c.by 30.1 KB
Newer Older
1
;;; c.by -- LL grammar for C/C++ language specification
Paul Eggert's avatar
Paul Eggert committed
2
;; Copyright (C) 1999-2015 Free Software Foundation, Inc.
3 4 5 6 7
;;
;; Author: Eric M. Ludlam <zappo@gnu.org>
;;         David Ponce <david@dponce.com>
;;         Klaus Berndl <klaus.berndl@sdm.de>
;;
8 9 10
;; This file is part of GNU Emacs.

;; GNU Emacs is free software: you can redistribute it and/or modify
11
;; it under the terms of the GNU General Public License as published by
12 13 14 15
;; the Free Software Foundation, either version 3 of the License, or
;; (at your option) any later version.

;; GNU Emacs is distributed in the hope that it will be useful,
16 17 18
;; but WITHOUT ANY WARRANTY; without even the implied warranty of
;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
;; GNU General Public License for more details.
19

20
;; You should have received a copy of the GNU General Public License
21
;; along with GNU Emacs.  If not, see <http://www.gnu.org/licenses/>.
22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39

;; TODO:  From Nate Schley
;; >  * Can't parse signature element: "const char* const rmc_ClrTxt"
;; >  * Can't parse signature element: "char* const dellog_ClrTxt"
;; >  * Can't parse signature element: "const char* dellog_SetTxt"
;; >  * Can't parse signature element: "const RmcCmdSSPADetailedStatus& status"
;; >
;; > And FWIW I have seen the following argument cases not handled, even
;; > with no leading/trailing spaces in the split:
;; >
;; >  * Can't parse signature element: "const bool currentAlarmStatus"
;; >  * Can't parse signature element: "unsigned char mode"
;; >  * Can't parse signature element: "TskTimingTask* tsktimingtask"
;; >  * Can't parse signature element: "unsigned char htrStatus"
;; >  * Can't parse signature element: "char trackPower[]"
;; >  * Can't parse signature element: "const RmcCmdMCDetailedStatus& status"
;; >  * Can't parse signature element: "RmcBucStatus* rftBucStatus"

40
%package semantic-c-by
Chong Yidong's avatar
Chong Yidong committed
41 42 43
%provide semantic/bovine/c-by

%{
44 45 46 47 48 49 50
(declare-function semantic-c-reconstitute-token "semantic/bovine/c"
		  (tokenpart declmods typedecl))
(declare-function semantic-c-reconstitute-template "semantic/bovine/c"
		  (tag specifier))
(declare-function semantic-expand-c-tag "semantic/bovine/c" (tag))
(declare-function semantic-parse-region "semantic"
		  (start end &optional nonterminal depth returnonerror))
Chong Yidong's avatar
Chong Yidong committed
51
}
52 53 54 55 56 57 58 59 60 61 62 63 64 65 66

%languagemode  c-mode c++-mode
%start         declaration
%scopestart    codeblock

%token <punctuation>   HASH       "\\`[#]\\'"
%token <punctuation>   PERIOD     "\\`[.]\\'"
%token <punctuation>   COLON      "\\`[:]\\'"
%token <punctuation>   SEMICOLON  "\\`[;]\\'"
%token <punctuation>   STAR       "\\`[*]\\'"
%token <punctuation>   AMPERSAND  "\\`[&]\\'"
%token <punctuation>   DIVIDE     "\\`[/]\\'"
%token <punctuation>   PLUS       "\\`[+]\\'"
%token <punctuation>   MINUS      "\\`[-]\\'"
%token <punctuation>   BANG       "\\`[!]\\'"
David Engster's avatar
David Engster committed
67
%token <punctuation>   QUESTION   "\\`[?]\\'"
68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111
%token <punctuation>   EQUAL      "\\`[=]\\'"
%token <punctuation>   LESS       "\\`[<]\\'"
%token <punctuation>   GREATER    "\\`[>]\\'"
%token <punctuation>   COMA       "\\`[,]\\'"
%token <punctuation>   TILDE      "\\`[~]\\'"
%token <punctuation>   MOD        "\\`[%]\\'"
%token <punctuation>   HAT        "\\`\\^\\'"
%token <punctuation>   OR         "\\`[|]\\'"
%token <string>        C          "\"C\""
%token <string>        CPP        "\"C\\+\\+\""
%token <number>        ZERO       "^0$"
%token <symbol>        RESTRICT   "\\<\\(__\\)?restrict\\>"
%token <open-paren>    LPAREN     "("
%token <close-paren>   RPAREN     ")"
%token <open-paren>    LBRACE     "{"
%token <close-paren>   RBRACE     "}"
%token <semantic-list> BRACK_BLCK "\\[.*\\]$"
%token <semantic-list> PAREN_BLCK "^("
%token <semantic-list> BRACE_BLCK "^{"
%token <semantic-list> VOID_BLCK  "^(void)$"
%token <semantic-list> PARENS     "()"
%token <semantic-list> BRACKETS   "\\[\\]"

%token EXTERN "extern"
%put EXTERN summary "Declaration Modifier: extern <type> <name> ..."
%token STATIC "static"
%put STATIC summary "Declaration Modifier: static <type> <name> ..."
%token CONST "const"
%put CONST summary "Declaration Modifier: const <type> <name> ..."
%token VOLATILE "volatile"
%put VOLATILE summary "Declaration Modifier: volatile <type> <name> ..."
%token REGISTER "register"
%put REGISTER summary "Declaration Modifier: register <type> <name> ..."
%token SIGNED "signed"
%put SIGNED summary "Numeric Type Modifier: signed <numeric type> <name> ..."
%token UNSIGNED "unsigned"
%put UNSIGNED summary "Numeric Type Modifier: unsigned <numeric type> <name> ..."

