view src/font-lock.c @ 5353:38e24b8be4ea

Improve the lexical scoping in #'block, #'return-from. lisp/ChangeLog addition: 2011-02-07 Aidan Kehoe <kehoea@parhasard.net> * bytecomp.el: * bytecomp.el (byte-compile-initial-macro-environment): Shadow `block', `return-from' here, we implement them differently when byte-compiling. * bytecomp.el (byte-compile-active-blocks): New. * bytecomp.el (byte-compile-block-1): New. * bytecomp.el (byte-compile-return-from-1): New. * bytecomp.el (return-from-1): New. * bytecomp.el (block-1): New. These are two aliases that exist to have their own associated byte-compile functions, which functions implement `block' and `return-from'. * cl-extra.el (cl-macroexpand-all): Fix a bug here when macros in the environment have been compiled. * cl-macs.el (block): * cl-macs.el (return): * cl-macs.el (return-from): Be more careful about lexical scope in these macros. * cl.el: * cl.el ('cl-block-wrapper): Removed. * cl.el ('cl-block-throw): Removed. These aren't needed in code generated by this XEmacs. They shouldn't be needed in code generated by XEmacs 21.4, but if it turns out the packages do need them, we can put them back. 2011-01-30 Mike Sperber <mike@xemacs.org> * font-lock.el (font-lock-fontify-pending-extents): Don't fail if `font-lock-mode' is unset, which can happen in the middle of `revert-buffer'. 2011-01-23 Aidan Kehoe <kehoea@parhasard.net> * cl-macs.el (delete): * cl-macs.el (delq): * cl-macs.el (remove): * cl-macs.el (remq): Don't use the compiler macro if these functions were given the wrong number of arguments, as happens in lisp-tests.el. * cl-seq.el (remove, remq): Removed. I added these to subr.el, and forgot to remove them from here. 2011-01-22 Aidan Kehoe <kehoea@parhasard.net> * bytecomp.el (byte-compile-setq, byte-compile-set): Remove kludge allowing keywords' values to be set, all the code that does that is gone. * cl-compat.el (elt-satisfies-test-p): * faces.el (set-face-parent): * faces.el (face-doc-string): * gtk-font-menu.el: * gtk-font-menu.el (gtk-reset-device-font-menus): * msw-font-menu.el: * msw-font-menu.el (mswindows-reset-device-font-menus): * package-get.el (package-get-installedp): * select.el (select-convert-from-image-data): * sound.el: * sound.el (load-sound-file): * x-font-menu.el (x-reset-device-font-menus-core): Don't quote keywords, they're self-quoting, and the win from backward-compatibility is sufficiently small now that the style problem overrides it. 2011-01-22 Aidan Kehoe <kehoea@parhasard.net> * cl-macs.el (block, return-from): Require that NAME be a symbol in these macros, as always documented in the #'block docstring and as required by Common Lisp. * descr-text.el (unidata-initialize-unihan-database): Correct the use of non-symbols in #'block and #'return-from in this function. 2011-01-15 Aidan Kehoe <kehoea@parhasard.net> * cl-extra.el (concatenate): Accept more complicated TYPEs in this function, handing the sequences over to #'coerce if we don't understand them here. * cl-macs.el (inline): Don't proclaim #'concatenate as inline, its compiler macro is more useful than doing that. 2011-01-11 Aidan Kehoe <kehoea@parhasard.net> * subr.el (delete, delq, remove, remq): Move #'remove, #'remq here, they don't belong in cl-seq.el; move #'delete, #'delq here from fns.c, implement them in terms of #'delete*, allowing support for sequences generally. * update-elc.el (do-autoload-commands): Use #'delete*, not #'delq here, now the latter's no longer dumped. * cl-macs.el (delete, delq): Add compiler macros transforming #'delete and #'delq to #'delete* calls. 2011-01-10 Aidan Kehoe <kehoea@parhasard.net> * dialog.el (make-dialog-box): Correct a misplaced parenthesis here, thank you Mats Lidell in 87zkr9gqrh.fsf@mail.contactor.se ! 2011-01-02 Aidan Kehoe <kehoea@parhasard.net> * dialog.el (make-dialog-box): * list-mode.el (display-completion-list): These functions used to use cl-parsing-keywords; change them to use defun* instead, fixing the build. (Not sure what led to me not including this change in d1b17a33450b!) 2011-01-02 Aidan Kehoe <kehoea@parhasard.net> * cl-macs.el (define-star-compiler-macros): Make sure the form has ITEM and LIST specified before attempting to change to calls with explicit tests; necessary for some tests in lisp-tests.el to compile correctly. (stable-union, stable-intersection): Add compiler macros for these functions, in the same way we do for most of the other functions in cl-seq.el. 2011-01-01 Aidan Kehoe <kehoea@parhasard.net> * cl-macs.el (dolist, dotimes, do-symbols, macrolet) (symbol-macrolet): Define these macros with defmacro* instead of parsing the argument list by hand, for the sake of style and readability; use backquote where appropriate, instead of calling #'list and and friends, for the same reason. 2010-12-30 Aidan Kehoe <kehoea@parhasard.net> * x-misc.el (device-x-display): Provide this function, documented in the Lispref for years, but not existing previously. Thank you Julian Bradfield, thank you Jeff Mincy. 2010-12-30 Aidan Kehoe <kehoea@parhasard.net> * cl-seq.el: Move the heavy lifting from this file to C. Dump the cl-parsing-keywords macro, but don't use defun* for the functions we define that do take keywords, dynamic scope lossage makes that not practical. * subr.el (sort, fillarray): Move these aliases here. (map-plist): #'nsublis is now built-in, but at this point #'eql isn't necessarily available as a test; use #'eq. * obsolete.el (cl-delete-duplicates): Make this available for old compiler macros and old code. (memql): Document that this is equivalent to #'member*, and worse. * cl.el (adjoin, subst): Removed. These are in C. 2010-12-30 Aidan Kehoe <kehoea@parhasard.net> * simple.el (assoc-ignore-case): Remove a duplicate definition of this function (it's already in subr.el). * iso8859-1.el (char-width): On non-Mule, make this function equivalent to that produced by (constantly 1), but preserve its docstring. * subr.el (subst-char-in-string): Define this in terms of #'substitute, #'nsubstitute. (string-width): Define this using #'reduce and #'char-width. (char-width): Give this a simpler definition, it makes far more sense to check for mule at load time and redefine, as we do in iso8859-1.el. (store-substring): Implement this in terms of #'replace, now #'replace is cheap. 