;;; spam.el --- Identifying spam
-;; Copyright (C) 2002 Free Software Foundation, Inc.
+;; Copyright (C) 2002, 2003 Free Software Foundation, Inc.
;; Author: Lars Magne Ingebrigtsen <larsi@gnus.org>
;; Keywords: network
;;; The integration with Gnus is not yet complete. See various `FIXME'
;;; comments, below, for supplementary explanations or discussions.
+;;; Several TODO items are marked as such
+
;;; Code:
+(eval-when-compile (require 'cl))
+
(require 'gnus-sum)
-;; FIXME! We should not require `dns' nor `message' until we actually
-;; need them. Best would be to declare needed functions as auto-loadable.
-(require 'dns)
-(require 'message)
+(require 'gnus-uu) ; because of key prefix issues
+(require 'gnus) ; for the definitions of group content classification and spam processors
+(require 'message) ;for the message-fetch-field functions
-;; Attempt to load BBDB macros
-(eval-when-compile
- (condition-case nil
- (require 'bbdb-com)
- (file-error (defalias 'bbdb-search 'ignore))))
+;; for nnimap-split-download-body-default
+(eval-when-compile (require 'nnimap))
;; autoload executable-find
(eval-and-compile
;; executable-find is not autoloaded in Emacs 20
(autoload 'executable-find "executable"))
-;; autoload ifile-spam-filter
-(eval-and-compile
- (autoload 'ifile-spam-filter "ifile-gnus"))
-
;; autoload query-dig
(eval-and-compile
(autoload 'query-dig "dig"))
+;; autoload spam-report
+(eval-and-compile
+ (autoload 'spam-report-gmane "spam-report"))
+
+;; autoload query-dns
+(eval-and-compile
+ (autoload 'query-dns "dns"))
+
;;; Main parameters.
-(defvar spam-use-dig t
- "True if query-dig should be used instead of query-dns.")
+(defgroup spam nil
+ "Spam configuration.")
+
+(defcustom spam-directory "~/News/spam/"
+ "Directory for spam whitelists and blacklists."
+ :type 'directory
+ :group 'spam)
+
+(defcustom spam-move-spam-nonspam-groups-only t
+ "Whether spam should be moved in non-spam groups only.
+When nil, only ham and unclassified groups will have their spam moved
+to the spam-process-destination. When t, spam will also be moved from
+spam groups."
+ :type 'boolean
+ :group 'spam)
+
+(defcustom spam-process-ham-in-nonham-groups nil
+ "Whether ham should be processed in non-ham groups."
+ :type 'boolean
+ :group 'spam)
+
+(defcustom spam-process-ham-in-spam-groups nil
+ "Whether ham should be processed in spam groups."
+ :type 'boolean
+ :group 'spam)
+
+(defcustom spam-mark-only-unseen-as-spam t
+ "Whether only unseen articles should be marked as spam in spam
+groups. When nil, all unread articles in a spam group are marked as
+spam. Set this if you want to leave an article unread in a spam group
+without losing it to the automatic spam-marking process."
+ :type 'boolean
+ :group 'spam)
+
+(defcustom spam-mark-ham-unread-before-move-from-spam-group nil
+ "Whether ham should be marked unread before it's moved out of a spam
+group according to ham-process-destination. This variable is an
+official entry in the international Longest Variable Name
+Competition."
+ :type 'boolean
+ :group 'spam)
+
+(defcustom spam-whitelist (expand-file-name "whitelist" spam-directory)
+ "The location of the whitelist.
+The file format is one regular expression per line.
+The regular expression is matched against the address."
+ :type 'file
+ :group 'spam)
-(defvar spam-use-blacklist t
- "True if the blacklist should be used.")
+(defcustom spam-blacklist (expand-file-name "blacklist" spam-directory)
+ "The location of the blacklist.
+The file format is one regular expression per line.
+The regular expression is matched against the address."
+ :type 'file
+ :group 'spam)
+
+(defcustom spam-use-dig t
+ "Whether query-dig should be used instead of query-dns."
+ :type 'boolean
+ :group 'spam)
+
+(defcustom spam-use-blacklist nil
+ "Whether the blacklist should be used by spam-split."
+ :type 'boolean
+ :group 'spam)
+
+(defcustom spam-use-whitelist nil
+ "Whether the whitelist should be used by spam-split."
+ :type 'boolean
+ :group 'spam)
+
+(defcustom spam-use-whitelist-exclusive nil
+ "Whether whitelist-exclusive should be used by spam-split.
+Exclusive whitelisting means that all messages from senders not in the whitelist
+are considered spam."
+ :type 'boolean
+ :group 'spam)
+
+(defcustom spam-use-blackholes nil
+ "Whether blackholes should be used by spam-split."
+ :type 'boolean
+ :group 'spam)
+
+(defcustom spam-use-hashcash nil
+ "Whether hashcash payments should be detected by spam-split."
+ :type 'boolean
+ :group 'spam)
+
+(defcustom spam-use-regex-headers nil
+ "Whether a header regular expression match should be used by spam-split.
+Also see the variables `spam-regex-headers-spam' and `spam-regex-headers-ham'."
+ :type 'boolean
+ :group 'spam)
+
+(defcustom spam-use-regex-body nil
+ "Whether a body regular expression match should be used by spam-split.
+Also see the variables `spam-regex-body-spam' and `spam-regex-body-ham'."
+ :type 'boolean
+ :group 'spam)
+
+(defcustom spam-use-bogofilter-headers nil
+ "Whether bogofilter headers should be used by spam-split.
+Enable this if you pre-process messages with Bogofilter BEFORE Gnus sees them."
+ :type 'boolean
+ :group 'spam)
+
+(defcustom spam-use-bogofilter nil
+ "Whether bogofilter should be invoked by spam-split.
+Enable this if you want Gnus to invoke Bogofilter on new messages."
+ :type 'boolean
+ :group 'spam)
+
+(defcustom spam-use-BBDB nil
+ "Whether BBDB should be used by spam-split."
+ :type 'boolean
+ :group 'spam)
+
+(defcustom spam-use-BBDB-exclusive nil
+ "Whether BBDB-exclusive should be used by spam-split.
+Exclusive BBDB means that all messages from senders not in the BBDB are
+considered spam."
+ :type 'boolean
+ :group 'spam)
+
+(defcustom spam-use-ifile nil
+ "Whether ifile should be used by spam-split."
+ :type 'boolean
+ :group 'spam)
+
+(defcustom spam-use-stat nil
+ "Whether spam-stat should be used by spam-split."
+ :type 'boolean
+ :group 'spam)
+
+(defcustom spam-use-spamoracle nil
+ "Whether spamoracle should be used by spam-split."
+ :type 'boolean
+ :group 'spam)
+
+(defcustom spam-install-hooks (or
+ spam-use-dig
+ spam-use-blacklist
+ spam-use-whitelist
+ spam-use-whitelist-exclusive
+ spam-use-blackholes
+ spam-use-hashcash
+ spam-use-regex-headers
+ spam-use-regex-body
+ spam-use-bogofilter-headers
+ spam-use-bogofilter
+ spam-use-BBDB
+ spam-use-BBDB-exclusive
+ spam-use-ifile
+ spam-use-stat
+ spam-use-spamoracle)
+ "Whether the spam hooks should be installed, default to t if one of
+the spam-use-* variables is set."
+ :group 'gnus-registry
+ :type 'boolean)
+
+(defcustom spam-split-group "spam"
+ "Group name where incoming spam should be put by spam-split."
+ :type 'string
+ :group 'spam)
+
+;;; TODO: deprecate this variable, it's confusing since it's a list of strings, not regular expressions
+(defcustom spam-junk-mailgroups (cons spam-split-group '("mail.junk" "poste.pourriel"))
+ "Mailgroups with spam contents.
+All unmarked article in such group receive the spam mark on group entry."
+ :type '(repeat (string :tag "Group"))
+ :group 'spam)
+
+(defcustom spam-blackhole-servers '("bl.spamcop.net" "relays.ordb.org"
+ "dev.null.dk" "relays.visi.com")
+ "List of blackhole servers."
