[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Orgmode] [PATCH 07/16] Unescape functions moved and renamed from org-pr
From: |
David Maus |
Subject: |
[Orgmode] [PATCH 07/16] Unescape functions moved and renamed from org-protocol.el |
Date: |
Sun, 13 Feb 2011 13:01:09 +0100 |
* org.el (org-link-unescape, org-link-unescape-compound)
(org-link-unescape-single-byte-sequence): Functions moved and renamed
from org-protocol.el.
---
lisp/org.el | 90 ++++++++++++++++++++++++++++++++++++++++++++++++----------
1 files changed, 74 insertions(+), 16 deletions(-)
diff --git a/lisp/org.el b/lisp/org.el
index a29d429..602462d 100644
--- a/lisp/org.el
+++ b/lisp/org.el
@@ -8579,22 +8579,80 @@ If optional argument MERGE is set, merge TABLE into
(encode-coding-char char 'utf-8) "")
(char-to-string char))) text "")))
-(defun org-link-unescape (text &optional table)
- "Reverse the action of `org-link-escape'."
- (if (and org-url-encoding-use-url-hexify (not table))
- (url-unhex-string text)
- (setq table (or table org-link-escape-chars))
- (when text
- (let ((case-fold-search t)
- (re (mapconcat (lambda (x) (regexp-quote (downcase (cdr x))))
- table "\\|")))
- (while (string-match re text)
- (setq text
- (replace-match
- (char-to-string (car (rassoc (upcase (match-string 0 text))
- table)))
- t t text)))
- text))))
+(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))
+
+(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 ))
+
+(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))
(defun org-xor (a b)
"Exclusive or."
--
1.7.2.3
- Re: [Orgmode] Improve percent escaping links in Org mode (pull request / OK to push), (continued)
[Orgmode] [PATCH 01/16] Decode single byte sequence if decoding unicode failed., David Maus, 2011/02/13
[Orgmode] [PATCH 02/16] New unicode aware percent encoding algorithm, David Maus, 2011/02/13
[Orgmode] [PATCH 03/16] New format of percent escape table, David Maus, 2011/02/13
[Orgmode] [PATCH 04/16] Fixup doc string, David Maus, 2011/02/13
[Orgmode] [PATCH 05/16] New optional argument: Merge user table with default table, David Maus, 2011/02/13
[Orgmode] [PATCH 06/16] Inline function to properly decode utf8 characters in Emacs 22, David Maus, 2011/02/13
[Orgmode] [PATCH 08/16] Declare obsolete & alias to respective org-link-unescape-* functions, David Maus, 2011/02/13
[Orgmode] [PATCH 09/16] Remove obsolete argument in call to org-link-unescape, David Maus, 2011/02/13
[Orgmode] [PATCH 07/16] Unescape functions moved and renamed from org-protocol.el,
David Maus <=
[Orgmode] [PATCH 10/16] Use new percent escape character table format, David Maus, 2011/02/13
[Orgmode] [PATCH 11/16] Add percent sign to list of escape chars, David Maus, 2011/02/13
[Orgmode] [PATCH 12/16] Rename lambda argument, David Maus, 2011/02/13
[Orgmode] [PATCH 14/16] Always percent escape the percent sign, David Maus, 2011/02/13
[Orgmode] [PATCH 13/16] Refactor unescaping functions, David Maus, 2011/02/13
[Orgmode] [PATCH 15/16] Use `org-link-unescape' instead of obsolete unhex string function, David Maus, 2011/02/13
[Orgmode] [PATCH 16/16] Throw error if encoding character in utf8 fails, David Maus, 2011/02/13