Mercurial > hg > xemacs-beta
view src/abbrev.c @ 826:6728e641994e
[xemacs-hg @ 2002-05-05 11:30:15 by ben]
syntax cache, 8-bit-format, lots of code cleanup
README.packages: Update info about --package-path.
i.c: Create an inheritable event and pass it on to XEmacs, so that ^C
can be handled properly. Intercept ^C and signal the event.
"Stop Build" in VC++ now works.
bytecomp-runtime.el: Doc string changes.
compat.el: Some attempts to redo this to
make it truly useful and fix the "multiple versions interacting
with each other" problem. Not yet done. Currently doesn't work.
files.el: Use with-obsolete-variable to avoid warnings in new revert-buffer code.
xemacs.mak: Split up CFLAGS into a version without flags specifying the C
library. The problem seems to be that minitar depends on zlib,
which depends specifically on libc.lib, not on any of the other C
libraries. Unless you compile with libc.lib, you get errors --
specifically, no _errno in the other libraries, which must make it
something other than an int. (#### But this doesn't seem to obtain
in XEmacs, which also uses zlib, and can be linked with any of the
C libraries. Maybe zlib is used differently and doesn't need
errno, or maybe XEmacs provides an int errno; ... I don't
understand.
Makefile.in.in: Fix so that packages are around when testing.
abbrev.c, alloc.c, buffer.c, buffer.h, bytecode.c, callint.c, casefiddle.c, casetab.c, casetab.h, charset.h, chartab.c, chartab.h, cmds.c, console-msw.h, console-stream.c, console-x.c, console.c, console.h, data.c, device-msw.c, device.c, device.h, dialog-msw.c, dialog-x.c, dired-msw.c, dired.c, doc.c, doprnt.c, dumper.c, editfns.c, elhash.c, emacs.c, eval.c, event-Xt.c, event-gtk.c, event-msw.c, event-stream.c, events.c, events.h, extents.c, extents.h, faces.c, file-coding.c, file-coding.h, fileio.c, fns.c, font-lock.c, frame-gtk.c, frame-msw.c, frame-x.c, frame.c, frame.h, glade.c, glyphs-gtk.c, glyphs-msw.c, glyphs-msw.h, glyphs-x.c, glyphs.c, glyphs.h, gui-msw.c, gui-x.c, gui.h, gutter.h, hash.h, indent.c, insdel.c, intl-win32.c, intl.c, keymap.c, lisp-disunion.h, lisp-union.h, lisp.h, lread.c, lrecord.h, lstream.c, lstream.h, marker.c, menubar-gtk.c, menubar-msw.c, menubar-x.c, menubar.c, minibuf.c, mule-ccl.c, mule-charset.c, mule-coding.c, mule-wnnfns.c, nas.c, objects-msw.c, objects-x.c, opaque.c, postgresql.c, print.c, process-nt.c, process-unix.c, process.c, process.h, profile.c, rangetab.c, redisplay-gtk.c, redisplay-msw.c, redisplay-output.c, redisplay-x.c, redisplay.c, redisplay.h, regex.c, regex.h, scrollbar-msw.c, search.c, select-x.c, specifier.c, specifier.h, symbols.c, symsinit.h, syntax.c, syntax.h, syswindows.h, tests.c, text.c, text.h, tooltalk.c, ui-byhand.c, ui-gtk.c, unicode.c, win32.c, window.c: Another big Ben patch.
-- FUNCTIONALITY CHANGES:
add partial support for 8-bit-fixed, 16-bit-fixed, and
32-bit-fixed formats. not quite done yet. (in particular, needs
functions to actually convert the buffer.) NOTE: lots of changes
to regex.c here. also, many new *_fmt() inline funs that take an
Internal_Format argument.
redo syntax cache code. make the cache per-buffer; keep the cache
valid across calls to functions that use it. also keep it valid
across insertions/deletions and extent changes, as much as is
possible. eliminate the junky regex-reentrancy code by passing in
the relevant lisp info to the regex routines as local vars.
add general mechanism in extents code for signalling extent changes.
fix numerous problems with the case-table implementation; yoshiki
never properly transferred many algorithms from old-style to
new-style case tables.
redo char tables to support a default argument, so that mapping
only occurs over changed args. change many chartab functions to
accept Lisp_Object instead of Lisp_Char_Table *.
comment out the code in font-lock.c by default, because
font-lock.el no longer uses it. we should consider eliminating it
entirely.
Don't output bell as ^G in console-stream when not a TTY.
add -mswindows-termination-handle to interface with i.c, so we can
properly kill a build.
add more error-checking to buffer/string macros.
add some additional buffer_or_string_() funs.
