view src/abbrev.c @ 814:a634e3b7acc8

[xemacs-hg @ 2002-04-14 12:41:59 by ben] latest changes TODO.ben-mule-21-5: Update. make-docfile.c: Add basic support for handling ISO 2022 doc strings -- we parse the basic charset designation sequences so we know whether we're in ASCII and have to pay attention to end quotes and such. Reformat code according to coding standards. abbrev.el: Add `global-abbrev-mode', which turns on or off abbrev-mode in all buffers. Added `defining-abbrev-turns-on-abbrev-mode' -- if non-nil, defining an abbrev through an interactive function will automatically turn on abbrev-mode, either globally or locally depending on the command. This is the "what you'd expect" behavior. indent.el: general function for indenting a balanced expression in a mode-correct way. Works similar to indent-region in that a mode can specify a specific command to do the whole operation; if not, figure out the region using forward-sexp and indent each line using indent-according-to-mode. keydefs.el: Removed. Modify M-C-backslash to do indent-region-or-balanced-expression. Make S-Tab just insert a TAB char, like it's meant to do. make-docfile.el: Now that we're using the call-process-in-lisp, we need to load an extra file win32-native.el because we're running a bare temacs. menubar-items.el: Totally redo the Cmds menu so that most used commands appear directly on the menu and less used commands appear in submenus. The old way may have been very pretty, but rather impractical. process.el: Under Windows, don't ever use old-call-process-internal, even in batch mode. We can do processes in batch mode. subr.el: Someone recoded truncate-string-to-width, saying "the FSF version is too complicated and does lots of hard-to-understand stuff" but the resulting recoded version was *totally* wrong! it misunderstood the basic point of this function, which is work in *columns* not chars. i dumped ours and copied the version from FSF 21.1. Also added truncate-string-with-continuation-dots, since this idiom is used often. config.inc.samp, xemacs.mak: Separate out debug and optimize flags. Remove all vestiges of USE_MINIMAL_TAGBITS, USE_INDEXED_LRECORD_IMPLEMENTATION, and GUNG_HO, since those ifdefs have long been removed. Make error-checking support actually work. Some rearrangement of config.inc.samp to make it more logical. Remove callproc.c and ntproc.c from xemacs.mak, no longer used. Make pdump the default. lisp.h: Add support for strong type-checking of Bytecount, Bytebpos, Charcount, Charbpos, and others, by making them classes, overloading the operators to provide integer-like operation and carefully controlling what operations are allowed. Not currently enabled in C++ builds because there are still a number of compile errors, and it won't really work till we merge in my "8-bit-Mule" workspace, in which I make use of the new types Charxpos, Bytexpos, Memxpos, representing a "position" either in a buffer or a string. (This is especially important in the extent code.) abbrev.c, alloc.c, eval.c, buffer.c, buffer.h, editfns.c, fns.c, text.h: Warning fixes, some of them related to new C++ strict type checking of Bytecount, Charbpos, etc. dired.c: Caught an actual error due to strong type checking -- char len being passed when should be byte len. alloc.c, backtrace.h, bytecode.c, bytecode.h, eval.c, sysdep.c: Further optimize Ffuncall: -- process arg list at compiled-function creation time, converting into an array for extra-quick access at funcall time. -- rewrite funcall_compiled_function to use it, and inline this function. -- change the order of check for magic stuff in SPECBIND_FAST_UNSAFE to be faster. -- move the check for need to garbage collect into the allocation code, so only a single flag needs to be checked in funcall. buffer.c, symbols.c: add debug funs to check on mule optimization info in buffers and strings. eval.c, emacs.c, text.c, regex.c, scrollbar-msw.c, search.c: Fix evil crashes due to eistrings not properly reinitialized under pdump. Redo a bit some of the init routines; convert some complex_vars_of() into simple vars_of(), because they didn't need complex processing. callproc.c, emacs.c, event-stream.c, nt.c, process.c, process.h, sysdep.c, sysdep.h, syssignal.h, syswindows.h, ntproc.c: Delete. Hallelujah, praise the Lord, there is no god but Allah!!! fix so that processes can be invoked in bare temacs -- thereby eliminating any need for callproc.c. (currently only eliminated under NT.) remove all crufty and unnecessary old process code in ntproc.c and elsewhere. move non-callproc-specific stuff (mostly environment) into process.c, so callproc.c can be left out under NT. console-tty.c, doc.c, file-coding.c, file-coding.h, lstream.c, lstream.h: fix doc string handling so it works with Japanese, etc docs. change handling of "character mode" so callers don't have to manually set it (quite error-prone). event-msw.c: spacing fixes. lread.c: eliminate unused crufty vintage-19 "FSF defun hack" code. lrecord.h: improve pdump description docs. buffer.c, ntheap.c, unexnt.c, win32.c, emacs.c: Mule-ize some unexec and startup code. It was pseudo-Mule-ized before by simply always calling the ...A versions of functions, but that won't cut it -- eventually we want to be able to run properly even if XEmacs has been installed in a Japanese directory. (The current problem is the timing of the loading of the Unicode tables; this will eventually be fixed.) Go through and fix various other places where the code was not Mule-clean. Provide a function mswindows_get_module_file_name() to get our own name without resort to PATH_MAX and such. Add a big comment in main() about the problem with Unicode table load timing that I just alluded to. emacs.c: When error-checking is enabled (interpreted as "user is developing XEmacs"), don't ask user to "pause to read messages" when a fatal error has occurred, because it will wedge if we are in an inner modal loop (typically when a menu is popped up) and make us unable to get a useful stack trace in the debugger. text.c: Correct update_entirely_ascii_p_flag to actually work. lisp.h, symsinit.h: declarations for above changes.
author ben
date Sun, 14 Apr 2002 12:43:31 +0000
parents e38acbeb1cae
children 6728e641994e
line wrap: on
line source

