]> git.saurik.com Git - cycript.git/blob - Cycript.l.in
Port to Substrate: use cynject (this is GPL-safe).
[cycript.git] / Cycript.l.in
1 /* Cycript - Optimizing JavaScript Compiler/Runtime
2 * Copyright (C) 2009-2014 Jay Freeman (saurik)
3 */
4
5 /* GNU Affero General Public License, Version 3 {{{ */
6 /*
7 * This program is free software: you can redistribute it and/or modify
8 * it under the terms of the GNU Affero General Public License as published by
9 * the Free Software Foundation, either version 3 of the License, or
10 * (at your option) any later version.
11
12 * This program is distributed in the hope that it will be useful,
13 * but WITHOUT ANY WARRANTY; without even the implied warranty of
14 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
15 * GNU Affero General Public License for more details.
16
17 * You should have received a copy of the GNU Affero General Public License
18 * along with this program. If not, see <http://www.gnu.org/licenses/>.
19 **/
20 /* }}} */
21
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 */
23
24 %{
25
26 #if defined(__clang__)
27 #pragma clang diagnostic push
28 #pragma clang diagnostic ignored "-Wunknown-pragmas"
29 #pragma clang diagnostic ignored "-Wdeprecated-register"
30 #endif
31
32 #define YYLTYPE cy::location
33 #include "Cycript.tab.hh"
34 typedef cy::parser::token tk;
35
36 #include "Highlight.hpp"
37
38 #define YY_EXTRA_TYPE CYDriver *
39
40 // do /not/ fold token to the return: this is a macro and the ordering is dependent
41 #define F(value, highlight) do { \
42 int token(value); \
43 @begin ObjectiveC
44 yyextra->no_.AtImplementation = false; \
45 @end
46 yyextra->no_.Function = false; \
47 yyextra->no_.OpenBrace = false; \
48 yylval->highlight_ = highlight; \
49 return token; \
50 } while (false)
51
52 #define A new($pool)
53 #define Y $pool.strmemdup(yytext, yyleng)
54
55 #define I(type, Type, value, highlight) do { \
56 yylval->type ## _ = A CY ## Type; \
57 F(value, highlight); \
58 } while (false)
59
60 #define T yylval->newline_ = yyextra->state_ == CYNewLine; BEGIN(Div);
61 #define C T yyextra->state_ = CYClear;
62 #define R T yyextra->state_ = CYRestricted;
63
64 #define N \
65 if (yyextra->state_ != CYNewLine) { \
66 if (yyextra->state_ != CYRestricted) \
67 yyextra->state_ = CYNewLine; \
68 else { \
69 yyextra->state_ = CYClear; \
70 F(tk::NewLine, hi::Nothing); \
71 } \
72 }
73
74 #define V(more) { \
75 if (const char *nl = reinterpret_cast<const char *>(memchr(yytext, '\n', yyleng))) { \
76 unsigned lines(0); \
77 size_t left; \
78 do { \
79 ++lines; \
80 left = yyleng - (nl - yytext) - 1; \
81 nl = reinterpret_cast<const char *>(memchr(nl + 1, '\n', left)); \
82 } while (nl != NULL); \
83 yylloc->end.lines(lines); \
84 yylloc->end.columns(left); \
85 yylloc->step(); \
86 more \
87 } else L \
88 }
89
90 #define L { \
91 yylloc->step(); \
92 yylloc->columns(yyleng); \
93 }
94
95 #define M { \
96 if (yyextra->commented_) { \
97 I(comment, Comment(Y), tk::Comment, hi::Comment); \
98 } \
99 }
