June 2006 - xemacs-cvs＠xemacs.org - XEmacs Mailing List Archives

CVS update by adrian xemacs-builds/adrian/website 17 years, 10 months

CVS Monitor

, update-about-created-from-article-buffer.el ... User: adrian Date: 06/06/05 17:11:41 Modified: xemacs-builds/adrian/website update-about-created-from-article-buffer.el Log: minor edit Revision Changes Path 1.4 +2 -0 XEmacs/xemacs-builds/adrian/website/update-about-created-from-article-buffer.el Index: update-about-created-from-article-buffer.el =================================================================== RCS file: /pack/xemacscvs/XEmacs/xemacs-builds/adrian/website/update-about-created-from-article-buffer.el,v retrieving revision 1.3 retrieving revision 1.4 diff -u -p -r1.3 -r1.4 --- update-about-created-from-article-buffer.el 2003/03/18 19:43:44 1.3 +++ update-about-created-from-article-buffer.el 2006/06/05 15:11:40 1.4 ＠＠ -1,3 +1,5 ＠＠ +; Adrian Aichner <adrian(a)xemacs.org>, The XEmacs Project, 2002-08-18. + (defun update-about-created-from-article-buffer () "Updates buffer \"created.content\" with entry for URL: and TITLE: fields in \"*Article*\" buffer."

1 participants
0 comments

CVS update by viteno xemacs ... 17 years, 10 months

CVS Monitor

User: viteno Date: 06/06/04 23:51:04 Modified: xemacs version.sh Log: Update xemacs_extra_name. Revision Changes Path 1.1552 +1 -1 XEmacs/xemacs/version.sh Index: version.sh =================================================================== RCS file: /pack/xemacscvs/XEmacs/xemacs/version.sh,v retrieving revision 1.1551 retrieving revision 1.1552 diff -u -p -r1.1551 -r1.1552 --- version.sh 2006/06/03 21:51:10 1.1551 +++ version.sh 2006/06/04 21:51:03 1.1552 ＠＠ -8,5 +8,5 ＠＠ emacs_kit_version= infodock_major_version=4 infodock_minor_version=0 infodock_build_version=8 -xemacs_extra_name="(+CVS-20060603)" +xemacs_extra_name="(+CVS-20060604)" xemacs_release_date="2006-05-16"

1 participants
0 comments

CVS update by viteno xemacs-builds/viteno ... 17 years, 10 months

CVS Monitor

User: viteno Date: 06/06/04 22:43:23 Modified: xemacs-builds/viteno package-index Log: Package database backup: - leim-1.23 Revision Changes Path 1.297 +6 -6 XEmacs/xemacs-builds/viteno/package-index Index: package-index =================================================================== RCS file: /pack/xemacscvs/XEmacs/xemacs-builds/viteno/package-index,v retrieving revision 1.296 retrieving revision 1.297 diff -u -p -r1.296 -r1.297 --- package-index 2006/06/02 09:41:33 1.296 +++ package-index 2006/06/04 20:43:22 1.297 ＠＠ -1075,19 +1075,19 ＠＠ (package-get-update-base-entry (quote (leim (standards-version 1.1 - version "1.22" + version "1.23" author-version "No-Upstream-Ver" - date "2003-10-31" - build-date "2003-10-31" + date "2006-06-04" + build-date "2006-06-04" maintainer "XEmacs Development Team <xemacs-beta(a)xemacs.org>" distribution mule priority medium category "mule" dump nil description "MULE: Quail. All non-English and non-Japanese language support." - filename "leim-1.22-pkg.tar.gz" - md5sum "942fbcd4d56eb59529bbd15c3b6c0b3b" - size 1708319 + filename "leim-1.23-pkg.tar.gz" + md5sum "7069e5bb013bbb3ad404b5729b848aee" + size 1708544 provides () requires (leim mule-base fsf-compat xemacs-base) type regular

1 participants
0 comments

CVS update by viteno packages/mule-packages/leim ... 17 years, 10 months

CVS Monitor

User: viteno Date: 06/06/04 22:28:47 Modified: packages/mule-packages/leim ChangeLog Makefile Log: Increment VERSION in Makefile Revision Changes Path 1.28 +4 -0 XEmacs/packages/mule-packages/leim/ChangeLog Index: ChangeLog =================================================================== RCS file: /pack/xemacscvs/XEmacs/packages/mule-packages/leim/ChangeLog,v retrieving revision 1.27 retrieving revision 1.28 diff -u -p -r1.27 -r1.28 --- ChangeLog 2006/06/03 06:58:18 1.27 +++ ChangeLog 2006/06/04 20:28:47 1.28 ＠＠ -1,3 +1,7 ＠＠ +2006-06-04 Norbert Koch <viteno(a)xemacs.org> + + * Makefile (VERSION): XEmacs package 1.23 released. + 2006-06-03 Aidan Kehoe <kehoea(a)parhasard.net> * quail.el (quail-define-rules): 1.33 +1 -1 XEmacs/packages/mule-packages/leim/Makefile Index: Makefile =================================================================== RCS file: /pack/xemacscvs/XEmacs/packages/mule-packages/leim/Makefile,v retrieving revision 1.32 retrieving revision 1.33 diff -u -p -r1.32 -r1.33 --- Makefile 2003/10/31 17:19:52 1.32 +++ Makefile 2006/06/04 20:28:47 1.33 ＠＠ -17,7 +17,7 ＠＠ # the Free Software Foundation, Inc., 59 Temple Place - Suite 330, # Boston, MA 02111-1307, USA. -VERSION = 1.22 +VERSION = 1.23 AUTHOR_VERSION = MAINTAINER = XEmacs Development Team <xemacs-beta(a)xemacs.org> PACKAGE = leim

1 participants
0 comments

CVS update by viteno packages ... 17 years, 10 months

CVS Monitor

User: viteno Date: 06/06/04 22:28:10 Modified: packages ChangeLog Log: Package release Revision Changes Path 1.625 +4 -0 XEmacs/packages/ChangeLog Index: ChangeLog =================================================================== RCS file: /pack/xemacscvs/XEmacs/packages/ChangeLog,v retrieving revision 1.624 retrieving revision 1.625 diff -u -p -r1.624 -r1.625 --- ChangeLog 2006/06/02 09:38:01 1.624 +++ ChangeLog 2006/06/04 20:28:10 1.625 ＠＠ -1,3 +1,7 ＠＠ +2006-06-04 Norbert Koch <viteno(a)xemacs.org> + + * Packages released: leim. + 2006-06-02 Norbert Koch <viteno(a)xemacs.org> * Packages released: xemacs-base.

1 participants
0 comments

CVS update by adrian xemacs-builds/adrian/website apa-linklint-utils.el 17 years, 11 months

CVS Monitor

User: adrian Date: 06/06/04 15:20:53 Added: xemacs-builds/adrian/website apa-linklint-utils.el Log: Initial lightly tested version. Revision Changes Path 1.1 XEmacs/xemacs-builds/adrian/website/apa-linklint-utils.el Index: apa-linklint-utils.el =================================================================== ; Adrian Aichner <adrian(a)xemacs.org>, The XEmacs Project, 2006-06-04. (defun apa-linklint-compilation-finish-function (buffer message) (with-current-buffer buffer (goto-char (point-min)) (sort-numeric-fields 5 (re-search-forward "^Compilation started.+\n" nil nil nil buffer) (and (goto-char (point-max buffer)) (re-search-backward "\n\n" nil nil nil buffer))) (if (fboundp 'apa-save-compilation) (apa-save-compilation nil)))) (defun apa-linklint-compilation-mode-hook nil (make-variable-buffer-local 'compilation-finish-function) (setq compilation-finish-function 'apa-linklint-compilation-finish-function) (insert (format "Compilation started at %s %+.4d (%s)\n" (current-time-string) (/ (nth 0 (current-time-zone)) 36) (nth 1 (current-time-zone))))) (defun apa-linklint-were-ok-urlsum (directory) "Search linklint urlsum.txt files for number of links that \"were ok, \". Files are searched recursively by `igrep-find'. The resulting igrep buffer is sorted by number of failed links and offered to be saved by use of `apa-save-compilation'. " (interactive (list (read-directory-name "linklint output directory"))) (save-excursion (let ((compilation-mode-hook 'apa-linklint-compilation-mode-hook)) (igrep-find "grep" "were ok, " '("urlsum.txt") "-Pi"))))

1 participants
0 comments

CVS update by viteno xemacs ... 17 years, 11 months

CVS Monitor

User: viteno Date: 06/06/03 23:51:11 Modified: xemacs version.sh Log: Update xemacs_extra_name. Revision Changes Path 1.1551 +1 -1 XEmacs/xemacs/version.sh Index: version.sh =================================================================== RCS file: /pack/xemacscvs/XEmacs/xemacs/version.sh,v retrieving revision 1.1550 retrieving revision 1.1551 diff -u -p -r1.1550 -r1.1551 --- version.sh 2006/06/02 21:51:19 1.1550 +++ version.sh 2006/06/03 21:51:10 1.1551 ＠＠ -8,5 +8,5 ＠＠ emacs_kit_version= infodock_major_version=4 infodock_minor_version=0 infodock_build_version=8 -xemacs_extra_name="(+CVS-20060602)" +xemacs_extra_name="(+CVS-20060603)" xemacs_release_date="2006-05-16"