-- INTERFACE CHANGES AFFECTING MORE CODE:
switch the arguments of write_c_string and friends to be
consistent with write_fmt_string, which must have printcharfun
first.
change BI_* macros to BYTE_* for increased clarity; similarly for
bi_* local vars.
change VOID_TO_LISP to be a one-argument function. eliminate
no-longer-needed CVOID_TO_LISP.
-- char/string macro changes:
rename MAKE_CHAR() to make_emchar() for slightly less confusion
with make_char(). (The former generates an Emchar, the latter a
Lisp object. Conceivably we should rename make_char() -> wrap_char()
and similarly for make_int(), make_float().)
Similar changes for other *CHAR* macros -- we now consistently use
names with `emchar' whenever we are working with Emchars. Any
remaining name with just `char' always refers to a Lisp object.
rename macros with XSTRING_* to string_* except for those that
reference actual fields in the Lisp_String object, following
conventions used elsewhere.
rename set_string_{data,length} macros (the only ones to work with
a Lisp_String_* instead of a Lisp_Object) to set_lispstringp_*
to make the difference clear.
try to be consistent about caps vs. lowercase in macro/inline-fun
names for chars and such, which wasn't the case before. we now
reserve caps either for XFOO_ macros that reference object fields
(e.g. XSTRING_DATA) or for things that have non-function semantics,
e.g. directly modifying an arg (BREAKUP_EMCHAR) or evaluating an
arg (any arg) more than once. otherwise, use lowercase.
here is a summary of most of the macros/inline funs changed by all
of the above changes:
BYTE_*_P -> byte_*_p
XSTRING_BYTE -> string_byte
set_string_data/length -> set_lispstringp_data/length
XSTRING_CHAR_LENGTH -> string_char_length
XSTRING_CHAR -> string_emchar
INTBYTE_FIRST_BYTE_P -> intbyte_first_byte_p
INTBYTE_LEADING_BYTE_P -> intbyte_leading_byte_p
charptr_copy_char -> charptr_copy_emchar
LEADING_BYTE_* -> leading_byte_*
CHAR_* -> EMCHAR_*
*_CHAR_* -> *_EMCHAR_*
*_CHAR -> *_EMCHAR
CHARSET_BY_ -> charset_by_*
BYTE_SHIFT_JIS* -> byte_shift_jis*
BYTE_BIG5* -> byte_big5*
REP_BYTES_BY_FIRST_BYTE -> rep_bytes_by_first_byte
char_to_unicode -> emchar_to_unicode
valid_char_p -> valid_emchar_p
Change intbyte_strcmp -> qxestrcmp_c (duplicated functionality).
-- INTERFACE CHANGES AFFECTING LESS CODE:
use DECLARE_INLINE_HEADER in various places.
remove '#ifdef emacs' from XEmacs-only files.
eliminate CHAR_TABLE_VALUE(), which duplicated the functionality
of get_char_table().
add BUFFER_TEXT_LOOP to simplify iterations over buffer text.
define typedefs for signed and unsigned types of fixed sizes
(INT_32_BIT, UINT_32_BIT, etc.).
create ALIGN_FOR_TYPE as a higher-level interface onto ALIGN_SIZE;
fix code to use it.
add charptr_emchar_len to return the text length of the character
pointed to by a ptr; use it in place of
charcount_to_bytecount(..., 1). add emchar_len to return the text
length of a given character.
add types Bytexpos and Charxpos to generalize Bytebpos/Bytecount
and Charbpos/Charcount, in code (particularly, the extents code
and redisplay code) that works with either kind of index. rename
redisplay struct params with names such as `charbpos' to
e.g. `charpos' when they are e.g. a Charxpos, not a Charbpos.
eliminate xxDEFUN in place of DEFUN; no longer necessary with
changes awhile back to doc.c.
split up big ugly combined list of EXFUNs in lisp.h on a
file-by-file basis, since other prototypes are similarly split.
rewrite some "*_UNSAFE" macros as inline funs and eliminate the
_UNSAFE suffix.
move most string code from lisp.h to text.h; the string code and
text.h code is now intertwined in such a fashion that they need
to be in the same place and partially interleaved. (you can't
create forward references for inline funs)
automated/lisp-tests.el, automated/symbol-tests.el, automated/test-harness.el: Fix test harness to output FAIL messages to stderr when in
batch mode.
Fix up some problems in lisp-tests/symbol-tests that were
causing spurious failures.
author | ben |
---|---|
date | Sun, 05 May 2002 11:33:57 +0000 |
parents | a634e3b7acc8 |
children | e7ee5f8bde58 |
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_Object 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 = string_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, string_emchar (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 = 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 = string_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 (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; }