Mercurial > hg > xemacs-beta

view lisp/mule/european.el @ 1292:f3437b56874d

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
[xemacs-hg @ 2003-02-13 09:57:04 by ben] profile updates profile.c: Major reworking. Keep track of new information -- total function timing (includes descendants), GC usage, total GC usage (includes descendants). New functions to be called appropriately from eval.c, alloc.c to keep track of this information. Keep track of when we're actually in a function vs. in its profile, for more accurate timing counts. Track profile overhead separately. Create new mechanism for specifying "internal sections" that are tracked just like regular Lisp functions and even appear in the backtrace if `backtrace-with-internal-sections' is non-nil (t by default for error-checking builds). Add some KKCC information for the straight (non-Elisp) hash table used by profile, which contains Lisp objects in its keys -- but not used yet. Remove old ad-hoc methods for tracking garbage collection, redisplay (which was incorrect anyway when Lisp was called within these sections). Don't record any tick info when blocking under MS Windows, since the timer there is in real time rather than in process time. Make `start-profiling', `stop-profiling' interactive. Be consistent wrt. recursive functions and functions currently on the stack when starting or stopping -- together these make implementing the `total' values extremely difficult. When we start profiling, we act as if we just entered all the functions currently on the stack. Likewise when exiting. Create vars in_profile for tracking time spent inside of profiling, and profiling_lock for setting exclusive access to the main hash table when reading from it or modifying it. (protects against getting screwed up by the signal handle going off at the same time. profile.h: New file. Create macros for declaring internal profiling sections. lisp.h: Move profile-related stuff to profile.h. alloc.c: Keep track of total consing, for profile. Tell profile when we are consing. Use new profile-section method for noting garbage-collection. alloc.c: Abort if we attempt to call the allocator reentrantly. backtrace.h, eval.c: Add info for use by profile in the backtrace frame and transfer PUSH_BACKTRACE/POP_BACKTRACE from eval.c, for use with profile. elhash.c: Author comment. eval.c, lisp.h: New Lisp var `backtrace-with-internal-sections'. Set to t when error-checking is on. eval.c: When unwinding, eval.c: Report to profile when we are about-to-call and just-called wrt. a function. alloc.c, eval.c: Allow for "fake" backtrace frames, for internal sections (used by profile and `backtrace-with-internal-sections'. event-Xt.c, event-gtk.c, event-msw.c, event-tty.c: Record when we are actually blocking on an event, for profile's sake. event-stream.c: Record internal profiling sections for getting, dispatching events. extents.c: Record internal profiling sections for map_extents. hash.c, hash.h: Add pregrow_hash_table_if_necessary(). (Used in profile code since the signal handler is the main grower but can't allow a realloc(). We make sure, at critical points, that the table is large enough.) lread.c: Create internal profiling sections for `load' (which may be triggered internally by autoload, etc.). redisplay.c: Remove old profile_redisplay_flag. Use new macros to declare internal profiling section for redisplay. text.c: Use new macros to declare internal profiling sections for char-byte conversion and internal-external conversion. SEMI-UNRELATED CHANGES: ----------------------- text.c: Update the long comments.
author ben
date Thu, 13 Feb 2003 09:57:08 +0000
parents 42375619fa45
children e71117a6ddac
line wrap: on
line source

;;; european.el --- European languages -*- coding: iso-2022-7bit; -*-

;; Copyright (C) 1995 Electrotechnical Laboratory, JAPAN.
;; Licensed to the Free Software Foundation.
;; Copyright (C) 1997 MORIOKA Tomohiko
;; Copyright (C) 2001 Ben Wing.
;; Copyright (C) 2002 Free Software Foundation

;; Keywords: multilingual, European

;; 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.

;;; Commentary:

;; For Europeans, six coded character sets ISO8859-1,2,3,4,9 are supported.
;; Note: ISO 8859/15 (Latin-9) is supported via the latin-unity package.

;; #### latin.el would be a better name for this file.

