1 /* Cycript - Optimizing JavaScript Compiler/Runtime
2 * Copyright (C) 2009-2010 Jay Freeman (saurik)
5 /* GNU Lesser General Public License, Version 3 {{{ */
7 * Cycript is free software: you can redistribute it and/or modify it under
8 * the terms of the GNU Lesser General Public License as published by the
9 * Free Software Foundation, either version 3 of the License, or (at your
10 * option) any later version.
12 * Cycript is distributed in the hope that it will be useful, but WITHOUT
13 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
14 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public
15 * License for more details.
17 * You should have received a copy of the GNU Lesser General Public License
18 * along with Cycript. If not, see <http://www.gnu.org/licenses/>.
22 /* XXX: supposedly I will be screwed on very very long multi-line comments and need to replace these with a manual lexer. http://websrv.cs.fsu.edu/~engelen/courses/COP5621/Pr2.pdf */
25 #define YYLTYPE cy::location
26 #include "Cycript.tab.hh"
27 typedef cy::parser::token tk;
29 #define YY_EXTRA_TYPE CYDriver *
32 #define Y apr_pstrmemdup($pool, yytext, yyleng)
34 #define I(type, Type, Name) do { \
35 yylval->type ## _ = A CY ## Type; \
39 #define T yylval->newline_ = yyextra->state_ == CYNewLine; BEGIN(Div);
40 #define C T yyextra->state_ = CYClear;
41 #define R T yyextra->state_ = CYRestricted;
43 #define E L C I(literal, RegEx(Y), RegularExpressionLiteral);
46 if (yyextra->state_ != CYNewLine) { \
47 if (yyextra->state_ != CYRestricted) \
48 yyextra->state_ = CYNewLine; \
50 yyextra->state_ = CYClear; \
56 if (const char *nl = reinterpret_cast<const char *>(memchr(yytext, '\n', yyleng))) { \
61 left = yyleng - (nl - yytext) - 1; \
62 nl = reinterpret_cast<const char *>(memchr(nl + 1, '\n', left)); \
63 } while (nl != NULL); \
64 yylloc->end.lines(lines); \
65 yylloc->end.columns(left); \
73 yylloc->columns(yyleng); \
77 if (c >= '0' && c <= '9')
79 if (c >= 'a' && c <= 'f')
81 if (c >= 'A' && c <= 'F')
86 #define YY_INPUT(data, value, size) { \
87 if (yyextra->file_ != NULL) { \
88 size_t copy(fread(data, 1, size, yyextra->file_)); \
89 value = copy == 0 ? YY_NULL : copy; \
90 } else if (yyextra->size_ == 0) \
94 copy = (std::min(copy, yyextra->size_)); \
95 memcpy(data, yyextra->data_, copy); \
96 yyextra->data_ += copy; \
97 yyextra->size_ -= copy; \
106 %option bison-locations
114 Exponent [eE][+-]?[0-9]+
115 Escape \\[\\'"bfnrtv]|\\0|\\x[0-9a-fA-F]{2}|\\u[0-9a-fA-F]{4}|\\\n
117 IdentifierStart [a-zA-Z$_]
118 IdentifierPart [a-zA-Z$_0-9]
121 BackslashSequence \\{NonTerminator}
122 RegularExpressionFirstChar [^\n*\\/]|{BackslashSequence}
123 RegularExpressionChar [^\n\\/]|{BackslashSequence}
124 RegularExpressionFlags {IdentifierPart}*
125 RegularExpressionChars {RegularExpressionChar}*
126 RegularExpressionBody {RegularExpressionFirstChar}{RegularExpressionChars}
129 XMLNameStart [a-zA-Z_:]
130 XMLNamePart [a-zA-Z0-9.-_:]
131 XMLName {XMLNameStart}{XMLNamePart}*
144 <RegExp>\/{RegularExpressionBody}\/{RegularExpressionFlags} E
148 /* http://ostermiller.org/findcomment.html */
149 /* XXX: unify these two rules using !? */
150 \/\*!([^*]|[\r\n]|(\*+([^*/]|[\r\n])))*\*+\/ V() C I(comment, Comment(Y), Comment);
151 \/\*([^*]|[\r\n]|(\*+([^*/]|[\r\n])))*\*+\/ V(N)
154 <RegExp>"<>" L return tk::LeftRight;
155 <XMLContent>"</>" L return tk::LeftSlashRight;
157 <RegExp,XMLContent>\<!\[CDATA\[(\n|[^[]|\[[^[]|\[\[[^>])*]]> V() return tk::XMLCDATA;
158 <RegExp,XMLContent>\<!--(\n|[^-]|-[^-])*--> V() return tk::XMLComment;
159 <RegExp,XMLContent>\<?(\n|[^?]|\?[^>])*?> V() return tk::XMLPI;
161 <XMLTag>"=" L return tk::Equal;
162 <XMLTag>">" L return tk::Right;
163 <XMLTag>"/>" L return tk::SlashRight;
164 <XMLTag>"{" L return tk::OpenBrace;
166 <XMLTag>\"(\n|[^"])*\"|'(\n|[^'])*' V() return tk::XMLAttributeValue;
167 <XMLTag>{XMLName} L return tk::XMLName;
168 <XMLTag>[ \t\r\n] V() return tk::XMLWhitespace;
170 <XMLContent>"{" L return tk::OpenBrace;
