emacs-diffs
[Top][All Lists]
Advanced

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[Emacs-diffs] Changes to emacs/lisp/gnus/html2text.el [emacs-unicode-2]


From: Miles Bader
Subject: [Emacs-diffs] Changes to emacs/lisp/gnus/html2text.el [emacs-unicode-2]
Date: Thu, 04 Nov 2004 04:02:32 -0500

Index: emacs/lisp/gnus/html2text.el
diff -c emacs/lisp/gnus/html2text.el:1.2.2.3 
emacs/lisp/gnus/html2text.el:1.2.2.4
*** emacs/lisp/gnus/html2text.el:1.2.2.3        Wed Oct 27 05:42:01 2004
--- emacs/lisp/gnus/html2text.el        Thu Nov  4 08:55:30 2004
***************
*** 24,34 ****
  
  ;; These functions provide a simple way to wash/clean html infected
  ;; mails.  Definitely do not work in all cases, but some improvement
! ;; in readability is generally obtained. Formatting is only done in
  ;; the buffer, so the next time you enter the article it will be
  ;; "re-htmlized".
  ;;
! ;; The main function is "html2text"
  
  ;;; Code:
  
--- 24,34 ----
  
  ;; These functions provide a simple way to wash/clean html infected
  ;; mails.  Definitely do not work in all cases, but some improvement
! ;; in readability is generally obtained.  Formatting is only done in
  ;; the buffer, so the next time you enter the article it will be
  ;; "re-htmlized".
  ;;
! ;; The main function is `html2text'.
  
  ;;; Code:
  
***************
*** 47,55 ****
    "The map of entity to text.
  
  This is an alist were each element is a dotted pair consisting of an
! old string, and a replacement string. This replacement is done by the
! function \"html2text-substitute\" which basically performs a
! replace-string operation for every element in the list. This is
  completely verbatim - without any use of REGEXP.")
  
  (defvar html2text-remove-tag-list
--- 47,55 ----
    "The map of entity to text.
  
  This is an alist were each element is a dotted pair consisting of an
! old string, and a replacement string.  This replacement is done by the
! function `html2text-substitute' which basically performs a
! `replace-string' operation for every element in the list.  This is
  completely verbatim - without any use of REGEXP.")
  
  (defvar html2text-remove-tag-list
***************
*** 57,67 ****
    "A list of removable tags.
  
  This is a list of tags which should be removed, without any
! formatting.  Observe that if you the tags in the list are presented
! *without* any \"<\" or \">\". All occurences of a tag appearing in
! this list are removed, irrespective of whether it is a closing or
! opening tag, or if the tag has additional attributes. The actual
! deletion is done by the function \"html2text-remove-tags\".
  
  For instance the text:
  
--- 57,67 ----
    "A list of removable tags.
  
  This is a list of tags which should be removed, without any
! formatting.  Note that tags in the list are presented *without*
! any \"<\" or \">\".  All occurences of a tag appearing in this
! list are removed, irrespective of whether it is a closing or
! opening tag, or if the tag has additional attributes.  The
! deletion is done by the function `html2text-remove-tags'.
  
  For instance the text:
  
***************
*** 75,82 ****
--- 75,84 ----
  
  (defvar html2text-format-tag-list
    '(("b"        . html2text-clean-bold)
+     ("strong"     . html2text-clean-bold)
      ("u"        . html2text-clean-underline)
      ("i"        . html2text-clean-italic)
+     ("em"         . html2text-clean-italic)
      ("blockquote" . html2text-clean-blockquote)
      ("a"          . html2text-clean-anchor)
      ("ul"         . html2text-clean-ul)
***************
*** 86,92 ****
    "An alist of tags and processing functions.
  
  This is an alist where each dotted pair consists of a tag, and then
! the name of a function to be called when this tag is found. The
  function is called with the arguments p1, p2, p3 and p4. These are
  demontrated below:
  
--- 88,94 ----
    "An alist of tags and processing functions.
  
