1 %{ 2 /* 3 * Copyright © 2010 Intel Corporation 4 * 5 * Permission is hereby granted, free of charge, to any person obtaining a 6 * copy of this software and associated documentation files (the "Software"), 7 * to deal in the Software without restriction, including without limitation 8 * the rights to use, copy, modify, merge, publish, distribute, sublicense, 9 * and/or sell copies of the Software, and to permit persons to whom the 10 * Software is furnished to do so, subject to the following conditions: 11 * 12 * The above copyright notice and this permission notice (including the next 13 * paragraph) shall be included in all copies or substantial portions of the 14 * Software. 15 * 16 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 17 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 18 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 19 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 20 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 21 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 22 * DEALINGS IN THE SOFTWARE. 23 */ 24 25 #include <stdio.h> 26 #include <string.h> 27 #include <ctype.h> 28 29 #include "glcpp.h" 30 #include "glcpp-parse.h" 31 32 /* Flex annoyingly generates some functions without making them 33 * static. Let's declare them here. */ 34 int glcpp_get_column (yyscan_t yyscanner); 35 void glcpp_set_column (int column_no , yyscan_t yyscanner); 36 37 #ifdef _MSC_VER 38 #define YY_NO_UNISTD_H 39 #endif 40 41 #define YY_NO_INPUT 42 43 #define YY_USER_ACTION \ 44 do { \ 45 if (parser->has_new_line_number) \ 46 yylineno = parser->new_line_number; \ 47 if (parser->has_new_source_number) \ 48 yylloc->source = parser->new_source_number; \ 49 yylloc->first_column = yycolumn + 1; \ 50 yylloc->first_line = yylloc->last_line = yylineno; \ 51 yycolumn += yyleng; \ 52 yylloc->last_column = yycolumn + 1; \ 53 parser->has_new_line_number = 0; \ 54 parser->has_new_source_number = 0; \ 55 } while(0); 56 57 #define YY_USER_INIT \ 58 do { \ 59 yylineno = 1; \ 60 yycolumn = 0; \ 61 yylloc->source = 0; \ 62 } while(0) 63 64 /* It's ugly to have macros that have return statements inside of 65 * them, but flex-based lexer generation is all built around the 66 * return statement. 67 * 68 * To mitigate the ugliness, we defer as much of the logic as possible 69 * to an actual function, not a macro (see 70 * glcpplex_update_state_per_token) and we make the word RETURN 71 * prominent in all of the macros which may return. 72 * 73 * The most-commonly-used macro is RETURN_TOKEN which will perform all 74 * necessary state updates based on the provided token,, then 75 * conditionally return the token. It will not return a token if the 76 * parser is currently skipping tokens, (such as within #if 77 * 0...#else). 78 * 79 * The RETURN_TOKEN_NEVER_SKIP macro is a lower-level variant that 80 * makes the token returning unconditional. This is needed for things 81 * like #if and the tokens of its condition, (since these must be 82 * evaluated by the parser even when otherwise skipping). 83 * 84 * Finally, RETURN_STRING_TOKEN is a simple convenience wrapper on top 85 * of RETURN_TOKEN that performs a string copy of yytext before the 86 * return. 