+ :type '(repeat (string :tag "Server"))
+ :group 'spam)
+
+(defcustom spam-blackhole-good-server-regex nil
+ "String matching IP addresses that should not be checked in the blackholes"
+ :type '(radio (const nil)
+ (regexp :format "%t: %v\n" :size 0))
+ :group 'spam)
+
+(defcustom spam-face 'gnus-splash-face
+ "Face for spam-marked articles"
+ :type 'face
+ :group 'spam)
+
+(defcustom spam-regex-headers-spam '("^X-Spam-Flag: YES")
+ "Regular expression for positive header spam matches"
+ :type '(repeat (regexp :tag "Regular expression to match spam header"))
+ :group 'spam)
+
+(defcustom spam-regex-headers-ham '("^X-Spam-Flag: NO")
+ "Regular expression for positive header ham matches"
+ :type '(repeat (regexp :tag "Regular expression to match ham header"))
+ :group 'spam)
+
+(defcustom spam-regex-body-spam '()
+ "Regular expression for positive body spam matches"
+ :type '(repeat (regexp :tag "Regular expression to match spam body"))
+ :group 'spam)
+
+(defcustom spam-regex-body-ham '()
+ "Regular expression for positive body ham matches"
+ :type '(repeat (regexp :tag "Regular expression to match ham body"))
+ :group 'spam)
+
+(defgroup spam-ifile nil
+ "Spam ifile configuration."
+ :group 'spam)
+
+(defcustom spam-ifile-path (executable-find "ifile")
+ "File path of the ifile executable program."
+ :type '(choice (file :tag "Location of ifile")
+ (const :tag "ifile is not installed"))
+ :group 'spam-ifile)
+
+(defcustom spam-ifile-database-path nil
+ "File path of the ifile database."
+ :type '(choice (file :tag "Location of the ifile database")
+ (const :tag "Use the default"))
+ :group 'spam-ifile)
+
+(defcustom spam-ifile-spam-category "spam"
+ "Name of the spam ifile category."
+ :type 'string
+ :group 'spam-ifile)
+
+(defcustom spam-ifile-ham-category nil
+ "Name of the ham ifile category. If nil, the current group name will
+be used."
+ :type '(choice (string :tag "Use a fixed category")
+ (const :tag "Use the current group name"))
+ :group 'spam-ifile)
+
+(defcustom spam-ifile-all-categories nil
+ "Whether the ifile check will return all categories, or just spam.
+Set this to t if you want to use the spam-split invocation of ifile as
+your main source of newsgroup names."
+ :type 'boolean
+ :group 'spam-ifile)
+
+(defgroup spam-bogofilter nil
+ "Spam bogofilter configuration."
+ :group 'spam)
+
+(defcustom spam-bogofilter-path (executable-find "bogofilter")
+ "File path of the Bogofilter executable program."
+ :type '(choice (file :tag "Location of bogofilter")
+ (const :tag "Bogofilter is not installed"))
+ :group 'spam-bogofilter)
+
+(defcustom spam-bogofilter-header "X-Bogosity"
+ "The header that Bogofilter inserts in messages."
+ :type 'string
+ :group 'spam-bogofilter)
+
+(defcustom spam-bogofilter-spam-switch "-s"
+ "The switch that Bogofilter uses to register spam messages."
+ :type 'string
+ :group 'spam-bogofilter)
+
+(defcustom spam-bogofilter-ham-switch "-n"
+ "The switch that Bogofilter uses to register ham messages."
+ :type 'string
+ :group 'spam-bogofilter)
+
+(defcustom spam-bogofilter-bogosity-positive-spam-header "^\\(Yes\\|Spam\\)"
+ "The regex on `spam-bogofilter-header' for positive spam identification."
+ :type 'regexp
+ :group 'spam-bogofilter)
+
+(defcustom spam-bogofilter-database-directory nil
+ "Directory path of the Bogofilter databases."
+ :type '(choice (directory :tag "Location of the Bogofilter database directory")
+ (const :tag "Use the default"))
+ :group 'spam-ifile)
+
+(defgroup spam-spamoracle nil
+ "Spam ifile configuration."
+ :group 'spam)
+
+(defcustom spam-spamoracle-database nil
+ "Location of spamoracle database file. When nil, use the default
+spamoracle database."
+ :type '(choice (directory :tag "Location of spamoracle database file.")
+ (const :tag "Use the default"))
+ :group 'spam-spamoracle)
+
+(defcustom spam-spamoracle-binary (executable-find "spamoracle")
+ "Location of the spamoracle binary."
+ :type '(choice (directory :tag "Location of the spamoracle binary")
+ (const :tag "Use the default"))
+ :group 'spam-spamoracle)
-(defvar spam-use-whitelist nil
- "True if the whitelist should be used.")
+;;; Key bindings for spam control.
-(defvar spam-use-blackholes nil
- "True if blackholes should be used.")
+(gnus-define-keys gnus-summary-mode-map
+ "St" spam-bogofilter-score
+ "Sx" gnus-summary-mark-as-spam
+ "Mst" spam-bogofilter-score
+ "Msx" gnus-summary-mark-as-spam
+ "\M-d" gnus-summary-mark-as-spam)
-(defvar spam-use-bogofilter nil
- "True if bogofilter should be used.")
+;; convenience functions
+(defun spam-group-ham-mark-p (group mark &optional spam)
+ (when (stringp group)
+ (let* ((marks (spam-group-ham-marks group spam))
+ (marks (if (symbolp mark)
+ marks
+ (mapcar 'symbol-value marks))))
+ (memq mark marks))))
-(defvar spam-use-bbdb nil
- "True if BBDB should be used.")
+(defun spam-group-spam-mark-p (group mark)
+ (spam-group-ham-mark-p group mark t))
-(defvar spam-use-ifile nil
- "True if ifile should be used.")
+(defun spam-group-ham-marks (group &optional spam)
+ (when (stringp group)
+ (let* ((marks (if spam
+ (gnus-parameter-spam-marks group)
+ (gnus-parameter-ham-marks group)))
+ (marks (car marks))
+ (marks (if (listp (car marks)) (car marks) marks)))
+ marks)))
-(defvar spam-split-group "spam"
- "Usual group name where spam should be split.")
+(defun spam-group-spam-marks (group)
+ (spam-group-ham-marks group t))
-(defvar spam-junk-mailgroups
- ;; FIXME! The mailgroup list evidently depends on other choices made by the
- ;; user, so the built-in default below is not likely to be appropriate.
- (cons spam-split-group '("mail.junk" "poste.pourriel"))
- "Mailgroups which are dedicated by splitting to receive various junk.
-All unmarked article in such group receive the spam mark on group entry.")
+(defun spam-group-spam-contents-p (group)
+ (if (stringp group)
+ (or (member group spam-junk-mailgroups)
+ (memq 'gnus-group-spam-classification-spam
+ (gnus-parameter-spam-contents group)))
+ nil))
+
+(defun spam-group-ham-contents-p (group)
+ (if (stringp group)
+ (memq 'gnus-group-spam-classification-ham
+ (gnus-parameter-spam-contents group))
+ nil))
-;; FIXME! For `spam-ham-marks' and `spam-spam-marks', I wonder if it would
-;; not be easier for the user to just accept a string of mark letters, instead
-;; of a list of Gnus variable names. In such case, the stunt of deferred
-;; evaluation would not be useful anymore. Lars?? :-)
+(defun spam-group-processor-p (group processor)
+ (if (and (stringp group)
+ (symbolp processor))
+ (member processor (car (gnus-parameter-spam-process group)))
+ nil))
-;; FIXME! It is rather questionable to see `K', `X' and `Y' as indicating
-;; positive ham. It much depends on how and why people use kill files, score
-;; files, and the kill command. Maybe it would be better, by default, to not
-;; process a message neither as ham nor spam, that is, just ignore it for
-;; learning purposes, when we are not sure of how the user sees it.
-;; But `r' and `R' should undoubtedly be seen as ham.
+(defun spam-group-spam-processor-report-gmane-p (group)
+ (spam-group-processor-p group 'gnus-group-spam-exit-processor-report-gmane))
-;; FIXME! Some might consider overkill to define a list of spam marks. On
-;; the other hand, who knows, some users might for example like that
-;; explicitly `E'xpired articles be processed as positive spam.
+(defun spam-group-spam-processor-bogofilter-p (group)
+ (spam-group-processor-p group 'gnus-group-spam-exit-processor-bogofilter))
-(defvar spam-ham-marks
- (list gnus-del-mark gnus-read-mark gnus-killed-mark
- gnus-kill-file-mark gnus-low-score-mark)
- "Marks considered as being ham (positively not spam).
-Such articles will be transmitted to `bogofilter -n' on group exit.")