171 <XMLContent>"<" L return tk::Left;
172 <XMLContent>"</" L return tk::LeftSlash;
175 "..." L C return tk::PeriodPeriodPeriod;
178 "::" L C return tk::ColonColon;
179 ".." L C return tk::PeriodPeriod;
182 @begin E4X ObjectiveC
183 "@" L C return tk::At;
186 "&" L C return tk::Ampersand;
187 "&&" L C return tk::AmpersandAmpersand;
188 "&=" L C return tk::AmpersandEqual;
189 "^" L C return tk::Carrot;
190 "^=" L C return tk::CarrotEqual;
191 "=" L C return tk::Equal;
192 "==" L C return tk::EqualEqual;
193 "===" L C return tk::EqualEqualEqual;
194 "!" L C return tk::Exclamation;
195 "!=" L C return tk::ExclamationEqual;
196 "!==" L C return tk::ExclamationEqualEqual;
197 "-" L C return tk::Hyphen;
198 "-=" L C return tk::HyphenEqual;
199 "--" L C return yylval->newline_ ? tk::HyphenHyphen_ : tk::HyphenHyphen;
200 "->" L C return tk::HyphenRight;
201 "<" L C return tk::Left;
202 "<=" L C return tk::LeftEqual;
203 "<<" L C return tk::LeftLeft;
204 "<<=" L C return tk::LeftLeftEqual;
205 "%" L C return tk::Percent;
206 "%=" L C return tk::PercentEqual;
207 "." L C return tk::Period;
208 "|" L C return tk::Pipe;
209 "|=" L C return tk::PipeEqual;
210 "||" L C return tk::PipePipe;
211 "+" L C return tk::Plus;
212 "+=" L C return tk::PlusEqual;
213 "++" L C return yylval->newline_ ? tk::PlusPlus_ : tk::PlusPlus;
214 ">" L C return tk::Right;
215 ">=" L C return tk::RightEqual;
216 ">>" L C return tk::RightRight;
217 ">>=" L C return tk::RightRightEqual;
218 ">>>" L C return tk::RightRightRight;
219 ">>>=" L C return tk::RightRightRightEqual;
220 "*" L C return tk::Star;
221 "*=" L C return tk::StarEqual;
222 "~" L C return tk::Tilde;
224 <Div>"/" L C return tk::Slash;
225 <Div>"/=" L C return tk::SlashEqual;
227 ":" L C return tk::Colon;
228 "," L C return tk::Comma;
229 "?" L C return tk::Question;
230 ";" L C return tk::SemiColon;
232 "(" L C return tk::OpenParen;
233 ")" L C return tk::CloseParen;
235 "{" L C return yylval->newline_ ? tk::OpenBrace_ : tk::OpenBrace;
236 "}" L C return tk::CloseBrace;
238 "[" L C return tk::OpenBracket;
239 "]" L C return tk::CloseBracket;
242 "@class" L C return tk::AtClass;
246 "@end" L C return tk::AtEnd;
247 "@implementation" L C return tk::AtImplementation;
248 "@import" L C return tk::AtImport;
249 "@selector" L C return tk::AtSelector;
252 "false" L C I(false, False(), False);
253 "null" L C I(null, Null(), Null);
254 "true" L C I(true, True(), True);
256 "break" L R I(word, Word("break"), Break);
257 "case" L C I(word, Word("case"), Case);
258 "catch" L C I(word, Word("catch"), Catch);
259 "continue" L R I(word, Word("continue"), Continue);
260 "default" L C I(word, Word("default"), Default);
261 "delete" L C I(word, Word("delete"), Delete);
262 "do" L C I(word, Word("do"), Do);
263 "else" L C I(word, Word("else"), Else);
264 "finally" L C I(word, Word("finally"), Finally);
265 "for" L C I(word, Word("for"), For);
266 "function" L C I(word, Word("function"), Function);
267 "if" L C I(word, Word("if"), If);
268 "in" L C I(word, Word("in"), In);
269 "instanceof" L C I(word, Word("instanceof"), InstanceOf);
270 "new" L C I(word, Word("new"), New);
271 "return" L R I(word, Word("return"), Return);
272 "switch" L C I(word, Word("switch"), Switch);
273 "this" L C I(this, This(), This);
274 "throw" L R I(word, Word("throw"), Throw);
275 "try" L C I(word, Word("try"), Try);
276 "typeof" L C I(word, Word("typeof"), TypeOf);
277 "var" L C I(word, Word("var"), Var);
278 "void" L C I(word, Word("void"), Void);
279 "while" L C I(word, Word("while"), While);
280 "with" L C I(word, Word("with"), With);
282 "debugger" L C I(word, Word("debugger"), Debugger);
284 "const" L C I(word, Word("const"), Const);
286 "class" L C I(word, Word("class"), Class);
287 "enum" L C I(word, Word("enum"), Enum);
288 "export" L C I(word, Word("export"), Export);
289 "extends" L C I(word, Word("extends"), Extends);
290 "import" L C I(word, Word("import"), Import);
291 "super" L C I(word, Word("super"), Super);
293 "implements" L C I(identifier, Identifier("implements"), Implements);
