') && c[3] == QLatin1Char('e')
|
---|
| 351 | && c[4] == QLatin1Char('r') && c[5] == QLatin1Char('f')
|
---|
| 352 | && c[6] == QLatin1Char('a') && c[7] == QLatin1Char('c')
|
---|
| 353 | && c[8] == QLatin1Char('e'))
|
---|
| 354 | return QScriptGrammar::T_RESERVED_WORD;
|
---|
| 355 | else if (c[0] == QLatin1Char('t') && c[1] == QLatin1Char('r')
|
---|
| 356 | && c[2] == QLatin1Char('a') && c[3] == QLatin1Char('n')
|
---|
| 357 | && c[4] == QLatin1Char('s') && c[5] == QLatin1Char('i')
|
---|
| 358 | && c[6] == QLatin1Char('e') && c[7] == QLatin1Char('n')
|
---|
| 359 | && c[8] == QLatin1Char('t'))
|
---|
| 360 | return QScriptGrammar::T_RESERVED_WORD;
|
---|
| 361 | else if (c[0] == QLatin1Char('p') && c[1] == QLatin1Char('r')
|
---|
| 362 | && c[2] == QLatin1Char('o') && c[3] == QLatin1Char('t')
|
---|
| 363 | && c[4] == QLatin1Char('e') && c[5] == QLatin1Char('c')
|
---|
| 364 | && c[6] == QLatin1Char('t') && c[7] == QLatin1Char('e')
|
---|
| 365 | && c[8] == QLatin1Char('d'))
|
---|
| 366 | return QScriptGrammar::T_RESERVED_WORD;
|
---|
| 367 | }
|
---|
| 368 | } break;
|
---|
| 369 |
|
---|
| 370 | case 10: {
|
---|
| 371 | if (c[0] == QLatin1Char('i') && c[1] == QLatin1Char('n')
|
---|
| 372 | && c[2] == QLatin1Char('s') && c[3] == QLatin1Char('t')
|
---|
| 373 | && c[4] == QLatin1Char('a') && c[5] == QLatin1Char('n')
|
---|
| 374 | && c[6] == QLatin1Char('c') && c[7] == QLatin1Char('e')
|
---|
| 375 | && c[8] == QLatin1Char('o') && c[9] == QLatin1Char('f'))
|
---|
| 376 | return QScriptGrammar::T_INSTANCEOF;
|
---|
| 377 | else if (check_reserved) {
|
---|
| 378 | if (c[0] == QLatin1Char('i') && c[1] == QLatin1Char('m')
|
---|
| 379 | && c[2] == QLatin1Char('p') && c[3] == QLatin1Char('l')
|
---|
| 380 | && c[4] == QLatin1Char('e') && c[5] == QLatin1Char('m')
|
---|
| 381 | && c[6] == QLatin1Char('e') && c[7] == QLatin1Char('n')
|
---|
| 382 | && c[8] == QLatin1Char('t') && c[9] == QLatin1Char('s'))
|
---|
| 383 | return QScriptGrammar::T_RESERVED_WORD;
|
---|
| 384 | }
|
---|
| 385 | } break;
|
---|
| 386 |
|
---|
| 387 | case 12: {
|
---|
| 388 | if (check_reserved) {
|
---|
| 389 | if (c[0] == QLatin1Char('s') && c[1] == QLatin1Char('y')
|
---|
| 390 | && c[2] == QLatin1Char('n') && c[3] == QLatin1Char('c')
|
---|
| 391 | && c[4] == QLatin1Char('h') && c[5] == QLatin1Char('r')
|
---|
| 392 | && c[6] == QLatin1Char('o') && c[7] == QLatin1Char('n')
|
---|
| 393 | && c[8] == QLatin1Char('i') && c[9] == QLatin1Char('z')
|
---|
| 394 | && c[10] == QLatin1Char('e') && c[11] == QLatin1Char('d'))
|
---|
| 395 | return QScriptGrammar::T_RESERVED_WORD;
|
---|
| 396 | }
|
---|
| 397 | } break;
|
---|
| 398 |
|
---|
| 399 | } // switch
|
---|
| 400 |
|
---|
| 401 | return -1;
|
---|
| 402 | }
|
---|
| 403 |
|
---|
| 404 | int QScript::Lexer::lex()
|
---|
| 405 | {
|
---|
| 406 | int token = 0;
|
---|
| 407 | state = Start;
|
---|
| 408 | ushort stringType = 0; // either single or double quotes
|
---|
| 409 | pos8 = pos16 = 0;
|
---|
| 410 | done = false;
|
---|
| 411 | terminator = false;
|
---|
| 412 |
|
---|
| 413 | // did we push a token on the stack previously ?
