Synch with Oort Gnus.

diff --git a/lisp/ChangeLog b/lisp/ChangeLog
index ced3649..d6e4560 100644 (file)
--- a/lisp/ChangeLog
+++ b/lisp/ChangeLog
@@ -1,3 +1,24 @@
+2003-01-10  Teodor Zlatanov  <tzz@lifelogs.com>
+
+       * spam.el (spam-use-stat): new variable
+       (spam-group-spam-processor-stat-p) 
+       (spam-group-ham-processor-stat-p): new convenience functions
+       (spam-summary-prepare-exit): add spam/ham processors to sequence
+       (spam-list-of-checks): add spam-use-stat to list of checks
+       (spam-split): conditionally load the spam-stat tables
+       (spam-stat-register-spam-routine, spam-stat-register-ham-routine,
+       spam-check-ifile): new functions
+
+       * spam-stat.el (spam-stat): typo fix
+       (spam-stat-install-hooks): new variable
+       (spam-stat-split-fancy-spam-group): added documentation clarification
+       (spam-stat-split-fancy-spam-threshhold): new variable
+       (spam-stat-install-hooks): make hooks conditional
+       (spam-stat-split-fancy): use spam-stat-split-fancy-spam-threshhold
+
+       * gnus.el (gnus-group-ham-exit-processor-stat, spam-process): add
+       spam-stat ham/spam processor symbols
+
 2003-01-10  Lars Magne Ingebrigtsen  <larsi@gnus.org>
 
        * gnus-start.el (gnus-read-newsrc-el-file): Make sure the .eld

diff --git a/lisp/gnus.el b/lisp/gnus.el
index 323eb2f..cf7bdbd 100644 (file)
--- a/lisp/gnus.el
+++ b/lisp/gnus.el
@@ -1829,6 +1829,10 @@ When a spam group is entered, all unread articles are marked as spam.")
   "The ifile summary exit spam processor.
 Only applicable to spam groups.")
 
+(defvar gnus-group-spam-exit-processor-stat "stat"
+  "The spam-stat summary exit spam processor.
+Only applicable to spam groups.")
+
 (defvar gnus-group-spam-exit-processor-bogofilter "bogofilter"
   "The Bogofilter summary exit spam processor.
 Only applicable to spam groups.")
@@ -1841,6 +1845,10 @@ Only applicable to spam groups.")
   "The ifile summary exit ham processor.
 Only applicable to non-spam (unclassified and ham) groups.")
 
+(defvar gnus-group-ham-exit-processor-stat "stat-ham"
+  "The spam-stat summary exit ham processor.
+Only applicable to non-spam (unclassified and ham) groups.")
+
 (defvar gnus-group-ham-exit-processor-whitelist "whitelist"
   "The whitelist summary exit ham processor.
 Only applicable to non-spam (unclassified and ham) groups.")
@@ -1857,9 +1865,11 @@ Only applicable to non-spam (unclassified and ham) groups.")
                          (list :tag "Spam Summary Exit Processor Choices"
                           (set 
                            (variable-item gnus-group-spam-exit-processor-ifile)
+                           (variable-item gnus-group-spam-exit-processor-stat)
                            (variable-item gnus-group-spam-exit-processor-bogofilter)
                            (variable-item gnus-group-spam-exit-processor-blacklist)
                            (variable-item gnus-group-ham-exit-processor-ifile)
+                           (variable-item gnus-group-ham-exit-processor-stat)
                            (variable-item gnus-group-ham-exit-processor-whitelist)
                            (variable-item gnus-group-ham-exit-processor-BBDB))))
  :function-document
@@ -1878,9 +1888,11 @@ for mail groups."
                          (regexp :tag "Group Regexp") 
                          (set :tag "Spam/Ham Summary Exit Processor"
                               (variable-item gnus-group-spam-exit-processor-ifile)
+                              (variable-item gnus-group-spam-exit-processor-stat)
                               (variable-item gnus-group-spam-exit-processor-bogofilter)
                               (variable-item gnus-group-spam-exit-processor-blacklist)
                               (variable-item gnus-group-ham-exit-processor-ifile)
+                              (variable-item gnus-group-ham-exit-processor-stat)
                               (variable-item gnus-group-ham-exit-processor-whitelist)
                               (variable-item gnus-group-ham-exit-processor-BBDB))))
  :parameter-document

diff --git a/lisp/spam-stat.el b/lisp/spam-stat.el
index 7a01ec3..fc134f9 100644 (file)
--- a/lisp/spam-stat.el
+++ b/lisp/spam-stat.el
@@ -127,7 +127,7 @@
   "Statistical spam detection for Emacs.
 Use the functions to build a dictionary of words and their statistical
 distribution in spam and non-spam mails.  Then use a function to determine
-wether a buffer contains spam or not."
+whether a buffer contains spam or not."
   :group 'gnus)
 
 (defcustom spam-stat-file "~/.spam-stat.el"
@@ -136,6 +136,12 @@ See `spam-stat-to-hash-table' for the format of the file."
   :type 'file
   :group 'spam-stat)
 
+(defcustom spam-stat-install-hooks t
+  "Whether spam-stat should install its hooks in Gnus.
+This is set to nil if you use spam-stat through spam.el."
+  :type 'boolean
+  :group 'spam-stat)
+
 (defcustom spam-stat-unknown-word-score 0.2
   "The score to use for unknown words.
 Also used for words that don't appear often enough."
@@ -155,10 +161,16 @@ This variable says how many characters this will be."
 