%token INLINE "inline"
%put INLINE summary "Function Modifier: inline <return  type> <name>(...) {...};"
%token VIRTUAL "virtual"
%put VIRTUAL summary "Method Modifier: virtual <type> <name>(...) ..."
%token MUTABLE "mutable"
%put MUTABLE summary "Member Declaration Modifier: mutable <type> <name> ..."
Chong Yidong's avatar
Chong Yidong committed
112 113
%token EXPLICIT "explicit"
%put EXPLICIT summary "Forbids implicit type conversion: explicit <constructor>"
114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137

%token STRUCT "struct"
%put STRUCT summary "Structure Type Declaration: struct [name] { ... };"
%token UNION "union"
%put UNION summary "Union Type Declaration: union [name] { ... };"
%token ENUM "enum"
%put ENUM summary "Enumeration Type Declaration: enum [name] { ... };"
%token TYPEDEF "typedef"
%put TYPEDEF summary "Arbitrary Type Declaration: typedef <typedeclaration> <name>;"
%token CLASS "class"
%put CLASS summary "Class Declaration: class <name>[:parents] { ... };"
%token TYPENAME "typename"
%put TYPENAME summary "typename is used to handle a qualified name as a typename;"
%token NAMESPACE "namespace"
%put NAMESPACE summary "Namespace Declaration: namespace <name> { ... };"
%token USING "using"
%put USING summary "using <namespace>;"

%token NEW "new"
%put NEW summary "new <classname>();"
%token DELETE "delete"
%put DELETE summary "delete <object>;"

;; Despite this, this parser can find templates by ignoring the TEMPLATE
Paul Eggert's avatar
Paul Eggert committed
138
;; keyword, and finding the class/method being templatized.
139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276
%token TEMPLATE "template"
%put TEMPLATE summary "template <class TYPE ...> TYPE_OR_FUNCTION"

%token THROW "throw"
%put THROW summary "<type> <methoddef> (<method args>) throw (<exception>) ..."
%token REENTRANT "reentrant"
%put REENTRANT summary "<type> <methoddef> (<method args>) reentrant ..."
%token TRY "try"
%token CATCH "catch"
%put { TRY CATCH } summary "try { <body> } catch { <catch code> }"

;; Leave these alone for now.
%token OPERATOR "operator"
%token PUBLIC "public"
%token PRIVATE "private"
%token PROTECTED "protected"
%token FRIEND "friend"
%put FRIEND summary "friend class <CLASSNAME>"

;; These aren't used for parsing, but is a useful place to describe the keywords.
%token IF "if"
%token ELSE "else"
%put {IF ELSE} summary  "if (<condition>) { code } [ else { code } ]"

%token DO "do"
%token WHILE "while"
%put DO summary " do { code } while (<condition>);"
%put WHILE summary "do { code } while (<condition>); or while (<condition>) { code };"

%token FOR "for"
%put FOR summary "for(<init>; <condition>; <increment>) { code }"

%token SWITCH "switch"
%token CASE "case"
%token DEFAULT "default"
%put {SWITCH CASE DEFAULT} summary
"switch (<variable>) { case <constvalue>: code; ... default: code; }"

%token RETURN "return"
%put RETURN summary "return <value>;"

%token BREAK "break"
%put BREAK summary "Non-local exit within a loop or switch (for, do/while, switch): break;"
%token CONTINUE "continue"
%put CONTINUE summary "Non-local continue within a loop (for, do/while): continue;"

%token SIZEOF "sizeof"
%put SIZEOF summary "Compile time macro: sizeof(<type or variable>) // size in bytes"

;; Types
%token VOID "void"
%put VOID summary "Built in typeless type: void"
%token CHAR "char"
%put CHAR summary "Integral Character Type: (0 to 256)"
%token WCHAR "wchar_t"
%put WCHAR summary "Wide Character Type"
%token SHORT "short"
%put SHORT summary "Integral Primitive Type: (-32768 to 32767)"
%token INT "int"
%put INT summary "Integral Primitive Type: (-2147483648 to 2147483647)"
%token LONG "long"
%put LONG summary "Integral primitive type (-9223372036854775808 to 9223372036854775807)"
%token FLOAT "float"
%put FLOAT summary "Primitive floating-point type (single-precision 32-bit IEEE 754)"
%token DOUBLE "double"
%put DOUBLE summary "Primitive floating-point type (double-precision 64-bit IEEE 754)"
%token BOOL "bool"
%put BOOL summary "Primitive boolean type"