|
---|
| 414 | // (after an automatic semicolon insertion)
|
---|
| 415 | if (stackToken >= 0) {
|
---|
| 416 | setDone(Other);
|
---|
| 417 | token = stackToken;
|
---|
| 418 | stackToken = -1;
|
---|
| 419 | }
|
---|
| 420 |
|
---|
| 421 | while (!done) {
|
---|
| 422 | switch (state) {
|
---|
| 423 | case Start:
|
---|
| 424 | if (isWhiteSpace()) {
|
---|
| 425 | // do nothing
|
---|
| 426 | } else if (current == '/' && next1 == '/') {
|
---|
| 427 | recordStartPos();
|
---|
| 428 | shift(1);
|
---|
| 429 | state = InSingleLineComment;
|
---|
| 430 | } else if (current == '/' && next1 == '*') {
|
---|
| 431 | recordStartPos();
|
---|
| 432 | shift(1);
|
---|
| 433 | state = InMultiLineComment;
|
---|
| 434 | } else if (current == 0) {
|
---|
| 435 | syncProhibitAutomaticSemicolon();
|
---|
| 436 | if (!terminator && !delimited && !prohibitAutomaticSemicolon) {
|
---|
| 437 | // automatic semicolon insertion if program incomplete
|
---|
| 438 | token = QScriptGrammar::T_SEMICOLON;
|
---|
| 439 | stackToken = 0;
|
---|
| 440 | setDone(Other);
|
---|
| 441 | } else {
|
---|
| 442 | setDone(Eof);
|
---|
| 443 | }
|
---|
| 444 | } else if (isLineTerminator()) {
|
---|
| 445 | shiftWindowsLineBreak();
|
---|
| 446 | yylineno++;
|
---|
| 447 | yycolumn = 0;
|
---|
| 448 | bol = true;
|
---|
| 449 | terminator = true;
|
---|
| 450 | syncProhibitAutomaticSemicolon();
|
---|
| 451 | if (restrKeyword) {
|
---|
| 452 | token = QScriptGrammar::T_SEMICOLON;
|
---|
| 453 | setDone(Other);
|
---|
| 454 | }
|
---|
| 455 | } else if (current == '"' || current == '\'') {
|
---|
| 456 | recordStartPos();
|
---|
| 457 | state = InString;
|
---|
| 458 | stringType = current;
|
---|
| 459 | } else if (isIdentLetter(current)) {
|
---|
| 460 | recordStartPos();
|
---|
| 461 | record16(current);
|
---|
| 462 | state = InIdentifier;
|
---|
| 463 | } else if (current == '0') {
|
---|
| 464 | recordStartPos();
|
---|
| 465 | record8(current);
|
---|
| 466 | state = InNum0;
|
---|
| 467 | } else if (isDecimalDigit(current)) {
|
---|
| 468 | recordStartPos();
|
---|
| 469 | record8(current);
|
---|
| 470 | state = InNum;
|
---|
| 471 | } else if (current == '.' && isDecimalDigit(next1)) {
|
---|
| 472 | recordStartPos();
|
---|
| 473 | record8(current);
|
---|
| 474 | state = InDecimal;
|
---|
| 475 | } else {
|
---|
| 476 | recordStartPos();
|
---|
| 477 | token = matchPunctuator(current, next1, next2, next3);
|
---|
| 478 | if (token != -1) {
|
---|
| 479 | if (terminator && !delimited && !prohibitAutomaticSemicolon
|
---|
| 480 | && (token == QScriptGrammar::T_PLUS_PLUS
|
---|
| 481 | || token == QScriptGrammar::T_MINUS_MINUS)) {
|
---|
| 482 | // automatic semicolon insertion
|
---|
| 483 | stackToken = token;
|
---|
| 484 | token = QScriptGrammar::T_SEMICOLON;
|
---|
| 485 | }
|
---|
| 486 | setDone(Other);
|
---|
| 487 | }
|
---|
| 488 | else {
|
---|
| 489 | setDone(Bad);
|
---|
| 490 | err = IllegalCharacter;
|
---|
| 491 | errmsg = QLatin1String("Illegal character");
|
---|
| 492 | }
|
---|
| 493 | }
|
---|
| 494 | break;
|
---|
| 495 | case InString:
|
---|
| 496 | if (current == stringType) {
|
---|
| 497 | shift(1);
|
---|
| 498 | setDone(String);
|
---|
| 499 | } else if (current == 0 || isLineTerminator()) {
|
---|
| 500 | setDone(Bad);
|
---|
| 501 | err = UnclosedStringLiteral;
|
---|
| 502 | errmsg = QLatin1String("Unclosed string at end of line");
|
---|
| 503 | } else if (current == '\\') {
|
---|
| 504 | state = InEscapeSequence;
|
---|
| 505 | } else {
|
---|
| 506 | record16(current);
|
---|
| 507 | }
|
---|
| 508 | break;
|
---|
| 509 | // Escape Sequences inside of strings
|
---|
| 510 | case InEscapeSequence:
|
---|
| 511 | if (isOctalDigit(current)) {