  This is an alist where each dotted pair consists of a tag, and then
! the name of a function to be called when this tag is found.  The
  function is called with the arguments p1, p2, p3 and p4. These are
  demontrated below:
  
***************
*** 117,133 ****
  ;;
  
  
! (defun html2text-replace-string (from-string to-string p1 p2)
!   (goto-char p1)
    (let ((delta (- (string-width to-string) (string-width from-string)))
        (change 0))
!     (while (search-forward from-string p2 t)
        (replace-match to-string)
!       (setq change (+ change delta))
!       )
!     change
!     )
!   )
  
  ;;
  ;; </Utility functions>
--- 119,133 ----
  ;;
  
  
! (defun html2text-replace-string (from-string to-string min max)
!   "Replace FROM-STRING with TO-STRING in region from MIN to MAX."
!   (goto-char min)
    (let ((delta (- (string-width to-string) (string-width from-string)))
        (change 0))
!     (while (search-forward from-string max t)
        (replace-match to-string)
!       (setq change (+ change delta)))
!     change))
  
  ;;
  ;; </Utility functions>
***************
*** 140,150 ****
  ;; <Functions related to attributes> i.e. <font size=+3>
  ;;
  
! (defun html2text-attr-value (attr-list attr)
!   (nth 1 (assoc attr attr-list))
!   )
  
! (defun html2text-get-attr (p1 p2 tag)
    (goto-char p1)
    (re-search-forward " +[^ ]" p2 t)
    (let* ((attr-string (buffer-substring-no-properties (1- (point)) (1- p2)))
--- 140,150 ----
  ;; <Functions related to attributes> i.e. <font size=+3>
  ;;
  
! (defun html2text-attr-value (list attribute)
!   "Get value of ATTRIBUTE from LIST."
!   (nth 1 (assoc attribute list)))
  
! (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)))
***************
*** 161,174 ****
       ((string-match "[^ ]=[^ ]" prev)
        (let ((attr  (nth 0 (split-string prev "=")))
            (value (nth 1 (split-string 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
--- 161,170 ----
       ((string-match "[^ ]=[^ ]" prev)
        (let ((attr  (nth 0 (split-string prev "=")))
            (value (nth 1 (split-string 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
***************
*** 176,204 ****
         ((string-match "[^ ]=[^ ]" this)
        (let ((attr  (nth 0 (split-string this "=")))
              (value (nth 1 (split-string 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
      ;;
--- 172,191 ----
         ((string-match "[^ ]=[^ ]" this)
        (let ((attr  (nth 0 (split-string this "=")))
              (value (nth 1 (split-string 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
      ;;
***************
*** 207,247 ****
      (setq next (nth 2 tmp-list))
      (setq index 1)
  
!     (if (not (string-match "=" prev))
!       (progn
!         (if (not (string= (substring this 0 1) "="))
!             (setq attr-list (cons (list prev nil) attr-list))
!           )
!         )
!       )
! 
      (while (< index (1- (length tmp-list)))
!       (if (not (string-match "=" this))
!         (if (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))
!       )
  
!     (if this
!       (progn
!         (if (not (string-match "=" this))
!             (progn
!               (if (not (string= (substring prev -1) "="))
!                   (setq attr-list (cons (list this nil) attr-list))
!                 )
!               )
!           )
!         )
!       )
!     attr-list ;; return - value
!     )
!   )
  
  ;;
  ;; </Functions related to attributes>
--- 194,218 ----
      (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
!     attr-list))
  
  ;;
  ;; </Functions related to attributes>
***************
*** 266,275 ****
        (cond
         ((string= list-type "ul") (insert " o "))
         ((string= list-type "ol") (insert (format " %s: " item-nr)))
!        (t (insert " x ")))
!       )
!     )
!   )
  