100
101 int H(char c) {
102 if (c >= '0' && c <= '9')
103 return c - '0';
104 if (c >= 'a' && c <= 'f')
105 return c - 'a' + 10;
106 if (c >= 'A' && c <= 'F')
107 return c - 'A' + 10;
108 return -1;
109 }
110
111 #define YY_INPUT(data, value, size) { \
112 if (yyextra->data_.eof()) \
113 value = YY_NULL; \
114 else { \
115 yyextra->data_.read(data, size); \
116 size_t copy(yyextra->data_.gcount()); \
117 value = copy == 0 ? YY_NULL : copy; \
118 } \
119 }
120
121 %}
122
123 %option prefix="cy"
124 %option bison-bridge
125 %option bison-locations
126 %option noyywrap
127 %option yylineno
128 %option nounput
129 %option batch
130 %option never-interactive
131 %option reentrant
132 %option stack
133
134 Exponent [eE][+-]?[0-9]+
135 Escape \\[\\'"bfnrtv]|\\0|\\x[0-9a-fA-F]{2}|\\u[0-9a-fA-F]{4}|\\\n
136
137 IdentifierStart [a-zA-Z$_]
138 IdentifierPart [a-zA-Z$_0-9]
139
140 NonTerminator [^\n]
141 BackslashSequence \\{NonTerminator}
142 RegularExpressionFirstChar [^\n*\\/]|{BackslashSequence}
143 RegularExpressionChar [^\n\\/]|{BackslashSequence}
144 RegularExpressionFlags {IdentifierPart}*
145 RegularExpressionChars {RegularExpressionChar}*
146 RegularExpressionBody {RegularExpressionFirstChar}{RegularExpressionChars}
147
148 @begin E4X
149 XMLNameStart [a-zA-Z_:]
150 XMLNamePart [a-zA-Z0-9.-_:]
151 XMLName {XMLNameStart}{XMLNamePart}*
152 @end
153
154 %s Div
155 %s RegExp
156
157 @begin E4X
158 %x XMLContent
159 %x XMLTag
160 @end
161
162 %%
163
164 <RegExp>\/{RegularExpressionBody}\/{RegularExpressionFlags} L C I(literal, RegEx(Y), tk::RegularExpressionLiteral, hi::Constant);
165
166 #![^\n]* L M
167
168 \/\/[^\n]* L M
169
170 /* http://ostermiller.org/findcomment.html */
171 /* XXX: unify these two rules using !? */
172 \/\*!([^*]|[\r\n]|(\*+([^*/]|[\r\n])))*\*+\/ V() C I(comment, Comment(Y), tk::Comment, hi::Comment);
173 \/\*([^*]|[\r\n]|(\*+([^*/]|[\r\n])))*\*+\/ V(N) M
174
175 @begin E4X
176 <RegExp>"<>" L F(tk::LeftRight, hi::Structure);
177 <XMLContent>"</>" L F(tk::LeftSlashRight, hi::Structure);
178
179 <RegExp,XMLContent>\<!\[CDATA\[(\n|[^[]|\[[^[]|\[\[[^>])*]]> V() F(tk::XMLCDATA, hi::Constant);
180 <RegExp,XMLContent>\<!--(\n|[^-]|-[^-])*--> V() F(tk::XMLComment, hi::Comment);
181 <RegExp,XMLContent>\<?(\n|[^?]|\?[^>])*?> V() F(tk::XMLPI, hi::Meta);
182
183 <XMLTag>"=" L F(tk::Equal, hi::Structure);
184 <XMLTag>">" L F(tk::Right, hi::Structure);
185 <XMLTag>"/>" L F(tk::SlashRight, hi::Structure);
186 <XMLTag>"{" L F(tk::OpenBrace, hi::Structure);
187
188 <XMLTag>\"(\n|[^"])*\"|'(\n|[^'])*' V() F(tk::XMLAttributeValue, hi::Constant);
189 <XMLTag>{XMLName} L F(tk::XMLName, hi::Identifier);
190 <XMLTag>[ \t\r\n] V() F(tk::XMLWhitespace, hi::Nothing);
191
192 <XMLContent>"{" L F(tk::OpenBrace, hi::Structure);
193 <XMLContent>"<" L F(tk::Left, hi::Structure);
194 <XMLContent>"</" L F(tk::LeftSlash, hi::Structure);
195 @end
196
197 "..." L C F(tk::PeriodPeriodPeriod, hi::Meta);
198
199 @begin E4X
200 "::" L C F(tk::ColonColon, hi::Operator);
