Mercurial > hg > xemacs-beta
view lisp/mule/mule-composite.el @ 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 | 2923009caf47 |
children | 308d34e9f07d |
line wrap: on
line source
;;; mule-composite.el --- support character composition ;; Copyright (C) 1999 Electrotechnical Laboratory, JAPAN. ;; Licensed to the Free Software Foundation. ;; Keywords: mule, multilingual, character composition ;; This file is part of GNU Emacs. ;; GNU Emacs 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. ;; GNU Emacs 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 GNU Emacs; 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: Emacs 21.1 (lisp/composite.el). ;;; Commentary: ;;; Code: ;;;###autoload (defconst reference-point-alist '((tl . 0) (tc . 1) (tr . 2) (Bl . 3) (Bc . 4) (Br . 5) (bl . 6) (bc . 7) (br . 8) (cl . 9) (cc . 10) (cr . 11) (top-left . 0) (top-center . 1) (top-right . 2) (base-left . 3) (base-center . 4) (base-right . 5) (bottom-left . 6) (bottom-center . 7) (bottom-right . 8) (center-left . 9) (center-center . 10) (center-right . 11) ;; For backward compatibility... (ml . 3) (mc . 10) (mr . 5) (mid-left . 3) (mid-center . 10) (mid-right . 5)) "UNIMPLEMENTED. Alist of symbols vs integer codes of glyph reference points. A glyph reference point symbol is to be used to specify a composition rule in COMPONENTS argument to such functions as `compose-region' and `make-composition'. Meanings of glyph reference point codes are as follows: 0----1----2 <---- ascent 0:tl or top-left | | 1:tc or top-center | | 2:tr or top-right | | 3:Bl or base-left 9:cl or center-left 9 10 11 <---- center 4:Bc or base-center 10:cc or center-center | | 5:Br or base-right 11:cr or center-right --3----4----5-- <-- baseline 6:bl or bottom-left | | 7:bc or bottom-center 6----7----8 <---- descent 8:br or bottom-right Glyph reference point symbols are to be used to specify composition rule of the form \(GLOBAL-REF-POINT . NEW-REF-POINT), where GLOBAL-REF-POINT is a reference point in the overall glyphs already composed, and NEW-REF-POINT is a reference point in the new glyph to be added. For instance, if GLOBAL-REF-POINT is `br' (bottom-right) and NEW-REF-POINT is `tc' (top-center), the overall glyph is updated as follows (the point `*' corresponds to both reference points): +-------+--+ <--- new ascent | | | | global| | | glyph | | -- | | |-- <--- baseline \(doesn't change) +----+--*--+ | | new | | |glyph| +----+-----+ <--- new descent ") ;; Encode composition rule RULE into an integer value. RULE is a cons ;; of global and new reference point symbols. ;; This must be compatible with C macro COMPOSITION_ENCODE_RULE ;; defined in mule-composite.h. (defun encode-composition-rule (rule) (if (and (integerp rule) (< rule 144)) ;; Already encoded. rule (or (consp rule) (error "Invalid composition rule: %S" rule)) (let ((gref (car rule)) (nref (cdr rule))) (or (integerp gref) (setq gref (cdr (assq gref reference-point-alist)))) (or (integerp nref) (setq nref (cdr (assq nref reference-point-alist)))) (or (and (>= gref 0) (< gref 12) (>= nref 0) (< nref 12)) (error "Invalid composition rule: %S" rule)) (+ (* gref 12) nref)))) ;; Decode encoded composition rule RULE-CODE. The value is a cons of ;; global and new reference point symbols. ;; This must be compatible with C macro COMPOSITION_DECODE_RULE ;; defined in mule-composite.h. (defun decode-composition-rule (rule-code) (or (and (natnump rule-code) (< rule-code 144)) (error "Invalid encoded composition rule: %S" rule-code)) (let ((gref (car (rassq (/ rule-code 12) reference-point-alist))) (nref (car (rassq (% rule-code 12) reference-point-alist)))) (or (and gref (symbolp gref) nref (symbolp nref)) (error "Invalid composition rule code: %S" rule-code)) (cons gref nref))) ;; Encode composition rules in composition components COMPONENTS. The ;; value is a copy of COMPONENTS, where composition rules (cons of ;; global and new glyph reference point symbols) are replaced with ;; encoded composition rules. Optional 2nd argument NOCOPY non-nil ;; means don't make a copy but modify COMPONENTS directly. (defun encode-composition-components (components &optional nocopy) (or nocopy (setq components (copy-sequence components))) (if (vectorp components) (let ((len (length components)) (i 1)) (while (< i len) (aset components i (encode-composition-rule (aref components i))) (setq i (+ i 2)))) (let ((tail (cdr components))) (while tail (setcar tail (encode-composition-rule (car tail))) (setq tail (nthcdr 2 tail))))) components) ;; Decode composition rule codes in composition components COMPONENTS. ;; The