1 participants
0 comments

CVS update by aidan xemacs/tests/automated ... 17 years, 11 months

CVS Monitor

User: aidan Date: 06/06/03 19:51:06 Modified: xemacs/tests/automated mule-tests.el Log: Just-in-time Unicode code point support. Revision Changes Path 1.748 +18 -0 XEmacs/xemacs/lisp/ChangeLog Index: ChangeLog =================================================================== RCS file: /pack/xemacscvs/XEmacs/xemacs/lisp/ChangeLog,v retrieving revision 1.747 retrieving revision 1.748 diff -u -p -r1.747 -r1.748 --- ChangeLog 2006/06/02 22:18:05 1.747 +++ ChangeLog 2006/06/03 17:50:39 1.748 ＠＠ -1,3 +1,21 ＠＠ +2006-06-03 Aidan Kehoe <kehoea(a)parhasard.net> + + * mule/mule-ccl.el: + "X Emacs" -> "XEmacs" + * mule/mule-ccl.el (ccl-compile-mule-to-unicode): New. + * mule/mule-ccl.el (ccl-compile-unicode-to-mule): New. + * mule/mule-ccl.el (ccl-dump-mule-to-unicode): New. + * mule/mule-ccl.el (ccl-dump-unicode-to-mule): New. + * mule/mule-ccl.el (define-ccl-program): + Add two new CCL commands, and commands to describe them; document + them. + +2006-06-03 Aidan Kehoe <kehoea(a)parhasard.net> + + * unicode.el: + * unicode.el (featurep): + * x-init.el (x-initialize-keyboard): + 2006-06-03 Adrian Aichner <adrian(a)xemacs.org> * package-get.el (package-get-download-sites): Welcome 1.13 +32 -0 XEmacs/xemacs/lisp/unicode.el Index: unicode.el =================================================================== RCS file: /pack/xemacscvs/XEmacs/xemacs/lisp/unicode.el,v retrieving revision 1.12 retrieving revision 1.13 diff -u -p -r1.12 -r1.13 --- unicode.el 2005/03/04 21:59:43 1.12 +++ unicode.el 2006/06/03 17:50:40 1.13 ＠＠ -318,6 +318,38 ＠＠ The second argument must be 'ucs, the th "Sorry, encode-char doesn't yet support anything but the UCS. ") (char-to-unicode char)) +(when (featurep 'mule) + ;; This CCL program is used for displaying the fallback UCS character set, + ;; and can be repurposed to lao and the IPA, all going well. + ;; + ;; define-ccl-program is available after mule-ccl is loaded, much later + ;; than this file in the build process. The below is the result of + ;; + ;; (macroexpand + ;; '(define-ccl-program ccl-encode-to-ucs-2 + ;; `(1 + ;; ((r1 = (r1 << 8)) + ;; (r1 = (r1 | r2)) + ;; (mule-to-unicode r0 r1) + ;; (r1 = (r0 >> 8)) + ;; (r2 = (r0 & 255)))) + ;; "CCL program to transform Mule characters to UCS-2.")) + ;; + ;; and it should occasionally be confirmed that the correspondence still + ;; holds. + + (let ((prog [1 10 131127 8 98872 65823 147513 8 82009 255 22])) + (defconst ccl-encode-to-ucs-2 prog + "CCL program to transform Mule characters to UCS-2.") + (put (quote ccl-encode-to-ucs-2) (quote ccl-program-idx) + (register-ccl-program (quote ccl-encode-to-ucs-2) prog)) nil)) + +;; Won't do this just yet, though. +;; (set-charset-registry 'lao "iso10646-1") +;; (set-charset-ccl-program 'lao 'ccl-encode-to-ucs-2) +;; (set-charset-registry 'ipa "iso10646-1") +;; (set-charset-ccl-program 'ipa 'ccl-encode-to-ucs-2) + ;; #### UTF-7 is not yet implemented, and it's tricky to do. There's ;; an implementation in appendix A.1 of the Unicode Standard, Version ;; 2.0, but I don't know its licensing characteristics. 1.17 +1 -1 XEmacs/xemacs/lisp/x-init.el Index: x-init.el =================================================================== RCS file: /pack/xemacscvs/XEmacs/xemacs/lisp/x-init.el,v retrieving revision 1.16 retrieving revision 1.17 diff -u -p -r1.16 -r1.17 --- x-init.el 2006/04/25 14:01:54 1.16 +++ x-init.el 2006/06/03 17:50:40 1.17 ＠＠ -247,7 +247,7 ＠＠ (when (and (not (get (intern sym-string) 'character-of-keysym)) (string-match "^U[0-9A-F]+$" sym-string)) (pushnew (concat sym-string " ") unknown-code-points :test 'equal))) - (when unknown-code-points + (when (and (featurep 'mule) unknown-code-points) (lwarn 'key-mapping 'info "Undefined Unicode key mappings. Your keyboard has, among many others, the following keysyms defined: 1.10 +46 -11 XEmacs/xemacs/lisp/mule/mule-ccl.el Index: mule-ccl.el =================================================================== RCS file: /pack/xemacscvs/XEmacs/xemacs/lisp/mule/mule-ccl.el,v retrieving revision 1.9 retrieving revision 1.10 diff -u -p -r1.9 -r1.10 --- mule-ccl.el 2005/05/05 17:10:38 1.9 +++ mule-ccl.el 2006/06/03 17:50:45 1.10 ＠＠ -5,20 +5,20 ＠＠ ;; Keywords: CCL, mule, multilingual, character set, coding-system -;; This file is part of X Emacs. +;; This file is part of XEmacs. -;; GNU Emacs is free software; you can redistribute it and/or modify +;; 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. -;; GNU Emacs is distributed in the hope that it will be useful, +;; 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 GNU Emacs; see the file COPYING. If not, write to the +;; 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. ＠＠ -48,7 +48,7 ＠＠ [if branch loop break repeat write-repeat write-read-repeat read read-if read-branch write call end read-multibyte-character write-multibyte-character - translate-character + translate-character mule-to-unicode unicode-to-mule iterate-multiple-map map-multiple map-single] "Vector of CCL commands (symbols).") ＠＠ -100,7 +100,9 ＠＠ write-multibyte-character translate-character translate-character-const-tbl - nil nil nil nil nil nil nil nil nil nil nil nil ; 0x04-0x0f + mule-to-unicode + unicode-to-mule + nil nil nil nil nil nil nil nil nil nil ; 0x06-0x0f iterate-multiple-map map-multiple map-single ＠＠ -830,6 +832,29 ＠＠ (ccl-embed-extended-command 'translate-character rrr RRR Rrr)))) nil) +;; Compile mule-to-unicode +(defun ccl-compile-mule-to-unicode (cmd) + (if (/= (length cmd) 3) + (error "CCL: Invalid number of arguments: %s" cmd)) + (let ((RRR (nth 1 cmd)) + (rrr (nth 2 cmd))) + (ccl-check-register RRR cmd) + (ccl-check-register rrr cmd) + (ccl-embed-extended-command 'mule-to-unicode RRR rrr 0)) + nil) + +;; Given a Unicode code point in register rrr, write the charset ID of the +;; corresponding character in RRR, and the Mule-CCL form of its code in rrr. +(defun ccl-compile-unicode-to-mule (cmd) + (if (/= (length cmd) 3) + (error "CCL: Invalid number of arguments: %s" cmd)) + (let ((rrr (nth 1 cmd)) + (RRR (nth 2 cmd))) + (ccl-check-register rrr cmd) + (ccl-check-register RRR cmd) + (ccl-embed-extended-command 'unicode-to-mule rrr RRR 0)) + nil) + (defun ccl-compile-iterate-multiple-map (cmd) (ccl-compile-multiple-map-function 'iterate-multiple-map cmd) nil) ＠＠ -1188,6 +1213,12 ＠＠ (let ((tbl (ccl-get-next-code))) (insert (format "translation table(%S) r%d r%d\n" tbl RRR rrr)))) +(defun ccl-dump-mule-to-unicode (rrr RRR Rrr) + (insert (format "change chars in r%d and r%d to unicode\n" RRR rrr))) + +(defun ccl-dump-unicode-to-mule (rrr RRR Rrr) + (insert (format "converter UCS code %d to a Mule char\n" rrr))) + (defun ccl-dump-iterate-multiple-map (rrr RRR Rrr) (let ((notbl (ccl-get-next-code)) (i 0) id) ＠＠ -1358,10 +1389,14 ＠＠ WRITE := ;; Call CCL program whose name is ccl-program-name. CALL := (call ccl-program-name) + +TRANSLATE:= ;; Not implemented under XEmacs, except mule-to-unicode and + ;; unicode-to-mule. + (translate-character REG(table) REG(charset) REG(codepoint)) + | (translate-character SYMBOL REG(charset) REG(codepoint)) + | (mule-to-unicode REG(charset) REG(codepoint)) + | (unicode-to-mule REG(unicode,code) REG(CHARSET)) -TRANSLATE:= ;; Not implemented under XEmacs. - (translate-character REG(table) REG(charset) REG(codepoint)) - | (translate-character SYMBOL REG(charset) REG(codepoint)) MAP := (iterate-multiple-map REG REG MAP-IDs) | (map-multiple REG REG (MAP-SET)) ＠＠ -1373,8 +1408,8 ＠＠ MAP-ID := INT-OR-CHAR ;; Terminate the CCL program. END := (end) -;; CCL registers. These can contain any integer value. As r7 is used by CCL -;; interpreter itself, its value change unexpectedly. +;; CCL registers. These can contain any integer value. As r7 is used by the +;; CCL interpreter itself, its value can change unexpectedly. REG := r0 | r1 | r2 | r3 | r4 | r5 | r6 | r7 ARG := REG | INT-OR-CHAR 1.343 +7 -0 XEmacs/xemacs/man/ChangeLog Index: ChangeLog =================================================================== RCS file: /pack/xemacscvs/XEmacs/xemacs/man/ChangeLog,v retrieving revision 1.342 retrieving revision 1.343 diff -u -p -r1.342 -r1.343 --- ChangeLog 2006/05/16 15:36:15 1.342 +++ ChangeLog 2006/06/03 17:50:46 1.343 ＠＠ -1,3 +1,10 ＠＠ +2006-06-03 Aidan Kehoe <kehoea(a)parhasard.net> + + * lispref/mule.texi (CCL Syntax): + * lispref/mule.texi (CCL Statements): + Describe the mule-to-unicode and unicode-to-mule statements; + rename the section they are described in. + 2006-05-17 Stephen J. Turnbull <stephen(a)xemacs.org> * xemacs-faq.texi (Q2.2.3): New node. 1.15 +32 -2 XEmacs/xemacs/man/lispref/mule.texi Index: mule.texi =================================================================== RCS file: /pack/xemacscvs/XEmacs/xemacs/man/lispref/mule.texi,v retrieving revision 1.14 retrieving revision 1.15 diff -u -p -r1.14 -r1.15 --- mule.texi 2005/06/19 20:49:47 1.14 +++ mule.texi 2006/06/03 17:50:48 1.15 ＠＠ -1825,6 +1825,15 ＠＠ WRITE := | (write INT-OR-CHAR) | (write string) | (write REG ARRAY) | string CALL := (call ccl-program-name) + + +TRANSLATE:= ;; Not implemented under XEmacs, except mule-to-unicode and + ;; unicode-to-mule. + (translate-character REG(table) REG(charset) REG(codepoint)) + | (translate-character SYMBOL REG(charset) REG(codepoint)) + | (mule-to-unicode REG(charset) REG(codepoint)) + | (unicode-to-mule REG(unicode,code) REG(CHARSET)) + END := (end) REG := r0 | r1 | r2 | r3 | r4 | r5 | r6 | r7 ＠＠ -1845,7 +1854,8 ＠＠ INT-OR-CHAR := integer | character The Emacs Code Conversion Language provides the following statement types: ＠dfn{set}, ＠dfn{if}, ＠dfn{branch}, ＠dfn{loop}, ＠dfn{repeat}, -＠dfn{break}, ＠dfn{read}, ＠dfn{write}, ＠dfn{call}, and ＠dfn{end}. +＠dfn{break}, ＠dfn{read}, ＠dfn{write}, ＠dfn{call}, ＠dfn{translate} and +＠dfn{end}. ＠heading Set statement: ＠＠ -1933,11 +1943,31 ＠＠ reads from the input into the register, ＠code{write} and ＠code{read} statements for the semantics of the I/O operations for each type of argument. -＠heading Other control statements: +＠heading Other statements: The ＠dfn{call} statement, written ＠samp{(call ＠var{ccl-program-name})}, executes a CCL program as a subroutine. It does not return a value to the caller, but can modify the register status. + + The ＠dfn{mule-to-unicode} statement translates an XEmacs character into a +UCS code point, using U+FFFD REPLACEMENT CHARACTER if the given XEmacs +character has no known corresponding code point. It takes two +arguments; the first is a register in which is stored the character set +ID of the character to be translated, and into which the UCS code is +stored. The second is a register which stores the XEmacs code of the +character in question; if it is from a multidimensional character set, +like most of the East Asian national sets, it's stored as ＠samp{((c1 << +8) & c2)}, where ＠samp{c1} is the first code, and ＠samp{c2} the second. +(That is, as a single integer, the high-order eight bits of which encode +the first position code, and the low order bits of which encode the +second.) + + The ＠dfn{unicode-to-mule} statement translates a Unicode code point +(an integer) into an XEmacs character. Its first argument is a register +containing the UCS code point; the code for the correspond character +will be written into this register, in the same format as for +＠samp{mule-to-unicode} The second argument is a register into which will +be written the character set ID of the converted character. The ＠dfn{end} statement, written ＠samp{(end)}, terminates the CCL program successfully, and returns to caller (which may be a CCL 1.971 +87 -0 XEmacs/xemacs/src/ChangeLog Index: ChangeLog =================================================================== RCS file: /pack/xemacscvs/XEmacs/xemacs/src/ChangeLog,v retrieving revision 1.970 retrieving revision 1.971 diff -u -p -r1.970 -r1.971 --- ChangeLog 2006/05/30 06:21:31 1.970 +++ ChangeLog 2006/06/03 17:50:51 1.971 ＠＠ -1,3 +1,90 ＠＠ +2006-06-03 Aidan Kehoe <kehoea(a)parhasard.net> + + * charset.h: + * charset.h (struct Lisp_Charset): + * charset.h (CHARSET_ENCODE_AS_UTF_8): + * charset.h (XCHARSET_ENCODE_AS_UTF_8): + Add a flag `encode-as-utf-8' to the Mule charset structure; if + set, it's an indication to ISO 2022-oriented coding systems that + the characters of that charset should be encoded using the ISO-IR + 196 UTF-8 escape syntax, since they're not members of any other + well-known character set we're aware of. + + Make enum unicode_type, encode_unicode_char and Funicode_to_char + available outside of unicode.c + + * lread.c: + * event-xlike-inc.c: + Use the charset.h declaration of Funicode_to_char, don't declare + it ourselves. + + My XFree86 installation has taken to passing me ASCII characters + using the Unicode keysyms; accept them too. + + * general-slots.h: + Make `ccl-program' and `encode-as-utf-8' available as symbols + generally. + + * mule-ccl.c: + Add CCL_MuleToUnicode, CCL_UnicodeToMule, implement them, enable + and debug CCL_MAKE_CHAR, have CCL_WriteMultibyteChar2 segfault + less, fix some grammar. + + * mule-charset.c (make_charset): + * mule-charset.c (Fmake_charset): + * mule-charset.c (Fcharset_property): + * mule-charset.c (complex_vars_of_mule_charset): + Require the encode_as_utf_8 property when calling make_charset (); + accept it when creating a charset from Lisp in Fmake_charset. + + * mule-coding.c: + * mule-coding.c (dynarr_add_2022_one_dimension): + * mule-coding.c (dynarr_add_2022_two_dimensions): + Add two convenience functions for iso2022_decode, to abstract out + writing UTF-8 a little. + + * mule-coding.c (enum iso_esc_flag): + Add one more state to reflect the existence of the UTF-8 escape. + + * mule-coding.c (struct iso2022_coding_stream): + Add a counter variable to the state to permit handling + variable-length UTF-8. + + * mule-coding.c (parse_iso2022_esc): + Update the function to work with ISO_STATE_UTF_8; only the ESC % ＠ + escape is processed in that state, everything else is ignored and + passed through by the error handler. + + * mule-coding.c (iso2022_decode): + * mule-coding.c (iso2022_designate): + * mule-coding.c (iso2022_encode): + Handle the UTF-8 escape sequences in reading and in writing ISO + 2022. + + * redisplay-x.c (separate_textual_runs): + Add a comment to the effect that the dimension stuff breaks when + using CCL programs and registries to map to a bigger charset. + + * unicode.c: + Add support for creating new characters on the fly as unknown + Unicode code points are encountered. + + * unicode.c (get_free_codepoint): New. + * unicode.c (unicode_to_ichar): Reworked to create new code points + on the fly. + * unicode.c (Funicode_to_char): Update the docstring. + * unicode.c (struct unicode_coding_system): + Move enum unicode_type into charset.h. + + * unicode.c (encode_unicode_char): + encode_unicode_char isn't static any longer, mule-coding.c uses + it. + * unicode.c (syms_of_unicode): + Make a couple of symbols available to unicode.c + * unicode.c (vars_of_unicode): + Tell the garbage collector about current_jit_charset, initialise + it. + 2006-05-25 Stephen J. Turnbull <stephen(a)xemacs.org> * objects-x.c (x_find_charset_font): Keep local names local; wrap 1.13 +26 -0 XEmacs/xemacs/src/charset.h Index: charset.h =================================================================== RCS file: /pack/xemacscvs/XEmacs/xemacs/src/charset.h,v retrieving revision 1.12 retrieving revision 1.13 diff -u -p -r1.12 -r1.13 --- charset.h 2005/10/24 10:07:34 1.12 +++ charset.h 2006/06/03 17:50:54 1.13 ＠＠ -229,6 +229,11 ＠＠ struct Lisp_Charset /* Which half of font to be used to display this character set */ int graphic; + /* If set, this charset should be written out in ISO-2022-based coding + systems using the escape sequence for UTF-8, not using our internal + representation and the associated real ISO 2022 designation. */ + unsigned int encode_as_utf_8 :1; + /* If set, this is a "temporary" charset created when we encounter an unknown final. This is so that we can successfully compile and load such files. We allow a real charset to be created on top ＠＠ -261,6 +266,7 ＠＠ DECLARE_LRECORD (charset, Lisp_Charset); #define CHARSET_REP_BYTES(cs) ((cs)->rep_bytes) #define CHARSET_COLUMNS(cs) ((cs)->columns) #define CHARSET_GRAPHIC(cs) ((cs)->graphic) +#define CHARSET_ENCODE_AS_UTF_8(cs) ((cs)->encode_as_utf_8) #define CHARSET_TYPE(cs) ((cs)->type) #define CHARSET_DIRECTION(cs) ((cs)->direction) #define CHARSET_FINAL(cs) ((cs)->final) ＠＠ -284,6 +290,7 ＠＠ DECLARE_LRECORD (charset, Lisp_Charset); #define XCHARSET_REP_BYTES(cs) CHARSET_REP_BYTES (XCHARSET (cs)) #define XCHARSET_COLUMNS(cs) CHARSET_COLUMNS (XCHARSET (cs)) #define XCHARSET_GRAPHIC(cs) CHARSET_GRAPHIC (XCHARSET (cs)) +#define XCHARSET_ENCODE_AS_UTF_8(cs) CHARSET_ENCODE_AS_UTF_8 (XCHARSET (cs)) #define XCHARSET_TYPE(cs) CHARSET_TYPE (XCHARSET (cs)) #define XCHARSET_DIRECTION(cs) CHARSET_DIRECTION (XCHARSET (cs)) #define XCHARSET_FINAL(cs) CHARSET_FINAL (XCHARSET (cs)) ＠＠ -547,6 +554,25 ＠＠ breakup_ichar_1 (Ichar c, Lisp_Object *c void get_charset_limits (Lisp_Object charset, int *low, int *high); int ichar_to_unicode (Ichar chr); +EXFUN (Fcharset_name, 1); + #endif /* MULE */ + +/* ISO 10646 UTF-16, UCS-4, UTF-8, UTF-7, etc. */ + +enum unicode_type +{ + UNICODE_UTF_16, + UNICODE_UTF_8, + UNICODE_UTF_7, + UNICODE_UCS_4 +}; + +void encode_unicode_char (Lisp_Object USED_IF_MULE (charset), int h, + int USED_IF_MULE (l), unsigned_char_dynarr *dst, + enum unicode_type type, unsigned int little_endian); + +EXFUN (Funicode_to_char, 2); +EXFUN (Fchar_to_unicode, 1); #endif /* INCLUDED_charset_h_ */ 1.3 +2 -4 XEmacs/xemacs/src/event-xlike-inc.c Index: event-xlike-inc.c =================================================================== RCS file: /pack/xemacscvs/XEmacs/xemacs/src/event-xlike-inc.c,v retrieving revision 1.2 retrieving revision 1.3 diff -u -p -r1.2 -r1.3 --- event-xlike-inc.c 2005/06/26 18:05:04 1.2 +++ event-xlike-inc.c 2006/06/03 17:50:54 1.3 ＠＠ -27,8 +27,6 ＠＠ Boston, MA 02111-1307, USA. */ included here, not in event-xlike.c. However, event-xlike.c is always X-specific, whereas the following code isn't, in the GTK case. */ -EXFUN (Funicode_to_char, 2); /* In unicode.c. */ - static int #ifdef THIS_IS_GTK emacs_gtk_event_pending_p (int how_many) ＠＠ -503,9 +501,9 ＠＠ gtk_keysym_to_character(guint keysym) and only those should correspond directly to Unicode code points, in the range #x100-#x10FFFF; actual implementations can have the Latin 1 code points do the same thing with keysyms - #x010000A0-#x01000100. */ + #x01000000-#x01000100. */ - if (keysym >= 0x010000A0 && keysym <= 0x0110FFFF) + if (keysym >= 0x01000000 && keysym <= 0x0110FFFF) return Funicode_to_char (make_int(keysym & 0xffffff), Qnil); if ((keysym & 0xff) < 0xa0) 1.17 +2 -0 XEmacs/xemacs/src/general-slots.h Index: general-slots.h =================================================================== RCS file: /pack/xemacscvs/XEmacs/xemacs/src/general-slots.h,v retrieving revision 1.16 retrieving revision 1.17 diff -u -p -r1.16 -r1.17 --- general-slots.h 2005/07/03 21:48:01 1.16 +++ general-slots.h 2006/06/03 17:50:54 1.17 ＠＠ -73,6 +73,7 ＠＠ SYMBOL_KEYWORD (Q_callback); SYMBOL_KEYWORD (Q_callback_ex); SYMBOL (Qcancel); SYMBOL (Qcategory); +SYMBOL (Qccl_program); SYMBOL (Qcenter); SYMBOL (Qchain); SYMBOL (Qchange); ＠＠ -115,6 +116,7 ＠＠ SYMBOL (Qduplex); SYMBOL (Qdynarr_overhead); SYMBOL (Qemergency); SYMBOL (Qempty); +SYMBOL (Qencode_as_utf_8); SYMBOL (Qeq); SYMBOL (Qeql); SYMBOL (Qequal); 1.78 +1 -2 