+;; TODO: spam scores, detection of spam in newsgroups, cross-server splitting, remote processing, training through files
+
;;; spam.el --- Identifying spam
;; Copyright (C) 2002, 2003 Free Software Foundation, Inc.
(require 'gnus-sum)
(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
+;;; for the definitions of group content classification and spam processors
+(require 'gnus)
+(require 'message) ;for the message-fetch-field functions
;; for nnimap-split-download-body-default
(eval-when-compile (require 'nnimap))
(eval-and-compile
(autoload 'spam-report-gmane "spam-report"))
+;; autoload gnus-registry
+(eval-and-compile
+ (autoload 'gnus-registry-group-count "gnus-registry")
+ (autoload 'gnus-registry-add-group "gnus-registry")
+ (autoload 'gnus-registry-store-extra-entry "gnus-registry")
+ (autoload 'gnus-registry-fetch-extra "gnus-registry"))
+
;; autoload query-dns
(eval-and-compile
(autoload 'query-dns "dns"))
(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
+When t, only ham and unclassified groups will have their spam moved
+to the spam-process-destination. When nil, 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-log-to-registry nil
+ "Whether spam/ham processing should be logged in the registry."
+ :type 'boolean
+ :group 'spam)
+
+(defcustom spam-split-symbolic-return nil
+ "Whether spam-split should work with symbols or group names."
+ :type 'boolean
+ :group 'spam)
+
+(defcustom spam-split-symbolic-return-positive nil
+ "Whether spam-split should ALWAYS work with symbols or group
+ names. Do not set this if you use spam-split in a fancy split
+ method."
+ :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
:type 'boolean
:group 'spam)
+(defcustom spam-disable-spam-split-during-ham-respool nil
+ "Whether spam-split should be ignored while resplitting ham in
+a process destination. This is useful to prevent ham from ending
+up in the same spam group after the resplit. Don't set this to t
+if you have spam-split as the last rule in your split
+configuration."
+ :type 'boolean
+ :group 'spam)
+
+(defcustom spam-autodetect-recheck-messages nil
+ "Should spam.el recheck all meessages when autodetecting?
+Normally this is nil, so only unseen messages will be checked."
+ :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.
:type 'boolean
:group 'spam)
+(defcustom spam-blacklist-ignored-regexes nil
+ "Regular expressions that the blacklist should ignore."
+ :type '(repeat (regexp :tag "Regular expression to ignore when blacklisting"))
+ :group 'spam)
+
(defcustom spam-use-whitelist nil
"Whether the whitelist should be used by spam-split."
:type 'boolean
: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-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 'spam
+ :type 'boolean)
+
(defcustom spam-split-group "spam"
"Group name where incoming spam should be put by spam-split."
:type 'string
:group 'spam)
-(defcustom spam-junk-mailgroups (cons spam-split-group '("mail.junk" "poste.pourriel"))
+;;; 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"))
(defcustom spam-blackhole-good-server-regex nil
"String matching IP addresses that should not be checked in the blackholes"
- :type 'regexp
+ :type '(radio (const nil)
+ (regexp :format "%t: %v\n" :size 0))
:group 'spam)
(defcustom spam-face 'gnus-splash-face
: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)
"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"))
+ (const :tag "Use the current group name"))
:group 'spam-ifile)
(defcustom spam-ifile-all-categories nil
:type 'string
:group 'spam-bogofilter)
+(defcustom spam-bogofilter-spam-strong-switch "-S"
+ "The switch that Bogofilter uses to unregister ham messages."
+ :type 'string
+ :group 'spam-bogofilter)
+
+(defcustom spam-bogofilter-ham-strong-switch "-N"
+ "The switch that Bogofilter uses to unregister spam 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
(defcustom spam-bogofilter-database-directory nil
"Directory path of the Bogofilter databases."
- :type '(choice (directory :tag "Location of the Bogofilter database directory")
+ :type '(choice (directory
+ :tag "Location of the Bogofilter database directory")
(const :tag "Use the default"))
- :group 'spam-ifile)
+ :group 'spam-bogofilter)
+
+(defgroup spam-spamoracle nil
+ "Spam spamoracle 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)
;;; Key bindings for spam control.
"Msx" gnus-summary-mark-as-spam
"\M-d" gnus-summary-mark-as-spam)
-;;; How to highlight a spam summary line.
+(defvar spam-old-ham-articles nil
+ "List of old ham articles, generated when a group is entered.")
-;; TODO: How do we redo this every time spam-face is customized?
+(defvar spam-old-spam-articles nil
+ "List of old spam articles, generated when a group is entered.")
-(push '((eq mark gnus-spam-mark) . spam-face)
- gnus-summary-highlight)
+(defvar spam-split-disabled nil
+ "If non-nil, spam-split is disabled, and always returns nil.")
+
+(defvar spam-split-last-successful-check nil
+ "spam-split will set this to nil or a spam-use-XYZ check if it
+ finds ham or spam.")