/* Primitives for word-abbrev mode.
   Copyright (C) 1985, 1986, 1992, 1993 Free Software Foundation, Inc.
   Copyright (C) 2002 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: FSF 19.30.  Note that there are many more functions in
   FSF's abbrev.c.  These have been moved into Lisp in XEmacs. */

/* Authorship:

   FSF: Original version; a long time ago.
   JWZ or Mly: Mostly moved into Lisp; maybe 1992.
   Ben Wing: Some changes for Mule for 19.12.
   Hrvoje Niksic: Largely rewritten in June 1997.
*/

/* This file has been Mule-ized. */

#include <config.h>
#include "lisp.h"

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

/* An abbrev table is an obarray.
   Each defined abbrev is represented by a symbol in that obarray
   whose print name is the abbreviation.
   The symbol's value is a string which is the expansion.
   If its function definition is non-nil, it is called
   after the expansion is done.
   The plist slot of the abbrev symbol is its usage count. */

/* The table of global abbrevs.  These are in effect
   in any buffer in which abbrev mode is turned on. */
Lisp_Object Vglobal_abbrev_table;

int abbrev_all_caps;

/* Non-nil => use this location as the start of abbrev to expand
 (rather than taking the word before point as the abbrev) */
Lisp_Object Vabbrev_start_location;

/* Buffer that Vabbrev_start_location applies to */
Lisp_Object Vabbrev_start_location_buffer;

/* The symbol representing the abbrev most recently expanded */
Lisp_Object Vlast_abbrev;

/* A string for the actual text of the abbrev most recently expanded.
   This has more info than Vlast_abbrev since case is significant.  */
Lisp_Object Vlast_abbrev_text;

/* Character address of start of last abbrev expanded */
Fixnum last_abbrev_location;

/* Hook to run before expanding any abbrev.  */
Lisp_Object Vpre_abbrev_expand_hook, Qpre_abbrev_expand_hook;


struct abbrev_match_mapper_closure {
  struct buffer *buf;
  Lisp_Char_Table *chartab;
  Charbpos point;
  Charcount maxlen;
  Lisp_Symbol *found;
};

/* For use by abbrev_match(): Match SYMBOL's name against buffer text
   before point, case-insensitively.  When found, return non-zero, so
   that map_obarray terminates mapping.  */
static int
abbrev_match_mapper (Lisp_Object symbol, void *arg)
{
  struct abbrev_match_mapper_closure *closure =
    (struct abbrev_match_mapper_closure *)arg;
  Charcount abbrev_length;
  Lisp_Symbol *sym = XSYMBOL (symbol);
  Lisp_Object abbrev;

