From: teranisi Date: Wed, 5 May 2004 11:27:40 +0000 (+0000) Subject: Synch up with latest gnus/utf7.el; X-Git-Tag: wl-2_11_27~10 X-Git-Url: http://git.chise.org/gitweb/?a=commitdiff_plain;h=e3402fbc4549e7542b6ab692146ce65b6d36f633;p=elisp%2Fwanderlust.git Synch up with latest gnus/utf7.el; Modified for latest Emacs. --- diff --git a/elmo/utf7.el b/elmo/utf7.el index 1000d68..21565e0 100644 --- a/elmo/utf7.el +++ b/elmo/utf7.el @@ -1,11 +1,10 @@ -;;; utf7.el --- UTF-7 encoding/decoding for Emacs -;; Copyright (C) 1999 Free Software Foundation, Inc. +;;; utf7.el --- UTF-7 encoding/decoding for Emacs -*-coding: iso-8859-1;-*- +;; Copyright (C) 1999, 2000, 2003 Free Software Foundation, Inc. -;; Author: Jon K Hellan +;; Author: Jon K Hellan +;; Maintainer: bugs@gnus.org ;; Keywords: mail -;; This file is part of GNU Emacs, but the same permissions apply - ;; GNU Emacs 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) @@ -22,207 +21,134 @@ ;; Boston, MA 02111-1307, USA. ;;; Commentary: -;;; UTF-7 - A Mail-Safe Transformation Format of Unicode - RFC 2152 -;;; This is a transformation format of Unicode that contains only 7-bit -;;; ASCII octets and is intended to be readable by humans in the limiting -;;; case that the document consists of characters from the US-ASCII -;;; repertoire. -;;; In short, runs of characters outside US-ASCII are encoded as base64 -;;; inside delimiters. -;;; A variation of UTF-7 is specified in IMAP 4rev1 (RFC 2060) as the way -;;; to represent characters outside US-ASCII in mailbox names in IMAP. -;;; This library supports both variants, but the IMAP variation was the -;;; reason I wrote it. -;;; The routines convert UTF-7 -> UTF-16 (16 bit encoding of Unicode) -;;; -> current character set, and vice versa. -;;; However, until Emacs supports Unicode, the only Emacs character set -;;; supported here is ISO-8859.1, which can trivially be converted to/from -;;; Unicode. -;;; When decoding results in a character outside the Emacs character set, -;;; an error is thrown. It is up to the application to recover. -;;; Modified 8 December 1999 by Yuuichi Teranishi so that it will work under -;;; Emacs+Mule-UCS and XEmacs. +;; UTF-7 - A Mail-Safe Transformation Format of Unicode - RFC 2152 +;; This is a transformation format of Unicode that contains only 7-bit +;; ASCII octets and is intended to be readable by humans in the limiting +;; case that the document consists of characters from the US-ASCII +;; repertoire. +;; In short, runs of characters outside US-ASCII are encoded as base64 +;; inside delimiters. +;; A variation of UTF-7 is specified in IMAP 4rev1 (RFC 2060) as the way +;; to represent characters outside US-ASCII in mailbox names in IMAP. +;; This library supports both variants, but the IMAP variation was the +;; reason I wrote it. +;; The routines convert UTF-7 -> UTF-16 (16 bit encoding of Unicode) +;; -> current character set, and vice versa. +;; However, until Emacs supports Unicode, the only Emacs character set +;; supported here is ISO-8859.1, which can trivially be converted to/from +;; Unicode. +;; When decoding results in a character outside the Emacs character set, +;; an error is thrown. It is up to the application to recover. + +;; UTF-7 should be done by providing a coding system. Mule-UCS does +;; already, but I don't know if it does the IMAP version and it's not +;; clear whether that should really be a coding system. The UTF-16 +;; part of the conversion can be done with coding systems available +;; with Mule-UCS or some versions of Emacs. Unfortunately these were +;; done wrongly (regarding handling of byte-order marks and how the +;; variants were named), so we don't have a consistent name for the +;; necessary coding system. The code below doesn't seem to DTRT +;; generally. E.g.: +;; +;; (utf7-encode "a+£") +;; => "a+ACsAow-" +;; +;; $ echo "a+£"|iconv -f