2010-12-30 Aidan Kehoe <kehoea@parhasard.net> * update-elc.el (lisp-files-needed-for-byte-compilation) (lisp-files-needing-early-byte-compilation): cl-macs belongs in the former, not the latter, it is as fundamental as bytecomp.el. 2010-12-30 Aidan Kehoe <kehoea@parhasard.net> * cl.el: Provde the Common Lisp program-error, type-error as error symbols. This doesn't nearly go far enough for anyone using the Common Lisp errors. 2010-12-29 Aidan Kehoe <kehoea@parhasard.net> * cl-macs.el (delete-duplicates): If the form has an incorrect number of arguments, don't attempt a compiler macroexpansion. 2010-12-29 Aidan Kehoe <kehoea@parhasard.net> * cl-macs.el (cl-safe-expr-p): Forms that start with the symbol lambda are also safe. 2010-12-29 Aidan Kehoe <kehoea@parhasard.net> * cl-macs.el (= < > <= >=): For these functions' compiler macros, the optimisation is safe even if the first and the last arguments have side effects, since they're only used the once. 2010-12-29 Aidan Kehoe <kehoea@parhasard.net> * cl-macs.el (inline-side-effect-free-compiler-macros): Unroll a loop here at macro-expansion time, so these compiler macros are compiled. Use #'eql instead of #'eq in a couple of places for better style. 2010-12-29 Aidan Kehoe <kehoea@parhasard.net> * cl-extra.el (notany, notevery): Avoid some dynamic scope stupidity with local variable names in these functions, when they weren't prefixed with cl-; go into some more detail in the doc strings. 2010-12-29 Aidan Kehoe <kehoea@parhasard.net> * byte-optimize.el (side-effect-free-fns): #'remove, #'remq are free of side-effects. (side-effect-and-error-free-fns): Drop dot, dot-marker from the list. 2010-11-17 Aidan Kehoe <kehoea@parhasard.net> * cl-extra.el (coerce): In the argument list, name the first argument OBJECT, not X; the former name was always used in the doc string and is clearer. Handle vector type specifications which include the length of the target sequence, error if there's a mismatch. * cl-macs.el (cl-make-type-test): Handle type specifications starting with the symbol 'eql. 2010-11-14 Aidan Kehoe <kehoea@parhasard.net> * cl-macs.el (eql): Don't remove the byte-compile property of this symbol. That was necessary to override a bug in bytecomp.el where #'eql was confused with #'eq, which bug we no longer have. If neither expression is constant, don't attempt to handle the expression in this compiler macro, leave it to byte-compile-eql, which produces better code anyway. * bytecomp.el (eq): #'eql is not the function associated with the byte-eq byte code. (byte-compile-eql): Add an explicit compile method for this function, for cases where the cl-macs compiler macro hasn't reduced it to #'eq or #'equal. 2010-10-25 Aidan Kehoe <kehoea@parhasard.net> Add compiler macros and compilation sanity-checking for various functions that take keywords. * byte-optimize.el (side-effect-free-fns): #'symbol-value is side-effect free and not error free. * bytecomp.el (byte-compile-normal-call): Check keyword argument lists for sanity; store information about the positions where keyword arguments start using the new byte-compile-keyword-start property. * cl-macs.el (cl-const-expr-val): Take a new optional argument, cl-not-constant, defaulting to nil, in this function; return it if the expression is not constant. (cl-non-fixnum-number-p): Make this into a separate function, we want to pass it to #'every. (eql): Use it. (define-star-compiler-macros): Use the same code to generate the member*, assoc* and rassoc* compiler macros; special-case some code in #'add-to-list in subr.el. (remove, remq): Add compiler macros for these two functions, in preparation for #'remove being in C. (define-foo-if-compiler-macros): Transform (remove-if-not ...) calls to (remove ... :if-not) at compile time, which will be a real win once the latter is in C. (define-substitute-if-compiler-macros) (define-subst-if-compiler-macros): Similarly for these functions. (delete-duplicates): Change this compiler macro to use #'plists-equal; if we don't have information about the type of SEQUENCE at compile time, don't bother attempting to inline the call, the function will be in C soon enough. (equalp): Remove an old commented-out compiler macro for this, if we want to see it it's in version control. (subst-char-in-string): Transform this to a call to nsubstitute or nsubstitute, if that is appropriate. * cl.el (ldiff): Don't call setf here, this makes for a load-time dependency problem in cl-macs.el 2010-06-14 Stephen J. Turnbull <stephen@xemacs.org> * term/vt100.el: Refer to XEmacs, not GNU Emacs, in permissions. * term/bg-mouse.el: * term/sup-mouse.el: Put copyright notice in canonical "Copyright DATE AUTHOR" form. Refer to XEmacs, not GNU Emacs, in permissions. * site-load.el: Add permission boilerplate. * mule/canna-leim.el: * alist.el: Refer to XEmacs, not APEL/this program, in permissions. * mule/canna-leim.el: Remove my copyright, I've assigned it to the FSF. 2010-06-14 Stephen J. Turnbull <stephen@xemacs.org> * gtk.el: * gtk-widget-accessors.el: * gtk-package.el: * gtk-marshal.el: * gtk-compose.el: * gnome.el: Add copyright notice based on internal evidence. 2010-06-14 Stephen J. Turnbull <stephen@xemacs.org> * easymenu.el: Add reference to COPYING to permission notice. * gutter.el: * gutter-items.el: * menubar-items.el: Fix typo "Xmacs" in permissions notice. 2010-06-14 Stephen J. Turnbull <stephen@xemacs.org> * auto-save.el: * font.el: * fontconfig.el: * mule/kinsoku.el: Add "part of XEmacs" text to permission notice. 2010-10-14 Aidan Kehoe <kehoea@parhasard.net> * byte-optimize.el (side-effect-free-fns): * cl-macs.el (remf, getf): * cl-extra.el (tailp, cl-set-getf, cl-do-remf): * cl.el (ldiff, endp): Tighten up Common Lisp compatibility for #'ldiff, #'endp, #'tailp; add circularity checking for the first two. #'cl-set-getf and #'cl-do-remf were Lisp implementations of #'plist-put and #'plist-remprop; change the names to aliases, changes the macros that use them to using #'plist-put and #'plist-remprop directly. 