view lisp/mule/tibet-util.el @ 5157:1fae11d56ad2

redo memory-usage mechanism, add way of dynamically initializing Lisp objects -------------------- ChangeLog entries follow: -------------------- lisp/ChangeLog addition: 2010-03-18 Ben Wing <ben@xemacs.org> * diagnose.el (show-memory-usage): Rewrite to take into account API changes in memory-usage functions. src/ChangeLog addition: 2010-03-18 Ben Wing <ben@xemacs.org> * alloc.c: * alloc.c (disksave_object_finalization_1): * alloc.c (lisp_object_storage_size): * alloc.c (listu): * alloc.c (listn): * alloc.c (Fobject_memory_usage_stats): * alloc.c (compute_memusage_stats_length): * alloc.c (Fobject_memory_usage): * alloc.c (Ftotal_object_memory_usage): * alloc.c (malloced_storage_size): * alloc.c (common_init_alloc_early): * alloc.c (reinit_alloc_objects_early): * alloc.c (reinit_alloc_early): * alloc.c (init_alloc_once_early): * alloc.c (syms_of_alloc): * alloc.c (reinit_vars_of_alloc): * buffer.c: * buffer.c (struct buffer_stats): * buffer.c (compute_buffer_text_usage): * buffer.c (compute_buffer_usage): * buffer.c (buffer_memory_usage): * buffer.c (buffer_objects_create): * buffer.c (syms_of_buffer): * buffer.c (vars_of_buffer): * console-impl.h (struct console_methods): * dynarr.c (Dynarr_memory_usage): * emacs.c (main_1): * events.c (clear_event_resource): * extents.c: * extents.c (compute_buffer_extent_usage): * extents.c (extent_objects_create): * extents.h: * faces.c: * faces.c (compute_face_cachel_usage): * faces.c (face_objects_create): * faces.h: * general-slots.h: * glyphs.c: * glyphs.c (compute_glyph_cachel_usage): * glyphs.c (glyph_objects_create): * glyphs.h: * lisp.h: * lisp.h (struct usage_stats): * lrecord.h: * lrecord.h (enum lrecord_type): * lrecord.h (struct lrecord_implementation): * lrecord.h (MC_ALLOC_CALL_FINALIZER_FOR_DISKSAVE): * lrecord.h (DEFINE_DUMPABLE_LISP_OBJECT): * lrecord.h (DEFINE_DUMPABLE_SIZABLE_LISP_OBJECT): * lrecord.h (DEFINE_DUMPABLE_FROB_BLOCK_LISP_OBJECT): * lrecord.h (DEFINE_DUMPABLE_FROB_BLOCK_SIZABLE_LISP_OBJECT): * lrecord.h (DEFINE_DUMPABLE_INTERNAL_LISP_OBJECT): * lrecord.h (DEFINE_DUMPABLE_SIZABLE_INTERNAL_LISP_OBJECT): * lrecord.h (DEFINE_NODUMP_LISP_OBJECT): * lrecord.h (DEFINE_NODUMP_SIZABLE_LISP_OBJECT): * lrecord.h (DEFINE_NODUMP_FROB_BLOCK_LISP_OBJECT): * lrecord.h (DEFINE_NODUMP_FROB_BLOCK_SIZABLE_LISP_OBJECT): * lrecord.h (DEFINE_NODUMP_INTERNAL_LISP_OBJECT): * lrecord.h (DEFINE_NODUMP_SIZABLE_INTERNAL_LISP_OBJECT): * lrecord.h (MAKE_LISP_OBJECT): * lrecord.h (DEFINE_DUMPABLE_MODULE_LISP_OBJECT): * lrecord.h (DEFINE_DUMPABLE_MODULE_SIZABLE_LISP_OBJECT): * lrecord.h (DEFINE_NODUMP_MODULE_LISP_OBJECT): * lrecord.h (DEFINE_NODUMP_MODULE_SIZABLE_LISP_OBJECT): * lrecord.h (MAKE_MODULE_LISP_OBJECT): * lrecord.h (INIT_LISP_OBJECT): * lrecord.h (INIT_MODULE_LISP_OBJECT): * lrecord.h (UNDEF_LISP_OBJECT): * lrecord.h (UNDEF_MODULE_LISP_OBJECT): * lrecord.h (DECLARE_LISP_OBJECT): * lrecord.h (DECLARE_MODULE_API_LISP_OBJECT): * lrecord.h (DECLARE_MODULE_LISP_OBJECT): * lstream.c: * lstream.c (syms_of_lstream): * lstream.c (vars_of_lstream): * marker.c: * marker.c (compute_buffer_marker_usage): * mc-alloc.c (mc_alloced_storage_size): * mc-alloc.h: * mule-charset.c: * mule-charset.c (struct charset_stats): * mule-charset.c (compute_charset_usage): * mule-charset.c (charset_memory_usage): * mule-charset.c (mule_charset_objects_create): * mule-charset.c (syms_of_mule_charset): * mule-charset.c (vars_of_mule_charset): * redisplay.c: * redisplay.c (compute_rune_dynarr_usage): * redisplay.c (compute_display_block_dynarr_usage): * redisplay.c (compute_glyph_block_dynarr_usage): * redisplay.c (compute_display_line_dynarr_usage): * redisplay.c (compute_line_start_cache_dynarr_usage): * redisplay.h: * scrollbar-gtk.c (gtk_compute_scrollbar_instance_usage): * scrollbar-msw.c (mswindows_compute_scrollbar_instance_usage): * scrollbar-x.c (x_compute_scrollbar_instance_usage): * scrollbar.c (compute_scrollbar_instance_usage): * scrollbar.h: * symbols.c: * symbols.c (reinit_symbol_objects_early): * symbols.c (init_symbols_once_early): * symbols.c (reinit_symbols_early): * symbols.c (defsymbol_massage_name_1): * symsinit.h: * ui-gtk.c: * ui-gtk.c (emacs_gtk_object_getprop): * ui-gtk.c (emacs_gtk_object_putprop): * ui-gtk.c (ui_gtk_objects_create): * unicode.c (compute_from_unicode_table_size_1): * unicode.c (compute_to_unicode_table_size_1): * unicode.c (compute_from_unicode_table_size): * unicode.c (compute_to_unicode_table_size): * window.c: * window.c (struct window_stats): * window.c (compute_window_mirror_usage): * window.c (compute_window_usage): * window.c (window_memory_usage): * window.c (window_objects_create): * window.c (syms_of_window): * window.c (vars_of_window): * window.h: Redo memory-usage mechanism, make it general; add way of dynamically initializing Lisp object types -- OBJECT_HAS_METHOD(), similar to CONSOLE_HAS_METHOD(). (1) Create OBJECT_HAS_METHOD(), OBJECT_HAS_PROPERTY() etc. for specifying that a Lisp object type has a particular method or property. Call such methods with OBJECT_METH, MAYBE_OBJECT_METH, OBJECT_METH_OR_GIVEN; retrieve properties with OBJECT_PROPERTY. Methods that formerly required a DEFINE_*GENERAL_LISP_OBJECT() to specify them (getprop, putprop, remprop, plist, disksave) now instead use the dynamic-method mechanism. The main benefit of this is that new methods or properties can be added without requiring that the declaration statements of all existing methods be modified. We have to make the `struct lrecord_implementation' non-const, but I don't think this should have any effect on speed -- the only possible method that's really speed-critical is the mark method, and we already extract those out into a separate (non-const) array for increased cache locality. Object methods need to be reinitialized after pdump, so we put them in separate functions such as face_objects_create(), extent_objects_create() and call them appropriately from emacs.c The only current object property (`memusage_stats_list') that objects can specify is a Lisp object and gets staticpro()ed so it only needs to be set during dump time, but because it references symbols that might not