diff options
Diffstat (limited to 'lisp/international')
| -rw-r--r-- | lisp/international/characters.el | 16 | ||||
| -rw-r--r-- | lisp/international/kinsoku.el | 6 | ||||
| -rw-r--r-- | lisp/international/mule-cmds.el | 45 | ||||
| -rw-r--r-- | lisp/international/mule-diag.el | 9 | ||||
| -rw-r--r-- | lisp/international/mule.el | 2 | ||||
| -rw-r--r-- | lisp/international/quail.el | 10 | ||||
| -rw-r--r-- | lisp/international/rfc1843.el | 131 | ||||
| -rw-r--r-- | lisp/international/ucs-normalize.el | 45 | ||||
| -rw-r--r-- | lisp/international/utf7.el | 236 |
9 files changed, 446 insertions, 54 deletions
diff --git a/lisp/international/characters.el b/lisp/international/characters.el index ab058a5df52..5085e637e39 100644 --- a/lisp/international/characters.el +++ b/lisp/international/characters.el @@ -194,6 +194,7 @@ with L, LRE, or LRO Unicode bidi character type.") (dolist (l '(katakana-jisx0201 japanese-jisx0208 japanese-jisx0212 japanese-jisx0213-1 japanese-jisx0213-2 + japanese-jisx0213.2004-1 cp932-2-byte)) (map-charset-chars #'modify-category-entry l ?j)) @@ -622,16 +623,19 @@ with L, LRE, or LRO Unicode bidi character type.") (set-case-syntax-pair ?Ʊ ?ʊ tbl) (set-case-syntax-pair ?Ʋ ?ʋ tbl) (set-case-syntax-pair ?Ʒ ?ʒ tbl) + ;; We use set-downcase-syntax below, since we want upcase of dž + ;; return DŽ, not Dž, and the same for the rest. (set-case-syntax-pair ?DŽ ?dž tbl) - (set-case-syntax-pair ?Dž ?dž tbl) + (set-downcase-syntax ?Dž ?dž tbl) (set-case-syntax-pair ?LJ ?lj tbl) - (set-case-syntax-pair ?Lj ?lj tbl) + (set-downcase-syntax ?Lj ?lj tbl) (set-case-syntax-pair ?NJ ?nj tbl) - (set-case-syntax-pair ?Nj ?nj tbl) + (set-downcase-syntax ?Nj ?nj tbl) ;; 01F0; F; 006A 030C; # LATIN SMALL LETTER J WITH CARON + (set-case-syntax-pair ?DZ ?dz tbl) - (set-case-syntax-pair ?Dz ?dz tbl) + (set-downcase-syntax ?Dz ?dz tbl) (set-case-syntax-pair ?Ƕ ?ƕ tbl) (set-case-syntax-pair ?Ƿ ?ƿ tbl) (set-case-syntax-pair ?Ⱥ ?ⱥ tbl) @@ -1382,10 +1386,10 @@ Setup char-width-table appropriate for non-CJK language environment." (aset char-acronym-table i (car c0-acronyms)) (setq c0-acronyms (cdr c0-acronyms)))) -(let ((c1-acronyms '("XXX" "XXX" "BPH" "NBH" "IND" "NEL" "SSA" "ESA" +(let ((c1-acronyms '("PAD" "HOP" "BPH" "NBH" "IND" "NEL" "SSA" "ESA" "HTS" "HTJ" "VTS" "PLD" "PLU" "R1" "SS2" "SS1" "DCS" "PU1" "PU2" "STS" "CCH" "MW" "SPA" "EPA" - "SOS" "XXX" "SC1" "CSI" "ST" "OSC" "PM" "APC"))) + "SOS" "SGCI" "SC1" "CSI" "ST" "OSC" "PM" "APC"))) (dotimes (i 32) (aset char-acronym-table (+ #x0080 i) (car c1-acronyms)) (setq c1-acronyms (cdr c1-acronyms)))) diff --git a/lisp/international/kinsoku.el b/lisp/international/kinsoku.el index e9609f493b7..f5824d486bf 100644 --- a/lisp/international/kinsoku.el +++ b/lisp/international/kinsoku.el @@ -104,10 +104,10 @@ The value 0 means there's no limitation.") ;; JISX0201 Katakana "(I"(B" ;; Japanese JISX0208 - "$B!F!H!J!L!N!P!R!T!V!X!Z!k!l!m!n!w!x(B\ -$A!.!0#"#(!2!4!6!8!:!<!>!c!d!e#@!f!l(B" + "$B!F!H!J!L!N!P!R!T!V!X!Z!k!l!m!n!w!x(B" ;; Chinese GB2312 - "$A(E(F(G(H(I(J(K(L(M(N(O(P(Q(R(S(T(U(V(W(X(Y(h(B\ + "$A!.!0#"#(!2!4!6!8!:!<!>!c!d!e#@!f!l(B\ +$A(E(F(G(H(I(J(K(L(M(N(O(P(Q(R(S(T(U(V(W(X(Y(h(B\ \$(0!>!@!B!D!F!H!J!L!N!P!R!T!V!X!Z!\!^!`!b(B" ;; Chinese BIG5 "$(0!d!f!h!j!k!q!p"i"j"k"n"x$u$v$w$x$y$z${(B\ diff --git a/lisp/international/mule-cmds.el b/lisp/international/mule-cmds.el index 1ec7456c9e1..7672edc0443 100644 --- a/lisp/international/mule-cmds.el +++ b/lisp/international/mule-cmds.el @@ -2235,7 +2235,7 @@ See `set-language-info-alist' for use in programs." ("br" . "Latin-1") ; Breton ("bs" . "Latin-2") ; Bosnian ("byn" . "UTF-8") ; Bilin; Blin - ("ca" . "Latin-1") ; Catalan + ("ca" "Catalan" iso-8859-1) ; Catalan ; co Corsican ("cs" "Czech" iso-8859-2) ("cy" "Welsh" iso-8859-14) @@ -2980,6 +2980,27 @@ on encoding." (let ((char (assoc name ucs-names))) (when char (format " (%c)" (cdr char))))) +(defun char-from-name (string &optional ignore-case) + "Return