+(defun spam-group-spam-processor-blacklist-p (group)
+ (spam-group-processor-p group 'gnus-group-spam-exit-processor-blacklist))
-(defvar spam-spam-marks
- (list gnus-spam-mark)
- "Marks considered as being spam (positively spam).
-Such articles will be transmitted to `bogofilter -s' on group exit.")
+(defun spam-group-spam-processor-ifile-p (group)
+ (spam-group-processor-p group 'gnus-group-spam-exit-processor-ifile))
-;; FIXME! Ideally, the remainder of this page should be fully integrated
-;; within `gnus-sum.el'.
+(defun spam-group-ham-processor-ifile-p (group)
+ (spam-group-processor-p group 'gnus-group-ham-exit-processor-ifile))
-;;; Key bindings for spam control.
+(defun spam-group-spam-processor-spamoracle-p (group)
+ (spam-group-processor-p group 'gnus-group-spam-exit-processor-spamoracle))
-;; FIXME! The justification for `M-d' is that this is what Paul Graham
-;; suggests in his original article, and what Eric Raymond's patch for Mutt
-;; uses. But more importantly, that binding was still free in Summary mode!
+(defun spam-group-ham-processor-bogofilter-p (group)
+ (spam-group-processor-p group 'gnus-group-ham-exit-processor-bogofilter))
-;; FIXME! Lars has not blessed the following key bindings yet. It looks
-;; convenient that the score analysis command uses a sequence ending with the
-;; letter `t', so it nicely parallels `B t' or `V t'. `M-d' is a kind of
-;; "alternate" `d', it is also the sequence suggested in Paul Graham article,
-;; and also in Eric Raymond's patch for Mutt. `S x' might be the more
-;; official key binding for `M-d'.
+(defun spam-group-spam-processor-stat-p (group)
+ (spam-group-processor-p group 'gnus-group-spam-exit-processor-stat))
-(gnus-define-keys gnus-summary-mode-map
- "St" spam-bogofilter-score
- "Sx" gnus-summary-mark-as-spam
- "Mst" spam-bogofilter-score
- "Msx" gnus-summary-mark-as-spam
- "\M-d" gnus-summary-mark-as-spam)
+(defun spam-group-ham-processor-stat-p (group)
+ (spam-group-processor-p group 'gnus-group-ham-exit-processor-stat))
-;;; How to highlight a spam summary line.
+(defun spam-group-ham-processor-whitelist-p (group)
+ (spam-group-processor-p group 'gnus-group-ham-exit-processor-whitelist))
-;; FIXME! Of course, `gnus-splash-face' has another purpose. Maybe a
-;; special face should be created, named and used instead, for spam lines.
+(defun spam-group-ham-processor-BBDB-p (group)
+ (spam-group-processor-p group 'gnus-group-ham-exit-processor-BBDB))
-(push '((eq mark gnus-spam-mark) . gnus-splash-face)
- gnus-summary-highlight)
+(defun spam-group-ham-processor-copy-p (group)
+ (spam-group-processor-p group 'gnus-group-ham-exit-processor-copy))
-;;; Hooks dispatching. A bit raw for now.
+(defun spam-group-ham-processor-spamoracle-p (group)
+ (spam-group-processor-p group 'gnus-group-ham-exit-processor-spamoracle))
+
+;;; Summary entry and exit processing.
(defun spam-summary-prepare ()
(spam-mark-junk-as-spam-routine))
+;; The spam processors are invoked for any group, spam or ham or neither
(defun spam-summary-prepare-exit ()
- (spam-bogofilter-register-routine))
-
-(add-hook 'gnus-summary-prepare-hook 'spam-summary-prepare)
-(add-hook 'gnus-summary-prepare-exit-hook 'spam-summary-prepare-exit)
+ (unless gnus-group-is-exiting-without-update-p
+ (gnus-message 6 "Exiting summary buffer and applying spam rules")
+ (when (and spam-bogofilter-path
+ (spam-group-spam-processor-bogofilter-p gnus-newsgroup-name))
+ (gnus-message 5 "Registering spam with bogofilter")
+ (spam-bogofilter-register-spam-routine))
+
+ (when (and spam-ifile-path
+ (spam-group-spam-processor-ifile-p gnus-newsgroup-name))
+ (gnus-message 5 "Registering spam with ifile")
+ (spam-ifile-register-spam-routine))
+
+ (when (spam-group-spam-processor-spamoracle-p gnus-newsgroup-name)
+ (gnus-message 5 "Registering spam with spamoracle")
+ (spam-spamoracle-learn-spam))
+
+ (when (spam-group-spam-processor-stat-p gnus-newsgroup-name)
+ (gnus-message 5 "Registering spam with spam-stat")
+ (spam-stat-register-spam-routine))
+
+ (when (spam-group-spam-processor-blacklist-p gnus-newsgroup-name)
+ (gnus-message 5 "Registering spam with the blacklist")
+ (spam-blacklist-register-routine))
+
+ (when (spam-group-spam-processor-report-gmane-p gnus-newsgroup-name)
+ (gnus-message 5 "Registering spam with the Gmane report")
+ (spam-report-gmane-register-routine))
+
+ (if spam-move-spam-nonspam-groups-only
+ (when (not (spam-group-spam-contents-p gnus-newsgroup-name))
+ (spam-mark-spam-as-expired-and-move-routine
+ (gnus-parameter-spam-process-destination gnus-newsgroup-name)))
+ (gnus-message 5 "Marking spam as expired and moving it to %s" gnus-newsgroup-name)
+ (spam-mark-spam-as-expired-and-move-routine
+ (gnus-parameter-spam-process-destination gnus-newsgroup-name)))
+
+ ;; now we redo spam-mark-spam-as-expired-and-move-routine to only
+ ;; expire spam, in case the above did not expire them
+ (gnus-message 5 "Marking spam as expired without moving it")
+ (spam-mark-spam-as-expired-and-move-routine nil)
+
+ (when (or (spam-group-ham-contents-p gnus-newsgroup-name)
+ (and (spam-group-spam-contents-p gnus-newsgroup-name)
+ spam-process-ham-in-spam-groups)
+ spam-process-ham-in-nonham-groups)
+ (when (spam-group-ham-processor-whitelist-p gnus-newsgroup-name)
+ (gnus-message 5 "Registering ham with the whitelist")
+ (spam-whitelist-register-routine))
+ (when (spam-group-ham-processor-ifile-p gnus-newsgroup-name)
+ (gnus-message 5 "Registering ham with ifile")
+ (spam-ifile-register-ham-routine))
+ (when (spam-group-ham-processor-bogofilter-p gnus-newsgroup-name)
+ (gnus-message 5 "Registering ham with Bogofilter")
+ (spam-bogofilter-register-ham-routine))
+ (when (spam-group-ham-processor-stat-p gnus-newsgroup-name)
+ (gnus-message 5 "Registering ham with spam-stat")
+ (spam-stat-register-ham-routine))
+ (when (spam-group-ham-processor-BBDB-p gnus-newsgroup-name)
+ (gnus-message 5 "Registering ham with the BBDB")
+ (spam-BBDB-register-routine))
+ (when (spam-group-ham-processor-spamoracle-p gnus-newsgroup-name)
+ (gnus-message 5 "Registering ham with spamoracle")
+ (spam-spamoracle-learn-ham)))
+
+ (when (spam-group-ham-processor-copy-p gnus-newsgroup-name)
+ (gnus-message 5 "Copying ham")
+ (spam-ham-copy-routine
+ (gnus-parameter-ham-process-destination gnus-newsgroup-name)))
+
+ ;; now move all ham articles out of spam groups
+ (when (spam-group-spam-contents-p gnus-newsgroup-name)
+ (gnus-message 5 "Moving ham messages from spam group")
+ (spam-ham-move-routine
+ (gnus-parameter-ham-process-destination gnus-newsgroup-name)))))
(defun spam-mark-junk-as-spam-routine ()
- (when (member gnus-newsgroup-name spam-junk-mailgroups)
- (let ((articles gnus-newsgroup-articles)
- article)
- (while articles
- (setq article (pop articles))
- (when (eq (gnus-summary-article-mark article) gnus-unread-mark)
- (gnus-summary-mark-article article gnus-spam-mark))))))
+ ;; check the global list of group names spam-junk-mailgroups and the