XEmacs/xemacs/src/lread.c Index: lread.c =================================================================== RCS file: /pack/xemacscvs/XEmacs/xemacs/src/lread.c,v retrieving revision 1.77 retrieving revision 1.78 diff -u -p -r1.77 -r1.78 --- lread.c 2006/04/29 14:36:57 1.77 +++ lread.c 2006/06/03 17:50:54 1.78 ＠＠ -34,6 +34,7 ＠＠ Boston, MA 02111-1307, USA. */ #include "lstream.h" #include "opaque.h" #include "profile.h" +#include "charset.h" /* For Funicode_to_char. */ #include "sysfile.h" #include "sysfloat.h" ＠＠ -207,8 +208,6 ＠＠ static int saved_doc_string_position; static int locate_file_open_or_access_file (Ibyte *fn, int access_mode); EXFUN (Fread_from_string, 3); - -EXFUN (Funicode_to_char, 2); /* In unicode.c. */ /* When errors are signaled, the actual readcharfun should not be used as an argument if it is an lstream, so that lstreams don't escape 1.29 +92 -18 XEmacs/xemacs/src/mule-ccl.c Index: mule-ccl.c =================================================================== RCS file: /pack/xemacscvs/XEmacs/xemacs/src/mule-ccl.c,v retrieving revision 1.28 retrieving revision 1.29 diff -u -p -r1.28 -r1.29 --- mule-ccl.c 2005/06/26 19:05:07 1.28 +++ mule-ccl.c 2006/06/03 17:50:54 1.29 ＠＠ -461,7 +461,17 ＠＠ Lisp_Object Vccl_program_table; 1:ExtendedCOMMNDRrrRRRrrrXXXXX 2:ARGUMENT(Translation Table ID) */ +/* Translate a character whose code point is reg[rrr] and charset ID is + reg[RRR], into its Unicode code point, which will be written into + reg[rrr]. */ +#define CCL_MuleToUnicode 0x04 + +/* Translate a Unicode code point, in reg[rrr], into a Mule character, + writing the charset ID into reg[RRR] and the code point into reg[Rrr]. */ + +#define CCL_UnicodeToMule 0x05 + /* Iterate looking up MAPs for reg[rrr] starting from the Nth (N = reg[RRR]) MAP until some value is found. ＠＠ -577,7 +587,6 ＠＠ Lisp_Object Vccl_program_table; ... N:SEPARATOR_z (< 0) */ - #define MAX_MAP_SET_LEVEL 30 typedef struct ＠＠ -837,26 +846,41 ＠＠ static int stack_idx_of_map_multiple; CODE to that invalid byte. */ /* On XEmacs, TranslateCharacter is not supported. Thus, this - macro is not used. */ -#if 0 + macro is only used in the MuleToUnicode transformation. */ #define CCL_MAKE_CHAR(charset, code, c) \ do { \ - if ((charset) == CHARSET_ASCII) \ - (c) = (code) & 0xFF; \ - else if (CHARSET_DEFINED_P (charset) \ - && ((code) & 0x7F) >= 32 \ - && ((code) < 256 || ((code >> 7) & 0x7F) >= 32)) \ + if ((charset) == LEADING_BYTE_ASCII) \ { \ - int c1 = (code) & 0x7F, c2 = 0; \ + c = (code) & 0xFF; \ + } \ + else if ((charset) == LEADING_BYTE_CONTROL_1) \ + { \ + c = ((code) & 0xFF) - 0xA0; \ + } \ + else if (!NILP(charset_by_leading_byte(charset)) \ + && ((code) >= 32) \ + && ((code) < 256 || ((code >> 8) & 0x7F) >= 32)) \ + { \ + int c1, c2 = 0; \ \ - if ((code) >= 256) \ - c2 = c1, c1 = ((code) >> 7) & 0x7F; \ - (c) = make_ichar (charset, c1, c2); \ + if ((code) < 256) \ + { \ + c1 = (code) & 0x7F; \ + c2 = 0; \ + } \ + else \ + { \ + c1 = ((code) >> 8) & 0x7F; \ + c2 = (code) & 0x7F; \ + } \ + c = make_ichar (charset_by_leading_byte(charset), \ + c1, c2); \ } \ else \ - (c) = (code) & 0xFF; \ - } while (0) -#endif + { \ + c = (code) & 0xFF; \ + } \ + } while (0) /* Execute CCL code on SRC_BYTES length text at SOURCE. The resulting ＠＠ -1392,9 +1416,9 ＠＠ ccl_driver (struct ccl_program *ccl, case CCL_TranslateCharacter: #if 0 - /* XEmacs does not have translate_char, and its - equivalent nor. We do nothing on this operation. */ - CCL_MAKE_CHAR (reg[RRR], reg[rrr], i); + /* XEmacs does not have translate_char, nor an + equivalent. We do nothing on this operation. */ + CCL_MAKE_CHAR(reg[RRR], reg[rrr], op); op = translate_char (GET_TRANSLATION_TABLE (reg[Rrr]), i, -1, 0, 0); SPLIT_CHAR (op, reg[RRR], i, j); ＠＠ -1420,6 +1444,56 ＠＠ ccl_driver (struct ccl_program *ccl, reg[rrr] = i; #endif break; + + case CCL_MuleToUnicode: + { + Lisp_Object ucs; + + CCL_MAKE_CHAR(reg[rrr], reg[RRR], op); + ucs = Fchar_to_unicode(make_char(op)); + + if (NILP(ucs)) + { + /* Uhh, char-to-unicode doesn't return nil at the + moment, only ever -1. */ + reg[rrr] = 0xFFFD; /* REPLACEMENT CHARACTER */ + } + else + { + reg[rrr] = XINT(ucs); + if (-1 == reg[rrr]) + { + reg[rrr] = 0xFFFD; /* REPLACEMENT CHARACTER */ + } + } + break; + } + + case CCL_UnicodeToMule: + { + Lisp_Object scratch; + + scratch = Funicode_to_char(make_int(reg[rrr]), Qnil); + + if (!NILP(scratch)) + { + op = XCHAR(scratch); + BREAKUP_ICHAR (op, scratch, i, j); + reg[RRR] = XCHARSET_ID(scratch); + + if (j != 0) + { + i = (i << 8) | j; + } + + reg[rrr] = i; + } + else + { + reg[rrr] = reg[RRR] = 0; + } + break; + } case CCL_IterateMultipleMap: { 1.47 +47 -31 XEmacs/xemacs/src/mule-charset.c Index: mule-charset.c =================================================================== RCS file: /pack/xemacscvs/XEmacs/xemacs/src/mule-charset.c,v retrieving revision 1.46 retrieving revision 1.47 diff -u -p -r1.46 -r1.47 --- mule-charset.c 2005/10/25 11:16:26 1.46 +++ mule-charset.c 2006/06/03 17:50:54 1.47 ＠＠ -190,7 +190,7 ＠＠ make_charset (int id, Lisp_Object name, int type, int columns, int graphic, Ibyte final, int direction, Lisp_Object short_name, Lisp_Object long_name, Lisp_Object doc, - Lisp_Object reg, int overwrite) + Lisp_Object reg, int overwrite, int encode_as_utf_8) { Lisp_Object obj; Lisp_Charset *cs; ＠＠ -240,6 +240,7 ＠＠ make_charset (int id, Lisp_Object name, CHARSET_FINAL (cs) = final; CHARSET_DOC_STRING (cs) = doc; CHARSET_REGISTRY (cs) = reg; + CHARSET_ENCODE_AS_UTF_8 (cs) = encode_as_utf_8 ? 1 : 0; CHARSET_CCL_PROGRAM (cs) = Qnil; CHARSET_REVERSE_DIRECTION_CHARSET (cs) = Qnil; ＠＠ -454,6 +455,12 ＠＠ character set. Recognized properties ar is passed the octets of the character, with the high bit cleared and set depending upon whether the value of the `graphic' property is 0 or 1. +`encode-as-utf-8' + If non-nil, the charset will be written out using the UTF-8 + escape syntax in ISO 2022-oriented coding systems. Used for + supporting characters we know are part of Unicode but not of + any other known character set in escape-quoted and compound + text. */ (name, doc_string, props)) { ＠＠ -465,6 +472,7 ＠＠ character set. Recognized properties ar Lisp_Object charset = Qnil; Lisp_Object ccl_program = Qnil; Lisp_Object short_name = Qnil, long_name = Qnil; + int encode_as_utf_8 = 0; Lisp_Object existing_charset; int temporary = UNBOUNDP (name); ＠＠ -546,6 +554,11 ＠＠ character set. Recognized properties ar invalid_constant ("Invalid value for `direction'", value); } + else if (EQ (keyword, Qencode_as_utf_8)) + { + encode_as_utf_8 = NILP (value) ? 0 : 1; + } + else if (EQ (keyword, Qfinal)) { CHECK_CHAR_COERCE_INT (value); ＠＠ -553,7 +566,6 ＠＠ character set. Recognized properties ar if (final < '0' || final > '~') invalid_constant ("Invalid value for `final'", value); } - else if (EQ (keyword, Qccl_program)) { struct ccl_program test_ccl; ＠＠ -612,7 +624,8 ＠＠ character set. Recognized properties ar charset = make_charset (id, name, dimension + 2, type, columns, graphic, final, direction, short_name, long_name, - doc_string, registry, !NILP (existing_charset)); + doc_string, registry, !NILP (existing_charset), + encode_as_utf_8); XCHARSET (charset)->temporary = temporary; if (!NILP (ccl_program)) ＠＠ -641,7 +654,7 ＠＠ NEW-NAME is the name of the new charset. (charset, new_name)) { Lisp_Object new_charset = Qnil; - int id, dimension, columns, graphic; + int id, dimension, columns, graphic, encode_as_utf_8; Ibyte final; int direction, type; Lisp_Object registry, doc_string, short_name, long_name; ＠＠ -672,10 +685,11 ＠＠ NEW-NAME is the name of the new charset. short_name = CHARSET_SHORT_NAME (cs); long_name = CHARSET_LONG_NAME (cs); registry = CHARSET_REGISTRY (cs); + encode_as_utf_8 = CHARSET_ENCODE_AS_UTF_8 (cs); new_charset = make_charset (id, new_name, dimension + 2, type, columns, graphic, final, direction, short_name, long_name, - doc_string, registry, 0); + doc_string, registry, 0, encode_as_utf_8); CHARSET_REVERSE_DIRECTION_CHARSET (cs) = new_charset; XCHARSET_REVERSE_DIRECTION_CHARSET (new_charset) = charset; ＠＠ -807,6 +821,8 ＠＠ Recognized properties are those listed i if (EQ (prop, Qfinal)) return make_char (CHARSET_FINAL (cs)); if (EQ (prop, Qchars)) return make_int (CHARSET_CHARS (cs)); if (EQ (prop, Qregistry)) return CHARSET_REGISTRY (cs); + if (EQ (prop, Qencode_as_utf_8)) + return CHARSET_ENCODE_AS_UTF_8 (cs) ? Qt : Qnil; if (EQ (prop, Qccl_program)) return CHARSET_CCL_PROGRAM (cs); if (EQ (prop, Qdirection)) return CHARSET_DIRECTION (cs) == CHARSET_LEFT_TO_RIGHT ? Ql2r : Qr2l; ＠＠ -1040,7 +1056,7 ＠＠ complex_vars_of_mule_charset (void) build_string ("ASCII"), build_msg_string ("ASCII"), build_msg_string ("ASCII (ISO646 IRV)"), - build_string ("\$iso8859-[0-9]*\\|-ascii\$"), 0); + build_string ("\$iso8859-[0-9]*\\|-ascii\$"), 0, 0); staticpro (&Vcharset_control_1); Vcharset_control_1 = make_charset (LEADING_BYTE_CONTROL_1, Qcontrol_1, 2, ＠＠ -1049,7 +1065,7 ＠＠ complex_vars_of_mule_charset (void) build_string ("C1"), build_msg_string ("Control characters"), build_msg_string ("Control characters 128-191"), - build_string (""), 0); + build_string (""), 0, 0); staticpro (&Vcharset_latin_iso8859_1); Vcharset_latin_iso8859_1 = make_charset (LEADING_BYTE_LATIN_ISO8859_1, Qlatin_iso8859_1, 2, ＠＠ -1058,7 +1074,7 ＠＠ complex_vars_of_mule_charset (void) build_string ("Latin-1"), build_msg_string ("ISO8859-1 (Latin-1)"), build_msg_string ("ISO8859-1 (Latin-1)"), - build_string ("iso8859-1"), 0); + build_string ("iso8859-1"), 0, 0); staticpro (&Vcharset_latin_iso8859_2); Vcharset_latin_iso8859_2 = make_charset (LEADING_BYTE_LATIN_ISO8859_2, Qlatin_iso8859_2, 2, ＠＠ -1067,7 +1083,7 ＠＠ complex_vars_of_mule_charset (void) build_string ("Latin-2"), build_msg_string ("ISO8859-2 (Latin-2)"), build_msg_string ("ISO8859-2 (Latin-2)"), - build_string ("iso8859-2"), 0); + build_string ("iso8859-2"), 0, 0); staticpro (&Vcharset_latin_iso8859_3); Vcharset_latin_iso8859_3 = make_charset (LEADING_BYTE_LATIN_ISO8859_3, Qlatin_iso8859_3, 2, ＠＠ -1076,7 +1092,7 ＠＠ complex_vars_of_mule_charset (void) build_string ("Latin-3"), build_msg_string ("ISO8859-3 (Latin-3)"), build_msg_string ("ISO8859-3 (Latin-3)"), - build_string ("iso8859-3"), 0); + build_string ("iso8859-3"), 0, 0); staticpro (&Vcharset_latin_iso8859_4); Vcharset_latin_iso8859_4 = make_charset (LEADING_BYTE_LATIN_ISO8859_4, Qlatin_iso8859_4, 2, ＠＠ -1085,7 +1101,7 ＠＠ complex_vars_of_mule_charset (void) build_string ("Latin-4"), build_msg_string ("ISO8859-4 (Latin-4)"), build_msg_string ("ISO8859-4 (Latin-4)"), - build_string ("iso8859-4"), 0); + build_string ("iso8859-4"), 0, 0); staticpro (&Vcharset_thai_tis620); Vcharset_thai_tis620 = make_charset (LEADING_BYTE_THAI_TIS620, Qthai_tis620, 2, ＠＠ -1094,7 +1110,7 ＠＠ complex_vars_of_mule_charset (void) build_string ("TIS620"), build_msg_string ("TIS620 (Thai)"), build_msg_string ("TIS620.2529 (Thai)"), - build_string ("tis620"),0); + build_string ("tis620"), 0, 0); staticpro (&Vcharset_greek_iso8859_7); Vcharset_greek_iso8859_7 = make_charset (LEADING_BYTE_GREEK_ISO8859_7, Qgreek_iso8859_7, 2, ＠＠ -1103,7 +1119,7 ＠＠ complex_vars_of_mule_charset (void) build_string ("ISO8859-7"), build_msg_string ("ISO8859-7 (Greek)"), build_msg_string ("ISO8859-7 (Greek)"), - build_string ("iso8859-7"), 0); + build_string ("iso8859-7"), 0, 0); staticpro (&Vcharset_arabic_iso8859_6); Vcharset_arabic_iso8859_6 = make_charset (LEADING_BYTE_ARABIC_ISO8859_6, Qarabic_iso8859_6, 2, ＠＠ -1112,7 +1128,7 ＠＠ complex_vars_of_mule_charset (void) build_string ("ISO8859-6"), build_msg_string ("ISO8859-6 (Arabic)"), build_msg_string ("ISO8859-6 (Arabic)"), - build_string ("iso8859-6"), 0); + build_string ("iso8859-6"), 0, 0); staticpro (&Vcharset_hebrew_iso8859_8); Vcharset_hebrew_iso8859_8 = make_charset (LEADING_BYTE_HEBREW_ISO8859_8, Qhebrew_iso8859_8, 2, ＠＠ -1121,7 +1137,7 ＠＠ complex_vars_of_mule_charset (void) build_string ("ISO8859-8"), build_msg_string ("ISO8859-8 (Hebrew)"), build_msg_string ("ISO8859-8 (Hebrew)"), - build_string ("iso8859-8"), 0); + build_string ("iso8859-8"), 0, 0); staticpro (&Vcharset_katakana_jisx0201); Vcharset_katakana_jisx0201 = make_charset (LEADING_BYTE_KATAKANA_JISX0201, Qkatakana_jisx0201, 2, ＠＠ -1130,7 +1146,7 ＠＠ complex_vars_of_mule_charset (void) build_string ("JISX0201 Kana"), build_msg_string ("JISX0201.1976 (Japanese Kana)"), build_msg_string ("JISX0201.1976 Japanese Kana"), - build_string ("jisx0201.1976"), 0); + build_string ("jisx0201.1976"), 0, 0); staticpro (&Vcharset_latin_jisx0201); Vcharset_latin_jisx0201 = make_charset (LEADING_BYTE_LATIN_JISX0201, Qlatin_jisx0201, 2, ＠＠ -1139,7 +1155,7 ＠＠ complex_vars_of_mule_charset (void) build_string ("JISX0201 Roman"), build_msg_string ("JISX0201.1976 (Japanese Roman)"), build_msg_string ("JISX0201.1976 Japanese Roman"), - build_string ("jisx0201.1976"), 0); + build_string ("jisx0201.1976"), 0, 0); staticpro (&Vcharset_cyrillic_iso8859_5); Vcharset_cyrillic_iso8859_5 = make_charset (LEADING_BYTE_CYRILLIC_ISO8859_5, Qcyrillic_iso8859_5, 2, ＠＠ -1148,7 +1164,7 ＠＠ complex_vars_of_mule_charset (void) build_string ("ISO8859-5"), build_msg_string ("ISO8859-5 (Cyrillic)"), build_msg_string ("ISO8859-5 (Cyrillic)"), - build_string ("iso8859-5"), 0); + build_string ("iso8859-5"), 0, 0); staticpro (&Vcharset_latin_iso8859_9); Vcharset_latin_iso8859_9 = make_charset (LEADING_BYTE_LATIN_ISO8859_9, Qlatin_iso8859_9, 2, ＠＠ -1157,7 +1173,7 ＠＠ complex_vars_of_mule_charset (void) build_string ("Latin-5"), build_msg_string ("ISO8859-9 (Latin-5)"), build_msg_string ("ISO8859-9 (Latin-5)"), - build_string ("iso8859-9"), 0); + build_string ("iso8859-9"), 0, 0); staticpro (&Vcharset_latin_iso8859_15); Vcharset_latin_iso8859_15 = make_charset (LEADING_BYTE_LATIN_ISO8859_15, Qlatin_iso8859_15, 2, ＠＠ -1166,7 +1182,7 ＠＠ complex_vars_of_mule_charset (void) build_string ("Latin-9"), build_msg_string ("ISO8859-15 (Latin-9)"), build_msg_string ("ISO8859-15 (Latin-9)"), - build_string ("iso8859-15"), 0); + build_string ("iso8859-15"), 0, 0); staticpro (&Vcharset_japanese_jisx0208_1978); Vcharset_japanese_jisx0208_1978 = make_charset (LEADING_BYTE_JAPANESE_JISX0208_1978, Qjapanese_jisx0208_1978, 3, ＠＠ -1176,7 +1192,7 ＠＠ complex_vars_of_mule_charset (void) build_msg_string ("JISX0208.1978 (Japanese)"), build_msg_string ("JISX0208.1978 Japanese Kanji (so called \"old JIS\")"), - build_string ("\$jisx0208\\|jisc6226\$\\.1978"), 0); + build_string ("\$jisx0208\\|jisc6226\$\\.1978"), 0, 0); staticpro (&Vcharset_chinese_gb2312); Vcharset_chinese_gb2312 = make_charset (LEADING_BYTE_CHINESE_GB2312, Qchinese_gb2312, 3, ＠＠ -1185,7 +1201,7 ＠＠ complex_vars_of_mule_charset (void) build_string ("GB2312"), build_msg_string ("GB2312)"), build_msg_string ("GB2312 Chinese simplified"), - build_string ("gb2312"), 0); + build_string ("gb2312"), 0, 0); staticpro (&Vcharset_japanese_jisx0208); Vcharset_japanese_jisx0208 = make_charset (LEADING_BYTE_JAPANESE_JISX0208, Qjapanese_jisx0208, 3, ＠＠ -1194,7 +1210,7 ＠＠ complex_vars_of_mule_charset (void) build_string ("JISX0208"), build_msg_string ("JISX0208.1983/1990 (Japanese)"), build_msg_string ("JISX0208.1983/1990 Japanese Kanji"), - build_string ("jisx0208.19\$83\\|90\$"), 0); + build_string ("jisx0208.19\$83\\|90\$"), 0, 0); staticpro (&Vcharset_korean_ksc5601); Vcharset_korean_ksc5601 = make_charset (LEADING_BYTE_KOREAN_KSC5601, Qkorean_ksc5601, 3, ＠＠ -1203,7 +1219,7 ＠＠ complex_vars_of_mule_charset (void) build_string ("KSC5601"), build_msg_string ("KSC5601 (Korean"), build_msg_string ("KSC5601 Korean Hangul and Hanja"), - build_string ("ksc5601"), 0); + build_string ("ksc5601"), 0, 0); staticpro (&Vcharset_japanese_jisx0212); Vcharset_japanese_jisx0212 = make_charset (LEADING_BYTE_JAPANESE_JISX0212, Qjapanese_jisx0212, 3, ＠＠ -1212,7 +1228,7 ＠＠ complex_vars_of_mule_charset (void) build_string ("JISX0212"), build_msg_string ("JISX0212 (Japanese)"), build_msg_string ("JISX0212 Japanese Supplement"), - build_string ("jisx0212"), 0); + build_string ("jisx0212"), 0, 0); #define CHINESE_CNS_PLANE_RE(n) "cns11643[.-]\$.*[.-]\$?" n "$" staticpro (&Vcharset_chinese_cns11643_1); ＠＠ -1224,7 +1240,7 ＠＠ complex_vars_of_mule_charset (void) build_msg_string ("CNS11643-1 (Chinese traditional)"), build_msg_string ("CNS 11643 Plane 1 Chinese traditional"), - build_string (CHINESE_CNS_PLANE_RE("1")), 0); + build_string (CHINESE_CNS_PLANE_RE("1")), 0, 0); staticpro (&Vcharset_chinese_cns11643_2); Vcharset_chinese_cns11643_2 = make_charset (LEADING_BYTE_CHINESE_CNS11643_2, Qchinese_cns11643_2, 3, ＠＠ -1234,7 +1250,7 ＠＠ complex_vars_of_mule_charset (void) build_msg_string ("CNS11643-2 (Chinese traditional)"), build_msg_string ("CNS 11643 Plane 2 Chinese traditional"), - build_string (CHINESE_CNS_PLANE_RE("2")), 0); + build_string (CHINESE_CNS_PLANE_RE("2")), 0, 0); staticpro (&Vcharset_chinese_big5_1); Vcharset_chinese_big5_1 = make_charset (LEADING_BYTE_CHINESE_BIG5_1, Qchinese_big5_1, 3, ＠＠ -1244,7 +1260,7 ＠＠ complex_vars_of_mule_charset (void) build_msg_string ("Big5 (Level-1)"), build_msg_string ("Big5 Level-1 Chinese traditional"), - build_string ("big5"), 0); + build_string ("big5"), 0, 0); staticpro (&Vcharset_chinese_big5_2); Vcharset_chinese_big5_2 = make_charset (LEADING_BYTE_CHINESE_BIG5_2, Qchinese_big5_2, 3, ＠＠ -1254,7 +1270,7 ＠＠ complex_vars_of_mule_charset (void) build_msg_string ("Big5 (Level-2)"), build_msg_string ("Big5 Level-2 Chinese traditional"), - build_string ("big5"), 0); + build_string ("big5"), 0, 0); #ifdef ENABLE_COMPOSITE_CHARS ＠＠ -1269,7 +1285,7 ＠＠ complex_vars_of_mule_charset (void) build_string ("Composite"), build_msg_string ("Composite characters"), build_msg_string ("Composite characters"), - build_string (""), 0); + build_string (""), 0, 0); #else /* We create a hack so that we have a way of storing ESC 0 and ESC 1 sequences as "characters", so that they will be output correctly. */ ＠＠ -1281,6 +1297,6 ＠＠ complex_vars_of_mule_charset (void) build_string ("Composite hack"), build_msg_string ("Composite characters hack"), build_msg_string ("Composite characters hack"), - build_string (""), 0); + build_string (""), 0, 0); #endif /* ENABLE_COMPOSITE_CHARS */ } 1.38 +213 -11 XEmacs/xemacs/src/mule-coding.c Index: mule-coding.c =================================================================== RCS file: /pack/xemacscvs/XEmacs/xemacs/src/mule-coding.c,v retrieving revision 1.37 retrieving revision 1.38 diff -u -p -r1.37 -r1.38 --- mule-coding.c 2006/05/11 08:58:01 1.37 +++ mule-coding.c 2006/06/03 17:50:55 1.38 ＠＠ -96,6 +96,42 ＠＠ byte_shift_jis_katakana_p (int c) return c >= 0xA1 && c <= 0xDF; } +inline static void +dynarr_add_2022_one_dimension (Lisp_Object charset, Ibyte c, + unsigned char charmask, + unsigned_char_dynarr *dst) +{ + if (XCHARSET_ENCODE_AS_UTF_8 (charset)) + { + encode_unicode_char (charset, c & charmask, 0, + dst, UNICODE_UTF_8, 0); + } + else + { + Dynarr_add (dst, c & charmask); + } +} + +inline static void +dynarr_add_2022_two_dimensions (Lisp_Object charset, Ibyte c, + unsigned int ch, + unsigned char charmask, + unsigned_char_dynarr *dst) +{ + if (XCHARSET_ENCODE_AS_UTF_8 (charset)) + { + encode_unicode_char (charset, + ch & charmask, + c & charmask, dst, + UNICODE_UTF_8, 0); + } + else + { + Dynarr_add (dst, ch & charmask); + Dynarr_add (dst, c & charmask); + } +} + /* Convert Shift-JIS data to internal format. */ static Bytecount ＠＠ -671,6 +707,10 ＠＠ enum iso_esc_flag ISO_ESC_2_4, /* We've seen ESC $. This indicates that we're designating a multi-byte, rather than a single-byte, character set. */ + ISO_ESC_2_5, /* We've seen ESC %. This indicates