87 */ 88 #define RETURN_TOKEN_NEVER_SKIP(token) \ 89 do { \ 90 if (glcpp_lex_update_state_per_token (parser, token)) \ 91 return token; \ 92 } while (0) 93 94 #define RETURN_TOKEN(token) \ 95 do { \ 96 if (! parser->skipping) { \ 97 RETURN_TOKEN_NEVER_SKIP(token); \ 98 } \ 99 } while(0) 100 101 #define RETURN_STRING_TOKEN(token) \ 102 do { \ 103 if (! parser->skipping) { \ 104 /* We're not doing linear_strdup here, to avoid \ 105 * an implicit call on strlen() for the length \ 106 * of the string, as this is already found by \ 107 * flex and stored in yyleng */ \ 108 void *mem_ctx = yyextra->linalloc; \ 109 yylval->str = linear_alloc_child(mem_ctx, \ 110 yyleng + 1); \ 111 memcpy(yylval->str, yytext, yyleng + 1); \ 112 RETURN_TOKEN_NEVER_SKIP (token); \ 113 } \ 114 } while(0) 115 116 117 /* Update all state necessary for each token being returned. 118 * 119 * Here we'll be tracking newlines and spaces so that the lexer can 120 * alter its behavior as necessary, (for example, '#' has special 121 * significance if it is the first non-whitespace, non-comment token 122 * in a line, but does not otherwise). 123 * 124 * NOTE: If this function returns FALSE, then no token should be 125 * returned at all. This is used to suprress duplicate SPACE tokens. 126 */ 127 static int 128 glcpp_lex_update_state_per_token (glcpp_parser_t *parser, int token) 129 { 130 if (token != NEWLINE && token != SPACE && token != HASH_TOKEN && 131 !parser->lexing_version_directive) { 132 glcpp_parser_resolve_implicit_version(parser); 133 } 134 135 /* After the first non-space token in a line, we won't 136 * allow any '#' to introduce a directive. */ 137 if (token == NEWLINE) { 138 parser->first_non_space_token_this_line = 1; 139 } else if (token != SPACE) { 140 parser->first_non_space_token_this_line = 0; 141 } 142 143 /* Track newlines just to know whether a newline needs 144 * to be inserted if end-of-file comes early. */ 145 if (token == NEWLINE) { 146 parser->last_token_was_newline = 1; 147 } else { 148 parser->last_token_was_newline = 0; 149 } 150 151 /* Track spaces to avoid emitting multiple SPACE 152 * tokens in a row. */ 153 if (token == SPACE) { 154 if (! parser->last_token_was_space) { 155 parser->last_token_was_space = 1; 156 return 1; 157 } else { 158 parser->last_token_was_space = 1; 159 return 0; 160 } 161 } else { 162 parser->last_token_was_space = 0; 163 return 1; 164 } 165 } 166 167 168 %} 169 170 %option bison-bridge bison-locations reentrant noyywrap 171 %option extra-type="glcpp_parser_t *" 172 %option prefix="glcpp_" 173 %option stack 174 %option never-interactive 175 %option warn nodefault 176 177 /* Note: When adding any start conditions to this list, you must also 178 * update the "Internal compiler error" catch-all rule near the end of 179 * this file. */ 180 181 %x COMMENT DEFINE DONE HASH NEWLINE_CATCHUP UNREACHABLE 182 183 SPACE [[:space:]] 184 NONSPACE [^[:space:]] 185 HSPACE [ \t\v\f] 186 HASH # 187 NEWLINE (\r\n|\n\r|\r|\n) 188 IDENTIFIER [_a-zA-Z][_a-zA-Z0-9]* 189 PP_NUMBER [.]?[0-9]([._a-zA-Z0-9]|[eEpP][-+])* 190 PUNCTUATION [][(){}.&*~!/%<>^|;,=+-] 191 192 /* The OTHER class is simply a catch-all for things that the CPP 193 parser just doesn't care about. Since flex regular expressions that 194 match longer strings take priority over those matching shorter 195 strings, we have to be careful to avoid OTHER matching and hiding 196 something that CPP does care about. So we simply exclude all 197 characters that appear in any other expressions. */ 198 199 OTHER [^][_#[:space:]#a-zA-Z0-9(){}.&*~!/%<>^|;,=+-] 200 201 DIGITS [0-9][0-9]* 202 DECIMAL_INTEGER [1-9][0-9]*[uU]? 203 OCTAL_INTEGER 0[0-7]*[uU]? 204 HEXADECIMAL_INTEGER 0[xX][0-9a-fA-F]+[uU]? 205 PATH ["][]^./ _A-Za-z0-9+*%[(){}|&~=!:;,?-]*["] 206 207 %% 208 209 glcpp_parser_t *parser = yyextra; 210 211 /* When we lex a multi-line comment, we replace it (as 212 * specified) with a single space. But if the comment spanned 213 * multiple lines, then subsequent parsing stages will not 214 * count correct line numbers. To avoid this problem we keep 215 * track of all newlines that were commented out by a 216 * multi-line comment, and we emit a NEWLINE token for each at 217 * the next legal opportunity, (which is when the lexer would 218 * be emitting a NEWLINE token anyway). 