+ ;; group parameters
+ (when (spam-group-spam-contents-p gnus-newsgroup-name)
+ (gnus-message 5 "Marking %s articles as spam"
+ (if spam-mark-only-unseen-as-spam
+ "unseen"
+ "unread"))
+ (let ((articles (if spam-mark-only-unseen-as-spam
+ gnus-newsgroup-unseen
+ gnus-newsgroup-unreads)))
+ (dolist (article articles)
+ (gnus-summary-mark-article article gnus-spam-mark)))))
+
+(defun spam-mark-spam-as-expired-and-move-routine (&rest groups)
+ (gnus-summary-kill-process-mark)
+ (let ((articles gnus-newsgroup-articles)
+ article tomove)
+ (dolist (article articles)
+ (when (eq (gnus-summary-article-mark article) gnus-spam-mark)
+ (gnus-summary-mark-article article gnus-expirable-mark)
+ (push article tomove)))
+
+ ;; now do the actual copies
+ (dolist (group groups)
+ (when (and tomove
+ (stringp group))
+ (dolist (article tomove)
+ (gnus-summary-set-process-mark article))
+ (when tomove
+ (gnus-summary-copy-article nil group))))
+
+ ;; now delete the articles
+ (dolist (article tomove)
+ (gnus-summary-set-process-mark article))
+ (when tomove
+ (gnus-summary-delete-article nil)))
+
+ (gnus-summary-yank-process-mark))
+
+(defun spam-ham-copy-or-move-routine (copy &rest groups)
+ (gnus-summary-kill-process-mark)
+ (let ((articles gnus-newsgroup-articles)
+ article mark todo)
+ (dolist (article articles)
+ (when (spam-group-ham-mark-p gnus-newsgroup-name
+ (gnus-summary-article-mark article))
+ (push article todo)))
+
+ ;; now do the actual move
+ (dolist (group groups)
+ (when todo
+ (dolist (article todo)
+ (when spam-mark-ham-unread-before-move-from-spam-group
+ (gnus-summary-mark-article article gnus-unread-mark))
+ (gnus-summary-set-process-mark article))
+ (gnus-summary-copy-article nil group)))
+
+ ;; now delete the articles
+ (dolist (article todo)
+ (gnus-summary-set-process-mark article))
+ (when todo
+ (gnus-summary-delete-article nil)))
+
+ (gnus-summary-yank-process-mark))
+
+(defun spam-ham-copy-routine (&rest groups)
+ (spam-ham-copy-or-move-routine t groups))
+
+(defun spam-ham-move-routine (&rest groups)
+ (spam-ham-copy-or-move-routine nil groups))
+
+(defun spam-generic-register-routine (spam-func ham-func)
+ (let ((articles gnus-newsgroup-articles)
+ article mark ham-articles spam-articles)
+
+ (while articles
+ (setq article (pop articles)
+ mark (gnus-summary-article-mark article))
+ (cond ((spam-group-spam-mark-p gnus-newsgroup-name mark)
+ (push article spam-articles))
+ ((memq article gnus-newsgroup-saved))
+ ((spam-group-ham-mark-p gnus-newsgroup-name mark)
+ (push article ham-articles))))
+
+ (when (and ham-articles ham-func)
+ (mapc ham-func ham-articles)) ; we use mapc because unlike
+ ; mapcar it discards the
+ ; return values
+ (when (and spam-articles spam-func)
+ (mapc spam-func spam-articles)))) ; we use mapc because unlike
+ ; mapcar it discards the
+ ; return values
+
+(eval-and-compile
+ (defalias 'spam-point-at-eol (if (fboundp 'point-at-eol)
+ 'point-at-eol
+ 'line-end-position)))
+
+(defun spam-get-article-as-string (article)
+ (let ((article-buffer (spam-get-article-as-buffer article))
+ article-string)
+ (when article-buffer
+ (save-window-excursion
+ (set-buffer article-buffer)
+ (setq article-string (buffer-string))))
+ article-string))
+
+(defun spam-get-article-as-buffer (article)
+ (let ((article-buffer))
+ (when (numberp article)
+ (save-window-excursion
+ (gnus-summary-goto-subject article)
+ (gnus-summary-show-article t)
+ (setq article-buffer (get-buffer gnus-article-buffer))))
+ article-buffer))
+
+;; disabled for now
+;; (defun spam-get-article-as-filename (article)
+;; (let ((article-filename))
+;; (when (numberp article)
+;; (nnml-possibly-change-directory (gnus-group-real-name gnus-newsgroup-name))
+;; (setq article-filename (expand-file-name (int-to-string article) nnml-current-directory)))
+;; (if (file-exists-p article-filename)
+;; article-filename
+;; nil)))
+
+(defun spam-fetch-field-from-fast (article)
+ "Fetch the `from' field quickly, using the internal gnus-data-list function"
+ (if (and (numberp article)
+ (assoc article (gnus-data-list nil)))
+ (mail-header-from (gnus-data-header (assoc article (gnus-data-list nil))))
+ nil))
+
+(defun spam-fetch-field-subject-fast (article)
+ "Fetch the `subject' field quickly, using the internal gnus-data-list function"
+ (if (and (numberp article)
+ (assoc article (gnus-data-list nil)))
+ (mail-header-subject (gnus-data-header (assoc article (gnus-data-list nil))))
+ nil))
+
\f
;;;; Spam determination.
-
(defvar spam-list-of-checks
- '((spam-use-blacklist . spam-check-blacklist)
- (spam-use-whitelist . spam-check-whitelist)
- (spam-use-bbdb . spam-check-bbdb)
- (spam-use-ifile . spam-check-ifile)
- (spam-use-blackholes . spam-check-blackholes)
- (spam-use-bogofilter . spam-check-bogofilter))
+ '((spam-use-blacklist . spam-check-blacklist)
+ (spam-use-regex-headers . spam-check-regex-headers)
+ (spam-use-regex-body . spam-check-regex-body)
+ (spam-use-whitelist . spam-check-whitelist)
+ (spam-use-BBDB . spam-check-BBDB)
+ (spam-use-ifile . spam-check-ifile)
+ (spam-use-spamoracle . spam-check-spamoracle)
+ (spam-use-stat . spam-check-stat)
+ (spam-use-blackholes . spam-check-blackholes)
+ (spam-use-hashcash . spam-check-hashcash)
+ (spam-use-bogofilter-headers . spam-check-bogofilter-headers)
+ (spam-use-bogofilter . spam-check-bogofilter))
"The spam-list-of-checks list contains pairs associating a parameter
variable with a spam checking function. If the parameter variable is
true, then the checking function is called, and its value decides what
-happens. Each individual check may return `nil', `t', or a mailgroup
-name. The value `nil' means that the check does not yield a decision,
-and so, that further checks are needed. The value `t' means that the
+happens. Each individual check may return nil, t, or a mailgroup
+name. The value nil means that the check does not yield a decision,
+and so, that further checks are needed. The value t means that the
message is definitely not spam, and that further spam checks should be
inhibited. Otherwise, a mailgroup name is returned where the mail
should go, and further checks are also inhibited. The usual mailgroup
name is the value of `spam-split-group', meaning that the message is
definitely a spam.")
-(defun spam-split ()
+(defvar spam-list-of-statistical-checks
+ '(spam-use-ifile spam-use-regex-body spam-use-stat spam-use-bogofilter spam-use-spamoracle)
+"The spam-list-of-statistical-checks list contains all the mail
+splitters that need to have the full message body available.")
+
+;;;TODO: modify to invoke self with each specific check if invoked without specific checks
+(defun spam-split (&rest specific-checks)
"Split this message into the `spam' group if it is spam.
This function can be used as an entry in `nnmail-split-fancy', for
-example like this: (: spam-split)
+example like this: (: spam-split). It can take checks as parameters.
See the Info node `(gnus)Fancy Mail Splitting' for more details."