  /* symbol_value should be OK here, because abbrevs are not expected
     to contain any SYMBOL_MAGIC stuff.  */
  if (UNBOUNDP (symbol_value (sym)) || NILP (symbol_value (sym)))
    {
      /* The symbol value of nil means that abbrev got undefined. */
      return 0;
    }
  abbrev = symbol_name (sym);
  abbrev_length = XSTRING_CHAR_LENGTH (abbrev);
  if (abbrev_length > closure->maxlen)
    {
      /* This abbrev is too large -- it wouldn't fit. */
      return 0;
    }
  /* If `bar' is an abbrev, and a user presses `fubar<SPC>', we don't
     normally want to expand it.  OTOH, if the abbrev begins with
     non-word syntax (e.g. `#if'), it is OK to abbreviate it anywhere.  */
  if (abbrev_length < closure->maxlen && abbrev_length > 0
      && (WORD_SYNTAX_P (closure->chartab, XSTRING_CHAR (abbrev, 0)))
      && (WORD_SYNTAX_P (closure->chartab,
			 BUF_FETCH_CHAR (closure->buf,
					 closure->point -
					 (abbrev_length + 1)))))
    {
      return 0;
    }
  /* Match abbreviation string against buffer text.  */
  {
    Intbyte *ptr = XSTRING_DATA (abbrev);
    Charcount idx;

    for (idx = 0; idx < abbrev_length; idx++)
      {
	if (DOWNCASE (closure->buf,
		      BUF_FETCH_CHAR (closure->buf,
				      closure->point - abbrev_length + idx))
	    != DOWNCASE (closure->buf, charptr_emchar (ptr)))
	  {
	    break;
	  }
	INC_CHARPTR (ptr);
      }
    if (idx == abbrev_length)
      {
	/* This is the one. */
	closure->found = sym;
	return 1;
      }
  }
  return 0;
}

/* Match the buffer text against names of symbols in obarray.  Returns
   the matching symbol, or 0 if not found.  */
static Lisp_Symbol *
abbrev_match (struct buffer *buf, Lisp_Object obarray)
{
  struct abbrev_match_mapper_closure closure;

  /* Precalculate some stuff, so mapper function needn't to it in each
     iteration.  */
  closure.buf = buf;
  closure.point = BUF_PT (buf);
  closure.maxlen = closure.point - BUF_BEGV (buf);
  closure.chartab = XCHAR_TABLE (buf->mirror_syntax_table);
  closure.found = 0;

  map_obarray (obarray, abbrev_match_mapper, &closure);

  return closure.found;
}

/* Take the word before point (or Vabbrev_start_location, if non-nil),
   and look it up in OBARRAY, and return the symbol (or zero).  This
   used to be the default method of searching, with the obvious
   limitation that the abbrevs may consist only of word characters.
   It is an order of magnitude faster than the proper abbrev_match(),
   but then again, vi is an order of magnitude faster than Emacs.

   This speed difference should be unnoticeable, though.  I have tested
   the degenerated cases of thousands of abbrevs being defined, and
   abbrev_match() was still fast enough for normal operation.  */
static Lisp_Symbol *
abbrev_oblookup (struct buffer *buf, Lisp_Object obarray)
{
  Charbpos wordstart, wordend;
  Intbyte *word, *p;
  Charbpos idx;
  Lisp_Object lookup;

  CHECK_VECTOR (obarray);

  if (!NILP (Vabbrev_start_location))
    {
      wordstart = get_buffer_pos_char (buf, Vabbrev_start_location,
				       GB_COERCE_RANGE);
      Vabbrev_start_location = Qnil;
#if 0
      /* Previously, abbrev-prefix-mark crockishly inserted a dash to
	 indicate the abbrev start point.  It now uses an extent with
	 a begin glyph so there's no dash to remove.  */
      if (wordstart != BUF_ZV (buf)
 	  && BUF_FETCH_CHAR (buf, wordstart) == '-')
	{
	  buffer_delete_range (buf, wordstart, wordstart + 1, 0);
	}
#endif
      wordend = BUF_PT (buf);
    }
  else
    {
      Charbpos point = BUF_PT (buf);

      wordstart = scan_words (buf, point, -1);
      if (!wordstart)
	return 0;

      wordend = scan_words (buf, wordstart, 1);
      if (!wordend)
	return 0;
      if (wordend > BUF_ZV (buf))
	wordend = BUF_ZV (buf);
      if (wordend > point)
	wordend = point;
      /* Unlike the original function, we allow expansion only after
	 the abbrev, not preceded by a number of spaces.  This is
	 because of consistency with abbrev_match. */
      if (wordend < point)
	return 0;
    }

  if (wordend <= wordstart)
    return 0;

  p = word = (Intbyte *) alloca (MAX_EMCHAR_LEN * (wordend - wordstart));
  for (idx = wordstart; idx < wordend; idx++)
    {
      Emchar c = BUF_FETCH_CHAR (buf, idx);
      if (UPPERCASEP (buf, c))
	c = DOWNCASE (buf, c);
      p += set_charptr_emchar (p, c);
    }
  lookup = oblookup (obarray, word, p - word);
  if (SYMBOLP (lookup) && !NILP (symbol_value (XSYMBOL (lookup))))
    return XSYMBOL (lookup);
  else
    return NULL;
}

