Mercurial > hg > xemacs-beta
annotate lisp/mule/general-late.el @ 4549:68d1ca56cffa
First part of interactive checks that coding systems encode regions.
2008-01-21 Aidan Kehoe <kehoea@parhasard.net>
* coding.el (decode-coding-string):
(encode-coding-string): Accept GNU's NOCOPY argument for
these. Todo; write compiler macros to use it.
(query-coding-warning-face): New face, to show unencodable
characters.
(default-query-coding-region-safe-charset-skip-chars-map):
New variable, a cache used by #'default-query-coding-region.
(default-query-coding-region): Default implementation of
#'query-coding-region, using the safe-charsets and safe-chars
coding systemproperties.
(query-coding-region): New function; can a given coding system
encode a given region?
(query-coding-string): New function; can a given coding system
encode a given string?
(unencodable-char-position): Function API taken from GNU; return
the first unencodable position given a string and coding system.
(encode-coding-char): Function API taken from GNU; return CHAR
encoded using CODING-SYSTEM, or nil if CODING-SYSTEM would trash
CHAR.
((unless (featurep 'mule)): Override the default
query-coding-region implementation on non-Mule.
* mule/mule-coding.el (make-8-bit-generate-helper): Eliminate a
duplicate comment.
(make-8-bit-choose-category): Simplify implementation.
(8-bit-fixed-query-coding-region): Implementation of
#'query-coding-region for coding systems created with
#'make-8-bit-coding-system.
(make-8-bit-coding-system): Initialise the #'query-coding-region
implementation for these character sets.
(make-8-bit-coding-system): Ditto for the compiler macro version
of this function.
* unicode.el (unicode-query-coding-skip-chars-arg): New variable,
used by unicode-query-coding-region, initialised in
mule/general-late.el.
(unicode-query-coding-region): New function, the
#'query-coding-region implementation for Unicode coding systems.
Initialise the query-coding-function property for the Unicode
coding systems to #'unicode-query-coding-region.
* mule/mule-charset.el (charset-skip-chars-string): New
function. Return a #'skip-chars-forward argument that skips all
characters in CHARSET.
(map-charset-chars): Function synced from GNU, modified to work
with XEmacs. Map FUNC across the int value charset ranges of
CHARSET.
| author | Aidan Kehoe <kehoea@parhasard.net> |
|---|---|
| date | Mon, 21 Jan 2008 22:51:21 +0100 |
| parents | 9fec7fedbf1b |
| children | 84d618b355f5 |
| rev | line source |
|---|---|
| 3707 | 1 ;;; general-late.el --- General Mule code that needs to be run late when |
| 2 ;; dumping. | |
| 3 ;; Copyright (C) 2006 Free Software Foundation | |
| 4 | |
| 5 ;; Author: Aidan Kehoe | |
| 6 | |
| 7 ;; This file is part of XEmacs. | |
| 8 | |
| 9 ;; XEmacs is free software; you can redistribute it and/or modify it | |
| 10 ;; under the terms of the GNU General Public License as published by | |
| 11 ;; the Free Software Foundation; either version 2, or (at your option) | |
| 12 ;; any later version. | |
| 13 | |
| 14 ;; XEmacs is distributed in the hope that it will be useful, but | |
| 15 ;; WITHOUT ANY WARRANTY; without even the implied warranty of | |
| 16 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU | |
| 17 ;; General Public License for more details. | |
| 18 | |
| 19 ;; You should have received a copy of the GNU General Public License | |
| 20 ;; along with XEmacs; see the file COPYING. If not, write to the | |
| 21 ;; Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, | |
| 22 ;; Boston, MA 02110-1301, USA. | |
| 23 | |
| 24 ;;; Commentary: | |
| 25 | |
| 26 ;;; Code: | |
| 27 | |
| 28 ;; The variable is declared in mule-cmds.el; it's initialised here, to give | |
| 29 ;; the language-specific code a chance to create its coding systems. | |
| 30 | |
| 31 (setq posix-charset-to-coding-system-hash | |
| 4145 | 32 (loop |
| 33 ;; We want both normal and internal coding systems in order | |
| 34 ;; to pick up coding system aliases. | |
| 35 for coding-system in (coding-system-list 'every) | |
| 36 with res = (make-hash-table :test #'equal) | |
| 37 do | |
| 38 (setq coding-system (symbol-name coding-system)) | |
| 39 (unless (or (string-match #r"\(-unix\|-mac\|-dos\)$" coding-system) | |
| 40 (string-match #r"^\(internal\|mswindows\)" coding-system)) | |
| 41 (puthash | |
| 42 (replace-in-string (downcase coding-system) "[^a-z0-9]" "") | |
| 43 (coding-system-name (intern coding-system)) res)) | |
| 44 finally return res) | |
| 3707 | 45 |
| 46 ;; In a thoughtless act of cultural imperialism, move English, German | |
| 47 ;; and Japanese to the front of language-info-alist to make start-up a | |
| 48 ;; fraction faster for those languages. | |
| 49 language-info-alist | |
| 50 (cons (assoc "Japanese" language-info-alist) | |
| 51 (remassoc "Japanese" language-info-alist)) | |
| 52 language-info-alist | |
| 53 (cons (assoc "German" language-info-alist) | |
| 54 (remassoc "German" language-info-alist)) | |
| 55 language-info-alist | |
| 56 (cons (assoc "English" language-info-alist) | |
| 4246 | 57 (remassoc "English" language-info-alist)) |
| 58 | |
| 59 ;; Make Installation-string actually reflect the environment at | |
| 60 ;; byte-compile time. (We can't necessarily decode it when version.el | |
| 61 ;; is loaded, since not all the coding systems are available then.) | |
| 62 Installation-string (if-boundp 'Installation-file-coding-system | |
| 63 (decode-coding-string | |
| 64 Installation-string | |
| 65 Installation-file-coding-system) | |
|
4549
68d1ca56cffa