(interactive)
+ (save-excursion
+ (save-restriction
+ (dolist (check spam-list-of-statistical-checks)
+ (when (symbol-value check)
+ (widen)
+ (gnus-message 8 "spam-split: widening the buffer (%s requires it)"
+ (symbol-name check))
+ (return)))
+ ;; (progn (widen) (debug (buffer-string)))
+ (let ((list-of-checks spam-list-of-checks)
+ decision)
+ (while (and list-of-checks (not decision))
+ (let ((pair (pop list-of-checks)))
+ (when (and (symbol-value (car pair))
+ (or (null specific-checks)
+ (memq (car pair) specific-checks)))
+ (gnus-message 5 "spam-split: calling the %s function" (symbol-name (cdr pair)))
+ (setq decision (funcall (cdr pair))))))
+ (if (eq decision t)
+ nil
+ decision)))))
+
+(defun spam-setup-widening ()
+ (dolist (check spam-list-of-statistical-checks)
+ (when (symbol-value check)
+ (setq nnimap-split-download-body-default t))))
+
+\f
+;;;; Regex body
+
+(defun spam-check-regex-body ()
+ (let ((spam-regex-headers-ham spam-regex-body-ham)
+ (spam-regex-headers-spam spam-regex-body-spam))
+ (spam-check-regex-headers t)))
+
+\f
+;;;; Regex headers
+
+(defun spam-check-regex-headers (&optional body)
+ (let ((type (if body "body" "header"))
+ ret found)
+ (dolist (h-regex spam-regex-headers-ham)
+ (unless found
+ (goto-char (point-min))
+ (when (re-search-forward h-regex nil t)
+ (message "Ham regex %s search positive." type)
+ (setq found t))))
+ (dolist (s-regex spam-regex-headers-spam)
+ (unless found
+ (goto-char (point-min))
+ (when (re-search-forward s-regex nil t)
+ (message "Spam regex %s search positive." type)
+ (setq found t)
+ (setq ret spam-split-group))))
+ ret))
- (let ((list-of-checks spam-list-of-checks)
- decision)
- (while (and list-of-checks (not decision))
- (let ((pair (pop list-of-checks)))
- (when (symbol-value (car pair))
- (setq decision (funcall (cdr pair))))))
- (if (eq decision t)
- nil
- decision)))
\f
;;;; Blackholes.
-(defvar spam-blackhole-servers '("bl.spamcop.net"
- "relays.ordb.org"
- "dev.null.dk"
- "relays.visi.com")
- "List of blackhole servers.")
+(defun spam-reverse-ip-string (ip)
+ (when (stringp ip)
+ (mapconcat 'identity
+ (nreverse (split-string ip "\\."))
+ ".")))
(defun spam-check-blackholes ()
"Check the Received headers for blackholed relays."
- (let ((headers (message-fetch-field "received"))
+ (let ((headers (nnmail-fetch-field "received"))
ips matches)
(when headers
(with-temp-buffer
(insert headers)
(goto-char (point-min))
+ (gnus-message 5 "Checking headers for relay addresses")
(while (re-search-forward
- "\\[\\([0-9]+.[0-9]+.[0-9]+.[0-9]+\\)\\]" nil t)
- (message "Blackhole search found host IP %s." (match-string 1))
- (push (mapconcat 'identity
- (nreverse (split-string (match-string 1) "\\."))
- ".")
+ "\\([0-9]+\\.[0-9]+\\.[0-9]+\\.[0-9]+\\)" nil t)
+ (gnus-message 9 "Blackhole search found host IP %s." (match-string 1))
+ (push (spam-reverse-ip-string (match-string 1))
ips)))
(dolist (server spam-blackhole-servers)
(dolist (ip ips)
- (let ((query-string (concat ip "." server)))
- (if spam-use-dig
- (let ((query-result (query-dig query-string)))
- (when query-result
- (message "spam detected with blackhole check of relay %s (dig query result '%s')" query-string query-result)
- (push (list ip server query-result)
- matches)))
- ;; else, if not using dig.el
- (when (query-dns query-string)
- (push (list ip server (query-dns query-string 'TXT))
- matches)))))))
+ (unless (and spam-blackhole-good-server-regex
+ ;; match the good-server-regex against the reversed (again) IP string
+ (string-match
+ spam-blackhole-good-server-regex
+ (spam-reverse-ip-string ip)))
+ (unless matches
+ (let ((query-string (concat ip "." server)))
+ (if spam-use-dig
+ (let ((query-result (query-dig query-string)))
+ (when query-result
+ (gnus-message 5 "(DIG): positive blackhole check '%s'"
+ query-result)
+ (push (list ip server query-result)
+ matches)))
+ ;; else, if not using dig.el
+ (when (query-dns query-string)
+ (gnus-message 5 "positive blackhole check")
+ (push (list ip server (query-dns query-string 'TXT))
+ matches)))))))))
(when matches
spam-split-group)))
\f
-;;;; Blacklists and whitelists.
+;;;; Hashcash.
-(defvar spam-directory "~/News/spam/"
- "When spam files are kept.")
+(condition-case nil
+ (progn
+ (require 'hashcash)
+
+ (defun spam-check-hashcash ()
+ "Check the headers for hashcash payments."
+ (mail-check-payment))) ;mail-check-payment returns a boolean
+
+ (file-error (progn
+ (defalias 'mail-check-payment 'ignore)
+ (defalias 'spam-check-hashcash 'ignore))))
+\f
+;;;; BBDB
-(defvar spam-whitelist (expand-file-name "whitelist" spam-directory)
- "The location of the whitelist.
-The file format is one regular expression per line.
-The regular expression is matched against the address.")
+;;; original idea for spam-check-BBDB from Alexander Kotelnikov
+;;; <sacha@giotto.sj.ru>
-(defvar spam-blacklist (expand-file-name "blacklist" spam-directory)
- "The location of the blacklist.
-The file format is one regular expression per line.
-The regular expression is matched against the address.")
+;; all this is done inside a condition-case to trap errors
+
+(condition-case nil
+ (progn
+ (require 'bbdb)
+ (require 'bbdb-com)
+
+ (defun spam-enter-ham-BBDB (from)
+ "Enter an address into the BBDB; implies ham (non-spam) sender"
+ (when (stringp from)
+ (let* ((parsed-address (gnus-extract-address-components from))
+ (name (or (car parsed-address) "Ham Sender"))
+ (net-address (car (cdr parsed-address))))
+ (gnus-message 5 "Adding address %s to BBDB" from)
+ (when (and net-address
+ (not (bbdb-search-simple nil net-address)))
+ (bbdb-create-internal name nil net-address nil nil
+ "ham sender added by spam.el")))))
+
+ (defun spam-BBDB-register-routine ()
+ (spam-generic-register-routine
+ ;; spam function
+ nil
+ ;; ham function
+ (lambda (article)
+ (spam-enter-ham-BBDB (spam-fetch-field-from-fast article)))))
+
+ (defun spam-check-BBDB ()
+ "Mail from people in the BBDB is classified as ham or non-spam"
+ (let ((who (nnmail-fetch-field "from")))
+ (when who
+ (setq who (cadr (gnus-extract-address-components who)))
+ (if (bbdb-search-simple nil who)
+ t
+ (if spam-use-BBDB-exclusive
+ spam-split-group
+ nil))))))
+
+ (file-error (progn
+ (defalias 'bbdb-search-simple 'ignore)
+ (defalias 'spam-check-BBDB 'ignore)
+ (defalias 'spam-BBDB-register-routine 'ignore)
+ (defalias 'spam-enter-ham-BBDB 'ignore)
+ (defalias 'bbdb-create-internal 'ignore)
+ (defalias 'bbdb-records 'ignore))))
+
+\f
+;;;; ifile
+
+;;; check the ifile backend; return nil if the mail was NOT classified
+;;; as spam
+
+(defun spam-get-ifile-database-parameter ()
+ "Get the command-line parameter for ifile's database from spam-ifile-database-path."
+ (if spam-ifile-database-path
+ (format "--db-file=%s" spam-ifile-database-path)
+ nil))
+
+(defun spam-check-ifile ()
+ "Check the ifile backend for the classification of this message"
+ (let ((article-buffer-name (buffer-name))
+ category return)
+ (with-temp-buffer
+ (let ((temp-buffer-name (buffer-name))
+ (db-param (spam-get-ifile-database-parameter)))
+ (save-excursion
+ (set-buffer article-buffer-name)
+ (if db-param
+ (call-process-region (point-min) (point-max) spam-ifile-path
+ nil temp-buffer-name nil "-q" "-c" db-param)
+ (call-process-region (point-min) (point-max) spam-ifile-path
+ nil temp-buffer-name nil "-q" "-c")))
+ (goto-char (point-min))
+ (if (not (eobp))
+ (setq category (buffer-substring (point) (spam-point-at-eol))))
+ (when (not (zerop (length category))) ; we need a category here
+ (if spam-ifile-all-categories
+ (setq return category)
+ ;; else, if spam-ifile-all-categories is not set...