exist in a syms_of_() function, we initialize it in vars_of_(). There is also an object property (`num_extra_memusage_stats') that is automatically initialized based on `memusage_stats_list'; we do that in reinit_vars_of_alloc(), which is called after all vars_of_() functions are called. `disksaver' method was renamed `disksave' to correspond with the name normally given to the function (e.g. disksave_lstream()). (2) Generalize the memory-usage mechanism in `buffer-memory-usage', `window-memory-usage', `charset-memory-usage' into an object-type- specific mechanism called by a single function `object-memory-usage'. (Former function `object-memory-usage' renamed to `total-object-memory-usage'). Generalize the mechanism of different "slices" so that we can have different "classes" of memory described and different "slices" onto each class; `t' separates classes, `nil' separates slices. Currently we have three classes defined: the memory of an object itself, non-Lisp-object memory associated with the object (e.g. arrays or dynarrs stored as fields in the object), and Lisp-object memory associated with the object (other internal Lisp objects stored in the object). This isn't completely finished yet and we might need to further separate the "other internal Lisp objects" class into two classes. The memory-usage mechanism uses a `struct usage_stats' (renamed from `struct overhead_stats') to describe a malloc-view onto a set of allocated memory (listing how much was requested and various types of overhead) and a more general `struct generic_usage_stats' (with a `struct usage_stats' in it) to hold all statistics about object memory. `struct generic_usage_stats' contains an array of 32 Bytecounts, which are statistics of unspecified semantics. The intention is that individual types declare a corresponding struct (e.g. `struct window_stats') with the same structure but with specific fields in place of the array, corresponding to specific statistics. The number of such statistics is an object property computed from the list of tags (Lisp symbols describing the statistics) stored in `memusage_stats_list'. The idea here is to allow particular object types to customize the number and semantics of the statistics where completely avoiding consing. This doesn't matter so much yet, but the intention is to have the memory usage of all objects computed at the end of GC, at the same time as other statistics are currently computed. The values for all statistics for a single type would be added up to compute aggregate values for all objects of a specific type. To make this efficient, we can't allow any memory allocation at all. (3) Create some additional functions for creating lists that specify the elements directly as args rather than indirectly through an array: listn() (number of args given), listu() (list terminated by Qunbound). (4) Delete a bit of remaining unused C window_config stuff, also unused lrecord_type_popup_data.
author Ben Wing <ben@xemacs.org>
date Thu, 18 Mar 2010 10:50:06 -0500
parents 026c5bf9c134
children 308d34e9f07d
line wrap: on
line source

