view src/font-lock.c @ 2367:ecf1ebac70d8

[xemacs-hg @ 2004-11-04 23:05:23 by ben] commit mega-patch configure.in: Turn off -Winline and -Wchar-subscripts. Use the right set of cflags when compiling modules. Rewrite ldap configuration to separate the inclusion of lber (needed in recent Cygwin) from the basic checks for the needed libraries. add a function for MAKE_JUNK_C; initially code was added to generate xemacs.def using this, but it will need to be rewritten. add an rm -f for junk.c to avoid weird Cygwin bug with cp -f onto an existing file. Sort list of auto-detected functions and eliminate unused checks for stpcpy, setlocale and getwd. Add autodetection of Cygwin scanf problems BETA: Rewrite section on configure to indicate what flags are important and what not. digest-doc.c, make-dump-id.c, profile.c, sorted-doc.c: Add proper decls for main(). make-msgfile.c: Document that this is old junk. Move proposal to text.c. make-msgfile.lex: Move proposal to text.c. make-mswin-unicode.pl: Convert error-generating code so that the entire message will be seen as a single unrecognized token. mule/mule-ccl.el: Update docs. lispref/mule.texi: Update CCL docs. ldap/eldap.c: Mule-ize. Use EXTERNAL_LIST_LOOP_2 instead of deleted EXTERNAL_LIST_LOOP. * XEmacs 21.5.18 "chestnut" is released. --------------------------------------------------------------- MULE-RELATED WORK: --------------------------------------------------------------- --------------------------- byte-char conversion --------------------------- buffer.c, buffer.h, insdel.c, text.c: Port FSF algorithm for byte-char conversion, replacing broken previous version. Track the char position of the gap. Add functions to do char-byte conversion downwards as well as upwards. Move comments about algorithm workings to internals manual. --------------------------- work on types --------------------------- alloc.c, console-x-impl.h, dump-data.c, dump-data.h, dumper.c, dialog-msw.c, dired-msw.c, doc.c, editfns.c, esd.c, event-gtk.h, event-msw.c, events.c, file-coding.c, file-coding.h, fns.c, glyphs-eimage.c, glyphs-gtk.c, glyphs-msw.c, glyphs-shared.c, glyphs-x.c, glyphs.c, glyphs.h, gui.c, hpplay.c, imgproc.c, intl-win32.c, lrecord.h, lstream.c, keymap.c, lisp.h, libsst.c, linuxplay.c, miscplay.c, miscplay.h, mule-coding.c, nas.c, nt.c, ntheap.c, ntplay.c, objects-msw.c, objects-tty.c, objects-x.c, print.c, process-nt.c, process.c, redisplay.h, select-common.h, select-gtk.c, select-x.c, sgiplay.c, sound.c, sound.h, sunplay.c, sysfile.h, sysdep.c, syswindows.h, text.c, unexnt.c, win32.c, xgccache.c: Further work on types. This creates a full set of types for all the basic semantics of `char' that I have so far identified, so that its semantics can always be identified for the purposes of proper Mule-safe code, and the raw use of `char' always avoided. (1) More type renaming, for consistency of naming. Char_ASCII -> Ascbyte UChar_ASCII -> UAscbyte Char_Binary -> CBinbyte UChar_Binary -> Binbyte SChar_Binary -> SBinbyte (2) Introduce Rawbyte, CRawbyte, Boolbyte, Chbyte, UChbyte, and Bitbyte and use them. (3) New types Itext, Wexttext and Textcount for separating out the concepts of bytes and textual units (different under UTF-16 and UTF-32, which are potential internal encodings). (4) qxestr*_c -> qxestr*_ascii. lisp.h: New; goes with other qxe() functions. #### Maybe goes in a different section. lisp.h: Group generic int-type defs together with EMACS_INT defs. lisp.h: * lisp.h (WEXTTEXT_IS_WIDE) New defns. lisp.h: New type to replace places where int occurs as a boolean. It's signed because occasionally people may want to use -1 as an error value, and because unsigned ints are viral -- see comments in the internals manual against using them. dynarr.c: int -> Bytecount. --------------------------- Mule-izing --------------------------- device-x.c: Partially Mule-ize. dumper.c, dumper.h: Mule-ize. Use Rawbyte. Use stderr_out not printf. Use wext_*(). sysdep.c, syswindows.h, text.c: New Wexttext API for manipulation of external text that may be Unicode (e.g. startup code under Windows). emacs.c: Mule-ize. Properly deal with argv in external