+ (when (string-equal spam-ifile-spam-category category)
+ (setq return spam-split-group))))))
+ return))
+
+(defun spam-ifile-register-with-ifile (article-string category)
+ "Register an article, given as a string, with a category.
+Uses `gnus-newsgroup-name' if category is nil (for ham registration)."
+ (when (stringp article-string)
+ (let ((category (or category gnus-newsgroup-name))
+ (db-param (spam-get-ifile-database-parameter)))
+ (with-temp-buffer
+ (insert article-string)
+ (if db-param
+ (call-process-region (point-min) (point-max) spam-ifile-path
+ nil nil nil
+ "-h" "-i" category db-param)
+ (call-process-region (point-min) (point-max) spam-ifile-path
+ nil nil nil
+ "-h" "-i" category))))))
+
+(defun spam-ifile-register-spam-routine ()
+ (spam-generic-register-routine
+ (lambda (article)
+ (spam-ifile-register-with-ifile
+ (spam-get-article-as-string article) spam-ifile-spam-category))
+ nil))
+
+(defun spam-ifile-register-ham-routine ()
+ (spam-generic-register-routine
+ nil
+ (lambda (article)
+ (spam-ifile-register-with-ifile
+ (spam-get-article-as-string article) spam-ifile-ham-category))))
+
+\f
+;;;; spam-stat
+
+(condition-case nil
+ (progn
+ (let ((spam-stat-install-hooks nil))
+ (require 'spam-stat))
+
+ (defun spam-check-stat ()
+ "Check the spam-stat backend for the classification of this message"
+ (let ((spam-stat-split-fancy-spam-group spam-split-group) ; override
+ (spam-stat-buffer (buffer-name)) ; stat the current buffer
+ category return)
+ (spam-stat-split-fancy)))
+
+ (defun spam-stat-register-spam-routine ()
+ (spam-generic-register-routine
+ (lambda (article)
+ (let ((article-string (spam-get-article-as-string article)))
+ (with-temp-buffer
+ (insert article-string)
+ (spam-stat-buffer-is-spam))))
+ nil))
+
+ (defun spam-stat-register-ham-routine ()
+ (spam-generic-register-routine
+ nil
+ (lambda (article)
+ (let ((article-string (spam-get-article-as-string article)))
+ (with-temp-buffer
+ (insert article-string)
+ (spam-stat-buffer-is-non-spam))))))
+
+ (defun spam-maybe-spam-stat-load ()
+ (when spam-use-stat (spam-stat-load)))
+
+ (defun spam-maybe-spam-stat-save ()
+ (when spam-use-stat (spam-stat-save))))
+
+ (file-error (progn
+ (defalias 'spam-maybe-spam-stat-load 'ignore)
+ (defalias 'spam-maybe-spam-stat-save 'ignore)
+ (defalias 'spam-stat-register-ham-routine 'ignore)
+ (defalias 'spam-stat-register-spam-routine 'ignore)
+ (defalias 'spam-stat-buffer-is-spam 'ignore)
+ (defalias 'spam-stat-buffer-is-non-spam 'ignore)
+ (defalias 'spam-stat-split-fancy 'ignore)
+ (defalias 'spam-stat-load 'ignore)
+ (defalias 'spam-stat-save 'ignore)
+ (defalias 'spam-check-stat 'ignore))))
+
+\f
+
+;;;; Blacklists and whitelists.
(defvar spam-whitelist-cache nil)
(defvar spam-blacklist-cache nil)
(save-excursion
(set-buffer
(find-file-noselect file))
- (goto-char (point-max))
- (unless (bobp)
- (insert "\n"))
- (insert address "\n")
- (save-buffer)))
-
-;;; returns nil if the sender is in the whitelist, spam-split-group otherwise
+ (goto-char (point-min))
+ (unless (re-search-forward (regexp-quote address) nil t)
+ (goto-char (point-max))
+ (unless (bobp)
+ (insert "\n"))
+ (insert address "\n")
+ (save-buffer))))
+
+;;; returns t if the sender is in the whitelist, nil or spam-split-group otherwise
(defun spam-check-whitelist ()
;; FIXME! Should it detect when file timestamps change?
(unless spam-whitelist-cache
(setq spam-whitelist-cache (spam-parse-list spam-whitelist)))
- (if (spam-from-listed-p spam-whitelist-cache) nil spam-split-group))
-
-;;; original idea from Alexander Kotelnikov <sacha@giotto.sj.ru>
-(condition-case nil
- (progn
- (require 'bbdb-com)
- (defun spam-check-bbdb ()
- "We want messages from people who are in the BBDB not to be split to spam"
- (let ((who (message-fetch-field "from")))
- (when who
- (setq who (regexp-quote (cadr (gnus-extract-address-components who))))
- (if (bbdb-search (bbdb-records) nil nil who) nil spam-split-group)))))
- (file-error (setq spam-list-of-checks
- (delete (assoc 'spam-use-bbdb spam-list-of-checks)
- spam-list-of-checks))))
-
-;;; check the ifile backend; return nil if the mail was NOT classified as spam
-(condition-case nil
- (progn
- (require 'ifile-gnus)
- ;;;
- (defun spam-check-ifile ()
- (let ((ifile-primary-spam-group spam-split-group))
- (ifile-spam-filter nil))))
- (file-error (setq spam-list-of-checks
- (delete (assoc 'spam-use-ifile spam-list-of-checks)
- spam-list-of-checks))))
+ (if (spam-from-listed-p spam-whitelist-cache)
+ t
+ (if spam-use-whitelist-exclusive
+ spam-split-group
+ nil)))
(defun spam-check-blacklist ()
;; FIXME! Should it detect when file timestamps change?
(setq spam-blacklist-cache (spam-parse-list spam-blacklist)))
(and (spam-from-listed-p spam-blacklist-cache) spam-split-group))
-(eval-and-compile
- (defalias 'spam-point-at-eol (if (fboundp 'point-at-eol)
- 'point-at-eol
- 'line-end-position)))
-
(defun spam-parse-list (file)
(when (file-readable-p file)
(let (contents address)
(while (not (eobp))
(setq address (buffer-substring (point) (spam-point-at-eol)))
(forward-line 1)
+ ;; insert the e-mail address if detected, otherwise the raw data
(unless (zerop (length address))
- (setq address (regexp-quote address))
- (while (string-match "\\\\\\*" address)
- (setq address (replace-match ".*" t t address)))
- (push address contents))))
+ (let ((pure-address (cadr (gnus-extract-address-components address))))
+ (push (or pure-address address) contents)))))
(nreverse contents))))
(defun spam-from-listed-p (cache)
- (let ((from (message-fetch-field "from"))
+ (let ((from (nnmail-fetch-field "from"))
found)
(while cache
- (when (string-match (pop cache) from)
- (setq found t
- cache nil)))
+ (let ((address (pop cache)))
+ (unless (zerop (length address)) ; 0 for a nil address too
+ (setq address (regexp-quote address))
+ ;; fix regexp-quote's treatment of user-intended regexes
+ (while (string-match "\\\\\\*" address)
+ (setq address (replace-match ".*" t t address))))
+ (when (and address (string-match address from))
+ (setq found t
+ cache nil))))
found))
+(defun spam-blacklist-register-routine ()
+ (spam-generic-register-routine
+ ;; the spam function
+ (lambda (article)
+ (let ((from (spam-fetch-field-from-fast article)))
+ (when (stringp from)
+ (spam-enter-blacklist from))))
+ ;; the ham function
+ nil))
+
+(defun spam-whitelist-register-routine ()
+ (spam-generic-register-routine
+ ;; the spam function
+ nil
+ ;; the ham function
+ (lambda (article)
+ (let ((from (spam-fetch-field-from-fast article)))
+ (when (stringp from)
+ (spam-enter-whitelist from))))))
+
\f
-;;;; Training via Bogofilter. Last updated 2002-09-02.
-
-;;; See Paul Graham article, at `http://www.paulgraham.com/spam.html'.
-
-;;; This page is for those wanting to control spam with the help of Eric
-;;; Raymond's speedy Bogofilter, see http://www.tuxedo.org/~esr/bogofilter.
-;;; This has been tested with a locally patched copy of version 0.4.