2010-10-12 Aidan Kehoe <kehoea@parhasard.net> * abbrev.el (fundamental-mode-abbrev-table, global-abbrev-table): Create both these abbrev tables using the usual #'define-abbrev-table calls, rather than attempting to special-case them. * cl-extra.el: Force cl-macs to be loaded here, if cl-extra.el is being loaded interpreted. Previously other, later files would redundantly call (load "cl-macs") when interpreted, it's more reasonable to do it here, once. * cmdloop.el (read-quoted-char-radix): Use defcustom here, we don't have any dump-order dependencies that would prevent that. * custom.el (eval-when-compile): Don't load cl-macs when interpreted or when byte-compiling, rely on cl-extra.el in the former case and the appropriate entry in bytecomp-load-hook in the latter. Get rid of custom-declare-variable-list, we have no dump-time dependencies that would require it. * faces.el (eval-when-compile): Don't load cl-macs when interpreted or when byte-compiling. * packages.el: Remove some inaccurate comments. * post-gc.el (cleanup-simple-finalizers): Use #'delete-if-not here, now the order of preloaded-file-list has been changed to make it available. * subr.el (custom-declare-variable-list): Remove. No need for it. Also remove a stub define-abbrev-table from this file, given the current order of preloaded-file-list there's no need for it. 2010-10-10 Aidan Kehoe <kehoea@parhasard.net> * bytecomp.el (byte-compile-constp) Forms quoted with FUNCTION are also constant. (byte-compile-initial-macro-environment): In #'the, if FORM is constant and does not match TYPE, warn at byte-compile time. 2010-10-10 Aidan Kehoe <kehoea@parhasard.net> * backquote.el (bq-vector-contents, bq-list*): Remove; the former is equivalent to (append VECTOR nil), the latter to (list* ...). (bq-process-2): Use (append VECTOR nil) instead of using #'bq-vector-contents to convert to a list. (bq-process-1): Now we use list* instead of bq-list * subr.el (list*): Moved from cl.el, since it is now required to be available the first time a backquoted form is encountered. * cl.el (list*): Move to subr.el. 2010-09-16 Aidan Kehoe <kehoea@parhasard.net> * test-harness.el (Check-Message): Add an omitted comma here, thank you the buildbot. 2010-09-16 Aidan Kehoe <kehoea@parhasard.net> * hash-table.el (hash-table-key-list, hash-table-value-list) (hash-table-key-value-alist, hash-table-key-value-plist): Remove some useless #'nreverse calls in these files; our hash tables have no order, it's not helpful to pretend they do. * behavior.el (read-behavior): Do the same in this file, in some code evidently copied from hash-table.el. 2010-09-16 Aidan Kehoe <kehoea@parhasard.net> * info.el (Info-insert-dir): * format.el (format-deannotate-region): * files.el (cd, save-buffers-kill-emacs): Use #'some, #'every and related functions for applying boolean operations to lists, instead of rolling our own ones that cons and don't short-circuit. 2010-09-16 Aidan Kehoe <kehoea@parhasard.net> * bytecomp.el (byte-compile-initial-macro-environment): * cl-macs.el (the): Rephrase the docstring, make its implementation when compiling files a little nicer. 2010-09-16 Aidan Kehoe <kehoea@parhasard.net> * descr-text.el (unidata-initialize-unicodedata-database) (unidata-initialize-unihan-database, describe-char-unicode-data) (describe-char-unicode-data): Wrap calls to the database functions with (with-fboundp ...), avoiding byte compile warnings on builds without support for the database functions. (describe-char): (reduce #'max ...), not (apply #'max ...), no need to cons needlessly. (describe-char): Remove a redundant lambda wrapping #'extent-properties. (describe-char-unicode-data): Call #'nsubst when replacing "" with nil in the result of #'split-string, instead of consing inside mapcar. 2010-09-16 Aidan Kehoe <kehoea@parhasard.net> * x-faces.el (x-available-font-sizes): * specifier.el (let-specifier): * package-ui.el (pui-add-required-packages): * msw-faces.el (mswindows-available-font-sizes): * modeline.el (modeline-minor-mode-menu): * minibuf.el (minibuf-directory-files): Replace the O2N (delq nil (mapcar (lambda (W) (and X Y)) Z)) with the ON (mapcan (lambda (W) (and X (list Y))) Z) in these files. 2010-09-16 Aidan Kehoe <kehoea@parhasard.net> * cl-macs.el (= < > <= >=): When these functions are handed more than two arguments, and those arguments have no side effects, transform to a series of two argument calls, avoiding funcall in the byte-compiled code. * mule/mule-cmds.el (finish-set-language-environment): Take advantage of this change in a function called 256 times at startup. 2010-09-16 Aidan Kehoe <kehoea@parhasard.net> * bytecomp.el (byte-compile-function-form, byte-compile-quote) (byte-compile-quote-form): Warn at compile time, and error at runtime, if a (quote ...) or a (function ...) form attempts to quote more than one object. 2010-09-16 Aidan Kehoe <kehoea@parhasard.net> * byte-optimize.el (byte-optimize-apply): Transform (apply 'nconc (mapcar ...)) to (mapcan ...); warn about use of the first idiom. * update-elc.el (do-autoload-commands): * packages.el (packages-find-package-library-path): * frame.el (frame-list): * extents.el (extent-descendants): * etags.el (buffer-tag-table-files): * dumped-lisp.el (preloaded-file-list): * device.el (device-list): * bytecomp-runtime.el (proclaim-inline, proclaim-notinline) Use #'mapcan, not (apply #'nconc (mapcar ...) in all these files. * bytecomp-runtime.el (eval-when-compile, eval-and-compile): In passing, mention that these macros also evaluate the body when interpreted. tests/ChangeLog addition: 2011-02-07 Aidan Kehoe <kehoea@parhasard.net> * automated/lisp-tests.el: Test lexical scope for `block', `return-from'; add a Known-Bug-Expect-Failure for a contorted example that fails when byte-compiled.
author Aidan Kehoe <kehoea@parhasard.net>
date Mon, 07 Feb 2011 12:01:24 +0000
parents 6f2158fa75ed
children 308d34e9f07d
line wrap: on
line source

