lisp/gnus/nnlistserv.el

   1 ;;; nnlistserv.el --- retrieving articles via web mailing list archives
   2
   3 ;; Copyright (C) 1997, 1998, 1999, 2000 Free Software Foundation, Inc.
   4
   5 ;; Author: Lars Magne Ingebrigtsen <larsi@gnus.org>
   6 ;; Keywords: news, mail
   7
   8 ;; This file is part of GNU Emacs.
   9
  10 ;; GNU Emacs is free software; you can redistribute it and/or modify
  11 ;; it under the terms of the GNU General Public License as published by
  12 ;; the Free Software Foundation; either version 2, or (at your option)
  13 ;; any later version.
  14
  15 ;; GNU Emacs is distributed in the hope that it will be useful,
  16 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
  17 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  18 ;; GNU General Public License for more details.
  19
  20 ;; You should have received a copy of the GNU General Public License
  21 ;; along with GNU Emacs; see the file COPYING.  If not, write to the
  22 ;; Free Software Foundation, Inc., 59 Temple Place - Suite 330,
  23 ;; Boston, MA 02111-1307, USA.
  24
  25 ;;; Commentary:
  26
  27 ;; Note: You need to have `url' and `w3' installed for this
  28 ;; backend to work.
  29
  30 ;;; Code:
  31
  32 (eval-when-compile (require 'cl))
  33
  34 (require 'nnoo)
  35 (eval-when-compile
  36   (ignore-errors
  37    (require 'nnweb))                    ; requires W3
  38   (autoload 'url-insert-file-contents "nnweb"))
  39
  40 (nnoo-declare nnlistserv
  41   nnweb)
  42
  43 (defvoo nnlistserv-directory (nnheader-concat gnus-directory "nnlistserv/")
  44   "Where nnlistserv will save its files."
  45   nnweb-directory)
  46
  47 (defvoo nnlistserv-name 'kk
  48   "What search engine type is being used."
  49   nnweb-type)
  50
  51 (defvoo nnlistserv-type-definition
  52     '((kk
  53        (article . nnlistserv-kk-wash-article)
  54        (map . nnlistserv-kk-create-mapping)
  55        (search . nnlistserv-kk-search)
  56        (address . "http://www.itk.ntnu.no/ansatte/Andresen_Trond/kk-f/%s/")
  57        (pages "fra160396" "fra160796" "fra061196" "fra160197"
  58               "fra090997" "fra040797" "fra130397" "nye")
  59        (index . "date.html")
  60        (identifier . nnlistserv-kk-identity)))
  61   "Type-definition alist."
  62   nnweb-type-definition)
  63
  64 (defvoo nnlistserv-search nil
  65   "Search string to feed to DejaNews."
  66   nnweb-search)
  67
  68 (defvoo nnlistserv-ephemeral-p nil
  69   "Whether this nnlistserv server is ephemeral."
  70   nnweb-ephemeral-p)
  71
  72 ;;; Internal variables
  73
  74 ;;; Interface functions
  75
  76 (nnoo-define-basics nnlistserv)
  77
  78 (nnoo-import nnlistserv
  79   (nnweb))
  80
  81 ;;; Internal functions
  82
  83 ;;;
  84 ;;; KK functions.
  85 ;;;
  86
  87 (defun nnlistserv-kk-create-mapping ()
  88   "Perform the search and create a number-to-url alist."
  89   (save-excursion
  90     (set-buffer nnweb-buffer)
  91     (let ((case-fold-search t)
  92           (active (or (cadr (assoc nnweb-group nnweb-group-alist))
  93                       (cons 1 0)))
  94           (pages (nnweb-definition 'pages))
  95           map url page subject from )
  96       (while (setq page (pop pages))
  97         (erase-buffer)
  98         (when (funcall (nnweb-definition 'search) page)
  99           ;; Go through all the article hits on this page.
 100           (goto-char (point-min))
 101           (nnweb-decode-entities)
 102           (goto-char (point-min))
 103           (while (re-search-forward "^<li> *<a href=\"\\([^\"]+\\)\"><b>\\([^\\>]+\\)</b></a> *<[^>]+><i>\\([^>]+\\)<" nil t)
 104             (setq url (match-string 1)
 105                   subject (match-string 2)
 106                   from (match-string 3))
 107             (setq url (concat (format (nnweb-definition 'address) page) url))
 108             (unless (nnweb-get-hashtb url)
 109               (push
 110                (list
 111                 (incf (cdr active))
 112                 (make-full-mail-header
 113                  (cdr active) subject from ""
 114                  (concat "<" (nnweb-identifier url) "@kk>")
 115                  nil 0 0 url))
 116                map)
 117               (nnweb-set-hashtb (cadar map) (car map))
 118               (nnheader-message 5 "%s %s %s" (cdr active) (point) pages)))))
 119       ;; Return the articles in the right order.
 120       (setq nnweb-articles
 121             (sort (nconc nnweb-articles map) 'car-less-than-car)))))
 122
 123 (defun nnlistserv-kk-wash-article ()
 124   (let ((case-fold-search t)
 125         (headers '(sent name email subject id))
 126         sent name email subject id)
 127     (nnweb-decode-entities)
 128     (while headers
 129       (goto-char (point-min))
 130       (re-search-forward (format "<!-- %s=\"\\([^\"]+\\)" (car headers) nil t))
 131       (set (pop headers) (match-string 1)))
 132     (goto-char (point-min))
 133     (search-forward "<!-- body" nil t)
 134     (delete-region (point-min) (progn (forward-line 1) (point)))
 135     (goto-char (point-max))
 136     (search-backward "<!-- body" nil t)
 137     (delete-region (point-max) (progn (beginning-of-line) (point)))
 138     (nnweb-remove-markup)
 139     (goto-char (point-min))
 140     (insert (format "From: %s <%s>\n" name email)
 141             (format "Subject: %s\n" subject)
 142             (format "Message-ID: %s\n" id)
 143             (format "Date: %s\n\n" sent))))
 144
 145 (defun nnlistserv-kk-search (search)
 146   (url-insert-file-contents
 147    (concat (format (nnweb-definition 'address) search)
 148            (nnweb-definition 'index)))
 149   t)
 150
 151 (defun nnlistserv-kk-identity (url)
 152   "Return an unique identifier based on URL."
 153   url)
 154
 155 (provide 'nnlistserv)
 156
 157 ;;; nnlistserv.el ends here