|
---|
| 512 | if (current >= '0' && current <= '3' &&
|
---|
| 513 | isOctalDigit(next1) && isOctalDigit(next2)) {
|
---|
| 514 | record16(convertOctal(current, next1, next2));
|
---|
| 515 | shift(2);
|
---|
| 516 | state = InString;
|
---|
| 517 | } else if (isOctalDigit(current) &&
|
---|
| 518 | isOctalDigit(next1)) {
|
---|
| 519 | record16(convertOctal('0', current, next1));
|
---|
| 520 | shift(1);
|
---|
| 521 | state = InString;
|
---|
| 522 | } else if (isOctalDigit(current)) {
|
---|
| 523 | record16(convertOctal('0', '0', current));
|
---|
| 524 | state = InString;
|
---|
| 525 | } else {
|
---|
| 526 | setDone(Bad);
|
---|
| 527 | err = IllegalEscapeSequence;
|
---|
| 528 | errmsg = QLatin1String("Illegal escape squence");
|
---|
| 529 | }
|
---|
| 530 | } else if (current == 'x')
|
---|
| 531 | state = InHexEscape;
|
---|
| 532 | else if (current == 'u')
|
---|
| 533 | state = InUnicodeEscape;
|
---|
| 534 | else {
|
---|
| 535 | if (isLineTerminator()) {
|
---|
| 536 | shiftWindowsLineBreak();
|
---|
| 537 | yylineno++;
|
---|
| 538 | yycolumn = 0;
|
---|
| 539 | bol = true;
|
---|
| 540 | } else {
|
---|
| 541 | record16(singleEscape(current));
|
---|
| 542 | }
|
---|
| 543 | state = InString;
|
---|
| 544 | }
|
---|
| 545 | break;
|
---|
| 546 | case InHexEscape:
|
---|
| 547 | if (isHexDigit(current) && isHexDigit(next1)) {
|
---|
| 548 | state = InString;
|
---|
| 549 | record16(QLatin1Char(convertHex(current, next1)));
|
---|
| 550 | shift(1);
|
---|
| 551 | } else if (current == stringType) {
|
---|
| 552 | record16(QLatin1Char('x'));
|
---|
| 553 | shift(1);
|
---|
| 554 | setDone(String);
|
---|
| 555 | } else {
|
---|
| 556 | record16(QLatin1Char('x'));
|
---|
| 557 | record16(current);
|
---|
| 558 | state = InString;
|
---|
| 559 | }
|
---|
| 560 | break;
|
---|
| 561 | case InUnicodeEscape:
|
---|
| 562 | if (isHexDigit(current) && isHexDigit(next1) &&
|
---|
| 563 | isHexDigit(next2) && isHexDigit(next3)) {
|
---|
| 564 | record16(convertUnicode(current, next1, next2, next3));
|
---|
| 565 | shift(3);
|
---|
| 566 | state = InString;
|
---|
| 567 | } else if (current == stringType) {
|
---|
| 568 | record16(QLatin1Char('u'));
|
---|
| 569 | shift(1);
|
---|
| 570 | setDone(String);
|
---|
| 571 | } else {
|
---|
| 572 | setDone(Bad);
|
---|
| 573 | err = IllegalUnicodeEscapeSequence;
|
---|
| 574 | errmsg = QLatin1String("Illegal unicode escape sequence");
|
---|
| 575 | }
|
---|
| 576 | break;
|
---|
| 577 | case InSingleLineComment:
|
---|
| 578 | if (isLineTerminator()) {
|
---|
| 579 | shiftWindowsLineBreak();
|
---|
| 580 | yylineno++;
|
---|
| 581 | yycolumn = 0;
|
---|
| 582 | terminator = true;
|
---|
| 583 | bol = true;
|
---|
| 584 | if (restrKeyword) {
|
---|
| 585 | token = QScriptGrammar::T_SEMICOLON;
|
---|
| 586 | setDone(Other);
|
---|
| 587 | } else
|
---|
| 588 | state = Start;
|
---|
| 589 | } else if (current == 0) {
|
---|
| 590 | setDone(Eof);
|
---|
| 591 | }
|
---|
| 592 | break;
|
---|
| 593 | case InMultiLineComment:
|
---|
| 594 | if (current == 0) {
|
---|
| 595 | setDone(Bad);
|
---|
| 596 | err = UnclosedComment;
|
---|
| 597 | errmsg = QLatin1String("Unclosed comment at end of file");
|
---|
| 598 | } else if (isLineTerminator()) {
|
---|
| 599 | shiftWindowsLineBreak();
|
---|
| 600 | yylineno++;
|
---|
| 601 | } else if (current == '*' && next1 == '/') {
|
---|
| 602 | state = Start;
|
---|
| 603 | shift(1);
|
---|
| 604 | }
|
---|
| 605 | break;
|
---|
| 606 | case InIdentifier:
|
---|
| 607 | if (isIdentLetter(current) || isDecimalDigit(current)) {
|
---|
| 608 | record16(current);
|
---|
| 609 | break;
|
---|
| 610 | }
|
---|
| 611 | setDone(Identifier);
|
---|
| 612 | break;
|
---|