an escape to a + Unicode coding system; the only one of these + we're prepared to deal with is UTF-8, which has + the next character as G. */ ISO_ESC_2_8, /* We've seen ESC 0x28, i.e. ESC (. This means designate a 94-character character set into G0. */ ＠＠ -752,11 +792,15 ＠＠ enum iso_error character constructed by overstriking two or more characters). */ #define ISO_STATE_COMPOSITE (1 << 5) +/* If set, we're processing UTF-8 encoded data within ISO-2022 + processing. */ +#define ISO_STATE_UTF_8 (1 << 6) + /* ISO_STATE_LOCK is the mask of flags that remain on until explicitly turned off when in the ISO2022 encoder/decoder. Other flags are turned off at the end of processing each character or escape sequence. */ # define ISO_STATE_LOCK \ - (ISO_STATE_COMPOSITE | ISO_STATE_R2L) + (ISO_STATE_COMPOSITE | ISO_STATE_R2L | ISO_STATE_UTF_8) typedef struct charset_conversion_spec { ＠＠ -922,6 +966,9 ＠＠ struct iso2022_coding_stream Lisp_Object current_charset; int current_half; int current_char_boundary; + + /* Used for handling UTF-8. */ + unsigned char counter; }; static const struct memory_description ccs_description_1[] = ＠＠ -1344,6 +1391,15 ＠＠ parse_iso2022_esc (Lisp_Object codesys, } case ISO_ESC: + + /* The only available ISO 2022 sequence in UTF-8 mode is ESC % ＠, to + exit from it. If we see any other escape sequence, pass it through + in the error handler. */ + if (*flags & ISO_STATE_UTF_8 && '%' != c) + { + return 0; + } + switch (c) { /**** single shift ****/ ＠＠ -1411,6 +1467,10 ＠＠ parse_iso2022_esc (Lisp_Object codesys, iso->esc = ISO_ESC_2_4; goto not_done; + case '%': /* Prefix to an escape to or from Unicode. */ + iso->esc = ISO_ESC_2_5; + goto not_done; + default: if (0x28 <= c && c <= 0x2F) { ＠＠ -1432,9 +1492,31 ＠＠ parse_iso2022_esc (Lisp_Object codesys, /* bzzzt! */ goto error; } - - + /* ISO-IR 196 UTF-8 support. */ + case ISO_ESC_2_5: + if ('G' == c) + { + /* Activate UTF-8 mode. */ + *flags &= ISO_STATE_LOCK; + *flags |= ISO_STATE_UTF_8; + iso->esc = ISO_ESC_NOTHING; + return 1; + } + else if ('＠' == c) + { + /* Deactive UTF-8 mode. */ + *flags &= ISO_STATE_LOCK; + *flags &= ~(ISO_STATE_UTF_8); + iso->esc = ISO_ESC_NOTHING; + return 1; + } + else + { + /* Oops, we don't support the other UTF-? coding systems within + ISO 2022, only in their own context. */ + goto error; + } /**** directionality ****/ case ISO_ESC_5_11: /* ISO6429 direction control */ ＠＠ -1822,6 +1904,87 ＠＠ iso2022_decode (struct coding_stream *st } ch = 0; } + else if (flags & ISO_STATE_UTF_8) + { + unsigned char counter = data->counter; + Ibyte work[MAX_ICHAR_LEN]; + int len; + Lisp_Object chr; + + if (ISO_CODE_ESC == c) + { + /* Allow the escape sequence parser to end the UTF-8 state. */ + flags |= ISO_STATE_ESCAPE; + data->esc = ISO_ESC; + data->esc_bytes_index = 1; + continue; + } + + switch (counter) + { + case 0: + if (c >= 0xfc) + { + ch = c & 0x01; + counter = 5; + } + else if (c >= 0xf8) + { + ch = c & 0x03; + counter = 4; + } + else if (c >= 0xf0) + { + ch = c & 0x07; + counter = 3; + } + else if (c >= 0xe0) + { + ch = c & 0x0f; + counter = 2; + } + else if (c >= 0xc0) + { + ch = c & 0x1f; + counter = 1; + } + else + /* ASCII, or the lower control characters. */ + Dynarr_add (dst, c); + + break; + case 1: + ch = (ch << 6) | (c & 0x3f); + chr = Funicode_to_char(make_int(ch), Qnil); + + if (!NILP (chr)) + { + assert(CHARP(chr)); + len = set_itext_ichar (work, XCHAR(chr)); + Dynarr_add_many (dst, work, len); + } + else + { + /* Shouldn't happen, this code should only be enabled in + XEmacsen with support for all of Unicode. */ + Dynarr_add (dst, LEADING_BYTE_JAPANESE_JISX0208); + Dynarr_add (dst, 34 + 128); + Dynarr_add (dst, 46 + 128); + } + + ch = 0; + counter = 0; + break; + default: + ch = (ch << 6) | (c & 0x3f); + counter--; + } + + if (str->eof) + DECODE_OUTPUT_PARTIAL_CHAR (ch, dst); + + data->counter = counter; + } else if (byte_c0_p (c) || byte_c1_p (c)) { /* Control characters */ ＠＠ -2010,6 +2173,7 ＠＠ iso2022_designate (Lisp_Object charset, } Dynarr_add (dst, ISO_CODE_ESC); + switch (type) { case CHARSET_TYPE_94: ＠＠ -2102,6 +2266,14 ＠＠ iso2022_encode (struct coding_stream *st { /* Processing ASCII character */ ch = 0; + if (flags & ISO_STATE_UTF_8) + { + Dynarr_add (dst, ISO_CODE_ESC); + Dynarr_add (dst, '%'); + Dynarr_add (dst, '＠'); + flags &= ~(ISO_STATE_UTF_8); + } + restore_left_to_right_direction (codesys, dst, &flags, 0); /* Make sure G0 contains ASCII */ ＠＠ -2145,18 +2317,43 ＠＠ iso2022_encode (struct coding_stream *st Dynarr_add (dst, c); char_boundary = 1; } - else if (ibyte_leading_byte_p (c) || ibyte_leading_byte_p (ch)) { /* Processing Leading Byte */ ch = 0; charset = charset_by_leading_byte (c); if (leading_byte_prefix_p (c)) - ch = c; + { + ch = c; + } + else if (XCHARSET_ENCODE_AS_UTF_8 (charset)) + { + assert (!EQ (charset, Vcharset_control_1) + && !EQ (charset, Vcharset_composite)); + + /* If the character set is to be encoded as UTF-8, the escape + is always the same. */ + if (!(flags & ISO_STATE_UTF_8)) + { + Dynarr_add (dst, ISO_CODE_ESC); + Dynarr_add (dst, '%'); + Dynarr_add (dst, 'G'); + flags |= ISO_STATE_UTF_8; + } + } else if (!EQ (charset, Vcharset_control_1) && !EQ (charset, Vcharset_composite)) { int reg; + /* End the UTF-8 state. */ + if (flags & ISO_STATE_UTF_8) + { + Dynarr_add (dst, ISO_CODE_ESC); + Dynarr_add (dst, '%'); + Dynarr_add (dst, '＠'); + flags &= ~(ISO_STATE_UTF_8); + } + ensure_correct_direction (XCHARSET_DIRECTION (charset), codesys, dst, &flags, 0); ＠＠ -2274,12 +2471,14 ＠＠ iso2022_encode (struct coding_stream *st switch (XCHARSET_REP_BYTES (charset)) { case 2: - Dynarr_add (dst, c & charmask); + dynarr_add_2022_one_dimension (charset, c, + charmask, dst); break; case 3: if (XCHARSET_PRIVATE_P (charset)) { - Dynarr_add (dst, c & charmask); + dynarr_add_2022_one_dimension (charset, c, + charmask, dst); ch = 0; } else if (ch) ＠＠ -2287,6 +2486,9 ＠＠ iso2022_encode (struct coding_stream *st #ifdef ENABLE_COMPOSITE_CHARS if (EQ (charset, Vcharset_composite)) { + /* #### Hasn't been written to handle composite + characters yet. */ + assert(!XCHARSET_ENCODE_AS_UTF_8 (charset)) if (in_composite) { /* #### Bother! We don't know how to ＠＠ -2310,8 +2512,8 ＠＠ iso2022_encode (struct coding_stream *st else #endif /* ENABLE_COMPOSITE_CHARS */ { - Dynarr_add (dst, ch & charmask); - Dynarr_add (dst, c & charmask); + dynarr_add_2022_two_dimensions (charset, c, ch, + charmask, dst); } ch = 0; } ＠＠ -2324,8 +2526,8 ＠＠ iso2022_encode (struct coding_stream *st case 4: if (ch) { - Dynarr_add (dst, ch & charmask); - Dynarr_add (dst, c & charmask); + dynarr_add_2022_two_dimensions (charset, c, ch, + charmask, dst); ch = 0; } else 1.42 +4 -0 XEmacs/xemacs/src/redisplay-x.c Index: redisplay-x.c =================================================================== RCS file: /pack/xemacscvs/XEmacs/xemacs/src/redisplay-x.c,v retrieving revision 1.41 retrieving revision 1.42 diff -u -p -r1.41 -r1.42 --- redisplay-x.c 2005/11/26 11:46:10 1.41 +++ redisplay-x.c 2006/06/03 17:50:55 1.42 ＠＠ -230,6 +230,10 ＠＠ separate_textual_runs (unsigned char *te } #endif /* MULE */ *text_storage++ = (unsigned char) byte1; + /* This dimension stuff is broken if you want to use a two-dimensional + X11 font to display a single-dimensional character set, as is + appropriate for the IPA (use one of the -iso10646-1 fonts) or some + of the other non-standard character sets. */ if (dimension == 2) *text_storage++ = (unsigned char) byte2; #else /* USE_XFT */ 1.33 +136 -43 XEmacs/xemacs/src/unicode.c Index: unicode.c =================================================================== RCS file: /pack/xemacscvs/XEmacs/xemacs/src/unicode.c,v retrieving revision 1.32 retrieving revision 1.33 diff -u -p -r1.32 -r1.33 --- unicode.c 2006/04/22 15:18:55 1.32 +++ unicode.c 2006/06/03 17:50:55 1.33 ＠＠ -321,6 +321,10 ＠＠ Lisp_Object Vdefault_unicode_precedence_ Lisp_Object Qignore_first_column; +Lisp_Object Vcurrent_jit_charset; +Lisp_Object Qlast_allocated_character; +Lisp_Object Qccl_encode_to_ucs_2; + /************************************************************************/ /* Unicode implementation */ ＠＠ -1001,12 +1005,72 ＠＠ ichar_to_unicode (Ichar chr) } static Ichar +get_free_codepoint(Lisp_Object charset) +{ + Lisp_Object name = Fcharset_name(charset); + Lisp_Object zeichen = Fget(name, Qlast_allocated_character, Qnil); + Ichar res; + + /* Only allow this with the 96x96 character sets we are using for + temporary Unicode support. */ + assert(2 == XCHARSET_DIMENSION(charset) && 96 == XCHARSET_CHARS(charset)); + + if (!NILP(zeichen)) + { + int c1, c2; + + BREAKUP_ICHAR(XCHAR(zeichen), charset, c1, c2); + + if (127 == c1 && 127 == c2) + { + /* We've already used the hightest-numbered character in this + set--tell our caller to create another. */ + return -1; + } + + if (127 == c2) + { + ++c1; + c2 = 0x20; + } + else + { + ++c2; + } + + res = make_ichar(charset, c1, c2); + Fput(name, Qlast_allocated_character, make_char(res)); + } + else + { + res = make_ichar(charset, 32, 32); + Fput(name, Qlast_allocated_character, make_char(res)); + } + return res; +} + +/* The just-in-time creation of XEmacs characters that correspond to unknown + Unicode code points happens when: + + 1. The lookup would otherwise fail. + + 2. The charsets array is the nil or the default. + + If there are no free code points in the just-in-time Unicode character + set, and the charsets array is the default unicode precedence list, + create a new just-in-time Unicode character set, add it at the end of the + unicode precedence list, create the XEmacs character in that character + set, and return it. */ + +static Ichar unicode_to_ichar (int code, Lisp_Object_dynarr *charsets) { int u1, u2, u3, u4; int code_levels; int i; int n = Dynarr_length (charsets); + static int