201 ".." L C F(tk::PeriodPeriod, hi::Operator);
202 @end
203
204 @begin E4X ObjectiveC
205 "@" L C F(tk::At, hi::Operator);
206 "#" L C F(tk::Pound, hi::Operator);
207 @end
208
209 "&" L C F(tk::Ampersand, hi::Operator);
210 "&&" L C F(tk::AmpersandAmpersand, hi::Operator);
211 "&=" L C F(tk::AmpersandEqual, hi::Operator);
212 "^" L C F(tk::Carrot, hi::Operator);
213 "^=" L C F(tk::CarrotEqual, hi::Operator);
214 "=" L C F(tk::Equal, hi::Operator);
215 "==" L C F(tk::EqualEqual, hi::Operator);
216 "===" L C F(tk::EqualEqualEqual, hi::Operator);
217 "=>" L C F(tk::EqualRight, hi::Operator);
218 "!" L C F(tk::Exclamation, hi::Operator);
219 "!=" L C F(tk::ExclamationEqual, hi::Operator);
220 "!==" L C F(tk::ExclamationEqualEqual, hi::Operator);
221 "-" L C F(tk::Hyphen, hi::Operator);
222 "-=" L C F(tk::HyphenEqual, hi::Operator);
223 "--" L C F(yylval->newline_ ? tk::HyphenHyphen_ : tk::HyphenHyphen, hi::Operator);
224 "->" L C F(tk::HyphenRight, hi::Operator);
225 "<" L C F(tk::Left, hi::Operator);
226 "<=" L C F(tk::LeftEqual, hi::Operator);
227 "<<" L C F(tk::LeftLeft, hi::Operator);
228 "<<=" L C F(tk::LeftLeftEqual, hi::Operator);
229 "%" L C F(tk::Percent, hi::Operator);
230 "%=" L C F(tk::PercentEqual, hi::Operator);
231 "." L C F(tk::Period, hi::Operator);
232 "|" L C F(tk::Pipe, hi::Operator);
233 "|=" L C F(tk::PipeEqual, hi::Operator);
234 "||" L C F(tk::PipePipe, hi::Operator);
235 "+" L C F(tk::Plus, hi::Operator);
236 "+=" L C F(tk::PlusEqual, hi::Operator);
237 "++" L C F(yylval->newline_ ? tk::PlusPlus_ : tk::PlusPlus, hi::Operator);
238 ">" L C F(tk::Right, hi::Operator);
239 ">=" L C F(tk::RightEqual, hi::Operator);
240 ">>" L C F(tk::RightRight, hi::Operator);
241 ">>=" L C F(tk::RightRightEqual, hi::Operator);
242 ">>>" L C F(tk::RightRightRight, hi::Operator);
243 ">>>=" L C F(tk::RightRightRightEqual, hi::Operator);
244 "*" L C F(tk::Star, hi::Operator);
245 "*=" L C F(tk::StarEqual, hi::Operator);
246 "~" L C F(tk::Tilde, hi::Operator);
247
248 <Div>"/" L C F(tk::Slash, hi::Operator);
249 <Div>"/=" L C F(tk::SlashEqual, hi::Operator);
250
251 ":" L C F(tk::Colon, hi::Structure);
252 "," L C F(tk::Comma, hi::Structure);
253 "?" L C F(tk::Question, hi::Structure);
254 ";" L C F(tk::SemiColon, hi::Structure);
255
256 "(" L C F(tk::OpenParen, hi::Structure);
257 ")" L C F(tk::CloseParen, hi::Structure);
258
259 "{" L C F(yyextra->no_.OpenBrace ? tk::OpenBrace__ : yylval->newline_ ? tk::OpenBrace_ : tk::OpenBrace, hi::Structure);
260 "}" L C F(tk::CloseBrace, hi::Structure);
261
262 "[" L C F(tk::OpenBracket, hi::Structure);
263 "]" L C F(tk::CloseBracket, hi::Structure);
264
265 "@error" L C F(tk::AtError, hi::Error);
266
267 @begin Java
268 "@class" L C F(tk::AtClass, hi::Meta);
269 @end
270
271 @begin C
272 "typedef" L C I(identifier, Identifier("typedef"), tk::Typedef, hi::Meta);
273 "unsigned" L C I(identifier, Identifier("unsigned"), tk::Unsigned, hi::Type);
274 "signed" L C I(identifier, Identifier("signed"), tk::Signed, hi::Type);
