all messages for Emacs-related lists mirrored at yhetil.org
 help / color / mirror / code / Atom feed
From: David Maus <dmaus@ictsoc.de>
To: emacs-orgmode@gnu.org, bastien.guerry@wikimedia.fr
Cc: David Maus <dmaus@ictsoc.de>
Subject: [PATCH 13/16] Refactor unescaping functions
Date: Sun, 13 Feb 2011 13:01:15 +0100	[thread overview]
Message-ID: <1297598478-9925-14-git-send-email-dmaus@ictsoc.de> (raw)
In-Reply-To: <87d3mwvqwq.fsf@gnu.org>

* org.el (org-link-unescape): Simpler algorithm for replacing percent
escapes.
(org-link-unescape-compound): Use cond statements instead of nested
if, convert hex string with string-to-number, save match data.
(org-link-unescape-single-byte-sequence): Use mapconcat and
string-to-number for unescaping single byte sequence.
---
 lisp/org.el |  102 ++++++++++++++++++++++------------------------------------
 1 files changed, 39 insertions(+), 63 deletions(-)

diff --git a/lisp/org.el b/lisp/org.el
index fcd421f..f35f898 100644
--- a/lisp/org.el
+++ b/lisp/org.el
@@ -8584,77 +8584,53 @@ If optional argument MERGE is set, merge TABLE into
 (defun org-link-unescape (str)
   "Unhex hexified unicode strings as returned from the JavaScript function
 encodeURIComponent. E.g. `%C3%B6' is the german Umlaut `ö'."
-  (setq str (or str ""))
-  (let ((tmp "")
-	(case-fold-search t))
-    (while (string-match "\\(%[0-9a-f][0-9a-f]\\)+" str)
-      (let* ((start (match-beginning 0))
-	     (end (match-end 0))
-	     (hex (match-string 0 str))
-	     (replacement (org-link-unescape-compound (upcase hex))))
-	(setq tmp (concat tmp (substring str 0 start) replacement))
-	(setq str (substring str end))))
-    (setq tmp (concat tmp str))
-    tmp))
+  (unless (and (null str) (string= "" str))
+    (let ((pos 0) (case-fold-search t) unhexed)
+      (while (setq pos (string-match "\\(%[0-9a-f][0-9a-f]\\)+" str pos))
+	(setq unhexed (org-link-unescape-compound (match-string 0 str)))
+	(setq str (replace-match unhexed t t str))
+	(setq pos (+ pos (length unhexed))))))
+  str)
 
 (defun org-link-unescape-compound (hex)
   "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)
-	 (sum 0))
-    (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)))
-	     (val (+ (lsh c1 4) c2))
-	     (shift
-	      (if (= 0 eat) ;; new byte
-		  (if (>= val 252) 6
-		    (if (>= val 248) 5
-		      (if (>= val 240) 4
-			(if (>= val 224) 3
-			  (if (>= val 192) 2 0)))))
-		6))
-	     (xor
-	      (if (= 0 eat) ;; new byte
-		  (if (>= val 252) 252
-		    (if (>= val 248) 248
-		      (if (>= val 240) 240
-			(if (>= val 224) 224
-			  (if (>= val 192) 192 0)))))
-		128)))
-	(if (>= val 192) (setq eat shift))
-	(setq val (logxor val xor))
-	(setq sum (+ (lsh sum shift) val))
-	(if (> eat 0) (setq eat (- eat 1)))
-	(cond
-	 ((= 0 eat)                         ;multi byte
-	  (setq ret (concat ret (org-char-to-string sum)))
-	  (setq sum 0))
-	 ((not bytes)                       ; single byte(s)
-	  (setq ret (org-link-unescape-single-byte-sequence hex))))
-	)) ;; end (while bytes
-    ret ))
+  (save-match-data
+    (let* ((bytes (cdr (split-string hex "%")))
+	   (ret "")
+	   (eat 0)
+	   (sum 0))
+      (while bytes
+	(let* ((val (string-to-number (pop bytes) 16))
+	       (shift-xor
+		(if (= 0 eat)
+		    (cond
+		     ((>= val 252) (cons 6 252))
+		     ((>= val 248) (cons 5 248))
+		     ((>= val 240) (cons 4 240))
+		     ((>= val 224) (cons 3 224))
+		     ((>= val 192) (cons 2 192))
+		     (t (cons 0 0)))
+		  (cons 6 128))))
+	  (if (>= val 192) (setq eat (car shift-xor)))
+	  (setq val (logxor val (cdr shift-xor)))
+	  (setq sum (+ (lsh sum (car shift-xor)) val))
+	  (if (> eat 0) (setq eat (- eat 1)))
+	  (cond
+	   ((= 0 eat)			;multi byte
+	    (setq ret (concat ret (org-char-to-string sum)))
+	    (setq sum 0))
+	   ((not bytes)			; single byte(s)
+	    (setq ret (org-link-unescape-single-byte-sequence hex))))
+	  )) ;; end (while bytes
+      ret )))
 
