| blob | 717016af7eae97d09d3e5ed60a66caefde64c5c8 |
1 ;;; cc-engine.el --- core syntax guessing engine for CC mode
3 ;; Copyright (C) 1985, 1987, 1992, 1993, 1994, 1995, 1996, 1997, 1998,
4 ;; 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007
5 ;; Free Software Foundation, Inc.
7 ;; Authors: 2001- Alan Mackenzie
8 ;; 1998- Martin Stjernholm
9 ;; 1992-1999 Barry A. Warsaw
10 ;; 1987 Dave Detlefs and Stewart Clamen
11 ;; 1985 Richard M. Stallman
12 ;; Maintainer: bug-cc-mode@gnu.org
13 ;; Created: 22-Apr-1997 (split from cc-mode.el)
14 ;; Version: See cc-mode.el
15 ;; Keywords: c languages oop
17 ;; This file is part of GNU Emacs.
19 ;; GNU Emacs is free software; you can redistribute it and/or modify
20 ;; it under the terms of the GNU General Public License as published by
21 ;; the Free Software Foundation; either version 2, or (at your option)
22 ;; any later version.
24 ;; GNU Emacs is distributed in the hope that it will be useful,
25 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
26 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
27 ;; GNU General Public License for more details.
29 ;; You should have received a copy of the GNU General Public License
30 ;; along with this program; see the file COPYING. If not, write to
31 ;; the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
32 ;; Boston, MA 02110-1301, USA.
34 ;;; Commentary:
36 ;; The functions which have docstring documentation can be considered
37 ;; part of an API which other packages can use in CC Mode buffers.
38 ;; Otoh, undocumented functions and functions with the documentation
39 ;; in comments are considered purely internal and can change semantics
40 ;; or even disappear in the future.
41 ;;
42 ;; (This policy applies to CC Mode as a whole, not just this file. It
43 ;; probably also applies to many other Emacs packages, but here it's
44 ;; clearly spelled out.)
46 ;; Hidden buffer changes
47 ;;
48 ;; Various functions in CC Mode use text properties for caching and
49 ;; syntactic markup purposes, and those of them that might modify such
50 ;; properties but still don't modify the buffer in a visible way are
51 ;; said to do "hidden buffer changes". They should be used within
52 ;; `c-save-buffer-state' or a similar function that saves and restores
53 ;; buffer modifiedness, disables buffer change hooks, etc.
54 ;;
55 ;; Interactive functions are assumed to not do hidden buffer changes,
56 ;; except in the specific parts of them that do real changes.
57 ;;
58 ;; Lineup functions are assumed to do hidden buffer changes. They
59 ;; must not do real changes, though.
60 ;;
61 ;; All other functions that do hidden buffer changes have that noted
62 ;; in their doc string or comment.
63 ;;
64 ;; The intention with this system is to avoid wrapping every leaf
65 ;; function that do hidden buffer changes inside
66 ;; `c-save-buffer-state'. It should be used as near the top of the
67 ;; interactive functions as possible.
68 ;;
69 ;; Functions called during font locking are allowed to do hidden
70 ;; buffer changes since the font-lock package run them in a context
71 ;; similar to `c-save-buffer-state' (in fact, that function is heavily
72 ;; inspired by `save-buffer-state' in the font-lock package).
74 ;; Use of text properties
75 ;;
76 ;; CC Mode uses several text properties internally to mark up various
77 ;; positions, e.g. to improve speed and to eliminate glitches in
78 ;; interactive refontification.
79 ;;
80 ;; Note: This doc is for internal use only. Other packages should not
81 ;; assume that these text properties are used as described here.
82 ;;
83 ;; 'syntax-table
84 ;; Used to modify the syntax of some characters. Currently used to
85 ;; mark the "<" and ">" of angle bracket parens with paren syntax.
86 ;;
87 ;; This property is used on single characters and is therefore
88 ;; always treated as front and rear nonsticky (or start and end open
89 ;; in XEmacs vocabulary). It's therefore installed on
90 ;; `text-property-default-nonsticky' if that variable exists (Emacs
91 ;; >= 21).
92 ;;
93 ;; 'c-is-sws and 'c-in-sws
94 ;; Used by `c-forward-syntactic-ws' and `c-backward-syntactic-ws' to
95 ;; speed them up. See the comment blurb before `c-put-is-sws'
96 ;; below for further details.
97 ;;
98 ;; 'c-type
99 ;; This property is used on single characters to mark positions with
100 ;; special syntactic relevance of various sorts. Its primary use is
101 ;; to avoid glitches when multiline constructs are refontified
102 ;; interactively (on font lock decoration level 3). It's cleared in
103 ;; a region before it's fontified and is then put on relevant chars
104 ;; in that region as they are encountered during the fontification.
105 ;; The value specifies the kind of position:
106 ;;
107 ;; 'c-decl-arg-start
108 ;; Put on the last char of the token preceding each declaration
109 ;; inside a declaration style arglist (typically in a function
110 ;; prototype).
111 ;;
112 ;; 'c-decl-end
113 ;; Put on the last char of the token preceding a declaration.
114 ;; This is used in cases where declaration boundaries can't be
115 ;; recognized simply by looking for a token like ";" or "}".
116 ;; `c-type-decl-end-used' must be set if this is used (see also
117 ;; `c-find-decl-spots').
118 ;;
119 ;; 'c-<>-arg-sep
120 ;; Put on the commas that separate arguments in angle bracket
121 ;; arglists like C++ template arglists.
122 ;;
123 ;; 'c-decl-id-start and 'c-decl-type-start
124 ;; Put on the last char of the token preceding each declarator
125 ;; in the declarator list of a declaration. They are also used
126 ;; between the identifiers cases like enum declarations.
127 ;; 'c-decl-type-start is used when the declarators are types,
128 ;; 'c-decl-id-start otherwise.
129 ;;
130 ;; 'c-awk-NL-prop
131 ;; Used in AWK mode to mark the various kinds of newlines. See
132 ;; cc-awk.el.
134 ;;; Code:
141 load-path)))
148 ;; Silence the compiler.
151 \f
152 ;; Make declarations for all the `c-lang-defvar' variables in cc-langs.
165 \f
166 ;;; Internal state variables.
168 ;; Internal state of hungry delete key feature
172 ;; The electric flag (toggled by `c-toggle-electric-state').
173 ;; If t, electric actions (like automatic reindentation, and (if
174 ;; c-auto-newline is also set) auto newlining) will happen when an electric
175 ;; key like `{' is pressed (or an electric keyword like `else').
179 ;; Internal state of auto newline feature.
183 ;; Included in the mode line to indicate the active submodes.
184 ;; (defvar c-submode-indicators nil)
185 ;; (make-variable-buffer-local 'c-submode-indicators)
188 ;; Calculate the new state of PREVSTATE, t or nil, based on arg. If
189 ;; arg is nil or zero, toggle the state. If arg is negative, turn
190 ;; the state off, and if arg is positive, turn the state on
196 ;; Dynamically bound cache for `c-in-literal'.
199 \f
200 ;; Basic handling of preprocessor directives.
202 ;; This is a dynamically bound cache used together with
203 ;; `c-query-macro-start' and `c-query-and-set-macro-start'. It only
204 ;; works as long as point doesn't cross a macro boundary.
213 c-macro-start))
221 c-macro-start))
224 "Go to the beginning of a preprocessor directive.
225 Leave point at the beginning of the directive and return t if in one,
226 otherwise return nil and leave point unchanged.
228 Note that this function might do hidden buffer changes. See the
229 comment at the start of cc-engine.el for more info."
240 t
242 nil)))))
245 "Go to the end of a preprocessor directive.
246 More accurately, move the point to the end of the closest following
247 line that doesn't end with a line continuation backslash - no check is
248 done that the point is inside a cpp directive to begin with.
250 Note that this function might do hidden buffer changes. See the
251 comment at the start of cc-engine.el for more info."
257 t))))
260 ;; Assuming point is at the "#" that introduces a preprocessor
261 ;; directive, it's moved forward to the end of the identifier which is
262 ;; "#define"d (or whatever c-opt-cpp-macro-define specifies). Non-nil
263 ;; is returned in this case, in all other cases nil is returned and
264 ;; point isn't moved.
265 ;;
266 ;; This function might do hidden buffer changes.
272 ;; Assuming point is at the "#" that introduces a preprocessor
273 ;; directive, it's moved forward to the start of the definition body
274 ;; if it's a "#define" (or whatever c-opt-cpp-macro-define
275 ;; specifies). Non-nil is returned in this case, in all other cases
276 ;; nil is returned and point isn't moved.
277 ;;
278 ;; This function might do hidden buffer changes.
284 \f
285 ;;; Basic utility functions.
288 ;; Return the given region as a string where all syntactic
289 ;; whitespace is removed or, where necessary, replaced with a single
290 ;; space. If PAREN-LEVEL is given then all parens in the region are
291 ;; collapsed to "()", "[]" etc.
292 ;;
293 ;; This function might do hidden buffer changes.
337 ;; Shift the indentation of the current line with the specified
338 ;; amount (positive inwards). The buffer is modified only if
339 ;; SHIFT-AMT isn't equal to zero.
342 tmp-char-inserted)
344 nil
345 ;; If we're on an empty line inside a macro, we take the point
346 ;; to be at the current indentation and shift it to the
347 ;; appropriate column. This way we don't treat the extra
348 ;; whitespace out to the line continuation as indentation.
364 ;; If initial point was within line's indentation and we're not on
365 ;; a line with a line continuation in a macro, position after the
366 ;; indentation. Else stay at same point in text.
374 ;; Return non-nil if the string KEYWORD is a known keyword. More
375 ;; precisely, the value is the symbol for the keyword in
376 ;; `c-keywords-obarray'.
380 ;; Return non-nil if the symbol KEYWORD-SYM, as returned by
381 ;; `c-keyword-sym', is a member of LANG-CONSTANT, which is the name
382 ;; of a language constant that ends with "-kwds". If KEYWORD-SYM is
383 ;; nil then the result is nil.
386 ;; String syntax chars, suitable for skip-syntax-(forward|backward).
391 ;; Regexp matching string limit syntax.
396 ;; Regexp matching WS followed by string limit syntax.
400 ;; Holds formatted error strings for the few cases where parse errors
401 ;; are reported.
408 c-parsing-error)
410 ;; Faces given to comments and string literals. This is used in some
411 ;; situations to speed up recognition; it isn't mandatory that font
412 ;; locking is in use. This variable is extended with the face in
413 ;; `c-doc-face-name' when fontification is activated in cc-fonts.el.
417 ;; New in Emacs 22.
421 ;; Put a c-type property with the given value at POS.
425 ;; Remove all occurences of the c-type property that has the given
426 ;; value in the region between FROM and TO. VALUE is assumed to not
427 ;; be nil.
428 ;;
429 ;; Note: This assumes that c-type is put on single chars only; it's
430 ;; very inefficient if matching properties cover large regions.
439 \f
440 ;; Some debug tools to visualize various special positions. This
441 ;; debug code isn't as portable as the rest of CC Mode.
477 \f
478 ;; `c-beginning-of-statement-1' and accompanying stuff.
480 ;; KLUDGE ALERT: c-maybe-labelp is used to pass information between
481 ;; c-crosses-statement-barrier-p and c-beginning-of-statement-1. A
482 ;; better way should be implemented, but this will at least shut up
483 ;; the byte compiler.
486 ;; New awk-compatible version of c-beginning-of-statement-1, ACM 2002/6/22
488 ;; Macros used internally in c-beginning-of-statement-1 for the
489 ;; automaton actions.
492 stack)))
497 t
498 ,do-if-done
503 ;; Throw nil if stack is empty, else throw non-nil.
527 noerror comma-delim)
528 "Move to the start of the current statement or declaration, or to
529 the previous one if already at the beginning of one. Only
530 statements/declarations on the same level are considered, i.e. don't
531 move into or out of sexps (not even normal expression parentheses).
535 is within the continuation. If starting at such a token, move to the
536 corresponding statement start. If at the beginning of a statement,
537 move to the closest containing statement if there is any. This might
538 also stop at a continuation clause.
540 Labels are treated as part of the following statements if
541 IGNORE-LABELS is non-nil. (FIXME: Doesn't work if we stop at a known
542 statement start keyword.) Otherwise, each label is treated as a
543 separate statement.
545 Macros are ignored \(i.e. skipped over) unless point is within one, in
546 which case the content of the macro is treated as normal code. Aside
547 from any normal statement starts found in it, stop at the first token
550 macros before leaving them.
552 Return 'label if stopped at a label, 'same if stopped at the beginning
553 of the current statement, 'up if stepped to a containing statement,
554 'previous if stepped to a preceding statement, 'beginning if stepped
555 from a statement continuation clause to its start clause, or 'macro if
556 stepped to a macro start. Note that 'same and not 'label is returned
557 if stopped at the same label without crossing the colon character.
559 LIM may be given to limit the search. If the search hits the limit,
560 point will be left at the closest following token, or at the start
561 position if that is less ('same is returned in this case).
563 NOERROR turns off error logging to `c-parsing-error'.
565 Normally only ';' and virtual semicolons are considered to delimit
566 statements, but if COMMA-DELIM is non-nil then ',' is treated
567 as a delimiter too.
569 Note that this function might do hidden buffer changes. See the
570 comment at the start of cc-engine.el for more info."
572 ;; The bulk of this function is a pushdown automaton that looks at statement
573 ;; boundaries and the tokens (such as "while") in c-opt-block-stmt-key. Its
574 ;; purpose is to keep track of nested statements, ensuring that such
575 ;; statments are skipped over in their entirety (somewhat akin to what C-M-p
576 ;; does with nested braces/brackets/parentheses).
577 ;;
578 ;; Note: The position of a boundary is the following token.
579 ;;
580 ;; Beginning with the current token (the one following point), move back one
581 ;; sexp at a time (where a sexp is, more or less, either a token or the
582 ;; entire contents of a brace/bracket/paren pair). Each time a statement
583 ;; boundary is crossed or a "while"-like token is found, update the state of
584 ;; the PDA. Stop at the beginning of a statement when the stack (holding
585 ;; nested statement info) is empty and the position has been moved.
586 ;;
587 ;; The following variables constitute the PDA:
588 ;;
589 ;; sym: This is either the "while"-like token (e.g. 'for) we've just
590 ;; scanned back over, 'boundary if we've just gone back over a
591 ;; statement boundary, or nil otherwise.
592 ;; state: takes one of the values (nil else else-boundary while
593 ;; while-boundary catch catch-boundary).
594 ;; nil means "no "while"-like token yet scanned".
595 ;; 'else, for example, means "just gone back over an else".
596 ;; 'else-boundary means "just gone back over a statement boundary
597 ;; immediately after having gone back over an else".
598 ;; saved-pos: A vector of either saved positions (tok ptok pptok, etc.) or
599 ;; of error reporting information.
600 ;; stack: The stack onto which the PDA pushes its state. Each entry
601 ;; consists of a saved value of state and saved-pos. An entry is
602 ;; pushed when we move back over a "continuation" token (e.g. else)
603 ;; and popped when we encounter the corresponding opening token
604 ;; (e.g. if).
605 ;;
606 ;;
607 ;; The following diagram briefly outlines the PDA.
608 ;;
609 ;; Common state:
610 ;; "else": Push state, goto state `else'.
611 ;; "while": Push state, goto state `while'.
612 ;; "catch" or "finally": Push state, goto state `catch'.
613 ;; boundary: Pop state.
614 ;; other: Do nothing special.
615 ;;
616 ;; State `else':
617 ;; boundary: Goto state `else-boundary'.
618 ;; other: Error, pop state, retry token.
619 ;;
620 ;; State `else-boundary':
621 ;; "if": Pop state.
622 ;; boundary: Error, pop state.
623 ;; other: See common state.
624 ;;
625 ;; State `while':
626 ;; boundary: Save position, goto state `while-boundary'.
627 ;; other: Pop state, retry token.
628 ;;
629 ;; State `while-boundary':
630 ;; "do": Pop state.
631 ;; boundary: Restore position if it's not at start, pop state. [*see below]
632 ;; other: See common state.
633 ;;
634 ;; State `catch':
635 ;; boundary: Goto state `catch-boundary'.
636 ;; other: Error, pop state, retry token.
637 ;;
638 ;; State `catch-boundary':
639 ;; "try": Pop state.
640 ;; "catch": Goto state `catch'.
641 ;; boundary: Error, pop state.
642 ;; other: See common state.
643 ;;
644 ;; [*] In the `while-boundary' state, we had pushed a 'while state, and were
645 ;; searching for a "do" which would have opened a do-while. If we didn't
646 ;; find it, we discard the analysis done since the "while", go back to this
647 ;; token in the buffer and restart the scanning there, this time WITHOUT
648 ;; pushing the 'while state onto the stack.
649 ;;
650 ;; In addition to the above there is some special handling of labels
651 ;; and macros.
655 macro-start
658 c-stmt-delim-chars-with-comma
659 c-stmt-delim-chars))
660 c-in-literal-cache c-maybe-labelp saved
661 ;; Current position.
662 pos
663 ;; Position of last stmt boundary character (e.g. ;).
664 boundary-pos
665 ;; The position of the last sexp or bound that follows the
666 ;; first found colon, i.e. the start of the nonlabel part of
667 ;; the statement. It's `start' if a colon is found just after
668 ;; the start.
669 after-labels-pos
670 ;; Like `after-labels-pos', but the first such position inside
671 ;; a label, i.e. the start of the last label before the start
672 ;; of the nonlabel part of the statement.
673 last-label-pos
674 ;; The last position where a label is possible provided the
675 ;; statement started there. It's nil as long as no invalid
676 ;; label content has been found (according to
677 ;; `c-nonlabel-token-key'. It's `start' if no valid label
678 ;; content was found in the label. Note that we might still
679 ;; regard it a label if it starts with `c-label-kwds'.
680 label-good-pos
681 ;; Symbol just scanned back over (e.g. 'while or 'boundary).
682 ;; See above.
683 sym
684 ;; Current state in the automaton. See above.
685 state
686 ;; Current saved positions. See above.
687 saved-pos
688 ;; Stack of conses (state . saved-pos).
689 stack
690 ;; Regexp which matches "for", "if", etc.
693 ;; Return value.
695 ;; Positions of the last three sexps or bounds we've stopped at.
696 tok ptok pptok)
706 ;; Try to skip back over unary operator characters, to register
707 ;; that we've moved.
711 ;; Protect post-++/-- operators just before a virtual semicolon.
715 ;; Skip back over any semicolon here. If it was a bare semicolon, we're
716 ;; done. Later on we ignore the boundaries for statements that don't
717 ;; contain any sexp. The only thing that is affected is that the error
718 ;; checking is a little less strict, and we really don't bother.
728 pos saved)
730 ;; Begin at start and not pos to detect macros if we stand
731 ;; directly after the #.
734 ;; Record this as the first token if not starting inside it.
737 ;; The following while loop goes back one sexp (balanced parens,
738 ;; etc. with contents, or symbol or suchlike) each iteration. This
739 ;; movement is accomplished with a call to scan-sexps approx 130 lines
740 ;; below.
758 ;; Stop at the first token in the content of the macro.
762 ret 'macro
763 ignore-labels t))
766 ;; Do a round through the automaton if we've just passed a
767 ;; statement boundary or passed a "while"-like token.
775 ;; The PDA state handling.
776 ;;
777 ;; Refer to the description of the PDA in the opening
778 ;; comments. In the following OR form, the first leaf
779 ;; attempts to handles one of the specific actions detailed
780 ;; (e.g., finding token "if" whilst in state `else-boundary').
781 ;; We drop through to the second leaf (which handles common
782 ;; state) if no specific handler is found in the first cond.
783 ;; If a parsing error is detected (e.g. an "else" with no
784 ;; preceding "if"), we throw to the enclosing catch.
785 ;;
786 ;; Note that the (eq state 'else) means
787 ;; "we've just passed an else", NOT "we're looking for an
788 ;; else".
805 ;; Since this can cause backtracking we do a
806 ;; little more careful analysis to avoid it:
807 ;; If there's a label in front of the while
808 ;; it can't be part of a do-while.
837 ;; This is state common. We get here when the previous
838 ;; cond statement found no particular state handler.
840 ;; If we have a boundary at the start
841 ;; position we push a frame to go to the
842 ;; previous statement.
851 ;; Is this a real while, or a do-while?
852 ;; The next `when' triggers unless we are SURE that
853 ;; the `while' is not the tailend of a `do-while'.
856 ;; The following kludge is to prevent
857 ;; infinite recursion when called from
858 ;; c-awk-after-if-for-while-condition-p,
859 ;; or the like.
863 ;; Since this can cause backtracking we do a
864 ;; little more careful analysis to avoid it: If
865 ;; the while isn't followed by a (possibly
866 ;; virtual) semicolon it can't be a do-while.
875 ;; We're either past a statement boundary or at the
876 ;; start of a statement, so throw away any label data
877 ;; for the previous one.
879 last-label-pos nil
880 c-maybe-labelp nil))))
882 ;; Step to the previous sexp, but not if we crossed a
883 ;; boundary, since that doesn't consume an sexp.
887 ;; HERE IS THE SINGLE PLACE INSIDE THE PDA LOOP WHERE WE MOVE
888 ;; BACKWARDS THROUGH THE SOURCE.
890 ;; This is typically fast with the caching done by
891 ;; c-(backward|forward)-sws.
895 ;; Set as long as we have to continue jumping by sexps.
896 ;; It's the position to use as end in the next round.
897 sexp-loop-continue-pos
898 ;; The end position of the area to search for statement
899 ;; barriers in this round.
902 ;; The following while goes back one sexp per iteration.
906 ;; Give up if we hit an unbalanced block. Since the
907 ;; stack won't be empty the code below will report a
908 ;; suitable error.
911 ;; Check if the sexp movement crossed a statement or
912 ;; declaration boundary. But first modify the point
913 ;; so that `c-crosses-statement-barrier-p' only looks
914 ;; at the non-sexp chars following the sexp.
917 boundary-pos
920 nil
923 ;; Set continuation position in case
924 ;; `c-crosses-statement-barrier-p'
925 ;; doesn't detect anything below.
927 ;; If the sexp movement took us into a
928 ;; macro then there were only some non-sexp
929 ;; chars after it. Skip out of the macro
930 ;; to analyze them but not the non-sexp
931 ;; chars that might be inside the macro.
939 ;; Passed a block sexp. That's a boundary
940 ;; alright.
944 ;; Passed some other paren. Only analyze
945 ;; the non-sexp chars after it.
947 before-sws-pos)))
948 ;; We're at a valid token start position
949 ;; (outside the `save-excursion') if
950 ;; `c-crosses-statement-barrier-p' failed.
955 ;; Passed a symbol sexp or line
956 ;; continuation. It doesn't matter that
957 ;; it's included in the analyzed region.
960 t
961 ;; If it was a line continuation then we
962 ;; have to continue looping.
965 nil))))
968 ptok tok
969 tok boundary-pos
971 ;; Like a C "continue". Analyze the next sexp.
977 sexp-loop-continue-pos nil))))
979 ;; ObjC method def?
986 ;; Handle labels.
989 ;; `c-crosses-statement-barrier-p' has found a colon, so we
990 ;; might be in a label now. Have we got a real label
991 ;; (including a case label) or something like C++'s "public:"?
996 ; wrong for AWK. 2006/1/14.
1003 label-good-pos nil))
1007 ; been found.
1009 ;; We're in a potential label and it's the first
1010 ;; time we've found something that isn't allowed in
1011 ;; one.
1014 ;; We've moved back by a sexp, so update the token positions.
1016 pptok ptok
1017 ptok tok
1021 ;; If the stack isn't empty there might be errors to report.
1030 ;; Need to investigate closer whether we've crossed
1031 ;; between a substatement and its containing statement.
1033 ptok
1034 pptok))
1041 after-labels-pos
1047 last-label-pos
1048 pos))
1050 ;; We're in a label. Maybe we should step to the statement
1051 ;; after it.
1056 ;; Might have jumped over several labels. Go to the last one.
1059 ;; Skip over the unary operators that can start the statement.