;;; tibet-util.el --- utilities for Tibetan   -*- coding: iso-2022-7bit; -*-

;; Copyright (C) 1995 Electrotechnical Laboratory, JAPAN.
;; Licensed to the Free Software Foundation.

;; Keywords: multilingual, Tibetan

;; 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: Emacs 21.1 (language/tibet-util.el).

;; Author: Toru TOMABECHI, <Toru.Tomabechi@orient.unil.ch>

;; Created: Feb. 17. 1997

;;; History:
;; 1997.03.13 Modification in treatment of text properties;
;;            Support for some special signs and punctuations.
;; 1999.10.25 Modification for a new composition way by K.Handa.

;;; Commentary:

;;; Code:

;;;###autoload
(defun tibetan-char-p (ch)
  "Check if char CH is Tibetan character.
Returns non-nil if CH is Tibetan. Otherwise, returns nil."
  (memq (char-charset ch) '(tibetan tibetan-1-column)))

;;; Functions for Tibetan <-> Tibetan-transcription.

;;;###autoload
(defun tibetan-tibetan-to-transcription (str)
  "Transcribe Tibetan string STR and return the corresponding Roman string."
  (let (;; Accumulate transcriptions here in reverse order.
	(trans nil)
	(len (length str))
	(i 0)
	ch this-trans)
    (while (< i len)
      (let ((idx (string-match tibetan-precomposition-rule-regexp str i)))
	(if (eq idx i)
	    ;; Ith character and the followings matches precomposable
	    ;; Tibetan sequence.
	    (setq i (match-end 0)
		  this-trans
		  (car (rassoc
			(cdr (assoc (match-string 0 str)
				    tibetan-precomposition-rule-alist))
			tibetan-precomposed-transcription-alist)))
	  (setq ch (substring str i (1+ i))
		i (1+ i)
		this-trans
		(car (or (rassoc ch tibetan-consonant-transcription-alist)
			 (rassoc ch tibetan-vowel-transcription-alist)
			 (rassoc ch tibetan-subjoined-transcription-alist)))))
	(setq trans (cons this-trans trans))))
    (apply 'concat (nreverse trans))))

;;;###autoload
(defun tibetan-transcription-to-tibetan (str)
  "Convert Tibetan Roman string STR to Tibetan character string.
The returned string has no composition information."
  (let (;; Case is significant.
	(case-fold-search nil)
	(idx 0)
	;; Accumulate Tibetan strings here in reverse order.
	(t-str-list nil)
	i subtrans)
    (while (setq i (string-match tibetan-regexp str idx))
      (if (< idx i)
	  ;; STR contains a pattern that doesn't match Tibetan
	  ;; transcription.  Include the pattern as is.
	  (setq t-str-list (cons (substring str idx i) t-str-list)))
      (setq subtrans (match-string 0 str)
	    idx (match-end 0))
      (let ((t-char (cdr (assoc subtrans
				tibetan-precomposed-transcription-alist))))
	(if t-char
	    ;; SUBTRANS corresponds to a transcription for
	    ;; precomposable Tibetan sequence.
	    (setq t-char (car (rassoc t-char
				      tibetan-precomposition-rule-alist)))
	  (setq t-char
		(cdr
		 (or (assoc subtrans tibetan-consonant-transcription-alist)
		     (assoc subtrans tibetan-vowel-transcription-alist)
		     (assoc subtrans tibetan-modifier-transcription-alist)
		     (assoc subtrans tibetan-subjoined-transcription-alist)))))
	(setq t-str-list (cons t-char t-str-list))))
    (if (< idx (length str))
	(setq t-str-list (cons (substring str idx) t-str-list)))
    (apply 'concat (nreverse t-str-list))))

;;;
;;; Functions for composing/decomposing Tibetan sequence.
;;;
;;; A Tibetan syllable is typically structured as follows:
;;;
;;;      [Prefix] C [C+] V [M] [Suffix [Post suffix]]
;;;
;;; where C's are all vertically stacked, V appears below or above
;;; consonant cluster and M is always put above the C[C+]V combination.
;;; (Sanskrit visarga, though it is a vowel modifier, is considered
;;;  to be a punctuation.)
;;;
;;; Here are examples of the words "bsgrubs" and "hfauM"
;;;
;;;            4$(7"70"714%qx!"U0"G###C"U14"70"714"G0"G1(B            4$(7"Hx!"Rx!"Ur'"_0"H"R"U"_1(B
;;;
;;;                             M
;;;             b s b s         h
;;;               g             fa
;;;               r             u
;;;               u
;;;
;;; Consonants `'' ($(7"A(B), `w' ($(7">(B), `y' ($(7"B(B), `r' ($(7"C(B) take special
;;; forms when they are used as subjoined consonant.  Consonant `r'
;;; takes another special form when used as superjoined in such a case
;;; as "rka", while it does not change its form when conjoined with
;;; subjoined `'', `w' or `y' as in "rwa", "rya".

;; Append a proper composition rule and glyph to COMPONENTS to compose
;; CHAR with a composition that has COMPONENTS.