;; convenience functions
+(defun spam-xor (a b) ; logical exclusive or
+ (and (or a b) (not (and a b))))
+
(defun spam-group-ham-mark-p (group mark &optional spam)
(when (stringp group)
(let* ((marks (spam-group-ham-marks group spam))
(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)))
+ (gnus-parameter-spam-marks group)
+ (gnus-parameter-ham-marks group)))
(marks (car marks))
(marks (if (listp (car marks)) (car marks) marks)))
marks)))
(gnus-parameter-spam-contents group))
nil))
+(defvar spam-list-of-processors
+ '((gnus-group-spam-exit-processor-report-gmane spam spam-use-gmane)
+ (gnus-group-spam-exit-processor-bogofilter spam spam-use-bogofilter)
+ (gnus-group-spam-exit-processor-blacklist spam spam-use-blacklist)
+ (gnus-group-spam-exit-processor-ifile spam spam-use-ifile)
+ (gnus-group-spam-exit-processor-stat spam spam-use-stat)
+ (gnus-group-spam-exit-processor-spamoracle spam spam-use-spamoracle)
+ (gnus-group-ham-exit-processor-ifile ham spam-use-ifile)
+ (gnus-group-ham-exit-processor-bogofilter ham spam-use-bogofilter)
+ (gnus-group-ham-exit-processor-stat ham spam-use-stat)
+ (gnus-group-ham-exit-processor-whitelist ham spam-use-whitelist)
+ (gnus-group-ham-exit-processor-BBDB ham spam-use-BBDB)
+ (gnus-group-ham-exit-processor-copy ham spam-use-ham-copy)
+ (gnus-group-ham-exit-processor-spamoracle ham spam-use-spamoracle))
+ "The spam-list-of-processors list contains pairs associating a
+ham/spam exit processor variable with a classification and a
+spam-use-* variable.")
+
(defun spam-group-processor-p (group processor)
(if (and (stringp group)
(symbolp processor))
- (member processor (car (gnus-parameter-spam-process group)))
+ (or (member processor (nth 0 (gnus-parameter-spam-process group)))
+ (spam-group-processor-multiple-p
+ group
+ (cdr-safe (assoc processor spam-list-of-processors))))
nil))
+(defun spam-group-processor-multiple-p (group processor-info)
+ (let* ((classification (nth 0 processor-info))
+ (check (nth 1 processor-info))
+ (parameters (nth 0 (gnus-parameter-spam-process group)))
+ found)
+ (dolist (parameter parameters)
+ (when (and (null found)
+ (listp parameter)
+ (eq classification (nth 0 parameter))
+ (eq check (nth 1 parameter)))
+ (setq found t)))
+ found))
+
(defun spam-group-spam-processor-report-gmane-p (group)
(spam-group-processor-p group 'gnus-group-spam-exit-processor-report-gmane))
(defun spam-group-ham-processor-ifile-p (group)
(spam-group-processor-p group 'gnus-group-ham-exit-processor-ifile))
+(defun spam-group-spam-processor-spamoracle-p (group)
+ (spam-group-processor-p group 'gnus-group-spam-exit-processor-spamoracle))
+
(defun spam-group-ham-processor-bogofilter-p (group)
(spam-group-processor-p group 'gnus-group-ham-exit-processor-bogofilter))
(defun spam-group-ham-processor-copy-p (group)
(spam-group-processor-p group 'gnus-group-ham-exit-processor-copy))
+(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 ()
+ (setq spam-old-ham-articles
+ (spam-list-articles gnus-newsgroup-articles 'ham))
+ (setq spam-old-spam-articles
+ (spam-list-articles gnus-newsgroup-articles 'spam))
(spam-mark-junk-as-spam-routine))
-(add-hook 'gnus-summary-prepare-hook 'spam-summary-prepare)
-
;; The spam processors are invoked for any group, spam or ham or neither
(defun 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-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))
+ ;; first of all, unregister any articles that are no longer ham or spam
+ ;; we have to iterate over the processors, or else we'll be too slow
+ (dolist (classification '(spam ham))
+ (let* ((old-articles (if (eq classification 'spam)
+ spam-old-spam-articles
+ spam-old-ham-articles))
+ (new-articles (spam-list-articles
+ gnus-newsgroup-articles
+ classification))
+ (changed-articles (gnus-set-difference old-articles new-articles)))
+ ;; now that we have the changed articles, we go through the processors
+ (dolist (processor-param spam-list-of-processors)
+ (let ((processor (nth 0 processor-param))
+ (processor-classification (nth 1 processor-param))
+ (check (nth 2 processor-param))
+ unregister-list)
+ (dolist (article changed-articles)
+ (let ((id (spam-fetch-field-message-id-fast article)))
+ (when (spam-log-unregistration-needed-p
+ id 'process classification check)
+ (push article unregister-list))))
+ ;; call spam-register-routine with specific articles to unregister,
+ ;; when there are articles to unregister and the check is enabled
+ (when (and unregister-list (symbol-value check))
+ (spam-register-routine classification check t unregister-list))))))
+
+ ;; find all the spam processors applicable to this group
+ (dolist (processor-param spam-list-of-processors)
+ (let ((processor (nth 0 processor-param))
+ (classification (nth 1 processor-param))
+ (check (nth 2 processor-param)))
+ (when (and (eq 'spam classification)
+ (spam-group-processor-p gnus-newsgroup-name processor))
+ (spam-register-routine classification check))))
(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)
+ (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)))
(gnus-message 5 "Marking spam as expired without moving it")
(spam-mark-spam-as-expired-and-move-routine nil)
- (when (spam-group-ham-contents-p gnus-newsgroup-name)
- (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 (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)
+ ;; find all the ham processors applicable to this group
+ (dolist (processor-param spam-list-of-processors)
+ (let ((processor (nth 0 processor-param))
+ (classification (nth 1 processor-param))
+ (check (nth 2 processor-param)))
+ (when (and (eq 'ham classification)
+ (spam-group-processor-p gnus-newsgroup-name processor))
+ (spam-register-routine classification check)))))
(when (spam-group-ham-processor-copy-p gnus-newsgroup-name)
(gnus-message 5 "Copying ham")
- (spam-ham-move-routine
- (gnus-parameter-ham-process-destination gnus-newsgroup-name) t))
+ (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)))))
+ (gnus-parameter-ham-process-destination gnus-newsgroup-name))))
-(add-hook 'gnus-summary-prepare-exit-hook 'spam-summary-prepare-exit)