1063 ;; protect AWK post-inc/decrement operators, etc.
1068 ret)))
1071 "Return non-nil if buffer positions FROM to TO cross one or more
1072 statement or declaration boundaries. The returned value is actually
1073 the position of the earliest boundary char. FROM must not be within
1074 a string or comment.
1076 The variable `c-maybe-labelp' is set to the position of the first `:' that
1077 might start a label (i.e. not part of `::' and not preceded by `?'). If a
1078 single `?' is found, then `c-maybe-labelp' is cleared.
1080 For AWK, a statement which is terminated by an EOL (not a \; or a }) is
1082 the line. If this virtual semicolon is _at_ from, the function recognises it.
1084 Note that this function might do hidden buffer changes. See the
1085 comment at the start of cc-engine.el for more info."
1087 lit-range)
1100 ;; Ignore scope operators.
1104 ;; A question mark. Can't be a label, so stop
1105 ;; looking for more : and ?.
1116 ;; In trailing space after an as yet undetected virtual semicolon?
1121 nil)))))
1124 "Return non-nil if the point is at the first token in a statement
1125 or somewhere in the syntactic whitespace before it.
1128 Any kind of declaration-like construct that occur outside function
1131 Note that this function might do hidden buffer changes. See the
1132 comment at the start of cc-engine.el for more info."
1136 c-maybe-labelp)
1147 "Return non-nil if the point is at the first token in an expression or
1148 statement, or somewhere in the syntactic whitespace before it.
1151 grammar sense: It's any sequence of expression tokens except commas,
1152 unless they are enclosed inside parentheses of some kind. Also, an
1153 expression never continues past an enclosing parenthesis, but it might
1154 contain parenthesis pairs of any sort except braces.
1156 Since expressions never cross statement boundaries, this function also
1157 recognizes statement beginnings, just like `c-at-statement-start-p'.
1159 Note that this function might do hidden buffer changes. See the
1160 comment at the start of cc-engine.el for more info."
1165 c-maybe-labelp)
1173 \f
1174 ;; A set of functions that covers various idiosyncrasies in
1175 ;; implementations of `forward-comment'.
1177 ;; Note: Some emacsen considers incorrectly that any line comment
1178 ;; ending with a backslash continues to the next line. I can't think
1179 ;; of any way to work around that in a reliable way without changing
1180 ;; the buffer, though. Suggestions welcome. ;) (No, temporarily
1181 ;; changing the syntax for backslash doesn't work since we must treat
1182 ;; escapes in string literals correctly.)
1185 "Move forward past whitespace and the closest following comment, if any.
1186 Return t if a comment was found, nil otherwise. In either case, the
1187 point is moved past the following whitespace. Line continuations,
1188 i.e. a backslashes followed by line breaks, are treated as whitespace.
1189 The line breaks that end line comments are considered to be the
1190 comment enders, so the point will be put on the beginning of the next
1191 line if it moved past a line comment.
1193 This function does not do any hidden buffer changes."
1201 ;; Some emacsen (e.g. XEmacs 21) return t when moving
1202 ;; forwards at eob.
1203 nil
1205 ;; Emacs includes the ending newline in a b-style (c++)
1206 ;; comment, but XEmacs doesn't. We depend on the Emacs
1207 ;; behavior (which also is symmetric).
1211 t))))
1214 "Move forward past all following whitespace and comments.
1215 Line continuations, i.e. a backslashes followed by line breaks, are
1216 treated as whitespace.
1218 Note that this function might do hidden buffer changes. See the
1219 comment at the start of cc-engine.el for more info."
1222 ;; If forward-comment in at least XEmacs 21 is given a large
1223 ;; positive value, it'll loop all the way through if it hits
1224 ;; eob.
1226 ;; Some emacsen (e.g. XEmacs 21) return t when moving
1227 ;; forwards at eob.
1232 t))))
1235 "Move backward past whitespace and the closest preceding comment, if any.
1236 Return t if a comment was found, nil otherwise. In either case, the
1237 point is moved past the preceding whitespace. Line continuations,
1238 i.e. a backslashes followed by line breaks, are treated as whitespace.
1239 The line breaks that end line comments are considered to be the
1240 comment enders, so the point cannot be at the end of the same line to
1241 move over a line comment.
1243 This function does not do any hidden buffer changes."
1246 ;; When we got newline terminated comments, forward-comment in all
1247 ;; supported emacsen so far will stop at eol of each line not
1248 ;; ending with a comment when moving backwards. This corrects for
1249 ;; that, and at the same time handles line continuations.
1257 ;; Some emacsen (e.g. Emacs 19.34) return t when moving
1258 ;; backwards at bob.
1259 nil
1261 ;; Leave point after the closest following newline if we've
1262 ;; backed up over any above, since forward-comment won't move
1263 ;; backward over a line comment if point is at the end of the
1264 ;; same line.
1269 ;; If forward-comment above succeeded and we're at eol
1270 ;; then the newline we moved over above didn't end a
1271 ;; line comment, so we give it another go.
1273 t))
1275 ;; Emacs <= 20 and XEmacs move back over the closer of a
1276 ;; block comment that lacks an opener.
1279 t)))))
1282 "Move backward past all preceding whitespace and comments.
1283 Line continuations, i.e. a backslashes followed by line breaks, are
1284 treated as whitespace. The line breaks that end line comments are
1285 considered to be the comment enders, so the point cannot be at the end
1286 of the same line to move over a line comment. Unlike
1287 c-backward-syntactic-ws, this function doesn't move back over
1288 preprocessor directives.
1290 Note that this function might do hidden buffer changes. See the
1291 comment at the start of cc-engine.el for more info."
1295 ;; `forward-comment' in some emacsen (e.g. XEmacs 21.4)
1296 ;; return t when moving backwards at bob.
1301 ;; Emacs <= 20 and XEmacs move back over the
1302 ;; closer of a block comment that lacks an opener.
1304 t)
1306 ;; XEmacs treats line continuations as whitespace but
1307 ;; only in the backward direction, which seems a bit
1308 ;; odd. Anyway, this is necessary for Emacs.
1313 t))))))
1315 \f
1316 ;; Tools for skipping over syntactic whitespace.
1318 ;; The following functions use text properties to cache searches over
1319 ;; large regions of syntactic whitespace. It works as follows:
1320 ;;
1321 ;; o If a syntactic whitespace region contains anything but simple
1322 ;; whitespace (i.e. space, tab and line breaks), the text property
1323 ;; `c-in-sws' is put over it. At places where we have stopped
1324 ;; within that region there's also a `c-is-sws' text property.
1325 ;; That since there typically are nested whitespace inside that
1326 ;; must be handled separately, e.g. whitespace inside a comment or
1327 ;; cpp directive. Thus, from one point with `c-is-sws' it's safe
1328 ;; to jump to another point with that property within the same
1329 ;; `c-in-sws' region. It can be likened to a ladder where
1330 ;; `c-in-sws' marks the bars and `c-is-sws' the rungs.
1331 ;;
1332 ;; o The `c-is-sws' property is put on the simple whitespace chars at
1333 ;; a "rung position" and also maybe on the first following char.
1334 ;; As many characters as can be conveniently found in this range
1335 ;; are marked, but no assumption can be made that the whole range
1336 ;; is marked (it could be clobbered by later changes, for
1337 ;; instance).
1338 ;;
1339 ;; Note that some part of the beginning of a sequence of simple
1340 ;; whitespace might be part of the end of a preceding line comment
1341 ;; or cpp directive and must not be considered part of the "rung".
1342 ;; Such whitespace is some amount of horizontal whitespace followed
1343 ;; by a newline. In the case of cpp directives it could also be
1344 ;; two newlines with horizontal whitespace between them.
1345 ;;
1346 ;; The reason to include the first following char is to cope with
1347 ;; "rung positions" that doesn't have any ordinary whitespace. If
1348 ;; `c-is-sws' is put on a token character it does not have
1349 ;; `c-in-sws' set simultaneously. That's the only case when that
1350 ;; can occur, and the reason for not extending the `c-in-sws'
1351 ;; region to cover it is that the `c-in-sws' region could then be
1352 ;; accidentally merged with a following one if the token is only
1353 ;; one character long.
1354 ;;
1355 ;; o On buffer changes the `c-in-sws' and `c-is-sws' properties are
1356 ;; removed in the changed region. If the change was inside
1357 ;; syntactic whitespace that means that the "ladder" is broken, but
1358 ;; a later call to `c-forward-sws' or `c-backward-sws' will use the
1359 ;; parts on either side and use an ordinary search only to "repair"
1360 ;; the gap.
1361 ;;
1362 ;; Special care needs to be taken if a region is removed: If there
1363 ;; are `c-in-sws' on both sides of it which do not connect inside
1364 ;; the region then they can't be joined. If e.g. a marked macro is
1365 ;; broken, syntactic whitespace inside the new text might be
1366 ;; marked. If those marks would become connected with the old
1367 ;; `c-in-sws' range around the macro then we could get a ladder
1368 ;; with one end outside the macro and the other at some whitespace
1369 ;; within it.
1370 ;;
1371 ;; The main motivation for this system is to increase the speed in
1372 ;; skipping over the large whitespace regions that can occur at the
1373 ;; top level in e.g. header files that contain a lot of comments and
1374 ;; cpp directives. For small comments inside code it's probably
1375 ;; slower than using `forward-comment' straightforwardly, but speed is
1376 ;; not a significant factor there anyway.
1378 ; (defface c-debug-is-sws-face
1379 ; '((t (:background "GreenYellow")))
1380 ; "Debug face to mark the `c-is-sws' property.")
1381 ; (defface c-debug-in-sws-face
1382 ; '((t (:underline t)))
1383 ; "Debug face to mark the `c-in-sws' property.")
1385 ; (defun c-debug-put-sws-faces ()
1386 ; ;; Put the sws debug faces on all the `c-is-sws' and `c-in-sws'
1387 ; ;; properties in the buffer.
1388 ; (interactive)
1389 ; (save-excursion
1390 ; (c-save-buffer-state (in-face)
1391 ; (goto-char (point-min))
1392 ; (setq in-face (if (get-text-property (point) 'c-is-sws)
1393 ; (point)))
1394 ; (while (progn
1395 ; (goto-char (next-single-property-change
1396 ; (point) 'c-is-sws nil (point-max)))
1397 ; (if in-face
1398 ; (progn
1399 ; (c-debug-add-face in-face (point) 'c-debug-is-sws-face)
1400 ; (setq in-face nil))
1401 ; (setq in-face (point)))
1402 ; (not (eobp))))
1403 ; (goto-char (point-min))
1404 ; (setq in-face (if (get-text-property (point) 'c-in-sws)
1405 ; (point)))
1406 ; (while (progn
1407 ; (goto-char (next-single-property-change
1408 ; (point) 'c-in-sws nil (point-max)))
1409 ; (if in-face
1410 ; (progn
1411 ; (c-debug-add-face in-face (point) 'c-debug-in-sws-face)
1412 ; (setq in-face nil))
1413 ; (setq in-face (point)))
1414 ; (not (eobp)))))))
1417 ;;`(message ,@args)
1418 )
1421 ;; This macro does a hidden buffer change.
1428 ;; This macro does a hidden buffer change.
1435 ;; This macro does a hidden buffer change.
1442 ;; This macro does a hidden buffer change.
1449 ;; This macro does a hidden buffer change.
1457 ;; Called from `after-change-functions'. Note that if
1458 ;; `c-forward-sws' or `c-backward-sws' are used outside
1459 ;; `c-save-buffer-state' or similar then this will remove the cache
1460 ;; properties right after they're added.
1461 ;;
1462 ;; This function does hidden buffer changes.
1465 ;; Adjust the end to remove the properties in any following simple
1466 ;; ws up to and including the next line break, if there is any
1467 ;; after the changed region. This is necessary e.g. when a rung
1468 ;; marked empty line is converted to a line comment by inserting
1469 ;; "//" before the line break. In that case the line break would
1470 ;; keep the rung mark which could make a later `c-backward-sws'
1471 ;; move into the line comment instead of over it.
1481 ;; Ensure that an `c-in-sws' range gets broken. Note that it isn't
1482 ;; safe to keep a range that was continuous before the change. E.g:
1483 ;;
1484 ;; #define foo
1485 ;; \
1486 ;; bar
1487 ;;
1488 ;; There can be a "ladder" between "#" and "b". Now, if the newline
1489 ;; after "foo" is removed then "bar" will become part of the cpp
1490 ;; directive instead of a syntactically relevant token. In that
1491 ;; case there's no longer syntactic ws from "#" to "b".
1498 ;; Used by `c-forward-syntactic-ws' to implement the unbounded search.
1499 ;;
1500 ;; This function might do hidden buffer changes.
1503 ;; unmarked part of the simple ws region.
1505 rung-is-marked next-rung-is-marked simple-ws-end
1506 ;; `safe-start' is set when it's safe to cache the start position.
1507 ;; It's not set if we've initially skipped over comments and line
1508 ;; continuations since we might have gone out through the end of a
1509 ;; macro then. This provision makes `c-forward-sws' not populate the
1510 ;; cache in the majority of cases, but otoh is `c-backward-sws' by far
1511 ;; more common.
1512 safe-start)
1514 ;; Skip simple ws and do a quick check on the following character to see
1515 ;; if it's anything that can't start syntactic ws, so we can bail out
1516 ;; early in the majority of cases when there just are a few ws chars.
1523 ;; Find the last rung position to avoid setting properties in all
1524 ;; the cases when the marked rung is complete.
1525 ;; (`next-single-property-change' is certain to move at least one
1526 ;; step forward.)
1529 ;; Got no marked rung here. Since the simple ws might have started
1530 ;; inside a line comment or cpp directive we must set `rung-pos' as
1531 ;; high as possible.
1540 ;; The following search is the main reason that `c-in-sws'
1541 ;; and `c-is-sws' aren't combined to one property.
1545 ;; If the `c-in-sws' region extended past the last
1546 ;; `c-is-sws' char we have to go back a bit.
1553 "c-forward-sws cached move %s -> %s (max %s)"
1560 ;; We'll loop here if there is simple ws after the last rung.
1561 ;; That means that there's been some change in it and it's
1562 ;; possible that we've stepped into another ladder, so extend
1563 ;; the previous one to join with it if there is one, and try to
1564 ;; use the cache again.
1566 "c-forward-sws extending rung with [%s..%s] (max %s)"
1569 ;; Remove any `c-in-sws' property from the last char of
1570 ;; the rung before we mark it with `c-is-sws', so that we
1571 ;; won't connect with the remains of a broken "ladder".
1577 last-put-in-sws-pos rung-pos)))
1584 ;; Skipped over comments. Don't cache at eob in case the buffer
1585 ;; is narrowed.
1596 ;; Skip a preprocessor directive.
1603 ;; Don't cache at eob in case the buffer is narrowed.
1606 ;; We've searched over a piece of non-white syntactic ws. See if this
1607 ;; can be cached.
1613 ;; Cache if we haven't skipped comments only, and if we started
1614 ;; either from a marked rung or from a completely uncached
1615 ;; position.
1620 ;; See if there's a marked rung in the encountered simple ws. If
1621 ;; so then we can cache, unless `safe-start' is nil. Even then
1622 ;; we need to do this to check if the cache can be used for the
1623 ;; next step.
1627 safe-start))
1631 "c-forward-sws caching [%s..%s] - [%s..%s] (max %s)"
1635 ;; Remove the properties for any nested ws that might be cached.
1636 ;; Only necessary for `c-is-sws' since `c-in-sws' will be set
1637 ;; anyway.
1645 last-put-in-sws-pos rung-pos))
1647 ;; Remove any `c-in-sws' property from the last char of
1648 ;; the rung before we mark it with `c-is-sws', so that we
1649 ;; won't connect with the remains of a broken "ladder".
1652 rung-end-pos))
1655 "c-forward-sws not caching [%s..%s] - [%s..%s] (max %s)"
1659 ;; Set `rung-pos' for the next rung. It's the same thing here as
1660 ;; initially, except that the rung position is set as early as
1661 ;; possible since we can't be in the ending ws of a line comment or
1662 ;; cpp directive now.
1669 ;; Make sure that the newly marked `c-in-sws' region doesn't connect to
1670 ;; another one after the point (which might occur when editing inside a
1671 ;; comment or macro).
1675 "c-forward-sws clearing at %s for cache separation"
1676 last-put-in-sws-pos)
1680 ;; If at eob we have to clear the last character before the end
1681 ;; instead since the buffer might be narrowed and there might
1682 ;; be a `c-in-sws' after (point-max). In this case it's
1683 ;; necessary to clear both properties.
1685 "c-forward-sws clearing thoroughly at %s for cache separation"
1688 last-put-in-sws-pos))))
1689 )))
1692 ;; Used by `c-backward-syntactic-ws' to implement the unbounded search.
1693 ;;
1694 ;; This function might do hidden buffer changes.
1697 ;; part of the simple ws region.
1699 rung-is-marked simple-ws-beg cmt-skip-pos)
1701 ;; Skip simple horizontal ws and do a quick check on the preceding
1702 ;; character to see if it's anying that can't end syntactic ws, so we can
1703 ;; bail out early in the majority of cases when there just are a few ws
1704 ;; chars. Newlines are complicated in the backward direction, so we can't
1705 ;; skip over them.
1712 ;; Try to find a rung position in the simple ws preceding point, so that
1713 ;; we can get a cache hit even if the last bit of the simple ws has
1714 ;; changed recently.
1720 ;; `rung-pos' will be the earliest marked position, which means that
1721 ;; there might be later unmarked parts in the simple ws region.
1722 ;; It's not worth the effort to fix that; the last part of the
1723 ;; simple ws is also typically edited often, so it could be wasted.
1734 ;; The following search is the main reason that `c-in-sws'
1735 ;; and `c-is-sws' aren't combined to one property.
1739 ;; If the `c-in-sws' region extended past the first
1740 ;; `c-is-sws' char we have to go forward a bit.
1745 "c-backward-sws cached move %s <- %s (min %s)"
1757 t
1759 nil))
1761 ;; We'll loop here if there is simple ws before the first rung.
1762 ;; That means that there's been some change in it and it's
1763 ;; possible that we've stepped into another ladder, so extend
1764 ;; the previous one to join with it if there is one, and try to
1765 ;; use the cache again.
1767 "c-backward-sws extending rung with [%s..%s] (min %s)"
1770 ;; Remove any `c-in-sws' property from the last char of
1771 ;; the rung before we mark it with `c-is-sws', so that we
1772 ;; won't connect with the remains of a broken "ladder".
1775 rung-pos)
1779 last-put-in-sws-pos rung-pos))
1788 ;; Inside a cpp directive. See if it should be skipped over.
1791 ;; Move back over all line continuations in the region skipped
1792 ;; over by `c-backward-comments'. If we go past it then we
1793 ;; started inside the cpp directive.
1802 ;; Don't move past the cpp directive if we began inside
1803 ;; it. Note that the position at the end of the last line
1804 ;; of the macro is also considered to be within it.
1806 nil)
1808 ;; It's worthwhile to spend a little bit of effort on finding
1809 ;; the end of the macro, to get a good `simple-ws-beg'
1810 ;; position for the cache. Note that `c-backward-comments'
1811 ;; could have stepped over some comments before going into
1812 ;; the macro, and then `simple-ws-beg' must be kept on the
1813 ;; same side of those comments.
1820 ;; Might happen if comments after the macro were skipped
1821 ;; over.
1825 t)))
1830 simple-ws-beg)
1831 ;; Skipped over comments. Must put point at the end of
1832 ;; the simple ws at point since we might be after a line
1833 ;; comment or cpp directive that's been partially
1834 ;; narrowed out, and we can't risk marking the simple ws
1835 ;; at the end of it.
1837 t)))
1839 ;; We've searched over a piece of non-white syntactic ws. See if this
1840 ;; can be cached.
1845 ;; Cache if we started either from a marked rung or from a
1846 ;; completely uncached position.
1847 rung-is-marked
1850 ;; Cache if there's a marked rung in the encountered simple ws.
1858 "c-backward-sws caching [%s..%s] - [%s..%s] (min %s)"
1863 ;; Remove the properties for any nested ws that might be cached.
1864 ;; Only necessary for `c-is-sws' since `c-in-sws' will be set
1865 ;; anyway.
1870 ;; Remove any `c-in-sws' property from the last char of
1871 ;; the rung before we mark it with `c-is-sws', so that we
1872 ;; won't connect with the remains of a broken "ladder".
1875 rung-end-pos)
1878 last-put-in-sws-pos simple-ws-beg)
1879 rung-pos)
1884 "c-backward-sws not caching [%s..%s] - [%s..%s] (min %s)"
1890 ))
1892 ;; Make sure that the newly marked `c-in-sws' region doesn't connect to
1893 ;; another one before the point (which might occur when editing inside a
1894 ;; comment or macro).
1898 "c-backward-sws clearing at %s for cache separation"
1901 last-put-in-sws-pos))
1903 ;; If at bob and the buffer is narrowed, we have to clear the
1904 ;; character we're standing on instead since there might be a
1905 ;; `c-in-sws' before (point-min). In this case it's necessary
1906 ;; to clear both properties.
1908 "c-backward-sws clearing thoroughly at %s for cache separation"
1909 last-put-in-sws-pos)
1912 )))
1914 \f
1915 ;; Other whitespace tools
1917 ;; Is the region (beg end) WS, and is there WS (or BOB/EOB) next to the
1918 ;; region? This is a "heuristic" function. .....
1919 ;;
1920 ;; The motivation for the second bit is to check whether removing this
1921 ;; region would coalesce two symbols.
1922 ;;
1923 ;; FIXME!!! This function doesn't check virtual semicolons in any way. Be
1924 ;; careful about using this function for, e.g. AWK. (2007/3/7)
1933 \f
1934 ;; A system for finding noteworthy parens before the point.
1938 ;; The state cache used by `c-parse-state' to cut down the amount of
1939 ;; searching. It's the result from some earlier `c-parse-state' call.
1940 ;;
1941 ;; The use of the cached info is more effective if the next
1942 ;; `c-parse-state' call is on a line close by the one the cached state
1943 ;; was made at; the cache can actually slow down a little if the
1944 ;; cached state was made very far back in the buffer. The cache is
1945 ;; most effective if `c-parse-state' is used on each line while moving
1946 ;; forward.
1950 ;; This is (point-min) when `c-state-cache' was calculated, since a
1951 ;; change of narrowing is likely to affect the parens that are visible
1952 ;; before the point.
1956 ;; This is a position where `c-state-cache' is known to be correct.
1957 ;; It's a position inside one of the recorded unclosed parens or the
1958 ;; top level, but not further nested inside any literal or subparen
1959 ;; that is closed before the last recorded position.
1960 ;;
1961 ;; The exact position is chosen to try to be close to yet earlier than
1962 ;; the position where `c-state-cache' will be called next. Right now
1963 ;; the heuristic is to set it to the position after the last found
1964 ;; closing paren (of any type) before the line on which
1965 ;; `c-parse-state' was called. That is chosen primarily to work well
1966 ;; with refontification of the current line.
1969 ;; Invalidate all info on `c-state-cache' that applies to the buffer
1970 ;; at POS or higher. This is much like `c-whack-state-after', but
1971 ;; it never changes a paren pair element into an open paren element.
1972 ;; Doing that would mean that the new open paren wouldn't have the
1973 ;; required preceding paren pair element.
1977 nil))
1983 nil))
1987 nil)))))
1991 ;; Return the start position for building `c-state-cache' from
1992 ;; scratch.
1994 ;; Go back 2 bods, but ignore any bogus positions returned by
1995 ;; beginning-of-defun (i.e. open paren in column zero).
2005 ;; Find and record all noteworthy parens between some good point
2006 ;; earlier in the file and point. That good point is at least the
2007 ;; beginning of the top-level construct we are in, or the beginning
2008 ;; of the preceding top-level construct if we aren't in one.