value is a copy of COMPONENTS, where composition rule codes are ;; replaced with composition rules (cons of global and new glyph ;; reference point symbols). Optional 2nd argument NOCOPY non-nil ;; means don't make a copy but modify COMPONENTS directly. ;; It is assumed that COMPONENTS is a vector and is for rule-base ;; composition, thus (2N+1)th elements are rule codes. (defun decode-composition-components (components &optional nocopy) (or nocopy (setq components (copy-sequence components))) (let ((len (length components)) (i 1)) (while (< i len) (aset components i (decode-composition-rule (aref components i))) (setq i (+ i 2)))) components) ;;;###autoload (defun compose-region (start end &optional components modification-func) "UNIMPLEMENTED. Compose characters in the current region. When called from a program, expects these four arguments. First two arguments START and END are positions (integers or markers) specifying the region. Optional 3rd argument COMPONENTS, if non-nil, is a character or a sequence (vector, list, or string) of integers. If it is a character, it is an alternate character to display instead of the text in the region. If it is a string, the elements are alternate characters. If it is a vector or list, it is a sequence of alternate characters and composition rules, where (2N)th elements are characters and (2N+1)th elements are composition rules to specify how to compose (2N+2)th elements with previously composed N glyphs. A composition rule is a cons of global and new glyph reference point symbols. See the documentation of `reference-point-alist' for more detail. Optional 4th argument MODIFICATION-FUNC is a function to call to adjust the composition when it gets invalid because of a change of text in the composition." (interactive "r") (let ((modified-p (buffer-modified-p)) (buffer-read-only nil)) (if (or (vectorp components) (listp components)) (setq components (encode-composition-components components))) (compose-region-internal start end components modification-func) (set-buffer-modified-p modified-p))) ;;;###autoload (defun decompose-region (start end) "UNIMPLEMENTED. Decompose text in the current region. When called from a program, expects two arguments, positions (integers or markers) specifying the region." (interactive "r") (let ((modified-p (buffer-modified-p)) (buffer-read-only nil)) (remove-text-properties start end '(composition nil)) (set-buffer-modified-p modified-p))) ;;;###autoload (defun compose-string (string &optional start end components modification-func) "UNIMPLEMENTED. Compose characters in string STRING. The return value is STRING where `composition' property is put on all the characters in it. Optional 2nd and 3rd arguments START and END specify the range of STRING to be composed. They defaults to the beginning and the end of STRING respectively. Optional 4th argument COMPONENTS, if non-nil, is a character or a sequence (vector, list, or string) of integers. See the function `compose-region' for more detail. Optional 5th argument MODIFICATION-FUNC is a function to call to adjust the composition when it gets invalid because of a change of text in the composition." (if (or (vectorp components) (listp components)) (setq components (encode-composition-components components))) (or start (setq start 0)) (or end (setq end (length string))) (compose-string-internal string start end components modification-func) string) ;;;###autoload (defun decompose-string (string) "UNIMPLEMENTED. Return STRING where `composition' property is removed." (remove-text-properties 0 (length string) '(composition nil) string) string) ;;;###autoload (defun compose-chars (&rest args) "UNIMPLEMENTED. Return a string from arguments in which all characters are composed. For relative composition, arguments are characters. For rule-based composition, Mth \(where M is odd) arguments are characters, and Nth \(where N is even) arguments are composition rules. A composition rule is a cons of glyph reference points of the form \(GLOBAL-REF-POINT . NEW-REF-POINT). See the documentation of `reference-point-alist' for more detail." (let (str components) (if (consp (car (cdr args))) ;; Rule-base composition. (let (;(len (length args)) (tail (encode-composition-components args 'nocopy))) (while tail (setq str (cons (car tail) str)) (setq tail (nthcdr 2 tail))) (setq str (concat (nreverse str)) components args)) ;; Relative composition. (setq str (concat args))) (compose-string-internal str 0 (length str) components))) ;;;###autoload (defun find-composition (pos &optional limit string detail-p) "UNIMPLEMENTED. Return