(defun tibetan-add-components (components char)
  (let ((last (last components))
	(stack-upper '(tc . bc))
	(stack-under '(bc . tc))
	rule comp-vowel ;tmp
	)
    ;; Special treatment for 'a chung.
    ;; If 'a follows a consonant, turn it into the subjoined form.
    ;; * Disabled by Tomabechi 2000/06/09 *
    ;; Because in Unicode, $(7"A(B may follow directly a consonant without
    ;; any intervening vowel, as in 4$(7"90"914""0"""Q14"A0"A1!;(B=4$(7"90"91(B 4$(7""0""1(B 4$(7"A0"A1(B not 4$(7"90"91(B 4$(7""0""1(B $(7"Q(B 4$(7"A0"A1(B  
    ;;(if (and (= char ?$(7"A(B)
    ;;	     (char-in-category-p (car last) ?0))
    ;;	(setq char ?$(7"R(B)) ;; modified for new font by Tomabechi 1999/12/10

    ;; Composite vowel signs are decomposed before being added
    ;; Added by Tomabechi 2000/06/08
    (if (memq char '(?$(7"T(B ?$(7"V(B ?$(7"W(B ?$(7"X(B ?$(7"Y(B ?$(7"Z(B ?$(7"b(B))
	(setq comp-vowel
	      (copy-sequence
	       (cddr (assoc (char-to-string char)
			    tibetan-composite-vowel-alist)))
	      char
	      (cadr (assoc (char-to-string char)
			   tibetan-composite-vowel-alist))))
    (cond
     ;; Compose upper vowel sign vertically over.
     ((char-in-category-p char ?2)
      (setq rule stack-upper))

     ;; Compose lower vowel sign vertically under.
     ((char-in-category-p char ?3)
      (if (eq char ?$(7"Q(B)		;; `$(7"Q(B' should not visible when composed.
	  (setq rule nil)
	(setq rule stack-under)))
     ;; Transform ra-mgo (superscribed r) if followed by a subjoined
     ;; consonant other than w, ', y, r.
     ((and (= (car last) ?$(7"C(B)
	   (not (memq char '(?$(7#>(B ?$(7"R(B ?$(7#B(B ?$(7#C(B))))
      (setcar last ?$(7!"(B) ;; modified for newfont by Tomabechi 1999/12/10
      (setq rule stack-under))
     ;; Transform initial base consonant if followed by a subjoined
     ;; consonant but 'a.
     (t
      (let ((laststr (char-to-string (car last))))
	(if (and (/= char ?$(7"R(B) ;; modified for new font by Tomabechi
		 (string-match "[$(7"!(B-$(7"="?"@"D(B-$(7"J"K(B]" laststr))
	    (setcar last (string-to-char
			  (cdr (assoc (char-to-string (car last))
				      tibetan-base-to-subjoined-alist)))))
	(setq rule stack-under))))

    (if rule
	(setcdr last (list rule char)))
    ;; Added by Tomabechi 2000/06/08
    (if comp-vowel
	(nconc last comp-vowel))
    ))

;;;###autoload
(defun tibetan-compose-string (str)
  "Compose Tibetan string STR."
  (let ((idx 0))
    ;; `$(7"A(B' is included in the pattern for subjoined consonants
    ;; because we treat it specially in tibetan-add-components.
    ;; (This feature is removed by Tomabechi 2000/06/08)
    (while (setq idx (string-match tibetan-composable-pattern str idx))
      (let ((from idx)
	    (to (match-end 0))
	    components)
	(if (eq (string-match tibetan-precomposition-rule-regexp str idx) idx)
	    (setq idx (match-end 0)
		  components
		  (list (string-to-char
			 (cdr
			  (assoc (match-string 0 str)
				 tibetan-precomposition-rule-alist)))))
	  (setq components (list (aref str idx))
		idx (1+ idx)))
	(while (< idx to)
	  (tibetan-add-components components (aref str idx))
	  (setq idx (1+ idx)))
	(compose-string str from to components))))
  str)