;;; Code:
; (make-charset 'latin-iso8859-1 
; 	      "Right-Hand Part of Latin Alphabet 1 (ISO/IEC 8859-1): ISO-IR-100"
; 	      '(dimension
; 		1
; 		registry "ISO8859-1"
; 		chars 96
; 		columns 1
; 		direction l2r
; 		final ?A
; 		graphic 1
; 		short-name "RHP of Latin-1"
; 		long-name "RHP of Latin-1 (ISO 8859-1): ISO-IR-100"
; 		))

; (make-charset 'latin-iso8859-2 
; 	      "Right-Hand Part of Latin Alphabet 2 (ISO/IEC 8859-2): ISO-IR-101"
; 	      '(dimension
; 		1
; 		registry "ISO8859-2"
; 		chars 96
; 		columns 1
; 		direction l2r
; 		final ?B
; 		graphic 1
; 		short-name "RHP of Latin-2"
; 		long-name "RHP of Latin-2 (ISO 8859-2): ISO-IR-101"
; 		))

; (make-charset 'latin-iso8859-3 
; 	      "Right-Hand Part of Latin Alphabet 3 (ISO/IEC 8859-3): ISO-IR-109"
; 	      '(dimension
; 		1
; 		registry "ISO8859-3"
; 		chars 96
; 		columns 1
; 		direction l2r
; 		final ?C
; 		graphic 1
; 		short-name "RHP of Latin-3"
; 		long-name "RHP of Latin-3 (ISO 8859-3): ISO-IR-109"
; 		))

; (make-charset 'latin-iso8859-4 
; 	      "Right-Hand Part of Latin Alphabet 4 (ISO/IEC 8859-4): ISO-IR-110"
; 	      '(dimension
; 		1
; 		registry "ISO8859-4"
; 		chars 96
; 		columns 1
; 		direction l2r
; 		final ?D
; 		graphic 1
; 		short-name "RHP of Latin-4"
; 		long-name "RHP of Latin-4 (ISO 8859-4): ISO-IR-110"
; 		))

; (make-charset 'latin-iso8859-9 
; 	      "Right-Hand Part of Latin Alphabet 5 (ISO/IEC 8859-9): ISO-IR-148"
; 	      '(dimension
; 		1
; 		registry "ISO8859-9"
; 		chars 96
; 		columns 1
; 		direction l2r
; 		final ?M
; 		graphic 1
; 		short-name "RHP of Latin-5"
; 		long-name "RHP of Latin-5 (ISO 8859-9): ISO-IR-148"
; 		))

; (make-charset 'latin-iso8859-15 
; 	      "Right-Hand Part of Latin Alphabet 9 (ISO/IEC 8859-15): ISO-IR-203"
; 	      '(dimension
; 		1
; 		registry "ISO8859-15"
; 		chars 96
; 		columns 1
; 		direction l2r
; 		final ?b
; 		graphic 1
; 		short-name "RHP of Latin-9"
; 		long-name "RHP of Latin-9 (ISO 8859-15): ISO-IR-203"
; 		))

(make-charset 'latin-iso8859-14 
	      "Right-Hand Part of Latin Alphabet 8 (ISO/IEC 8859-14)"
	      '(dimension
		1
		registry "ISO8859-14"
		chars 96
		columns 1
		direction l2r
		final ?_
		graphic 1
		short-name "RHP of Latin-8"
		long-name "RHP of Latin-8 (ISO 8859-14)"
		))


;; For syntax of Latin-1 characters.
(loop for c from 64 to 127              ; from ',A@(B' to ',A(B'
      do (modify-syntax-entry (make-char 'latin-iso8859-1 c) "w"))

(modify-syntax-entry (make-char 'latin-iso8859-1 32) "w") ; no-break space
(modify-syntax-entry ?,AW(B "_")
(modify-syntax-entry ?,Aw(B "_")

;; For syntax of Latin-9 characters.
;; Based on Latin-1 and differences from Jukka Korpela
;; http://www.cs.tut.fi/~jkorpela/latin9.html
(loop for c in '(?,b&(B ?,b((B ?,b4(B ?,b8(B ?,b<(B ?,b=(B ?,b>(B)
      do (modify-syntax-entry c "w"))

(loop for c from 64 to 127              ; from ',b@(B' to ',b(B'
      do (modify-syntax-entry (make-char 'latin-iso8859-1 c) "w"))

(modify-syntax-entry (make-char 'latin-iso8859-15 32) "w") ; no-break space
(modify-syntax-entry ?,bW(B "_")
(modify-syntax-entry ?,bw(B "_")

;; For syntax of Latin-2
(loop for c in '(?,B!(B ?,B#(B ?,B%(B ?,B&(B ?,B)(B ?,B*(B ?,B+(B ?,B,(B ?,B.(B ?,B/(B ?,B1(B ?,B3(B ?,B5(B ?,B6(B ?,B9(B ?,B:(B ?,B;(B ?,B<(B)
      do (modify-syntax-entry c "w"))

(loop for c from 62 to 126
      do (modify-syntax-entry (make-char 'latin-iso8859-2 c) "w"))

(modify-syntax-entry (make-char 'latin-iso8859-2 32) "w") ; no-break space
(modify-syntax-entry ?,BW(B ".")
(modify-syntax-entry ?,Bw(B ".")