  (defun html2text-clean-dtdd (p1 p2)
    (goto-char p1)
--- 237,243 ----
        (cond
         ((string= list-type "ul") (insert " o "))
         ((string= list-type "ol") (insert (format " %s: " item-nr)))
!        (t (insert " x "))))))
  
  (defun html2text-clean-dtdd (p1 p2)
    (goto-char p1)
***************
*** 308,368 ****
    (html2text-delete-single-tag p1 p2)
    (goto-char p1)
    (newline 1)
!   (insert (make-string fill-column ?-))
!   )
  
  (defun html2text-clean-ul (p1 p2 p3 p4)
    (html2text-delete-tags p1 p2 p3 p4)
!   (html2text-clean-list-items p1 (- p3 (- p1 p2)) "ul")
!   )
  
  (defun html2text-clean-ol (p1 p2 p3 p4)
    (html2text-delete-tags p1 p2 p3 p4)
!   (html2text-clean-list-items p1 (- p3 (- p1 p2)) "ol")
!   )
  
  (defun html2text-clean-dl (p1 p2 p3 p4)
    (html2text-delete-tags p1 p2 p3 p4)
!   (html2text-clean-dtdd p1 (- p3 (- p1 p2)))
!   )
  
  (defun html2text-clean-center (p1 p2 p3 p4)
    (html2text-delete-tags p1 p2 p3 p4)
!   (center-region p1 (- p3 (- p2 p1)))
!   )
  
  (defun html2text-clean-bold (p1 p2 p3 p4)
    (put-text-property p2 p3 'face 'bold)
!   (html2text-delete-tags p1 p2 p3 p4)
!   )
  
  (defun html2text-clean-title (p1 p2 p3 p4)
    (put-text-property p2 p3 'face 'bold)
!   (html2text-delete-tags p1 p2 p3 p4)
!   )
  
  (defun html2text-clean-underline (p1 p2 p3 p4)
    (put-text-property p2 p3 'face 'underline)
!   (html2text-delete-tags p1 p2 p3 p4)
!   )
  
  (defun html2text-clean-italic (p1 p2 p3 p4)
    (put-text-property p2 p3 'face 'italic)
!   (html2text-delete-tags p1 p2 p3 p4)
!   )
  
  (defun html2text-clean-font (p1 p2 p3 p4)
!   (html2text-delete-tags p1 p2 p3 p4)
!   )
  
  (defun html2text-clean-blockquote (p1 p2 p3 p4)
!   (html2text-delete-tags p1 p2 p3 p4)
!   )
  
  (defun html2text-clean-anchor (p1 p2 p3 p4)
!   ;; If someone can explain how to make the URL clickable I will
!   ;; surely improve upon this.
!   (let* ((attr-list (html2text-get-attr p1 p2 "a"))
         (href (html2text-attr-value attr-list "href")))
      (delete-region p1 p4)
      (when href
--- 276,326 ----
    (html2text-delete-single-tag p1 p2)
    (goto-char p1)
    (newline 1)
!   (insert (make-string fill-column ?-)))
  
  (defun html2text-clean-ul (p1 p2 p3 p4)
    (html2text-delete-tags p1 p2 p3 p4)
!   (html2text-clean-list-items p1 (- p3 (- p1 p2)) "ul"))
  
  (defun html2text-clean-ol (p1 p2 p3 p4)
    (html2text-delete-tags p1 p2 p3 p4)
!   (html2text-clean-list-items p1 (- p3 (- p1 p2)) "ol"))
  
  (defun html2text-clean-dl (p1 p2 p3 p4)
    (html2text-delete-tags p1 p2 p3 p4)
!   (html2text-clean-dtdd p1 (- p3 (- p1 p2))))
  
  (defun html2text-clean-center (p1 p2 p3 p4)
    (html2text-delete-tags p1 p2 p3 p4)
!   (center-region p1 (- p3 (- p2 p1))))
  
  (defun html2text-clean-bold (p1 p2 p3 p4)
    (put-text-property p2 p3 'face 'bold)
!   (html2text-delete-tags p1 p2 p3 p4))
  