encoding. Use wext_*() and Wexttext. Use Rawbyte. #if 0 some old junk on SCO that is unlikely to be correct. Rewrite allocation code in run-temacs. emacs.c, symsinit.h, win32.c: Rename win32 init function and call it even earlier, to initialize mswindows_9x_p even earlier, for use in startup code (XEUNICODE_P). process.c: Use _wenviron not environ under Windows, to get Unicode environment variables. event-Xt.c: Mule-ize drag-n-drop related stuff. dragdrop.c, dragdrop.h, frame-x.c: Mule-ize. text.h: Add some more stand-in defines for particular kinds of conversion; use in Mule-ization work in frame-x.c etc. --------------------------- Freshening --------------------------- intl-auto-encap-win32.c, intl-auto-encap-win32.h: Regenerate. --------------------------- Unicode-work --------------------------- intl-win32.c, syswindows.h: Factor out common options to MultiByteToWideChar and WideCharToMultiByte. Add convert_unicode_to_multibyte_malloc() and convert_unicode_to_multibyte_dynarr() and use. Add stuff for alloca() conversion of multibyte/unicode. alloc.c: Use dfc_external_data_len() in case of unicode coding system. alloc.c, mule-charset.c: Don't zero out and reinit charset Unicode tables. This fucks up dump-time loading. Anyway, either we load them at dump time or run time, never both. unicode.c: Dump the blank tables as well. --------------------------------------------------------------- DOCUMENTATION, MOSTLY MULE-RELATED: --------------------------------------------------------------- EmacsFrame.c, emodules.c, event-Xt.c, fileio.c, input-method-xlib.c, mule-wnnfns.c, redisplay-gtk.c, redisplay-tty.c, redisplay-x.c, regex.c, sysdep.c: Add comment about Mule work needed. text.h: Add more documentation describing why DFC routines were not written to return their value. Add some other DFC documentation. console-msw.c, console-msw.h: Add pointer to docs in win32.c. emacs.c: Add comments on sources of doc info. text.c, charset.h, unicode.c, intl-win32.c, intl-encap-win32.c, text.h, file-coding.c, mule-coding.c: Collect background comments and related to text matters and internationalization, and proposals for work to be done, in text.c or Internals manual, stuff related to specific textual API's in text.h, and stuff related to internal implementation of Unicode conversion in unicode.c. Put lots of pointers to the comments to make them easier to find. s/mingw32.h, s/win32-common.h, s/win32-native.h, s/windowsnt.h, win32.c: Add bunches of new documentation on the different kinds of builds and environments under Windows and how they work. Collect this info in win32.c. Add pointers to these docs in the relevant s/* files. emacs.c: Document places with long comments. Remove comment about exiting, move to internals manual, put in pointer. event-stream.c: Move docs about event queues and focus to internals manual, put in pointer. events.h: Move docs about event stream callbacks to internals manual, put in pointer. profile.c, redisplay.c, signal.c: Move documentation to the Internals manual. process-nt.c: Add pointer to comment in win32-native.el. lisp.h: Add comments about some comment conventions. lisp.h: Add comment about the second argument. device-msw.c, redisplay-msw.c: @@#### comments are out-of-date. --------------------------------------------------------------- PDUMP WORK (MOTIVATED BY UNICODE CHANGES) --------------------------------------------------------------- alloc.c, buffer.c, bytecode.c, console-impl.h, console.c, device.c, dumper.c, lrecord.h, elhash.c, emodules.h, events.c, extents.c, frame.c, glyphs.c, glyphs.h, mule-charset.c, mule-coding.c, objects.c, profile.c, rangetab.c, redisplay.c, specifier.c, specifier.h, window.c, lstream.c, file-coding.h, file-coding.c: PDUMP: Properly implement dump_add_root_block(), which never worked before, and is necessary for dumping Unicode tables. Pdump name changes for accuracy: XD_STRUCT_PTR -> XD_BLOCK_PTR. XD_STRUCT_ARRAY -> XD_BLOCK_ARRAY. XD_C_STRING -> XD_ASCII_STRING. *_structure_* -> *_block_*. lrecord.h: some comments added about dump_add_root_block() vs dump_add_root_block_ptr(). extents.c: remove incorrect comment about