2009 ;;
2010 ;; The returned value is a list of the noteworthy parens with the
2011 ;; last one first. If an element in the list is an integer, it's
2012 ;; the position of an open paren which has not been closed before
2013 ;; the point. If an element is a cons, it gives the position of a
2014 ;; closed brace paren pair; the car is the start paren position and
2015 ;; the cdr is the position following the closing paren. Only the
2016 ;; last closed brace paren pair before each open paren and before
2017 ;; the point is recorded, and thus the state never contains two cons
2018 ;; elements in succession.
2019 ;;
2020 ;; Currently no characters which are given paren syntax with the
2021 ;; syntax-table property are recorded, i.e. angle bracket arglist
2022 ;; parens are never present here. Note that this might change.
2023 ;;
2024 ;; BUG: This function doesn't cope entirely well with unbalanced
2025 ;; parens in macros. E.g. in the following case the brace before
2026 ;; the macro isn't balanced with the one after it:
2027 ;;
2028 ;; {
2029 ;; #define X {
2030 ;; }
2031 ;;
2032 ;; This function might do hidden buffer changes.
2039 old-state last-pos brace-pair-open brace-pair-close
2040 pos save-pos)
2043 ;; If the minimum position has changed due to narrowing then we
2044 ;; have to fix the tail of `c-state-cache' accordingly.
2047 ;; If point-min has moved forward then we just need to cut
2048 ;; off a bit of the tail.
2059 ;; If point-min has moved backward then we drop the state
2060 ;; completely. It's possible to do a better job here and
2061 ;; recalculate the top only.
2066 ;; Get the latest position we know are directly inside the
2067 ;; closest containing paren of the cached state.
2075 ;; Take the opportunity to move the cached good position
2076 ;; further down.
2080 ;; Check if `last-pos' is in a macro. If it is, and we're not
2081 ;; in the same macro, we must discard everything on
2082 ;; `c-state-cache' that is inside the macro before using it.
2088 ;; Set `last-pos' again just like above except that there's
2089 ;; no use looking at `c-state-cache-good-pos' here.
2096 ;; If we've moved very far from the last cached position then
2097 ;; it's probably better to redo it from scratch, otherwise we
2098 ;; might spend a lot of time searching from `last-pos' down to
2099 ;; here.
2101 ;; First get the fallback start position. If it turns out
2102 ;; that it's so far back that the cached state is closer then
2103 ;; we'll keep it afterall.
2108 c-state-cache nil
2111 ;; Find the start position for the forward search. (Can't
2112 ;; search in the backward direction since the point might be in
2113 ;; some kind of literal.)
2118 ;; There's a cached state with a containing paren. Pop off
2119 ;; the stale containing sexps from it by going forward out of
2120 ;; parens as far as possible.
2134 ;; The last paren pair we moved out from was a brace
2135 ;; pair. Modify the state to record this as a closed
2136 ;; pair now.
2140 c-state-cache))))
2142 ;; Check if the preceding balanced paren is within a
2143 ;; macro; it should be ignored if we're outside the
2144 ;; macro. There's no need to check any further upwards;
2145 ;; if the macro contains an unbalanced opening paren then
2146 ;; we're smoked anyway.
2156 ;; Have to adjust the cached good position if state has been
2157 ;; popped off.
2164 old-state c-state-cache))
2169 ;; Get the fallback start position.
2172 c-state-cache nil
2179 brace-pair-open nil)
2181 ;; Find the balanced brace pairs. This loop is hot, so it
2182 ;; does ugly tricks to go faster.
2192 ;; Update the cached good position and record the brace
2193 ;; pair, whichever is applicable for the paren we've
2194 ;; just jumped over. But first check that it isn't
2195 ;; inside a macro and the point isn't inside the same
2196 ;; one.
2206 brace-pair-close pos))))))
2208 ;; Record the last brace pair.
2216 brace-pair-close)
2217 c-state-cache)))))
2220 ;; Prepare to loop, but record the open paren only if it's
2221 ;; outside a macro or within the same macro as point, and
2222 ;; if it is a legitimate open paren and not some character
2223 ;; that got an open paren syntax-table property.
2230 ;; Check for known types of parens that we
2231 ;; want to record. The syntax table is not to
2232 ;; be trusted here since the caller might be
2233 ;; using e.g. `c++-template-syntax-table'.
2240 ;; Found a close paren without a corresponding opening
2241 ;; one. Maybe we didn't go back far enough, so try to
2242 ;; scan backward for the start paren and then start over.
2245 c-state-cache nil
2246 c-state-cache-good-pos c-state-cache-start)
2248 ;; Emacs (up to at least 21.2) can get confused by
2249 ;; open parens in column zero inside comments: The
2250 ;; sexp functions can then misbehave and bring us
2251 ;; back to the same point again. Check this so that
2252 ;; we don't get an infinite loop.
2255 c-parsing-error
2261 ;;(message "c-parse-state: %S end: %S" c-state-cache c-state-cache-good-pos)
2262 c-state-cache)))
2264 ;; Debug tool to catch cache inconsistencies.
2276 ;; The cache can actually go further back due to the ad-hoc way
2277 ;; the first paren is found, so try to whack off a bit of its
2278 ;; start before complaining.
2287 res1 res2))))
2288 res1))
2293 'c-debug-parse-state
2300 ;; Whack off any state information from PAREN-STATE which lies
2301 ;; before BUFPOS. Not destructive on PAREN-STATE.
2304 car)
2315 ;; Whack off any state information from PAREN-STATE which lies at or
2316 ;; after BUFPOS. Not destructive on PAREN-STATE.
2321 ;; just check the car, because in a balanced brace
2322 ;; expression, it must be impossible for the corresponding
2323 ;; close brace to be before point, but the open brace to
2324 ;; be after.
2326 nil ; whack it off
2328 ;; its possible that the open brace is before
2329 ;; bufpos, but the close brace is after. In that
2330 ;; case, convert this to a non-cons element. The
2331 ;; rest of the state is before bufpos, so we're
2332 ;; done.
2334 ;; we know that both the open and close braces are
2335 ;; before bufpos, so we also know that everything else
2336 ;; on state is before bufpos.
2339 nil ; whack it off
2340 ;; it's before bufpos, so everything else should too.
2343 nil)))
2346 ;; Return the bufpos of the innermost enclosing open paren before
2347 ;; bufpos, or nil if none was found.
2357 enclosingp))
2360 ;; Return the bufpos of the outermost enclosing open paren, or nil
2361 ;; if none was found.
2368 pos))
2371 ;; Return the closest "safe" position recorded on PAREN-STATE that
2372 ;; is higher up than BUFPOS. Return nil if PAREN-STATE doesn't
2373 ;; contain any. Return nil if BUFPOS is nil, which is useful to
2374 ;; find the closest limit before a given limit that might be nil.
2375 ;;
2376 ;; A "safe" position is a position at or after a recorded open
2377 ;; paren, or after a recorded close paren. The returned position is
2378 ;; thus either the first position after a close brace, or the first
2379 ;; position after an enclosing paren, or at the enclosing paren in
2380 ;; case BUFPOS is immediately after it.
2390 ;; See below.
2393 ;; elem is the position at and not after the opening paren, so
2394 ;; we can go forward one more step unless it's equal to
2395 ;; bufpos. This is useful in some cases avoid an extra paren
2396 ;; level between the safe position and bufpos.
2401 ;; This is used for `font-lock-beginning-of-syntax-function'. It
2402 ;; goes to the closest previous point that is known to be outside
2403 ;; any string literal or comment. `c-state-cache' is used if it has
2404 ;; a position in the vicinity.
2406 elem
2409 ;; Note: Similar code in `c-safe-position'. The
2410 ;; difference is that we accept a safe position at
2411 ;; the point and don't bother to go forward past open
2412 ;; parens.
2427 ;; The position is far back. Try `c-beginning-of-defun-1'
2428 ;; (although we can't be entirely sure it will go to a position
2429 ;; outside a comment or string in current emacsen). FIXME:
2430 ;; Consult `syntax-ppss' here.
2435 \f
2436 ;; Tools for scanning identifiers and other tokens.
2439 "Return non-nil if the point is on or directly after an identifier.
2440 Keywords are recognized and not considered identifiers. If an
2441 identifier is detected, the returned value is its starting position.
2442 If an identifier ends at the point and another begins at it \(can only
2443 happen in Pike) then the point for the preceding one is returned.
2445 Note that this function might do hidden buffer changes. See the
2446 comment at the start of cc-engine.el for more info."
2448 ;; FIXME: Shouldn't this function handle "operator" in C++?
2455 ;; Check for a normal (non-keyword) identifier.
2461 ;; Handle the `<operator> syntax in Pike.
2465 t
2472 ;; Handle the "operator +" syntax in C++.
2489 )))
2492 ;; If the point is at the end of a symbol then skip backward to the
2493 ;; beginning of it. Don't move otherwise. Return non-nil if point
2494 ;; moved.
2495 ;;
2496 ;; This function might do hidden buffer changes.
2499 ;; Handle the `<operator> syntax in Pike.
2505 t
2507 nil)))))
2510 ;; Move to the beginning of the current token. Do not move if not
2511 ;; in the middle of one. BACK-LIMIT may be used to bound the
2512 ;; backward search; if given it's assumed to be at the boundary
2513 ;; between two tokens. Return non-nil if the point is move, nil
2514 ;; otherwise.
2515 ;;
2516 ;; This function might do hidden buffer changes.
2523 ;; `c-nonsymbol-token-regexp' should always match
2524 ;; since we've skipped backward over punctuator
2525 ;; or paren syntax, but consume one char in case
2526 ;; it doesn't so that we don't leave point before
2527 ;; some earlier incorrect token.
2534 ;; Move to the end of the current token. Do not move if not in the
2535 ;; middle of one. BACK-LIMIT may be used to bound the backward
2536 ;; search; if given it's assumed to be at the boundary between two
2537 ;; tokens. Return non-nil if the point is moved, nil otherwise.
2538 ;;
2539 ;; This function might do hidden buffer changes.
2547 ;; `c-nonsymbol-token-regexp' should always match since
2548 ;; we've skipped backward over punctuator or paren
2549 ;; syntax, but move forward in case it doesn't so that
2550 ;; we don't leave point earlier than we started with.
2566 "Move forward by tokens.
2567 A token is defined as all symbols and identifiers which aren't
2569 treated properly). Point is always either left at the beginning of a
2570 token or not moved at all. COUNT specifies the number of tokens to
2571 move; a negative COUNT moves in the opposite direction. A COUNT of 0
2572 moves to the next token beginning only if not already at one. If
2573 BALANCED is true, move over balanced parens, otherwise move into them.
2574 Also, if BALANCED is true, never move out of an enclosing paren.
2576 LIMIT sets the limit for the movement and defaults to the point limit.
2577 The case when LIMIT is set in the middle of a token, comment or macro
2578 is handled correctly, i.e. the point won't be left there.
2580 Return the number of tokens left to move \(positive or negative). If
2581 BALANCED is true, a move over a balanced paren counts as one. Note
2582 that if COUNT is 0 and no appropriate token beginning is found, 1 will
2583 be returned. Thus, a return value of 0 guarantees that point is at
2584 the requested position and a return value less \(without signs) than
2585 COUNT guarantees that point is at the beginning of some token.
2587 Note that this function might do hidden buffer changes. See the
2588 comment at the start of cc-engine.el for more info."
2595 c-jump-syntax-balanced
2596 c-jump-syntax-unbalanced))
2601 ;; If count is zero we should jump if in the middle of a token.
2608 ;; Skip whitespace. Count this as a move if we did in
2609 ;; fact move.
2613 ;; Moved out of bounds. Make sure the returned count isn't zero.
2618 ;; Use `condition-case' to avoid having the limit tests
2619 ;; inside the loop.
2627 t)
2630 t)
2631 ;; `c-nonsymbol-token-regexp' above should always
2632 ;; match if there are correct tokens. Try to
2633 ;; widen to see if the limit was set in the
2634 ;; middle of one, else fall back to treating
2635 ;; the offending thing as a one character token.
2640 nil)
2643 t))))
2653 count)))
2656 "Move backward by tokens.
2657 See `c-forward-token-2' for details."
2665 c-jump-syntax-balanced
2666 c-jump-syntax-unbalanced))
2670 ;; The count is zero so try to skip to the beginning of the
2671 ;; current token.
2675 ;; The limit is inside the same token, so return 1.
2678 ;; We're not in the middle of a token. If there's
2679 ;; whitespace after the point then we must move backward,
2680 ;; so set count to 1 in that case.
2682 ;; If we're looking at a '#' that might start a cpp
2683 ;; directive then we have to do a more elaborate check.
2696 ;; Use `condition-case' to avoid having to check for buffer
2697 ;; limits in `backward-char', `scan-sexps' and `goto-char' below.
2706 ;; This can be very inefficient if there's a long
2707 ;; sequence of operator tokens without any separation.
2708 ;; That doesn't happen in practice, anyway.
2718 count)))
2721 "Like `c-forward-token-2' but doesn't treat multicharacter operator
2723 characters are jumped over character by character. This function is
2724 for compatibility only; it's only a wrapper over `c-forward-token-2'."
2729 "Like `c-backward-token-2' but doesn't treat multicharacter operator
2731 characters are jumped over character by character. This function is
2732 for compatibility only; it's only a wrapper over `c-backward-token-2'."
2736 \f
2737 ;; Tools for doing searches restricted to syntactically relevant text.
2740 paren-level not-inside-token
2741 lookbehind-submatch)
2742 "Like `re-search-forward', but only report matches that are found
2743 in syntactically significant text. I.e. matches in comments, macros
2744 or string literals are ignored. The start point is assumed to be
2745 outside any comment, macro or string literal, or else the content of
2746 that region is taken as syntactically significant text.
2748 If PAREN-LEVEL is non-nil, an additional restriction is added to
2749 ignore matches in nested paren sexps. The search will also not go
2750 outside the current list sexp, which has the effect that if the point
2751 should be moved to BOUND when no match is found \(i.e. NOERROR is
2752 neither nil nor t), then it will be at the closing paren if the end of
2753 the current list sexp is encountered first.
2755 If NOT-INSIDE-TOKEN is non-nil, matches in the middle of tokens are
2756 ignored. Things like multicharacter operators and special symbols
2758 constants.
2760 If LOOKBEHIND-SUBMATCH is non-nil, it's taken as a number of a
2761 subexpression in REGEXP. The end of that submatch is used as the
2762 position to check for syntactic significance. If LOOKBEHIND-SUBMATCH
2763 isn't used or if that subexpression didn't match then the start
2765 subexpression is never tested before the starting position, so it
2769 subexpression can match the end of nonwhite syntactic whitespace,
2770 i.e. the end of comments or cpp directives. This since the function
2771 skips over such things before resuming the search. It's on the other
2773 matches syntactic whitespace.
2775 Bug: Unbalanced parens inside cpp directives are currently not handled
2776 correctly \(i.e. they don't get ignored as they should) when
2777 PAREN-LEVEL is set.
2779 Note that this function might do hidden buffer changes. See the
2780 comment at the start of cc-engine.el for more info."
2785 ;;(message "c-syntactic-re-search-forward %s %s %S" (point) bound regexp)
2788 tmp
2789 ;; Start position for the last search.
2790 search-pos
2791 ;; The `parse-partial-sexp' state between the start position
2792 ;; and the point.
2793 state
2794 ;; The current position after the last state update. The next
2795 ;; `parse-partial-sexp' continues from here.
2797 ;; The position at which to check the state and the state
2798 ;; there. This is separate from `state-pos' since we might
2799 ;; need to back up before doing the next search round.
2800 check-pos check-state
2801 ;; Last position known to end a token.
2803 ;; Set when a valid match is found.
2804 found)
2822 state-pos check-pos paren-level nil state))
2824 check-state state))
2826 ;; NOTE: If we got a look behind subexpression and get
2827 ;; an insignificant match in something that isn't
2828 ;; syntactic whitespace (i.e. strings or in nested
2829 ;; parentheses), then we can never skip more than a
2830 ;; single character from the match start position
2831 ;; (i.e. `state-pos' here) before continuing the
2832 ;; search. That since the look behind subexpression
2833 ;; might match the end of the insignificant region in
2834 ;; the next search.
2838 ;; Match inside a line comment. Skip to eol. Use
2839 ;; `re-search-forward' instead of `skip-chars-forward' to get
2840 ;; the right bound behavior.
2844 ;; Match inside a block comment. Skip to the '*/'.
2851 ;; Match in the middle of the opener of a block or line
2852 ;; comment.
2857 ;; The last `parse-partial-sexp' above might have
2858 ;; stopped short of the real check position if the end
2859 ;; of the current sexp was encountered in paren-level
2860 ;; mode. The checks above are always false in that
2861 ;; case, and since they can do better skipping in
2862 ;; lookbehind-submatch mode, we do them before
2863 ;; checking the paren level.
2867 ;; Check the paren level first since we're short of the
2868 ;; syntactic checking position if the end of the
2869 ;; current sexp was encountered by `parse-partial-sexp'.
2872 ;; Inside a nested paren sexp.
2874 ;; See the NOTE above.
2876 ;; Skip out of the paren quickly.
2880 ;; Have exited the current paren sexp.
2883 ;; The last `parse-partial-sexp' call above
2884 ;; has left us just after the closing paren
2885 ;; in this case, so we can modify the bound
2886 ;; to leave the point at the right position
2887 ;; upon return.
2889 nil)
2893 ;; Match inside a string.
2896 ;; See the NOTE above.
2898 ;; Skip to the end of the string before continuing.
2907 continue)))
2912 ;; Match inside a macro. Skip to the end of it.
2920 (< check-pos
2926 ;; Inside a token.
2928 ;; See the NOTE above.
2933 ;; A real match.
2935 nil)))
2937 ;; Should loop to search again, but take care to avoid
2938 ;; looping on the same spot.
2942 nil
2945 t))))
2951 ;;(message "c-syntactic-re-search-forward done %s" (or (match-end 0) (point)))
2958 ;; Search failed. Set point as appropriate.
2962 nil)))
2965 "Like `skip-chars-backward' but only look at syntactically relevant chars,
2966 i.e. don't stop at positions inside syntactic whitespace or string
2967 literals. Preprocessor directives are also ignored, with the exception
2968 of the one that the point starts within, if any. If LIMIT is given,
2969 it's assumed to be at a syntactically relevant position.
2971 If PAREN-LEVEL is non-nil, the function won't stop in nested paren
2972 sexps, and the search will also not go outside the current paren sexp.
2973 However, if LIMIT or the buffer limit is reached inside a nested paren
2974 then the point will be left at the limit.
2976 Non-nil is returned if the point moved, nil otherwise.
2978 Note that this function might do hidden buffer changes. See the
2979 comment at the start of cc-engine.el for more info."
2982 state
2983 ;; A list of syntactically relevant positions in descending
2984 ;; order. It's used to avoid scanning repeatedly over
2985 ;; potentially large regions with `parse-partial-sexp' to verify
2986 ;; each position.
2987 safe-pos-list
2988 ;; The position at the beginning of `safe-pos-list'.
2989 safe-pos
2990 ;; The result from `c-beginning-of-macro' at the start position or the
2991 ;; start position itself if it isn't within a macro. Evaluated on
2992 ;; demand.
2993 start-macro-beg
2994 ;; The earliest position after the current one with the same paren
2995 ;; level. Used only when `paren-level' is set.
3002 ;; Use `parse-partial-sexp' from a safe position down to
3003 ;; the point to check if it's outside comments and
3004 ;; strings.
3006 ;; Pick a safe position as close to the point as
3007 ;; possible.
3008 ;;
3009 ;; FIXME: Consult `syntax-ppss' here if our
3010 ;; cache doesn't give a good position.
3022 ;; Cache positions along the way to use if we have to
3023 ;; back up more. We cache every closing paren on the
3024 ;; same level. If the paren cache is relevant in this
3025 ;; region then we're typically already on the same
3026 ;; level as the target position. Note that we might
3027 ;; cache positions after opening parens in case
3028 ;; safe-pos is in a nested list. That's both uncommon
3029 ;; and harmless.
3039 ;; Inside string or comment. Continue search at the
3040 ;; beginning of it.
3042 t)
3050 ;; Not at the right level.
3053 ;; We stop above if we go out of a paren.
3054 ;; Now check whether it precedes or is
3055 ;; nested in the starting sexp.
3059 pps-end-pos paren-level-pos
3060 nil nil state-2))
3063 ;; We've stopped short of the starting position
3064 ;; so the hit was inside a nested list. Go up
3065 ;; until we are at the right level.
3074 nil)
3075 t))
3078 nil))
3080 ;; The hit was outside the list at the start
3081 ;; position. Go to the start of the list and exit.
3083 nil))
3086 ;; Inside a macro.
3094 t
3096 ;; It's inside the same macro we started in so it's
3097 ;; a relevant match.
3099 nil)))))
3101 ;; If the state contains the start of the containing sexp we
3102 ;; cache that position too, so that parse-partial-sexp in the
3103 ;; next run has a bigger chance of starting at the same level
3104 ;; as the target position and thus will get more good safe
3105 ;; positions into the list.
3112 ;; Skip syntactic ws afterwards so that we don't stop at the
3113 ;; end of a comment if `skip-chars' is something like "^/".
3117 ;; We might want to extend this with more useful return values in
3118 ;; the future.
3121 ;; The following is an alternative implementation of
3122 ;; `c-syntactic-skip-backward' that uses backward movement to keep
3123 ;; track of the syntactic context. It turned out to be generally
3124 ;; slower than the one above which uses forward checks from earlier
3125 ;; safe positions.
3126 ;;
3127 ;;(defconst c-ssb-stop-re
3128 ;; ;; The regexp matching chars `c-syntactic-skip-backward' needs to
3129 ;; ;; stop at to avoid going into comments and literals.
3130 ;; (concat
3131 ;; ;; Match comment end syntax and string literal syntax. Also match
3132 ;; ;; '/' for block comment endings (not covered by comment end
3133 ;; ;; syntax).
3134 ;; "\\s>\\|/\\|\\s\""
3135 ;; (if (memq 'gen-string-delim c-emacs-features)
3136 ;; "\\|\\s|"
3137 ;; "")
3138 ;; (if (memq 'gen-comment-delim c-emacs-features)
3139 ;; "\\|\\s!"
3140 ;; "")))
3141 ;;
3142 ;;(defconst c-ssb-stop-paren-re
3143 ;; ;; Like `c-ssb-stop-re' but also stops at paren chars.
3144 ;; (concat c-ssb-stop-re "\\|\\s(\\|\\s)"))
3145 ;;
3146 ;;(defconst c-ssb-sexp-end-re
3147 ;; ;; Regexp matching the ending syntax of a complex sexp.
3148 ;; (concat c-string-limit-regexp "\\|\\s)"))
3149 ;;
3150 ;;(defun c-syntactic-skip-backward (skip-chars &optional limit paren-level)
3151 ;; "Like `skip-chars-backward' but only look at syntactically relevant chars,
3152 ;;i.e. don't stop at positions inside syntactic whitespace or string
3153 ;;literals. Preprocessor directives are also ignored. However, if the
3154 ;;point is within a comment, string literal or preprocessor directory to
3155 ;;begin with, its contents is treated as syntactically relevant chars.
3156 ;;If LIMIT is given, it limits the backward search and the point will be
3157 ;;left there if no earlier position is found.
3158 ;;
3159 ;;If PAREN-LEVEL is non-nil, the function won't stop in nested paren
3160 ;;sexps, and the search will also not go outside the current paren sexp.
3161 ;;However, if LIMIT or the buffer limit is reached inside a nested paren
3162 ;;then the point will be left at the limit.
3163 ;;
3164 ;;Non-nil is returned if the point moved, nil otherwise.
3165 ;;
3166 ;;Note that this function might do hidden buffer changes. See the
3167 ;;comment at the start of cc-engine.el for more info."
3168 ;;
3169 ;; (save-restriction
3170 ;; (when limit
3171 ;; (narrow-to-region limit (point-max)))
3172 ;;
3173 ;; (let ((start (point)))
3174 ;; (catch 'done
3175 ;; (while (let ((last-pos (point))
3176 ;; (stop-pos (progn
3177 ;; (skip-chars-backward skip-chars)
3178 ;; (point))))
3179 ;;
3180 ;; ;; Skip back over the same region as
3181 ;; ;; `skip-chars-backward' above, but keep to
3182 ;; ;; syntactically relevant positions.