iso-8859-1 -t utf-7 +;; a+-+AKM +;; +;; -- fx + +;; Modified 5 May 2004 by Yuuichi Teranishi so that it can run with APEL/FLIM +;; instead of mm-util in Gnus. +;; +;; * Use find-coding-system instead of mm-coding-system-p. +;; * Use mel.el instead of base64.el. +;; * Don't use mm-with-unibyte-current-buffer etc. +;; * Do nothing if utf-16 coding system is not found. ;;; Code: (eval-when-compile (require 'cl)) -(eval-when-compile (require 'pces)) -(eval-when-compile (require 'static)) +(require 'pces) +(require 'mel) -;; base64 stuff. -;;(static-if (and (fboundp 'base64-decode-region) -;; (subrp (symbol-function 'base64-decode-region))) -;; (eval-and-compile (fset 'utf7-base64-decode-region 'base64-decode-region)) -;; (require 'mel) -;; (defun utf7-base64-decode-region (start end) -;; (fset 'utf7-base64-decode-string -;; (symbol-function (mel-find-function 'mime-decode-region "base64"))) -;; (utf7-base64-decode-region start end))) +;; base64 encoding/decoding +(defun utf7-base64-encode-region (beg end &optional no-line-break)) +(defun utf7-base64-decode-region (beg end)) +(fset 'utf7-base64-encode-region + (mel-find-function 'mime-encode-region "base64")) +(fset 'utf7-base64-decode-region + (mel-find-function 'mime-decode-region "base64")) -;;(static-if (and (fboundp 'base64-encode-region) -;; (subrp (symbol-function 'base64-encode-region))) -;; (eval-and-compile (fset 'utf7-base64-encode-region 'base64-encode-region)) -;; (defun utf7-base64-encode-string (start end) -;; (fset 'utf7-base64-encode-region -;; (symbol-function (mel-find-function 'mime-encode-region "base64"))) -;; (utf7-base64-encode-region start end))) +(defconst utf7-direct-encoding-chars " -%'-*,-[]-}" + "Character ranges which do not need escaping in UTF-7.") -;; On XEmacs which does not support UTF-16 have to use u7tou8 and u8tou7. -;; These programs are included in -;; ftp://ftp.ifcss.org/pub/software/unix/convert/utf7.tar.gz -(defvar utf7-utf7-to-utf8-program "u7tou8" - "Program to convert utf7 to utf8.") -(defvar utf7-utf8-to-utf7-program "u8tou7" - "Program to convert utf8 to utf7.") +(defconst utf7-imap-direct-encoding-chars + (concat utf7-direct-encoding-chars "+\\~") + "Character ranges which do not need escaping in the IMAP variant of UTF-7.") -(defvar utf7-direct-encoding-chars " -%'-*,-[]-} \t\n\r" - "Characters ranges which do not need escaping in UTF-7") -(defvar utf7-imap-direct-encoding-chars - (concat utf7-direct-encoding-chars "+\\\\~") - "Characters ranges which do not need escaping in the IMAP modified variant of UTF-7") +(defconst utf7-utf-16-coding-system (find-coding-system 'utf-16-be) + "Coding system which encodes big endian UTF-16.") -(defsubst utf7-imap-get-pad-length (len modulus) +(defsubst utf7-imap-get-pad-length (len modulus) "Return required length of padding for IMAP modified base64 fragment." (mod (- len) modulus)) -(cond - ((or (and (fboundp 'find-coding-system) - (find-coding-system 'utf-7)) - (module-installed-p 'un-define)) - (defun utf7-fragment-decode (start end &optional imap) - "Decode base64 encoded fragment from START to END of UTF-7 text in buffer. -Use IMAP modification if IMAP is non-nil." - (require 'un-define) - (save-restriction - (narrow-to-region start end) - (goto-char (point-min)) - (insert "+") - (when imap - (goto-char start) - (while (search-forward "," nil 'move-to-end) (replace-match "/"))) - (decode-coding-region (point-min) (point-max) 'utf-7))) - - (defun utf7-fragment-encode (start end &optional imap) - "Encode text from START to END in buffer as UTF-7 escape fragment. -Use IMAP modification if IMAP is non-nil." - (require 'un-define) - (let ((buffer (current-buffer)) - encoded-string) - (setq encoded-string - (with-temp-buffer - (insert-buffer-substring buffer start end) - (encode-coding-region (point-min) - (point-max) 'utf-7) - (goto-char (point-min)) - (when imap - (skip-chars-forward "+") - (delete-region (point-min) (point)) - (insert "&") - (while (search-forward "/" nil t) - (replace-match ","))) - (skip-chars-forward "^= \t\n" (point-max)) - (delete-region (point) (point-max)) - (buffer-string))) - (delete-region start end) - (insert encoded-string)))) - ((and (featurep 'xemacs) - (or (and (fboundp 'find-coding-system) - (find-coding-system 'utf-8)) - (module-installed-p 'xemacs-ucs))) - (defun utf7-fragment-decode (start end &optional imap) - "Decode base64 encoded fragment from START to END of UTF-7 text in buffer. -Use IMAP modification if IMAP is non-nil." - (require 'xemacs-ucs) - (save-restriction - (narrow-to-region start end) - (when imap - (goto-char start) - (while (search-forward "," nil 'move-to-end) (replace-match "/"))) - (goto-char (point-min)) - (insert "+") - (as-binary-process - (call-process-region (point-min) (point-max) - utf7-utf7-to-utf8-program - t (current-buffer))) - (decode-coding-region (point-min) (point-max) 'utf-8))) - - (defun utf7-fragment-encode (start end &optional imap) - "Decode base64 encoded fragment from START to END of UTF-7 text in buffer. -Use IMAP modification if IMAP is non-nil." - (require 'xemacs-ucs) - (let ((buffer (current-buffer)) - encoded-string) - (setq encoded-string - (with-temp-buffer - (insert-buffer-substring buffer start end) - (save-excursion - (goto-char (point-max)) - (insert "\n")) - (encode-coding-region (point-min) (point-max) 'utf-8) - (as-binary-process - (call-process-region (point-min) (point-max) - utf7-utf8-to-utf7-program - t (current-buffer))) - (goto-char (point-min)) - (when imap - (skip-chars-forward "+") - (delete-region (point-min) (point)) - (insert "&") - (while (search-forward "/" nil t) - (replace-match ","))) - (goto-char (point-max)) - (delete-backward-char 1) - (insert "-") - (buffer-string))) - (delete-region start end) - (insert encoded-string)))) - (t - (defun utf7-fragment-decode (start end &optional imap) - "Encode text from START to END in buffer as UTF-7 escape fragment. -Use IMAP modification if IMAP is non-nil." - ;; Define as a null function. - ) - - (defun utf7-fragment-encode (start end &optional imap) - "Encode text from START to END in buffer as UTF-7 escape fragment. -Use IMAP modification if IMAP is non-nil." - ;; Define as a null function. - ))) - -(defun utf7-encode-region (start end &optional imap) - "Encode text in region as UTF-7. -Use IMAP modification if IMAP is non-nil." - (interactive "r") - (save-restriction - ;;(set-buffer-multibyte default-enable-multibyte-characters) +(defun utf7-encode-internal (&optional for-imap) + "Encode text in (temporary) buffer as UTF-7. +Use IMAP modification if FOR-IMAP is non-nil." + (let ((start (point-min)) + (end (point-max))) (narrow-to-region start end) (goto-char start) - (let ((esc-char (if imap ?& ?+)) - (direct-encoding-chars - (if imap utf7-imap-direct-encoding-chars - utf7-direct-encoding-chars))) + (let* ((esc-char (if for-imap ?& ?+)) + (direct-encoding-chars + (if for-imap utf7-imap-direct-encoding-chars + utf7-direct-encoding-chars)) + (not-direct-encoding-chars (concat "^" direct-encoding-chars))) (while (not (eobp)) (skip-chars-forward direct-encoding-chars) (unless (eobp) + (insert esc-char) (let ((p (point)) (fc (following-char)) - (run-length - (skip-chars-forward (concat "^" direct-encoding-chars)))) + (run-length + (skip-chars-forward not-direct-encoding-chars))) (if (and (= fc esc-char) (= run-length 1)) ; Lone esc-char? (delete-backward-char 1) ; Now there's one too many - (utf7-fragment-encode p (point) imap)))))))) + (utf7-fragment-encode p (point) for-imap)) + (insert "-"))))))) -(defun utf7-decode-region (start end &optional imap) - "Decode UTF-7 text in region. -Use IMAP modification if IMAP is non-nil." - (interactive "r") - (save-excursion +(defun utf7-fragment-encode (start end &optional for-imap) + "Encode