275 "extern" L C I(identifier, Identifier("extern"), tk::Extern, hi::Type);
276 @end
277
278 @begin C
279 "@encode" L C F(tk::AtEncode, hi::Meta);
280 @end
281
282 @begin ObjectiveC
283 "@end" L C F(tk::AtEnd, hi::Meta);
284 "@implementation" L C F(yyextra->no_.AtImplementation ? tk::AtImplementation_ : tk::AtImplementation, hi::Meta);
285 "@import" L C F(tk::AtImport, hi::Special);
286 "@selector" L C F(tk::AtSelector, hi::Meta);
287
288 "NULL" L C I(identifier, Identifier("NULL"), tk::Identifier_, hi::Constant);
289 "nil" L C I(identifier, Identifier("nil"), tk::Identifier_, hi::Constant);
290 "YES" L C I(identifier, Identifier("YES"), tk::Yes, hi::Constant);
291 "NO" L C I(identifier, Identifier("NO"), tk::No, hi::Constant);
292
293 "bool" L C I(identifier, Identifier("bool"), tk::Identifier_, hi::Type);
294 "BOOL" L C I(identifier, Identifier("BOOL"), tk::Identifier_, hi::Type);
295 "id" L C I(identifier, Identifier("id"), tk::Identifier_, hi::Type);
296 "SEL" L C I(identifier, Identifier("SEL"), tk::Identifier_, hi::Type);
297 @end
298
299 "undefined" L C I(identifier, Identifier("undefined"), tk::Identifier_, hi::Operator);
300
301 "false" L C I(false, False(), tk::False, hi::Constant);
302 "null" L C I(null, Null(), tk::Null, hi::Constant);
303 "true" L C I(true, True(), tk::True, hi::Constant);
304
305 "auto" L C I(word, Word("auto"), tk::Auto, hi::Meta);
306 "break" L R I(word, Word("break"), tk::Break, hi::Control);
307 "case" L C I(word, Word("case"), tk::Case, hi::Control);
308 "catch" L C I(word, Word("catch"), tk::Catch, hi::Control);
309 "continue" L R I(word, Word("continue"), tk::Continue, hi::Control);
310 "default" L C I(word, Word("default"), tk::Default, hi::Control);
311 "delete" L C I(word, Word("delete"), tk::Delete, hi::Operator);
312 "do" L C I(word, Word("do"), tk::Do, hi::Control);
313 "else" L C I(word, Word("else"), tk::Else, hi::Control);
314 "finally" L C I(word, Word("finally"), tk::Finally, hi::Control);
315 "for" L C I(word, Word("for"), tk::For, hi::Control);
316 "function" L C I(word, Word("function"), yyextra->no_.Function ? tk::Function_ : tk::Function, hi::Meta);
317 "if" L C I(word, Word("if"), tk::If, hi::Control);
318 "in" L C I(word, Word("in"), yyextra->in_.top() ? tk::In_ : tk::In, hi::Operator);
319 "instanceof" L C I(word, Word("instanceof"), tk::InstanceOf, hi::Operator);
320 "new" L C I(word, Word("new"), tk::New, hi::Operator);
321 "return" L R I(word, Word("return"), tk::Return, hi::Control);
322 "switch" L C I(word, Word("switch"), tk::Switch, hi::Control);
323 "this" L C I(this, This(), tk::This, hi::Constant);
324 "throw" L R I(word, Word("throw"), tk::Throw, hi::Control);
325 "try" L C I(word, Word("try"), tk::Try, hi::Control);
326 "typeof" L C I(word, Word("typeof"), tk::TypeOf, hi::Operator);
327 "var" L C I(word, Word("var"), tk::Var, hi::Meta);
328 "void" L C I(word, Word("void"), tk::Void, hi::Operator);
329 "while" L C I(word, Word("while"), tk::While, hi::Control);
330 "with" L C I(word, Word("with"), tk::With, hi::Control);
331