number_of_jit_charsets; + static Ascbyte last_jit_charset_final; type_checking_assert (code >= 0); /* This shortcut depends on the representation of an Ichar, see text.c. ＠＠ -1040,8 +1104,64 ＠＠ unicode_to_ichar (int code, Lisp_Object_ return make_ichar (charset, retval >> 8, retval & 0xFF); } } + + /* Only do the magic just-in-time assignment if we're using the default + list. */ + if (unicode_precedence_dynarr == charsets) + { + if (NILP (Vcurrent_jit_charset) || + (-1 == (i = get_free_codepoint(Vcurrent_jit_charset)))) + { + Ascbyte setname[32]; + Lisp_Object charset_descr = build_string + ("Mule charset for otherwise unknown Unicode code points."); + Lisp_Object charset_regr = build_string("iso10646-1"); + + struct gcpro gcpro1, gcpro2; + + if ('\0' == last_jit_charset_final) + { + /* This final byte shit is, umm, not that cool. */ + last_jit_charset_final = 0x30; + } - return (Ichar) -1; + snprintf(setname, sizeof(setname), + "jit-ucs-charset-%d", number_of_jit_charsets++); + + /* Aside: GCPROing here would be overkill according to the FSF's + philosophy. make-charset cannot currently GC, but is intended + to be called from Lisp, with its arguments protected by the + Lisp reader. We GCPRO in case it GCs in the future and no-one + checks all the C callers. */ + + GCPRO2 (charset_descr, charset_regr); + Vcurrent_jit_charset = Fmake_charset + (intern(setname), charset_descr, + /* Set encode-as-utf-8 to t, to have this character set written + using UTF-8 escapes in escape-quoted and ctext. This + sidesteps the fact that our internal character -> Unicode + mapping is not stable from one invocation to the next. */ + nconc2 (list2(Qencode_as_utf_8, Qt), + nconc2 (list6(Qcolumns, make_int(1), Qchars, make_int(96), + Qdimension, make_int(2)), + list6(Qregistry, charset_regr, + Qfinal, make_char(last_jit_charset_final++), + /* This CCL program is initialised in + unicode.el. */ + Qccl_program, Qccl_encode_to_ucs_2)))); + UNGCPRO; + + i = get_free_codepoint(Vcurrent_jit_charset); + } + + if (-1 != i) + { + set_unicode_conversion((Ichar)i, code); + /* No need to add the charset to the end of the list; it's done + automatically. */ + } + } + return (Ichar) i; } /* Add charsets to precedence list. ＠＠ -1284,37 +1404,13 ＠＠ When there is no international support ( present), this function simply does `int-to-char' and ignores the CHARSETS argument. -Note that the current XEmacs internal encoding has no mapping for many -Unicode code points, and if you use characters that are vaguely obscure with -XEmacs' Unicode coding systems, you will lose data. - -To add support for some desired code point in the short term--note that our -intention is to move to a Unicode-compatible internal encoding soon, for -some value of soon--if you are a distributor, add something like the -following to `site-start.el.' - -(make-charset 'distro-name-private - "Private character set for DISTRO" - '(dimension 1 - chars 96 - columns 1 - final ?5 ;; Change this--see docs for make-charset - long-name "Private charset for some Unicode char support." - short-name "Distro-Private")) - -(set-unicode-conversion - (make-char 'distro-name-private #x20) #x263A) ;; WHITE SMILING FACE - -(set-unicode-conversion - (make-char 'distro-name-private #x21) #x3030) ;; WAVY DASH - -;; ... -;;; Repeat as necessary. - -Redisplay will work on the sjt-xft branch, but not with server-side X11 -fonts as is the default. However, data read in will be preserved when they -are written out again. - +If the CODE would not otherwise be converted to an XEmacs character, and the +list of character sets to be consulted is nil or the default, a new XEmacs +character will be created for it in one of the `jit-ucs-charset' Mule +character sets, and that character will be returned. There is scope for +tens of thousands of separate Unicode code points in every session using +this technique, so despite XEmacs' internal encoding not being based on +Unicode, your data won't be trashed. */ (code, USED_IF_MULE (charsets))) { ＠＠ -1558,16 +1654,6 ＠＠ Unicode tables or in the charset: /* Unicode coding system */ /************************************************************************/ -/* ISO 10646 UTF-16, UCS-4, UTF-8, UTF-7, etc. */ - -enum unicode_type -{ - UNICODE_UTF_16, - UNICODE_UTF_8, - UNICODE_UTF_7, - UNICODE_UCS_4 -}; - struct unicode_coding_system { enum unicode_type type; ＠＠ -1728,7 +1814,9 ＠＠ encode_unicode_char_1 (int code, unsigne } } -static void +/* Also used in mule-coding.c for UTF-8 handling in ISO 2022-oriented + encodings. */ +void encode_unicode_char (Lisp_Object USED_IF_MULE (charset), int h, int USED_IF_MULE (l), unsigned_char_dynarr *dst, enum unicode_type type, unsigned int little_endian) ＠＠ -2444,6 +2532,8 ＠＠ syms_of_unicode (void) DEFSUBR (Fload_unicode_mapping_table); + DEFSYMBOL (Qccl_encode_to_ucs_2); + DEFSYMBOL (Qlast_allocated_character); DEFSYMBOL (Qignore_first_column); #endif /* MULE */ ＠＠ -2518,6 +2608,9 ＠＠ vars_of_unicode (void) &lisp_object_dynarr_description); init_blank_unicode_tables (); + + staticpro (&Vcurrent_jit_charset); + Vcurrent_jit_charset = Qnil; /* Note that the "block" we are describing is a single pointer, and hence we could potentially use dump_add_root_block_ptr(). However, given 1.80 +10 -0 XEmacs/xemacs/tests/ChangeLog Index: ChangeLog =================================================================== RCS file: /pack/xemacscvs/XEmacs/xemacs/tests/ChangeLog,v retrieving revision 1.79 retrieving revision 1.80 diff -u -p -r1.79 -r1.80 --- ChangeLog 2006/05/16 08:25:02 1.79 +++ ChangeLog 2006/06/03 17:51:03 1.80 ＠＠ -1,3 +1,13 ＠＠ +2006-06-03 Aidan Kehoe <kehoea(a)parhasard.net> + + * automated/mule-tests.el: + Add checks that several Unicode characters, expressed as + UTF-8-encoded strings, are handled correctly by the UTF-8 support + of the escape-quoted character set. + * automated/mule-tests.el (unicode-code-point-to-utf-8-string): New. + Convert a Unicode code point to the equivalent UTF-8 string. + This is a naive implementation in Lisp. + 2006-05-16 Stephen J. Turnbull <stephen(a)xemacs.org> * XEmacs 21.5.27 "fiddleheads" is released. 1.9 +63 -0 XEmacs/xemacs/tests/automated/mule-tests.el Index: mule-tests.el =================================================================== RCS file: /pack/xemacscvs/XEmacs/xemacs/tests/automated/mule-tests.el,v retrieving revision 1.8 retrieving revision 1.9 diff -u -p -r1.8 -r1.9 --- mule-tests.el 2004/04/19 06:22:34 1.8 +++ mule-tests.el 2006/06/03 17:51:06 1.9 ＠＠ -78,6 +78,38 ＠＠ the Assert macro checks for correctness. ;; once compiled, for no good reason. (test-chars t) +(defun unicode-code-point-to-utf-8-string (code-point) + "Convert a Unicode code point to the equivalent UTF-8 string. +This is a naive implementation in Lisp. " + (check-argument-type 'natnump code-point) + (check-argument-range code-point 0 #x1fffff) + (if (< code-point #x80) + (format "%c" code-point) + (if (< code-point #x800) + (format "%c%c" + ;; ochars[0] = 0xC0 | (input & ~(0xFFFFF83F)) >> 6; + (logior #xc0 (lsh (logand code-point #x7c0) -6)) + ;; ochars[1] = 0x80 | input & ~(0xFFFFFFC0); + (logior #x80 (logand code-point #x3f))) + (if (< code-point #x00010000) + (format "%c%c%c" + ;; ochars[0] = 0xE0 | (input >> 12) & ~(0xFFFFFFF0); + (logior #xe0 (logand (lsh code-point -12) #x0f)) + ;; ochars[1] = 0x80 | (input >> 6) & ~(0xFFFFFFC0); + (logior #x80 (logand (lsh code-point -6) #x3f)) + ;; ochars[2] = 0x80 | input & ~(0xFFFFFFC0); + (logior #x80 (logand code-point #x3f))) + (if (< code-point #x200000) + (format "%c%c%c%c" + ;; ochars[0] = 0xF0 | (input >> 18) & ~(0xFFFFFFF8) + (logior #xF0 (logand (lsh code-point -18) #x7)) + ;; ochars[1] = 0x80 | (input >> 12) & ~(0xFFFFFFC0); + (logior #x80 (logand (lsh code-point -12) #x3f)) + ;; ochars[2] = 0x80 | (input >> 6) & ~(0xFFFFFFC0); + (logior #x80 (logand (lsh code-point -6) #x3f)) + ;; ochars[3] = 0x80 | input & ~(0xFFFFFFC0); + (logior #x80 (logand code-point #x3f)))))))) + ;;----------------------------------------------------------------- ;; Test string modification functions that modify the length of a char. ;;----------------------------------------------------------------- ＠＠ -335,6 +367,37 ＠＠ the Assert macro checks for correctness. (Assert (eq scaron (unicode-to-char code '(latin-iso8859-2)))))) (Check-Error wrong-type-argument (set-unicode-conversion scaron -10000))) + + (dolist (utf-8-char + '("\xc6\x92" ;; U+0192 LATIN SMALL LETTER F WITH HOOK + "\xe2\x81\x8a" ;; U+204A TIRONIAN SIGN ET + "\xe2\x82\xae" ;; U+20AE TUGRIK SIGN + "\xf0\x9d\x92\xbd" ;; U+1D4BD MATHEMATICAL SCRIPT SMALL H + "\xf0\x9d\x96\x93" ;; U+1D593 MATHEMATICAL BOLD FRAKTUR SMALL N + "\xf0\xaf\xa8\x88" ;; U+2FA08 CJK COMPATIBILITY FOR U+4BCE + "\xf4\x8f\xbf\xbd")) ;; U+10FFFD <Plane 16 Private Use, Last> + (let* ((xemacs-character (car (append + (decode-coding-string utf-8-char 'utf-8) + nil))) + (xemacs-charset (car (split-char xemacs-character)))) + + ;; Trivial test of the UTF-8 support of the escape-quoted character set. + (Assert (equal (decode-coding-string utf-8-char 'utf-8) + (decode-coding-string (concat "\033%G" utf-8-char) + 'escape-quoted))) + + ;; Check that the reverse mapping holds. + (Assert (equal (unicode-code-point-to-utf-8-string + (encode-char xemacs-character 'ucs)) + utf-8-char)) + + ;; Check that, if this character has been JIT-allocated, it is encoded + ;; in escape-quoted using the corresponding UTF-8 escape. + (when (charset-property xemacs-charset 'encode-as-utf-8) + (Assert (equal (concat "\033%G" utf-8-char) + (encode-coding-string xemacs-character 'escape-quoted))) + (Assert (equal (concat "\033%G" utf-8-char) + (encode-coding-string xemacs-character 'ctext)))))) ;;--------------------------------------------------------------- ;; Test charset-in-* functions

