From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Maus Subject: [PATCH] Decode single byte sequence if decoding unicode failed. Date: Mon, 27 Sep 2010 07:36:01 +0200 Message-ID: <1285565761-7558-2-git-send-email-dmaus@ictsoc.de> References: <8739swi0f0.fsf@gmx.de> Return-path: Received: from [140.186.70.92] (port=33784 helo=eggs.gnu.org) by lists.gnu.org with esmtp (Exim 4.43) id 1P06Nw-0004XZ-2t for emacs-orgmode@gnu.org; Mon, 27 Sep 2010 01:36:21 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.69) (envelope-from ) id 1P06Nu-0002Gp-5C for emacs-orgmode@gnu.org; Mon, 27 Sep 2010 01:36:19 -0400 Received: from mysql1.xlhost.de ([213.202.242.106]:43001) by eggs.gnu.org with esmtp (Exim 4.69) (envelope-from ) id 1P06Nt-0002Gf-TV for emacs-orgmode@gnu.org; Mon, 27 Sep 2010 01:36:18 -0400 In-Reply-To: <8739swi0f0.fsf@gmx.de> List-Id: "General discussions about Org-mode." List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: emacs-orgmode-bounces+geo-emacs-orgmode=m.gmane.org@gnu.org Errors-To: emacs-orgmode-bounces+geo-emacs-orgmode=m.gmane.org@gnu.org To: emacs-orgmode@gnu.org From: Sebastian Rose * org-protocol.el (org-protocol-unhex-single-byte-sequence): New function. Decode hex-encoded singly byte sequences. (org-protocol-unhex-compound): Use new function if decoding sequence as unicode character failed. --- lisp/org-protocol.el | 26 +++++++++++++++++++++++--- 1 files changed, 23 insertions(+), 3 deletions(-) diff --git a/lisp/org-protocol.el b/lisp/org-protocol.el index 21f28e7..3cd2167 100644 --- a/lisp/org-protocol.el +++ b/lisp/org-protocol.el @@ -305,7 +305,7 @@ part." (defun org-protocol-unhex-string(str) "Unhex hexified unicode strings as returned from the JavaScript function -encodeURIComponent. E.g. `%C3%B6' is the german Umlaut `ü'." +encodeURIComponent. E.g. `%C3%B6' is the german Umlaut `ö'." (setq str (or str "")) (let ((tmp "") (case-fold-search t)) @@ -321,7 +321,9 @@ encodeURIComponent. E.g. `%C3%B6' is the german Umlaut `ü'." (defun org-protocol-unhex-compound (hex) - "Unhexify unicode hex-chars. E.g. `%C3%B6' is the German Umlaut `ü'." + "Unhexify unicode hex-chars. E.g. `%C3%B6' is the German Umlaut `ö'. +Note: this function also decodes single byte encodings like +`%E1' (\"á\") if not followed by another `%[A-F0-9]{2}' group." (let* ((bytes (remove "" (split-string hex "%"))) (ret "") (eat 0) @@ -353,12 +355,30 @@ encodeURIComponent. E.g. `%C3%B6' is the german Umlaut `ü'." (setq val (logxor val xor)) (setq sum (+ (lsh sum shift) val)) (if (> eat 0) (setq eat (- eat 1))) - (when (= 0 eat) + (cond + ((= 0 eat) ;multi byte (setq ret (concat ret (org-protocol-char-to-string sum))) (setq sum 0)) + ((not bytes) ; single byte(s) + (setq ret (org-protocol-unhex-single-byte-sequence hex)))) )) ;; end (while bytes ret )) +(defun org-protocol-unhex-single-byte-sequence(hex) + "Unhexify hex-encoded single byte character sequences." + (let ((bytes (remove "" (split-string hex "%"))) + (ret "")) + (while bytes + (let* ((b (pop bytes)) + (a (elt b 0)) + (b (elt b 1)) + (c1 (if (> a ?9) (+ 10 (- a ?A)) (- a ?0))) + (c2 (if (> b ?9) (+ 10 (- b ?A)) (- b ?0)))) + (setq ret + (concat ret (char-to-string + (+ (lsh c1 4) c2)))))) + ret)) + (defun org-protocol-flatten-greedy (param-list &optional strip-path replacement) "Greedy handlers might receive a list like this from emacsclient: '( (\"/dir/org-protocol:/greedy:/~/path1\" (23 . 12)) (\"/dir/param\") -- 1.7.1