3183 ;; (goto-char last-pos)
3184 ;; (while (and
3185 ;; ;; `re-search-backward' with a single char regexp
3186 ;; ;; should be fast.
3187 ;; (re-search-backward
3188 ;; (if paren-level c-ssb-stop-paren-re c-ssb-stop-re)
3189 ;; stop-pos 'move)
3190 ;;
3191 ;; (progn
3192 ;; (cond
3193 ;; ((looking-at "\\s(")
3194 ;; ;; `paren-level' is set and we've found the
3195 ;; ;; start of the containing paren.
3196 ;; (forward-char)
3197 ;; (throw 'done t))
3198 ;;
3199 ;; ((looking-at c-ssb-sexp-end-re)
3200 ;; ;; We're at the end of a string literal or paren
3201 ;; ;; sexp (if `paren-level' is set).
3202 ;; (forward-char)
3203 ;; (condition-case nil
3204 ;; (c-backward-sexp)
3205 ;; (error
3206 ;; (goto-char limit)
3207 ;; (throw 'done t))))
3208 ;;
3209 ;; (t
3210 ;; (forward-char)
3211 ;; ;; At the end of some syntactic ws or possibly
3212 ;; ;; after a plain '/' operator.
3213 ;; (let ((pos (point)))
3214 ;; (c-backward-syntactic-ws)
3215 ;; (if (= pos (point))
3216 ;; ;; Was a plain '/' operator. Go past it.
3217 ;; (backward-char)))))
3218 ;;
3219 ;; (> (point) stop-pos))))
3220 ;;
3221 ;; ;; Now the point is either at `stop-pos' or at some
3222 ;; ;; position further back if `stop-pos' was at a
3223 ;; ;; syntactically irrelevant place.
3224 ;;
3225 ;; ;; Skip additional syntactic ws so that we don't stop
3226 ;; ;; at the end of a comment if `skip-chars' is
3227 ;; ;; something like "^/".
3228 ;; (c-backward-syntactic-ws)
3229 ;;
3230 ;; (< (point) stop-pos))))
3231 ;;
3232 ;; ;; We might want to extend this with more useful return values
3233 ;; ;; in the future.
3234 ;; (/= (point) start))))
3236 \f
3237 ;; Tools for handling comments and string literals.
3240 "Return the type of literal point is in, if any.
3241 The return value is `c' if in a C-style comment, `c++' if in a C++
3242 style comment, `string' if in a string literal, `pound' if DETECT-CPP
3243 is non-nil and in a preprocessor line, or nil if somewhere else.
3244 Optional LIM is used as the backward limit of the search. If omitted,
3245 or nil, `c-beginning-of-defun' is used.
3247 The last point calculated is cached if the cache is enabled, i.e. if
3248 `c-in-literal-cache' is bound to a two element vector.
3250 Note that this function might do hidden buffer changes. See the
3251 comment at the start of cc-engine.el for more info."
3267 ;; cache this result if the cache is enabled
3270 rtn)))
3272 ;; XEmacs has a built-in function that should make this much quicker.
3273 ;; I don't think we even need the cache, which makes our lives more
3274 ;; complicated anyway. In this case, lim is only used to detect
3275 ;; cpp directives.
3276 ;;
3277 ;; Note that there is a bug in Xemacs's buffer-syntactic-context when used in
3278 ;; conjunction with syntax-table-properties. The bug is present in, e.g.,
3279 ;; Xemacs 21.4.4. It manifested itself thus:
3280 ;;
3281 ;; Starting with an empty AWK Mode buffer, type
3282 ;; /regexp/ {<C-j>
3283 ;; Point gets wrongly left at column 0, rather than being indented to tab-width.
3284 ;;
3285 ;; AWK Mode is designed such that when the first / is typed, it gets the
3286 ;; syntax-table property "string fence". When the second / is typed, BOTH /s
3287 ;; are given the s-t property "string". However, buffer-syntactic-context
3288 ;; fails to take account of the change of the s-t property on the opening / to
3289 ;; "string", and reports that the { is within a string started by the second /.
3290 ;;
3291 ;; The workaround for this is for the AWK Mode initialisation to switch the
3292 ;; defalias for c-in-literal to c-slow-in-literal. This will slow down other
3293 ;; cc-modes in Xemacs whenever an awk-buffer has been initialised.
3294 ;;
3295 ;; (Alan Mackenzie, 2003/4/30).
3298 ;; This function might do hidden buffer changes.
3311 ;; The defalias above isn't enough to shut up the byte compiler.
3315 "Return a cons of the beginning and end positions of the comment or
3316 string surrounding point (including both delimiters), or nil if point
3318 to start parsing from. If NEAR is non-nil, then the limits of any
3320 spaces and tabs between point and the literal. The search for such a
3321 literal is done first in forward direction. If NOT-IN-DELIMITER is
3322 non-nil, the case when point is inside a starting delimiter won't be
3323 recognized. This only has effect for comments, which have starting
3324 delimiters with more than one character.
3326 Note that this function might do hidden buffer changes. See the
3327 comment at the start of cc-engine.el for more info."
3349 ;; We're standing in a comment starter.
3356 ;; Search forward for a literal.
3368 ;; Search backward.
3379 ;; Block comment. Due to the nature of line
3380 ;; comments, they will always be covered by the
3381 ;; normal case above.
3384 ;; If LIM is bogus, beg will be bogus.
3388 ))))
3390 ;; In case external callers use this; it did have a docstring.
3394 "If the argument is a cons of two buffer positions (such as returned by
3395 `c-literal-limits'), and that range contains a C++ style line comment,
3396 then an extended range is returned that contains all adjacent line
3397 comments (i.e. all comments that starts in the same column with no
3398 empty lines or non-whitespace characters between them). Otherwise the
3399 argument is returned.
3401 Note that this function might do hidden buffer changes. See the
3402 comment at the start of cc-engine.el for more info."
3413 ;; Got to take care in the backward direction to handle
3414 ;; comments which are preceded by code.
3428 range)
3432 "Convenience function that given the result of `c-literal-limits',
3433 returns nil or the type of literal that the range surrounds. It's
3434 much faster than using `c-in-literal' and is intended to be used when
3435 you need both the type of a literal and its limits.
3437 Note that this function might do hidden buffer changes. See the
3438 comment at the start of cc-engine.el for more info."
3449 range))
3451 \f
3452 ;; `c-find-decl-spots' and accompanying stuff.
3454 ;; Variables used in `c-find-decl-spots' to cache the search done for
3455 ;; the first declaration in the last call. When that function starts,
3456 ;; it needs to back up over syntactic whitespace to look at the last
3457 ;; token before the region being searched. That can sometimes cause
3458 ;; moves back and forth over a quite large region of comments and
3459 ;; macros, which would be repeated for each changed character when
3460 ;; we're called during fontification, since font-lock refontifies the
3461 ;; current line for each change. Thus it's worthwhile to cache the
3462 ;; first match.
3463 ;;
3464 ;; `c-find-decl-syntactic-pos' is a syntactically relevant position in
3465 ;; the syntactic whitespace less or equal to some start position.
3466 ;; There's no cached value if it's nil.
3467 ;;
3468 ;; `c-find-decl-match-pos' is the match position if
3469 ;; `c-find-decl-prefix-search' matched before the syntactic whitespace
3470 ;; at `c-find-decl-syntactic-pos', or nil if there's no such match.
3481 ; (defface c-debug-decl-spot-face
3482 ; '((t (:background "Turquoise")))
3483 ; "Debug face to mark the spots where `c-find-decl-spots' stopped.")
3484 ; (defface c-debug-decl-sws-face
3485 ; '((t (:background "Khaki")))
3486 ; "Debug face to mark the syntactic whitespace between the declaration
3487 ; spots and the preceding token end.")
3503 ;; Macro used inside `c-find-decl-spots'. It ought to be a defun,
3504 ;; but it contains lots of free variables that refer to things
3505 ;; inside `c-find-decl-spots'. The point is left at `cfd-match-pos'
3506 ;; if there is a match, otherwise at `cfd-limit'.
3507 ;;
3508 ;; This macro might do hidden buffer changes.
3511 ;; Find the next property match position if we haven't got one already.
3522 ;; Find the next `c-decl-prefix-or-start-re' match if we haven't
3523 ;; got one already.
3533 ;; Match. Check if it's inside a comment or string literal.
3536 ;; Matched the end of a token preceding a decl spot.
3540 ;; Matched a token that start a decl spot.
3543 c-literal-faces)
3545 ;; No match. Finish up and exit the loop.
3547 nil)
3549 ;; Skip out of comments and string literals.
3556 ;; If we matched at the decl start, we have to back up over the
3557 ;; preceding syntactic ws to set `cfd-match-pos' and to catch
3558 ;; any decl spots in the syntactic ws.
3563 ;; Choose whichever match is closer to the start.
3566 cfd-re-match nil)
3568 cfd-prop-match nil))
3573 ;; Skip forward past comments only so we don't skip macros.
3575 ;; Set the position to continue at. We can avoid going over
3576 ;; the comments skipped above a second time, but it's possible
3577 ;; that the comment skipping has taken us past `cfd-prop-match'
3578 ;; since the property might be used inside comments.
3584 ;; Call CFD-FUN for each possible spot for a declaration, cast or
3585 ;; label from the point to CFD-LIMIT. Such a spot is:
3586 ;;
3587 ;; o The first token after bob.
3588 ;; o The first token after the end of submatch 1 in
3589 ;; `c-decl-prefix-or-start-re' when that submatch matches.
3590 ;; o The start of each `c-decl-prefix-or-start-re' match when
3591 ;; submatch 1 doesn't match.
3592 ;; o The first token after the end of each occurence of the
3593 ;; `c-type' text property with the value `c-decl-end', provided
3594 ;; `c-type-decl-end-used' is set.
3595 ;;
3596 ;; Only a spot that match CFD-DECL-RE and whose face is in the
3597 ;; CFD-FACE-CHECKLIST list causes CFD-FUN to be called. The face
3598 ;; check is disabled if CFD-FACE-CHECKLIST is nil.
3599 ;;
3600 ;; If the match is inside a macro then the buffer is narrowed to the
3601 ;; end of it, so that CFD-FUN can investigate the following tokens
3602 ;; without matching something that begins inside a macro and ends
3603 ;; outside it. It's to avoid this work that the CFD-DECL-RE and
3604 ;; CFD-FACE-CHECKLIST checks exist.
3605 ;;
3606 ;; CFD-FUN is called with point at the start of the spot. It's
3607 ;; passed two arguments: The first is the end position of the token
3608 ;; preceding the spot, or 0 for the implicit match at bob. The
3609 ;; second is a flag that is t when the match is inside a macro. If
3610 ;; CFD-FUN adds `c-decl-end' properties somewhere below the current
3611 ;; spot, it should return non-nil to ensure that the next search
3612 ;; will find them.
3613 ;;
3614 ;; The spots are visited approximately in order from top to bottom.
3615 ;; It's however the positions where `c-decl-prefix-or-start-re'
3616 ;; matches and where `c-decl-end' properties are found that are in
3617 ;; order. Since the spots often are at the following token, they
3618 ;; might be visited out of order insofar as more spots are reported
3619 ;; later on within the syntactic whitespace between the match
3620 ;; positions and their spots.
3621 ;;
3622 ;; It's assumed that comments and strings are fontified in the
3623 ;; searched range.
3624 ;;
3625 ;; This is mainly used in fontification, and so has an elaborate
3626 ;; cache to handle repeated calls from the same start position; see
3627 ;; the variables above.
3628 ;;
3629 ;; All variables in this function begin with `cfd-' to avoid name
3630 ;; collision with the (dynamically bound) variables used in CFD-FUN.
3631 ;;
3632 ;; This function might do hidden buffer changes.
3636 ;; The end of the token preceding the decl spot last found
3637 ;; with `c-decl-prefix-or-start-re'. `cfd-limit' if there's
3638 ;; no match.
3639 cfd-re-match
3640 ;; The end position of the last `c-decl-prefix-or-start-re'
3641 ;; match. If this is greater than `cfd-continue-pos', the
3642 ;; next regexp search is started here instead.
3644 ;; The end of the last `c-decl-end' found by
3645 ;; `c-find-decl-prefix-search'. `cfd-limit' if there's no
3646 ;; match. If searching for the property isn't needed then we
3647 ;; disable it by setting it to `cfd-limit' directly.
3649 ;; The end of the token preceding the decl spot last found by
3650 ;; `c-find-decl-prefix-search'. 0 for the implicit match at
3651 ;; bob. `cfd-limit' if there's no match. In other words,
3652 ;; this is the minimum of `cfd-re-match' and `cfd-prop-match'.
3654 ;; The position to continue searching at.
3655 cfd-continue-pos
3656 ;; The position of the last "real" token we've stopped at.
3657 ;; This can be greater than `cfd-continue-pos' when we get
3658 ;; hits inside macros or at `c-decl-end' positions inside
3659 ;; comments.
3661 ;; The end position of the last entered macro.
3664 ;; Initialize by finding a syntactically relevant start position
3665 ;; before the point, and do the first `c-decl-prefix-or-start-re'
3666 ;; search unless we're at bob.
3669 ;; Must back up a bit since we look for the end of the previous
3670 ;; statement or declaration, which is earlier than the first
3671 ;; returned match.
3674 ;; First we need to move to a syntactically relevant position.
3675 ;; Begin by backing out of comment or string literals.
3678 ;; Try to use the faces to back up to the start of the
3679 ;; literal. FIXME: What if the point is on a declaration
3680 ;; inside a comment?
3686 ;; XEmacs doesn't fontify the quotes surrounding string
3687 ;; literals.
3696 ;; Don't trust the literal to contain only literal faces
3697 ;; (the font lock package might not have fontified the
3698 ;; start of it at all, for instance) so check that we have
3699 ;; arrived at something that looks like a start or else
3700 ;; resort to `c-literal-limits'.
3707 ;; The start is in a literal. If the limit is in the same
3708 ;; one we don't have to find a syntactic position etc. We
3709 ;; only check that if the limit is at or before bonl to save
3710 ;; time; it covers the by far most common case when font-lock
3711 ;; refontifies the current line only.
3722 ;; Completely inside a literal. Set up variables to trig the
3723 ;; (< cfd-continue-pos cfd-start-pos) case below and it'll
3724 ;; find a suitable start position.
3727 ;; Check if the region might be completely inside a macro, to
3728 ;; optimize that like the completely-inside-literal above.
3735 ;; (Maybe) completely inside a macro. Only need to trig the
3736 ;; (< cfd-continue-pos cfd-start-pos) case below to make it
3737 ;; set things up.
3739 start-in-macro t))
3742 ;; Back out of any macro so we don't miss any declaration
3743 ;; that could follow after it.
3747 ;; Now we're at a proper syntactically relevant position so we
3748 ;; can use the cache. But first clear it if it applied
3749 ;; further down.
3754 ;; Don't have to do this if the cache is relevant here,
3755 ;; typically if the same line is refontified again. If
3756 ;; we're just some syntactic whitespace further down we can
3757 ;; still use the cache to limit the skipping.
3760 ;; If we hit `c-find-decl-syntactic-pos' and
3761 ;; `c-find-decl-match-pos' is set then we install the cached
3762 ;; values. If we hit `c-find-decl-syntactic-pos' and
3763 ;; `c-find-decl-match-pos' is nil then we know there's no decl
3764 ;; prefix in the whitespace before `c-find-decl-syntactic-pos'
3765 ;; and so we can continue the search from this point. If we
3766 ;; didn't hit `c-find-decl-syntactic-pos' then we're now in
3767 ;; the right spot to begin searching anyway.
3769 c-find-decl-match-pos)
3771 cfd-continue-pos syntactic-pos)
3776 ;; Always consider bob a match to get the first
3777 ;; declaration in the file. Do this separately instead of
3778 ;; letting `c-decl-prefix-or-start-re' match bob, so that
3779 ;; regexp always can consume at least one character to
3780 ;; ensure that we won't get stuck in an infinite loop.
3785 ;; Do an initial search now. In the bob case above it's
3786 ;; only done to search for a `c-decl-end' spot.
3790 cfd-match-pos)))))
3792 ;; Advance `cfd-continue-pos' if it's before the start position.
3793 ;; The closest continue position that might have effect at or
3794 ;; after the start depends on what we started in. This also
3795 ;; finds a suitable start position in the special cases when the
3796 ;; region is completely within a literal or macro.
3801 ;; If we're in a macro then it's the closest preceding token
3802 ;; in the macro. Check this before `start-in-literal',
3803 ;; since if we're inside a literal in a macro, the preceding
3804 ;; token is earlier than any `c-decl-end' spot inside the
3805 ;; literal (comment).
3807 ;; The only syntactic ws in macros are comments.
3813 ;; If we're in a comment it can only be the closest
3814 ;; preceding `c-decl-end' position within that comment, if
3815 ;; any. Go back to the beginning of such a property so that
3816 ;; `c-find-decl-prefix-search' will find the end of it.
3817 ;; (Can't stop at the end and install it directly on
3818 ;; `cfd-prop-match' since that variable might be cleared
3819 ;; after `cfd-fun' below.)
3820 ;;
3821 ;; Note that if the literal is a string then the property
3822 ;; search will simply skip to the beginning of it right
3823 ;; away.
3835 ;; Didn't find any property inside the comment, so we can
3836 ;; skip it entirely. (This won't skip past a string, but
3837 ;; that'll be handled quickly by the next
3838 ;; `c-find-decl-prefix-search' anyway.)
3844 ;; If we started in normal code, the only match that might
3845 ;; apply before the start is what we already got in
3846 ;; `cfd-match-pos' so we can continue at the start position.
3847 ;; (Note that we don't get here if the first match is below
3848 ;; it.)
3851 ;; Delete found matches if they are before our new continue
3852 ;; position, so that `c-find-decl-prefix-search' won't back up
3853 ;; to them later on.
3861 ;; This is the normal case and we got a proper syntactic
3862 ;; position. If there's a match then it's always outside
3863 ;; macros and comments, so advance to the next token and set
3864 ;; `cfd-token-pos'. The loop below will later go back using
3865 ;; `cfd-continue-pos' to fix declarations inside the
3866 ;; syntactic ws.
3874 ;; Have one of the special cases when the region is completely
3875 ;; within a literal or macro. `cfd-continue-pos' is set to a
3876 ;; good start position for the search, so do it.
3879 ;; Now loop. Round what? (ACM, 2006/7/5). We already got the first match.
3886 ;; Kludge to filter out matches on the "<" that
3887 ;; aren't open parens, for the sake of languages
3888 ;; that got `c-recognize-<>-arglists' set.
3893 ;; If `cfd-continue-pos' is less or equal to
3894 ;; `cfd-token-pos', we've got a hit inside a macro
3895 ;; that's in the syntactic whitespace before the last
3896 ;; "real" declaration we've checked. If they're equal
3897 ;; we've arrived at the declaration a second time, so
3898 ;; there's nothing to do.
3902 ;; If `cfd-continue-pos' is less than `cfd-token-pos'
3903 ;; we're still searching for declarations embedded in
3904 ;; the syntactic whitespace. In that case we need
3905 ;; only to skip comments and not macros, since they
3906 ;; can't be nested, and that's already been done in
3907 ;; `c-find-decl-prefix-search'.
3912 ;; Continue if the following token fails the
3913 ;; CFD-DECL-RE and CFD-FACE-CHECKLIST checks.
3920 t)))
3931 ;; Narrow to the end of the macro if we got a hit inside
3932 ;; one, to avoid recognizing things that start inside the
3933 ;; macro and end outside it.
3935 ;; Not in the same macro as in the previous round.
3946 t
3949 t)
3950 ;; The matched token was the last thing in the macro,
3951 ;; so the whole match is bogus.
3953 nil))))
3960 ;; Restore limits if we did macro narrowment above.
3968 \f
3969 ;; A cache for found types.
3971 ;; Buffer local variable that contains an obarray with the types we've
3972 ;; found. If a declaration is recognized somewhere we record the
3973 ;; fully qualified identifier in it to recognize it as a type
3974 ;; elsewhere in the file too. This is not accurate since we do not
3975 ;; bother with the scoping rules of the languages, but in practice the
3976 ;; same name is seldom used as both a type and something else in a
3977 ;; file, and we only use this as a last resort in ambiguous cases (see
3978 ;; `c-forward-decl-or-cast-1').
3979 ;;
3980 ;; Not every type need be in this cache. However, things which have
3981 ;; ceased to be types must be removed from it.
3982 ;;
3983 ;; Template types in C++ are added here too but with the template
3984 ;; arglist replaced with "<>" in references or "<" for the one in the
3985 ;; primary type. E.g. the type "Foo<A,B>::Bar<C>" is stored as
3986 ;; "Foo<>::Bar<". This avoids storing very long strings (since C++
3987 ;; template specs can be fairly sized programs in themselves) and
3988 ;; improves the hit ratio (it's a type regardless of the template
3989 ;; args; it's just not the same type, but we're only interested in
3990 ;; recognizing types, not telling distinct types apart). Note that
3991 ;; template types in references are added here too; from the example
3992 ;; above there will also be an entry "Foo<".
3997 ;; Clears `c-found-types'.
4001 ;; Add the given region as a type in `c-found-types'. If the region
4002 ;; doesn't match an existing type but there is a type which is equal
4003 ;; to the given one except that the last character is missing, then
4004 ;; the shorter type is removed. That's done to avoid adding all
4005 ;; prefixes of a type as it's being entered and font locked. This
4006 ;; doesn't cover cases like when characters are removed from a type
4007 ;; or added in the middle. We'd need the position of point when the
4008 ;; font locking is invoked to solve this well.
4009 ;;
4010 ;; This function might do hidden buffer changes.
4017 ;; Remove the "NAME" from c-found-types, if present.
4021 ;; Return non-nil if the given region contains a type in
4022 ;; `c-found-types'.
4023 ;;
4024 ;; This function might do hidden buffer changes.
4026 c-found-types))
4029 ;; Return all the types in `c-found-types' as a sorted list of
4030 ;; strings.
4034 type-list)))
4035 c-found-types)
4039 ;; An after change function which, in conjunction with the info in
4040 ;; c-maybe-stale-found-type (set in c-before-change), removes a type
4041 ;; from `c-found-types', should this type have become stale. For
4042 ;; example, this happens to "foo" when "foo \n bar();" becomes
4043 ;; "foo(); \n bar();". Such stale types, if not removed, foul up
4044 ;; the fontification.
4045 ;;
4046 ;; Have we, perhaps, added non-ws characters to the front/back of a found
4047 ;; type?
4067 ;; Changing the amount of (already existing) whitespace - don't do anything.
4070 ; (string-match "\\s *\\'" (nth 5 c-maybe-stale-found-type))
4073 ;; The syntactic relationship which defined a "found type" has been
4074 ;; destroyed.
4077 ;; ((eq (car c-maybe-stale-found-type) 'c-decl-type-start) FIXME!!!
4078 )))
4080 \f
4081 ;; Handling of small scale constructs like types and names.
4084 ;; This is called from `after-change-functions' when
4085 ;; c-recognize-<>-arglists' is set. It ensures that no "<" or ">"
4086 ;; chars with paren syntax become part of another operator like "<<"
4087 ;; or ">=".
4088 ;;
4089 ;; This function might do hidden buffer changes.
4121 ;; Dynamically bound variable that instructs `c-forward-type' to also
4122 ;; treat possible types (i.e. those that it normally returns 'maybe or
4123 ;; 'found for) as actual types (and always return 'found for them).
4124 ;; This means that it records them in `c-record-type-identifiers' if
4125 ;; that is set, and that it adds them to `c-found-types'.
4128 ;; Dynamically bound variable that instructs `c-forward-<>-arglist' to
4129 ;; mark up successfully parsed arglists with paren syntax properties on
4130 ;; the surrounding angle brackets and with `c-<>-arg-sep' in the
4131 ;; `c-type' property of each argument separating comma.