%token UNDERP "_P"
%token UNDERUNDERP "__P"
%put UNDERP summary "Common macro to eliminate prototype compatibility on some compilers"
%put UNDERUNDERP summary "Common macro to eliminate prototype compatibility on some compilers"

%%

declaration
  : macro
  | type
 ;; TODO: Klaus Berndl: Is the define here necessary or even wrong?
 ;; Is this part not already covered by macro??
  | define
  | var-or-fun
  | extern-c
  | template
  | using
  ;

codeblock
  : define
  | codeblock-var-or-fun
  | type ;; type is less likely to be used here.
  | using
  ;

extern-c-contents
  : open-paren
    ( nil )
  | declaration
  | close-paren
    ( nil )
  ;

extern-c
  : EXTERN C semantic-list
 ;; Extern C commands which contain a list need to have the
 ;; entries of the list extracted, and spliced into the main
 ;; list of entries.  This must be done via the function
 ;; that expands singular nonterminals, such as int x,y;
    (TAG "C" 'extern :members (EXPANDFULL $3 extern-c-contents) )
  | EXTERN CPP semantic-list
    (TAG "C" 'extern :members (EXPANDFULL $3 extern-c-contents) )
  | EXTERN C
 ;; A plain extern "C" call should add something to the token,
 ;; but just strip it from the buffer here for now.
    ( nil )
  | EXTERN CPP
    ( nil )
  ;

macro
  : spp-macro-def
    (VARIABLE-TAG $1 nil nil :constant-flag t )
  | spp-system-include
    (INCLUDE-TAG $1 t)
  | spp-include
    (INCLUDE-TAG $1 nil)
  ;

;; This is used in struct parts.
define
  : spp-macro-def
    (VARIABLE-TAG $1 nil nil :constant-flag t)
  | spp-macro-undef
    ( nil )
  ;

;; In C++, structures can have the same things as classes.
Paul Eggert's avatar
Paul Eggert committed
277
;; So delete this some day in the figure.
278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385
;;
;;structparts : semantic-list
;;            (EXPANDFULL $1 structsubparts)
;;          ;
;;
;;structsubparts : LBRACE
;;               ( nil )
;;             | RBRACE
;;               ( nil )
;;             | var-or-fun
;;             | define
;;             ;; sometimes there are defines in structs.
;;             ;

unionparts
  : semantic-list
    (EXPANDFULL $1 classsubparts)
  ;

opt-symbol
  : symbol
  | ;;EMPTY
  ;

;; @todo - support 'friend' construct.
classsubparts
  : LBRACE
    ( nil )
  | RBRACE
    ( nil )
  | class-protection opt-symbol COLON
 ;; For QT, they may put a `slot' keyword between the protection
 ;; and the COLON.  @todo - Have the QT stuff use macros.
    (TAG (car $1) 'label)
  | var-or-fun
  | FRIEND func-decl
    (TAG (car $2) 'friend)
  | FRIEND CLASS symbol
    (TAG $3 'friend)
  | type
  | define
  | template
  | ;;EMPTY
  ;

opt-class-parents
  : COLON class-parents opt-template-specifier
    ( $2 )
  | ;;EMPTY
    ( )
  ;

one-class-parent
  : opt-class-protection opt-class-declmods namespace-symbol
    (TYPE-TAG (car $3) "class" nil nil :protection (car $1))
  | opt-class-declmods opt-class-protection namespace-symbol
    (TYPE-TAG (car $3) "class" nil nil :protection (car $2))
  ;

class-parents
  : one-class-parent COMA class-parents
    ( ,(cons ,$1 $3 ) )
  | one-class-parent
    ( $1 )
  ;

opt-class-declmods
  : class-declmods opt-class-declmods
    ( nil )
  | ;;EMPTY
  ;

class-declmods
  : VIRTUAL
  ;

class-protection
  : PUBLIC
  | PRIVATE
  | PROTECTED
  ;

opt-class-protection
  : class-protection
    ( ,$1 )
  | ;;EMPTY - Same as private
    ( "unspecified" )
  ;

namespaceparts
  : semantic-list
    (EXPANDFULL $1 namespacesubparts)
  ;

namespacesubparts
  : LBRACE
    ( nil )
  | RBRACE
    ( nil )
  | type
  | var-or-fun
  | define
  | class-protection COLON
    (TAG (car $1) 'label)
 ;; In C++, this label in a classsubpart represents
 ;; PUBLIC or PRIVATE bits.  Ignore them for now.
  | template
  | using
Chong Yidong's avatar
Chong Yidong committed
386 387 388
 ;; Includes inside namespaces
  | spp-include
    (TAG $1 'include :inside-ns t)
389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584
  | ;;EMPTY
  ;

enumparts
  : semantic-list
    (EXPANDFULL $1 enumsubparts)
  ;

enumsubparts
  : symbol opt-assign
    (VARIABLE-TAG $1 "int" (car $2) :constant-flag t )
  | LBRACE
    ( nil )
  | RBRACE
    ( nil )
  | COMA
    ( nil )
  ;