| 613 | case InNum0:
|
---|
| 614 | if (current == 'x' || current == 'X') {
|
---|
| 615 | record8(current);
|
---|
| 616 | state = InHex;
|
---|
| 617 | } else if (current == '.') {
|
---|
| 618 | record8(current);
|
---|
| 619 | state = InDecimal;
|
---|
| 620 | } else if (current == 'e' || current == 'E') {
|
---|
| 621 | record8(current);
|
---|
| 622 | state = InExponentIndicator;
|
---|
| 623 | } else if (isOctalDigit(current)) {
|
---|
| 624 | record8(current);
|
---|
| 625 | state = InOctal;
|
---|
| 626 | } else if (isDecimalDigit(current)) {
|
---|
| 627 | record8(current);
|
---|
| 628 | state = InDecimal;
|
---|
| 629 | } else {
|
---|
| 630 | setDone(Number);
|
---|
| 631 | }
|
---|
| 632 | break;
|
---|
| 633 | case InHex:
|
---|
| 634 | if (isHexDigit(current))
|
---|
| 635 | record8(current);
|
---|
| 636 | else
|
---|
| 637 | setDone(Hex);
|
---|
| 638 | break;
|
---|
| 639 | case InOctal:
|
---|
| 640 | if (isOctalDigit(current)) {
|
---|
| 641 | record8(current);
|
---|
| 642 | } else if (isDecimalDigit(current)) {
|
---|
| 643 | record8(current);
|
---|
| 644 | state = InDecimal;
|
---|
| 645 | } else {
|
---|
| 646 | setDone(Octal);
|
---|
| 647 | }
|
---|
| 648 | break;
|
---|
| 649 | case InNum:
|
---|
| 650 | if (isDecimalDigit(current)) {
|
---|
| 651 | record8(current);
|
---|
| 652 | } else if (current == '.') {
|
---|
| 653 | record8(current);
|
---|
| 654 | state = InDecimal;
|
---|
| 655 | } else if (current == 'e' || current == 'E') {
|
---|
| 656 | record8(current);
|
---|
| 657 | state = InExponentIndicator;
|
---|
| 658 | } else {
|
---|
| 659 | setDone(Number);
|
---|
| 660 | }
|
---|
| 661 | break;
|
---|
| 662 | case InDecimal:
|
---|
| 663 | if (isDecimalDigit(current)) {
|
---|
| 664 | record8(current);
|
---|
| 665 | } else if (current == 'e' || current == 'E') {
|
---|
| 666 | record8(current);
|
---|
| 667 | state = InExponentIndicator;
|
---|
| 668 | } else {
|
---|
| 669 | setDone(Number);
|
---|
| 670 | }
|
---|
| 671 | break;
|
---|
| 672 | case InExponentIndicator:
|
---|
| 673 | if (current == '+' || current == '-') {
|
---|
| 674 | record8(current);
|
---|
| 675 | } else if (isDecimalDigit(current)) {
|
---|
| 676 | record8(current);
|
---|
| 677 | state = InExponent;
|
---|
| 678 | } else {
|
---|
| 679 | setDone(Bad);
|
---|
| 680 | err = IllegalExponentIndicator;
|
---|
| 681 | errmsg = QLatin1String("Illegal syntax for exponential number");
|
---|
| 682 | }
|
---|
| 683 | break;
|
---|
| 684 | case InExponent:
|
---|
| 685 | if (isDecimalDigit(current)) {
|
---|
| 686 | record8(current);
|
---|
| 687 | } else {
|
---|
| 688 | setDone(Number);
|
---|
| 689 | }
|
---|
| 690 | break;
|
---|
| 691 | default:
|
---|
| 692 | Q_ASSERT_X(0, "Lexer::lex", "Unhandled state in switch statement");
|
---|
| 693 | }
|
---|
| 694 |
|
---|
| 695 | // move on to the next character
|
---|
| 696 | if (!done)
|
---|
| 697 | shift(1);
|
---|
| 698 | if (state != Start && state != InSingleLineComment)
|
---|
| 699 | bol = false;
|
---|
| 700 | }
|
---|
| 701 |
|
---|
| 702 | // no identifiers allowed directly after numeric literal, e.g. "3in" is bad
|
---|
| 703 | if ((state == Number || state == Octal || state == Hex)
|
---|
| 704 | && isIdentLetter(current)) {
|
---|
| 705 | state = Bad;
|
---|
| 706 | err = IllegalIdentifier;
|
---|
| 707 | errmsg = QLatin1String("Identifier cannot start with numeric literal");
|
---|
| 708 | }
|
---|
| 709 |
|
---|
| 710 | // terminate string
|
---|
| 711 | buffer8[pos8] = '\0';
|
---|
| 712 |
|
---|
| 713 | double dval = 0;
|
---|
| 714 | if (state == Number) {
|
---|
| 715 | dval = qstrtod(buffer8, 0, 0);
|
---|
| 716 | } else if (state == Hex) { // scan hex numbers
|
---|