+ (setq spam-old-ham-articles nil)
+ (setq spam-old-spam-articles nil))
(defun spam-mark-junk-as-spam-routine ()
;; check the global list of group names spam-junk-mailgroups and the
(dolist (article articles)
(gnus-summary-mark-article article gnus-spam-mark)))))
-(defun spam-mark-spam-as-expired-and-move-routine (&optional group)
+(defun spam-mark-spam-as-expired-and-move-routine (&rest groups)
+ (if (and (car-safe groups) (listp (car-safe groups)))
+ (apply 'spam-mark-spam-as-expired-and-move-routine (car groups))
+ (gnus-summary-kill-process-mark)
+ (let ((articles gnus-newsgroup-articles)
+ (backend-supports-deletions
+ (gnus-check-backend-function
+ 'request-move-article gnus-newsgroup-name))
+ article tomove deletep)
+ (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
+ (if (or (not backend-supports-deletions)
+ (> (length groups) 1))
+ (progn
+ (gnus-summary-copy-article nil group)
+ (setq deletep t))
+ (gnus-summary-move-article nil group)))))
+
+ ;; now delete the articles, if there was a copy done, and the
+ ;; backend allows it
+ (when (and deletep backend-supports-deletions)
+ (dolist (article tomove)
+ (gnus-summary-set-process-mark article))
+ (when tomove
+ (let ((gnus-novice-user nil)) ; don't ask me if I'm sure
+ (gnus-summary-delete-article nil))))
+
+ (gnus-summary-yank-process-mark))))
+
+(defun spam-ham-copy-or-move-routine (copy groups)
(gnus-summary-kill-process-mark)
(let ((articles gnus-newsgroup-articles)
- article tomove)
+ (backend-supports-deletions
+ (gnus-check-backend-function
+ 'request-move-article gnus-newsgroup-name))
+ (respool-method (gnus-find-method-for-group gnus-newsgroup-name))
+ article mark todo deletep respool)
(dolist (article articles)
- (when (eq (gnus-summary-article-mark article) gnus-spam-mark)
- (gnus-summary-mark-article article gnus-expirable-mark)
- (push article tomove)))
+ (when (spam-group-ham-mark-p gnus-newsgroup-name
+ (gnus-summary-article-mark article))
+ (push article todo)))
- ;; now do the actual move
- (when (and tomove
- (stringp group))
- (dolist (article tomove)
- (gnus-summary-set-process-mark article))
- (when tomove (gnus-summary-move-article nil group))))
- (gnus-summary-yank-process-mark))
-
-(defun spam-ham-move-routine (&optional group copy)
- (gnus-summary-kill-process-mark)
- (let ((articles gnus-newsgroup-articles)
- article mark tomove)
- (when (stringp group) ; this routine will do nothing
- ; without a valid group
- (dolist (article articles)
- (when (spam-group-ham-mark-p gnus-newsgroup-name
- (gnus-summary-article-mark article))
- (push article tomove)))
+ (when (member 'respool groups)
+ (setq respool t) ; boolean for later
+ (setq groups '("fake"))) ; when respooling, groups are dynamic so fake it
- ;; now do the actual move
- (when tomove
- (dolist (article tomove)
+ ;; now do the actual move
+ (dolist (group groups)
+ (when (and todo (stringp group))
+ (dolist (article todo)
(when spam-mark-ham-unread-before-move-from-spam-group
- (gnus-summary-mark-article article gnus-unread-mark))
+ (gnus-summary-mark-article article gnus-unread-mark))
(gnus-summary-set-process-mark article))
- (if copy
- (gnus-summary-copy-article nil group)
- (gnus-summary-move-article nil group)))))
+
+ (if respool ; respooling is with a "fake" group
+ (let ((spam-split-disabled
+ (or spam-split-disabled
+ spam-disable-spam-split-during-ham-respool)))
+ (gnus-summary-respool-article nil respool-method))
+ (if (or (not backend-supports-deletions) ; else, we are not respooling
+ (> (length groups) 1))
+ (progn ; if copying, copy and set deletep
+ (gnus-summary-copy-article nil group)
+ (setq deletep t))
+ (gnus-summary-move-article nil group))))) ; else move articles
+
+ ;; now delete the articles, unless a) copy is t, and there was a copy done
+ ;; b) a move was done to a single group
+ ;; c) backend-supports-deletions is nil
+ (unless copy
+ (when (and deletep backend-supports-deletions)
+ (dolist (article todo)
+ (gnus-summary-set-process-mark article))
+ (when todo
+ (let ((gnus-novice-user nil)) ; don't ask me if I'm sure
+ (gnus-summary-delete-article nil))))))
+
(gnus-summary-yank-process-mark))
-(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
-
+(defun spam-ham-copy-routine (&rest groups)
+ (if (and (car-safe groups) (listp (car-safe groups)))
+ (apply 'spam-ham-copy-routine (car groups))
+ (spam-ham-copy-or-move-routine t groups)))
+
+(defun spam-ham-move-routine (&rest groups)
+ (if (and (car-safe groups) (listp (car-safe groups)))
+ (apply 'spam-ham-move-routine (car groups))
+ (spam-ham-copy-or-move-routine nil groups)))
+
(eval-and-compile
(defalias 'spam-point-at-eol (if (fboundp 'point-at-eol)
'point-at-eol
(defun spam-get-article-as-string (article)
(let ((article-buffer (spam-get-article-as-buffer article))
- article-string)
+ article-string)
(when article-buffer
(save-window-excursion
(set-buffer article-buffer)
(setq article-string (buffer-string))))
- article-string))
+ article-string))
(defun spam-get-article-as-buffer (article)
(let ((article-buffer))
;; (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)))
+;; (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)))
"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))))
+ (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"
+ "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))))
+ (mail-header-subject
+ (gnus-data-header (assoc article (gnus-data-list nil))))
+ nil))
+
+(defun spam-fetch-field-message-id-fast (article)
+ "Fetch the `Message-ID' field quickly, using the internal
+ gnus-data-list function"
+ (if (and (numberp article)
+ (assoc article (gnus-data-list nil)))
+ (mail-header-message-id
+ (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-regex-headers . spam-check-regex-headers)
- (spam-use-whitelist . spam-check-whitelist)
- (spam-use-BBDB . spam-check-BBDB)
- (spam-use-ifile . spam-check-ifile)
- (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
-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
+ '((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 message is definitely not
+spam, and that further spam checks should be inhibited.