opt-name
  : symbol
  | ;;EMPTY
    ( "" )
  ;

typesimple
  : struct-or-class opt-class opt-name opt-template-specifier
    opt-class-parents semantic-list
    (TYPE-TAG (car $3) (car $1)
          (let ((semantic-c-classname (cons (car ,$3) (car ,$1))))
            (EXPANDFULL $6 classsubparts))
          $5
          :template-specifier $4
          :parent (car ,$2))
  | struct-or-class opt-class opt-name opt-template-specifier
    opt-class-parents
    (TYPE-TAG (car $3) (car $1) nil $5
              :template-specifier $4
	      :prototype t
              :parent (car ,$2))
  | UNION opt-class opt-name unionparts
    (TYPE-TAG (car $3) $1 $4 nil
              :parent (car ,$2))
  | ENUM opt-class opt-name enumparts
    (TYPE-TAG (car $3) $1 $4 nil
              :parent (car ,$2))
 ;; Klaus Berndl: a typedef can be a typeformbase with all this
 ;; declmods stuff.
  | TYPEDEF declmods typeformbase cv-declmods typedef-symbol-list
 ;;;; We put the type this typedef renames into PARENT
 ;;;; but will move it in the expand function.
    (TYPE-TAG $5 $1 nil (list $3) )
  ;

typedef-symbol-list
  : typedefname COMA typedef-symbol-list
    ( ,(cons $1 $3) )
  | typedefname
    ( $1 )
  ;

;; TODO: Klaus Berndl: symbol -> namespace-symbol?!  Answer: Probably
;; symbol is correct here!
typedefname
  : opt-stars symbol opt-bits opt-array
    ( $1 $2 )
  ;

struct-or-class
  : STRUCT
  | CLASS
  ;

type
  : typesimple SEMICOLON
    ( ,$1 )
 ;; named namespaces like "namespace XXX {"
  | NAMESPACE symbol namespaceparts
    (TYPE-TAG $2 $1 $3 nil )
 ;; unnamed namespaces like "namespace {"
  | NAMESPACE namespaceparts
    (TYPE-TAG "unnamed" $1 $2 nil )
 ;; David Engster: namespace alias like "namespace foo = bar;"
  | NAMESPACE symbol EQUAL typeformbase SEMICOLON
    (TYPE-TAG $2 $1 (list (TYPE-TAG (car $4) $1 nil nil)) nil :kind 'alias )
  ;

;; Klaus Berndl: We must parse "using namespace XXX" too

;; Using is vaguely like an include statement in the named portions
;; of the code.  We should probably specify a new token type for this.

using
  : USING usingname SEMICOLON
    (TAG (car $2) 'using :type ,$2 )
  ;

;; Jan Moringen: Differentiate between 'using' and 'using namespace'
;; Adapted to creating type tags by EML.
usingname
  : typeformbase
    (TYPE-TAG (car $1) "class" nil nil :prototype t)
  | NAMESPACE typeformbase
    (TYPE-TAG (car $2) "namespace" nil nil :prototype t)
  ;

template
  : TEMPLATE template-specifier opt-friend template-definition
    ( ,(semantic-c-reconstitute-template $4 ,$2) )
  ;

opt-friend
  : FRIEND
  | ;;EMPTY
  ;

opt-template-specifier
  : template-specifier
    ( ,$1 )
  | ;;EMPTY
    ( )
  ;

template-specifier
  : LESS template-specifier-types GREATER
    ( ,$2 )
  ;

template-specifier-types
  : template-var template-specifier-type-list
    ( ,(cons ,$1 ,$2 ) )
  | ;;EMPTY
  ;

template-specifier-type-list
  : COMA template-specifier-types
    ( ,$2 )
  | ;;EMPTY
    ( )
  ;

;; template-var
;;   : template-type opt-stars opt-template-equal
;;     ( ,(cons (concat (car $1) (make-string (car ,$2) ?*))
;;              (cdr $1)))
;;  ;; Klaus Berndl: for template-types the template-var can also be
;;  ;; literals or constants.  Example: map<ClassX, ClassY, 10>
;;  ;; map_size10_var; This parses also template<class T, 0> which is
;;  ;; nonsense but who cares....
;;   | string
;;     ( $1 )
;;   | number
;;     ( $1 )
;;   ;

template-var
  :
 ;; Klaus Berndl: The following handles all template-vars of
 ;; template-definitions
    template-type opt-template-equal
    ( ,(cons (car $1) (cdr $1)) )
 ;; Klaus Berndl: for template-types the template-var can also be
 ;; literals or constants.
 ;; Example: map<ClassX, ClassY, 10> map_size10_var; This parses also
 ;; template<class T, 0> which is nonsense but who cares....
  | string
    ( $1 )
  | number
    ( $1 )
 ;; Klaus Berndl: In template-types arguments can be any symbols with
 ;; optional address-operator (&) and optional dereferencing operator
 ;; (*).  Example map<ClassX, ClassY, *size_var_ptr> sized_map_var.
  | opt-stars opt-ref namespace-symbol
    ( ,$3 )
 ;; Some code can compile down into a number, but starts out as an
 ;; expression, such as "sizeof(a)", or (sizeof(a)/sizeof(b))
  | semantic-list
    ( $1 )
  | SIZEOF semantic-list
    ( $2 )
  ;