-
-;;; Make sure Bogofilter is installed. Bogofilter internally uses Judy fast
-;;; associative arrays, so you need to install Judy first, and Bogofilter
-;;; next. Fetch both distributions by visiting the following links and
-;;; downloading the latest version of each:
-;;;
-;;; http://sourceforge.net/projects/judy/
-;;; http://www.tuxedo.org/~esr/bogofilter/
-;;;
-;;; Unpack the Judy distribution and enter its main directory. Then do:
-;;;
-;;; ./configure
-;;; make
-;;; make install
-;;;
-;;; You will likely need to become super-user for the last step. Then, unpack
-;;; the Bogofilter distribution and enter its main directory:
-;;;
-;;; make
-;;; make install
-;;;
-;;; Here as well, you need to become super-user for the last step. Now,
-;;; initialize your word lists by doing, under your own identity:
-;;;
-;;; mkdir ~/.bogofilter
-;;; touch ~/.bogofilter/badlist
-;;; touch ~/.bogofilter/goodlist
-;;;
-;;; These two files are text files you may edit, but you normally don't!
-
-;;; The `M-d' command gets added to Gnus summary mode, marking current article
-;;; as spam, showing it with the `H' mark. Whenever you see a spam article,
-;;; make sure to mark its summary line with `M-d' before leaving the group.
-;;; Some groups, as per variable `spam-junk-mailgroups' below, receive articles
-;;; from Gnus splitting on clues added by spam recognisers, so for these
-;;; groups, we tack an `H' mark at group entry for all summary lines which
-;;; would otherwise have no other mark. Make sure to _remove_ `H' marks for
-;;; any article which is _not_ genuine spam, before leaving such groups: you
-;;; may use `M-u' to "unread" the article, or `d' for declaring it read the
-;;; non-spam way. When you leave a group, all `H' marked articles, saved or
-;;; unsaved, are sent to Bogofilter which will study them as spam samples.
-
-;;; Messages may also be deleted in various other ways, and unless
-;;; `spam-ham-marks-form' gets overridden below, marks `R' and `r' for default
-;;; read or explicit delete, marks `X' and 'K' for automatic or explicit
-;;; kills, as well as mark `Y' for low scores, are all considered to be
-;;; associated with articles which are not spam. This assumption might be
-;;; false, in particular if you use kill files or score files as means for
-;;; detecting genuine spam, you should then adjust `spam-ham-marks-form'. When
-;;; you leave a group, all _unsaved_ articles bearing any the above marks are
-;;; sent to Bogofilter which will study these as not-spam samples. If you
-;;; explicit kill a lot, you might sometimes end up with articles marked `K'
-;;; which you never saw, and which might accidentally contain spam. Best is
-;;; to make sure that real spam is marked with `H', and nothing else.
-
-;;; All other marks do not contribute to Bogofilter pre-conditioning. In
-;;; particular, ticked, dormant or souped articles are likely to contribute
-;;; later, when they will get deleted for real, so there is no need to use
-;;; them prematurely. Explicitly expired articles do not contribute, command
-;;; `E' is a way to get rid of an article without Bogofilter ever seeing it.
-
-;;; In a word, with a minimum of care for associating the `H' mark for spam
-;;; articles only, Bogofilter training all gets fairly automatic. You should
-;;; do this until you get a few hundreds of articles in each category, spam
-;;; or not. The shell command `head -1 ~/.bogofilter/*' shows both article
-;;; counts. The command `S S' in summary mode, either for debugging or for
-;;; curiosity, triggers Bogofilter into displaying in another buffer the
-;;; "spamicity" score of the current article (between 0.0 and 1.0), together
-;;; with the article words which most significantly contribute to the score.
-
-;;; The real way for using Bogofilter, however, is to have some use tool like
-;;; `procmail' for invoking it on message reception, then adding some
-;;; recognisable header in case of detected spam. Gnus splitting rules might
-;;; later trip on these added headers and react by sorting such articles into
-;;; specific junk folders as per `spam-junk-mailgroups'. Here is a possible
-;;; `.procmailrc' contents (still untested -- please tell me how it goes):
-;;;
-;;; :0HBf:
-;;; * ? bogofilter
-;;; | formail -bfI "X-Spam-Status: Yes"
-
-(defvar spam-output-buffer-name "*Bogofilter Output*"
- "Name of buffer when displaying `bogofilter -v' output.")
-
-(defvar spam-spaminfo-header-regexp
- ;; FIXME! In the following regexp, we should explain which tool produces
- ;; which kind of header. I do not even remember them all by now. X-Junk
- ;; (and previously X-NoSpam) are produced by the `NoSpam' tool, which has
- ;; never been published, so it might not be reasonable leaving it in the
- ;; list.
- "^X-\\(jf\\|Junk\\|NoSpam\\|Spam\\|SB\\)[^:]*:"
- "Regexp for spam markups in headers.
-Markup from spam recognisers, as well as `Xref', are to be removed from
-articles before they get registered by Bogofilter.")
-
-(defvar spam-bogofilter-path (executable-find "bogofilter")
- "File path of the Bogofilter executable program.
-Force this variable to nil if you want to inhibit the functionality.")
-
-(defun spam-check-bogofilter ()
- ;; Dynamic spam check. I do not know how to check the exit status,
- ;; so instead, read `bogofilter -v' output.
- (when (and spam-use-bogofilter spam-bogofilter-path)
- (spam-bogofilter-articles nil "-v" (list (gnus-summary-article-number)))
- (when (save-excursion
- (set-buffer spam-output-buffer-name)
- (goto-char (point-min))
- (re-search-forward "Spamicity: \\(0\\.9\\|1\\.0\\)" nil t))
- spam-split-group)))
+;;;; Spam-report glue
+(defun spam-report-gmane-register-routine ()
+ (spam-generic-register-routine
+ 'spam-report-gmane
+ nil))
+\f
+;;;; Bogofilter
+(defun spam-check-bogofilter-headers (&optional score)
+ (let ((header (nnmail-fetch-field spam-bogofilter-header)))
+ (when header ; return nil when no header
+ (if score ; scoring mode
+ (if (string-match "spamicity=\\([0-9.]+\\)" header)
+ (match-string 1 header)
+ "0")
+ ;; spam detection mode
+ (when (string-match spam-bogofilter-bogosity-positive-spam-header
+ header)
+ spam-split-group)))))
+
+;; return something sensible if the score can't be determined
(defun spam-bogofilter-score ()
- "Use `bogofilter -v' on the current article.
-This yields the 15 most discriminant words for this article and the
-spamicity coefficient of each, and the overall article spamicity."
+ "Get the Bogofilter spamicity score"
+ (interactive)
+ (save-window-excursion
+ (gnus-summary-show-article t)
+ (set-buffer gnus-article-buffer)
+ (let ((score (or (spam-check-bogofilter-headers t)
+ (spam-check-bogofilter t))))
+ (message "Spamicity score %s" score)
+ (or score "0"))
+ (gnus-summary-show-article)))
+
+(defun spam-check-bogofilter (&optional score)
+ "Check the Bogofilter backend for the classification of this message"
+ (let ((article-buffer-name (buffer-name))
+ return)
+ (with-temp-buffer
+ (let ((temp-buffer-name (buffer-name)))
+ (save-excursion
+ (set-buffer article-buffer-name)
+ (if spam-bogofilter-database-directory
+ (call-process-region (point-min) (point-max)
+ spam-bogofilter-path
+ nil temp-buffer-name nil "-v"
+ "-d" spam-bogofilter-database-directory)
+ (call-process-region (point-min) (point-max) spam-bogofilter-path
+ nil temp-buffer-name nil "-v")))
+ (setq return (spam-check-bogofilter-headers score))))
+ return))
+
+(defun spam-bogofilter-register-with-bogofilter (article-string spam)
+ "Register an article, given as a string, as spam or non-spam."
+ (when (stringp article-string)
+ (let ((switch (if spam spam-bogofilter-spam-switch
+ spam-bogofilter-ham-switch)))
+ (with-temp-buffer
+ (insert article-string)
+ (if spam-bogofilter-database-directory
+ (call-process-region (point-min) (point-max)
+ spam-bogofilter-path
+ nil nil nil "-v" switch
+ "-d" spam-bogofilter-database-directory)
+ (call-process-region (point-min) (point-max) spam-bogofilter-path
+ nil nil nil "-v" switch))))))
+
+(defun spam-bogofilter-register-spam-routine ()
+ (spam-generic-register-routine
+ (lambda (article)
+ (spam-bogofilter-register-with-bogofilter
+ (spam-get-article-as-string article) t))
+ nil))
+
+(defun spam-bogofilter-register-ham-routine ()
+ (spam-generic-register-routine
+ nil
+ (lambda (article)
+ (spam-bogofilter-register-with-bogofilter
+ (spam-get-article-as-string article) nil))))
+
+\f
+;;;; spamoracle
+(defun spam-check-spamoracle ()
+ "Run spamoracle on an article to determine whether it's spam."