/* Routines to compute the current syntactic context, for font-lock mode.
   Copyright (C) 1992, 1993, 1994 Free Software Foundation, Inc.
   Copyright (C) 1995 Sun Microsystems, Inc.
   Copyright (C) 2002, 2003, 2010 Ben Wing.

This file is part of XEmacs.

XEmacs is free software; you can redistribute it and/or modify it
under the terms of the GNU General Public License as published by the
Free Software Foundation; either version 2, or (at your option) any
later version.

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

You should have received a copy of the GNU General Public License
along with XEmacs; see the file COPYING.  If not, write to
the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
Boston, MA 02111-1307, USA.  */

/* Synched up with: Not in FSF. */

/* This code computes the syntactic context of the current point, that is,
   whether point is within a comment, a string, what have you.  It does
   this by picking a point "known" to be outside of any syntactic constructs
   and moving forward, examining the syntax of each character.

   Two caches are used: one caches the last point computed, and the other
   caches the last point at the beginning of a line.  This makes there
   be little penalty for moving left-to-right on a line a character at a
   time; makes starting over on a line be cheap; and makes random-accessing
   within a line relatively cheap.

   When we move to a different line farther down in the file (but within the
   current top-level form) we simply continue computing forward.  If we move
   backward more than a line, or move beyond the end of the current tlf, or
   switch buffers, then we call `beginning-of-defun' and start over from
   there.

   #### We should really rewrite this to keep extents over the buffer
   that hold the current syntactic information.  This would be a big win.
   This way there would be no guessing or incorrect results.
 */

#include <config.h>

#ifdef USE_C_FONT_LOCK

#include "lisp.h"

#include "buffer.h"
#include "insdel.h"
#include "syntax.h"

Lisp_Object Qcomment;
Lisp_Object Qblock_comment;
Lisp_Object Qbeginning_of_defun;

enum syntactic_context
{
  context_none,
  context_string,
  context_comment,
  context_block_comment,
  context_generic_comment,
  context_generic_string
};

enum block_comment_context
{
  ccontext_none,
  ccontext_start1,
  ccontext_start2,
  ccontext_end1
};

enum comment_style
{
  comment_style_none,
  comment_style_a,
  comment_style_b
};

struct context_cache
{
  Charbpos start_point;			/* beginning of defun */
  Charbpos cur_point;			/* cache location */
  Charbpos end_point;			/* end of defun */
  struct buffer *buffer;		/* does this need to be staticpro'd? */
  enum syntactic_context context;	/* single-char-syntax state */
  enum block_comment_context ccontext;	/* block-comment state */
  enum comment_style style;		/* which comment group */
  Ichar scontext;			/* active string delimiter */
  int depth;				/* depth in parens */
  int backslash_p;			/* just read a backslash */
  int needs_its_head_reexamined;	/* we're apparently outside of
					   a top level form, and far away
					   from it.  This is a bad situation
					   because it will lead to constant
					   slowness as we keep going way
					   back to that form and moving
					   forward again.  In this case,
					   we try to compute a "pseudo-
					   top-level-form" where the
					   depth is 0 and the context
					   is none at both ends. */
};

/* We have two caches; one for the current point and one for
   the beginning of line.  We used to rely on the caller to
   tell us when to invalidate them, but now we do it ourselves;
   it lets us be smarter. */

static struct context_cache context_cache;

static struct context_cache bol_context_cache;

int font_lock_debug;

#define reset_context_cache(cc) memset (cc, 0, sizeof (struct context_cache))

/* This function is called from signal_after_change() to tell us when
   textual changes are made so we can flush our caches when necessary.

   We make the following somewhat heuristic assumptions:

     (remember that current_point is always >= start_point, but may be
     less than or greater than end_point (we might not be inside any
     top-level form)).