opt-template-equal
  : EQUAL symbol LESS template-specifier-types GREATER
    ( $2 )
  | EQUAL symbol
    ( $2 )
  | ;;EMPTY
    ( )
  ;

template-type
  : CLASS symbol
    (TYPE-TAG $2 "class" nil nil )
  | STRUCT symbol
    (TYPE-TAG $2 "struct" nil nil )
Juanma Barranquero's avatar
Juanma Barranquero committed
585
 ;; TODO: Klaus Berndl: For the moment it is ok, that we parse the C++
586 587 588 589 590 591 592 593
 ;; keyword typename as a class....
  | TYPENAME symbol
    (TYPE-TAG $2 "class" nil nil)
 ;; Klaus Berndl: template-types can be all flavors of variable-args
 ;; but here the argument is ignored, only the type stuff is needed.
  | declmods typeformbase cv-declmods opt-stars
    opt-ref variablearg-opt-name
    (TYPE-TAG (car $2) nil nil nil
David Engster's avatar
David Engster committed
594
	      :template-specifier (plist-get (nth 2 $2) :template-specifier)
595 596 597 598
              :constant-flag (if (member "const" (append $1 $3)) t nil)
              :typemodifiers (delete "const" (append $1 $3))
              :reference (car ,$5)
              :pointer (car $4)
David Engster's avatar
David Engster committed
599
	      :typevar (car $6)
600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754
              )
  ;

template-definition
  : type
    ( ,$1 )
  | var-or-fun
    ( ,$1 )
  ;

opt-stars
  : STAR opt-starmod opt-stars
    ( (1+ (car $3)) )
  | ;;EMPTY
    ( 0 )
  ;

opt-starmod
  : STARMOD opt-starmod
    ( ,(cons (,car ,$1) $2) )
  | ;;EMPTY
    ()
  ;

STARMOD
  : CONST
  ;

declmods
  : DECLMOD declmods
    ( ,(cons ,(car ,$1) $2 ) )
  | DECLMOD
    ( ,$1 )
  | ;;EMPTY
    ()
  ;

DECLMOD
  : EXTERN
  | STATIC
  | CVDECLMOD
 ;; Klaus Berndl: IMHO signed and unsigned are not decl-modes but
 ;; these are only valid for some buildin-types like short, int
 ;; etc... whereas "real" declmods are valid for all types, buildin
 ;; and user-defined!  SIGNED UNSIGNED
  | INLINE
  | REGISTER
  | FRIEND
 ;; Klaus Berndl: There can be a few cases where TYPENAME is not
 ;; allowed in C++-syntax but better than not recognizing the allowed
 ;; situations.
  | TYPENAME
  | METADECLMOD
 ;; This is a hack in case we are in a class.
  | VIRTUAL
  ;

metadeclmod
  : METADECLMOD
    ()
  | ;;EMPTY
    ()
  ;

CVDECLMOD
  : CONST
  | VOLATILE
  ;

cv-declmods
  : CVDECLMOD cv-declmods
    ( ,(cons ,(car ,$1) $2 ) )
  | CVDECLMOD
    ( ,$1 )
  | ;;EMPTY
    ()
  ;

METADECLMOD
  : VIRTUAL
  | MUTABLE
  ;

;; C++: A type can be modified into a reference by "&"
opt-ref
  : AMPERSAND
    ( 1 )
  | ;;EMPTY
    ( 0 )
  ;

typeformbase
  : typesimple
    ( ,$1 )
  | STRUCT symbol
    (TYPE-TAG $2 $1 nil nil )
  | UNION symbol
    (TYPE-TAG $2 $1 nil nil )
  | ENUM symbol
    (TYPE-TAG $2 $1 nil nil )
  | builtintype
    ( ,$1 )
  | symbol template-specifier
    (TYPE-TAG $1 "class" nil nil :template-specifier $2)
 ;;| namespace-symbol opt-stars opt-template-specifier
 ;;| namespace-symbol opt-template-specifier
  | namespace-symbol-for-typeformbase opt-template-specifier
    (TYPE-TAG (car $1) "class" nil nil
	      :template-specifier $2)
  | symbol
    ( $1 )
  ;

signedmod
  : UNSIGNED
  | SIGNED
  ;

;; Klaus Berndl: builtintype-types was builtintype
builtintype-types
  : VOID
  | CHAR
 ;; Klaus Berndl: Added WCHAR
  | WCHAR
  | SHORT INT
    ( (concat $1 " " $2) )
  | SHORT
  | INT
  | LONG INT
    ( (concat $1 " " $2) )
  | FLOAT
  | DOUBLE
  | BOOL
  | LONG DOUBLE
    ( (concat $1 " " $2) )
 ;; TODO: Klaus Berndl: Is there a long long, i think so?!
  | LONG LONG
    ( (concat $1 " " $2) )
  | LONG
  ;

builtintype
  : signedmod builtintype-types
    ( (concat (car $1) " " (car $2)) )
  | builtintype-types
    ( ,$1 )
 ;; Klaus Berndl: unsigned is synonym for unsigned int and signed for
 ;; signed int. To make this confusing stuff clear we add here the
 ;; int.
  | signedmod
    ( (concat (car $1) " int") )
  ;