219 */ 220 if (YY_START == NEWLINE_CATCHUP) { 221 if (parser->commented_newlines) 222 parser->commented_newlines--; 223 if (parser->commented_newlines == 0) 224 BEGIN INITIAL; 225 RETURN_TOKEN_NEVER_SKIP (NEWLINE); 226 } 227 228 /* Set up the parser->skipping bit here before doing any lexing. 229 * 230 * This bit controls whether tokens are skipped, (as implemented by 231 * RETURN_TOKEN), such as between "#if 0" and "#endif". 232 * 233 * The parser maintains a skip_stack indicating whether we should be 234 * skipping, (and nested levels of #if/#ifdef/#ifndef/#endif) will 235 * push and pop items from the stack. 236 * 237 * Here are the rules for determining whether we are skipping: 238 * 239 * 1. If the skip stack is NULL, we are outside of all #if blocks 240 * and we are not skipping. 241 * 242 * 2. If the skip stack is non-NULL, the type of the top node in 243 * the stack determines whether to skip. A type of 244 * SKIP_NO_SKIP is used for blocks wheere we are emitting 245 * tokens, (such as between #if 1 and #endif, or after the 246 * #else of an #if 0, etc.). 247 * 248 * 3. The lexing_directive bit overrides the skip stack. This bit 249 * is set when we are actively lexing the expression for a 250 * pre-processor condition, (such as #if, #elif, or #else). In 251 * this case, even if otherwise skipping, we need to emit the 252 * tokens for this condition so that the parser can evaluate 253 * the expression. (For, #else, there's no expression, but we 254 * emit tokens so the parser can generate a nice error message 255 * if there are any tokens here). 256 */ 257 if (parser->skip_stack && 258 parser->skip_stack->type != SKIP_NO_SKIP && 259 ! parser->lexing_directive) 260 { 261 parser->skipping = 1; 262 } else { 263 parser->skipping = 0; 264 } 265 266 /* Single-line comments */ 267 <INITIAL,DEFINE,HASH>"//"[^\r\n]* { 268 } 269 270 /* Multi-line comments */ 271 <INITIAL,DEFINE,HASH>"/*" { yy_push_state(COMMENT, yyscanner); } 272 <COMMENT>[^*\r\n]* 273 <COMMENT>[^*\r\n]*{NEWLINE} { yylineno++; yycolumn = 0; parser->commented_newlines++; } 274 <COMMENT>"*"+[^*/\r\n]* 275 <COMMENT>"*"+[^*/\r\n]*{NEWLINE} { yylineno++; yycolumn = 0; parser->commented_newlines++; } 276 <COMMENT>"*"+"/" { 277 yy_pop_state(yyscanner); 278 /* In the <HASH> start condition, we don't want any SPACE token. */ 279 if (yyextra->space_tokens && YY_START != HASH) 280 RETURN_TOKEN (SPACE); 281 } 282 283 {HASH} { 284 285 /* If the '#' is the first non-whitespace, non-comment token on this 286 * line, then it introduces a directive, switch to the <HASH> start 287 * condition. 288 * 289 * Otherwise, this is just punctuation, so return the HASH_TOKEN 290 * token. */ 291 if (parser->first_non_space_token_this_line) { 292 BEGIN HASH; 293 yyextra->in_define = false; 294 } 295 296 RETURN_TOKEN_NEVER_SKIP (HASH_TOKEN); 297 } 298 299 <HASH>version{HSPACE}+ { 300 BEGIN INITIAL; 301 yyextra->space_tokens = 0; 302 yyextra->lexing_version_directive = 1; 303 RETURN_STRING_TOKEN (VERSION_TOKEN); 304 } 305 306 /* Swallow empty #pragma directives, (to avoid confusing the 307 * downstream compiler). 308 * 309 * Note: We use a simple regular expression for the lookahead 310 * here. Specifically, we cannot use the complete {NEWLINE} expression 311 * since it uses alternation and we've found that there's a flex bug 312 * where using alternation in the lookahead portion of a pattern 313 * triggers a buffer overrun. */ 314 <HASH>pragma{HSPACE}*/[\r\n] { 315 BEGIN INITIAL; 316 } 317 318 /* glcpp doesn't handle #extension, #version, or #pragma directives. 