a character as a number from its Unicode name STRING. +If optional IGNORE-CASE is non-nil, ignore case in STRING. +Return nil if STRING does not name a character." + (or (cdr (assoc-string string (ucs-names) ignore-case)) + (let ((minus (string-match-p "-[0-9A-F]+\\'" string))) + (when minus + ;; Parse names like "VARIATION SELECTOR-17" and "CJK + ;; COMPATIBILITY IDEOGRAPH-F900" that are not in ucs-names. + (ignore-errors + (let* ((case-fold-search ignore-case) + (vs (string-match-p "\\`VARIATION SELECTOR-" string)) + (minus-num (string-to-number (substring string minus) + (if vs 10 16))) + (vs-offset (if vs (if (< minus-num -16) #xE00EF #xFDFF) 0)) + (code (- vs-offset minus-num)) + (name (get-char-code-property code 'name))) + (when (eq t (compare-strings string nil nil name nil nil + ignore-case)) + code))))))) + (defun read-char-by-name (prompt) "Read a character by its Unicode name or hex number string. Display PROMPT and read a string that represents a character by its @@ -2993,9 +3014,11 @@ preceded by an asterisk `*' and use completion, it will show all the characters whose names include that substring, not necessarily at the beginning of the name. -This function also accepts a hexadecimal number of Unicode code -point or a number in hash notation, e.g. #o21430 for octal, -#x2318 for hex, or #10r8984 for decimal." +Accept a name like \"CIRCULATION FUNCTION\", a hexadecimal +number like \"2A10\", or a number in hash notation (e.g., +\"#x2a10\" for hex, \"10r10768\" for decimal, or \"#o25020\" for +octal). Treat otherwise-ambiguous strings like \"BED\" (U+1F6CF) +as names, not numbers." (let* ((enable-recursive-minibuffers t) (completion-ignore-case t) (input @@ -3008,13 +3031,13 @@ point or a number in hash notation, e.g. #o21430 for octal, (category . unicode-name)) (complete-with-action action (ucs-names) string pred))))) (char - (cond - ((string-match-p "\\`[0-9a-fA-F]+\\'" input) - (string-to-number input 16)) - ((string-match-p "\\`#" input) - (read input)) - (t - (cdr (assoc-string input (ucs-names) t)))))) + (cond + ((char-from-name input t)) + ((string-match-p "\\`[0-9a-fA-F]+\\'" input) + (ignore-errors (string-to-number input 16))) + ((string-match-p "\\`#\\([bBoOxX]\\|[0-9]+[rR]\\)[0-9a-zA-Z]+\\'" + input) + (ignore-errors (read input)))))) (unless (characterp char) (error "Invalid character")) char)) diff --git a/lisp/international/mule-diag.el b/lisp/international/mule-diag.el index fbb0e0cb96f..f543083b8c5 100644 --- a/lisp/international/mule-diag.el +++ b/lisp/international/mule-diag.el @@ -204,13 +204,6 @@ Character sets for defining other charsets, or for backward compatibility "Obsolete.") (make-obsolete-variable 'non-iso-charset-alist "no longer relevant." "23.1") -(defun decode-codepage-char (codepage code) - "Decode a character that has code CODE in CODEPAGE. -Return a decoded character string. Each CODEPAGE corresponds to a -coding system cpCODEPAGE." - (declare (obsolete decode-char "23.1")) - (decode-char (intern (format "cp%d" codepage)) code)) - ;; A variable to hold charset input history. (defvar charset-history nil) @@ -1121,7 +1114,7 @@ system which uses fontsets)." (insert "\n\n") (if window-system - (let ((font (cdr (assq 'font (frame-parameters))))) + (let ((font (frame-parameter nil 'font))) (insert "The font and fontset of the selected frame are:\n" " font: " font "\n" " fontset: " (face-attribute 'default :fontset) "\n")) diff --git a/lisp/international/mule.el b/lisp/international/mule.el index 08d37b45a3d..0761e688684 100644 --- a/lisp/international/mule.el +++ b/lisp/international/mule.el @@ -1873,7 +1873,7 @@ files.") (defun auto-coding-alist-lookup (filename) "Return the coding system specified by `auto-coding-alist' for FILENAME." (let ((alist auto-coding-alist) - (case-fold-search (memq system-type '(windows-nt ms-dos cygwin))) + (case-fold-search (file-name-case-insensitive-p filename)) coding-system) (while (and alist (not coding-system)) (if (string-match (car (car alist)) filename) diff --git a/lisp/international/quail.el b/lisp/international/quail.el index f5e390278ca..320d783d410 100644 --- a/lisp/international/quail.el +++ b/lisp/international/quail.el @@ -1333,7 +1333,15 @@ If STR has `advice' text property, append the following special event: (defun quail-input-method (key) (if (or buffer-read-only - overriding-terminal-local-map + (and overriding-terminal-local-map + ;; If the overriding map is `universal-argument-map', that + ;; must mean the user has pressed 'C-u KEY'. If KEY has a + ;; binding in `universal-argument-map' just return + ;; (list KEY), otherwise act as if there was no + ;; overriding map. + (or (not (eq (cadr overriding-terminal-local-map) + universal-argument-map)) + (lookup-key overriding-terminal-local-map (vector key)))) overriding-local-map) (list key) (quail-setup-overlays (quail-conversion-keymap)) 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/ucs-normalize.el b/lisp/international/ucs-normalize.el index 29cd042eee9..b2bc622858d 100644 --- a/lisp/international/ucs-normalize.el +++ b/lisp/international/ucs-normalize.el @@ -263,7 +263,7 @@ Note that Hangul are excluded.") (defvar ucs-normalize-combining-chars-regexp nil "Regular expression to match sequence of combining characters.") (setq ucs-normalize-combining-chars-regexp - (eval-when-compile (concat (regexp-opt (mapcar 'char-to-string combining-chars)) "+"))) + (eval-when-compile (concat (regexp-opt-charset combining-chars) "+"))) (declare-function decomposition-translation-alist "ucs-normalize" (decomposition-function)) @@ -396,20 +396,22 @@ If COMPOSITION-PREDICATE is not given, then do nothing." It includes Singletons, CompositionExclusions, and Non-Starter decomposition." (let (entries decomposition composition) - (mapc - (lambda (start-end) - (cl-do ((i (car start-end) (+ i 1))) ((> i (cdr start-end))) - (setq decomposition - (string-to-list - (with-temp-buffer - (insert i) - (translate-region 1 2 decomposition-translation) - (buffer-string)))) - (setq composition - (ucs-normalize-block-compose-chars decomposition composition-predicate)) - (when (not (equal composition (list i))) - (setq entries (cons i entries))))) - check-range) + (with-temp-buffer + (mapc + (lambda (start-end) + (cl-do ((i (car start-end) (+ i 1))) ((> i (cdr start-end))) + (setq decomposition + (string-to-list + (progn + (erase-buffer) + (insert i) + (translate-region 1 2 decomposition-translation) + (buffer-string)))) + (setq composition + (ucs-normalize-block-compose-chars decomposition composition-predicate)) + (when (not (equal composition (list i))) + (setq entries (cons i entries))))) + check-range)) ;;(remove-duplicates (append entries ucs-normalize-composition-exclusions @@ -431,7 +433,7 @@ decomposition." (setq hfs-nfc-quick-check-list (quick-check-list 'ucs-normalize-hfs-nfd-table t )) (defun quick-check-list-to-regexp (quick-check-list) - (regexp-opt (mapcar 'char-to-string (append quick-check-list combining-chars)))) + (regexp-opt-charset (append quick-check-list combining-chars))) (defun quick-check-decomposition-list-to-regexp (quick-check-list) (concat (quick-check-list-to-regexp quick-check-list) "\\|[가-힣]")) @@ -613,14 +615,9 @@ COMPOSITION-PREDICATE will be used to compose region." (- (point-max) (point-min))))) ;; Pre-write conversion for `utf-8-hfs'. -(defun ucs-normalize-hfs-nfd-pre-write-conversion (from to) - (let ((old-buf (current-buffer))) - (set-buffer (generate-new-buffer " *temp*")) - (if (stringp from) - (insert from) - (insert-buffer-substring old-buf from to)) - (ucs-normalize-HFS-NFD-region (point-min) (point-max)) - nil)) +;; _from and _to are legacy arguments (see `define-coding-system'). +(defun ucs-normalize-hfs-nfd-pre-write-conversion (_from _to) + (ucs-normalize-HFS-NFD-region (point-min) (point-max))) ;;; coding-system definition (define-coding-system 'utf-8-hfs 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 |