;; Klaus Berndl: This parses also nonsense like "const volatile int
;; const volatile const const volatile a ..." but IMHO nobody writes
Paul Eggert's avatar
Paul Eggert committed
755
;; such code. Normally we should define a rule like typeformbase-mode
756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837
;; which exactly defines the different allowed cases and combinations
;; of declmods (minus the CVDECLMOD) typeformbase and cv-declmods so
;; we could recognize more invalid code but IMHO this is not worth the
;; effort...
codeblock-var-or-fun
  : declmods typeformbase declmods
    opt-ref var-or-func-decl
    ( ,(semantic-c-reconstitute-token ,$5 $1 $2 ) )
  ;

var-or-fun
  : codeblock-var-or-fun
    ( ,$1 )
 ;; it is possible for a function to not have a type, and
 ;; it is then assumed to be an int.  How annoying.
 ;; In C++, this could be a constructor or a destructor.
 ;; Even more annoying.  Only ever do this for regular
 ;; top-level items.  Ignore this problem in code blocks
 ;; so that we don't have to deal with regular code
 ;; being erroneously converted into types.
  | declmods var-or-func-decl
    ( ,(semantic-c-reconstitute-token ,$2 $1 nil ) )
  ;

var-or-func-decl
  : func-decl
    ( ,$1 )
  | var-decl
    ( ,$1 )
  ;

func-decl
  : opt-stars opt-class opt-destructor functionname
    opt-template-specifier
    opt-under-p
    arg-list
    opt-post-fcn-modifiers
    opt-throw
    opt-initializers
    fun-or-proto-end
    ( ,$4 'function
          ;; Extra stuff goes in here.
          ;; Continue with the stuff we found in
          ;; this definition
          $2 $3 $7 $9 $8 ,$1 ,$11 $5 ,$10)
  | opt-stars opt-class opt-destructor functionname
    opt-template-specifier
    opt-under-p
 ;; arg-list   - - ini this case, a try implies a fcn.
    opt-post-fcn-modifiers
    opt-throw
    opt-initializers
    fun-try-end
    ( ,$4 'function
          ;; Extra stuff goes in here.
          ;; Continue with the stuff we found in
          ;; this definition
          $2 $3 nil $8 $7 ,$1 ,$10 $5 ,$9)
  ;

var-decl
  : varnamelist SEMICOLON
    ( $1 'variable )
  ;

opt-under-p
  : UNDERP
    ( nil )
  | UNDERUNDERP
    ( nil )
  | ;;EMPTY
  ;

;; Klaus Berndl: symbol -> namespace-symbol
opt-initializers
  : COLON namespace-symbol semantic-list opt-initializers
  | COMA namespace-symbol semantic-list opt-initializers
  | ;;EMPTY
  ;

opt-post-fcn-modifiers
  : post-fcn-modifiers opt-post-fcn-modifiers
David Engster's avatar
David Engster committed
838
    ( ,(cons ,(car $1) $2) )
839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906
  | ;;EMPTY
    ( nil )
  ;

post-fcn-modifiers
  : REENTRANT
  | CONST
  ;

opt-throw
  : THROW semantic-list
    ( EXPAND $2 throw-exception-list )
  | ;;EMPTY
  ;

;; Is this true?  I don't actually know.
throw-exception-list
  : namespace-symbol COMA throw-exception-list
    ( ,(cons (car $1) $3) )
  | namespace-symbol RPAREN
    ( ,$1 )
  | symbol RPAREN
    ( $1 )
  | LPAREN throw-exception-list
    ( ,$2 )
  | RPAREN
    (  )
  ;

opt-bits
  : COLON number
    ( $2 )
  | ;;EMPTY
    ( nil )
  ;

opt-array
  : BRACK_BLCK opt-array
 ;; Eventually we want to replace the 1 below with a size
 ;; (if available)
    ( (cons 1 (car ,$2) ) )
  | ;;EMPTY
    ( nil )
  ;

opt-assign
  : EQUAL expression
    ( $2 )
  | ;;EMPTY
    ( nil )
  ;

opt-restrict
  : RESTRICT
  | ;;EMPTY
  ;

;; Klaus Berndl: symbol -> namespace-symbol?! I think so. Can be that
;; then also some invalid C++-syntax is parsed but this is better than
;; not parsing valid syntax.
varname
  : opt-stars opt-restrict namespace-symbol opt-bits opt-array
    ( ,$3 ,$1 ,$4 ,$5 )
  ;