4132 ;;
4133 ;; Setting this variable also makes `c-forward-<>-arglist' recurse into
4134 ;; all arglists for side effects (i.e. recording types), otherwise it
4135 ;; exploits any existing paren syntax properties to quickly jump to the
4136 ;; end of already parsed arglists.
4137 ;;
4138 ;; Marking up the arglists is not the default since doing that correctly
4139 ;; depends on a proper value for `c-restricted-<>-arglists'.
4142 ;; Dynamically bound variable that instructs `c-forward-<>-arglist' to
4143 ;; not accept arglists that contain binary operators.
4144 ;;
4145 ;; This is primarily used to handle C++ template arglists. C++
4146 ;; disambiguates them by checking whether the preceding name is a
4147 ;; template or not. We can't do that, so we assume it is a template
4148 ;; if it can be parsed as one. That usually works well since
4149 ;; comparison expressions on the forms "a < b > c" or "a < b, c > d"
4150 ;; in almost all cases would be pointless.
4151 ;;
4152 ;; However, in function arglists, e.g. in "foo (a < b, c > d)", we
4153 ;; should let the comma separate the function arguments instead. And
4154 ;; in a context where the value of the expression is taken, e.g. in
4155 ;; "if (a < b || c > d)", it's probably not a template.
4158 ;; Dynamically bound variables that instructs
4159 ;; `c-forward-keyword-clause', `c-forward-<>-arglist',
4160 ;; `c-forward-name', `c-forward-type', `c-forward-decl-or-cast-1', and
4161 ;; `c-forward-label' to record the ranges of all the type and
4162 ;; reference identifiers they encounter. They will build lists on
4163 ;; these variables where each element is a cons of the buffer
4164 ;; positions surrounding each identifier. This recording is only
4165 ;; activated when `c-record-type-identifiers' is non-nil.
4166 ;;
4167 ;; All known types that can't be identifiers are recorded, and also
4168 ;; other possible types if `c-promote-possible-types' is set.
4169 ;; Recording is however disabled inside angle bracket arglists that
4170 ;; are encountered inside names and other angle bracket arglists.
4171 ;; Such occurrences are taken care of by `c-font-lock-<>-arglists'
4172 ;; instead.
4173 ;;
4174 ;; Only the names in C++ template style references (e.g. "tmpl" in
4175 ;; "tmpl<a,b>::foo") are recorded as references, other references
4176 ;; aren't handled here.
4177 ;;
4178 ;; `c-forward-label' records the label identifier(s) on
4179 ;; `c-record-ref-identifiers'.
4183 ;; This variable will receive a cons cell of the range of the last
4184 ;; single identifier symbol stepped over by `c-forward-name' if it's
4185 ;; successful. This is the range that should be put on one of the
4186 ;; record lists above by the caller. It's assigned nil if there's no
4187 ;; such symbol in the name.
4192 ;; Always true.
4202 ;; Always true.
4210 ;; Dynamically bound variable that instructs `c-forward-type' to
4211 ;; record the ranges of types that only are found. Behaves otherwise
4212 ;; like `c-record-type-identifiers'.
4216 ;; Used internally in `c-forward-keyword-clause' to move forward
4217 ;; over a type (if TYPE is 'type) or a name (otherwise) which
4218 ;; possibly is prefixed by keywords and their associated clauses.
4219 ;; Try with a type/name first to not trip up on those that begin
4220 ;; with a keyword. Return t if a known or found type is moved
4221 ;; over. The point is clobbered if nil is returned. If range
4222 ;; recording is enabled, the identifier is recorded on as a type
4223 ;; if TYPE is 'type or as a reference if TYPE is 'ref.
4224 ;;
4225 ;; This macro might do hidden buffer changes.
4230 nil
4237 t)))
4240 ;; Used internally in `c-forward-keyword-clause' to move forward
4241 ;; over a comma separated list of types or names using
4242 ;; `c-forward-keyword-prefixed-id'.
4243 ;;
4244 ;; This macro might do hidden buffer changes.
4255 ;; Submatch MATCH in the current match data is assumed to surround a
4256 ;; token. If it's a keyword, move over it and any immediately
4257 ;; following clauses associated with it, stopping at the start of
4258 ;; the next token. t is returned in that case, otherwise the point
4259 ;; stays and nil is returned. The kind of clauses that are
4260 ;; recognized are those specified by `c-type-list-kwds',
4261 ;; `c-ref-list-kwds', `c-colon-type-list-kwds',
4262 ;; `c-paren-nontype-kwds', `c-paren-type-kwds', `c-<>-type-kwds',
4263 ;; and `c-<>-arglist-kwds'.
4264 ;;
4265 ;; This function records identifier ranges on
4266 ;; `c-record-type-identifiers' and `c-record-ref-identifiers' if
4267 ;; `c-record-type-identifiers' is non-nil.
4268 ;;
4269 ;; Note that for `c-colon-type-list-kwds', which doesn't necessary
4270 ;; apply directly after the keyword, the type list is moved over
4271 ;; only when there is no unaccounted token before it (i.e. a token
4272 ;; that isn't moved over due to some other keyword list). The
4273 ;; identifier ranges in the list are still recorded if that should
4274 ;; be done, though.
4275 ;;
4276 ;; This function might do hidden buffer changes.
4279 ;; The call to `c-forward-<>-arglist' below is made after
4280 ;; `c-<>-sexp-kwds' keywords, so we're certain they actually
4281 ;; are angle bracket arglists and `c-restricted-<>-arglists'
4282 ;; should therefore be nil.
4294 ;; There's a type directly after a keyword in `c-type-list-kwds'.
4299 ;; There's a name directly after a keyword in `c-ref-list-kwds'.
4304 ;; There's an open paren after a keyword in `c-paren-any-kwds'.
4311 ;; Use `c-forward-type' on every identifier we can find
4312 ;; inside the paren, to record the types.
4337 ;; If we are at the colon already, we move over the type
4338 ;; list after it.
4344 ;; Not at the colon, so stop here. But the identifier
4345 ;; ranges in the type list later on should still be
4346 ;; recorded.
4349 ;; If a keyword matched both one of the types above and
4350 ;; this one, we match `c-colon-type-list-re' after the
4351 ;; clause matched above.
4358 ;; There's a type after the `c-colon-type-list-re' match
4359 ;; after a keyword in `c-colon-type-list-kwds'.
4363 t)))
4366 ;; The point is assumed to be at a "<". Try to treat it as the open
4367 ;; paren of an angle bracket arglist and move forward to the the
4368 ;; corresponding ">". If successful, the point is left after the
4369 ;; ">" and t is returned, otherwise the point isn't moved and nil is
4370 ;; returned. If ALL-TYPES is t then all encountered arguments in
4371 ;; the arglist that might be types are treated as found types.
4372 ;;
4373 ;; The variable `c-parse-and-markup-<>-arglists' controls how this
4374 ;; function handles text properties on the angle brackets and argument
4375 ;; separating commas.
4376 ;;
4377 ;; `c-restricted-<>-arglists' controls how lenient the template
4378 ;; arglist recognition should be.
4379 ;;
4380 ;; This function records identifier ranges on
4381 ;; `c-record-type-identifiers' and `c-record-ref-identifiers' if
4382 ;; `c-record-type-identifiers' is non-nil.
4383 ;;
4384 ;; This function might do hidden buffer changes.
4387 ;; If `c-record-type-identifiers' is set then activate
4388 ;; recording of any found types that constitute an argument in
4389 ;; the arglist.
4397 ;; `nconc' doesn't mind that the tail of
4398 ;; `c-record-found-types' is t.
4400 t)
4403 nil)))
4406 ;; Recursive part of `c-forward-<>-arglist'.
4407 ;;
4408 ;; This function might do hidden buffer changes.
4411 ;; Cover this so that any recorded found type ranges are
4412 ;; automatically lost if it turns out to not be an angle
4413 ;; bracket arglist. It's propagated through the return value
4414 ;; on successful completion.
4416 ;; List that collects the positions after the argument
4417 ;; separating ',' in the arglist.
4418 arg-start-pos)
4420 ;; If the '<' has paren open syntax then we've marked it as an angle
4421 ;; bracket arglist before, so skip to the end.
4429 t
4431 ;; Got unmatched paren angle brackets. We don't clear the paren
4432 ;; syntax properties and retry, on the basis that it's very
4433 ;; unlikely that paren angle brackets become operators by code
4434 ;; manipulation. It's far more likely that it doesn't match due
4435 ;; to narrowing or some temporary change.
4437 nil))
4447 ;; All encountered identifiers are types, so set the
4448 ;; promote flag and parse the type.
4455 ;; Check if this arglist argument is a sole type. If
4456 ;; it's known then it's recorded in
4457 ;; `c-record-type-identifiers'. If it only is found
4458 ;; then it's recorded in `c-record-found-types' which we
4459 ;; might roll back if it turns out that this isn't an
4460 ;; angle bracket arglist afterall.
4466 ;; A found type was recorded but it's not the
4467 ;; only thing in the arglist argument, so reset
4468 ;; `c-record-found-types'.
4470 orig-record-found-types))))))
4474 ;; Must check for '>' at the very start separately,
4475 ;; since the regexp below has to avoid ">>" without
4476 ;; using \\=.
4478 t)
4480 ;; Note: These regexps exploit the match order in \| so
4481 ;; that "<>" is matched by "<" rather than "[^>:-]>".
4484 ;; Stop on ',', '|', '&', '+' and '-' to catch
4485 ;; common binary operators that could be between
4486 ;; two comparison expressions "a<b" and "c>d".
4488 ;; Otherwise we still stop on ',' to find the
4489 ;; argument start positions.
4493 ;; If the arglist starter has lost its open paren
4494 ;; syntax but not the closer, we won't find the
4495 ;; closer above since we only search in the
4496 ;; balanced sexp. In that case we stop just short
4497 ;; of it so check if the following char is the closer.
4500 t)))
4504 ;; Either an operator starting with '>' or the end of
4505 ;; the angle bracket arglist.
4512 ;; The angle bracket arglist is finished.
4524 ;; Either an operator starting with '<' or a nested arglist.
4536 ;; There's always an identifier before an angle
4537 ;; bracket arglist, or a keyword in
4538 ;; `c-<>-type-kwds' or `c-<>-arglist-kwds'.
4555 )))
4557 ;; It was not an angle bracket arglist.
4560 ;; It was an angle bracket arglist.
4563 ;; Record the identifier before the template as a type
4564 ;; or reference depending on whether the arglist is last
4565 ;; in a qualified identifier.
4574 t)
4578 ;; Just another argument. Record the position. The
4579 ;; type check stuff that made us stop at it is at
4580 ;; the top of the loop.
4584 ;; Got a character that can't be in an angle bracket
4585 ;; arglist argument. Abort using `throw', since
4586 ;; it's useless to try to find a surrounding arglist
4587 ;; if we're nested.
4594 ;; The point is assumed to be directly after a ">". Try to treat it
4595 ;; as the close paren of an angle bracket arglist and move back to
4596 ;; the corresponding "<". If successful, the point is left at
4597 ;; the "<" and t is returned, otherwise the point isn't moved and
4598 ;; nil is returned. ALL-TYPES is passed on to
4599 ;; `c-forward-<>-arglist'.
4600 ;;
4601 ;; If the optional LIMIT is given, it bounds the backward search.
4602 ;; It's then assumed to be at a syntactically relevant position.
4603 ;;
4604 ;; This is a wrapper around `c-forward-<>-arglist'. See that
4605 ;; function for more details.
4614 t
4615 ;; See corresponding note in `c-forward-<>-arglist'.
4617 nil)
4624 t
4625 ;; Stopped at bob or a char that isn't allowed in an
4626 ;; arglist, so we've failed.
4628 nil)
4633 ;; If we moved then the "<" was part of some
4634 ;; multicharacter token.
4635 t
4641 ;; Matched the arglist. Break the while.
4643 nil)
4645 ;; We started from a non-paren ">" inside an
4646 ;; arglist.
4648 nil)
4650 ;; Matched a shorter arglist. Can be a nested
4651 ;; one so continue looking.
4653 t))
4654 t))))))
4659 ;; Move forward over a complete name if at the beginning of one,
4660 ;; stopping at the next following token. If the point is not at
4661 ;; something that are recognized as name then it stays put. A name
4662 ;; could be something as simple as "foo" in C or something as
4663 ;; complex as "X<Y<class A<int>::B, BIT_MAX >> b>, ::operator<> ::
4664 ;; Z<(a>b)> :: operator const X<&foo>::T Q::G<unsigned short
4665 ;; int>::*volatile const" in C++ (this function is actually little
4666 ;; more than a `looking-at' call in all modes except those that,
4667 ;; like C++, have `c-recognize-<>-arglists' set). Return nil if no
4668 ;; name is found, 'template if it's an identifier ending with an
4669 ;; angle bracket arglist, 'operator of it's an operator identifier,
4670 ;; or t if it's some other kind of name.
4671 ;;
4672 ;; This function records identifier ranges on
4673 ;; `c-record-type-identifiers' and `c-record-ref-identifiers' if
4674 ;; `c-record-type-identifiers' is non-nil.
4675 ;;
4676 ;; This function might do hidden buffer changes.
4679 ;; Turn off `c-promote-possible-types' here since we might
4680 ;; call `c-forward-<>-arglist' and we don't want it to promote
4681 ;; every suspect thing in the arglist to a type. We're
4682 ;; typically called from `c-forward-type' in this case, and
4683 ;; the caller only wants the top level type that it finds to
4684 ;; be promoted.
4685 c-promote-possible-types)
4691 ;; Check for keyword. We go to the last symbol in
4692 ;; `c-identifier-key' first.
4705 ;; "template" is only valid inside an
4706 ;; identifier if preceded by "::".
4711 t))
4713 ;; Handle a C++ operator or template identifier.
4717 ;; Got "... ::template".
4721 res subres))))
4724 ;; Got a cast operator.
4728 ;; Now we should match a sequence of either
4729 ;; '*', '&' or a name followed by ":: *",
4730 ;; where each can be followed by a sequence
4731 ;; of `c-opt-type-modifier-key'.
4734 t)
4744 t))))
4752 ;; Got some other operator.
4760 nil)
4762 ;; `id-start' is equal to `id-end' if we've jumped over
4763 ;; an identifier that doesn't end with a symbol token.
4764 ;; That can occur e.g. for Java import directives on the
4765 ;; form "foo.bar.*".
4772 res t)))
4782 ;; Got a concatenated identifier. This handles the
4783 ;; cases with tricky syntactic whitespace that aren't
4784 ;; covered in `c-identifier-key'.
4787 t)
4791 ;; Maybe an angle bracket arglist.
4794 c-record-found-types)
4800 c-last-identifier-range nil)
4805 ;; Continue if there's an identifier concatenation
4806 ;; operator after the template argument.
4812 t)
4817 nil)))
4818 )))))
4821 res))
4824 ;; Move forward over a type spec if at the beginning of one,
4825 ;; stopping at the next following token. Return t if it's a known
4826 ;; type that can't be a name or other expression, 'known if it's an
4827 ;; otherwise known type (according to `*-font-lock-extra-types'),
4828 ;; 'prefix if it's a known prefix of a type, 'found if it's a type
4829 ;; that matches one in `c-found-types', 'maybe if it's an identfier
4830 ;; that might be a type, or nil if it can't be a type (the point
4831 ;; isn't moved then). The point is assumed to be at the beginning
4832 ;; of a token.
4833 ;;
4834 ;; Note that this function doesn't skip past the brace definition
4835 ;; that might be considered part of the type, e.g.
4836 ;; "enum {a, b, c} foo".
4837 ;;
4838 ;; This function records identifier ranges on
4839 ;; `c-record-type-identifiers' and `c-record-ref-identifiers' if
4840 ;; `c-record-type-identifiers' is non-nil.
4841 ;;
4842 ;; This function might do hidden buffer changes.
4846 ;; Skip leading type modifiers. If any are found we know it's a
4847 ;; prefix of a type.
4856 ;; Looking at a keyword that prefixes a type identifier,
4857 ;; e.g. "class".
4864 ;; In many languages the name can be used without the
4865 ;; prefix, so we add it to `c-found-types'.
4868 c-last-identifier-range)
4871 ;; Invalid syntax.
4883 id-range c-last-identifier-range))))
4895 id-end)
4897 ;; Looking at a primitive or known type identifier. We've
4898 ;; checked for a name first so that we don't go here if the
4899 ;; known type match only is a prefix of another name.
4910 ;; There might be more keywords for the type.
4938 ;; A normal identifier.
4948 ;; It's an identifier that has been used as
4949 ;; a type somewhere else.
4950 'found
4951 ;; It's an identifier that might be a type.
4954 ;; A template is a type.
4958 ;; Otherwise it's an operator identifier, which is not a type.
4963 ;; Skip trailing type modifiers. If any are found we know it's
4964 ;; a type.
4971 ;; Step over any type suffix operator. Do not let the existence
4972 ;; of these alter the classification of the found type, since
4973 ;; these operators typically are allowed in normal expressions
4974 ;; too.
4981 ;; Look for a trailing operator that concatenates the type
4982 ;; with a following one, and if so step past that one through
4983 ;; a recursive call. Note that we don't record concatenated
4984 ;; types in `c-found-types' - it's the component types that
4985 ;; are recorded when appropriate.
4988 c-promote-possible-types))
4989 ;; If we can't promote then set `c-record-found-types' so that
4990 ;; we can merge in the types from the second part afterwards if
4991 ;; it turns out to be a known type there.
4994 subres)
5003 ;; If either operand certainly is a type then both are, but we
5004 ;; don't let the existence of the operator itself promote two
5005 ;; uncertain types to a certain one.
5024 ;; Merge in the ranges of any types found by the second
5025 ;; `c-forward-type'.
5027 ;; `nconc' doesn't mind that the tail of
5028 ;; `c-record-found-types' is t.
5030 c-record-type-identifiers))))
5038 ;;(message "c-forward-type %s -> %s: %s" start (point) res)
5040 res))
5042 \f
5043 ;; Handling of large scale constructs like statements and declarations.
5045 ;; Macro used inside `c-forward-decl-or-cast-1'. It ought to be a
5046 ;; defsubst or perhaps even a defun, but it contains lots of free
5047 ;; variables that refer to things inside `c-forward-decl-or-cast-1'.
5049 ;; `c-forward-decl-or-cast-1' can consume an arbitrary length list
5050 ;; of types when parsing a declaration, which means that it
5051 ;; sometimes consumes the identifier in the declaration as a type.
5052 ;; This is used to "backtrack" and make the last type be treated as
5053 ;; an identifier instead.
5056 ;; These identifiers are bound only in the inner let.
5058 identifier-start type-start
5059 got-parens nil
5060 got-identifier t
5061 got-suffix t
5062 got-suffix-after-parens id-start
5066 t
5067 backup-at-type))
5069 id-start backup-id-start)
5071 id-start start-pos))
5073 ;; When these flags already are set we've found specifiers that
5074 ;; unconditionally signal these attributes - backtracking doesn't
5075 ;; change that. So keep them set in that case.
5082 ;; This identifier is bound only in the inner let.
5086 ;; Move forward over a declaration or a cast if at the start of one.
5087 ;; The point is assumed to be at the start of some token. Nil is
5088 ;; returned if no declaration or cast is recognized, and the point
5089 ;; is clobbered in that case.
5090 ;;
5091 ;; If a declaration is parsed:
5092 ;;
5093 ;; The point is left at the first token after the first complete
5094 ;; declarator, if there is one. The return value is a cons where
5095 ;; the car is the position of the first token in the declarator.
5096 ;; Some examples:
5097 ;;
5098 ;; void foo (int a, char *b) stuff ...
5099 ;; car ^ ^ point
5100 ;; float (*a)[], b;
5101 ;; car ^ ^ point
5102 ;; unsigned int a = c_style_initializer, b;
5103 ;; car ^ ^ point
5104 ;; unsigned int a (cplusplus_style_initializer), b;
5105 ;; car ^ ^ point (might change)
5106 ;; class Foo : public Bar {}
5107 ;; car ^ ^ point
5108 ;; class PikeClass (int a, string b) stuff ...
5109 ;; car ^ ^ point
5110 ;; enum bool;
5111 ;; car ^ ^ point
5112 ;; enum bool flag;
5113 ;; car ^ ^ point
5114 ;; void cplusplus_function (int x) throw (Bad);
5115 ;; car ^ ^ point
5116 ;; Foo::Foo (int b) : Base (b) {}
5117 ;; car ^ ^ point
5118 ;;
5119 ;; The cdr of the return value is non-nil iff a
5120 ;; `c-typedef-decl-kwds' specifier is found in the declaration,
5121 ;; i.e. the declared identifier(s) are types.
5122 ;;
5123 ;; If a cast is parsed:
5124 ;;
5125 ;; The point is left at the first token after the closing paren of
5126 ;; the cast. The return value is `cast'. Note that the start
5127 ;; position must be at the first token inside the cast parenthesis
5128 ;; to recognize it.
5129 ;;
5130 ;; PRECEDING-TOKEN-END is the first position after the preceding
5131 ;; token, i.e. on the other side of the syntactic ws from the point.
5132 ;; Use a value less than or equal to (point-min) if the point is at
5133 ;; the first token in (the visible part of) the buffer.
5134 ;;
5135 ;; CONTEXT is a symbol that describes the context at the point:
5136 ;; 'decl In a comma-separatded declaration context (typically
5137 ;; inside a function declaration arglist).
5138 ;; '<> In an angle bracket arglist.
5139 ;; 'arglist Some other type of arglist.
5140 ;; nil Some other context or unknown context.
5141 ;;
5142 ;; LAST-CAST-END is the first token after the closing paren of a
5143 ;; preceding cast, or nil if none is known. If
5144 ;; `c-forward-decl-or-cast-1' is used in succession, it should be
5145 ;; the position after the closest preceding call where a cast was
5146 ;; matched. In that case it's used to discover chains of casts like
5147 ;; "(a) (b) c".
5148 ;;
5149 ;; This function records identifier ranges on
5150 ;; `c-record-type-identifiers' and `c-record-ref-identifiers' if
5151 ;; `c-record-type-identifiers' is non-nil.
5152 ;;
5153 ;; This function might do hidden buffer changes.
5156 ;; first type, i.e. after any leading specifiers. It might
5157 ;; also point at the beginning of the preceding syntactic
5158 ;; whitespace.
5160 ;; Set to the result of `c-forward-type'.
5161 at-type
5162 ;; The position of the first token in what we currently
5163 ;; believe is the type in the declaration or cast, after any
5164 ;; specifiers and their associated clauses.
5165 type-start
5166 ;; The position of the first token in what we currently
5167 ;; believe is the declarator for the first identifier. Set
5168 ;; when the type is found, and moved forward over any
5169 ;; `c-decl-hangon-kwds' and their associated clauses that
5170 ;; occurs after the type.
5171 id-start
5172 ;; These store `at-type', `type-start' and `id-start' of the
5173 ;; identifier before the one in those variables. The previous
5174 ;; identifier might turn out to be the real type in a
5175 ;; declaration if the last one has to be the declarator in it.
5176 ;; If `backup-at-type' is nil then the other variables have
5177 ;; undefined values.
5178 backup-at-type backup-type-start backup-id-start
5179 ;; Set if we've found a specifier that makes the defined
5180 ;; identifier(s) types.
5181 at-type-decl
5182 ;; Set if we've found a specifier that can start a declaration
5183 ;; where there's no type.
5184 maybe-typeless
5185 ;; If a specifier is found that also can be a type prefix,
5186 ;; these flags are set instead of those above. If we need to
5187 ;; back up an identifier, they are copied to the real flag
5188 ;; variables. Thus they only take effect if we fail to
5189 ;; interpret it as a type.
5190 backup-at-type-decl backup-maybe-typeless
5191 ;; Whether we've found a declaration or a cast. We might know
5192 ;; this before we've found the type in it. It's 'ids if we've
5193 ;; found two consecutive identifiers (usually a sure sign, but
5194 ;; we should allow that in labels too), and t if we've found a
5195 ;; specifier keyword (a 100% sure sign).
5196 at-decl-or-cast
5197 ;; Set when we need to back up to parse this as a declaration
5198 ;; but not as a cast.