+Otherwise, a mailgroup name or the symbol 'spam (depending on
+spam-split-symbolic-return) 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.")
-(defvar spam-list-of-statistical-checks
- '(spam-use-ifile spam-use-stat spam-use-bogofilter)
-"The spam-list-of-statistical-checks list contains all the mail
+(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 check if invoked without specifics
(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). It can take checks as parameters.
+This function can be used as an entry in `nnmail-split-fancy',
+for example like this: (: spam-split). It can take checks as
+parameters. A string as a parameter will set the
+spam-split-group to that string.
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)))))
+ (setq spam-split-last-successful-check nil)
+ (unless spam-split-disabled
+ (let ((spam-split-group-choice spam-split-group))
+ (dolist (check specific-checks)
+ (when (stringp check)
+ (setq spam-split-group-choice check)
+ (setq specific-checks (delq check specific-checks))))
+
+ (let ((spam-split-group spam-split-group-choice))
+ (save-excursion
+ (save-restriction
+ (dolist (check spam-list-of-statistical-checks)
+ (when (and (symbolp check) (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 we got a decision at all, save the current check
+ (when decision
+ (setq spam-split-last-successful-check (car pair)))
+
+ (when (eq decision 'spam)
+ (if spam-split-symbolic-return
+ (setq decision spam-split-group)
+ (gnus-error
+ 5
+ (format "spam-split got %s but %s is nil"
+ (symbol-name decision)
+ (symbol-name spam-split-symbolic-return))))))))
+ (if (eq decision t)
+ (if spam-split-symbolic-return-positive 'ham nil)
+ decision))))))))
+
+(defun spam-find-spam ()
+ "This function will detect spam in the current newsgroup using spam-split"
+ (interactive)
+ (let* ((group gnus-newsgroup-name)
+ (autodetect (gnus-parameter-spam-autodetect group))
+ (methods (gnus-parameter-spam-autodetect-methods group))
+ (first-method (nth 0 methods)))
+ (when (and autodetect
+ (not (equal first-method 'none)))
+ (mapcar
+ (lambda (article)
+ (let ((id (spam-fetch-field-message-id-fast article))
+ (subject (spam-fetch-field-subject-fast article))
+ (sender (spam-fetch-field-from-fast article)))
+ (unless (and spam-log-to-registry
+ (spam-log-registered-p id 'incoming))
+ (let* ((spam-split-symbolic-return t)
+ (spam-split-symbolic-return-positive t)
+ (split-return
+ (with-temp-buffer
+ (gnus-request-article-this-buffer
+ article
+ group)
+ (if (or (null first-method)
+ (equal first-method 'default))
+ (spam-split)
+ (apply 'spam-split methods)))))
+ (if (equal split-return 'spam)
+ (gnus-summary-mark-article article gnus-spam-mark))
+
+ (when (and split-return spam-log-to-registry)
+ (when (zerop (gnus-registry-group-count id))
+ (gnus-registry-add-group
+ id group subject sender))
+
+ (spam-log-processing-to-registry
+ id
+ 'incoming
+ split-return
+ spam-split-last-successful-check
+ group))))))
+ (if spam-autodetect-recheck-messages
+ gnus-newsgroup-articles
+ gnus-newsgroup-unseen)))))
+
+(defvar spam-registration-functions
+ ;; first the ham register, second the spam register function
+ ;; third the ham unregister, fourth the spam unregister function
+ '((spam-use-blacklist nil
+ spam-blacklist-register-routine
+ nil
+ spam-blacklist-unregister-routine)
+ (spam-use-whitelist spam-whitelist-register-routine
+ nil
+ spam-whitelist-unregister-routine
+ nil)
+ (spam-use-BBDB spam-BBDB-register-routine
+ nil
+ spam-BBDB-unregister-routine
+ nil)
+ (spam-use-ifile spam-ifile-register-ham-routine
+ spam-ifile-register-spam-routine
+ spam-ifile-unregister-ham-routine
+ spam-ifile-unregister-spam-routine)
+ (spam-use-spamoracle spam-spamoracle-learn-ham
+ spam-spamoracle-learn-spam
+ spam-spamoracle-unlearn-ham
+ spam-spamoracle-unlearn-spam)
+ (spam-use-stat spam-stat-register-ham-routine
+ spam-stat-register-spam-routine
+ spam-stat-unregister-ham-routine
+ spam-stat-unregister-spam-routine)
+ ;; note that spam-use-gmane is not a legitimate check
+ (spam-use-gmane nil
+ spam-report-gmane-register-routine
+ ;; does Gmane support unregistration?