First part of interactive checks that coding systems encode regions.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4246
diff
changeset
|
66 Installation-string) |
|
68d1ca56cffa
First part of interactive checks that coding systems encode regions.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4246
diff
changeset
|
67 |
|
68d1ca56cffa
First part of interactive checks that coding systems encode regions.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4246
diff
changeset
|
68 ;; Convince the byte compiler that, really, this file can't be encoded |
|
68d1ca56cffa
First part of interactive checks that coding systems encode regions.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4246
diff
changeset
|
69 ;; as binary. Ugh. |
|
68d1ca56cffa
First part of interactive checks that coding systems encode regions.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4246
diff
changeset
|
70 system-type (symbol-value (intern "\u0073ystem-type")) |
|
68d1ca56cffa
First part of interactive checks that coding systems encode regions.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4246
diff
changeset
|
71 |
|
68d1ca56cffa
First part of interactive checks that coding systems encode regions.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4246
diff
changeset
|
72 unicode-query-coding-skip-chars-arg |
|
68d1ca56cffa
First part of interactive checks that coding systems encode regions.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4246
diff
changeset
|
73 (eval-when-compile |
|
68d1ca56cffa
First part of interactive checks that coding systems encode regions.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4246
diff
changeset
|
74 (when-fboundp #'map-charset-chars |
|
68d1ca56cffa
First part of interactive checks that coding systems encode regions.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4246
diff
changeset
|
75 (loop |
|
68d1ca56cffa
First part of interactive checks that coding systems encode regions.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4246
diff
changeset
|
76 for charset in (charset-list) |
|
68d1ca56cffa
First part of interactive checks that coding systems encode regions.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4246
diff
changeset
|
77 with skip-chars-string = "" |
|
68d1ca56cffa
First part of interactive checks that coding systems encode regions.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4246
diff
changeset
|
78 do |
|
68d1ca56cffa
First part of interactive checks that coding systems encode regions.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4246
diff
changeset
|
79 (block no-ucs-mapping |
|
68d1ca56cffa
First part of interactive checks that coding systems encode regions.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4246
diff
changeset
|
80 (map-charset-chars |
|
68d1ca56cffa
First part of interactive checks that coding systems encode regions.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4246
diff
changeset
|
81 #'(lambda (begin end) |
|
68d1ca56cffa
First part of interactive checks that coding systems encode regions.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4246
diff
changeset
|
82 (loop |
|
68d1ca56cffa
First part of interactive checks that coding systems encode regions.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4246
diff
changeset
|
83 while (/= end begin) |
|
68d1ca56cffa
First part of interactive checks that coding systems encode regions.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4246
diff
changeset
|
84 do |
|
68d1ca56cffa
First part of interactive checks that coding systems encode regions.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4246
diff
changeset
|
85 (when (= -1 (char-to-unicode begin)) |
|
68d1ca56cffa
First part of interactive checks that coding systems encode regions.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4246
diff
changeset
|
86 (setq this-charset-works nil) |
|
68d1ca56cffa
First part of interactive checks that coding systems encode regions.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4246
diff
changeset
|
87 (return-from no-ucs-mapping)) |
|
68d1ca56cffa
First part of interactive checks that coding systems encode regions.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4246
diff
changeset
|
88 (setq begin (int-to-char (1+ begin))))) |
|
68d1ca56cffa
First part of interactive checks that coding systems encode regions.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4246
diff
changeset
|
89 charset) |
|
68d1ca56cffa
First part of interactive checks that coding systems encode regions.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4246
diff
changeset
|
90 (setq skip-chars-string |
|
68d1ca56cffa
First part of interactive checks that coding systems encode regions.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4246
diff
changeset
|
91 (concat skip-chars-string |
|
68d1ca56cffa
First part of interactive checks that coding systems encode regions.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4246
diff
changeset
|
92 (charset-skip-chars-string charset)))) |
|
68d1ca56cffa
First part of interactive checks that coding systems encode regions.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4246
diff
changeset
|
93 finally return skip-chars-string)))) |
| 3707 | 94 |
| 3767 | 95 ;; At this point in the dump, all the charsets have been loaded. Now, load |
| 96 ;; their Unicode mappings. | |
| 97 (if load-unicode-tables-at-dump-time | |
| 98 (let ((data-directory (expand-file-name "etc" source-directory))) | |
| 99 (load-unicode-tables))) | |
| 100 | |
| 4246 | 101 ;;; general-late.el ends here |