;;;###autoload
(defun tibetan-compose-region (beg end)
  "Compose Tibetan text the region BEG and END."
  (interactive "r")
  ;(let (str result chars)
    (save-excursion
      (save-restriction
	(narrow-to-region beg end)
	(goto-char (point-min))
	;; `$(7"A(B' is included in the pattern for subjoined consonants
	;; because we treat it specially in tibetan-add-components.
	;; (This feature is removed by Tomabechi 2000/06/08)
	(while (re-search-forward tibetan-composable-pattern nil t)
	  (let ((from (match-beginning 0))
		(to (match-end 0))
		components)
	    (goto-char from)
	    (if (looking-at tibetan-precomposition-rule-regexp)
		(progn
		  (setq components
			(list (string-to-char
			       (cdr
				(assoc (match-string 0)
				       tibetan-precomposition-rule-alist)))))
		  (goto-char (match-end 0)))
	      (setq components (list (char-after from)))
	      (forward-char 1))
	    (while (< (point) to)
	      (tibetan-add-components components (following-char))
	      (forward-char 1))
	    (compose-region from to components)))))
    ;)
    )

(defvar tibetan-decompose-precomposition-alist
  (mapcar (function (lambda (x) (cons (string-to-char (cdr x)) (car x))))
	  tibetan-precomposition-rule-alist))

;;;###autoload
(defun tibetan-decompose-region (from to)
  "Decompose Tibetan text in the region FROM and TO.
This is different from decompose-region because precomposed Tibetan characters
are decomposed into normal Tiebtan character sequences."
  (interactive "r")
  (save-restriction
    (narrow-to-region from to)
    (decompose-region from to)
    (goto-char from)
    (while (not (eobp))
      (let* ((char (following-char))
	     (slot (assq char tibetan-decompose-precomposition-alist)))
	(if slot
	    (progn
	      (delete-char 1)
	      (insert (cdr slot)))
	  (forward-char 1))))))


;;;###autoload
(defun tibetan-decompose-string (str)
  "Decompose Tibetan string STR.
This is different from decompose-string because precomposed Tibetan characters
are decomposed into normal Tiebtan character sequences."
  (let ((new "")
	(len (length str))
	(idx 0)
	char slot)
    (while (< idx len)
      (setq char (aref str idx)
	    slot (assq (aref str idx) tibetan-decompose-precomposition-alist)
	    new (concat new (if slot (cdr slot) (char-to-string char)))
	    idx (1+ idx)))
    new))

;;;###autoload
(defun tibetan-composition-function (from to pattern &optional string)
  (if string
      (tibetan-compose-string string)
    (tibetan-compose-region from to))
  (- to from))

;;;
;;; This variable is used to avoid repeated decomposition.
;;;
(setq-default tibetan-decomposed nil)

;;;###autoload
(defun tibetan-decompose-buffer ()
  "Decomposes Tibetan characters in the buffer into their components.
See also the documentation of the function `tibetan-decompose-region'."
  (interactive)
  (make-local-variable 'tibetan-decomposed)
  (cond ((not tibetan-decomposed)
	 (tibetan-decompose-region (point-min) (point-max))
	 (setq tibetan-decomposed t))))

;;;###autoload
(defun tibetan-compose-buffer ()
  "Composes Tibetan character components in the buffer.
See also docstring of the function tibetan-compose-region."
  (interactive)
  (make-local-variable 'tibetan-decomposed)
  (tibetan-compose-region (point-min) (point-max))
  (setq tibetan-decomposed nil))

;;;###autoload
(defun tibetan-post-read-conversion (len)
  (save-excursion
    (save-restriction
      (let ((buffer-modified-p (buffer-modified-p)))
	(narrow-to-region (point) (+ (point) len))
	(tibetan-compose-region (point-min) (point-max))
	(set-buffer-modified-p buffer-modified-p)
	(make-local-variable 'tibetan-decomposed)
	(setq tibetan-decomposed nil)
	(- (point-max) (point-min))))))


;;;###autoload
(defun tibetan-pre-write-conversion (from to)
  (setq tibetan-decomposed-temp tibetan-decomposed)
  (let ((old-buf (current-buffer)))
    (set-buffer (generate-new-buffer " *temp*"))
    (if (stringp from)
	(insert from)
      (insert-buffer-substring old-buf from to))
    (if (not tibetan-decomposed-temp)
	(tibetan-decompose-region (point-min) (point-max)))
    ;; Should return nil as annotations.
    nil))

(provide 'tibet-util)

;;; tibet-util.el ends here