1 participants
0 comments

CVS update by aidan packages/mule-packages/leim ... 17 years, 11 months

CVS Monitor

User: aidan Date: 06/06/03 08:58:19 Modified: packages/mule-packages/leim ChangeLog quail.el Log: Quail docstring improvements, and a bugfix. Revision Changes Path 1.27 +11 -0 XEmacs/packages/mule-packages/leim/ChangeLog Index: ChangeLog =================================================================== RCS file: /pack/xemacscvs/XEmacs/packages/mule-packages/leim/ChangeLog,v retrieving revision 1.26 retrieving revision 1.27 diff -u -p -r1.26 -r1.27 --- ChangeLog 2003/10/31 17:19:52 1.26 +++ ChangeLog 2006/06/03 06:58:18 1.27 ＠＠ -1,3 +1,14 ＠＠ +2006-06-03 Aidan Kehoe <kehoea(a)parhasard.net> + + * quail.el (quail-define-rules): + * quail.el (quail-defrule): + Document in more detail what happens when a function symbol is + specified as the Quail translation for a key. + * quail.el (quail-show-translations): + Check that quail-overlay is an overlay before trying to move + it. Fixes an occasional "Wrong type argument: overlayp, nil" + message in XEmacs 21.5. + 2003-10-31 Norbert Koch <viteno(a)xemacs.org> * Makefile (VERSION): XEmacs package 1.22 released. 1.7 +20 -5 XEmacs/packages/mule-packages/leim/quail.el Index: quail.el =================================================================== RCS file: /pack/xemacscvs/XEmacs/packages/mule-packages/leim/quail.el,v retrieving revision 1.6 retrieving revision 1.7 diff -u -p -r1.6 -r1.7 --- quail.el 2003/06/30 12:36:25 1.6 +++ quail.el 2006/06/03 06:58:18 1.7 ＠＠ -808,9 +808,16 ＠＠ If it is a string, each character is a c If it is a vector, each element (string or character) is a candidate for the translation. In these cases, a key specific Quail map is generated and assigned to KEY. +(A Quail map is a cons that satisfies `quail-map-p', which see.) -If TRANSLATION is a Quail map or a function symbol which returns a Quail map, - it is used to handle KEY." +If TRANSLATION is a Quail map it is used to handle KEY. + +If TRANSLATION is a function symbol, that function should take two +arguments, the input string and its length, and it should return a Quail map +to be used to handle KEY. For each KEY that translates to the function, +that function will be called just once, and the result cached by Quail--this +means that some of the context-dependent processing you may be tempted to +do, like manipulating unread-command-events, is not possible. " `(quail-install-map ',(let ((l rules) (map (list nil))) ＠＠ -844,9 +851,17 ＠＠ If it is a cons, the car is one of the a variable `quail-current-data'). If the cdr part is not a function, the value itself is assigned to `quail-current-data'. In these cases, a key specific Quail map is generated and assigned to KEY. +(A Quail map is a cons that satisfies `quail-map-p', which see.) + +If TRANSLATION is a Quail map it is used to handle KEY. + +If TRANSLATION is a function symbol, that function should take two +arguments, the input string and its length. It should return a Quail map to +be used to handle KEY. For each KEY that translates to the function, that +function will be called just once, and the result cached by Quail--this +means that some of the context-dependent processing you may be tempted to +do, like manipulating `unread-command-events', is not possible. -If TRANSLATION is a Quail map or a function symbol which returns a Quail map, - it is used to handle KEY. Optional argument NAME, if specified, says which Quail package to define this translation rule in. The default is to define it in the current Quail package." ＠＠ -1635,7 +1650,7 ＠＠ or in a newly created frame (if the sele (1+ (- idx start))))) (let ((pos (point))) (insert (aref (cdr quail-current-translations) idx)) - (if (= idx cur) + (if (and (overlayp quail-overlay) (= idx cur)) (move-overlay quail-overlay pos (point)))) (setq idx (1+ idx))))) )))

1 participants
0 comments

CVS update by adrian xemacs/lisp ... 17 years, 11 months

CVS Monitor

User: adrian Date: 06/06/03 00:18:14 Modified: xemacs/lisp ChangeLog package-get.el Log: xemacs-21.5-clean: Welcome nl.xemacs.org and Thanks! -------------------- ChangeLog entries follow: -------------------- lisp/ChangeLog addition: 2006-06-03 Adrian Aichner <adrian(a)xemacs.org> * package-get.el (package-get-download-sites): Welcome nl.xemacs.org and Thanks! * package-get.el (package-get-pre-release-download-sites): Ditto. Revision Changes Path 1.747 +6 -0 XEmacs/xemacs/lisp/ChangeLog Index: ChangeLog =================================================================== RCS file: /pack/xemacscvs/XEmacs/xemacs/lisp/ChangeLog,v retrieving revision 1.746 retrieving revision 1.747 diff -u -p -r1.746 -r1.747 --- ChangeLog 2006/05/29 21:25:48 1.746 +++ ChangeLog 2006/06/02 22:18:05 1.747 ＠＠ -1,3 +1,9 ＠＠ +2006-06-03 Adrian Aichner <adrian(a)xemacs.org> + + * package-get.el (package-get-download-sites): Welcome + nl.xemacs.org and Thanks! + * package-get.el (package-get-pre-release-download-sites): Ditto. + 2006-05-24 Jerry James <james(a)xemacs.org> * autoload.el (batch-update-autoloads): Only write to 1.76 +3 -0 XEmacs/xemacs/lisp/package-get.el Index: package-get.el =================================================================== RCS file: /pack/xemacscvs/XEmacs/xemacs/lisp/package-get.el,v retrieving revision 1.75 retrieving revision 1.76 diff -u -p -r1.75 -r1.76 --- package-get.el 2006/01/06 12:24:20 1.75 +++ package-get.el 2006/06/02 22:18:08 1.76 ＠＠ -242,6 +242,7 ＠＠ directory." ; ("Japan (nucba.ac.jp)" "mirror.nucba.ac.jp" "mirror/xemacs/packages") ("Japan (sut.ac.jp)" "sunsite.sut.ac.jp" "pub/archives/packages/xemacs/packages") ("Korea (kr.xemacs.org)" "ftp.kr.xemacs.org" "pub/tools/emacs/xemacs/packages") + ("Netherlands (nl.xemacs.org)" "ftp.nl.xemacs.org" "pub/xemacs/ftp/packages") ("New Zealand (nz.xemacs.org)" "ftp.nz.xemacs.org" "mirror/ftp.xemacs.org/packages") ("Norway (no.xemacs.org)" "ftp.no.xemacs.org" "pub/xemacs/packages") ("Poland (pl.xemacs.org)" "ftp.pl.xemacs.org" "pub/unix/editors/xemacs/packages") ＠＠ -332,6 +333,8 ＠＠ variable actually used to specify packag "pub/archives/packages/xemacs/xemacs-21.5/experimental/packages") ("Korea (kr.xemacs.org)" "ftp.kr.xemacs.org" "pub/tools/emacs/xemacs/beta/experimental/packages") + ("Netherlands (nl.xemacs.org)" "ftp.nl.xemacs.org" + "pub/xemacs/ftp/beta/experimental/packages") ("New Zealand Pre-Releases (nz.xemacs.org)" "ftp.nz.xemacs.org" "mirror/ftp.xemacs.org/packages") ("Norway Pre-Releases (no.xemacs.org)" "ftp.no.xemacs.org"

1 participants
0 comments

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

2004

xemacs-cvs June 2006