 (defcustom spam-stat-split-fancy-spam-group "mail.spam"
   "Name of the group where spam should be stored, if
-`spam-stat-split-fancy' is used in fancy splitting rules."
+`spam-stat-split-fancy' is used in fancy splitting rules.  Has no
+effect when spam-stat is invoked through spam.el."
   :type 'string
   :group 'spam-stat)
 
+(defcustom spam-stat-split-fancy-spam-threshhold 0.9
+  "Spam score threshhold in spam-stat-split-fancy."
+  :type 'number
+  :group 'spam-stat)
+
 (defvar spam-stat-syntax-table
   (let ((table (copy-syntax-table text-mode-syntax-table)))
     (modify-syntax-entry ?- "w" table)
@@ -226,10 +238,11 @@ This uses `gnus-article-buffer'."
     (set-buffer gnus-original-article-buffer)
     (spam-stat-store-current-buffer)))
 
-(add-hook 'nnmail-prepare-incoming-message-hook
-         'spam-stat-store-current-buffer)
-(add-hook 'gnus-select-article-hook
-         'spam-stat-store-gnus-article-buffer)
+(when spam-stat-install-hooks
+  (add-hook 'nnmail-prepare-incoming-message-hook
+           'spam-stat-store-current-buffer)
+  (add-hook 'gnus-select-article-hook
+           'spam-stat-store-gnus-article-buffer))
 
 ;; Data -- not using defstruct in order to save space and time
 
@@ -471,7 +484,7 @@ check the variable `spam-stat-score-data'."
       (progn
        (set-buffer spam-stat-buffer)
        (goto-char (point-min))
-       (when (> (spam-stat-score-buffer) 0.9)
+       (when (> (spam-stat-score-buffer) spam-stat-split-fancy-spam-threshhold)
          (when (boundp 'nnmail-split-trace)
            (mapc (lambda (entry)
                    (push entry nnmail-split-trace))

diff --git a/lisp/spam.el b/lisp/spam.el
index e11115a..cb171df 100644 (file)
--- a/lisp/spam.el
+++ b/lisp/spam.el
@@ -120,6 +120,11 @@ The regular expression is matched against the address."
   :type 'boolean
   :group 'spam)
 
+(defcustom spam-use-stat nil
+  "Whether spam-stat should be used by spam-split."
+  :type 'boolean
+  :group 'spam)
+
 (defcustom spam-split-group "spam"
   "Group name where incoming spam should be put by spam-split."
   :type 'string
@@ -279,6 +284,12 @@ articles before they get registered by Bogofilter."
 (defun spam-group-ham-processor-ifile-p (group)
   (spam-group-processor-p group 'gnus-group-ham-exit-processor-ifile))
 
+(defun spam-group-spam-processor-stat-p (group)
+  (spam-group-processor-p group 'gnus-group-spam-exit-processor-stat))
+
+(defun spam-group-ham-processor-stat-p (group)
+  (spam-group-processor-p group 'gnus-group-ham-exit-processor-stat))
+
 (defun spam-group-ham-processor-whitelist-p (group)
   (spam-group-processor-p group 'gnus-group-ham-exit-processor-whitelist))
 
@@ -302,6 +313,9 @@ articles before they get registered by Bogofilter."
             (spam-group-spam-processor-ifile-p gnus-newsgroup-name))
     (spam-ifile-register-spam-routine))
   
+  (when (spam-group-spam-processor-stat-p gnus-newsgroup-name)
+    (spam-stat-register-spam-routine))
+
   (when (spam-group-spam-processor-bogofilter-p gnus-newsgroup-name)
     (spam-blacklist-register-routine))
 
@@ -321,6 +335,8 @@ articles before they get registered by Bogofilter."
       (spam-whitelist-register-routine))
     (when (spam-group-ham-processor-ifile-p gnus-newsgroup-name)
       (spam-ifile-register-ham-routine))
+    (when (spam-group-ham-processor-stat-p gnus-newsgroup-name)
+      (spam-stat-register-ham-routine))
     (when (spam-group-ham-processor-BBDB-p gnus-newsgroup-name)
       (spam-BBDB-register-routine)))
 
@@ -432,6 +448,7 @@ articles before they get registered by Bogofilter."
     (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-bogofilter . spam-check-bogofilter))
 "The spam-list-of-checks list contains pairs associating a parameter
@@ -453,6 +470,9 @@ example like this: (: spam-split)
 
 See the Info node `(gnus)Fancy Mail Splitting' for more details."
   (interactive)
+  
+  ;; load the spam-stat tables if needed
+  (when spam-use-stat (spam-stat-load))
 
   (let ((list-of-checks spam-list-of-checks)
        decision)
@@ -580,7 +600,6 @@ See the Info node `(gnus)Fancy Mail Splitting' for more details."
              (setq return category)
            ;; else, if spam-ifile-all-categories is not set...
            (when (string-equal spam-ifile-spam-category category)
-             ;; always accept the ifile category
              (setq return spam-split-group))))))
     return))
 
@@ -615,6 +634,52 @@ Uses `gnus-newsgroup-name' if category is nil (for ham registration)."
       (spam-get-article-as-string article) nil))))
 
 \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-string article-string)
+              (spam-stat-buffer-is-spam))))
+        nil)
+       (spam-stat-save))
+
+      (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-string article-string)
+              (spam-stat-buffer-is-non-spam)))))
+       (spam-stat-save)))
+
+  (file-error (progn
+               (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)