+ (let ((article-buffer-name (buffer-name)))
+ (with-temp-buffer
+ (let ((temp-buffer-name (buffer-name)))
+ (save-excursion
+ (set-buffer article-buffer-name)
+ (let ((status
+ (apply 'call-process-region
+ (point-min) (point-max)
+ spam-spamoracle-binary
+ nil temp-buffer-name nil
+ (if spam-spamoracle-database
+ `("-f" ,spam-spamoracle-database "mark")
+ '("mark")))))
+ (if (zerop status)
+ (progn
+ (set-buffer temp-buffer-name)
+ (goto-char (point-min))
+ (when (re-search-forward "^X-Spam: yes;" nil t)
+ spam-split-group))
+ (error "Error running spamoracle" status))))))))
+
+(defun spam-spamoracle-learn (article article-is-spam-p)
+ "Run spamoracle in training mode."
+ (with-temp-buffer
+ (let ((temp-buffer-name (buffer-name)))
+ (save-excursion
+ (goto-char (point-min))
+ (insert (spam-get-article-as-string article))
+ (let* ((arg (if article-is-spam-p "-spam" "-good"))
+ (status
+ (apply 'call-process-region
+ (point-min) (point-max)
+ spam-spamoracle-binary
+ nil temp-buffer-name nil
+ (if spam-spamoracle-database
+ `("-f" ,spam-spamoracle-database
+ "add" ,arg)
+ `("add" ,arg)))))
+ (when (not (zerop status))
+ (error "Error running spamoracle" status)))))))
+
+(defun spam-spamoracle-learn-ham ()
+ (spam-generic-register-routine
+ nil
+ (lambda (article)
+ (spam-spamoracle-learn article nil))))
+
+(defun spam-spamoracle-learn-spam ()
+ (spam-generic-register-routine
+ (lambda (article)
+ (spam-spamoracle-learn article t))
+ nil))
+\f
+;;;; Hooks
+
+;;;###autoload
+(defun spam-initialize ()
+ "Install the spam.el hooks and do other initialization"
+ (interactive)
+ (setq spam-install-hooks t)
+ ;; TODO: How do we redo this every time spam-face is customized?
+ (push '((eq mark gnus-spam-mark) . spam-face)
+ gnus-summary-highlight)
+ ;; Add hooks for loading and saving the spam stats
+ (when spam-use-stat
+ (add-hook 'gnus-save-newsrc-hook 'spam-maybe-spam-stat-save)
+ (add-hook 'gnus-get-top-new-news-hook 'spam-maybe-spam-stat-load)
+ (add-hook 'gnus-startup-hook 'spam-maybe-spam-stat-load))
+ (add-hook 'gnus-summary-prepare-exit-hook 'spam-summary-prepare-exit)
+ (add-hook 'gnus-summary-prepare-hook 'spam-summary-prepare)
+ (add-hook 'gnus-get-new-news-hook 'spam-setup-widening))
+
+(defun spam-unload-hook ()
+ "Uninstall the spam.el hooks"
(interactive)
- (when (and spam-use-bogofilter spam-bogofilter-path)
- (spam-bogofilter-articles nil "-v" (list (gnus-summary-article-number)))
- (with-current-buffer spam-output-buffer-name
- (unless (zerop (buffer-size))
- (if (<= (count-lines (point-min) (point-max)) 1)
- (progn
- (goto-char (point-max))
- (when (bolp)
- (backward-char 1))
- (message "%s" (buffer-substring (point-min) (point))))
- (goto-char (point-min))
- (display-buffer (current-buffer)))))))
-
-(defun spam-bogofilter-register-routine ()
- (when (and spam-use-bogofilter spam-bogofilter-path)
- (let ((articles gnus-newsgroup-articles)
- article mark ham-articles spam-articles)
- (while articles
- (setq article (pop articles)
- mark (gnus-summary-article-mark article))
- (cond ((memq mark spam-spam-marks) (push article spam-articles))
- ((memq article gnus-newsgroup-saved))
- ((memq mark spam-ham-marks) (push article ham-articles))))
- (when ham-articles
- (spam-bogofilter-articles "ham" "-n" ham-articles))
- (when spam-articles
- (spam-bogofilter-articles "SPAM" "-s" spam-articles)))))
-
-(defvar spam-bogofilter-initial-timeout 40
- "Timeout in seconds for the initial reply from the `bogofilter' program.")
-
-(defvar spam-bogofilter-subsequent-timeout 15
- "Timeout in seconds for any subsequent reply from the `bogofilter' program.")
-
-(defun spam-bogofilter-articles (type option articles)
- (let ((output-buffer (get-buffer-create spam-output-buffer-name))
- (article-copy (get-buffer-create " *Bogofilter Article Copy*"))
- (remove-regexp (concat spam-spaminfo-header-regexp "\\|Xref:"))
- (counter 0)
- prefix process article)
- (when type
- (setq prefix (format "Studying %d articles as %s..." (length articles)
- type))
- (message "%s" prefix))
- (save-excursion (set-buffer output-buffer) (erase-buffer))
- (setq process (start-process "bogofilter" output-buffer
- spam-bogofilter-path "-F" option))
- (process-kill-without-query process t)
- (unwind-protect
- (save-window-excursion
- (while articles
- (setq counter (1+ counter))
- (when prefix
- (message "%s %d" prefix counter))
- (setq article (pop articles))
- (gnus-summary-goto-subject article)
- (gnus-summary-show-article t)
- (gnus-eval-in-buffer-window article-copy
- (insert-buffer-substring gnus-original-article-buffer)
- ;; Remove spam classification redundant headers: they may induce
- ;; unwanted biases in later analysis.
- (message-remove-header remove-regexp t)
- ;; Bogofilter really wants From envelopes for counting articles.
- ;; Fake one at the beginning, make sure there will be no other.
- (goto-char (point-min))
- (if (looking-at "From ")
- (forward-line 1)
- (insert "From nobody " (current-time-string) "\n"))
- (let (case-fold-search)
- (while (re-search-forward "^From " nil t)
- (beginning-of-line)
- (insert ">")))
- (process-send-region process (point-min) (point-max))
- (erase-buffer))))
- ;; Sending the EOF is unwind-protected. This is to prevent lost copies
- ;; of `bogofilter', hung on reading their standard input, in case the
- ;; whole registering process gets interrupted by the user.
- (process-send-eof process))
- (kill-buffer article-copy)
- ;; Receive process output. It sadly seems that we still have to protect
- ;; ourselves against hung `bogofilter' processes.
- (let ((status (process-status process))
- (timeout (* 1000 spam-bogofilter-initial-timeout))
- (quanta 200)) ; also counted in milliseconds
- (while (and (not (eq status 'exit)) (> timeout 0))
- ;; `accept-process-output' timeout is counted in microseconds.
- (setq timeout (if (accept-process-output process 0 (* 1000 quanta))
- (* 1000 spam-bogofilter-subsequent-timeout)
- (- timeout quanta))
- status (process-status process)))
- (if (eq status 'exit)
- (when prefix
- (message "%s done!" prefix))
- ;; Sigh! The process did time out... Become brutal!
- (interrupt-process process)
- (message "%s %d INTERRUPTED! (Article %d, status %s)"
- (or prefix "Bogofilter process...")
- counter article status)
- ;; Give some time for user to read. Sitting redisplays but gives up
- ;; if input is pending. Sleeping does not give up, but it does not
- ;; redisplay either. Mix both: let's redisplay and not give up.
- (sit-for 1)
- (sleep-for 3)))))
+ (remove-hook 'gnus-save-newsrc-hook 'spam-maybe-spam-stat-save)
+ (remove-hook 'gnus-get-top-new-news-hook 'spam-maybe-spam-stat-load)
+ (remove-hook 'gnus-startup-hook 'spam-maybe-spam-stat-load)
+ (remove-hook 'gnus-summary-prepare-exit-hook 'spam-summary-prepare-exit)
+ (remove-hook 'gnus-summary-prepare-hook 'spam-summary-prepare)
+ (remove-hook 'gnus-get-new-news-hook 'spam-setup-widening))
+
+(when spam-install-hooks
+ (spam-initialize))
(provide 'spam)
projects / gnus / blobdiff