| 717 | dval = QScript::integerFromString(buffer8, pos8, 16);
|
---|
| 718 | state = Number;
|
---|
| 719 | } else if (state == Octal) { // scan octal number
|
---|
| 720 | dval = QScript::integerFromString(buffer8, pos8, 8);
|
---|
| 721 | state = Number;
|
---|
| 722 | }
|
---|
| 723 |
|
---|
| 724 | restrKeyword = false;
|
---|
| 725 | delimited = false;
|
---|
| 726 |
|
---|
| 727 | switch (parenthesesState) {
|
---|
| 728 | case IgnoreParentheses:
|
---|
| 729 | break;
|
---|
| 730 | case CountParentheses:
|
---|
| 731 | if (token == QScriptGrammar::T_RPAREN) {
|
---|
| 732 | --parenthesesCount;
|
---|
| 733 | if (parenthesesCount == 0)
|
---|
| 734 | parenthesesState = BalancedParentheses;
|
---|
| 735 | } else if (token == QScriptGrammar::T_LPAREN) {
|
---|
| 736 | ++parenthesesCount;
|
---|
| 737 | }
|
---|
| 738 | break;
|
---|
| 739 | case BalancedParentheses:
|
---|
| 740 | parenthesesState = IgnoreParentheses;
|
---|
| 741 | break;
|
---|
| 742 | }
|
---|
| 743 |
|
---|
| 744 | switch (state) {
|
---|
| 745 | case Eof:
|
---|
| 746 | return 0;
|
---|
| 747 | case Other:
|
---|
| 748 | if(token == QScriptGrammar::T_RBRACE || token == QScriptGrammar::T_SEMICOLON)
|
---|
| 749 | delimited = true;
|
---|
| 750 | return token;
|
---|
| 751 | case Identifier:
|
---|
| 752 | if ((token = findReservedWord(buffer16, pos16)) < 0) {
|
---|
| 753 | /* TODO: close leak on parse error. same holds true for String */
|
---|
| 754 | if (driver) {
|
---|
| 755 | Q_ASSERT_X(false, Q_FUNC_INFO, "not implemented");
|
---|
| 756 | qsyylval.ustr = 0; // driver->intern(buffer16, pos16);
|
---|
| 757 | } else
|
---|
| 758 | qsyylval.ustr = 0;
|
---|
| 759 | return QScriptGrammar::T_IDENTIFIER;
|
---|
| 760 | }
|
---|
| 761 | if (token == QScriptGrammar::T_CONTINUE || token == QScriptGrammar::T_BREAK
|
---|
| 762 | || token == QScriptGrammar::T_RETURN || token == QScriptGrammar::T_THROW) {
|
---|
| 763 | restrKeyword = true;
|
---|
| 764 | } else if (token == QScriptGrammar::T_IF || token == QScriptGrammar::T_FOR
|
---|
| 765 | || token == QScriptGrammar::T_WHILE || token == QScriptGrammar::T_WITH) {
|
---|
| 766 | parenthesesState = CountParentheses;
|
---|
| 767 | parenthesesCount = 0;
|
---|
| 768 | } else if (token == QScriptGrammar::T_DO) {
|
---|
| 769 | parenthesesState = BalancedParentheses;
|
---|
| 770 | }
|
---|
| 771 | return token;
|
---|
| 772 | case String:
|
---|
| 773 | if (driver) {
|
---|
| 774 | Q_ASSERT_X(false, Q_FUNC_INFO, "not implemented");
|
---|
| 775 | qsyylval.ustr = 0; // driver->intern(buffer16, pos16);
|
---|
| 776 | } else
|
---|
| 777 | qsyylval.ustr = 0;
|
---|
| 778 | return QScriptGrammar::T_STRING_LITERAL;
|
---|
| 779 | case Number:
|
---|
| 780 | qsyylval.dval = dval;
|
---|
| 781 | return QScriptGrammar::T_NUMERIC_LITERAL;
|
---|
| 782 | case Bad:
|
---|
| 783 | return -1;
|
---|
| 784 | default:
|
---|
| 785 | Q_ASSERT(!"unhandled numeration value in switch");
|
---|
| 786 | return -1;
|
---|
| 787 | }
|
---|
| 788 | }
|
---|
| 789 |
|
---|
| 790 | bool QScript::Lexer::isWhiteSpace() const
|
---|
| 791 | {
|
---|
| 792 | return (current == ' ' || current == '\t' ||
|
---|
| 793 | current == 0x0b || current == 0x0c);
|
---|
| 794 | }
|
---|
| 795 |
|
---|
| 796 | bool QScript::Lexer::isLineTerminator() const
|
---|
| 797 | {
|
---|
| 798 | return (current == '\n' || current == '\r');
|
---|
| 799 | }
|
---|
| 800 |
|
---|
| 801 | bool QScript::Lexer::isIdentLetter(ushort c)
|
---|
| 802 | {
|
---|
| 803 | /* TODO: allow other legitimate unicode chars */
|
---|
| 804 | return ((c >= 'a' && c <= 'z')
|
---|
| 805 | || (c >= 'A' && c <= 'Z')
|
---|
| 806 | || c == '$'
|
---|
| 807 | || c == '_');
|
---|
| 808 | }
|
---|
| 809 |
|
---|