5199 backup-if-not-cast
5200 ;; For casts, the return position.
5201 cast-end
5202 ;; Save `c-record-type-identifiers' and
5203 ;; `c-record-ref-identifiers' since ranges are recorded
5204 ;; speculatively and should be thrown away if it turns out
5205 ;; that it isn't a declaration or cast.
5209 ;; Check for a type. Unknown symbols are treated as possible
5210 ;; types, but they could also be specifiers disguised through
5211 ;; macros like __INLINE__, so we recognize both types and known
5212 ;; specifiers after them too.
5216 ;; Look for a specifier keyword clause.
5224 ;; Found a known or possible type or a prefix of a known type.
5227 ;; Got two identifiers with nothing but whitespace
5228 ;; between them. That can only happen in declarations.
5232 ;; If the previous identifier is a found type we
5233 ;; record it as a real one; it might be some sort of
5234 ;; alias for a prefix like "unsigned".
5241 backup-type-start type-start
5242 backup-id-start id-start
5243 at-type found-type
5244 type-start start
5246 ;; The previous ambiguous specifier/type turned out
5247 ;; to be a type since we've parsed another one after
5248 ;; it, so clear these backup flags.
5249 backup-at-type-decl nil
5250 backup-maybe-typeless nil))
5254 ;; Handle known specifier keywords and
5255 ;; `c-decl-hangon-kwds' which can occur after known
5256 ;; types.
5259 ;; It's a hang-on keyword that can occur anywhere.
5263 ;; Move the identifier start position if
5264 ;; we've passed a type.
5266 ;; Otherwise treat this as a specifier and
5267 ;; move the fallback position.
5271 ;; It's an ordinary specifier so we know that
5272 ;; anything before this can't be the type.
5274 start-pos kwd-clause-end)
5277 ;; It's ambiguous whether this keyword is a
5278 ;; specifier or a type prefix, so set the backup
5279 ;; flags. (It's assumed that `c-forward-type'
5280 ;; moved further than `c-forward-keyword-clause'.)
5292 ;; Haven't matched a type so it's an umambiguous
5293 ;; specifier keyword and we know we're in a
5294 ;; declaration.
5299 ;; If the type isn't known we continue so that we'll jump
5300 ;; over all specifiers and type identifiers. The reason
5301 ;; to do this for a known type prefix is to make things
5302 ;; like "unsigned INT16" work.
5307 ;; If a known type was found, we still need to skip over any
5308 ;; hangon keyword clauses after it. Otherwise it has already
5309 ;; been done in the loop above.
5315 ;; A prefix type is itself a primitive type when it's not
5316 ;; followed by another type.
5320 ;; Got no type but set things up to continue anyway to handle
5321 ;; the various cases when a declaration doesn't start with a
5322 ;; type.
5327 ;; If it's C++ then check if the last "type" ends on the form
5328 ;; "foo::foo" or "foo::~foo", i.e. if it's the name of a
5329 ;; (con|de)structor.
5340 ;; Cheating in the handling of syntactic ws below.
5347 name))
5348 ;; It is a (con|de)structor name. In that case the
5349 ;; declaration is typeless so zap out any preceding
5350 ;; identifier(s) that we might have taken as types.
5353 backup-at-type nil
5354 id-start type-start))))))
5356 ;; Check for and step over a type decl expression after the thing
5357 ;; that is or might be a type. This can't be skipped since we
5358 ;; need the correct end position of the declarator for
5359 ;; `max-type-decl-end-*'.
5361 ;; True if there's a non-open-paren match of
5362 ;; `c-type-decl-prefix-key'.
5363 got-prefix
5364 ;; True if the declarator is surrounded by a parenthesis pair.
5365 got-parens
5366 ;; True if there is an identifier in the declarator.
5367 got-identifier
5368 ;; True if there's a non-close-paren match of
5369 ;; `c-type-decl-suffix-key'.
5370 got-suffix
5371 ;; True if there's a prefix match outside the outermost
5372 ;; paren pair that surrounds the declarator.
5373 got-prefix-before-parens
5374 ;; True if there's a suffix match outside the outermost
5375 ;; paren pair that surrounds the declarator. The value is
5376 ;; the position of the first suffix match.
5377 got-suffix-after-parens
5378 ;; True if we've parsed the type decl to a token that is
5379 ;; known to end declarations in this context.
5380 at-decl-end
5381 ;; The earlier values of `at-type' and `type-start' if we've
5382 ;; shifted the type backwards.
5383 identifier-type identifier-start
5384 ;; If `c-parse-and-markup-<>-arglists' is set we need to
5385 ;; turn it off during the name skipping below to avoid
5386 ;; getting `c-type' properties that might be bogus. That
5387 ;; can happen since we don't know if
5388 ;; `c-restricted-<>-arglists' will be correct inside the
5389 ;; arglist paren that gets entered.
5394 ;; Skip over type decl prefix operators. (Note similar code in
5395 ;; `c-font-lock-declarators'.)
5399 ;; If the second submatch matches in C++ then
5400 ;; we're looking at an identifier that's a
5401 ;; prefix only if it specifies a member pointer.
5404 ;; We only check for a trailing "::" and
5405 ;; let the "*" that should follow be
5406 ;; matched in the next round.
5408 ;; It turned out to be the real identifier,
5409 ;; so stop.
5410 nil))
5411 t))
5425 ;; Skip over an identifier.
5430 ;; Skip over type decl suffix operators.
5437 t)
5441 t)
5447 ;; No suffix matched. We might have matched the
5448 ;; identifier as a type and the open paren of a
5449 ;; function arglist as a type decl prefix. In that
5450 ;; case we should "backtrack": Reinterpret the last
5451 ;; type as the identifier, move out of the arglist and
5452 ;; continue searching for suffix operators.
5453 ;;
5454 ;; Do this even if there's no preceding type, to cope
5455 ;; with old style function declarations in K&R C,
5456 ;; (con|de)structors in C++ and `c-typeless-decl-kwds'
5457 ;; style declarations. That isn't applicable in an
5458 ;; arglist context, though.
5463 maybe-typeless
5464 backup-maybe-typeless
5471 t))
5478 at-type)
5479 ;; Have found no identifier but `c-typeless-decl-kwds' has
5480 ;; matched so we know we're inside a declaration. The
5481 ;; preceding type must be the identifier instead.
5485 at-decl-or-cast
5489 ;; Encountered something inside parens that isn't matched by
5490 ;; the `c-type-decl-*' regexps, so it's not a type decl
5491 ;; expression. Try to skip out to the same paren depth to
5492 ;; not confuse the cast check below.
5494 ;; If we've found a specifier keyword then it's a
5495 ;; declaration regardless.
5503 ;; Now we've collected info about various characteristics of
5504 ;; the construct we're looking at. Below follows a decision
5505 ;; tree based on that. It's ordered to check more certain
5506 ;; signs before less certain ones.
5513 ;; Got another identifier directly after the type, so it's a
5514 ;; declaration.
5521 maybe-typeless
5522 backup-maybe-typeless))
5523 ;; Got a declaration of the form "foo bar (gnu);" where we've
5524 ;; recognized "bar" as the type and "gnu" as the declarator.
5525 ;; In this case it's however more likely that "bar" is the
5526 ;; declarator and "gnu" a function argument or initializer (if
5527 ;; `c-recognize-paren-inits' is set), since the parens around
5528 ;; "gnu" would be superfluous if it's a declarator. Shift the
5529 ;; type one step backward.
5532 ;; Found no identifier.
5538 ;; Got a plain list of identifiers. If a colon follows it's
5539 ;; a valid label. Otherwise the last one probably is the
5540 ;; declared identifier and we should back up to the previous
5541 ;; type, providing it isn't a cast.
5543 ;; If we've found a specifier keyword then it's a
5544 ;; declaration regardless.
5552 ;; Got a plain list of identifiers followed by some suffix.
5553 ;; If this isn't a cast then the last identifier probably is
5554 ;; the declared one and we should back up to the previous
5555 ;; type.
5560 ;; If the type is known we know that there can't be any
5561 ;; identifier somewhere else, and it's only in declarations in
5562 ;; e.g. function prototypes and in casts that the identifier may
5563 ;; be left out.
5567 ;; Only got a single identifier (parsed as a type so far).
5569 ;; Check that the identifier isn't at the start of an
5570 ;; expression.
5571 at-decl-end
5574 ;; Inside an arglist that contains declarations. If K&R
5575 ;; style declarations and parenthesis style initializers
5576 ;; aren't allowed then the single identifier must be a
5577 ;; type, else we require that it's known or found
5578 ;; (primitive types are handled above).
5583 ;; Inside a template arglist. Accept known and found
5584 ;; types; other identifiers could just as well be
5585 ;; constants in C++.
5588 ;; Can't be a valid declaration or cast, but if we've found a
5589 ;; specifier it can't be anything else either, so treat it as
5590 ;; an invalid/unfinished declaration or cast.
5598 maybe-typeless
5599 backup-maybe-typeless
5603 c-after-suffixed-type-maybe-decl-key))))))
5604 ;; Got an empty paren pair and a preceding type that probably
5605 ;; really is the identifier. Shift the type backwards to make
5606 ;; the last one the identifier. This is analogous to the
5607 ;; "backtracking" done inside the `c-type-decl-suffix-key' loop
5608 ;; above.
5609 ;;
5610 ;; Exception: In addition to the conditions in that
5611 ;; "backtracking" code, do not shift backward if we're not
5612 ;; looking at either `c-after-suffixed-type-decl-key' or "[;,]".
5613 ;; Since there's no preceding type, the shift would mean that
5614 ;; the declaration is typeless. But if the regexp doesn't match
5615 ;; then we will simply fall through in the tests below and not
5616 ;; recognize it at all, so it's better to try it as an abstract
5617 ;; declarator instead.
5620 ;; Still no identifier.
5623 ;; Require `got-prefix' together with either `got-parens' or
5624 ;; `got-suffix' to recognize it as an abstract declarator:
5625 ;; `got-parens' only is probably an empty function call.
5626 ;; `got-suffix' only can build an ordinary expression together
5627 ;; with the preceding identifier which we've taken as a type.
5628 ;; We could actually accept on `got-prefix' only, but that can
5629 ;; easily occur temporarily while writing an expression so we
5630 ;; avoid that case anyway. We could do a better job if we knew
5631 ;; the point when the fontification was invoked.
5637 got-suffix-after-parens
5639 ;; Got a type, no declarator but a paren suffix. I.e. it's a
5640 ;; normal function call afterall (or perhaps a C++ style object
5641 ;; instantiation expression).
5645 ;; By now we've located the type in the declaration that we know
5646 ;; we're in.
5656 ;; Shift the type backward in the case that there's a
5657 ;; single identifier inside parens. That can only
5658 ;; occur in K&R style function declarations so it's
5659 ;; more likely that it really is a function call.
5660 ;; Therefore we only do this after
5661 ;; `c-after-suffixed-type-decl-key' has matched.
5663 got-suffix-after-parens))
5664 ;; A declaration according to `c-after-suffixed-type-decl-key'.
5669 ;; It's a declaration if a known type precedes it and it can't be a
5670 ;; function call.
5673 ;; If we get here we can't tell if this is a type decl or a normal
5674 ;; expression by looking at it alone. (That's under the assumption
5675 ;; that normal expressions always can look like type decl expressions,
5676 ;; which isn't really true but the cases where it doesn't hold are so
5677 ;; uncommon (e.g. some placements of "const" in C++) it's not worth
5678 ;; the effort to look for them.)
5681 ;; If this is a declaration it should end here or its initializer(*)
5682 ;; should start here, so check for allowed separation tokens. Note
5683 ;; that this rule doesn't work e.g. with a K&R arglist after a
5684 ;; function header.
5685 ;;
5686 ;; *) Don't check for C++ style initializers using parens
5687 ;; since those already have been matched as suffixes.
5688 ;;
5689 ;; If `at-decl-or-cast' is then we've found some other sign that
5690 ;; it's a declaration or cast, so then it's probably an
5691 ;; invalid/unfinished one.
5694 ;; Below are tests that only should be applied when we're certain to
5695 ;; not have parsed halfway through an expression.
5698 ;; The expression starts with a known type so treat it as a
5699 ;; declaration.
5703 ;; In C++ we check if the identifier is a known type, since
5704 ;; (con|de)structors use the class name as identifier.
5705 ;; We've always shifted over the identifier as a type and
5706 ;; then backed up again in this case.
5707 identifier-type
5710 ;; `at-type' probably won't be 'found for
5711 ;; destructors since the "~" is then part of the
5712 ;; type name being checked against the list of
5713 ;; known types, so do a check without that
5714 ;; operator.
5719 c-identifier-syntax-table
5723 ;; We have already parsed the type earlier,
5724 ;; so it'd be possible to cache the end
5725 ;; position instead of redoing it here, but
5726 ;; then we'd need to keep track of another
5727 ;; position everywhere.
5736 at-type
5740 ;; Got something like "foo * bar;". Since we're not inside an
5741 ;; arglist it would be a meaningless expression because the
5742 ;; result isn't used. We therefore choose to recognize it as
5743 ;; a declaration. Do not allow a suffix since it could then
5744 ;; be a function call.
5751 ;; Got something like "a (*b) (c);" or "a (b) = c;". It could
5752 ;; be an odd expression or it could be a declaration. Treat
5753 ;; it as a declaration if "a" has been used as a type
5754 ;; somewhere else (if it's a known type we won't get here).
5762 ;; Got a type followed by an abstract declarator. If `got-prefix'
5763 ;; is set it's something like "a *" without anything after it. If
5764 ;; `got-parens' or `got-suffix' is set it's "a()", "a[]", "a()[]",
5765 ;; or similar, which we accept only if the context rules out
5766 ;; expressions.
5769 ;; If we had a complete symbol table here (which rules out
5770 ;; `c-found-types') we should return t due to the disambiguation rule
5771 ;; (in at least C++) that anything that can be parsed as a declaration
5772 ;; is a declaration. Now we're being more defensive and prefer to
5773 ;; highlight things like "foo (bar);" as a declaration only if we're
5774 ;; inside an arglist that contains declarations.
5777 ;; The point is now after the type decl expression.
5780 ;; Check for a cast.
5783 c-cast-parens
5785 ;; Should be the first type/identifier in a cast paren.
5789 ;; The closing paren should follow.
5794 ;; There should be a primary expression after it.
5803 ;; Check if the expression begins with a prefix keyword.
5806 ;; Expression begins with an ambiguous operator. Treat
5807 ;; it as a cast if it's a type decl or if we've
5808 ;; recognized the type somewhere else.
5811 ;; Unless it's a keyword, it's the beginning of a primary
5812 ;; expression.
5814 ;; If `c-primary-expr-regexp' matched a nonsymbol token, check
5815 ;; that it matched a whole one so that we don't e.g. confuse
5816 ;; the operator '-' with '->'. It's ok if it matches further,
5817 ;; though, since it e.g. can match the float '.5' while the
5818 ;; operator regexp only matches '.'.
5822 ;; There should either be a cast before it or something that isn't an
5823 ;; identifier or close paren.
5831 ;; It's a symbol. Accept it only if it's one of the
5832 ;; keywords that can precede an expression (without
5833 ;; surrounding parens).
5836 ;; Check that it isn't a close paren (block close is ok,
5837 ;; though).
5839 ;; Check that it isn't a nonsymbol identifier.
5842 ;; Handle the cast.
5852 ;; We're at a declaration. Highlight the type and the following
5853 ;; declarators.
5859 ;; Make sure to propagate the `c-decl-arg-start' property to
5860 ;; the next argument if it's set in this one, to cope with
5861 ;; interactive refontification.
5873 ;; False alarm. Restore the recorded ranges.
5875 c-record-ref-identifiers save-rec-ref-ids)
5876 nil))))
5879 ;; Assuming that point is at the beginning of a token, check if it starts a
5880 ;; label and if so move over it and return non-nil (t in default situations,
5881 ;; specific symbols (see below) for interesting situations), otherwise don't
5882 ;; move and return nil. "Label" here means "most things with a colon".
5883 ;;
5884 ;; More precisely, a "label" is regarded as one of:
5885 ;; (i) a goto target like "foo:" - returns the symbol `goto-target';
5886 ;; (ii) A case label - either the entire construct "case FOO:", or just the
5887 ;; bare "case", should the colon be missing. We return t;
5888 ;; (iii) a keyword which needs a colon, like "default:" or "private:"; We
5889 ;; return t;
5890 ;; (iv) One of QT's "extended" C++ variants of
5891 ;; "private:"/"protected:"/"public:"/"more:" looking like "public slots:".
5892 ;; Returns the symbol `qt-2kwds-colon'.
5893 ;; (v) QT's construct "signals:". Returns the symbol `qt-1kwd-colon'.
5894 ;; (v) One of the keywords matched by `c-opt-extra-label-key' (without any
5895 ;; colon). Currently (2006-03), this applies only to Objective C's
5896 ;; keywords "@private", "@protected", and "@public". Returns t.
5897 ;;
5898 ;; One of the things which will NOT be recognised as a label is a bit-field
5899 ;; element of a struct, something like "int foo:5".
5900 ;;
5901 ;; The end of the label is taken to be just after the colon, or the end of
5902 ;; the first submatch in `c-opt-extra-label-key'. The point is directly
5903 ;; after the end on return. The terminating char gets marked with
5904 ;; `c-decl-end' to improve recognition of the following declaration or
5905 ;; statement.
5906 ;;
5907 ;; If ASSUME-MARKUP is non-nil, it's assumed that the preceding
5908 ;; label, if any, has already been marked up like that.
5909 ;;
5910 ;; If PRECEDING-TOKEN-END is given, it should be the first position
5911 ;; after the preceding token, i.e. on the other side of the
5912 ;; syntactic ws from the point. Use a value less than or equal to
5913 ;; (point-min) if the point is at the first token in (the visible
5914 ;; part of) the buffer.
5915 ;;
5916 ;; The optional LIMIT limits the forward scan for the colon.
5917 ;;
5918 ;; This function records the ranges of the label symbols on
5919 ;; `c-record-ref-identifiers' if `c-record-type-identifiers' (!) is
5920 ;; non-nil.
5921 ;;
5922 ;; This function might do hidden buffer changes.
5925 label-end
5926 qt-symbol-idx
5927 macro-start ; if we're in one.
5928 label-type)
5930 ;; "case" or "default" (Doesn't apply to AWK).
5933 ;; Record only the keyword itself for fontification, since in
5934 ;; case labels the following is a constant expression and not
5935 ;; a label.
5939 ;; Find the label end.
5943 ;; Stop on chars that aren't allowed in expressions,
5944 ;; and on operator chars that would be meaningless
5945 ;; there. FIXME: This doesn't cope with ?: operators.
5953 t)
5955 ;; It's an unfinished label. We consider the keyword enough
5956 ;; to recognize it as a label, so that it gets fontified.
5957 ;; Leave the point at the end of it, but don't put any
5958 ;; `c-decl-end' marker.
5960 t))))
5962 ;; @private, @protected, @public, in Objective C, or similar.
5965 ;; For a `c-opt-extra-label-key' match, we record the whole
5966 ;; thing for fontification. That's to get the leading '@' in
5967 ;; Objective-C protection labels fontified.
5974 ;; All other cases of labels.
5977 ;; A colon label must have something before the colon.
5980 ;; Check that we're not after a token that can't precede a label.
5982 ;; Trivially succeeds when there's no preceding token.
5990 ;; Check if we're after a label, if we're after a closing
5991 ;; paren that belong to statement, and with
5992 ;; `c-label-prefix-re'. It's done in different order
5993 ;; depending on `assume-markup' since the checks have
5994 ;; different expensiveness.
6021 ;; Might be after another label, so check it recursively.
6025 ;; Essentially the same as the
6026 ;; `c-syntactic-re-search-forward' regexp below.
6032 ;; Note: the following should work instead of the
6033 ;; narrow-to-region above. Investigate why not,
6034 ;; sometime. ACM, 2006-03-31.
6035 ;; (c-syntactic-skip-backward "^-]:?;}=*/%&|,<>!@+"
6036 ;; macro-start t)
6038 ;; If the caller turned on recording for us,
6039 ;; it shouldn't apply when we check the
6040 ;; preceding label.
6041 c-record-type-identifiers)
6042 ;; A label can't start at a cpp directive. Check for
6043 ;; this, since c-forward-syntactic-ws would foul up on it.
6048 ;; Point is still at the beginning of the possible label construct.
6049 ;;
6050 ;; Check that the next nonsymbol token is ":", or that we're in one
6051 ;; of QT's "slots" declarations. Allow '(' for the sake of macro
6052 ;; arguments. FIXME: Should build this regexp from the language
6053 ;; constants.
6055 ;; public: protected: private:
6065 ;; QT double keyword like "protected slots:" or goto target.
6083 'qt-1kwd-colon
6095 ;; Check that `c-nonlabel-token-key' doesn't match anywhere.
6105 t)
6108 ;; Record the identifiers in the label for fontification, unless
6109 ;; it begins with `c-label-kwds' in which case the following
6110 ;; identifiers are part of a (constant) expression that
6111 ;; shouldn't be fontified.
6121 )))
6124 ;; Not a label.
6126 label-type))
6129 ;; Assuming the point is at the beginning of a token, try to move
6130 ;; forward to the end of the Objective-C directive that starts
6131 ;; there. Return t if a directive was fully recognized, otherwise
6132 ;; the point is moved as far as one could be successfully parsed and
6133 ;; nil is returned.
6134 ;;
6135 ;; This function records identifier ranges on
6136 ;; `c-record-type-identifiers' and `c-record-ref-identifiers' if
6137 ;; `c-record-type-identifiers' is non-nil.
6138 ;;
6139 ;; This function might do hidden buffer changes.
6142 start-char
6144 ;; Turn off recognition of angle bracket arglists while parsing
6145 ;; types here since the protocol reference list might then be
6146 ;; considered part of the preceding name or superclass-name.
6157 t)
6166 ;; Handle the name of the class itself.
6168 ; (c-forward-token-2) ; 2006/1/13 This doesn't move if the token's
6169 ; at EOB.
6175 ;; Look for ": superclass-name" or "( category-name )".
6186 ;; Look for a protocol reference list.
6192 t))))
6198 t)
6201 nil)))
6204 ;; Go to the first non-whitespace after the colon that starts a
6205 ;; multiple inheritance introduction. Optional LIM is the farthest
6206 ;; back we should search.
6207 ;;
6208 ;; This function might do hidden buffer changes.
6216 ;; Return nil if we aren't in a method definition, otherwise the
6217 ;; position of the initial [+-].
6218 ;;
6219 ;; This function might do hidden buffer changes.
6225 ))
6227 ;; Contributed by Kevin Ryde <user42@zip.com.au>.
6229 ;; Return non-nil if point is within a gcc \"asm\" block.
6230 ;;
6231 ;; This should be called with point inside an argument list.
6232 ;;
6233 ;; Only one level of enclosing parentheses is considered, so for
6234 ;; instance `nil' is returned when in a function call within an asm
6235 ;; operand.
6236 ;;
6237 ;; This function might do hidden buffer changes.
6247 "Return a determination as to whether point is at the `top-level'.
6248 Being at the top-level means that point is either outside any
6249 enclosing block (such function definition), or only inside a class,
6250 namespace or other block that contains another declaration level.
6252 If point is not at the top-level (e.g. it is inside a method
6253 definition), then nil is returned. Otherwise, if point is at a
6254 top-level not enclosed within a class definition, t is returned.
6255 Otherwise, a 2-vector is returned where the zeroth element is the
6256 buffer position of the start of the class declaration, and the first
6257 element is the buffer position of the enclosing class's opening
6258 brace.
6260 Note that this function might do hidden buffer changes. See the
6261 comment at the start of cc-engine.el for more info."
6267 ;; Return non-nil if the point is in the region after the argument
6268 ;; list of a function and its opening brace (or semicolon in case it
6269 ;; got no body). If there are K&R style argument declarations in
6270 ;; that region, the point has to be inside the first one for this
6271 ;; function to recognize it.
6272 ;;
6273 ;; If successful, the point is moved to the first token after the
6274 ;; function header (see `c-forward-decl-or-cast-1' for details) and
6275 ;; the position of the opening paren of the function arglist is
6276 ;; returned.