   1) Textual changes before the beginning of the current top-level form
      don't affect anything; all we need to do is offset the caches
      appropriately.
   2) Textual changes right at the beginning of the current
      top-level form messes things up and requires that we flush
      the caches.
   3) Textual changes after the beginning of the current top-level form
      and before one or both or the caches invalidates the corresponding
      cache(s).
   4) Textual changes after the caches and before the end of the
      current top-level form don't affect anything; all we need to do is
      offset the caches appropriately.
   5) Textual changes right at the end of the current top-level form
      necessitate recomputing that end value.
   6) Textual changes after the end of the current top-level form
      are ignored. */


void
font_lock_maybe_update_syntactic_caches (struct buffer *buf, Charbpos start,
					 Charbpos orig_end, Charbpos new_end)
{
  /* Note: either both context_cache and bol_context_cache are valid and
     point to the same buffer, or both are invalid.  If we have to
     invalidate just context_cache, we recopy it from bol_context_cache.
   */
  if (context_cache.buffer != buf)
    /* caches don't apply */
    return;
  /* NOTE: The order of the if statements below is important.  If you
     change them around unthinkingly, you will probably break something. */
  if (orig_end <= context_cache.start_point - 1)
    {
      /* case 1: before the beginning of the current top-level form */
      Charcount diff = new_end - orig_end;
      if (font_lock_debug)
	stderr_out ("font-lock; Case 1\n");
      context_cache.start_point += diff;
      context_cache.cur_point += diff;
      context_cache.end_point += diff;
      bol_context_cache.start_point += diff;
        bol_context_cache.cur_point += diff;
      bol_context_cache.end_point += diff;
    }
  else if (start <= context_cache.start_point)
    {
      if (font_lock_debug)
	stderr_out ("font-lock; Case 2\n");
      /* case 2: right at the current top-level form (paren that starts
	 top level form got deleted or moved away from the newline it
	 was touching) */
      reset_context_cache (&context_cache);
      reset_context_cache (&bol_context_cache);
    }
  /* OK, now we know that the start is after the beginning of the
     current top-level form. */
  else if (start < bol_context_cache.cur_point)
    {
      if (font_lock_debug)
	stderr_out ("font-lock; Case 3 (1)\n");
      /* case 3: after the beginning of the current top-level form
	 and before both of the caches */
      reset_context_cache (&context_cache);
      reset_context_cache (&bol_context_cache);
    }
  else if (start < context_cache.cur_point)
    {
      if (font_lock_debug)
	stderr_out ("font-lock; Case 3 (2)\n");
      /* case 3: but only need to invalidate one cache */
      context_cache = bol_context_cache;
    }
  /* OK, now we know that the start is after the caches. */
  else if (start >= context_cache.end_point)
    {
      if (font_lock_debug)
	stderr_out ("font-lock; Case 6\n");
      /* case 6: after the end of the current top-level form
         and after the caches. */
    }
  else if (orig_end <= context_cache.end_point - 2)
    {
      /* case 4: after the caches and before the end of the
	 current top-level form */
      Charcount diff = new_end - orig_end;
      if (font_lock_debug)
	stderr_out ("font-lock; Case 4\n");
      context_cache.end_point += diff;
      bol_context_cache.end_point += diff;
    }
  else
    {
      if (font_lock_debug)
	stderr_out ("font-lock; Case 5\n");
      /* case 5: right at the end of the current top-level form */
      context_cache.end_point = context_cache.start_point - 1;
      bol_context_cache.end_point = context_cache.start_point - 1;
    }
}

/* This function is called from Fkill_buffer(). */

void
font_lock_buffer_was_killed (struct buffer *buf)
{
  if (context_cache.buffer == buf)
    {
      reset_context_cache (&context_cache);
      reset_context_cache (&bol_context_cache);
    }
}

static Charbpos
beginning_of_defun (struct buffer *buf, Charbpos pt)
{
  /* This function can GC */
  Charbpos opt = BUF_PT (buf);
  if (pt == BUF_BEGV (buf))
    return pt;
  BUF_SET_PT (buf, pt);
  /* There used to be some kludginess to call c++-beginning-of-defun
     if we're in C++ mode.  There's no point in this any more;
     we're using cc-mode.  If you really want to get the old c++
     mode working, fix it rather than the C code. */
  call0_in_buffer (buf, Qbeginning_of_defun);
  pt = BUF_PT (buf);
  BUF_SET_PT (buf, opt);
  return pt;
}

static Charbpos
end_of_defun (struct buffer *buf, Charbpos pt)
{
  Lisp_Object retval = scan_lists (buf, pt, 1, 0, 0, 1);
  if (NILP (retval))
    return BUF_ZV (buf);
  else
    return XINT (retval);
}

/* Set up context_cache for attempting to determine the syntactic context
   in buffer BUF at point PT. */