  (defun html2text-clean-title (p1 p2 p3 p4)
    (put-text-property p2 p3 'face 'bold)
!   (html2text-delete-tags p1 p2 p3 p4))
  
  (defun html2text-clean-underline (p1 p2 p3 p4)
    (put-text-property p2 p3 'face 'underline)
!   (html2text-delete-tags p1 p2 p3 p4))
  
  (defun html2text-clean-italic (p1 p2 p3 p4)
    (put-text-property p2 p3 'face 'italic)
!   (html2text-delete-tags p1 p2 p3 p4))
  
  (defun html2text-clean-font (p1 p2 p3 p4)
!   (html2text-delete-tags p1 p2 p3 p4))
  
  (defun html2text-clean-blockquote (p1 p2 p3 p4)
!   (html2text-delete-tags p1 p2 p3 p4))
  
  (defun html2text-clean-anchor (p1 p2 p3 p4)
!   ;; If someone can explain how to make the URL clickable I will surely
!   ;; improve upon this.
!   ;; Maybe `goto-addr.el' can be used here.
!   (let* ((attr-list (html2text-get-attr p1 p2))
         (href (html2text-attr-value attr-list "href")))
      (delete-region p1 p4)
      (when href
***************
*** 386,423 ****
    (let ((has-br-line)
        (refill-start)
        (refill-stop))
!     (if (re-search-forward "<br>$" p2 t)
!       (setq has-br-line t)
!       )
!     (if has-br-line
!       (progn
!         (goto-char p1)
!         (if (re-search-forward ".+[^<][^b][^r][^>]$" p2 t)
!             (progn
!               (beginning-of-line)
!               (setq refill-start (point))
!               (goto-char p2)
!               (re-search-backward ".+[^<][^b][^r][^>]$" refill-start t)
!               (next-line 1)
!               (end-of-line)
!               ;; refill-stop should ideally be adjusted to
!               ;; accomodate the "<br>" strings which are removed
!               ;; between refill-start and refill-stop.  Can simply
!               ;; be returned from my-replace-string
!               (setq refill-stop (+ (point)
!                                    (html2text-replace-string
!                                     "<br>" ""
!                                     refill-start (point))))
!               ;; (message "Point = %s  refill-stop = %s" (point) refill-stop)
!               ;; (sleep-for 4)
!               (fill-region refill-start refill-stop)
!               )
!           )
!         )
!       )
!     )
!   (html2text-replace-string "<br>" "" p1 p2)
!   )
  
  ;;
  ;; This one is interactive ...
--- 344,370 ----
    (let ((has-br-line)
        (refill-start)
        (refill-stop))
!     (when (re-search-forward "<br>$" p2 t)
!       (goto-char p1)
!       (when (re-search-forward ".+[^<][^b][^r][^>]$" p2 t)
!       (beginning-of-line)
!       (setq refill-start (point))
!       (goto-char p2)
!       (re-search-backward ".+[^<][^b][^r][^>]$" refill-start t)
!       (next-line 1)
!       (end-of-line)
!       ;; refill-stop should ideally be adjusted to
!       ;; accomodate the "<br>" strings which are removed
!       ;; between refill-start and refill-stop.  Can simply
!       ;; be returned from my-replace-string
!       (setq refill-stop (+ (point)
!                            (html2text-replace-string
!                             "<br>" ""
!                             refill-start (point))))
!       ;; (message "Point = %s  refill-stop = %s" (point) refill-stop)
!       ;; (sleep-for 4)
!       (fill-region refill-start refill-stop))))
!   (html2text-replace-string "<br>" "" p1 p2))
  
  ;;
  ;; This one is interactive ...
***************
*** 452,458 ****
  ;;
  
  (defun html2text-remove-tags (tag-list)
!   "Removes the tags listed in the list \"html2text-remove-tag-list\".
  See the documentation for that variable."
    (interactive)
    (dolist (tag tag-list)
--- 399,405 ----
  ;;
  