6277 ;;
6278 ;; The point is clobbered if not successful.
6279 ;;
6280 ;; LIM is used as bound for backward buffer searches.
6281 ;;
6282 ;; This function might do hidden buffer changes.
6295 ;; There should not be a '=' or ',' between beg and the
6296 ;; start of the declaration since that means we were in the
6297 ;; "expression part" of the declaration.
6302 ;; Check that there's an arglist paren in the
6303 ;; declaration.
6306 ;; The declarator is a paren expression, so skip past it
6307 ;; so that we don't get stuck on that instead of the
6308 ;; function arglist.
6312 ;; Don't trip up on "operator ()".
6319 ;; Return the position of the first argument declaration if point is
6320 ;; inside a K&R style argument declaration list, nil otherwise.
6321 ;; `c-recognize-knr-p' is not checked. If LIM is non-nil, it's a
6322 ;; position that bounds the backward search for the argument list.
6323 ;;
6324 ;; Point must be within a possible K&R region, e.g. just before a top-level
6325 ;; "{". It must be outside of parens and brackets. The test can return
6326 ;; false positives otherwise.
6327 ;;
6328 ;; This function might do hidden buffer changes.
6332 ;; If we're in a macro, our search range is restricted to it. Narrow to
6333 ;; the searchable range.
6336 before-lparen after-rparen)
6339 ;; Search backwards for the defun's argument list. We give up if we
6340 ;; encounter a "}" (end of a previous defun) or BOB.
6341 ;;
6342 ;; The criterion for a paren structure being the arg list is:
6343 ;; o - there is non-WS stuff after it but before any "{"; AND
6344 ;; o - the token after it isn't a ";" AND
6345 ;; o - it is preceded by either an identifier (the function name) or
6346 ;; a macro expansion like "DEFUN (...)"; AND
6347 ;; o - its content is a non-empty comma-separated list of identifiers
6348 ;; (an empty arg list won't have a knr region).
6349 ;;
6350 ;; The following snippet illustrates these rules:
6351 ;; int foo (bar, baz, yuk)
6352 ;; int bar [] ;
6353 ;; int (*baz) (my_type) ;
6354 ;; int (*) (void) (*yuk) (void) ;
6355 ;; {
6368 ;; We're inside a paren. Could it be our argument list....?
6374 ;; FIXME!!! What about macros between the parens? 2007/01/20
6377 ;; It can't be the arg list if next token is ; or {
6382 ;; Is the thing preceding the list an identifier (the
6383 ;; function name), or a macro expansion?
6393 ;; Have we got a non-empty list of comma-separated
6394 ;; identifiers?
6408 ;; ...Yes. We've identified the function's argument list.
6414 ;; ...No. The current parens aren't the function's arg list.
6421 ;; skip forward over conditional at point, including any predicate
6422 ;; statements in parentheses. No error checking is performed.
6423 ;;
6424 ;; This function might do hidden buffer changes.
6426 ;; else if()
6431 ;; do, else, try, finally
6436 ;; for, if, while, switch, catch, synchronized, foreach
6440 ;; If looking at the token after a conditional then return the
6441 ;; position of its start, otherwise return nil.
6442 ;;
6443 ;; This function might do hidden buffer changes.
6453 ;; If the point is after an operator identifier that isn't handled
6454 ;; like an ordinary symbol (i.e. like "operator =" in C++) then the
6455 ;; position of the start of that identifier is returned. nil is
6456 ;; returned otherwise. The point may be anywhere in the syntactic
6457 ;; whitespace after the last token of the operator identifier.
6458 ;;
6459 ;; This function might do hidden buffer changes.
6471 ;; Assuming point is at a brace that opens a statement block of some
6472 ;; kind, move to the proper anchor point for that block. It might
6473 ;; need to be adjusted further by c-add-stmt-syntax, but the
6474 ;; position at return is suitable as start position for that
6475 ;; function.
6476 ;;
6477 ;; This function might do hidden buffer changes.
6484 ;; Assuming point is at a brace that opens the block of a top level
6485 ;; declaration of some kind, move to the proper anchor point for
6486 ;; that block.
6487 ;;
6488 ;; This function might do hidden buffer changes.
6493 ;; Search forward for the end of the "header" of the current
6494 ;; declaration. That's the position where the definition body
6495 ;; starts, or the first variable initializer, or the ending
6496 ;; semicolon. I.e. search forward for the closest following
6497 ;; (syntactically relevant) '{', '=' or ';' token. Point is left
6498 ;; _after_ the first found token, or at point-max if none is found.
6499 ;;
6500 ;; This function might do hidden buffer changes.
6505 ;; In C++ we need to take special care to handle operator
6506 ;; tokens and those pesky template brackets.
6511 ;; Handle operator identifiers, i.e. ignore any
6512 ;; operator token preceded by "operator".
6519 t
6521 nil)))))
6530 ;; Go to the beginning of the current declaration, or the beginning
6531 ;; of the previous one if already at the start of it. Point won't
6532 ;; be moved out of any surrounding paren. Return a cons cell of the
6533 ;; form (MOVE . KNR-POS). MOVE is like the return value from
6534 ;; `c-beginning-of-statement-1'. If point skipped over some K&R
6535 ;; style argument declarations (and they are to be recognized) then
6536 ;; KNR-POS is set to the start of the first such argument
6537 ;; declaration, otherwise KNR-POS is nil. If LIM is non-nil, it's a
6538 ;; position that bounds the backward search.
6539 ;;
6540 ;; NB: Cases where the declaration continues after the block, as in
6541 ;; "struct foo { ... } bar;", are currently recognized as two
6542 ;; declarations, e.g. "struct foo { ... }" and "bar;" in this case.
6543 ;;
6544 ;; This function might do hidden buffer changes.
6550 ;; `c-beginning-of-statement-1' stops at a block start, but we
6551 ;; want to continue if the block doesn't begin a top level
6552 ;; construct, i.e. if it isn't preceded by ';', '}', ':', bob,
6553 ;; or an open paren.
6555 ;; Go back one "statement" each time round the loop until we're just
6556 ;; after a ;, }, or :, or at BOB or the start of a macro or start of
6557 ;; an ObjC method. This will move over a multiple declaration whose
6558 ;; components are comma separated.
6560 ;; Must check with c-opt-method-key in ObjC mode.
6570 ;; Check that we don't move from the first thing in a
6571 ;; macro to its header.
6577 move tentative-move))
6582 ;; Handle K&R argdecls. Back up after the "statement" jumped
6583 ;; over by `c-beginning-of-statement-1', unless it was the
6584 ;; function body, in which case we're sitting on the opening
6585 ;; brace now. Then test if we're in a K&R argdecl region and
6586 ;; that we started at the other side of the first argdecl in
6587 ;; it.
6597 'previous
6599 knr-argdecl-start))
6602 ;; `c-beginning-of-statement-1' counts each brace block as a separate
6603 ;; statement, so the result will be 'previous if we've moved over any.
6604 ;; So change our result back to 'same if necessary.
6605 ;;
6606 ;; If they were brace list initializers we might not have moved over a
6607 ;; declaration boundary though, so change it to 'same if we've moved
6608 ;; past a '=' before '{', but not ';'. (This ought to be integrated
6609 ;; into `c-beginning-of-statement-1', so we avoid this extra pass which
6610 ;; potentially can search over a large amount of text.). Take special
6611 ;; pains not to get mislead by C++'s "operator=", and the like.
6614 c++-template-syntax-table
6620 ; no more, or get to one which isn't an "operator ="
6623 c-overloadable-operators-regexp
6624 c-opt-op-identifier-prefix
6639 ;; Assuming point is at the start of a declaration (as detected by
6640 ;; e.g. `c-beginning-of-decl-1'), go to the end of it. Unlike
6641 ;; `c-beginning-of-decl-1', this function handles the case when a
6642 ;; block is followed by identifiers in e.g. struct declarations in C
6643 ;; or C++. If a proper end was found then t is returned, otherwise
6644 ;; point is moved as far as possible within the current sexp and nil
6645 ;; is returned. This function doesn't handle macros; use
6646 ;; `c-end-of-macro' instead in those cases.
6647 ;;
6648 ;; This function might do hidden buffer changes.
6651 c++-template-syntax-table
6659 ;; Stopped at the ';' in a K&R argdecl section which is
6660 ;; detected using the same criteria as in
6661 ;; `c-beginning-of-decl-1'. Move to the following block
6662 ;; start.
6666 ;; Encountered a block in the declaration. Jump over it.
6677 ;; Check for `c-opt-block-decls-with-vars-key'
6678 ;; before the first paren.
6681 c-opt-block-decls-with-vars-key
6683 lim t t t)
6686 ;; Check that the first following paren is
6687 ;; the block.
6689 lim t t t)
6691 ;; The declaration doesn't have any of the
6692 ;; `c-opt-block-decls-with-vars' keywords in the
6693 ;; beginning, so it ends here at the end of the block.
6701 nil)))
6704 ;; Assuming the point is at an open brace, check if it starts a
6705 ;; block that contains another declaration level, i.e. that isn't a
6706 ;; statement block or a brace list, and if so return non-nil.
6707 ;;
6708 ;; If the check is successful, the return value is the start of the
6709 ;; keyword that tells what kind of construct it is, i.e. typically
6710 ;; what `c-decl-block-key' matched. Also, if GOTO-START is set then
6711 ;; the point will be at the start of the construct, before any
6712 ;; leading specifiers, otherwise it's at the returned position.
6713 ;;
6714 ;; The point is clobbered if the check is unsuccessful.
6715 ;;
6716 ;; CONTAINING-SEXP is the position of the open of the surrounding
6717 ;; paren, or nil if none.
6718 ;;
6719 ;; The optional LIMIT limits the backward search for the start of
6720 ;; the construct. It's assumed to be at a syntactically relevant
6721 ;; position.
6722 ;;
6723 ;; If any template arglists are found in the searched region before
6724 ;; the open brace, they get marked with paren syntax.
6725 ;;
6726 ;; This function might do hidden buffer changes.
6733 ;; Could be at the end of a template arglist.
6744 ;; Note: Can't get bogus hits inside template arglists below since they
6745 ;; have gotten paren syntax above.
6747 ;; If `goto-start' is set we begin by searching for the
6748 ;; first possible position of a leading specifier list.
6749 ;; The `c-decl-block-key' search continues from there since
6750 ;; we know it can't match earlier.
6753 open-brace t t)
6755 t)
6756 t)
6763 ;; Found a keyword that can't be a type?
6766 ;; Can be a type too, in which case it's the return type of a
6767 ;; function (under the assumption that no declaration level
6768 ;; block construct starts with a type).
6771 ;; Jumped over a type, but it could be a declaration keyword
6772 ;; followed by the declared identifier that we've jumped over
6773 ;; instead (e.g. in "class Foo {"). If it indeed is a type
6774 ;; then we should be at the declarator now, so check for a
6775 ;; valid declarator start.
6776 ;;
6777 ;; Note: This doesn't cope with the case when a declared
6778 ;; identifier is followed by e.g. '(' in a language where '('
6779 ;; also might be part of a declarator expression. Currently
6780 ;; there's no such language.
6784 ;; In Pike a list of modifiers may be followed by a brace
6785 ;; to make them apply to many identifiers. Note that the
6786 ;; match data will be empty on return in this case.
6792 ;; Use this variant to avoid yet another special regexp.
6796 t)))
6798 ;; Got a match.
6801 ;; Back up over any preceding specifiers and their clauses
6802 ;; by going forward from `first-specifier-pos', which is the
6803 ;; earliest possible position where the specifier list can
6804 ;; start.
6810 ;; Accept any plain symbol token on the ground that
6811 ;; it's a specifier masked through a macro (just
6812 ;; like `c-forward-decl-or-cast-1' skip forward over
6813 ;; such tokens).
6814 ;;
6815 ;; Could be more restrictive wrt invalid keywords,
6816 ;; but that'd only occur in invalid code so there's
6817 ;; no use spending effort on it.
6823 ;; Can't parse a declaration preamble and is still
6824 ;; before `kwd-start'. That means `first-specifier-pos'
6825 ;; was in some earlier construct. Search again.
6829 ;; Got no preamble before the block declaration keyword.
6835 kwd-start)))
6838 ;; Check if the closest containing paren sexp is a declaration
6839 ;; block, returning a 2 element vector in that case. Aref 0
6840 ;; contains the bufpos at boi of the class key line, and aref 1
6841 ;; contains the bufpos of the open brace. This function is an
6842 ;; obsolete wrapper for `c-looking-at-decl-block'.
6843 ;;
6844 ;; This function might do hidden buffer changes.
6852 nil))
6857 ;; return the buffer position of the beginning of the brace list
6858 ;; statement if we're inside a brace list, otherwise return nil.
6859 ;; CONTAINING-SEXP is the buffer pos of the innermost containing
6860 ;; paren. PAREN-STATE is the remainder of the state of enclosing
6861 ;; braces
6862 ;;
6863 ;; N.B.: This algorithm can potentially get confused by cpp macros
6864 ;; placed in inconvenient locations. It's a trade-off we make for
6865 ;; speed.
6866 ;;
6867 ;; This function might do hidden buffer changes.
6869 ;; This will pick up brace list declarations.
6882 ;; this will pick up array/aggregate init lists, even if they are nested.
6885 ;; Pike can have class definitions anywhere, so we must
6886 ;; check for the class key here.
6888 c-decl-block-key))
6889 bufpos braceassignp lim next-containing)
6891 containing-sexp)
6902 ;; We're in an in-expression block of some kind. Do not
6903 ;; check nesting. We deliberately set the limit to the
6904 ;; containing sexp, so that c-looking-at-inexpr-block
6905 ;; doesn't check for an identifier before it.
6907 ;; see if the open brace is preceded by = or [...] in
6908 ;; this statement, but watch out for operator=
6911 ;; Checks to do only on the first sexp before the brace.
6914 ;; In Java, an initialization brace list may follow
6915 ;; directly after "new Foo[]", so check for a "new"
6916 ;; earlier.
6922 ;; Carry on looking if this is an
6923 ;; identifier (may contain "." in Java)
6924 ;; or another "[]" sexp.
6927 ;; Checks to do on all sexps before the brace, up to the
6928 ;; beginning of the statement.
6936 ;; We've seen a =, but must check earlier tokens so
6937 ;; that it isn't something that should be ignored.
6943 ;; Check for operator =
6946 nil)
6947 ;; Check for `<opchar>= in Pike.
6950 ;; Special case for Pikes
6951 ;; `[]=, since '[' is not in
6952 ;; the punctuation class.
6955 nil)
6957 ;; make sure we're not in a C++ template
6958 ;; argument assignment
6970 ))))
6971 nil)
6978 ;; Brace lists can't contain a semicolon, so we're done.
6980 ;; Go up one level.
6982 lim nil
6983 next-containing nil))
6984 ;; we've hit the beginning of the aggregate list
6988 )
6989 bufpos))
6990 ))
6993 ;; If we're looking at the start of a pike-style list, ie `({Â })',
6994 ;; `([Â ])', `(<Â >)' etc, a cons of a cons of its starting and ending
6995 ;; positions and its entry in c-special-brace-lists is returned, nil
6996 ;; otherwise. The ending position is nil if the list is still open.
6997 ;; LIM is the limit for forward search. The point may either be at
6998 ;; the `(' or at the following paren character. Tries to check the
6999 ;; matching closer, but assumes it's correct if no balanced paren is
7000 ;; found (i.e. the case `({ ... } ... )' is detected as _not_ being
7001 ;; a special brace list).
7002 ;;
7003 ;; This function might do hidden buffer changes.
7008 inner-beg end type)
7023 nil)))))
7033 ;; Check balancing of the inner paren
7034 ;; below.
7037 t)
7038 ;; If the inner char isn't a paren then
7039 ;; we can't check balancing, so just
7040 ;; check the char before the outer
7041 ;; closing paren.
7056 ;; Return non-nil if between two statements or declarations, assuming
7057 ;; point is not inside a literal or comment.
7058 ;;
7059 ;; Obsolete - `c-at-statement-start-p' or `c-at-expression-start-p'
7060 ;; are recommended instead.
7061 ;;
7062 ;; This function might do hidden buffer changes.
7067 ;; Return non-nil if we're looking at the beginning of a block
7068 ;; inside an expression. The value returned is actually a cons of
7069 ;; either 'inlambda, 'inexpr-statement or 'inexpr-class and the
7070 ;; position of the beginning of the construct.
7071 ;;
7072 ;; LIM limits the backward search. CONTAINING-SEXP is the start
7073 ;; position of the closest containing list. If it's nil, the
7074 ;; containing paren isn't used to decide whether we're inside an
7075 ;; expression or not. If both LIM and CONTAINING-SEXP are used, LIM
7076 ;; needs to be farther back.
7077 ;;
7078 ;; If CHECK-AT-END is non-nil then extra checks at the end of the
7079 ;; brace block might be done. It should only be used when the
7080 ;; construct can be assumed to be complete, i.e. when the original
7081 ;; starting position was further down than that.
7082 ;;
7083 ;; This function might do hidden buffer changes.
7088 ;; Look at the character after point only as a last resort
7089 ;; when we can't disambiguate.
7109 ;; If the class definition is at the start of
7110 ;; a statement, we don't consider it an
7111 ;; in-expression class.
7119 ;; Also, in Pike we treat it as an
7120 ;; in-expression class if it's used in an
7121 ;; object clone expression.
7137 nil)
7145 ;; Accept several square bracket sexps for
7146 ;; Java array initializations.
7154 block-follows
7155 containing-sexp
7164 nil
7167 res))))
7170 ;; Returns non-nil if we're looking at the end of an in-expression
7171 ;; block, otherwise the same as `c-looking-at-inexpr-block'.
7172 ;; PAREN-STATE is the paren state relevant at the current position.
7173 ;;
7174 ;; This function might do hidden buffer changes.
7176 ;; We currently only recognize a block.
7179 containing-sexp)
7188 paren-state)
7189 containing-sexp)))))
7191 \f
7192 ;; `c-guess-basic-syntax' and the functions that precedes it below
7193 ;; implements the main decision tree for determining the syntactic
7194 ;; analysis of the current line of code.
7196 ;; Dynamically bound to t when `c-guess-basic-syntax' is called during
7197 ;; auto newline analysis.
7201 ;; A simple function to prepend a new syntax element to
7202 ;; `c-syntactic-context'. Using `setq' on it is unsafe since it
7203 ;; should always be dynamically bound but since we read it first
7204 ;; we'll fail properly anyway if this function is misused.
7206 c-syntactic-context)))
7209 ;; Like `c-add-syntax' but appends to the end of the syntax list.
7210 ;; (Normally not necessary.)
7215 syntax-extra-args
7216 stop-at-boi-only
7217 containing-sexp
7218 paren-state)
7219 ;; Add the indicated SYNTAX-SYMBOL to `c-syntactic-context', extending it as
7220 ;; needed with further syntax elements of the types `substatement',
7221 ;; `inexpr-statement', `arglist-cont-nonempty', `statement-block-intro', and
7222 ;; `defun-block-intro'.
7223 ;;
7224 ;; Do the generic processing to anchor the given syntax symbol on
7225 ;; the preceding statement: Skip over any labels and containing
7226 ;; statements on the same line, and then search backward until we
7227 ;; find a statement or block start that begins at boi without a
7228 ;; label or comment.
7229 ;;
7230 ;; Point is assumed to be at the prospective anchor point for the
7231 ;; given SYNTAX-SYMBOL. More syntax entries are added if we need to
7232 ;; skip past open parens and containing statements. All the added
7233 ;; syntax elements will get the same anchor point.
7234 ;;
7235 ;; SYNTAX-EXTRA-ARGS are a list of the extra arguments for the
7236 ;; syntax symbol. They are appended after the anchor point.
7237 ;;
7238 ;; If STOP-AT-BOI-ONLY is nil, we can stop in the middle of the line
7239 ;; if the current statement starts there.
7240 ;;
7241 ;; Note: It's not a problem if PAREN-STATE "overshoots"
7242 ;; CONTAINING-SEXP, i.e. contains info about parens further down.
7243 ;;
7244 ;; This function might do hidden buffer changes.
7247 ;; This is by far the most common case, so let's give it special
7248 ;; treatment.
7253 ;; Set when we're on a label, so that we don't stop there.
7254 ;; FIXME: To be complete we should check if we're on a label
7255 ;; now at the start.
7256 on-label)
7260 ;; Loop while we have to back out of containing blocks.
7265 ;; Loop while we have to back up statements.
7267 on-label
7270 ;; Skip past any comments that stands between the
7271 ;; statement start and boi.
7279 ;; Skip to the beginning of this statement or backward
7280 ;; another one.
7288 ;; If we didn't move we're at the start of a block and
7289 ;; have to continue outside it.
7298 ;; Special case to avoid deeper and deeper indentation
7299 ;; of "else if" clauses.
7300 )
7305 ;; If stop-at-boi-only is nil, we shouldn't back up
7306 ;; over previous or containing statements to try to
7307 ;; reach boi, so go back to the last position and
7308 ;; exit.
7315 ;; If we've moved into another statement then we
7316 ;; should no longer try to stop in the middle of a
7317 ;; line.
7320 ;; Record this as a substatement if we skipped up one
7321 ;; level.
7324 )))
7326 containing-sexp)
7328 ;; Now we have to go out of this block.
7331 ;; Don't stop in the middle of a special brace list opener
7332 ;; like "({".
7344 ;; Analyze the construct in front of the block we've stepped out
7345 ;; from and add the right syntactic element for it.
7348 step-type)
7351 ;; Stepped out of a parenthesis block, so we're in an
7352 ;; expression now.
7364 ;; Stepped out of an in-expression statement. This
7365 ;; syntactic element won't get an anchor pos.
7368 ;; A parenthesis normally belongs to an arglist.
7376 on-label nil))
7387 paren-state)
7388 containing-sexp)))
7396 ;; Always done if the open brace was at boi. The
7397 ;; c-beginning-of-statement-1 call above is necessary
7398 ;; anyway, to decide the type of block-intro to add.
7401 ))
7403 ;; Fill in the current point as the anchor for all the symbols
7404 ;; added above.
7410 )))
7413 containing-decl-open
7414 containing-decl-start
7415 containing-decl-kwd
7416 paren-state)
7417 ;; The inclass and class-close syntactic symbols are added in
7418 ;; several places and some work is needed to fix everything.
7419 ;; Therefore it's collected here.
7420 ;;
7421 ;; This function might do hidden buffer changes.
7426 containing-decl-open)
7428 ;; Ought to use `c-add-stmt-syntax' instead of backing up to boi
7429 ;; here, but we have to do like this for compatibility.
7439 char-after-ip
7440 beg-of-same-or-containing-stmt
7441 containing-sexp
7442 paren-state)
7443 ;; This function contains the decision tree reached through both
7444 ;; cases 18 and 10. It's a continued statement or top level
7445 ;; construct of some kind.
7446 ;;
7447 ;; This function might do hidden buffer changes.
7454 ;; (CASE A removed.)
7455 ;; CASE B: open braces for class or brace-lists
7462 ;; CASE B.1: class-open
7469 ;; CASE B.2: brace-list-open
7474 indent-point t t t)))
7475 ;; The most semantically accurate symbol here is
7476 ;; brace-list-open, but we normally report it simply as a
7477 ;; statement-cont. The reason is that one normally adjusts
7478 ;; brace-list-open for brace lists as top-level constructs,
7479 ;; and brace lists inside statements is a completely different
7480 ;; context. C.f. case 5A.3.
7483 ;; Turn off the dwim above when we're
7484 ;; analyzing the nature of the brace
7485 ;; for the auto newline feature.
7486 'brace-list-open
7488 nil nil
7489 containing-sexp paren-state))
7491 ;; CASE B.3: The body of a function declared inside a normal
7492 ;; block. Can occur e.g. in Pike and when using gcc
7493 ;; extensions, but watch out for macros followed by blocks.
7494 ;; C.f. cases E, 16F and 17G.