;; I should store more in this def, but leave it simple for now.
;; Klaus Berndl: const and volatile can be written after the type!
variablearg
David Engster's avatar
David Engster committed
907 908
  : declmods typeformbase cv-declmods opt-ref variablearg-opt-name opt-assign
    ( VARIABLE-TAG (list (append $5 ,$6)) $2 nil
909 910 911 912 913 914 915 916 917
                   :constant-flag (if (member "const" (append $1 $3)) t nil)
                   :typemodifiers (delete "const" (append $1 $3))
                   :reference (car ,$4)
                   )
  ;

variablearg-opt-name
  : varname
    ( ,$1 )
David Engster's avatar
David Engster committed
918 919
  | semantic-list arg-list
    ( (car ( EXPAND $1 function-pointer )) $2)
920 921 922 923 924 925 926 927 928 929 930 931 932 933
 ;; Klaus Berndl: This allows variableargs without a arg-name being
 ;; parsed correct even if there several pointers (*)
  | opt-stars
    ( "" ,$1 nil nil nil )
  ;

varname-opt-initializer
  : semantic-list
  | opt-assign
  | ;; EMPTY
  ;

varnamelist
  : opt-ref varname varname-opt-initializer COMA varnamelist
David Engster's avatar
David Engster committed
934
    ( ,(cons (append $2 $3) $5) )
935
  | opt-ref varname varname-opt-initializer
David Engster's avatar
David Engster committed
936
    ( (append $2 $3) )
937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118
  ;

;; Klaus Berndl: Is necessary to parse stuff like
;;     class list_of_facts : public list<fact>, public entity
;; and
;;     list <shared_ptr<item> >::const_iterator l;
;; Parses also invalid(?) and senseless(?) c++-syntax like
;;     symbol<template-spec>::symbol1<template-spec1>::test_iterator
;; but better parsing too much than to less
namespace-symbol
  : symbol opt-template-specifier COLON COLON namespace-symbol
    ( (concat $1 "::" (car $5)) )
  | symbol opt-template-specifier
    ( $1 )
  ;

;; Don't pull an optional template specifier at the end of the
;; namespace symbol so that it can be picked up by the type.
namespace-symbol-for-typeformbase
  : symbol opt-template-specifier COLON COLON namespace-symbol-for-typeformbase
    ( (concat $1 "::" (car $5)) )
  | symbol
    ( $1 )
  ;
;; namespace-symbol
;;   : symbol COLON COLON namespace-symbol
;;     ( (concat $1 "::" (car $4)) )
;;   | symbol
;;     ( $1 )
;;   ;

namespace-opt-class
  : symbol COLON COLON namespace-opt-class
    ( (concat $1 "::" (car $4)) )
 ;; Klaus Berndl: We must recognize template-specifiers here so we can
 ;; parse correctly the method-implementations of template-classes
 ;; outside the template-class-declaration Example:
 ;; TemplateClass1<T>::method_1(...)
  | symbol opt-template-specifier COLON COLON
    ( $1 )
  ;

;; Klaus Berndl: The opt-class of a func-decl must be able to
;; recognize opt-classes with namespaces, e.g.
;; Test1::Test2::classname::
opt-class
  : namespace-opt-class
    ( ,$1 )
  | ;;EMPTY
    ( nil )
  ;

opt-destructor
  : TILDE
    ( t )
  | ;;EMPTY
    ( nil )
  ;

arg-list
  : PAREN_BLCK knr-arguments
    ( ,$2 )
  | PAREN_BLCK
    (EXPANDFULL $1 arg-sub-list)
  | VOID_BLCK
    ( )
  ;

knr-varnamelist
  : varname COMA knr-varnamelist
    ( ,(cons $1 $3) )
  | varname
    ( $1 )
  ;


knr-one-variable-decl
  : declmods typeformbase cv-declmods knr-varnamelist
    ( VARIABLE-TAG (nreverse $4) $2 nil
                   :constant-flag (if (member "const" (append $3)) t nil)
                   :typemodifiers (delete "const" $3)
                   )
  ;

knr-arguments
  : knr-one-variable-decl SEMICOLON knr-arguments
    ( ,(append (semantic-expand-c-tag ,$1) ,$3) )
  | knr-one-variable-decl SEMICOLON
    ( ,(semantic-expand-c-tag ,$1) )
  ;

arg-sub-list
  : variablearg
    ( ,$1 )
  | PERIOD PERIOD PERIOD RPAREN
    (VARIABLE-TAG "..." "vararg" nil)
  | COMA
    ( nil )
  | LPAREN
    ( nil )
  | RPAREN
    ( nil )
  ;

