* html2text.el (html2text-get-attr): Rewrite to handle spaces in quoted

attribute values.  (Bug#17834)

diff --git a/lisp/gnus/ChangeLog b/lisp/gnus/ChangeLog
index c9a23e47e6c7188a70fddd500667c643481bda63..4ad3a6de63e3ec02cd1c47fea78a1a695e744283 100644 (file)
--- a/lisp/gnus/ChangeLog
+++ b/lisp/gnus/ChangeLog
@@ -1,3 +1,8 @@
+2014-06-22  Andreas Schwab  <schwab@linux-m68k.org>
+
+       * html2text.el (html2text-get-attr): Rewrite to handle spaces in quoted
+       attribute values.  (Bug#17834)
+
 2014-05-28  Andreas Schwab  <schwab@linux-m68k.org>
 
        * html2text.el (html2text-get-attr): Fix typo when splitting value from

diff --git a/lisp/gnus/html2text.el b/lisp/gnus/html2text.el
index 78cecd923561d0bdad6acc89249c37e75c1a7c8a..22ee1c3921e509d25999915a3a463ec3acc26b0e 100644 (file)
--- a/lisp/gnus/html2text.el
+++ b/lisp/gnus/html2text.el
@@ -179,72 +179,20 @@ formatting, and then moved afterward.")
 
 (defun html2text-get-attr (p1 p2)
   (goto-char p1)
-  (re-search-forward " +[^ ]" p2 t)
-  (let* ((attr-string (buffer-substring-no-properties (1- (point)) (1- p2)))
-        (tmp-list (split-string attr-string))
-        (attr-list)
-        (counter 0)
-        (prev (car tmp-list))
-        (this (nth 1 tmp-list))
-        (next (nth 2 tmp-list))
-        (index 1))
-
-    (cond
-     ;; size=3
-     ((string-match "[^ ]=[^ ]" prev)
-      (let ((attr  (nth 0 (split-string prev "=")))
-           (value (substring prev (1+ (string-match "=" prev)))))
-       (setq attr-list (cons (list attr value) attr-list))))
-     ;; size= 3
-     ((string-match "[^ ]=\\'" prev)
-      (setq attr-list (cons (list (substring prev 0 -1) this) attr-list))))
-
-    (while (< index (length tmp-list))
-      (cond
-       ;; size=3
-       ((string-match "[^ ]=[^ ]" this)
-       (let ((attr  (nth 0 (split-string this "=")))
-             (value (substring this (1+ (string-match "=" this)))))
-         (setq attr-list (cons (list attr value) attr-list))))
-       ;; size =3
-       ((string-match "\\`=[^ ]" this)
-       (setq attr-list (cons (list prev (substring this 1)) attr-list)))
-       ;; size= 3
-       ((string-match "[^ ]=\\'" this)
-       (setq attr-list (cons (list (substring this 0 -1) next) attr-list)))
-       ;; size = 3
-       ((string= "=" this)
-       (setq attr-list (cons (list prev next) attr-list))))
-      (setq index (1+ index))
-      (setq prev this)
-      (setq this next)
-      (setq next (nth (1+ index) tmp-list)))
-    ;;
-    ;; Tags with no accompanying "=" i.e. value=nil
-    ;;
-    (setq prev (car tmp-list))
-    (setq this (nth 1 tmp-list))
-    (setq next (nth 2 tmp-list))
-    (setq index 1)
-
-    (when (and (not (string-match "=" prev))
-              (not (string= (substring this 0 1) "=")))
-      (setq attr-list (cons (list prev nil) attr-list)))
-    (while (< index (1- (length tmp-list)))
-      (when (and (not (string-match "=" this))
-                (not (or (string= (substring next 0 1) "=")
-                         (string= (substring prev -1) "="))))
-       (setq attr-list (cons (list this nil) attr-list)))
-      (setq index (1+ index))
-      (setq prev this)
-      (setq this next)
-      (setq next (nth (1+ index) tmp-list)))
-
-    (when (and this
-              (not (string-match "=" this))
-              (not (string= (substring prev -1) "=")))
-      (setq attr-list (cons (list this nil) attr-list)))
-    ;; return - value
+  (re-search-forward "\\s-+" p2 t)
+  (let (attr-list)
+    (while (re-search-forward "[-a-z0-9._]+" p2 t)
+      (setq attr-list
+           (cons
+            (list (match-string 0)
+                  (when (looking-at "\\s-*=")
+                    (goto-char (match-end 0))
+                    (skip-chars-forward "[:space:]")
+                    (when (or (looking-at "\"[^\"]*\"\\|'[^']*'")
+                              (looking-at "[-a-z0-9._:]+"))
+                      (goto-char (match-end 0))
+                      (match-string 0))))
+            attr-list)))
     attr-list))
 
 ;;