| 810 | bool QScript::Lexer::isDecimalDigit(ushort c)
|
---|
| 811 | {
|
---|
| 812 | return (c >= '0' && c <= '9');
|
---|
| 813 | }
|
---|
| 814 |
|
---|
| 815 | bool QScript::Lexer::isHexDigit(ushort c) const
|
---|
| 816 | {
|
---|
| 817 | return ((c >= '0' && c <= '9')
|
---|
| 818 | || (c >= 'a' && c <= 'f')
|
---|
| 819 | || (c >= 'A' && c <= 'F'));
|
---|
| 820 | }
|
---|
| 821 |
|
---|
| 822 | bool QScript::Lexer::isOctalDigit(ushort c) const
|
---|
| 823 | {
|
---|
| 824 | return (c >= '0' && c <= '7');
|
---|
| 825 | }
|
---|
| 826 |
|
---|
| 827 | int QScript::Lexer::matchPunctuator(ushort c1, ushort c2,
|
---|
| 828 | ushort c3, ushort c4)
|
---|
| 829 | {
|
---|
| 830 | if (c1 == '>' && c2 == '>' && c3 == '>' && c4 == '=') {
|
---|
| 831 | shift(4);
|
---|
| 832 | return QScriptGrammar::T_GT_GT_GT_EQ;
|
---|
| 833 | } else if (c1 == '=' && c2 == '=' && c3 == '=') {
|
---|
| 834 | shift(3);
|
---|
| 835 | return QScriptGrammar::T_EQ_EQ_EQ;
|
---|
| 836 | } else if (c1 == '!' && c2 == '=' && c3 == '=') {
|
---|
| 837 | shift(3);
|
---|
| 838 | return QScriptGrammar::T_NOT_EQ_EQ;
|
---|
| 839 | } else if (c1 == '>' && c2 == '>' && c3 == '>') {
|
---|
| 840 | shift(3);
|
---|
| 841 | return QScriptGrammar::T_GT_GT_GT;
|
---|
| 842 | } else if (c1 == '<' && c2 == '<' && c3 == '=') {
|
---|
| 843 | shift(3);
|
---|
| 844 | return QScriptGrammar::T_LT_LT_EQ;
|
---|
| 845 | } else if (c1 == '>' && c2 == '>' && c3 == '=') {
|
---|
| 846 | shift(3);
|
---|
| 847 | return QScriptGrammar::T_GT_GT_EQ;
|
---|
| 848 | } else if (c1 == '<' && c2 == '=') {
|
---|
| 849 | shift(2);
|
---|
| 850 | return QScriptGrammar::T_LE;
|
---|
| 851 | } else if (c1 == '>' && c2 == '=') {
|
---|
| 852 | shift(2);
|
---|
| 853 | return QScriptGrammar::T_GE;
|
---|
| 854 | } else if (c1 == '!' && c2 == '=') {
|
---|
| 855 | shift(2);
|
---|
| 856 | return QScriptGrammar::T_NOT_EQ;
|
---|
| 857 | } else if (c1 == '+' && c2 == '+') {
|
---|
| 858 | shift(2);
|
---|
| 859 | return QScriptGrammar::T_PLUS_PLUS;
|
---|
| 860 | } else if (c1 == '-' && c2 == '-') {
|
---|
| 861 | shift(2);
|
---|
| 862 | return QScriptGrammar::T_MINUS_MINUS;
|
---|
| 863 | } else if (c1 == '=' && c2 == '=') {
|
---|
| 864 | shift(2);
|
---|
| 865 | return QScriptGrammar::T_EQ_EQ;
|
---|
| 866 | } else if (c1 == '+' && c2 == '=') {
|
---|
| 867 | shift(2);
|
---|
| 868 | return QScriptGrammar::T_PLUS_EQ;
|
---|
| 869 | } else if (c1 == '-' && c2 == '=') {
|
---|
| 870 | shift(2);
|
---|
| 871 | return QScriptGrammar::T_MINUS_EQ;
|
---|
| 872 | } else if (c1 == '*' && c2 == '=') {
|
---|
| 873 | shift(2);
|
---|
| 874 | return QScriptGrammar::T_STAR_EQ;
|
---|
| 875 | } else if (c1 == '/' && c2 == '=') {
|
---|
| 876 | shift(2);
|
---|
| 877 | return QScriptGrammar::T_DIVIDE_EQ;
|
---|
| 878 | } else if (c1 == '&' && c2 == '=') {
|
---|
| 879 | shift(2);
|
---|
| 880 | return QScriptGrammar::T_AND_EQ;
|
---|
| 881 | } else if (c1 == '^' && c2 == '=') {
|
---|
| 882 | shift(2);
|
---|
| 883 | return QScriptGrammar::T_XOR_EQ;
|
---|
| 884 | } else if (c1 == '%' && c2 == '=') {
|
---|
| 885 | shift(2);
|
---|
| 886 | return QScriptGrammar::T_REMAINDER_EQ;
|
---|
| 887 | } else if (c1 == '|' && c2 == '=') {
|
---|
| 888 | shift(2);
|
---|
| 889 | return QScriptGrammar::T_OR_EQ;
|
---|
| 890 | } else if (c1 == '<' && c2 == '<') {
|
---|
| 891 | shift(2);
|
---|
| 892 | return QScriptGrammar::T_LT_LT;
|
---|
| 893 | } else if (c1 == '>' && c2 == '>') {
|
---|
| 894 | shift(2);
|
---|
| 895 | return QScriptGrammar::T_GT_GT;
|
---|
| 896 | } else if (c1 == '&' && c2 == '&') {
|
---|
| 897 | shift(2);
|
---|
| 898 | return QScriptGrammar::T_AND_AND;
|
---|
| 899 | } else if (c1 == '|' && c2 == '|') {