information about a composition at or nearest to buffer position POS. If the character at POS has `composition' property, the value is a list of FROM, TO, and VALID-P. FROM and TO specify the range of text that has the same `composition' property, VALID-P is non-nil if and only if this composition is valid. If there's no composition at POS, and the optional 2nd argument LIMIT is non-nil, search for a composition toward LIMIT. If no composition is found, return nil. Optional 3rd argument STRING, if non-nil, is a string to look for a composition in; nil means the current buffer. If a valid composition is found and the optional 4th argument DETAIL-P is non-nil, the return value is a list of FROM, TO, COMPONENTS, RELATIVE-P, MOD-FUNC, and WIDTH. COMPONENTS is a vector of integers, the meaning depends on RELATIVE-P. RELATIVE-P is t if the composition method is relative, else nil. If RELATIVE-P is t, COMPONENTS is a vector of characters to be composed. If RELATIVE-P is nil, COMPONENTS is a vector of characters and composition rules as described in `compose-region'. MOD-FUNC is a modification function of the composition. WIDTH is a number of columns the composition occupies on the screen." (let ((result (find-composition-internal pos limit string detail-p))) (if (and detail-p result (nth 2 result) (not (nth 3 result))) ;; This is a valid rule-base composition. (decode-composition-components (nth 2 result) 'nocopy)) result)) ;;;###autoload (defun compose-chars-after (pos &optional limit object) "UNIMPLEMENTED. Compose characters in current buffer after position POS. It looks up the char-table `composition-function-table' (which see) by a character after POS. If non-nil value is found, the format of the value should be an alist of PATTERNs vs FUNCs, where PATTERNs are regular expressions and FUNCs are functions. If the text after POS matches one of PATTERNs, call the corresponding FUNC with three arguments POS, TO, and PATTERN, where TO is the end position of text matching PATTERN, and return what FUNC returns. Otherwise, return nil. FUNC is responsible for composing the text properly. The return value is: nil -- if no characters were composed. CHARS (integer) -- if CHARS characters were composed. Optional 2nd arg LIMIT, if non-nil, limits the matching of text. Optional 3rd arg OBJECT, if non-nil, is a string that contains the text to compose. In that case, POS and LIMIT index to the string. This function is the default value of `compose-chars-after-function'." (let ((tail (get-char-table (char-after pos) composition-function-table)) pattern func result) (when tail (save-match-data (save-excursion (while (and tail (not func)) (setq pattern (car (car tail)) func (cdr (car tail))) (goto-char pos) (if (if limit (and (re-search-forward pattern limit t) (= (match-beginning 0) pos)) (looking-at pattern)) (setq result (funcall func pos (match-end 0) pattern nil)) (setq func nil tail (cdr tail))))))) result)) ;;;###autoload (defun compose-last-chars (args) "UNIMPLEMENTED. Compose last characters. The argument is a parameterized event of the form \(compose-last-chars N COMPONENTS), where N is the number of characters before point to compose, COMPONENTS, if non-nil, is the same as the argument to `compose-region' \(which see). If it is nil, `compose-chars-after' is called, and that function find a proper rule to compose the target characters. This function is intended to be used from input methods. The global keymap binds special event `compose-last-chars' to this function. Input method may generate an event (compose-last-chars N COMPONENTS) after a sequence character events." (interactive "e") (let ((chars (nth 1 args))) (if (and (numberp chars) (>= (- (point) (point-min)) chars)) (if (nth 2 args) (compose-region (- (point) chars) (point) (nth 2 args)) (compose-chars-after (- (point) chars) (point)))))) ;;;###autoload(global-set-key [compose-last-chars] 'compose-last-chars) ;;; The following codes are only for backward compatibility with Emacs ;;; 20.4 and the earlier. ;;;###autoload (defun decompose-composite-char (char &optional type with-composition-rule) "UNIMPLEMENTED. Convert CHAR to string. This is only for backward compatibility with Emacs 20.4 and the earlier. If optional 2nd arg TYPE is non-nil, it is `string', `list', or `vector'. In this case, CHAR is converted string, list of CHAR, or vector of CHAR respectively." (cond ((or (null type) (eq type 'string)) (char-to-string char)) ((eq type 'list) (list char)) (t (vector char)))) (make-obsolete 'decompose-composite-char 'char-to-string ;;"21.1" ) ;;; mule-composite.el ends here