pdump problems with gap array. --------------------------------------------------------------- ALLOCATION --------------------------------------------------------------- abbrev.c, alloc.c, bytecode.c, casefiddle.c, device-msw.c, device-x.c, dired-msw.c, doc.c, doprnt.c, dragdrop.c, editfns.c, emodules.c, file-coding.c, fileio.c, filelock.c, fns.c, glyphs-eimage.c, glyphs-gtk.c, glyphs-msw.c, glyphs-x.c, gui-msw.c, gui-x.c, imgproc.c, intl-win32.c, lread.c, menubar-gtk.c, menubar.c, nt.c, objects-msw.c, objects-x.c, print.c, process-nt.c, process-unix.c, process.c, realpath.c, redisplay.c, search.c, select-common.c, symbols.c, sysdep.c, syswindows.h, text.c, text.h, ui-byhand.c: New macros {alloca,xnew}_{itext,{i,ext,raw,bin,asc}bytes} for more convenient allocation of these commonly requested items. Modify functions to use alloca_ibytes, alloca_array, alloca_extbytes, xnew_ibytes, etc. also XREALLOC_ARRAY, xnew. alloc.c: Rewrite the allocation functions to factor out repeated code. Add assertions for freeing dumped data. lisp.h: Moved down and consolidated with other allocation stuff. lisp.h, dynarr.c: New functions for allocation that's very efficient when mostly in LIFO order. lisp.h, text.c, text.h: Factor out some stuff for general use by alloca()-conversion funs. text.h, lisp.h: Fill out convenience routines for allocating various kinds of bytes and put them in lisp.h. Use them in place of xmalloc(), ALLOCA(). text.h: Fill out the convenience functions so the _MALLOC() kinds match the alloca() kinds. --------------------------------------------------------------- ERROR-CHECKING --------------------------------------------------------------- text.h: Create ASSERT_ASCTEXT_ASCII() and ASSERT_ASCTEXT_ASCII_LEN() from similar Eistring checkers and change the Eistring checkers to use them instead. --------------------------------------------------------------- MACROS IN LISP.H --------------------------------------------------------------- lisp.h: Redo GCPRO declarations. Create a "base" set of functions that can be used to generate any kind of gcpro sets -- regular, ngcpro, nngcpro, private ones used in GC_EXTERNAL_LIST_LOOP_2. buffer.c, callint.c, chartab.c, console-msw.c, device-x.c, dialog-msw.c, dired.c, extents.c, ui-gtk.c, rangetab.c, nt.c, mule-coding.c, minibuf.c, menubar-msw.c, menubar.c, menubar-gtk.c, lread.c, lisp.h, gutter.c, glyphs.c, glyphs-widget.c, fns.c, fileio.c, file-coding.c, specifier.c: Eliminate EXTERNAL_LIST_LOOP, which does not check for circularities. Use EXTERNAL_LIST_LOOP_2 instead or EXTERNAL_LIST_LOOP_3 or EXTERNAL_PROPERTY_LIST_LOOP_3 or GC_EXTERNAL_LIST_LOOP_2 (new macro). Removed/redid comments on EXTERNAL_LIST_LOOP. --------------------------------------------------------------- SPACING FIXES --------------------------------------------------------------- callint.c, hftctl.c, number-gmp.c, process-unix.c: Spacing fixes. --------------------------------------------------------------- FIX FOR GEOMETRY PROBLEM IN FIRST FRAME --------------------------------------------------------------- unicode.c: Add workaround for newlib bug in sscanf() [should be fixed by release 1.5.12 of Cygwin]. toolbar.c: bug fix for problem of initial frame being 77 chars wide on Windows. will be overridden by my other ws. --------------------------------------------------------------- FIX FOR LEAKING PROCESS HANDLES: --------------------------------------------------------------- process-nt.c: Fixes for leaking handles. Inspired by work done by Adrian Aichner <adrian@xemacs.org>. --------------------------------------------------------------- FIX FOR CYGWIN BUG (Unicode-related): --------------------------------------------------------------- unicode.c: Add workaround for newlib bug in sscanf() [should be fixed by release 1.5.12 of Cygwin]. --------------------------------------------------------------- WARNING FIXES: --------------------------------------------------------------- console-stream.c: `reinit' is unused. compiler.h, event-msw.c, frame-msw.c, intl-encap-win32.c, text.h: Add stuff to deal with ANSI-aliasing warnings I got. regex.c: Gather includes together