  (defun html2text-remove-tags (tag-list)
!   "Removes the tags listed in the list `html2text-remove-tag-list'.
  See the documentation for that variable."
    (interactive)
    (dolist (tag tag-list)
***************
*** 461,467 ****
        (delete-region (match-beginning 0) (match-end 0)))))
  
  (defun html2text-format-tags ()
!   "See the variable \"html2text-format-tag-list\" for documentation"
    (interactive)
    (dolist (tag-and-function html2text-format-tag-list)
      (let ((tag      (car tag-and-function))
--- 408,414 ----
        (delete-region (match-beginning 0) (match-end 0)))))
  
  (defun html2text-format-tags ()
!   "See the variable `html2text-format-tag-list' for documentation."
    (interactive)
    (dolist (tag-and-function html2text-format-tag-list)
      (let ((tag      (car tag-and-function))
***************
*** 471,478 ****
                                (point-max) t)
        (let ((p1)
              (p2 (point))
!             (p3) (p4)
!             (attr (match-string 1)))
          (search-backward "<" (point-min) t)
          (setq p1 (point))
          (re-search-forward (format "</%s>" tag) (point-max) t)
--- 418,424 ----
                                (point-max) t)
        (let ((p1)
              (p2 (point))
!             (p3) (p4))
          (search-backward "<" (point-min) t)
          (setq p1 (point))
          (re-search-forward (format "</%s>" tag) (point-max) t)
***************
*** 480,506 ****
          (search-backward "</" (point-min) t)
          (setq p3 (point))
          (funcall function p1 p2 p3 p4)
!         (goto-char p1)
!         )
!       )
!       )
!     )
!   )
  
  (defun html2text-substitute ()
!   "See the variable \"html2text-replace-list\" for documentation"
    (interactive)
    (dolist (e html2text-replace-list)
      (goto-char (point-min))
      (let ((old-string (car e))
          (new-string (cdr e)))
!       (html2text-replace-string old-string new-string (point-min) (point-max))
!       )
!     )
!   )
  
  (defun html2text-format-single-elements ()
-   ""
    (interactive)
    (dolist (tag-and-function html2text-format-single-element-list)
      (let ((tag      (car tag-and-function))
--- 426,443 ----
          (search-backward "</" (point-min) t)
          (setq p3 (point))
          (funcall function p1 p2 p3 p4)
!         (goto-char p1))))))
  
  (defun html2text-substitute ()
!   "See the variable `html2text-replace-list' for documentation."
    (interactive)
    (dolist (e html2text-replace-list)
      (goto-char (point-min))
      (let ((old-string (car e))
          (new-string (cdr e)))
!       (html2text-replace-string old-string new-string (point-min) 
(point-max)))))
  
  (defun html2text-format-single-elements ()
    (interactive)
    (dolist (tag-and-function html2text-format-single-element-list)
      (let ((tag      (car tag-and-function))
***************
*** 512,523 ****
              (p2 (point)))
          (search-backward "<" (point-min) t)
          (setq p1 (point))
!         (funcall function p1 p2)
!         )
!       )
!       )
!     )
!   )
  
  ;;
  ;; Main function
--- 449,455 ----
              (p2 (point)))
          (search-backward "<" (point-min) t)
          (setq p1 (point))
!         (funcall function p1 p2))))))
  
  ;;
  ;; Main function
***************
*** 540,545 ****
  ;;
  ;; </Interactive functions>
  ;;
! 
  ;;; arch-tag: e9e57b79-35d4-4de1-a647-e7e01fe56d1e
  ;;; html2text.el ends here
--- 472,477 ----
  ;;
  ;; </Interactive functions>
  ;;
! (provide 'html2text)
  ;;; arch-tag: e9e57b79-35d4-4de1-a647-e7e01fe56d1e
  ;;; html2text.el ends here




reply via email to

[Prev in Thread] Current Thread [Next in Thread]