+ nil
+ nil)
+ (spam-use-bogofilter spam-bogofilter-register-ham-routine
+ spam-bogofilter-register-spam-routine
+ spam-bogofilter-unregister-ham-routine
+ spam-bogofilter-unregister-spam-routine))
+ "The spam-registration-functions list contains pairs
+associating a parameter variable with the ham and spam
+registration functions, and the ham and spam unregistration
+functions")
+
+(defun spam-classification-valid-p (classification)
+ (or (eq classification 'spam)
+ (eq classification 'ham)))
+
+(defun spam-process-type-valid-p (process-type)
+ (or (eq process-type 'incoming)
+ (eq process-type 'process)))
+
+(defun spam-registration-check-valid-p (check)
+ (assoc check spam-registration-functions))
+
+(defun spam-unregistration-check-valid-p (check)
+ (assoc check spam-registration-functions))
+
+(defun spam-registration-function (classification check)
+ (let ((flist (cdr-safe (assoc check spam-registration-functions))))
+ (if (eq classification 'spam)
+ (nth 1 flist)
+ (nth 0 flist))))
+
+(defun spam-unregistration-function (classification check)
+ (let ((flist (cdr-safe (assoc check spam-registration-functions))))
+ (if (eq classification 'spam)
+ (nth 3 flist)
+ (nth 2 flist))))
+
+(defun spam-list-articles (articles classification)
+ (let ((mark-check (if (eq classification 'spam)
+ 'spam-group-spam-mark-p
+ 'spam-group-ham-mark-p))
+ mark list)
+ (dolist (article articles)
+ (when (funcall mark-check
+ gnus-newsgroup-name
+ (gnus-summary-article-mark article))
+ (push article list)))
+ list))
+
+(defun spam-register-routine (classification
+ check
+ &optional unregister
+ specific-articles)
+ (when (and (spam-classification-valid-p classification)
+ (spam-registration-check-valid-p check))
+ (let* ((register-function
+ (spam-registration-function classification check))
+ (unregister-function
+ (spam-unregistration-function classification check))
+ (run-function (if unregister
+ unregister-function
+ register-function))
+ (log-function (if unregister
+ 'spam-log-undo-registration
+ 'spam-log-processing-to-registry))
+ article articles)
+
+ (when run-function
+ ;; make list of articles, using specific-articles if given
+ (setq articles (or specific-articles
+ (spam-list-articles
+ gnus-newsgroup-articles
+ classification)))
+ ;; process them
+ (gnus-message 5 "%s %d %s articles with classification %s, check %s"
+ (if unregister "Unregistering" "Registering")
+ (length articles)
+ (if specific-articles "specific" "")
+ (symbol-name classification)
+ (symbol-name check))
+ (funcall run-function articles)
+ ;; now log all the registrations (or undo them, depending on unregister)
+ (dolist (article articles)
+ (funcall log-function
+ (spam-fetch-field-message-id-fast article)
+ 'process
+ classification
+ check
+ gnus-newsgroup-name))))))
+
+;;; log a ham- or spam-processor invocation to the registry
+(defun spam-log-processing-to-registry (id type classification check group)
+ (when spam-log-to-registry
+ (if (and (stringp id)
+ (stringp group)
+ (spam-process-type-valid-p type)
+ (spam-classification-valid-p classification)
+ (spam-registration-check-valid-p check))
+ (let ((cell-list (cdr-safe (gnus-registry-fetch-extra id type)))
+ (cell (list classification check group)))
+ (push cell cell-list)
+ (gnus-registry-store-extra-entry
+ id
+ type
+ cell-list))
+
+ (gnus-message 5 (format "%s called with bad ID, type, classification, check, or group"
+ "spam-log-processing-to-registry")))))
+
+;;; check if a ham- or spam-processor registration has been done
+(defun spam-log-registered-p (id type)
+ (when spam-log-to-registry
+ (if (and (stringp id)
+ (spam-process-type-valid-p type))
+ (cdr-safe (gnus-registry-fetch-extra id type))
+ (progn
+ (gnus-message 5 (format "%s called with bad ID, type, classification, or check"
+ "spam-log-registered-p"))
+ nil))))
+
+;;; check if a ham- or spam-processor registration needs to be undone
+(defun spam-log-unregistration-needed-p (id type classification check)
+ (when spam-log-to-registry
+ (if (and (stringp id)
+ (spam-process-type-valid-p type)
+ (spam-classification-valid-p classification)
+ (spam-registration-check-valid-p check))
+ (let ((cell-list (cdr-safe (gnus-registry-fetch-extra id type)))
+ found)
+ (dolist (cell cell-list)
+ (unless found
+ (when (and (eq classification (nth 0 cell))
+ (eq check (nth 1 cell)))
+ (setq found t))))
+ found)
+ (progn
+ (gnus-message 5 (format "%s called with bad ID, type, classification, or check"
+ "spam-log-unregistration-needed-p"))
+ nil))))
+
+
+;;; undo a ham- or spam-processor registration (the group is not used)
+(defun spam-log-undo-registration (id type classification check &optional group)
+ (when (and spam-log-to-registry
+ (spam-log-unregistration-needed-p id type classification check))
+ (if (and (stringp id)
+ (spam-process-type-valid-p type)
+ (spam-classification-valid-p classification)
+ (spam-registration-check-valid-p check))
+ (let ((cell-list (cdr-safe (gnus-registry-fetch-extra id type)))
+ new-cell-list found)
+ (dolist (cell cell-list)
+ (unless (and (eq classification (nth 0 cell))
+ (eq check (nth 1 cell)))
+ (push cell new-cell-list)))
+ (gnus-registry-store-extra-entry
+ id
+ type
+ new-cell-list))
+ (progn
+ (gnus-message 5 (format "%s called with bad ID, type, check, or group"
+ "spam-log-undo-registration"))
+ nil))))
+
+;;; set up IMAP widening if it's necessary
(defun spam-setup-widening ()
(dolist (check spam-list-of-statistical-checks)
(when (symbol-value check)
(setq nnimap-split-download-body-default t))))
-(add-hook 'gnus-get-new-news-hook 'spam-setup-widening)
+\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 ()
- (let (ret found)
+(defun spam-check-regex-headers (&optional body)
+ (let ((type (if body "body" "header"))
+ (spam-split-group (if spam-split-symbolic-return
+ 'spam
+ spam-split-group))
+ 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 header search positive.")