|
---|
| 900 | shift(2);
|
---|
| 901 | return QScriptGrammar::T_OR_OR;
|
---|
| 902 | }
|
---|
| 903 |
|
---|
| 904 | switch(c1) {
|
---|
| 905 | case '=': shift(1); return QScriptGrammar::T_EQ;
|
---|
| 906 | case '>': shift(1); return QScriptGrammar::T_GT;
|
---|
| 907 | case '<': shift(1); return QScriptGrammar::T_LT;
|
---|
| 908 | case ',': shift(1); return QScriptGrammar::T_COMMA;
|
---|
| 909 | case '!': shift(1); return QScriptGrammar::T_NOT;
|
---|
| 910 | case '~': shift(1); return QScriptGrammar::T_TILDE;
|
---|
| 911 | case '?': shift(1); return QScriptGrammar::T_QUESTION;
|
---|
| 912 | case ':': shift(1); return QScriptGrammar::T_COLON;
|
---|
| 913 | case '.': shift(1); return QScriptGrammar::T_DOT;
|
---|
| 914 | case '+': shift(1); return QScriptGrammar::T_PLUS;
|
---|
| 915 | case '-': shift(1); return QScriptGrammar::T_MINUS;
|
---|
| 916 | case '*': shift(1); return QScriptGrammar::T_STAR;
|
---|
| 917 | case '/': shift(1); return QScriptGrammar::T_DIVIDE_;
|
---|
| 918 | case '&': shift(1); return QScriptGrammar::T_AND;
|
---|
| 919 | case '|': shift(1); return QScriptGrammar::T_OR;
|
---|
| 920 | case '^': shift(1); return QScriptGrammar::T_XOR;
|
---|
| 921 | case '%': shift(1); return QScriptGrammar::T_REMAINDER;
|
---|
| 922 | case '(': shift(1); return QScriptGrammar::T_LPAREN;
|
---|
| 923 | case ')': shift(1); return QScriptGrammar::T_RPAREN;
|
---|
| 924 | case '{': shift(1); return QScriptGrammar::T_LBRACE;
|
---|
| 925 | case '}': shift(1); return QScriptGrammar::T_RBRACE;
|
---|
| 926 | case '[': shift(1); return QScriptGrammar::T_LBRACKET;
|
---|
| 927 | case ']': shift(1); return QScriptGrammar::T_RBRACKET;
|
---|
| 928 | case ';': shift(1); return QScriptGrammar::T_SEMICOLON;
|
---|
| 929 |
|
---|
| 930 | default: return -1;
|
---|
| 931 | }
|
---|
| 932 | }
|
---|
| 933 |
|
---|
| 934 | ushort QScript::Lexer::singleEscape(ushort c) const
|
---|
| 935 | {
|
---|
| 936 | switch(c) {
|
---|
| 937 | case 'b':
|
---|
| 938 | return 0x08;
|
---|
| 939 | case 't':
|
---|
| 940 | return 0x09;
|
---|
| 941 | case 'n':
|
---|
| 942 | return 0x0A;
|
---|
| 943 | case 'v':
|
---|
| 944 | return 0x0B;
|
---|
| 945 | case 'f':
|
---|
| 946 | return 0x0C;
|
---|
| 947 | case 'r':
|
---|
| 948 | return 0x0D;
|
---|
| 949 | case '"':
|
---|
| 950 | return 0x22;
|
---|
| 951 | case '\'':
|
---|
| 952 | return 0x27;
|
---|
| 953 | case '\\':
|
---|
| 954 | return 0x5C;
|
---|
| 955 | default:
|
---|
| 956 | return c;
|
---|
| 957 | }
|
---|
| 958 | }
|
---|
| 959 |
|
---|
| 960 | ushort QScript::Lexer::convertOctal(ushort c1, ushort c2,
|
---|
| 961 | ushort c3) const
|
---|
| 962 | {
|
---|
| 963 | return ((c1 - '0') * 64 + (c2 - '0') * 8 + c3 - '0');
|
---|
| 964 | }
|
---|
| 965 |
|
---|
| 966 | unsigned char QScript::Lexer::convertHex(ushort c)
|
---|
| 967 | {
|
---|
| 968 | if (c >= '0' && c <= '9')
|
---|
| 969 | return (c - '0');
|
---|
| 970 | else if (c >= 'a' && c <= 'f')
|
---|
| 971 | return (c - 'a' + 10);
|
---|
| 972 | else
|
---|
| 973 | return (c - 'A' + 10);
|
---|
| 974 | }
|
---|
| 975 |
|
---|
| 976 | unsigned char QScript::Lexer::convertHex(ushort c1, ushort c2)
|
---|
| 977 | {
|
---|
| 978 | return ((convertHex(c1) << 4) + convertHex(c2));
|
---|
| 979 | }
|
---|
| 980 |
|
---|
| 981 | QChar QScript::Lexer::convertUnicode(ushort c1, ushort c2,
|
---|
| 982 | ushort c3, ushort c4)
|
---|
| 983 | {
|
---|
| 984 | return QChar((convertHex(c3) << 4) + convertHex(c4),
|
---|
| 985 | (convertHex(c1) << 4) + convertHex(c2));
|
---|
| 986 | }
|
---|
| 987 |
|
---|
| 988 | void QScript::Lexer::record8(ushort c)
|
---|
| 989 | {
|
---|
| 990 | Q_ASSERT(c <= 0xff);
|
---|
| 991 |
|
---|
| 992 | // enlarge buffer if full