operatorsym
  : LESS LESS EQUAL
    ( "<<=" )
  | GREATER GREATER EQUAL
    ( ">>=" )
  | LESS LESS
    ( "<<" )
  | GREATER GREATER
    ( ">>" )
  | EQUAL EQUAL
    ( "==" )
  | LESS EQUAL
    ( "<=" )
  | GREATER EQUAL
    ( ">=" )
  | BANG EQUAL
    ( "!=" )
  | PLUS EQUAL
    ( "+=" )
  | MINUS EQUAL
    ( "-=" )
  | STAR EQUAL
    ( "*=" )
  | DIVIDE EQUAL
    ( "/=" )
  | MOD EQUAL
    ( "%=" )
  | AMPERSAND EQUAL
    ( "&=" )
  | OR EQUAL
    ( "|=" )
  | MINUS GREATER STAR
    ( "->*" )
  | MINUS GREATER
    ( "->" )
  | PARENS
    ( "()" )
  | BRACKETS
    ( "[]" )
  | LESS
  | GREATER
  | STAR
  | PLUS PLUS
    ( "++" )
  | PLUS
  | MINUS MINUS
    ( "--" )
  | MINUS
  | AMPERSAND AMPERSAND
    ( "&&" )
  | AMPERSAND
  | OR OR
    ( "||" )
  | OR
  | DIVIDE
  | EQUAL
  | BANG
  | TILDE
  | MOD
  | COMA
 ;; HAT EQUAL seems to have a really unpleasant result and
 ;; breaks everything after it.  Leave it at the end, though it
 ;; doesn't seem to work.
  | HAT EQUAL
    ( "^=" )
  | HAT
  ;

functionname
  : OPERATOR operatorsym
    ( ,$2 )
  | semantic-list
    ( EXPAND $1 function-pointer )
  | symbol
    ( $1 )
  ;

function-pointer
1119 1120
  : LPAREN STAR opt-symbol RPAREN
    ( (concat "*" ,(car $3)) )
Chong Yidong's avatar
Chong Yidong committed
1121 1122
  | LPAREN symbol RPAREN
    ( $2 )
1123 1124 1125 1126 1127 1128 1129
  ;

fun-or-proto-end
  : SEMICOLON
    ( t )
  | semantic-list
    ( nil )
Paul Eggert's avatar
Paul Eggert committed
1130
 ;; Here is an annoying feature of C++ pure virtual methods
1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159
  | EQUAL ZERO SEMICOLON
    ( :pure-virtual-flag )
  | fun-try-end
    ( nil )
  ;

fun-try-end
  : TRY opt-initializers BRACE_BLCK fun-try-several-catches
    ( nil )
  ;

fun-try-several-catches
  : CATCH PAREN_BLCK BRACE_BLCK fun-try-several-catches
    ( )
  | CATCH BRACE_BLCK fun-try-several-catches
    ( )
  | ;; EMPTY
    ( )
  ;

type-cast
  : semantic-list
    ( EXPAND $1 type-cast-list )
  ;

type-cast-list
  : open-paren typeformbase close-paren
  ;

1160 1161 1162 1163 1164
opt-brackets-after-symbol
  : brackets-after-symbol
  | ;; EMPTY
  ;

David Engster's avatar
David Engster committed
1165
brackets-after-symbol
1166 1167 1168 1169 1170
  : PAREN_BLCK
  | BRACK_BLCK
  ;

multi-stage-dereference
1171 1172 1173 1174 1175 1176 1177 1178
  : namespace-symbol opt-brackets-after-symbol
    PERIOD multi-stage-dereference ;; method call
  | namespace-symbol opt-brackets-after-symbol
    MINUS GREATER multi-stage-dereference ;;method call
  | namespace-symbol opt-brackets-after-symbol
    PERIOD namespace-symbol opt-brackets-after-symbol
  | namespace-symbol opt-brackets-after-symbol
    MINUS GREATER namespace-symbol opt-brackets-after-symbol
David Engster's avatar
David Engster committed
1179
  | namespace-symbol brackets-after-symbol
1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204
  ;

string-seq
  : string string-seq
    ( (concat $1 (car $2)) )
  | string
    ( $1 )
  ;

expr-start
  : MINUS
  | PLUS
  | STAR
  | AMPERSAND
  ;

expr-binop
  : MINUS
  | PLUS
  | STAR
  | DIVIDE
  | AMPERSAND AMPERSAND
  | AMPERSAND
  | OR OR
  | OR
David Engster's avatar
David Engster committed
1205
  | MOD
1206 1207 1208 1209 1210 1211
 ;; There are more.
  ;

;; Use expression for parsing only.  Don't actually return anything
;; for now.  Hopefully we can fix this later.
expression
David Engster's avatar
David Engster committed
1212 1213 1214
  : unaryexpression QUESTION unaryexpression COLON unaryexpression
    ( (identity start) (identity end) )
  | unaryexpression expr-binop unaryexpression
1215 1216 1217 1218 1219 1220 1221 1222 1223 1224
    ( (identity start) (identity end) )
  | unaryexpression
    ( (identity start) (identity end) )
  ;

unaryexpression
  : number
  | multi-stage-dereference
  | NEW multi-stage-dereference
  | NEW builtintype-types semantic-list
David Engster's avatar
David Engster committed
1225
  | symbol
1226 1227 1228 1229 1230 1231 1232 1233 1234 1235
 ;; Klaus Berndl: C/C++ allows sequences of strings which are
 ;; concatenated by the precompiler to one string
  | string-seq
  | type-cast expression  ;; A cast to some other type
 ;; Casting the results of one expression to something else.
  | semantic-list expression
  | semantic-list
  | expr-start expression
  ;

1236
;;; c.by ends here