+ (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 header search positive." (match-string 1))
+ (message "Spam regex %s search positive." type)
(setq found t)
(setq ret spam-split-group))))
ret))
\f
;;;; Blackholes.
+(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"))
+ (spam-split-group (if spam-split-symbolic-return
+ 'spam
+ spam-split-group))
ips matches)
(when headers
(with-temp-buffer
(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)
+ "\\([0-9]+\\.[0-9]+\\.[0-9]+\\.[0-9]+\\)" nil t)
(gnus-message 9 "Blackhole search found host IP %s." (match-string 1))
- (push (mapconcat 'identity
- (nreverse (split-string (match-string 1) "\\."))
- ".")
+ (push (spam-reverse-ip-string (match-string 1))
ips)))
(dolist (server spam-blackhole-servers)
(dolist (ip ips)
(unless (and spam-blackhole-good-server-regex
- (string-match spam-blackhole-good-server-regex ip))
- (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))))))))
+ ;; 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
(defun spam-check-hashcash ()
"Check the headers for hashcash payments."
- (mail-check-payment))) ;mail-check-payment returns a boolean
+ (mail-check-payment))) ;mail-check-payment returns a boolean
(file-error (progn
(defalias 'mail-check-payment 'ignore)
(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 (message-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))))))
+ (defun spam-enter-ham-BBDB (addresses &optional remove)
+ "Enter an address into the BBDB; implies ham (non-spam) sender"
+ (dolist (from addresses)
+ (when (stringp from)
+ (let* ((parsed-address (gnus-extract-address-components from))
+ (name (or (nth 0 parsed-address) "Ham Sender"))
+ (remove-function (if remove
+ 'bbdb-delete-record-internal
+ 'ignore))
+ (net-address (nth 1 parsed-address))
+ (record (and net-address
+ (bbdb-search-simple nil net-address))))
+ (when net-address
+ (gnus-message 5 "%s address %s %s BBDB"
+ (if remove "Deleting" "Adding")
+ from
+ (if remove "from" "to"))
+ (if record
+ (funcall remove-function record)
+ (bbdb-create-internal name nil net-address nil nil
+ "ham sender added by spam.el")))))))
+
+ (defun spam-BBDB-register-routine (articles &optional unregister)
+ (let (addresses)
+ (dolist (article articles)
+ (when (stringp (spam-fetch-field-from-fast article))
+ (push (spam-fetch-field-from-fast article) addresses)))
+ ;; now do the register/unregister action
+ (spam-enter-ham-BBDB addresses unregister)))
+
+ (defun spam-BBDB-unregister-routine (articles)
+ (spam-BBDB-register-routine articles t))
+
+ (defun spam-check-BBDB ()
+ "Mail from people in the BBDB is classified as ham or non-spam"
+ (let ((who (nnmail-fetch-field "from"))
+ (spam-split-group (if spam-split-symbolic-return
+ 'spam
+ spam-split-group)))
+ (when who
+ (setq who (nth 1 (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-BBDB-register-routine 'ignore)
(defalias 'spam-enter-ham-BBDB 'ignore)
(defalias 'bbdb-create-internal 'ignore)
+ (defalias 'bbdb-delete-record-internal 'ignore)
(defalias 'bbdb-records 'ignore))))
\f
;;; as spam
(defun spam-get-ifile-database-parameter ()
- "Get the command-line parameter for ifile's database from spam-ifile-database-path."
+ "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))
+ (spam-split-group (if spam-split-symbolic-return
+ 'spam
+ spam-split-group))
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")))
+ (apply 'call-process-region
+ (point-min) (point-max) spam-ifile-path
+ nil temp-buffer-name nil "-c"
+ (if db-param `(,db-param "-q") `("-q"))))
+ ;; check the return now (we're back in the temp buffer)
(goto-char (point-min))
(if (not (eobp))
(setq category (buffer-substring (point) (spam-point-at-eol))))
(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))))))
+ (setq return spam-split-group)))))) ; note return is nil otherwise
return))
-(defun spam-ifile-register-with-ifile (article-string category)
+(defun spam-ifile-register-with-ifile (articles category &optional unregister)
"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))))
+ (let ((category (or category gnus-newsgroup-name))
+ (add-or-delete-option (if unregister "-d" "-i"))
+ (db (spam-get-ifile-database-parameter))
+ parameters)
+ (with-temp-buffer
+ (dolist (article articles)
+ (let ((article-string (spam-get-article-as-string article)))
+ (when (stringp article-string)
+ (insert article-string))))
+ (apply 'call-process-region
+ (point-min) (point-max) spam-ifile-path
+ nil nil nil
+ add-or-delete-option category
+ (if db `(,db "-h") `("-h"))))))
+
+(defun spam-ifile-register-spam-routine (articles &optional unregister)
+ (spam-ifile-register-with-ifile articles spam-ifile-spam-category unregister))
+
+(defun spam-ifile-unregister-spam-routine (articles)
+ (spam-ifile-register-spam-routine articles t))
+
+(defun spam-ifile-register-ham-routine (articles &optional unregister)
+ (spam-ifile-register-with-ifile articles spam-ifile-ham-category unregister))
+
+(defun spam-ifile-unregister-ham-routine (articles)
+ (spam-ifile-register-ham-routine articles t))
\f
;;;; 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
+ (let ((spam-split-group (if spam-split-symbolic-return
+ 'spam
+ spam-split-group))
+ (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-stat-register-spam-routine (articles &optional unregister)
+ (dolist (article articles)
+ (let ((article-string (spam-get-article-as-string article)))
+ (with-temp-buffer
+ (insert article-string)
+ (if unregister
+ (spam-stat-buffer-change-to-non-spam)
+ (spam-stat-buffer-is-spam))))))
+
+ (defun spam-stat-unregister-spam-routine (articles)
+ (spam-stat-register-spam-routine articles t))
+
+ (defun spam-stat-register-ham-routine (articles &optional unregister)
+ (dolist (article articles)
+ (let ((article-string (spam-get-article-as-string article)))
+ (with-temp-buffer
+ (insert article-string)
+ (if unregister
+ (spam-stat-buffer-change-to-spam)
+ (spam-stat-buffer-is-non-spam))))))
+
+ (defun spam-stat-unregister-ham-routine (articles)
+ (spam-stat-register-ham-routine articles t))
(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)))
-
- ;; Add hooks for loading and saving the spam stats
- (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))
+ (when spam-use-stat (spam-stat-save))))
(file-error (progn
+ (defalias 'spam-stat-load 'ignore)
+ (defalias 'spam-stat-save 'ignore)
+ (defalias 'spam-maybe-spam-stat-load 'ignore)
+ (defalias 'spam-maybe-spam-stat-save 'ignore)
(defalias 'spam-stat-register-ham-routine 'ignore)
+ (defalias 'spam-stat-unregister-ham-routine 'ignore)
(defalias 'spam-stat-register-spam-routine 'ignore)
+ (defalias 'spam-stat-unregister-spam-routine 'ignore)
(defalias 'spam-stat-buffer-is-spam 'ignore)
+ (defalias 'spam-stat-buffer-change-to-spam 'ignore)
(defalias 'spam-stat-buffer-is-non-spam 'ignore)
+ (defalias 'spam-stat-buffer-change-to-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
(defvar spam-whitelist-cache nil)
(defvar spam-blacklist-cache nil)
-(defun spam-enter-whitelist (address)
- "Enter ADDRESS into the whitelist."