|
---|
| 993 | if (pos8 >= size8 - 1) {
|
---|
| 994 | char *tmp = new char[2 * size8];
|
---|
| 995 | memcpy(tmp, buffer8, size8 * sizeof(char));
|
---|
| 996 | delete [] buffer8;
|
---|
| 997 | buffer8 = tmp;
|
---|
| 998 | size8 *= 2;
|
---|
| 999 | }
|
---|
| 1000 |
|
---|
| 1001 | buffer8[pos8++] = (char) c;
|
---|
| 1002 | }
|
---|
| 1003 |
|
---|
| 1004 | void QScript::Lexer::record16(QChar c)
|
---|
| 1005 | {
|
---|
| 1006 | // enlarge buffer if full
|
---|
| 1007 | if (pos16 >= size16 - 1) {
|
---|
| 1008 | QChar *tmp = new QChar[2 * size16];
|
---|
| 1009 | memcpy(tmp, buffer16, size16 * sizeof(QChar));
|
---|
| 1010 | delete [] buffer16;
|
---|
| 1011 | buffer16 = tmp;
|
---|
| 1012 | size16 *= 2;
|
---|
| 1013 | }
|
---|
| 1014 |
|
---|
| 1015 | buffer16[pos16++] = c;
|
---|
| 1016 | }
|
---|
| 1017 |
|
---|
| 1018 | void QScript::Lexer::recordStartPos()
|
---|
| 1019 | {
|
---|
| 1020 | startlineno = yylineno;
|
---|
| 1021 | startcolumn = yycolumn;
|
---|
| 1022 | }
|
---|
| 1023 |
|
---|
| 1024 | bool QScript::Lexer::scanRegExp(RegExpBodyPrefix prefix)
|
---|
| 1025 | {
|
---|
| 1026 | pos16 = 0;
|
---|
| 1027 | bool lastWasEscape = false;
|
---|
| 1028 |
|
---|
| 1029 | if (prefix == EqualPrefix)
|
---|
| 1030 | record16(QLatin1Char('='));
|
---|
| 1031 |
|
---|
| 1032 | while (1) {
|
---|
| 1033 | if (isLineTerminator() || current == 0) {
|
---|
| 1034 | errmsg = QLatin1String("Unterminated regular expression literal");
|
---|
| 1035 | return false;
|
---|
| 1036 | }
|
---|
| 1037 | else if (current != '/' || lastWasEscape == true)
|
---|
| 1038 | {
|
---|
| 1039 | record16(current);
|
---|
| 1040 | lastWasEscape = !lastWasEscape && (current == '\\');
|
---|
| 1041 | }
|
---|
| 1042 | else {
|
---|
| 1043 | if (driver) {
|
---|
| 1044 | Q_ASSERT_X(false, Q_FUNC_INFO, "not implemented");
|
---|
| 1045 | pattern = 0; // driver->intern(buffer16, pos16);
|
---|
| 1046 | } else
|
---|
| 1047 | pattern = 0;
|
---|
| 1048 | pos16 = 0;
|
---|
| 1049 | shift(1);
|
---|
| 1050 | break;
|
---|
| 1051 | }
|
---|
| 1052 | shift(1);
|
---|
| 1053 | }
|
---|
| 1054 |
|
---|
| 1055 | flags = 0;
|
---|
| 1056 | while (isIdentLetter(current)) {
|
---|
| 1057 | // current version was remade from this line:
|
---|
| 1058 | //int flag = QScript::Ecma::RegExp::flagFromChar(current);
|
---|
| 1059 | //code was "inlined" because it was only one call to this function
|
---|
| 1060 | int flag;
|
---|
| 1061 | switch (current) {
|
---|
| 1062 | case 'g': flag = 0x01; break;
|
---|
| 1063 | case 'm': flag = 0x02; break;
|
---|
| 1064 | case 'i': flag = 0x04; break;
|
---|
| 1065 | default: flag = 0;
|
---|
| 1066 | }
|
---|
| 1067 | if (flag == 0) {
|
---|
| 1068 | errmsg = QString::fromLatin1("Invalid regular expression flag '%0'")
|
---|
| 1069 | .arg(QChar(current));
|
---|
| 1070 | return false;
|
---|
| 1071 | }
|
---|
| 1072 | flags |= flag;
|
---|
| 1073 | record16(current);
|
---|
| 1074 | shift(1);
|
---|
| 1075 | }
|
---|
| 1076 |
|
---|
| 1077 | return true;
|
---|
| 1078 | }
|
---|
| 1079 |
|
---|
| 1080 | void QScript::Lexer::syncProhibitAutomaticSemicolon()
|
---|
| 1081 | {
|
---|
| 1082 | if (parenthesesState == BalancedParentheses) {
|
---|
| 1083 | // we have seen something like "if (foo)", which means we should
|
---|
| 1084 | // never insert an automatic semicolon at this point, since it would
|
---|
| 1085 | // then be expanded into an empty statement (ECMA-262 7.9.1)
|
---|
| 1086 | prohibitAutomaticSemicolon = true;
|
---|
| 1087 | parenthesesState = IgnoreParentheses;
|
---|
| 1088 | } else {
|
---|
| 1089 | prohibitAutomaticSemicolon = false;
|
---|
| 1090 | }
|
---|
| 1091 | }
|
---|
| 1092 |
|
---|
| 1093 | QT_END_NAMESPACE
|
---|