to avoid warning. --------------------------------------------------------------- CHANGES TO INITIALIZATION ROUTINES: --------------------------------------------------------------- buffer.c, emacs.c, console.c, debug.c, device-x.c, device.c, dragdrop.c, emodules.c, eval.c, event-Xt.c, event-gtk.c, event-msw.c, event-stream.c, event-tty.c, events.c, extents.c, faces.c, file-coding.c, fileio.c, font-lock.c, frame-msw.c, glyphs-widget.c, glyphs.c, gui-x.c, insdel.c, lread.c, lstream.c, menubar-gtk.c, menubar-x.c, minibuf.c, mule-wnnfns.c, objects-msw.c, objects.c, print.c, scrollbar-x.c, search.c, select-x.c, text.c, undo.c, unicode.c, window.c, symsinit.h: Call reinit_*() functions directly from emacs.c, for clarity. Factor out some redundant init code. Move disallowed stuff that had crept into vars_of_glyphs() into complex_vars_of_glyphs(). Call init_eval_semi_early() from eval.c not in the middle of vars_of_() in emacs.c since there should be no order dependency in the latter calls. --------------------------------------------------------------- ARMAGEDDON: --------------------------------------------------------------- alloc.c, emacs.c, lisp.h, print.c: Rename inhibit_non_essential_printing_operations to inhibit_non_essential_conversion_operations. text.c: Assert on !inhibit_non_essential_conversion_operations. console-msw.c, print.c: Don't do conversion in SetConsoleTitle or FindWindow to avoid problems during armageddon. Put #errors for NON_ASCII_INTERNAL_FORMAT in places where problems would arise. --------------------------------------------------------------- CHANGES TO THE BUILD PROCEDURE: --------------------------------------------------------------- config.h.in, s/cxux.h, s/usg5-4-2.h, m/powerpc.h: Add comment about correct ordering of this file. Rearrange everything to follow this -- put all #undefs together and before the s&m files. Add undefs for HAVE_ALLOCA, C_ALLOCA, BROKEN_ALLOCA_IN_FUNCTION_CALLS, STACK_DIRECTION. Remove unused HAVE_STPCPY, HAVE_GETWD, HAVE_SETLOCALE. m/gec63.h: Deleted; totally broken, not used at all, not in FSF. m/7300.h, m/acorn.h, m/alliant-2800.h, m/alliant.h, m/altos.h, m/amdahl.h, m/apollo.h, m/att3b.h, m/aviion.h, m/celerity.h, m/clipper.h, m/cnvrgnt.h, m/convex.h, m/cydra5.h, m/delta.h, m/delta88k.h, m/dpx2.h, m/elxsi.h, m/ews4800r.h, m/gould.h, m/hp300bsd.h, m/hp800.h, m/hp9000s300.h, m/i860.h, m/ibmps2-aix.h, m/ibmrs6000.h, m/ibmrt-aix.h, m/ibmrt.h, m/intel386.h, m/iris4d.h, m/iris5d.h, m/iris6d.h, m/irist.h, m/isi-ov.h, m/luna88k.h, m/m68k.h, m/masscomp.h, m/mg1.h, m/mips-nec.h, m/mips-siemens.h, m/mips.h, m/news.h, m/nh3000.h, m/nh4000.h, m/ns32000.h, m/orion105.h, m/pfa50.h, m/plexus.h, m/pmax.h, m/powerpc.h, m/pyrmips.h, m/sequent-ptx.h, m/sequent.h, m/sgi-challenge.h, m/symmetry.h, m/tad68k.h, m/tahoe.h, m/targon31.h, m/tekxd88.h, m/template.h, m/tower32.h, m/tower32v3.h, m/ustation.h, m/vax.h, m/wicat.h, m/xps100.h: Delete C_ALLOCA, HAVE_ALLOCA, STACK_DIRECTION, BROKEN_ALLOCA_IN_FUNCTION_CALLS. All of this is auto-detected. When in doubt, I followed recent FSF sources, which also have these things deleted.
author ben
date Thu, 04 Nov 2004 23:08:28 +0000
parents 87084e8445a7
children 3d8143fc88e1
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 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);
	      if (context_cache.style == comment_style_none) abort ();
	    }
	  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);
	  if (context_cache.style == comment_style_none) abort ();
	}
      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 */
	{
	  if (context_cache.style == comment_style_none) abort ();
	  context_cache.ccontext = ccontext_end1;
	}

      else if (context_cache.ccontext == ccontext_start1)
	{
	  if (context_cache.context != context_none) abort ();
	  context_cache.ccontext = ccontext_none;
	}
      else if (context_cache.ccontext == ccontext_end1)
	{
	  if (context_cache.context != context_block_comment) abort ();
	  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;
	  if (context_cache.style == comment_style_none) abort ();
	}
      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 */