X-Git-Url: http://git.chise.org/gitweb/?p=elisp%2Fgnus.git-;a=blobdiff_plain;f=lisp%2Fhtml2text.el;fp=lisp%2Fhtml2text.el;h=4e39d66f11196ba732b66ebef56965c9ba65ebd6;hp=b5c74784a4b566ddf22cc060412010023c424a54;hb=9dd8d144dd2d47bd0ea84e76881ec0f46af778f1;hpb=249142f014344b6f7e1a85fdebc289fd45819a84 diff --git a/lisp/html2text.el b/lisp/html2text.el index b5c7478..4e39d66 100644 --- a/lisp/html2text.el +++ b/lisp/html2text.el @@ -24,11 +24,11 @@ ;; 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 +;; 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" +;; The main function is `html2text'. ;;; Code: @@ -47,9 +47,9 @@ "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 +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 @@ -57,11 +57,11 @@ completely verbatim - without any use of REGEXP.") "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\". +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: @@ -75,8 +75,10 @@ If this list contains the element \"font\".") (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) @@ -86,7 +88,7 @@ If this list contains the element \"font\".") "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 +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: @@ -116,16 +118,13 @@ formatting, and then moved afterward.") ;; ;; -(defun html2text-buffer-head () - (if (string= mode-name "Article") - (beginning-of-buffer) - (beginning-of-buffer))) -(defun html2text-replace-string (from-string to-string p1 p2) - (goto-char p1) +(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 p2 t) + (while (search-forward from-string max t) (replace-match to-string) (setq change (+ change delta))) change)) @@ -141,27 +140,80 @@ formatting, and then moved afterward.") ;; i.e. ;; -(defun html2text-attr-value (attr-list attr) - (nth 1 (assoc attr attr-list))) +(defun html2text-attr-value (list attribute) + "Get value of ATTRIBUTE from LIST." + (nth 1 (assoc attribute list))) (defun html2text-get-attr (p1 p2) - (save-restriction - (narrow-to-region p1 p2) - (let (result) - (goto-char (point-min)) - (while (not (eobp)) - (when (re-search-forward "[^= ]+" nil t) - (push - (list - (match-string 0) - (when (looking-at " *= *") - (goto-char (match-end 0)) - (buffer-substring - (point) - (goto-char (or (ignore-errors (scan-sexps (point) 1)) - (point-max)))))) - result))) - result))) + (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 (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 + ;; size=3 + ((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 + ;; + (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 + attr-list)) + ;; ;; ;; @@ -176,12 +228,12 @@ formatting, and then moved afterward.") (goto-char p1) (let ((item-nr 0) (items 0)) - (while (re-search-forward "
  • " p2 t) + (while (search-forward "
  • " p2 t) (setq items (1+ items))) (goto-char p1) (while (< item-nr items) (setq item-nr (1+ item-nr)) - (re-search-forward "
  • " (point-max) t) + (search-forward "
  • " (point-max) t) (cond ((string= list-type "ul") (insert " o ")) ((string= list-type "ol") (insert (format " %s: " item-nr))) @@ -191,7 +243,7 @@ formatting, and then moved afterward.") (goto-char p1) (let ((items 0) (item-nr 0)) - (while (re-search-forward "
    " p2 t) + (while (search-forward "
    " p2 t) (setq items (1+ items))) (goto-char p1) (while (< item-nr items) @@ -265,9 +317,11 @@ formatting, and then moved afterward.") (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 ((href (html2text-attr-value (html2text-get-attr p1 p2) "href"))) + ;; 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 (goto-char p1) @@ -287,31 +341,28 @@ formatting, and then moved afterward.") (defun html2text-fix-paragraph (p1 p2) (goto-char p1) - (let ((has-br-line) - (refill-start) + (let ((refill-start) (refill-stop)) (when (re-search-forward "
    $" p2 t) - (setq has-br-line t)) - (when has-br-line - (goto-char p1) - (when (re-search-forward ".+[^<][^b][^r][^>]$" p2 t) - (beginning-of-line) - (setq refill-start (point)) - (goto-char p2) - (re-search-backward ".+[^<][^b][^r][^>]$" refill-start t) - (next-line 1) - (end-of-line) - ;; refill-stop should ideally be adjusted to - ;; accomodate the "
    " strings which are removed - ;; between refill-start and refill-stop. Can simply - ;; be returned from my-replace-string - (setq refill-stop (+ (point) - (html2text-replace-string - "
    " "" - refill-start (point)))) - ;; (message "Point = %s refill-stop = %s" (point) refill-stop) - ;; (sleep-for 4) - (fill-region refill-start refill-stop)))) + (goto-char p1) + (when (re-search-forward ".+[^<][^b][^r][^>]$" 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 "
    " 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 + "
    " "" + refill-start (point)))) + ;; (message "Point = %s refill-stop = %s" (point) refill-stop) + ;; (sleep-for 4) + (fill-region refill-start refill-stop)))) (html2text-replace-string "
    " "" p1 p2)) ;; @@ -321,11 +372,11 @@ formatting, and then moved afterward.") "This _tries_ to fix up the paragraphs - this is done in quite a ad-hook fashion, quite close to pure guess-work. It does work in some cases though." (interactive) - (html2text-buffer-head) + (goto-char (point-min)) (replace-regexp "^
    $" "") ;; Removing lonely
    on a single line, if they are left intact we ;; dont have any paragraphs at all. - (html2text-buffer-head) + (goto-char (point-min)) (while (not (eobp)) (let ((p1 (point))) (forward-paragraph 1) @@ -347,55 +398,51 @@ fashion, quite close to pure guess-work. It does work in some cases though." ;; (defun html2text-remove-tags (tag-list) - "Removes the tags listed in the list \"html2text-remove-tag-list\". + "Removes the tags listed in the list `html2text-remove-tag-list'. See the documentation for that variable." (interactive) (dolist (tag tag-list) - (html2text-buffer-head) - (while (re-search-forward (format "]*>" tag) (point-max) t) + (goto-char (point-min)) + (while (re-search-forward (format "\\(]*>\\)" tag) (point-max) t) (delete-region (match-beginning 0) (match-end 0))))) (defun html2text-format-tags () - "See the variable \"html2text-format-tag-list\" for documentation" + "See the variable `html2text-format-tag-list' for documentation." (interactive) (dolist (tag-and-function html2text-format-tag-list) (let ((tag (car tag-and-function)) (function (cdr tag-and-function))) - (html2text-buffer-head) - (while (re-search-forward (format "<%s\\( [^>]*\\)?>" tag) + (goto-char (point-min)) + (while (re-search-forward (format "\\(<%s\\( [^>]*\\)?>\\)" tag) (point-max) t) (let ((p1) (p2 (point)) - (p3) (p4) - (attr (match-string 0))) + (p3) (p4)) (search-backward "<" (point-min) t) (setq p1 (point)) - (re-search-forward (format "" tag) (point-max) t) + (search-forward (format "" tag) (point-max) t) (setq p4 (point)) (search-backward "]*\\)?>" tag) + (goto-char (point-min)) + (while (re-search-forward (format "\\(<%s\\( [^>]*\\)?>\\)" tag) (point-max) t) (let ((p1) (p2 (point))) @@ -424,5 +471,6 @@ See the documentation for that variable." ;; ;; ;; - +(provide 'html2text) +;;; arch-tag: e9e57b79-35d4-4de1-a647-e7e01fe56d1e ;;; html2text.el ends here