/* Return non-zero if OBARRAY contains an interned symbol ` '. */
static int
obarray_has_blank_p (Lisp_Object obarray)
{
  return !ZEROP (oblookup (obarray, (Intbyte *)" ", 1));
}

/* Analyze case in the buffer substring, and report it.  */
static void
abbrev_count_case (struct buffer *buf, Charbpos pos, Charcount length,
		   int *lccount, int *uccount)
{
  *lccount = *uccount = 0;
  while (length--)
    {
      Emchar c = BUF_FETCH_CHAR (buf, pos);
      if (UPPERCASEP (buf, c))
	++*uccount;
      else if (LOWERCASEP (buf, c))
	++*lccount;
      ++pos;
    }
}

DEFUN ("expand-abbrev", Fexpand_abbrev, 0, 0, "", /*
Expand the abbrev before point, if any.
Effective when explicitly called even when `abbrev-mode' is nil.
Returns the abbrev symbol, if expansion took place.
If no abbrev matched, but `pre-abbrev-expand-hook' changed the buffer,
 returns t.
*/
       ())
{
  /* This function can GC */
  struct buffer *buf = current_buffer;
  int oldmodiff = BUF_MODIFF (buf);
  Lisp_Object pre_modiff_p;
  Charbpos point;			/* position of point */
  Charbpos abbrev_start;		/* position of abbreviation beginning */

  Lisp_Symbol *(*fun) (struct buffer *, Lisp_Object);

  Lisp_Symbol *abbrev_symbol;
  Lisp_Object expansion, count, hook;
  Charcount abbrev_length;
  int lccount, uccount;

  run_hook (Qpre_abbrev_expand_hook);
  /* If the hook changes the buffer, treat that as having "done an
     expansion".  */
  pre_modiff_p = (BUF_MODIFF (buf) != oldmodiff ? Qt : Qnil);

  abbrev_symbol = NULL;
  if (!BUFFERP (Vabbrev_start_location_buffer) ||
      XBUFFER (Vabbrev_start_location_buffer) != buf)
    Vabbrev_start_location = Qnil;
  /* We use the more general abbrev_match() if the obarray blank flag
     is not set, and Vabbrev_start_location is nil.  Otherwise, use
     abbrev_oblookup(). */
#define MATCHFUN(tbl) ((obarray_has_blank_p (tbl)		 \
			&& NILP (Vabbrev_start_location))	 \
		       ? abbrev_match : abbrev_oblookup)
  if (!NILP (buf->abbrev_table))
    {
      fun = MATCHFUN (buf->abbrev_table);
      abbrev_symbol = fun (buf, buf->abbrev_table);
    }
  if (!abbrev_symbol && !NILP (Vglobal_abbrev_table))
    {
      fun = MATCHFUN (Vglobal_abbrev_table);
      abbrev_symbol = fun (buf, Vglobal_abbrev_table);
    }
  if (!abbrev_symbol)
    return pre_modiff_p;

  /* NOTE: we hope that `pre-abbrev-expand-hook' didn't do something
     nasty, such as changed the buffer.  Here we protect against the
     buffer getting killed.  */
  if (! BUFFER_LIVE_P (buf))
    return Qnil;
  point = BUF_PT (buf);

  /* OK, we're out of the must-be-fast part.  An abbreviation matched.
     Now find the parameters, insert the expansion, and make it all
     look pretty.  */
  abbrev_length = XSTRING_CHAR_LENGTH (symbol_name (abbrev_symbol));
  abbrev_start = point - abbrev_length;

  expansion = symbol_value (abbrev_symbol);
  CHECK_STRING (expansion);

  count = symbol_plist (abbrev_symbol); /* Gag */
  if (NILP (count))
    count = Qzero;
  else
    CHECK_NATNUM (count);
  symbol_plist (abbrev_symbol) = make_int (1 + XINT (count));