;; For syntax of Latin-3
(loop for c in '(?,C!(B ?,C&(B ?,C)(B ?,C*(B ?,C+(B ?,C,(B ?,C/(B ?,C1(B ?,C5(B ?,C6(B ?,C:(B ?,C;(B ?,C<(B ?,C?(B)
  do (modify-syntax-entry c "w"))

(loop for c from 64 to 126
  do (modify-syntax-entry (make-char 'latin-iso8859-3 c) "w"))

(modify-syntax-entry (make-char 'latin-iso8859-3 32) "w") ; no-break space
(modify-syntax-entry ?,CW(B ".")
(modify-syntax-entry ?,Cw(B ".")

;; For syntax of Latin-4
(loop for c in '(?,D!(B ?,D"(B ?,D#(B ?,D%(B ?,D&(B ?,D)(B ?,D*(B ?,D+(B ?,D,(B ?,D.(B ?,D1(B ?,D3(B ?,D5(B ?,D6(B ?,D9(B ?,D:(B ?,D;(B ?,D<(B ?,D=(B ?,D>(B ?,D?(B)
  do (modify-syntax-entry c "w"))

(loop for c from 64 to 126
  do (modify-syntax-entry (make-char 'latin-iso8859-4 c) "w"))

(modify-syntax-entry (make-char 'latin-iso8859-4 32) "w") ; no-break space
(modify-syntax-entry ?,DW(B ".")
(modify-syntax-entry ?,Dw(B ".")


;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
;;; EUROPEANS
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;


;; Latin-1 (ISO-8859-1)

;; (make-coding-system
;;  'iso-latin-1 2 ?1
;;  "ISO 2022 based 8-bit encoding for Latin-1 (MIME:ISO-8859-1)"
;;  '(ascii latin-iso8859-1 nil nil
;;    nil nil nil nil nil nil nil nil nil nil nil nil t)
;;  '((safe-charsets ascii latin-iso8859-1)
;;    (mime-charset . iso-8859-1)))

;; (define-coding-system-alias 'iso-8859-1 'iso-latin-1)
;; (define-coding-system-alias 'latin-1 'iso-latin-1)

;; (make-coding-system
;;  'compound-text 2 ?1
;;  "ISO 2022 based encoding used in inter client communication of X"
;;  '((ascii t) (latin-iso8859-1 t) nil nil
;;    nil ascii-eol ascii-cntl nil nil nil nil nil nil nil nil nil t)
;;  '((safe-charsets . t)))

;; (define-coding-system-alias 'ctext 'compound-text)

;; "Hello, Hej, Tere, Hei, Bonjour, Gr,A|_(B Gott, Ciao, ,A!(BHola!"


;; Latin-9 (ISO-8859-15)
;; Latin-1 plus Euro, plus a few accented characters

;; (make-charset 'latin-iso8859-15
;;   "Latin-9, aka Latin-1 with Euro etc"
;;   '(short-name "Latin 9"
;;     long-name  "Latin-9 (typically GR of ISO 8859/15)"
;;     registry   "iso8859-15"
;;     dimension  1
;;     columns    1
;;     chars      96
;;     final      ?b                  ; ISO-IR-203
;;     graphic    1
;;     direction  l2r))

(make-coding-system
 'iso-8859-15 'iso2022
  "ISO 4873 conforming 8-bit code (ASCII + Latin 9; aka Latin-1 with Euro)"
  `(mnemonic "MIME/Ltn-9"		; bletch
    eol-type nil
    charset-g0 ascii
    charset-g1 latin-iso8859-15
    charset-g2 t
    charset-g3 t
    ))


;; Latin-2 (ISO-8859-2)

;; (make-coding-system
;;  'iso-latin-2 2 ?2
;;  "ISO 2022 based 8-bit encoding (MIME:ISO-8859-2)"
;;  '(ascii latin-iso8859-2 nil nil
;;    nil nil nil nil nil nil nil)
;;  '((safe-charsets ascii latin-iso8859-2)
;;    (mime-charset . iso-8859-2)))

;; (define-coding-system-alias 'iso-8859-2 'iso-latin-2)
;; (define-coding-system-alias 'latin-2 'iso-latin-2)

(make-coding-system
 'iso-8859-2 'iso2022 "ISO-8859-2 (Latin-2)"
 '(charset-g0 ascii
   charset-g1 latin-iso8859-2
   charset-g2 t
   charset-g3 t
   mnemonic "MIME/Ltn-2"
   ))