+(defun spam-kill-whole-line ()
+ (beginning-of-line)
+ (let ((kill-whole-line t))
+ (kill-line)))
+
+;;; address can be a list, too
+(defun spam-enter-whitelist (address &optional remove)
+ "Enter ADDRESS (list or single) into the whitelist. With a
+ non-nil REMOVE, remove them."
(interactive "sAddress: ")
- (spam-enter-list address spam-whitelist)
+ (spam-enter-list address spam-whitelist remove)
(setq spam-whitelist-cache nil))
-(defun spam-enter-blacklist (address)
- "Enter ADDRESS into the blacklist."
+;;; address can be a list, too
+(defun spam-enter-blacklist (address &optional remove)
+ "Enter ADDRESS (list or single) into the blacklist. With a
+ non-nil REMOVE, remove them."
(interactive "sAddress: ")
- (spam-enter-list address spam-blacklist)
+ (spam-enter-list address spam-blacklist remove)
(setq spam-blacklist-cache nil))
-(defun spam-enter-list (address file)
- "Enter ADDRESS into the given FILE, either the whitelist or the blacklist."
- (unless (file-exists-p (file-name-directory file))
- (make-directory (file-name-directory file) t))
- (save-excursion
- (set-buffer
- (find-file-noselect file))
- (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-enter-list (addresses file &optional remove)
+ "Enter ADDRESSES into the given FILE.
+Either the whitelist or the blacklist files can be used. With
+REMOVE not nil, remove the ADDRESSES."
+ (if (stringp addresses)
+ (spam-enter-list (list addresses) file remove)
+ ;; else, we have a list of addresses here
+ (unless (file-exists-p (file-name-directory file))
+ (make-directory (file-name-directory file) t))
+ (save-excursion
+ (set-buffer
+ (find-file-noselect file))
+ (dolist (a addresses)
+ (when (stringp a)
+ (goto-char (point-min))
+ (if (re-search-forward (regexp-quote a) nil t)
+ ;; found the address
+ (when remove
+ (spam-kill-whole-line))
+ ;; else, the address was not found
+ (unless remove
+ (goto-char (point-max))
+ (unless (bobp)
+ (insert "\n"))
+ (insert a "\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)
- t
- (if spam-use-whitelist-exclusive
- spam-split-group
- nil)))
+ (let ((spam-split-group (if spam-split-symbolic-return
+ 'spam
+ spam-split-group)))
+ (unless spam-whitelist-cache
+ (setq spam-whitelist-cache (spam-parse-list spam-whitelist)))
+ (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?