static void
setup_context_cache (struct buffer *buf, Charbpos pt)
{
  int recomputed_start_point = 0;
  /* This function can GC */
  if (context_cache.buffer != buf || pt < context_cache.start_point)
    {
    start_over:
      if (font_lock_debug)
	stderr_out ("reset context cache\n");
      /* OK, completely invalid. */
      reset_context_cache (&context_cache);
      reset_context_cache (&bol_context_cache);
    }
  if (!context_cache.buffer)
    {
      /* Need to recompute the start point. */
      if (font_lock_debug)
	stderr_out ("recompute start\n");
      context_cache.start_point = beginning_of_defun (buf, pt);
      recomputed_start_point = 1;
      bol_context_cache.start_point = context_cache.start_point;
      bol_context_cache.buffer = context_cache.buffer = buf;
    }
  if (context_cache.end_point < context_cache.start_point)
    {
      /* Need to recompute the end point. */
      if (font_lock_debug)
	stderr_out ("recompute end\n");
      context_cache.end_point = end_of_defun (buf, context_cache.start_point);
      bol_context_cache.end_point = context_cache.end_point;
    }
  if (bol_context_cache.cur_point == 0 ||
      pt < bol_context_cache.cur_point)
    {
      if (font_lock_debug)
	stderr_out ("reset to start\n");
      if (pt > context_cache.end_point
	  /* 3000 is some arbitrary delta but seems reasonable;
	     about the size of a reasonable function */
	  && pt - context_cache.end_point > 3000)
	/* If we're far past the end of the top level form,
	   don't trust it; recompute it. */
	{
	  /* But don't get in an infinite loop doing this.
	     If we're really far past the end of the top level
	     form, try to compute a pseudo-top-level form. */
	  if (recomputed_start_point)
	    context_cache.needs_its_head_reexamined = 1;
	  else
	    /* force recomputation */
	    goto start_over;
	}
      /* Go to the nearest end of the top-level form that's before
	 us. */
      if (pt > context_cache.end_point)
	pt = context_cache.end_point;
      else
	pt = context_cache.start_point;
      /* Reset current point to start of buffer. */
      context_cache.cur_point = pt;
      context_cache.context = context_none;
      context_cache.ccontext = ccontext_none;
      context_cache.style = comment_style_none;
      context_cache.scontext = '\000';
      context_cache.depth = 0;
      /* #### shouldn't this be checking the character's syntax instead of
         explicitly testing for backslash characters? */
      context_cache.backslash_p = ((pt > 1) &&
				   (BUF_FETCH_CHAR (buf, pt - 1) == '\\'));
      /* Note that the BOL context cache may not be at the beginning
	 of the line, but that should be OK, nobody's checking. */
      bol_context_cache = context_cache;
      return;
    }
  else if (pt < context_cache.cur_point)
    {
      if (font_lock_debug)
	stderr_out ("reset to bol\n");
      /* bol cache is OK but current_cache is not. */
      context_cache = bol_context_cache;
      return;
    }
  else if (pt <= context_cache.end_point)
    {
      if (font_lock_debug)
	stderr_out ("everything is OK\n");
      /* in same top-level form. */
      return;
    }
  {
    /* OK, we're past the end of the top-level form. */
    Charbpos maxpt = max (context_cache.end_point, context_cache.cur_point);
#if 0
    int shortage;
#endif

    if (font_lock_debug)
      stderr_out ("past end\n");
    if (pt <= maxpt)
      /* OK, fine. */
      return;
#if 0
    /* This appears to cause huge slowdowns in files which have no
       top-level forms.

       In any case, it's not really necessary that we know for
       sure the top-level form we're in; if we're in a form
       but the form we have recorded is the previous one,
       it will be OK. */

    scan_buffer (buf, '\n', maxpt, pt, 1, &shortage, 1);
    if (!shortage)
      /* If there was a newline in the region past the known universe,
	 we might be inside another top-level form, so start over.
	 Otherwise, we're outside of any top-level forms and we know
	 the one directly before us, so it's OK. */
      goto start_over;
#endif
  }
}

/* You'd think it wouldn't be necessary to cast something to the type
   it's already defined is, but if you're GCC, you apparently think
   differently */
#define SYNTAX_START_STYLE(c1, c2)					\
 ((enum comment_style)							\
  (SYNTAX_CODES_MATCH_START_P (c1, c2, SYNTAX_COMMENT_STYLE_A) ?	\
   comment_style_a :							\
   SYNTAX_CODES_MATCH_START_P (c1, c2, SYNTAX_COMMENT_STYLE_B) ?	\
   comment_style_b :							\
   comment_style_none))

#define SYNTAX_END_STYLE(c1, c2)				\
  ((enum comment_style)						\
   (SYNTAX_CODES_MATCH_END_P (c1, c2, SYNTAX_COMMENT_STYLE_A) ?	\
   comment_style_a :						\
   SYNTAX_CODES_MATCH_END_P (c1, c2, SYNTAX_COMMENT_STYLE_B) ?	\
   comment_style_b :						\
   comment_style_none))

#define SINGLE_SYNTAX_STYLE(c)						\
      ((enum comment_style)						\
       (SYNTAX_CODE_MATCHES_1CHAR_P (c, SYNTAX_COMMENT_STYLE_A) ?	\
       comment_style_a :						\
       SYNTAX_CODE_MATCHES_1CHAR_P (c, SYNTAX_COMMENT_STYLE_B) ?	\
       comment_style_b :						\
       comment_style_none))

/* Set up context_cache for position PT in BUF. */

static void
find_context (struct buffer *buf, Charbpos pt)
{
  /* This function can GC */
  Ichar prev_c, c;
  int prev_syncode, syncode;
  Charbpos target = pt;
  struct syntax_cache *scache;
  int spec = specpdl_depth ();

  /* If we are narrowed, we will get confused.  In fact, we are quite often
     narrowed when this function is called. */
  if (BUF_BEGV (buf) != BUF_BEG (buf) || BUF_ZV (buf) != BUF_Z (buf))
    {
      record_unwind_protect (save_restriction_restore,
			     save_restriction_save (buf));
      Fwiden (wrap_buffer (buf));
    }
  
  setup_context_cache (buf, pt);
  pt = context_cache.cur_point;

  scache = setup_buffer_syntax_cache (buf, pt > BUF_BEGV (buf) ? pt - 1 : pt,
				      1);
  if (pt > BUF_BEGV (buf))
    {
      c = BUF_FETCH_CHAR (buf, pt - 1);
      syncode = SYNTAX_CODE_FROM_CACHE (scache, c);
    }
  else
    {
      c = '\n'; /* to get bol_context_cache at point-min */
      syncode = Swhitespace;
    }

  for (; pt < target; pt++, context_cache.cur_point = pt)
    {
      if (context_cache.needs_its_head_reexamined)
	{
	  if (context_cache.depth == 0
	      && context_cache.context == context_none)
	    {
	      /* We've found an anchor spot.
		 Try to put the start of defun within 6000 chars of
		 the target, and the end of defun as close as possible.
		 6000 is also arbitrary but tries to strike a balance
		 between two conflicting pulls when dealing with a
		 file that has lots of stuff sitting outside of a top-
		 level form:

		 a) If you move past the start of defun, you will
		    have to recompute defun, which in this case
		    means that start of defun goes all the way back
		    to the beginning of the file; so you want
		    to set start of defun a ways back from the
		    current point.
		 b) If you move a line backwards but within start of
		    defun, you have to move back to start of defun;
		    so you don't want start of defun too far from
		    the current point.
		 */
	      if (target - context_cache.start_point > 6000)
		context_cache.start_point = pt;
	      context_cache.end_point = pt;
	      bol_context_cache = context_cache;
	    }
	}