text from START to END in buffer as UTF-7 escape fragment. +Use IMAP modification if FOR-IMAP is non-nil." + (save-restriction + (narrow-to-region start end) + (let ((converter (utf7-get-u16char-converter 'to-utf-16)) + pm) + (when converter + (funcall converter) + (set-buffer-multibyte nil) + (utf7-base64-encode-region start (point-max)) + (goto-char start) + (setq pm (point-max)) + (when for-imap + (while (search-forward "/" nil t) + (replace-match ","))) + (skip-chars-forward "^= \t\n" pm) + (delete-region (point) pm))))) + +(defun utf7-decode-internal (&optional for-imap) + "Decode UTF-7 text in (temporary) buffer. +Use IMAP modification if FOR-IMAP is non-nil." + (let ((start (point-min)) + (end (point-max))) (goto-char start) - (let* ((esc-pattern (concat "^" (char-to-string (if imap ?& ?+)))) - (base64-chars (concat "A-Za-z0-9+" - (char-to-string (if imap ?, ?/))))) + (let* ((esc-pattern (concat "^" (char-to-string (if for-imap ?& ?+)))) + (base64-chars (concat "A-Za-z0-9+" + (char-to-string (if for-imap ?, ?/))))) (while (not (eobp)) (skip-chars-forward esc-pattern) (unless (eobp) @@ -233,29 +159,60 @@ Use IMAP modification if IMAP is non-nil." (delete-char 1)) (unless (= run-length 0) ; Encoded lone esc-char? (save-excursion - (utf7-fragment-decode p (point) imap) + (utf7-fragment-decode p (point) for-imap) (goto-char p) - (delete-backward-char 1))))))) - ;;(set-buffer-multibyte default-enable-multibyte-characters) - )) - -(defun utf7-encode-string (string &optional imap) - "Encode UTF-7 string. Use IMAP modification if IMAP is non-nil." - (with-temp-buffer - (insert string) - (utf7-encode-region (point-min) (point-max) imap) - (buffer-string))) + (delete-backward-char 1))))))))) -(defun utf7-decode-string (string &optional imap) - "Decode UTF-7 string. Use IMAP modification if IMAP is non-nil." - (with-temp-buffer - (insert string) - (utf7-decode-region (point-min) (point-max) imap) - (buffer-string))) - -;; For compatibility. -(defalias 'utf7-decode 'utf7-decode-string) -(defalias 'utf7-encode 'utf7-encode-string) +(defun utf7-fragment-decode (start end &optional for-imap) + "Decode base64 encoded fragment from START to END of UTF-7 text in buffer. +Use IMAP modification if FOR-IMAP is non-nil." + (save-restriction + (narrow-to-region start end) + (let ((converter (utf7-get-u16char-converter 'from-utf-16))) + (when converter + (when for-imap + (goto-char start) + (while (search-forward "," nil 'move-to-end) (replace-match "/"))) + (let ((pl (utf7-imap-get-pad-length (- end start) 4))) + (insert (make-string pl ?=)) + (utf7-base64-decode-region start (+ end pl))) + (funcall converter))))) + +(defun utf7-get-u16char-converter (which-way) + "Return a function to convert between UTF-16 and current character set." + (if utf7-utf-16-coding-system + (if (eq which-way 'to-utf-16) + (lambda () + (encode-coding-region (point-min)(point-max) + utf7-utf-16-coding-system) + (set-buffer-multibyte nil) + (goto-char (point-min)) + ;; Remove BOM (Big-endian UTF-16 FE FF) + (while (re-search-forward "\376\377" nil t) + (delete-region (match-beginning 0)(match-end 0)))) + (lambda () + (goto-char (point-min)) + ;; Add BOM (Big-endian UTF-16 FE FF) + (insert "\376\377") + (decode-coding-region (point-min) (point-max) + utf7-utf-16-coding-system))))) + +(defun utf7-encode (string &optional for-imap) + "Encode UTF-7 STRING. Use IMAP modification if FOR-IMAP is non-nil." + (let ((default-enable-multibyte-characters t)) + (with-temp-buffer + (insert string) + (utf7-encode-internal for-imap) + (buffer-string)))) + +(defun utf7-decode (string &optional for-imap) + "Decode UTF-7 STRING. Use IMAP modification if FOR-IMAP is non-nil." + (let ((default-enable-multibyte-characters nil)) + (with-temp-buffer + (insert string) + (utf7-decode-internal for-imap) + (set-buffer-multibyte t) + (buffer-string)))) (provide 'utf7)