332 "debugger" L C I(word, Word("debugger"), tk::Debugger, hi::Meta);
333
334 "const" L C I(word, Word("const"), tk::Const, hi::Meta);
335
336 "class" L C I(word, Word("class"), tk::Class, hi::Meta);
337 "enum" L C I(word, Word("enum"), tk::Enum, hi::Meta);
338 "export" L C I(word, Word("export"), tk::Export, hi::Meta);
339 "extends" L C I(word, Word("extends"), tk::Extends, hi::Meta);
340 "import" L C I(word, Word("import"), tk::Import, hi::Meta);
341 "super" L C I(word, Word("super"), tk::Super, hi::Constant);
342
343 "implements" L C I(identifier, Identifier("implements"), tk::Implements, hi::Meta);
344 "interface" L C I(identifier, Identifier("interface"), tk::Interface, hi::Meta);
345 "package" L C I(identifier, Identifier("package"), tk::Package, hi::Meta);
346 "private" L C I(identifier, Identifier("private"), tk::Private, hi::Meta);
347 "protected" L C I(identifier, Identifier("protected"), tk::Protected, hi::Meta);
348 "public" L C I(identifier, Identifier("public"), tk::Public, hi::Meta);
349 "static" L C I(identifier, Identifier("static"), tk::Static, hi::Meta);
350
351 "abstract" L C I(identifier, Identifier("abstract"), tk::Abstract, hi::Meta);
352 "boolean" L C I(identifier, Identifier("boolean"), tk::Boolean, hi::Type);
353 "byte" L C I(identifier, Identifier("byte"), tk::Byte, hi::Type);
354 "char" L C I(identifier, Identifier("char"), tk::Char, hi::Type);
355 "double" L C I(identifier, Identifier("double"), tk::Double, hi::Type);
356 "final" L C I(identifier, Identifier("final"), tk::Final, hi::Meta);
357 "float" L C I(identifier, Identifier("float"), tk::Float, hi::Type);
358 "goto" L C I(identifier, Identifier("goto"), tk::Goto, hi::Control);
359 "int" L C I(identifier, Identifier("int"), tk::Int, hi::Type);
360 "long" L C I(identifier, Identifier("long"), tk::Long, hi::Type);
361 "native" L C I(identifier, Identifier("native"), tk::Native, hi::Meta);
362 "short" L C I(identifier, Identifier("short"), tk::Short, hi::Type);
363 "synchronized" L C I(identifier, Identifier("synchronized"), tk::Synchronized, hi::Meta);
364 "throws" L C I(identifier, Identifier("throws"), tk::Throws, hi::Meta);
365 "transient" L C I(identifier, Identifier("transient"), tk::Transient, hi::Meta);
366 "volatile" L C I(identifier, Identifier("volatile"), tk::Volatile, hi::Meta);
367
368 "let" L C I(identifier, Identifier("let"), tk::Let, hi::Meta);
369 "yield" L C I(identifier, Identifier("yield"), tk::Yield, hi::Control);
370
371 "each" L C I(identifier, Identifier("each"), tk::Each, hi::Control);
372 "of" L C I(identifier, Identifier("of"), tk::Of, hi::Operator);
373
374 @begin E4X
375 "namespace" L C I(identifier, Identifier("namespace"), tk::Namespace, hi::Meta);
376 "xml" L C I(identifier, Identifier("xml"), tk::XML, hi::Meta);
377 @end
378
379 {IdentifierStart}{IdentifierPart}* L C I(identifier, Identifier(Y), tk::Identifier_, hi::Identifier);
380
381 (\.[0-9]+|(0|[1-9][0-9]*)(\.[0-9]*)?){Exponent}? L C I(number, Number(strtod(yytext, NULL)), tk::NumericLiteral, hi::Constant);