      UPDATE_SYNTAX_CACHE_FORWARD (scache, pt);
      prev_c = c;
      prev_syncode = syncode;
      c = BUF_FETCH_CHAR (buf, pt);
      syncode = SYNTAX_CODE_FROM_CACHE (scache, c);

      if (prev_c == '\n')
	bol_context_cache = context_cache;

      if (context_cache.backslash_p)
	{
	  context_cache.backslash_p = 0;
	  continue;
	}

      switch (SYNTAX_FROM_CODE (syncode))
	{
	case Sescape:
	  context_cache.backslash_p = 1;
	  break;

	case Sopen:
	  if (context_cache.context == context_none)
	    context_cache.depth++;
	  break;

	case Sclose:
	  if (context_cache.context == context_none)
	    context_cache.depth--;
	  break;

	case Scomment:
	  if (context_cache.context == context_none)
	    {
	      context_cache.context = context_comment;
	      context_cache.ccontext = ccontext_none;
	      context_cache.style = SINGLE_SYNTAX_STYLE (syncode);
	      assert (context_cache.style != comment_style_none);
	    }
	  break;

	case Sendcomment:
	  if (context_cache.style != SINGLE_SYNTAX_STYLE (syncode))
	    ;
	  else if (context_cache.context == context_comment)
	    {
	      context_cache.context = context_none;
	      context_cache.style = comment_style_none;
	    }
	  else if (context_cache.context == context_block_comment &&
		   (context_cache.ccontext == ccontext_start2 ||
		    context_cache.ccontext == ccontext_end1))
	    {
	      context_cache.context = context_none;
	      context_cache.ccontext = ccontext_none;
	      context_cache.style = comment_style_none;
	    }
	  break;

	case Sstring:
          {
            if (context_cache.context == context_string &&
                context_cache.scontext == c)
	      {
		context_cache.context = context_none;
		context_cache.scontext = '\000';
	      }
            else if (context_cache.context == context_none)
	      {
		Lisp_Object stringtermobj =
		  syntax_match (scache->syntax_table, c);
		Ichar stringterm;

		if (CHARP (stringtermobj))
		  stringterm = XCHAR (stringtermobj);
		else
		  stringterm = c;
		context_cache.context = context_string;
		context_cache.scontext = stringterm;
		context_cache.ccontext = ccontext_none;
	      }
            break;
          }

	case Scomment_fence:
	  {
	    if (context_cache.context == context_generic_comment)
	      {
		context_cache.context = context_none;
	      }
	    else if (context_cache.context == context_none)
	      {
		context_cache.context = context_generic_comment;
		context_cache.ccontext = ccontext_none;
	      }
	    break;
	  }

	case Sstring_fence:
	  {
	    if (context_cache.context == context_generic_string)
	      {
		context_cache.context = context_none;
	      }
	    else if (context_cache.context == context_none)
	      {
		context_cache.context = context_generic_string;
		context_cache.ccontext = ccontext_none;
	      }
	    break;
	  }

	default:
	  ;
	}

      /* That takes care of the characters with manifest syntax.
	 Now we've got to hack multi-char sequences that start
	 and end block comments.
       */
      if ((SYNTAX_CODE_COMMENT_BITS (syncode) &
	   SYNTAX_SECOND_CHAR_START) &&
	  context_cache.context == context_none &&
	  context_cache.ccontext == ccontext_start1 &&
	  SYNTAX_CODES_START_P (prev_syncode, syncode) /* the two chars match */
	  )
	{
	  context_cache.ccontext = ccontext_start2;
	  context_cache.style = SYNTAX_START_STYLE (prev_syncode, syncode);
	  assert (context_cache.style != comment_style_none);
	}
      else if ((SYNTAX_CODE_COMMENT_BITS (syncode) &
		SYNTAX_FIRST_CHAR_START) &&
	       context_cache.context == context_none &&
	       (context_cache.ccontext == ccontext_none ||
		context_cache.ccontext == ccontext_start1))
	{
	  context_cache.ccontext = ccontext_start1;
	  context_cache.style = comment_style_none; /* should be this already*/
	}
      else if ((SYNTAX_CODE_COMMENT_BITS (syncode) &
		SYNTAX_SECOND_CHAR_END) &&
	       context_cache.context ==
	       (enum syntactic_context) context_block_comment &&
	       context_cache.ccontext ==
	       (enum block_comment_context) ccontext_end1 &&
	       SYNTAX_CODES_END_P (prev_syncode, syncode) &&
	       /* the two chars match */
	       context_cache.style ==
	       SYNTAX_END_STYLE (prev_syncode, syncode)
	       )
	{
	  context_cache.context = context_none;
	  context_cache.ccontext = ccontext_none;
	  context_cache.style = comment_style_none;
	}
      else if ((SYNTAX_CODE_COMMENT_BITS (syncode) &
		SYNTAX_FIRST_CHAR_END) &&
	       context_cache.context == context_block_comment &&
	       context_cache.style == SINGLE_SYNTAX_STYLE (syncode) &&
	       (context_cache.ccontext == ccontext_start2 ||
		context_cache.ccontext == ccontext_end1))
	/* #### is it right to check for end1 here?? 
	   yes, because this might be a repetition of the first char
	   of a comment-end sequence. ie, '/xxx foo xxx/' or
	   '/xxx foo x/', where 'x' = '*' -- mct */
	{
	  assert (context_cache.style != comment_style_none);
	  context_cache.ccontext = ccontext_end1;
	}