(provide 'romanian)

;; Czech support originally from czech.el
;; Author: Milan Zamazal <pdm@zamazal.org>
;; Maintainer (FSF): Pavel Jan,Am(Bk <Pavel@Janik.cz>
;; Maintainer (for XEmacs): David Sauer <davids@penguin.cz>

(provide 'czech)

;; Slovak support originally from slovak.el
;; Authors:    Tibor ,B)(Bimko <tibor.simko@fmph.uniba.sk>,
;;             Milan Zamazal <pdm@fi.muni.cz>
;; Maintainer: Milan Zamazal <pdm@fi.muni.cz>

(provide 'slovenian)


;; Latin-3 (ISO-8859-3)

;; (make-coding-system
;;  'iso-latin-3 2 ?3
;;  "ISO 2022 based 8-bit encoding (MIME:ISO-8859-3)"
;;  '(ascii latin-iso8859-3 nil nil
;;    nil nil nil nil nil nil nil)
;;  '((safe-charsets ascii latin-iso8859-3)
;;    (mime-charset . iso-8859-3)))

;; (define-coding-system-alias 'iso-8859-3 'iso-latin-3)
;; (define-coding-system-alias 'latin-3 'iso-latin-3)

(make-coding-system
 'iso-8859-3 'iso2022 "ISO-8859-3 (Latin-3)"
 '(charset-g0 ascii
   charset-g1 latin-iso8859-3
   charset-g2 t
   charset-g3 t
   mnemonic "MIME/Ltn-3"
   ))


;; Latin-4 (ISO-8859-4)

;; (make-coding-system
;;  'iso-latin-4 2 ?4
;;  "ISO 2022 based 8-bit encoding (MIME:ISO-8859-4)"
;;  '(ascii latin-iso8859-4 nil nil
;;    nil nil nil nil nil nil nil)
;;  '((safe-charsets ascii latin-iso8859-4)
;;    (mime-charset . iso-8895-4)))

;; (define-coding-system-alias 'iso-8859-4 'iso-latin-4)
;; (define-coding-system-alias 'latin-4 'iso-latin-4)

(make-coding-system
 'iso-8859-4 'iso2022 "ISO-8859-4 (Latin-4)"
 '(charset-g0 ascii
   charset-g1 latin-iso8859-4
   charset-g2 t
   charset-g3 t
   mnemonic "MIME/Ltn-4"
   ))


;; Latin-5 (ISO-8859-9)

;; (make-coding-system
;;  'iso-latin-5 2 ?9
;;  "ISO 2022 based 8-bit encoding (MIME:ISO-8859-9)"
;;  '(ascii latin-iso8859-9 nil nil
;;    nil nil nil nil nil nil nil)
;;  '((safe-charsets ascii latin-iso8859-9)
;;    (mime-charset . iso-8859-9)))

;; (define-coding-system-alias 'iso-8859-9 'iso-latin-5)
;; (define-coding-system-alias 'latin-5 'iso-latin-5)

(make-coding-system
 'iso-8859-9 'iso2022 "ISO-8859-9 (Latin-5)"
 '(charset-g0 ascii
   charset-g1 latin-iso8859-9
   charset-g2 t
   charset-g3 t
   mnemonic "MIME/Ltn-5"
   ))