319 * Simply pass them through to the main compiler's lexer/parser. */ 320 <HASH>(extension|pragma)[^\r\n]* { 321 BEGIN INITIAL; 322 RETURN_STRING_TOKEN (PRAGMA); 323 } 324 325 <HASH>include{HSPACE}+["<][]^./ _A-Za-z0-9+*%[(){}|&~=!:;,?-]+[">] { 326 BEGIN INITIAL; 327 RETURN_STRING_TOKEN (INCLUDE); 328 } 329 330 <HASH>line{HSPACE}+ { 331 BEGIN INITIAL; 332 RETURN_TOKEN (LINE); 333 } 334 335 <HASH>{NEWLINE} { 336 BEGIN INITIAL; 337 yyextra->space_tokens = 0; 338 yylineno++; 339 yycolumn = 0; 340 RETURN_TOKEN_NEVER_SKIP (NEWLINE); 341 } 342 343 /* For the pre-processor directives, we return these tokens 344 * even when we are otherwise skipping. */ 345 <HASH>ifdef { 346 if (!yyextra->in_define) { 347 BEGIN INITIAL; 348 yyextra->lexing_directive = 1; 349 yyextra->space_tokens = 0; 350 RETURN_TOKEN_NEVER_SKIP (IFDEF); 351 } 352 } 353 354 <HASH>ifndef { 355 if (!yyextra->in_define) { 356 BEGIN INITIAL; 357 yyextra->lexing_directive = 1; 358 yyextra->space_tokens = 0; 359 RETURN_TOKEN_NEVER_SKIP (IFNDEF); 360 } 361 } 362 363 <HASH>if/[^_a-zA-Z0-9] { 364 if (!yyextra->in_define) { 365 BEGIN INITIAL; 366 yyextra->lexing_directive = 1; 367 yyextra->space_tokens = 0; 368 RETURN_TOKEN_NEVER_SKIP (IF); 369 } 370 } 371 372 <HASH>elif/[^_a-zA-Z0-9] { 373 if (!yyextra->in_define) { 374 BEGIN INITIAL; 375 yyextra->lexing_directive = 1; 376 yyextra->space_tokens = 0; 377 RETURN_TOKEN_NEVER_SKIP (ELIF); 378 } 379 } 380 381 <HASH>else { 382 if (!yyextra->in_define) { 383 BEGIN INITIAL; 384 yyextra->space_tokens = 0; 385 RETURN_TOKEN_NEVER_SKIP (ELSE); 386 } 387 } 388 389 <HASH>endif { 390 if (!yyextra->in_define) { 391 BEGIN INITIAL; 392 yyextra->space_tokens = 0; 393 RETURN_TOKEN_NEVER_SKIP (ENDIF); 394 } 395 } 396 397 <HASH>error[^\r\n]* { 398 BEGIN INITIAL; 399 RETURN_STRING_TOKEN (ERROR_TOKEN); 400 } 401 402 /* After we see a "#define" we enter the <DEFINE> start state 403 * for the lexer. Within <DEFINE> we are looking for the first 404 * identifier and specifically checking whether the identifier 405 * is followed by a '(' or not, (to lex either a 406 * FUNC_IDENTIFIER or an OBJ_IDENITIFIER token). 407 * 408 * While in the <DEFINE> state we also need to explicitly 409 * handle a few other things that may appear before the 410 * identifier: 411 * 412 * * Comments, (handled above with the main support for 413 * comments). 414 * 415 * * Whitespace (simply ignored) 416 * 417 * * Anything else, (not an identifier, not a comment, 418 * and not whitespace). This will generate an error. 419 */ 420 <HASH>define{HSPACE}* { 421 yyextra->in_define = true; 422 if (!parser->skipping) { 423 BEGIN DEFINE; 424 yyextra->space_tokens = 0; 425 RETURN_TOKEN (DEFINE_TOKEN); 426 } 427 } 428 429 <HASH>undef { 430 BEGIN INITIAL; 431 yyextra->space_tokens = 0; 432 RETURN_TOKEN (UNDEF); 433 } 434 435 <HASH>{HSPACE}+ { 436 /* Nothing to do here. Importantly, don't leave the <HASH> 437 * start condition, since it's legal to have space between the 438 * '#' and the directive.. */ 439 } 440 441 /* This will catch any non-directive garbage after a HASH */ 442 <HASH>{NONSPACE} { 443 if (!parser->skipping) { 444 BEGIN INITIAL; 445 RETURN_TOKEN (GARBAGE); 446 } 447 } 448 449 /* An identifier immediately followed by '(' */ 450 <DEFINE>{IDENTIFIER}/"(" { 451 BEGIN INITIAL; 452 RETURN_STRING_TOKEN (FUNC_IDENTIFIER); 453 } 454 455 /* An identifier not immediately followed by '(' */ 456 <DEFINE>{IDENTIFIER} { 457 BEGIN INITIAL; 458 RETURN_STRING_TOKEN (OBJ_IDENTIFIER); 