 (defun org-link-unescape-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))
+  (mapconcat (lambda (byte)
+	       (char-to-string (string-to-number byte 16)))
+	     (cdr (split-string hex "%")) ""))
 
 (defun org-xor (a b)
   "Exclusive or."
-- 
1.7.2.3

  parent reply	other threads:[~2011-02-13 12:02 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-01-02 19:37 Improve percent escaping links in Org mode (pull request / OK to push) David Maus
2011-02-12 22:17 ` Bastien
2011-02-13 12:01   ` David Maus
2011-02-13 13:41     ` Bastien
2011-02-14  6:38       ` David Maus
2011-02-14 10:09         ` Bastien
2011-02-13 12:01   ` [PATCH 01/16] Decode single byte sequence if decoding unicode failed David Maus
2011-02-13 12:01   ` [PATCH 02/16] New unicode aware percent encoding algorithm David Maus
2011-02-13 12:01   ` [PATCH 03/16] New format of percent escape table David Maus
2011-02-13 12:01   ` [PATCH 04/16] Fixup doc string David Maus
2011-02-13 12:01   ` [PATCH 05/16] New optional argument: Merge user table with default table David Maus
2011-02-13 12:01   ` [PATCH 06/16] Inline function to properly decode utf8 characters in Emacs 22 David Maus
2011-02-13 12:01   ` [PATCH 07/16] Unescape functions moved and renamed from org-protocol.el David Maus
2011-02-13 12:01   ` [PATCH 08/16] Declare obsolete & alias to respective org-link-unescape-* functions David Maus
2011-02-13 12:01   ` [PATCH 09/16] Remove obsolete argument in call to org-link-unescape David Maus
2011-02-13 12:01   ` [PATCH 10/16] Use new percent escape character table format David Maus
2011-02-13 12:01   ` [PATCH 11/16] Add percent sign to list of escape chars David Maus
2011-02-13 12:01   ` [PATCH 12/16] Rename lambda argument David Maus
2011-02-13 12:01   ` David Maus [this message]
2011-02-13 12:01   ` [PATCH 14/16] Always percent escape the percent sign David Maus
2011-02-13 12:01   ` [PATCH 15/16] Use `org-link-unescape' instead of obsolete unhex string function David Maus
2011-02-13 12:01   ` [PATCH 16/16] Throw error if encoding character in utf8 fails David Maus

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1297598478-9925-14-git-send-email-dmaus@ictsoc.de \
    --to=dmaus@ictsoc.de \
    --cc=bastien.guerry@wikimedia.fr \
    --cc=emacs-orgmode@gnu.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
Code repositories for project(s) associated with this external index

	https://git.savannah.gnu.org/cgit/emacs.git
	https://git.savannah.gnu.org/cgit/emacs/org-mode.git

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.