- (unless spam-blacklist-cache
- (setq spam-blacklist-cache (spam-parse-list spam-blacklist)))
- (and (spam-from-listed-p spam-blacklist-cache) spam-split-group))
+ (let ((spam-split-group (if spam-split-symbolic-return
+ 'spam
+ spam-split-group)))
+ (unless spam-blacklist-cache
+ (setq spam-blacklist-cache (spam-parse-list spam-blacklist)))
+ (and (spam-from-listed-p spam-blacklist-cache) spam-split-group)))
(defun spam-parse-list (file)
(when (file-readable-p file)
(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 (nth 1 (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))))))
+(defun spam-filelist-register-routine (articles blacklist &optional unregister)
+ (let ((de-symbol (if blacklist 'spam-use-whitelist 'spam-use-blacklist))
+ (declassification (if blacklist 'ham 'spam))
+ (enter-function
+ (if blacklist 'spam-enter-blacklist 'spam-enter-whitelist))
+ (remove-function
+ (if blacklist 'spam-enter-whitelist 'spam-enter-blacklist))
+ from addresses unregister-list)
+ (dolist (article articles)
+ (let ((from (spam-fetch-field-from-fast article))
+ (id (spam-fetch-field-message-id-fast article))
+ sender-ignored)
+ (when (stringp from)
+ (dolist (ignore-regex spam-blacklist-ignored-regexes)
+ (when (and (not sender-ignored)
+ (stringp ignore-regex)
+ (string-match ignore-regex from))
+ (setq sender-ignored t)))
+ ;; remember the messages we need to unregister, unless remove is set
+ (when (and
+ (null unregister)
+ (spam-log-unregistration-needed-p
+ id 'process declassification de-symbol))
+ (push from unregister-list))
+ (unless sender-ignored
+ (push from addresses)))))
+
+ (if unregister
+ (funcall enter-function addresses t) ; unregister all these addresses
+ ;; else, register normally and unregister what we need to
+ (funcall remove-function unregister-list t)
+ (dolist (article unregister-list)
+ (spam-log-undo-registration
+ (spam-fetch-field-message-id-fast article)
+ 'process
+ declassification
+ de-symbol))
+ (funcall enter-function addresses nil))))
+
+(defun spam-blacklist-unregister-routine (articles)
+ (spam-blacklist-register-routine articles t))
+
+(defun spam-blacklist-register-routine (articles &optional unregister)
+ (spam-filelist-register-routine articles t unregister))
+
+(defun spam-whitelist-unregister-routine (articles)
+ (spam-whitelist-register-routine articles t))
+
+(defun spam-whitelist-register-routine (articles &optional unregister)
+ (spam-filelist-register-routine articles nil unregister))
\f
;;;; Spam-report glue
-(defun spam-report-gmane-register-routine ()
- (spam-generic-register-routine
- 'spam-report-gmane
- nil))
+(defun spam-report-gmane-register-routine (articles)
+ (when articles
+ (apply 'spam-report-gmane articles)))
\f
;;;; Bogofilter
(defun spam-check-bogofilter-headers (&optional score)
- (let ((header (message-fetch-field spam-bogofilter-header)))
- (when (and header
- (string-match spam-bogofilter-bogosity-positive-spam-header
- header))
- (if score
- (when (string-match "spamicity=\\([0-9.]+\\)" header)
- (match-string 1 header))
- spam-split-group))))
+ (let ((header (nnmail-fetch-field spam-bogofilter-header))
+ (spam-split-group (if spam-split-symbolic-return
+ 'spam
+ spam-split-group)))
+ (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 ()
(let ((score (or (spam-check-bogofilter-headers t)
(spam-check-bogofilter t))))
(message "Spamicity score %s" score)
- (or score "0"))))
+ (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))
+ (let ((article-buffer-name (buffer-name))
+ (db spam-bogofilter-database-directory)
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")))
+ (apply 'call-process-region
+ (point-min) (point-max)
+ spam-bogofilter-path
+ nil temp-buffer-name nil
+ (if db `("-d" ,db "-v") `("-v"))))
(setq return (spam-check-bogofilter-headers score))))
return))
-(defun spam-bogofilter-register-with-bogofilter (article-string spam)
+(defun spam-bogofilter-register-with-bogofilter (articles
+ spam
+ &optional unregister)
"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))))
+ (dolist (article articles)
+ (let ((article-string (spam-get-article-as-string article))
+ (db spam-bogofilter-database-directory)
+ (switch (if unregister
+ (if spam
+ spam-bogofilter-spam-strong-switch
+ spam-bogofilter-ham-strong-switch)
+ (if spam
+ spam-bogofilter-spam-switch
+ spam-bogofilter-ham-switch))))
+ (when (stringp article-string)
+ (with-temp-buffer
+ (insert article-string)
+
+ (apply 'call-process-region
+ (point-min) (point-max)
+ spam-bogofilter-path
+ nil nil nil switch
+ (if db `("-d" ,db "-v") `("-v"))))))))
+
+(defun spam-bogofilter-register-spam-routine (articles &optional unregister)
+ (spam-bogofilter-register-with-bogofilter articles t unregister))
+
+(defun spam-bogofilter-unregister-spam-routine (articles)
+ (spam-bogofilter-register-spam-routine articles t))
+
+(defun spam-bogofilter-register-ham-routine (articles &optional unregister)
+ (spam-bogofilter-register-with-bogofilter articles nil unregister))
+
+(defun spam-bogofilter-unregister-ham-routine (articles)
+ (spam-bogofilter-register-ham-routine articles t))
+
+
+\f
+;;;; spamoracle
+(defun spam-check-spamoracle ()
+ "Run spamoracle on an article to determine whether it's spam."
+ (let ((article-buffer-name (buffer-name))
+ (spam-split-group (if spam-split-symbolic-return
+ 'spam
+ spam-split-group)))
+ (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 (eq 0 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 (articles article-is-spam-p &optional unregister)
+ "Run spamoracle in training mode."
+ (with-temp-buffer
+ (let ((temp-buffer-name (buffer-name)))
+ (save-excursion
+ (goto-char (point-min))
+ (dolist (article articles)
+ (insert (spam-get-article-as-string article)))
+ (let* ((arg (if (spam-xor unregister 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 (eq 0 status))
+ (error "Error running spamoracle" status)))))))
+
+(defun spam-spamoracle-learn-ham (articles &optional unregister)
+ (spam-spamoracle-learn articles nil unregister))
+
+(defun spam-spamoracle-unlearn-ham (articles &optional unregister)
+ (spam-spamoracle-learn-ham articles t))
+
+(defun spam-spamoracle-learn-spam (articles &optional unregister)
+ (spam-spamoracle-learn articles t unregister))
+
+(defun spam-spamoracle-unlearn-spam (articles &optional unregister)
+ (spam-spamoracle-learn-spam articles t))
+
+\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
+ (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)
+ (add-hook 'gnus-summary-prepare-hook 'spam-find-spam))
+
+(defun spam-unload-hook ()
+ "Uninstall the spam.el hooks"
+ (interactive)
+ (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)
+ (remove-hook 'gnus-summary-prepare-hook 'spam-find-spam))
+
+(when spam-install-hooks
+ (spam-initialize))
(provide 'spam)
projects / elisp / gnus.git- / blobdiff