294 "interface" L C I(identifier, Identifier("interface"), Interface);
295 "package" L C I(identifier, Identifier("package"), Package);
296 "private" L C I(identifier, Identifier("private"), Private);
297 "protected" L C I(identifier, Identifier("protected"), Protected);
298 "public" L C I(identifier, Identifier("public"), Public);
299 "static" L C I(identifier, Identifier("static"), Static);
301 "abstract" L C I(identifier, Identifier("abstract"), Abstract);
302 "boolean" L C I(identifier, Identifier("boolean"), Boolean);
303 "byte" L C I(identifier, Identifier("byte"), Byte);
304 "char" L C I(identifier, Identifier("char"), Char);
305 "double" L C I(identifier, Identifier("double"), Double);
306 "final" L C I(identifier, Identifier("final"), Final);
307 "float" L C I(identifier, Identifier("float"), Float);
308 "goto" L C I(identifier, Identifier("goto"), Goto);
309 "int" L C I(identifier, Identifier("int"), Int);
310 "long" L C I(identifier, Identifier("long"), Long);
311 "native" L C I(identifier, Identifier("native"), Native);
312 "short" L C I(identifier, Identifier("short"), Short);
313 "synchronized" L C I(identifier, Identifier("synchronized"), Synchronized);
314 "throws" L C I(identifier, Identifier("throws"), Throws);
315 "transient" L C I(identifier, Identifier("transient"), Transient);
316 "volatile" L C I(identifier, Identifier("volatile"), Volatile);
318 "let" L C I(identifier, Identifier("let"), Let);
319 "yield" L C I(identifier, Identifier("yield"), Yield);
321 "each" L C I(identifier, Identifier("each"), Each);
324 "namespace" L C I(identifier, Identifier("namespace"), Namespace);
325 "xml" L C I(identifier, Identifier("xml"), XML);
328 {IdentifierStart}{IdentifierPart}* L C I(identifier, Identifier(Y), Identifier_);
330 (\.[0-9]+|(0|[1-9][0-9]*)(\.[0-9]*)?){Exponent}? L C I(number, Number(strtod(yytext, NULL)), NumericLiteral);
332 0[xX][0-9a-fA-F]+ L C I(number, Number(strtoull(yytext + 2, NULL, 16)), NumericLiteral);
333 0[0-7]+ L C I(number, Number(strtoull(yytext + 1, NULL, 8)), NumericLiteral);
334 0[bB][0-1]+ L C I(number, Number(strtoull(yytext + 2, NULL, 2)), NumericLiteral);
336 \"([^"\\\n]|{Escape})*\"|'([^'\\\n]|{Escape})*' L C {
337 char *value(A char[yyleng]);
340 for (yy_size_t i(1), e(yyleng - 1); i != e; ++i) {
341 char next(yytext[i]);
343 if (yytext[i] == '\\')
344 switch (next = yytext[++i]) {
346 case '\\': next = '\\'; break;
347 case '\'': next = '\''; break;
348 case '"': next = '"'; break;
349 case 'b': next = '\b'; break;
350 case 'f': next = '\f'; break;
351 case 'n': next = '\n'; break;
352 case 'r': next = '\r'; break;
353 case 't': next = '\t'; break;
354 case 'v': next = '\v'; break;
355 case '0': next = '\0'; break;
358 next = H(yytext[i + 1]) << 4 | H(yytext[i + 2]);
367 I(string, String(value, local - value), StringLiteral);
370 \r?\n yylloc->end.lines(); yylloc->step(); N
374 <<EOF>> if (yyextra->auto_) { yyextra->auto_ = false; return tk::AutoComplete; } L yyterminate();
377 CYDriver::Error error;
378 error.location_ = *yylloc;
379 error.message_ = "syntax error, unknown token";
380 yyextra->errors_.push_back(error);
386 void CYDriver::ScannerInit() {
387 cylex_init(&scanner_);
388 cyset_extra(this, scanner_);
391 void CYDriver::ScannerDestroy() {
392 cylex_destroy(scanner_);
395 CYDriver::Condition CYDriver::GetCondition() {
396 switch (yy_top_state(scanner_)) {
398 return RegExpCondition;
401 return XMLContentCondition;
403 return XMLTagCondition;
410 void CYDriver::SetCondition(Condition condition) {
411 struct yyguts_t *yyg(reinterpret_cast<struct yyguts_t *>(scanner_));
414 case RegExpCondition:
418 case XMLContentCondition:
421 case XMLTagCondition:
430 void CYDriver::PushCondition(Condition condition) {
432 case RegExpCondition:
433 yy_push_state(RegExp, scanner_);
436 case XMLContentCondition:
437 yy_push_state(XMLContent, scanner_);
439 case XMLTagCondition:
440 yy_push_state(XMLTag, scanner_);
448 void CYDriver::PopCondition() {
449 yy_pop_state(scanner_);