382
383 0[xX][0-9a-fA-F]+ L C I(number, Number(strtoull(yytext + 2, NULL, 16)), tk::NumericLiteral, hi::Constant);
384 0[0-7]+ L C I(number, Number(strtoull(yytext + 1, NULL, 8)), tk::NumericLiteral, hi::Constant);
385 0[bB][0-1]+ L C I(number, Number(strtoull(yytext + 2, NULL, 2)), tk::NumericLiteral, hi::Constant);
386
387 \"([^"\\\n]|{Escape})*\"|'([^'\\\n]|{Escape})*' L C {
388 char *value(A char[yyleng]);
389 char *local(value);
390
391 for (yy_size_t i(1), e(yyleng - 1); i != e; ++i) {
392 char next(yytext[i]);
393
394 if (yytext[i] == '\\')
395 switch (next = yytext[++i]) {
396 case '\n': continue;
397 case '\\': next = '\\'; break;
398 case '\'': next = '\''; break;
399 case '"': next = '"'; break;
400 case 'b': next = '\b'; break;
401 case 'f': next = '\f'; break;
402 case 'n': next = '\n'; break;
403 case 'r': next = '\r'; break;
404 case 't': next = '\t'; break;
405 case 'v': next = '\v'; break;
406 case '0': next = '\0'; break;
407
408 case 'x':
409 next = H(yytext[i + 1]) << 4 | H(yytext[i + 2]);
410 i += 2;
411 break;
412 }
413
414 *local++ = next;
415 }
416
417 *local = '\0';
418 I(string, String(value, local - value), tk::StringLiteral, hi::Constant);
419 }
420
421 \r?\n|\r|\xe2\x80[\xa8\xa9] yylloc->end.lines(); yylloc->step(); N
422
423 [ \t] L
424
425 <<EOF>> if (yyextra->auto_) { yyextra->auto_ = false; F(tk::AutoComplete, hi::Nothing); } L yyterminate();
426
427 . L {
428 CYDriver::Error error;
429 error.location_ = *yylloc;
430 error.message_ = "syntax error, unknown token";
431 yyextra->errors_.push_back(error);
432 yyterminate();
433 }
434
435 %%
436
437 void CYDriver::ScannerInit() {
438 cylex_init(&scanner_);
439 cyset_extra(this, scanner_);
440 }
441
442 void CYDriver::ScannerDestroy() {
443 cylex_destroy(scanner_);
444 }
445
446 CYDriver::Condition CYDriver::GetCondition() {
447 switch (yy_top_state(scanner_)) {
448 case RegExp:
449 return RegExpCondition;
450 @begin E4X
451 case XMLContent:
452 return XMLContentCondition;
453 case XMLTag:
454 return XMLTagCondition;
455 @end
456 default:
457 _assert(false);
458 }
459 }
460
461 void CYDriver::SetCondition(Condition condition) {
462 struct yyguts_t *yyg(reinterpret_cast<struct yyguts_t *>(scanner_));
463
464 switch (condition) {
465 case RegExpCondition:
466 BEGIN(RegExp);
467 break;
468 @begin E4X
469 case XMLContentCondition:
470 BEGIN(XMLContent);
471 break;
472 case XMLTagCondition:
473 BEGIN(XMLTag);
474 break;
475 @end
476 default:
477 _assert(false);
478 }
479 }
480
481 void CYDriver::PushCondition(Condition condition) {
482 switch (condition) {
483 case RegExpCondition:
484 yy_push_state(RegExp, scanner_);
485 break;
486 @begin E4X
487 case XMLContentCondition:
488 yy_push_state(XMLContent, scanner_);
489 break;
490 case XMLTagCondition:
491 yy_push_state(XMLTag, scanner_);
492 break;
493 @end
494 default:
495 _assert(false);
496 }
497 }
498
499 void CYDriver::PopCondition() {
500 yy_pop_state(scanner_);
501 }
502
503 #if defined(__clang__)
504 #pragma clang diagnostic pop
505 #endif