1 ;;; utf7.el --- UTF-7 encoding/decoding for Emacs -*-coding: iso-8859-1;-*-
2 ;; Copyright (C) 1999, 2000, 2003 Free Software Foundation, Inc.
4 ;; Author: Jon K Hellan <hellan@acm.org>
5 ;; Maintainer: bugs@gnus.org
8 ;; This file is part of GNU Emacs.
10 ;; GNU Emacs is free software; you can redistribute it and/or modify
11 ;; it under the terms of the GNU General Public License as published by
12 ;; the Free Software Foundation; either version 2, or (at your option)
15 ;; GNU Emacs is distributed in the hope that it will be useful,
16 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
17 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
18 ;; GNU General Public License for more details.
20 ;; You should have received a copy of the GNU General Public License
21 ;; along with GNU Emacs; see the file COPYING. If not, write to
22 ;; the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
23 ;; Boston, MA 02111-1307, USA.
27 ;; UTF-7 - A Mail-Safe Transformation Format of Unicode - RFC 2152
28 ;; This is a transformation format of Unicode that contains only 7-bit
29 ;; ASCII octets and is intended to be readable by humans in the limiting
30 ;; case that the document consists of characters from the US-ASCII
32 ;; In short, runs of characters outside US-ASCII are encoded as base64
34 ;; A variation of UTF-7 is specified in IMAP 4rev1 (RFC 2060) as the way
35 ;; to represent characters outside US-ASCII in mailbox names in IMAP.
36 ;; This library supports both variants, but the IMAP variation was the
38 ;; The routines convert UTF-7 -> UTF-16 (16 bit encoding of Unicode)
39 ;; -> current character set, and vice versa.
40 ;; However, until Emacs supports Unicode, the only Emacs character set
41 ;; supported here is ISO-8859.1, which can trivially be converted to/from
43 ;; When decoding results in a character outside the Emacs character set,
44 ;; an error is thrown. It is up to the application to recover.
46 ;; UTF-7 should be done by providing a coding system. Mule-UCS does
47 ;; already, but I don't know if it does the IMAP version and it's not
48 ;; clear whether that should really be a coding system. The UTF-16
49 ;; part of the conversion can be done with coding systems available
50 ;; with Mule-UCS or some versions of Emacs. Unfortunately these were
51 ;; done wrongly (regarding handling of byte-order marks and how the
52 ;; variants were named), so we don't have a consistent name for the
53 ;; necessary coding system. The code below doesn't seem to DTRT
56 ;; (utf7-encode "a+£")
59 ;; $ echo "a+£"|iconv -f iso-8859-1 -t utf-7
68 (eval-when-compile (require 'cl))
71 (defconst utf7-direct-encoding-chars " -%'-*,-[]-}"
72 "Character ranges which do not need escaping in UTF-7.")
74 (defconst utf7-imap-direct-encoding-chars
75 (concat utf7-direct-encoding-chars "+\\~")
76 "Character ranges which do not need escaping in the IMAP variant of UTF-7.")
78 (defconst utf7-utf-16-coding-system
79 (cond ((mm-coding-system-p 'utf-16-be-no-signature) ; Mule-UCS
80 'utf-16-be-no-signature)
81 ((and (mm-coding-system-p 'utf-16-be) ; Emacs 21.4 (?), Emacs 22
82 ;; Avoid versions with BOM.
83 (= 2 (length (encode-coding-string "a" 'utf-16-be))))
85 ((mm-coding-system-p 'utf-16-be-nosig) ; ?
87 "Coding system which encodes big endian UTF-16 without a BOM signature.")