  /* Count the case in the original text. */
  abbrev_count_case (buf, abbrev_start, abbrev_length, &lccount, &uccount);

  /* Remember the last abbrev text, location, etc. */
  Vlast_abbrev = wrap_symbol (abbrev_symbol);
  Vlast_abbrev_text =
    make_string_from_buffer (buf, abbrev_start, abbrev_length);
  last_abbrev_location = abbrev_start;

  /* Add an undo boundary, in case we are doing this for a
     self-inserting command which has avoided making one so far.  */
  if (INTERACTIVE)
    Fundo_boundary ();

  /* Remove the abbrev */
  buffer_delete_range (buf, abbrev_start, point, 0);
  /* And insert the expansion. */
  buffer_insert_lisp_string (buf, expansion);
  point = BUF_PT (buf);

  /* Now fiddle with the case. */
  if (uccount && !lccount)
    {
      /* Abbrev was all caps */
      if (!abbrev_all_caps
	  && scan_words (buf, point, -1) > scan_words (buf, abbrev_start, 1))
	{
	  Fupcase_initials_region (make_int (abbrev_start), make_int (point),
				   wrap_buffer (buf));
	}
      else
	{
	  /* If expansion is one word, or if user says so, upcase it all. */
	  Fupcase_region (make_int (abbrev_start), make_int (point),
			  wrap_buffer (buf));
	}
    }
  else if (uccount)
    {
      /* Abbrev included some caps.  Cap first initial of expansion */
      Charbpos pos = abbrev_start;
      /* Find the initial.  */
      while (pos < point
	     && !WORD_SYNTAX_P (XCHAR_TABLE (buf->mirror_syntax_table),
				BUF_FETCH_CHAR (buf, pos)))
	pos++;
      /* Change just that.  */
      Fupcase_initials_region (make_int (pos), make_int (pos + 1),
			       wrap_buffer (buf));
    }

  hook = symbol_function (abbrev_symbol);
  if (!NILP (hook) && !UNBOUNDP (hook))
    call0 (hook);

  return Vlast_abbrev;
}


void
syms_of_abbrev (void)
{
  DEFSYMBOL (Qpre_abbrev_expand_hook);
  DEFSUBR (Fexpand_abbrev);
}

void
vars_of_abbrev (void)
{
  DEFVAR_LISP ("global-abbrev-table", &Vglobal_abbrev_table /*
The abbrev table whose abbrevs affect all buffers.
Each buffer may also have a local abbrev table.
If it does, the local table overrides the global one
for any particular abbrev defined in both.
*/ );
  Vglobal_abbrev_table = Qnil;  /* setup by Lisp code */

  DEFVAR_LISP ("last-abbrev", &Vlast_abbrev /*
The abbrev-symbol of the last abbrev expanded.
See the function `abbrev-symbol'.
*/ );

  DEFVAR_LISP ("last-abbrev-text", &Vlast_abbrev_text /*
The exact text of the last abbrev expanded.
nil if the abbrev has already been unexpanded.
*/ );

  DEFVAR_INT ("last-abbrev-location", &last_abbrev_location /*
The location of the start of the last abbrev expanded.
*/ );

  Vlast_abbrev = Qnil;
  Vlast_abbrev_text = Qnil;
  last_abbrev_location = 0;

  DEFVAR_LISP ("abbrev-start-location", &Vabbrev_start_location /*
Buffer position for `expand-abbrev' to use as the start of the abbrev.
nil means use the word before point as the abbrev.
Calling `expand-abbrev' sets this to nil.
*/ );
  Vabbrev_start_location = Qnil;

  DEFVAR_LISP ("abbrev-start-location-buffer", &Vabbrev_start_location_buffer /*
Buffer that `abbrev-start-location' has been set for.
Trying to expand an abbrev in any other buffer clears `abbrev-start-location'.
*/ );
  Vabbrev_start_location_buffer = Qnil;

  DEFVAR_BOOL ("abbrev-all-caps", &abbrev_all_caps /*
*Non-nil means expand multi-word abbrevs all caps if abbrev was so.
*/ );
  abbrev_all_caps = 0;

  DEFVAR_LISP ("pre-abbrev-expand-hook", &Vpre_abbrev_expand_hook /*
Function or functions to be called before abbrev expansion is done.
This is the first thing that `expand-abbrev' does, and so this may change
the current abbrev table before abbrev lookup happens.
*/ );
  Vpre_abbrev_expand_hook = Qnil;
}