Merge from gnus--rel--5.10

[gnus] / lisp / nnweb.el

diff --git a/lisp/nnweb.el b/lisp/nnweb.el
index f055c6f..56a287e 100644 (file)
--- a/lisp/nnweb.el
+++ b/lisp/nnweb.el
@@ -1,7 +1,7 @@
 ;;; nnweb.el --- retrieving articles via web search engines
 
 ;; Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003,
-;;   2004, 2005, 2006 Free Software Foundation, Inc.
+;;   2004, 2005, 2006, 2007, 2008 Free Software Foundation, Inc.
 
 ;; Author: Lars Magne Ingebrigtsen <larsi@gnus.org>
 ;; Keywords: news
@@ -10,7 +10,7 @@
 
 ;; GNU Emacs is free software; you can redistribute it and/or modify
 ;; it under the terms of the GNU General Public License as published by
-;; the Free Software Foundation; either version 2, or (at your option)
+;; the Free Software Foundation; either version 3, or (at your option)
 ;; any later version.
 
 ;; GNU Emacs is distributed in the hope that it will be useful,
@@ -79,7 +79,7 @@ Valid types include `google', `dejanews', and `gmane'.")
      (reference . identity)
      (map . nnweb-gmane-create-mapping)
      (search . nnweb-gmane-search)
-     (address . "http://search.gmane.org/cgi-bin/omega.cgi")
+     (address . "http://search.gmane.org/nov.php")
      (identifier . nnweb-gmane-identity)))
   "Type-definition alist.")
 
@@ -171,7 +171,8 @@ Valid types include `google', `dejanews', and `gmane'.")
                       (when (string-match "^<\\(.*\\)>$" article)
                         (setq art (match-string 1 article)))
                       (when (and fetch art)
-                        (setq url (format fetch art))
+                        (setq url (format fetch
+                                          (mm-url-form-encode-xwfu art)))
                         (mm-with-unibyte-current-buffer
                           (mm-url-insert url))
                         (if (nnweb-definition 'reference t)
@@ -307,8 +308,8 @@ Valid types include `google', `dejanews', and `gmane'.")
 (defun nnweb-google-wash-article ()
   ;; We have Google's masked e-mail addresses here.  :-/
   (let ((case-fold-search t)
-       (start-re "<pre>\n *")
-       (end-re "\n *</pre>"))
+       (start-re "<pre>[\r\n ]*")
+       (end-re "[\r\n ]*</pre>"))
     (goto-char (point-min))
     (if (save-excursion
          (or (re-search-forward "The requested message.*could not be found."
@@ -359,22 +360,24 @@ Valid types include `google', `dejanews', and `gmane'.")
       (goto-char (point-max))
       (widen)
       (narrow-to-region (point)
-                       (search-forward "</td" nil t))
+                       (search-forward "</table" nil t))
 
       (mm-url-remove-markup)
       (mm-url-decode-entities)
-      (search-backward " - ")
-      (when (looking-at
-            " - \\([a-zA-Z]+\\) \\([0-9]+\\)\\(?: \\([0-9]\\{4\\}\\)\\)?, [^\n]+by \\([^<\n]+\\)\n")
-       (setq From (match-string 4)
-             Date (format "%s %s 00:00:00 %s"
-                          (match-string 1)
-                          (match-string 2)
-                          (or (match-string 3)
-                              (substring (current-time-string) -4)))))
-
+      (goto-char (point-max))
+      (when
+         (re-search-backward
+          "^\\(?:\\(\\w+\\) \\([0-9]+\\)\\|\\S-+\\)\\(?: \\([0-9]\\{4\\}\\)\\)? by ?\\(.*\\)"
+          nil t)
+       (setq Date (if (match-string 1)
+                      (format "%s %s 00:00:00 %s"
+                              (match-string 1)
+                              (match-string 2)
+                              (or (match-string 3)
+                                  (substring (current-time-string) -4)))
+                    (current-time-string)))
+       (setq From (match-string 4)))
       (widen)
-      (forward-line 1)
       (incf i)
       (unless (nnweb-get-hashtb url)
        (push
@@ -415,7 +418,7 @@ Valid types include `google', `dejanews', and `gmane'.")
            (goto-char (point-min))
            (incf i 100)
            (if (or (not (re-search-forward
-                         "<a href=\"\n\\([^>\"]+\\)\"><img src=\"[^\"]+next"
+                         "<a [^>]+href=\"\n?\\([^>\" \n\t]+\\)[^<]*<img[^>]+src=[^>]+next"
                          nil t))
                    (>= i nnweb-max-hits))
                (setq more nil)
@@ -437,7 +440,8 @@ Valid types include `google', `dejanews', and `gmane'.")
     "?"
     (mm-url-encode-www-form-urlencoded
      `(("q" . ,search)
-       ("num" . "100")
+       ("num" . ,(number-to-string
+                 (min 100 nnweb-max-hits)))
        ("hq" . "")
        ("hl" . "en")
        ("lr" . "")
@@ -471,13 +475,13 @@ Valid types include `google', `dejanews', and `gmane'.")
        (forward-line 1)
        ;; Thanks to Olly Betts we now have NOV lines in our buffer!
        (while (not (eobp))
-         (unless (eolp)
+         (unless (or (eolp) (looking-at "\x0d"))
            (let ((header (nnheader-parse-nov)))
              (let ((xref (mail-header-xref header))
                    (from (mail-header-from header))
                    (subject (mail-header-subject header))
                    (rfc2047-encoding-type 'mime))
-               (when (string-match " \\([^:]+\\):\\([0-9]+\\)" xref)
+               (when (string-match " \\([^:]+\\)[:/]\\([0-9]+\\)" xref)
                  (mail-header-set-xref
                   header
                   (format "http://article.gmane.org/%s/%s/raw"
@@ -493,11 +497,8 @@ Valid types include `google', `dejanews', and `gmane'.")
                                         (rfc2047-encode-string subject))
 
                (unless (nnweb-get-hashtb (mail-header-xref header))
-                 (push
-                  (list
-                   (incf (cdr active))
-                   header)
-                  map)
+                 (mail-header-set-number header (incf (cdr active)))
+                 (push (list (mail-header-number header) header) map)
                  (nnweb-set-hashtb (cadar map) (car map))))))
          (forward-line 1)))
       (nnheader-message 7 "Searching Gmane...done")
@@ -522,8 +523,9 @@ Valid types include `google', `dejanews', and `gmane'.")
     "?"
     (mm-url-encode-www-form-urlencoded
      `(("query" . ,search)
-       ("FMT" . "nov")
-       ("HITSPERPAGE" . ,(number-to-string nnweb-max-hits))))))
+       ("HITSPERPAGE" . ,(number-to-string nnweb-max-hits))
+       ;;("TOPDOC" . "1000")
+       ))))
   (setq buffer-file-name nil)
   (set-buffer-multibyte t)
   (mm-decode-coding-region (point-min) (point-max) 'utf-8)