(loop for ((charset codesys default-input nice-charset-1 nice-charset-2
		    supported-langs ;; a list if the doc string is replaced
				    ;; entirely
		    )
	   langenvs) in
  '(
    ((latin-iso8859-1 iso-8859-1 "latin-1-prefix" "Latin-1" "ISO-8859-1"
" Danish, Dutch, English, Faeroese, Finnish, French, German, Icelandic,
 Irish, Italian, Norwegian, Portuguese, Spanish, and Swedish.")
     (("Danish" "da")
      ("Dutch" "nl" "TUTORIAL.nl")
      ("Faeroese")
      ("Finnish" "fi")
      ("French" "fr" "TUTORIAL.fr" "Bonjour, ,Ag(Ba va?")
      ("German" "de" "TUTORIAL.de" "\
German (Deutsch Nord)	Guten Tag
German (Deutsch S,A|(Bd)	Gr,A|_(B Gott"
       "german-postfix")
      ("Icelandic" "is")
      ("Irish" "ga")
      ("Italian" "it")
      ("Norwegian" "no" "TUTORIAL.no")
      ("Portuguese" "pt" nil "Bem-vindo! Tudo bem?")
      ("Spanish" "es" "TUTORIAL.es" ",A!(BHola!")
      ("Swedish" "sv" "TUTORIAL.se" "Hej!")))
    ((latin-iso8859-15 iso-8859-15 "latin-1-prefix" ;; #### FIXME
		       "Latin-9" "ISO-8859-15"
		       ("\
This language environment is a generic one for Latin-9 (ISO-8859-15)
character set which supports the Euro sign and the following languages
(they use the Latin-1 character set by default):
 Danish, Dutch, English, Faeroese, Finnish, French, German, Icelandic,
 Irish, Italian, Norwegian, Portuguese, Spanish, and Swedish.
Each also has its own specific language environment."))
     ())
    ((latin-iso8859-2 iso-8859-2 "latin-2-prefix" "Latin-2" "ISO-8859-2"
" Albanian, Czech, English, German, Hungarian, Polish, Romanian,
 Serbian, Croatian, Slovak, Slovene, Sorbian (upper and lower),
 and Swedish.")
     (("Albanian" nil)
      ("Croatian" ("hrvatski" "hr") "TUTORIAL.hr")
      ("Czech" ("cs" "cz") "TUTORIAL.cs" "P,Bx(Bejeme v,Ba(Bm hezk,B}(B den!"
       "latin-2-postfix")
      ("Hungarian" ("hungarian" "hu"))
      ("Polish" "po" "TUTORIAL.pl")
      ("Romanian" "ro" "TUTORIAL.ro" "Bun,Bc(B ziua, bine a,B~(Bi venit!"
       "latin-2-postfix")
      ("Serbian" "sr")
      ("Slovak" "sk" "TUTORIAL.sk" "Prajeme V,Ba(Bm pr,Bm(Bjemn,B}(B de,Br(B!"
       ;; !!#### FSF "slovak"
       "latin-2-postfix")
      ("Slovenian" "sl" "TUTORIAL.sl" ",B.(Belimo vam uspe,B9(Ben dan!"
       "latin-2-postfix")
      ("Sorbian" nil)))
    ((latin-iso8859-3 iso-8859-3 "latin-3-prefix" "Latin-3" "ISO-8859-3"
" Afrikaans, Catalan, Dutch, English, Esperanto, French, Galician,
 German, Italian, Maltese, Spanish, and Turkish.")
     (("Afrikaans" "af")
      ("Catalan" ("catalan" "ca"))
      ("Esperanto")
      ("Galician")
      ("Maltese")))
    ((latin-iso8859-4 iso-8859-4 "latin-4-prefix" "Latin-4" "ISO-8859-4"
" Danish, English, Estonian, Finnish, German, Greenlandic, Lappish,
 Latvian, Lithuanian, and Norwegian.")
     (("Estonian" "et")
      ("Greenlandic")
      ("Lappish")
      ("Latvian" "lv")
      ("Lithuanian" "li")))
    ((latin-iso8859-5 iso-8859-9 "latin-5-prefix" "Latin-5" "ISO-8859-9")
     (("Turkish" "tr"))))
  do
  (set-language-info-alist
   nice-charset-1
   `((charset ascii ,charset)
     (coding-system ,codesys)
     (coding-priority ,codesys)
     (documentation . ,(if (listp supported-langs) (car supported-langs)
			 (format "\
This language environment is a generic one for %s (%s)
character set which supports the following languages (not all of them may
use this character set by default):
%s
Each also has its own specific language environment."
				 nice-charset-1 nice-charset-2
				 supported-langs))))
   '("European"))
  (loop for (name locale tutorial sample-text input-method) in langenvs
    do
    (set-language-info-alist
     name
     `((charset ascii ,charset)
       (coding-system ,codesys)
       (coding-priority ,codesys)
       ,@(if locale `((locale . ,locale)))
       ,@(if tutorial `((tutorial . ,tutorial)))
       ,@(if sample-text `((sample-text . ,sample-text)))
       (input-method . ,(or input-method default-input))
       (documentation . ,(format "\
This language environment supports %s using the Latin-1 (ISO-8859-1)
character set.  Languages supported by Latin-1 are Danish, Dutch, English,
Faeroese, Finnish, French, German, Icelandic, Irish, Italian, Norwegian,
Portuguese, Spanish, and Swedish.  The various language environments for
these languages are similar to the Latin-1 environment, but typically have
their own locale specified (for subprocesses and for selection of the
correct language environment at startup), and may have their own tutorials
and/or a different input method."
			       name)))
     '("European"))
    ))

;;; european.el ends here