diff options
Diffstat (limited to 'lisp/international')
| -rw-r--r-- | lisp/international/rfc1843.el | 131 | ||||
| -rw-r--r-- | lisp/international/utf7.el | 236 |
2 files changed, 367 insertions, 0 deletions
diff --git a/lisp/international/rfc1843.el b/lisp/international/rfc1843.el new file mode 100644 index 00000000000..508629fb062 --- /dev/null +++ b/lisp/international/rfc1843.el @@ -0,0 +1,131 @@ +;;; rfc1843.el --- HZ (rfc1843) decoding + +;; Copyright (C) 1998-2016 Free Software Foundation, Inc. + +;; Author: Shenghuo Zhu <zsh@cs.rochester.edu> +;; Keywords: news HZ HZ+ mail i18n + +;; This file is part of GNU Emacs. + +;; 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 3 of the License, or +;; (at your option) any later version. + +;; GNU Emacs 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. If not, see <http://www.gnu.org/licenses/>. + +;;; Commentary: + +;; Test: +;; (rfc1843-decode-string "~{<:Ky2;S{#,NpJ)l6HK!#~}") + +;;; Code: + +(eval-when-compile (require 'cl)) + +(defvar rfc1843-word-regexp + "~\\({\\([\041-\167][\041-\176]\\| \\)+\\)\\(~}\\|$\\)") + +(defvar rfc1843-word-regexp-strictly + "~\\({\\([\041-\167][\041-\176]\\)+\\)\\(~}\\|$\\)") + +(defvar rfc1843-hzp-word-regexp + "~\\({\\([\041-\167][\041-\176]\\| \\)+\\|\ +[<>]\\([\041-\175][\041-\176]\\| \\)+\\)\\(~}\\|$\\)") + +(defvar rfc1843-hzp-word-regexp-strictly + "~\\({\\([\041-\167][\041-\176]\\)+\\|\ +[<>]\\([\041-\175][\041-\176]\\)+\\)\\(~}\\|$\\)") + +(defcustom rfc1843-decode-loosely nil + "Loosely check HZ encoding if non-nil. +When it is set non-nil, only buffers or strings with strictly +HZ-encoded are decoded." + :type 'boolean + :group 'mime) + +(defcustom rfc1843-decode-hzp t + "HZ+ decoding support if non-nil. +HZ+ specification (also known as HZP) is to provide a standardized +7-bit representation of mixed Big5, GB, and ASCII text for convenient +e-mail transmission, news posting, etc. +The document of HZ+ 0.78 specification can be found at +ftp://ftp.math.psu.edu/pub/simpson/chinese/hzp/hzp.doc" + :type 'boolean + :group 'mime) + +(defcustom rfc1843-newsgroups-regexp "chinese\\|hz" + "Regexp of newsgroups in which might be HZ encoded." + :type 'string + :group 'mime) + +(defun rfc1843-decode-region (from to) + "Decode HZ in the region between FROM and TO." + (interactive "r") + (let (str firstc) + (save-excursion + (goto-char from) + (if (or rfc1843-decode-loosely + (re-search-forward (if rfc1843-decode-hzp + rfc1843-hzp-word-regexp-strictly + rfc1843-word-regexp-strictly) to t)) + (save-restriction + (narrow-to-region from to) + (goto-char (point-min)) + (while (re-search-forward (if rfc1843-decode-hzp + rfc1843-hzp-word-regexp + rfc1843-word-regexp) (point-max) t) + (setq str (buffer-substring-no-properties + (match-beginning 1) + (match-end 1))) + (setq firstc (aref str 0)) + (insert (decode-coding-string + (rfc1843-decode + (prog1 + (substring str 1) + (delete-region (match-beginning 0) (match-end 0))) + firstc) + (if (eq firstc ?{) 'cn-gb-2312 'cn-big5)))) + (goto-char (point-min)) + (while (search-forward "~" (point-max) t) + (cond ((eq (char-after) ?\n) + (delete-char -1) + (delete-char 1)) + ((eq (char-after) ?~) + (delete-char 1))))))))) + +(defun rfc1843-decode-string (string) + "Decode HZ STRING and return the results." + (let ((m enable-multibyte-characters)) + (with-temp-buffer + (when m + (set-buffer-multibyte 'to)) + (insert string) + (inline + (rfc1843-decode-region (point-min) (point-max))) + (buffer-string)))) + +(defun rfc1843-decode (word &optional firstc) + "Decode HZ WORD and return it." + (let ((i -1) (s (substring word 0)) v) + (if (or (not firstc) (eq firstc ?{)) + (while (< (incf i) (length s)) + (if (eq (setq v (aref s i)) ? ) nil + (aset s i (+ 128 v)))) + (while (< (incf i) (length s)) + (if (eq (setq v (aref s i)) ? ) nil + (setq v (+ (* 94 v) (aref s (1+ i)) -3135)) + (aset s i (+ (/ v 157) (if (eq firstc ?