459 } 460 461 /* Whitespace */ 462 <DEFINE>{HSPACE}+ { 463 /* Just ignore it. Nothing to do here. */ 464 } 465 466 /* '/' not followed by '*', so not a comment. This is an error. */ 467 <DEFINE>[/][^*]{NONSPACE}* { 468 BEGIN INITIAL; 469 glcpp_error(yylloc, yyextra, "#define followed by a non-identifier: %s", yytext); 470 RETURN_STRING_TOKEN (INTEGER_STRING); 471 } 472 473 /* A character that can't start an identifier, comment, or 474 * space. This is an error. */ 475 <DEFINE>[^_a-zA-Z/[:space:]]{NONSPACE}* { 476 BEGIN INITIAL; 477 glcpp_error(yylloc, yyextra, "#define followed by a non-identifier: %s", yytext); 478 RETURN_STRING_TOKEN (INTEGER_STRING); 479 } 480 481 {DECIMAL_INTEGER} { 482 RETURN_STRING_TOKEN (INTEGER_STRING); 483 } 484 485 {OCTAL_INTEGER} { 486 RETURN_STRING_TOKEN (INTEGER_STRING); 487 } 488 489 {HEXADECIMAL_INTEGER} { 490 RETURN_STRING_TOKEN (INTEGER_STRING); 491 } 492 493 "<<" { 494 RETURN_TOKEN (LEFT_SHIFT); 495 } 496 497 ">>" { 498 RETURN_TOKEN (RIGHT_SHIFT); 499 } 500 501 "<=" { 502 RETURN_TOKEN (LESS_OR_EQUAL); 503 } 504 505 ">=" { 506 RETURN_TOKEN (GREATER_OR_EQUAL); 507 } 508 509 "==" { 510 RETURN_TOKEN (EQUAL); 511 } 512 513 "!=" { 514 RETURN_TOKEN (NOT_EQUAL); 515 } 516 517 "&&" { 518 RETURN_TOKEN (AND); 519 } 520 521 "||" { 522 RETURN_TOKEN (OR); 523 } 524 525 "++" { 526 RETURN_TOKEN (PLUS_PLUS); 527 } 528 529 "--" { 530 RETURN_TOKEN (MINUS_MINUS); 531 } 532 533 "##" { 534 if (! parser->skipping) { 535 if (parser->is_gles) 536 glcpp_error(yylloc, yyextra, "Token pasting (##) is illegal in GLES"); 537 RETURN_TOKEN (PASTE); 538 } 539 } 540 541 "defined" { 542 RETURN_TOKEN (DEFINED); 543 } 544 545 {IDENTIFIER} { 546 RETURN_STRING_TOKEN (IDENTIFIER); 547 } 548 549 {PP_NUMBER} { 550 RETURN_STRING_TOKEN (OTHER); 551 } 552 553 {PUNCTUATION} { 554 RETURN_TOKEN (yytext[0]); 555 } 556 557 {OTHER}+ { 558 RETURN_STRING_TOKEN (OTHER); 559 } 560 561 {HSPACE} { 562 if (yyextra->space_tokens) { 563 RETURN_TOKEN (SPACE); 564 } 565 } 566 567 {PATH} { 568 RETURN_STRING_TOKEN (PATH); 569 } 570 571 /* We preserve all newlines, even between #if 0..#endif, so no 572 skipping.. */ 573 <*>{NEWLINE} { 574 if (parser->commented_newlines) { 575 BEGIN NEWLINE_CATCHUP; 576 } else { 577 BEGIN INITIAL; 578 } 579 yyextra->space_tokens = 1; 580 yyextra->lexing_directive = 0; 581 yyextra->lexing_version_directive = 0; 582 yylineno++; 583 yycolumn = 0; 584 RETURN_TOKEN_NEVER_SKIP (NEWLINE); 585 } 586 587 <INITIAL,COMMENT,DEFINE,HASH><<EOF>> { 588 if (YY_START == COMMENT) 589 glcpp_error(yylloc, yyextra, "Unterminated comment"); 590 BEGIN DONE; /* Don't keep matching this rule forever. */ 591 yyextra->lexing_directive = 0; 592 yyextra->lexing_version_directive = 0; 593 if (! parser->last_token_was_newline) 594 RETURN_TOKEN (NEWLINE); 595 } 596 597 /* This is a catch-all to avoid the annoying default flex action which 598 * matches any character and prints it. If any input ever matches this 599 * rule, then we have made a mistake above and need to fix one or more 600 * of the preceding patterns to match that input. */ 601 602 <*>. { 603 glcpp_error(yylloc, yyextra, "Internal compiler error: Unexpected character: %s", yytext); 604 605 /* We don't actually use the UNREACHABLE start condition. We 606 only have this block here so that we can pretend to call some 607 generated functions, (to avoid "defined but not used" 608 warnings. */ 609 if (YY_START == UNREACHABLE) { 610 unput('.'); 611 yy_top_state(yyextra); 612 } 613 } 614 615 %% 616 617 void 618 glcpp_lex_set_source_string(glcpp_parser_t *parser, const char *shader) 619 { 620 yy_scan_string(shader, parser->scanner); 621 } 622