      else if (context_cache.ccontext == ccontext_start1)
	{
	  assert (context_cache.context == context_none);
	  context_cache.ccontext = ccontext_none;
	}
      else if (context_cache.ccontext == ccontext_end1)
	{
	  assert (context_cache.context == context_block_comment);
	  context_cache.context = context_none;
	  context_cache.ccontext = ccontext_start2;
	}

      if (context_cache.ccontext == ccontext_start2 &&
	  context_cache.context == context_none)
	{
	  context_cache.context = context_block_comment;
	  assert (context_cache.style != comment_style_none);
	}
      else if (context_cache.ccontext == ccontext_none &&
	       context_cache.context == context_block_comment)
	{
	  context_cache.context = context_none;
	}
    }

  context_cache.needs_its_head_reexamined = 0;
  unbind_to (spec);
}

static Lisp_Object
context_to_symbol (enum syntactic_context context)
{
  switch (context)
    {
    case context_none:			return Qnil;
    case context_string:		return Qstring;
    case context_comment:		return Qcomment;
    case context_block_comment:		return Qblock_comment;
    case context_generic_comment:	return Qblock_comment;
    case context_generic_string:	return Qstring;
    default: ABORT (); return Qnil; /* suppress compiler warning */
    }
}

DEFUN ("buffer-syntactic-context", Fbuffer_syntactic_context, 0, 1, 0, /*
Return the syntactic context of BUFFER at point.
If BUFFER is nil or omitted, the current buffer is assumed.
The returned value is one of the following symbols:

	nil		; meaning no special interpretation
	string		; meaning point is within a string
	comment		; meaning point is within a line comment
	block-comment	; meaning point is within a block comment

See also the function `buffer-syntactic-context-depth', which returns
the current nesting-depth within all parenthesis-syntax delimiters
and the function `syntactically-sectionize', which will map a function
over each syntactic context in a region.

WARNING: this may alter match-data.
*/
       (buffer))
{
  /* This function can GC */
  struct buffer *buf = decode_buffer (buffer, 0);
  find_context (buf, BUF_PT (buf));
  return context_to_symbol (context_cache.context);
}

DEFUN ("buffer-syntactic-context-depth", Fbuffer_syntactic_context_depth,
       0, 1, 0, /*
Return the depth within all parenthesis-syntax delimiters at point.
If BUFFER is nil or omitted, the current buffer is assumed.
WARNING: this may alter match-data.
*/
       (buffer))
{
  /* This function can GC */
  struct buffer *buf = decode_buffer (buffer, 0);
  find_context (buf, BUF_PT (buf));
  return make_int (context_cache.depth);
}


DEFUN ("syntactically-sectionize", Fsyntactically_sectionize, 3, 4, 0, /*
Call FUNCTION for each contiguous syntactic context in the region.
Call the given function with four arguments: the start and end of the
region, a symbol representing the syntactic context, and the current
depth (as returned by the functions `buffer-syntactic-context' and
`buffer-syntactic-context-depth').  When this function is called, the
current buffer will be set to BUFFER.

WARNING: this may alter match-data.
*/
       (function, start, end, buffer))
{
  /* This function can GC */
  Charbpos s, pt, e;
  int edepth;
  enum syntactic_context this_context;
  Lisp_Object extent = Qnil;
  struct gcpro gcpro1;
  struct buffer *buf = decode_buffer (buffer, 0);

  get_buffer_range_char (buf, start, end, &s, &e, 0);

  pt = s;
  find_context (buf, pt);

  GCPRO1 (extent);
  while (pt < e)
    {
      Charbpos estart, eend;
      /* skip over "blank" areas, and bug out at end-of-buffer. */
      while (context_cache.context == context_none)
	{
	  pt++;
	  if (pt >= e) goto DONE_LABEL;
	  find_context (buf, pt);
	}
      /* We've found a non-blank area; keep going until we reach its end */
      this_context = context_cache.context;
      estart = pt;

      /* Minor kludge: consider the comment-start character(s) a part of
	 the comment.
       */
      if (this_context == context_block_comment &&
	  context_cache.ccontext == ccontext_start2)
	estart -= 2;
      else if (this_context == context_comment
	       || this_context == context_generic_comment
	       )
	estart -= 1;

      edepth = context_cache.depth;
      while (context_cache.context == this_context && pt < e)
	{
	  pt++;
	  find_context (buf, pt);
	}

      eend = pt;

      /* Minor kludge: consider the character which terminated the comment
	 a part of the comment.
       */
      if ((this_context == context_block_comment ||
	   this_context == context_comment
	   || this_context == context_generic_comment
	   )
	  && pt < e)
	eend++;

      if (estart == eend)
	continue;
      /* Make sure not to pass in values that are outside the
	 actual bounds of this function. */
      call4_in_buffer (buf, function, make_int (max (s, estart)),
		       make_int (eend == e ? e : eend - 1),
		       context_to_symbol (this_context),
		       make_int (edepth));
    }
 DONE_LABEL:
  UNGCPRO;
  return Qnil;
}

void
syms_of_font_lock (void)
{
  DEFSYMBOL (Qcomment);
  DEFSYMBOL (Qblock_comment);
  DEFSYMBOL (Qbeginning_of_defun);

  DEFSUBR (Fbuffer_syntactic_context);
  DEFSUBR (Fbuffer_syntactic_context_depth);
  DEFSUBR (Fsyntactically_sectionize);
}

void
reinit_vars_of_font_lock (void)
{
  xzero (context_cache);
  xzero (bol_context_cache);
}

void
vars_of_font_lock (void)
{
}

#endif /* USE_C_FONT_LOCK */