<) 201 161))) + (setq v (% v 157)) + (aset s (incf i) (+ v (if (< v 63) 64 98)))))) + s)) + +(provide 'rfc1843) + +;;; rfc1843.el ends here diff --git a/lisp/international/utf7.el b/lisp/international/utf7.el new file mode 100644 index 00000000000..bd04eba2fae --- /dev/null +++ b/lisp/international/utf7.el @@ -0,0 +1,236 @@ +;;; utf7.el --- UTF-7 encoding/decoding for Emacs -*-coding: utf-8;-*- + +;; Copyright (C) 1999-2016 Free Software Foundation, Inc. + +;; Author: Jon K Hellan <hellan@acm.org> +;; Maintainer: bugs@gnus.org +;; Keywords: mail + +;; This file is part of GNU Emacs. + +;; 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 3 of the License, or +;; (at your option) any later version. + +;; GNU Emacs 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. If not, see <http://www.gnu.org/licenses/>. + +;;; 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. + +;; 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 utf-8 -t utf-7 +;; a+-+AKM +;; +;; -- fx + + +;;; Code: + +(require 'base64) +(eval-when-compile (require 'cl)) +(require 'mm-util) + +(defconst utf7-direct-encoding-chars " -%'-*,-[]-}" + "Character ranges which do not need escaping in UTF-7.") + +(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.") + +(defconst utf7-utf-16-coding-system + (cond ((mm-coding-system-p 'utf-16-be-no-signature) ; Mule-UCS + 'utf-16-be-no-signature) + ((and (mm-coding-system-p 'utf-16-be) ; Emacs + ;; Avoid versions with BOM. + (= 2 (length (encode-coding-string "a" 'utf-16-be)))) + 'utf-16-be) + ((mm-coding-system-p 'utf-16-be-nosig) ; ? + 'utf-16-be-nosig)) + "Coding system which encodes big endian UTF-16 without a BOM signature.") + +(defsubst utf7-imap-get-pad-length (len modulus) + "Return required length of padding for IMAP modified base64 fragment." + (mod (- len) modulus)) + +(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 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 not-direct-encoding-chars))) + (if (and (= fc esc-char) + (= run-length 1)) ; Lone esc-char? + (delete-char -1) ; Now there's one too many + (utf7-fragment-encode p (point) for-imap)) + (insert "-"))))))) + +(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 + (let* ((buf (current-buffer)) + (base (with-temp-buffer + (set-buffer-multibyte nil) + (insert-buffer-substring buf start end) + (funcall (utf7-get-u16char-converter 'to-utf-16)) + (base64-encode-region (point-min) (point-max)) + (buffer-string)))) + (narrow-to-region start end) + (delete-region (point-min) (point-max)) + (insert base)) + (goto-char (point-min)) + (let ((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 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) + (forward-char) + (let ((p (point)) + (run-length (skip-chars-forward base64-chars))) + (when (and (not (eobp)) (= (following-char) ?-)) + (delete-char 1)) + (unless (= run-length 0) ; Encoded lone esc-char? + (save-excursion + (utf7-fragment-decode p (point) for-imap) + (goto-char p) + (delete-char -1))))))))) + +(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) + (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 ?=)) + (base64-decode-region start (+ end pl))) + (funcall (utf7-get-u16char-converter 'from-utf-16)))) + +(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)) + (lambda () + (decode-coding-region (point-min) (point-max) + utf7-utf-16-coding-system))) + ;; Add test to check if we are really Latin-1. + (if (eq which-way 'to-utf-16) + 'utf7-latin1-u16-char-converter + 'utf7-u16-latin1-char-converter))) + +(defun utf7-latin1-u16-char-converter () + "Convert latin 1 (ISO-8859.1) characters to 16 bit Unicode. +Characters are converted to raw byte pairs in narrowed buffer." + (encode-coding-region (point-min) (point-max) 'iso-8859-1) + (goto-char (point-min)) + (while (not (eobp)) + (insert 0) + (forward-char))) + +(defun utf7-u16-latin1-char-converter () + "Convert 16 bit Unicode characters to latin 1 (ISO-8859.1). +Characters are in raw byte pairs in narrowed buffer." + (goto-char (point-min)) + (while (not (eobp)) + (if (= 0 (following-char)) + (delete-char 1) + (error "Unable to convert from Unicode")) + (forward-char)) + (decode-coding-region (point-min) (point-max) 'iso-8859-1) + (mm-enable-multibyte)) + +;;;###autoload +(defun utf7-encode (string &optional for-imap) + "Encode UTF-7 STRING. Use IMAP modification if FOR-IMAP is non-nil." + (if (and (coding-system-p 'utf-7) (coding-system-p 'utf-7-imap)) + ;; Emacs 23 with proper support for IMAP + (encode-coding-string string (if for-imap 'utf-7-imap 'utf-7)) + (mm-with-multibyte-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." + (if (and (coding-system-p 'utf-7) (coding-system-p 'utf-7-imap)) + ;; Emacs 23 with proper support for IMAP + (decode-coding-string string (if for-imap 'utf-7-imap 'utf-7)) + (mm-with-unibyte-buffer + (insert string) + (utf7-decode-internal for-imap) + (mm-enable-multibyte) + (buffer-string)))) + +(provide 'utf7) + +;;; utf7.el ends here |