7500 ;; Turn off recognition of constructs that lacks a
7501 ;; type in this case, since that's more likely to be
7502 ;; a macro followed by a block.
7505 containing-sexp paren-state))
7507 ;; CASE B.4: Continued statement with block open. The most
7508 ;; accurate analysis is perhaps `statement-cont' together with
7509 ;; `block-open' but we play DWIM and use `substatement-open'
7510 ;; instead. The rationaly is that this typically is a macro
7511 ;; followed by a block which makes it very similar to a
7512 ;; statement with a substatement block.
7515 containing-sexp paren-state))
7516 ))
7518 ;; CASE C: iostream insertion or extraction operator
7522 ;; If there is no preceding streamop in the statement
7523 ;; then indent this line as a normal statement-cont.
7527 t))))
7529 ;; CASE E: In the "K&R region" of a function declared inside a
7530 ;; normal block. C.f. case B.3.
7532 ;; Check that the next token is a '{'. This works as
7533 ;; long as no language that allows nested function
7534 ;; definitions allows stuff like member init lists, K&R
7535 ;; declarations or throws clauses there.
7536 ;;
7537 ;; Note that we do a forward search for something ahead
7538 ;; of the indentation line here. That's not good since
7539 ;; the user might not have typed it yet. Unfortunately
7540 ;; it's exceedingly tricky to recognize a function
7541 ;; prototype in a code block without resorting to this.
7549 ;; Turn off recognition of constructs that lacks a
7550 ;; type in this case, since that's more likely to be
7551 ;; a macro followed by a block.
7554 containing-sexp paren-state))
7556 ;; CASE D: continued statement.
7560 containing-sexp paren-state))
7561 )))
7563 ;; The next autoload was added by RMS on 2005/8/9 - don't know why (ACM,
7564 ;; 2005/11/29).
7565 ;;;###autoload
7567 "Return the syntactic context of the current line."
7573 ;; A whole ugly bunch of various temporary variables. Have
7574 ;; to declare them here since it's not possible to declare
7575 ;; a variable with only the scope of a cond test and the
7576 ;; following result clauses, and most of this function is a
7577 ;; single gigantic cond. :P
7578 literal char-before-ip before-ws-ip char-after-ip macro-start
7579 in-macro-expr c-syntactic-context placeholder c-in-literal-cache
7580 step-type tmpsymbol keyword injava-inher special-brace-list tmp-pos
7581 ;; The following record some positions for the containing
7582 ;; declaration block if we're directly within one:
7583 ;; `containing-decl-open' is the position of the open
7584 ;; brace. `containing-decl-start' is the start of the
7585 ;; declaration. `containing-decl-kwd' is the keyword
7586 ;; symbol of the keyword that tells what kind of block it
7587 ;; is.
7588 containing-decl-open
7589 containing-decl-start
7590 containing-decl-kwd
7591 ;; The open paren of the closest surrounding sexp or nil if
7592 ;; there is none.
7593 containing-sexp
7594 ;; The position after the closest preceding brace sexp
7595 ;; (nested sexps are ignored), or the position after
7596 ;; `containing-sexp' if there is none, or (point-min) if
7597 ;; `containing-sexp' is nil.
7598 lim
7599 ;; The paren state outside `containing-sexp', or at
7600 ;; `indent-point' if `containing-sexp' is nil.
7602 ;; There's always at most one syntactic element which got
7603 ;; an anchor pos. It's stored in syntactic-relpos.
7604 syntactic-relpos
7607 ;; Check if we're directly inside an enclosing declaration
7608 ;; level block.
7617 containing-sexp)
7618 t)))
7621 containing-sexp nil)
7626 ;; Init some position variables.
7635 ;; Ignore balanced paren. The next entry
7636 ;; can't be another one.
7639 ;; If there is no surrounding open paren then
7640 ;; put the last balanced pair back on paren-state.
7642 containing-sexp nil)))
7646 ;; If we're in a parenthesis list then ',' delimits the
7647 ;; "statements" rather than being an operator (with the
7648 ;; exception of the "for" clause). This difference is
7649 ;; typically only noticeable when statements are used in macro
7650 ;; arglists.
7655 ;; cache char before and after indent point, and move point to
7656 ;; the most likely position to perform the majority of tests
7665 ;; are we in a literal?
7668 ;; now figure out syntactic qualities of the current line
7671 ;; CASE 1: in a string.
7675 ;; CASE 2: in a C or C++ style comment.
7677 ;; This is a kludge for XEmacs where we use
7678 ;; `buffer-syntactic-context', which doesn't correctly
7679 ;; recognize "\*/" to end a block comment.
7680 ;; `parse-partial-sexp' which is used by
7681 ;; `c-literal-limits' will however do that in most
7682 ;; versions, which results in that we get nil from
7683 ;; `c-literal-limits' even when `c-in-literal' claims
7684 ;; we're inside a comment.
7688 ;; CASE 3: in a cpp preprocessor macro continuation.
7698 ;; If at the beginning of the body of a #define
7699 ;; directive then analyze as cpp-define-intro
7700 ;; only. Go on with the syntactic analysis
7701 ;; otherwise. in-macro-expr is set if we're in a
7702 ;; cpp expression, i.e. before the #define body
7703 ;; or anywhere in a non-#define directive.
7710 nil)))))
7714 ;; CASE 11: an else clause?
7718 containing-sexp paren-state))
7720 ;; CASE 12: while closure of a do/while construct?
7728 containing-sexp paren-state))
7730 ;; CASE 13: A catch or finally clause? This case is simpler
7731 ;; than if-else and do-while, because a block is required
7732 ;; after every try, catch and finally.
7740 t)
7744 t)
7747 t))
7752 containing-sexp paren-state))
7754 ;; CASE 18: A substatement we can recognize by keyword.
7764 ;; Ought to cache the result from the
7765 ;; c-beginning-of-statement-1 calls here.
7775 ;; Step up to the containing statement if we
7776 ;; stayed in the same one.
7784 ;; There was no containing statement afterall.
7786 placeholder))
7788 ;; Require a parenthesis after these keywords.
7789 ;; Necessary to catch e.g. synchronized in Java,
7790 ;; which can be used both as statement and
7791 ;; modifier.
7797 ;; CASE 18A: Simple substatement.
7803 containing-sexp paren-state))
7809 containing-sexp paren-state))
7812 containing-sexp paren-state))))
7814 ;; CASE 18B: Some other substatement. This is shared
7815 ;; with case 10.
7817 char-after-ip
7818 placeholder
7819 lim
7820 paren-state)))
7822 ;; CASE 14: A case or default label
7828 containing-sexp))
7831 ;; Got a bogus label at the top level. In lack of better
7832 ;; alternatives, anchor it on (point-min).
7835 ;; CASE 15: any other label
7842 containing-decl-open
7843 containing-decl-start
7844 containing-decl-kwd
7845 paren-state))
7846 ;; Append access-label with the same anchor point as
7847 ;; inclass gets.
7853 containing-sexp))
7858 ;; If the surrounding statement is a switch then
7859 ;; let's analyze all labels as switch labels, so
7860 ;; that they get lined up consistently.
7861 'case-label
7867 ;; A label on the top level. Treat it as a class
7868 ;; context. (point-min) is the closest we get to the
7869 ;; class open brace.
7872 ;; CASE 4: In-expression statement. C.f. cases 7B, 16A and
7873 ;; 17E.
7876 containing-sexp
7877 ;; Have to turn on the heuristics after
7878 ;; the point even though it doesn't work
7879 ;; very well. C.f. test case class-16.pike.
7880 t))
7885 ;; It's a statement block or an anonymous class.
7887 ;; It's a Pike lambda. Check whether we are between the
7888 ;; lambda keyword and the argument list or at the defun
7889 ;; opener.
7891 'inline-open
7897 paren-state)
7901 ;; CASE 5: Line is inside a declaration level block or at top level.
7905 ;; CASE 5A: we are looking at a defun, brace list, class,
7906 ;; or inline-inclass method opening brace
7913 ;; CASE 5A.1: Non-class declaration block open.
7928 ;; Special case for extern-lang-open.
7929 'extern-lang-open
7931 nil t containing-sexp paren-state))
7933 ;; CASE 5A.2: we are looking at a class opening brace
7942 ;; CASE 5A.3: brace list open
7967 ))))
7971 ;; We're in Java and have found that the open brace
7972 ;; belongs to a "new Foo[]" initialization list,
7973 ;; which means the brace list is part of an
7974 ;; expression and not a top level definition. We
7975 ;; therefore treat it as any topmost continuation
7976 ;; even though the semantically correct symbol still
7977 ;; is brace-list-open, on the same grounds as in
7978 ;; case B.2.
7984 ;; CASE 5A.4: inline defun open
7990 containing-decl-open
7991 containing-decl-start
7992 containing-decl-kwd
7993 paren-state))
7995 ;; CASE 5A.5: ordinary defun open
8000 ;; Bogus to use bol here, but it's the legacy.
8002 )))
8004 ;; CASE 5B: After a function header but before the body (or
8005 ;; the ending semicolon if there's no body).
8011 ;; CASE 5B.1: Member init list.
8016 ;; There is no preceding member init clause.
8017 ;; Indent relative to the beginning of indentation
8018 ;; for the topmost-intro line that contains the
8019 ;; prototype's open paren.
8022 ;; Indent relative to the first member init clause.
8027 ;; CASE 5B.2: K&R arg decl intro
8034 containing-decl-open
8035 containing-decl-start
8036 containing-decl-kwd
8037 paren-state)))
8039 ;; CASE 5B.4: Nether region after a C++ or Java func
8040 ;; decl, which could include a `throws' declaration.
8044 )))
8046 ;; CASE 5C: inheritance line. could be first inheritance
8047 ;; line, or continuation of a multiple inheritance
8055 ;; watch out for scope operator
8060 )))
8069 ;; for Java
8074 cont done)
8079 done t))
8083 )
8085 injava-inher)
8088 ))
8091 ;; CASE 5C.1: non-hanging colon on an inher intro
8095 ;; don't add inclass symbol since relative point already
8096 ;; contains any class offset
8097 )
8099 ;; CASE 5C.2: hanging colon on an inher intro
8105 containing-decl-open
8106 containing-decl-start
8107 containing-decl-kwd
8108 paren-state)))
8110 ;; CASE 5C.3: in a Java implements/extends
8124 )))
8126 ;; CASE 5C.4: a continued inheritance line
8130 ;; don't add inclass symbol since relative point already
8131 ;; contains any class offset
8132 )))
8134 ;; CASE 5D: this could be a top-level initialization, a
8135 ;; member init list continuation, or a template argument
8136 ;; list continuation.
8138 ;; Note: We use the fact that lim always is after any
8139 ;; preceding brace sexp.
8149 t))
8154 t)
8160 nil)
8161 t))
8163 ;; NB: No c-after-special-operator-id stuff in this
8164 ;; clause - we assume only C++ needs it.
8169 ;; CASE 5D.3: perhaps a template list continuation?
8184 ;; In a nested template arglist.
8190 ;; FIXME: Should use c-add-stmt-syntax, but it's not yet
8191 ;; template aware.
8194 ;; CASE 5D.4: perhaps a multiple inheritance line?
8206 t)
8211 ;; CASE 5D.5: Continuation of the "expression part" of a
8212 ;; top level construct.
8221 ;; A preceding comma at the top level means that a
8222 ;; new variable declaration starts here. Use
8223 ;; topmost-intro-cont for it, for consistency with
8224 ;; the first variable declaration. C.f. case 5N.
8225 'topmost-intro-cont
8227 nil nil containing-sexp paren-state))
8228 ))
8230 ;; CASE 5F: Close of a non-class declaration level block.
8234 ;; This is inconsistent: Should use `containing-decl-open'
8235 ;; here if it's at boi, like in case 5J.
8239 ;; Special case for compatibility with the
8240 ;; extern-lang syntactic symbols.
8241 'extern-lang-close
8244 nil t
8246 paren-state))
8248 ;; CASE 5G: we are looking at the brace which closes the
8249 ;; enclosing nested class decl
8254 containing-decl-open
8255 containing-decl-start
8256 containing-decl-kwd
8257 paren-state))
8259 ;; CASE 5H: we could be looking at subsequent knr-argdecls
8265 ;; Do an extra check to avoid tripping up on
8266 ;; statements that occur in invalid contexts
8267 ;; (e.g. in macro bodies where we don't really
8268 ;; know the context of what we're looking at).
8275 ;; CASE 5I: ObjC method definition.
8280 ;; Handle the case when it's the first (non-comment)
8281 ;; thing in the buffer. Can't look for a 'same return
8282 ;; value from cbos1 since ObjC directives currently
8283 ;; aren't recognized fully, so that we get 'same
8284 ;; instead of 'previous if it moved over a preceding
8285 ;; directive.
8289 ;; CASE 5P: AWK pattern or function or continuation
8290 ;; thereof.
8296 'topmost-intro-cont
8298 nil nil
8299 containing-sexp paren-state))
8301 ;; CASE 5N: At a variable declaration that follows a class
8302 ;; definition or some other block declaration that doesn't
8303 ;; end at the closing '}'. C.f. case 5D.5.
8312 ;; Speed up the backward search a bit.
8317 ;; The '}' is unbalanced.
8318 nil
8323 containing-sexp paren-state))
8325 ;; NOTE: The point is at the end of the previous token here.
8327 ;; CASE 5J: we are at the topmost level, make
8328 ;; sure we skip back past any access specifiers
8330 ;; A macro continuation line is never at top level.
8352 nil)))))
8353 ;; For historic reasons we anchor at bol of the last
8354 ;; line of the previous declaration. That's clearly
8355 ;; highly bogus and useless, and it makes our lives hard
8356 ;; to remain compatible. :P
8369 ;; Special case for compatibility with the
8370 ;; extern-lang syntactic symbols.
8371 'inextern-lang
8374 nil t
8376 paren-state))
8378 containing-decl-open
8379 containing-decl-start
8380 containing-decl-kwd
8381 paren-state)))
8383 macro-start
8388 ;; CASE 5K: we are at an ObjC method definition
8389 ;; continuation line.
8398 ;; CASE 5L: we are at the first argument of a template
8399 ;; arglist that begins on the previous line.
8407 ;; CASE 5Q: we are at a statement within a macro.
8412 ;; CASE 5M: we are at a topmost continuation line
8423 ))
8425 ;; (CASE 6 has been removed.)
8427 ;; CASE 7: line is an expression, not a statement. Most
8428 ;; likely we are either in a function prototype or a function
8429 ;; call argument list
8437 ;; CASE 7A: we are looking at the arglist closing paren.
8438 ;; C.f. case 7F.
8450 paren-state))
8452 ;; CASE 7B: Looking at the opening brace of an
8453 ;; in-expression block or brace list. C.f. cases 4, 16A
8454 ;; and 17E.
8458 paren-state))
8462 placeholder
8465 paren-state)
8466 containing-sexp)))
8467 ;; placeholder is nil if it's a block directly in
8468 ;; a function arglist. That makes us skip out of
8469 ;; this case.
8470 )))
8475 paren-state)
8479 ;; CASE 7C: we are looking at the first argument in an empty
8480 ;; argument list. Use arglist-close if we're actually
8481 ;; looking at a close paren or bracket.
8493 paren-state))
8495 ;; CASE 7D: we are inside a conditional test clause. treat
8496 ;; these things as statements
8506 ))
8508 ;; CASE 7E: maybe a continued ObjC method call. This is the
8509 ;; case when we are inside a [] bracketed exp, and what
8510 ;; precede the opening bracket is not an identifier.
8518 )))
8520 ;; CASE 7F: we are looking at an arglist continuation line,
8521 ;; but the preceding argument is on the same line as the
8522 ;; opening paren. This case includes multi-line
8523 ;; mathematical paren groupings, but we could be on a
8524 ;; for-list continuation line. C.f. case 7A.
8541 paren-state))
8543 ;; CASE 7G: we are looking at just a normal arglist
8544 ;; continuation line
8547 ))
8549 ;; CASE 8: func-local multi-inheritance line
8559 ;; CASE 8A: non-hanging colon on an inher intro
8564 ;; CASE 8B: hanging colon on an inher intro
8568 ;; CASE 8C: a continued inheritance line
8572 )))
8574 ;; CASE 9: we are inside a brace-list
8584 ;; CASE 9A: In the middle of a special brace list opener.
8604 ;; CASE 9B: brace-list-close brace
8606 ;; Check special brace list closer.
8613 ;; We were between the special close char and the `)'.
8616 ;; We were before the special close char.
8620 ;; Normal brace list check.
8631 ;; Prepare for the rest of the cases below by going to the
8632 ;; token following the opening brace
8645 ;; CASE 9C: we're looking at the first line in a brace-list
8656 ;; CASE 9D: this is just a later brace-list-entry or
8657 ;; brace-entry-open
8666 ))
8667 ))))
8669 ;; CASE 10: A continued statement or top level construct.
8679 ;; This is shared with case 18.
8681 char-after-ip
8682 placeholder
8683 containing-sexp
8684 paren-state))
8686 ;; CASE 16: block close brace, possibly closing the defun or
8687 ;; the class
8689 ;; From here on we have the next containing sexp in lim.
8694 ;; CASE 16E: Closing a statement block? This catches
8695 ;; cases where it's preceded by a statement keyword,
8696 ;; which works even when used in an "invalid" context,
8697 ;; e.g. a macro argument.
8702 ;; CASE 16A: closing a lambda defun or an in-expression
8703 ;; block? C.f. cases 4, 7B and 17E.
8706 nil))
8708 'inline-close
8718 paren-state)
8722 ;; CASE 16B: does this close an inline or a function in
8723 ;; a non-class declaration level block?
8730 nil))
8740 ;; CASE 16F: Can be a defun-close of a function declared
8741 ;; in a statement block, e.g. in Pike or when using gcc
8742 ;; extensions, but watch out for macros followed by
8743 ;; blocks. Let it through to be handled below.
8744 ;; C.f. cases B.3 and 17G.
8750 ;; Turn off recognition of constructs that
8751 ;; lacks a type in this case, since that's more
8752 ;; likely to be a macro followed by a block.
8759 ;; CASE 16C: If there is an enclosing brace then this is
8760 ;; a block close since defun closes inside declaration
8761 ;; level blocks have been handled above.
8763 ;; If the block is preceded by a case/switch label on
8764 ;; the same line, we anchor at the first preceding label
8765 ;; at boi. The default handling in c-add-stmt-syntax
8766 ;; really fixes it better, but we do like this to keep
8767 ;; the indentation compatible with version 5.28 and
8768 ;; earlier. C.f. case 17H.
8775 ;; c-backward-to-block-anchor not necessary here; those
8776 ;; situations are handled in case 16E above.
8779 ;; CASE 16D: Only top level defun close left.
8785 paren-state))
8786 ))
8788 ;; CASE 17: Statement or defun catchall.
8791 ;; Back up statements until we find one that starts at boi.
8794 containing-sexp)))
8798 nil)
8803 ;; CASE 17B: continued statement
8807 containing-sexp paren-state))
8809 ;; CASE 17A: After a case/default label?
8817 'statement-case-open
8819 nil t containing-sexp paren-state))
8821 ;; CASE 17D: any old statement
8828 containing-sexp paren-state)
8832 ;; CASE 17I: Inside a substatement block.
8834 ;; The following tests are all based on containing-sexp.
8836 ;; From here on we have the next containing sexp in lim.
8841 lim paren-state)
8845 ;; CASE 17E: first statement in an in-expression block.
8846 ;; C.f. cases 4, 7B and 16A.
8849 nil))
8851 'defun-block-intro
8860 paren-state)
8866 ;; CASE 17F: first statement in an inline, or first
8867 ;; statement in a top-level defun. we can tell this is it
8868 ;; if there are no enclosing braces that haven't been
8869 ;; narrowed out by a class (i.e. don't use bod here).
8872 paren-state)))
8878 nil))))
8883 ;; CASE 17G: First statement in a function declared inside
8884 ;; a normal block. This can occur in Pike and with
8885 ;; e.g. the gcc extensions, but watch out for macros
8886 ;; followed by blocks. C.f. cases B.3 and 16F.
8892 ;; Turn off recognition of constructs that lacks
8893 ;; a type in this case, since that's more likely
8894 ;; to be a macro followed by a block.
8900 lim paren-state))
8902 ;; CASE 17H: First statement in a block.
8904 ;; If the block is preceded by a case/switch label on the
8905 ;; same line, we anchor at the first preceding label at
8906 ;; boi. The default handling in c-add-stmt-syntax is
8907 ;; really fixes it better, but we do like this to keep the
8908 ;; indentation compatible with version 5.28 and earlier.
8909 ;; C.f. case 16C.
8916 ;; c-backward-to-block-anchor not necessary here; those
8917 ;; situations are handled in case 17I above.
8919 lim paren-state))
8922 ))
8923 )
8925 ;; now we need to look at any modifiers
8929 ;; are we looking at a comment only line?
8934 ;; we might want to give additional offset to friends (in C++).
8939 ;; Set syntactic-relpos.
8945 nil)
8946 t))
8949 ;; Start of or a continuation of a preprocessor directive?
8964 ;; If inside a cpp expression, i.e. anywhere in a
8965 ;; cpp directive except a #define body, we only let
8966 ;; through the syntactic analysis that is internal
8967 ;; in the expression. That means the arglist
8968 ;; elements, if they are anchored inside the cpp
8969 ;; expression.
8978 ;; Inside a #define body and the syntactic analysis is
8979 ;; anchored on the start of the #define. In this case
8980 ;; we add cpp-define-intro to get the extra
8981 ;; indentation of the #define body.
8984 ;; return the syntax
8985 c-syntactic-context)))
8987 \f
8988 ;; Indentation calculation.
8991 ;; offset can be a number, a function, a variable, a list, or one of
8992 ;; the symbols + or -
8993 ;;
8994 ;; This function might do hidden buffer changes.
9013 langelem symbol))
9019 offset symbol)
9020 nil)
9034 Error evaluating offset %S for %s: \
9035 Cannot combine absolute offset %S with relative %S in `%s' method"
9041 Error evaluating offset %S for %s: \
9042 Cannot combine relative offset %S with absolute %S in `%s' method"
9047 res))
9065 Error evaluating offset %S for %s: \
9066 Cannot combine absolute offsets %S and %S in `add' method"
9070 res))
9079 res))))
9086 nil))))
9090 res
9092 offset symbol res)
9093 nil)))
9096 ;; Get offset from LANGELEM which is a list beginning with the
9097 ;; syntactic symbol and followed by any analysis data it provides.
9098 ;; That data may be zero or more elements, but if at least one is
9099 ;; given then the first is the anchor position (or nil). The symbol
9100 ;; is matched against `c-offsets-alist' and the offset calculated
9101 ;; from that is returned.
9102 ;;
9103 ;; This function might do hidden buffer changes.
9113 offset
9117 ))
9120 ;; This is a compatibility wrapper for `c-calc-offset' in case
9121 ;; someone is calling it directly. It takes an old style syntactic
9122 ;; element on the form (SYMBOL . ANCHOR-POS) and converts it to the
9123 ;; new list form.
9124 ;;
9125 ;; This function might do hidden buffer changes.
9132 ;; Calculate the syntactic indentation from a syntactic description
9133 ;; as returned by `c-guess-syntax'.
9134 ;;
9135 ;; Note that topmost-intro always has an anchor position at bol, for
9136 ;; historical reasons. It's often used together with other symbols
9137 ;; that has more sane positions. Since we always use the first
9138 ;; found anchor position, we rely on that these other symbols always
9139 ;; precede topmost-intro in the LANGELEMS list.
9140 ;;
9141 ;; This function might do hidden buffer changes.
9149 ;; Got an absolute column that overrides any indentation
9150 ;; we've collected so far, but not the relative
9151 ;; indentation we might get for the nested structures
9152 ;; further down the langelems list.
9156 ;; Got a relative change of the current calculated
9157 ;; indentation.
9160 ;; Use the anchor position from the first syntactic
9161 ;; element with one.
9171 indent)))
9173 \f
9176 ;;; arch-tag: 149add18-4673-4da5-ac47-6805e4eae089
9177 ;;; cc-engine.el ends here