Mercurial > emacs
annotate lisp/gnus/spam-stat.el @ 84671:f061115a812f
*** empty log message ***
author | Glenn Morris <rgm@gnu.org> |
---|---|
date | Thu, 20 Sep 2007 02:53:58 +0000 |
parents | 24202b793a08 |
children | 1cb31606209f a3c27999decb |
rev | line source |
---|---|
56927
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
1 ;;; spam-stat.el --- detecting spam based on statistics |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
2 |
75347 | 3 ;; Copyright (C) 2002, 2003, 2004, 2005, 2006, 2007 Free Software Foundation, Inc. |
56927
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
4 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
5 ;; Author: Alex Schroeder <alex@gnu.org> |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
6 ;; Keywords: network |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
7 ;; URL: http://www.emacswiki.org/cgi-bin/wiki.pl?SpamStat |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
8 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
9 ;; This file is part of GNU Emacs. |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
10 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
11 ;; This is free software; you can redistribute it and/or modify it |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
12 ;; under the terms of the GNU General Public License as published by |
78224
24202b793a08
Switch license to GPLv3 or later.
Glenn Morris <rgm@gnu.org>
parents:
75347
diff
changeset
|
13 ;; the Free Software Foundation; either version 3, or (at your option) |
56927
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
14 ;; any later version. |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
15 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
16 ;; This is distributed in the hope that it will be useful, but WITHOUT |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
17 ;; ANY WARRANTY; without even the implied warranty of MERCHANTABILITY |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
18 ;; or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
19 ;; License for more details. |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
20 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
21 ;; You should have received a copy of the GNU General Public License |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
22 ;; along with GNU Emacs; see the file COPYING. If not, write to the |
64085 | 23 ;; Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, |
24 ;; Boston, MA 02110-1301, USA. | |
56927
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
25 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
26 ;;; Commentary: |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
27 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
28 ;; This implements spam analysis according to Paul Graham in "A Plan |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
29 ;; for Spam". The basis for all this is a statistical distribution of |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
30 ;; words for your spam and non-spam mails. We need this information |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
31 ;; in a hash-table so that the analysis can use the information when |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
32 ;; looking at your mails. Therefore, before you begin, you need tons |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
33 ;; of mails (Graham uses 4000 non-spam and 4000 spam mails for his |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
34 ;; experiments). |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
35 ;; |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
36 ;; The main interface to using spam-stat, are the following functions: |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
37 ;; |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
38 ;; `spam-stat-buffer-is-spam' -- called in a buffer, that buffer is |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
39 ;; considered to be a new spam mail; use this for new mail that has |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
40 ;; not been processed before |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
41 ;; |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
42 ;; `spam-stat-buffer-is-non-spam' -- called in a buffer, that buffer |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
43 ;; is considered to be a new non-spam mail; use this for new mail that |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
44 ;; has not been processed before |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
45 ;; |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
46 ;; `spam-stat-buffer-change-to-spam' -- called in a buffer, that |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
47 ;; buffer is no longer considered to be normal mail but spam; use this |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
48 ;; to change the status of a mail that has already been processed as |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
49 ;; non-spam |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
50 ;; |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
51 ;; `spam-stat-buffer-change-to-non-spam' -- called in a buffer, that |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
52 ;; buffer is no longer considered to be spam but normal mail; use this |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
53 ;; to change the status of a mail that has already been processed as |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
54 ;; spam |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
55 ;; |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
56 ;; `spam-stat-save' -- save the hash table to the file; the filename |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
57 ;; used is stored in the variable `spam-stat-file' |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
58 ;; |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
59 ;; `spam-stat-load' -- load the hash table from a file; the filename |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
60 ;; used is stored in the variable `spam-stat-file' |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
61 ;; |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
62 ;; `spam-stat-score-word' -- return the spam score for a word |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
63 ;; |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
64 ;; `spam-stat-score-buffer' -- return the spam score for a buffer |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
65 ;; |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
66 ;; `spam-stat-split-fancy' -- for fancy mail splitting; add |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
67 ;; the rule (: spam-stat-split-fancy) to `nnmail-split-fancy' |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
68 ;; |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
69 ;; This requires the following in your ~/.gnus file: |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
70 ;; |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
71 ;; (require 'spam-stat) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
72 ;; (spam-stat-load) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
73 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
74 ;;; Testing: |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
75 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
76 ;; Typical test will involve calls to the following functions: |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
77 ;; |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
78 ;; Reset: (spam-stat-reset) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
79 ;; Learn spam: (spam-stat-process-spam-directory "~/Mail/mail/spam") |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
80 ;; Learn non-spam: (spam-stat-process-non-spam-directory "~/Mail/mail/misc") |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
81 ;; Save table: (spam-stat-save) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
82 ;; File size: (nth 7 (file-attributes spam-stat-file)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
83 ;; Number of words: (hash-table-count spam-stat) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
84 ;; Test spam: (spam-stat-test-directory "~/Mail/mail/spam") |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
85 ;; Test non-spam: (spam-stat-test-directory "~/Mail/mail/misc") |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
86 ;; Reduce table size: (spam-stat-reduce-size) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
87 ;; Save table: (spam-stat-save) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
88 ;; File size: (nth 7 (file-attributes spam-stat-file)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
89 ;; Number of words: (hash-table-count spam-stat) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
90 ;; Test spam: (spam-stat-test-directory "~/Mail/mail/spam") |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
91 ;; Test non-spam: (spam-stat-test-directory "~/Mail/mail/misc") |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
92 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
93 ;;; Dictionary Creation: |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
94 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
95 ;; Typically, you will filter away mailing lists etc. using specific |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
96 ;; rules in `nnmail-split-fancy'. Somewhere among these rules, you |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
97 ;; will filter spam. Here is how you would create your dictionary: |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
98 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
99 ;; Reset: (spam-stat-reset) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
100 ;; Learn spam: (spam-stat-process-spam-directory "~/Mail/mail/spam") |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
101 ;; Learn non-spam: (spam-stat-process-non-spam-directory "~/Mail/mail/misc") |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
102 ;; Repeat for any other non-spam group you need... |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
103 ;; Reduce table size: (spam-stat-reduce-size) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
104 ;; Save table: (spam-stat-save) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
105 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
106 ;;; Todo: |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
107 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
108 ;; Speed it up. Integrate with Gnus such that it uses spam and expiry |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
109 ;; marks to call the appropriate functions when leaving the summary |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
110 ;; buffer and saves the hash table when leaving Gnus. More testing: |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
111 ;; More mails, disabling SpamAssassin, double checking algorithm, find |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
112 ;; improved algorithm. |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
113 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
114 ;;; Thanks: |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
115 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
116 ;; Ted Zlatanov <tzz@lifelogs.com> |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
117 ;; Jesper Harder <harder@myrealbox.com> |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
118 ;; Dan Schmidt <dfan@dfan.org> |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
119 ;; Lasse Rasinen <lrasinen@iki.fi> |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
120 ;; Milan Zamazal <pdm@zamazal.org> |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
121 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
122 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
123 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
124 ;;; Code: |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
125 |
65284
6e266fbfe59b
(gnus-original-article-buffer): Add defvar.
Juanma Barranquero <lekktu@gmail.com>
parents:
64754
diff
changeset
|
126 (defvar gnus-original-article-buffer) |
6e266fbfe59b
(gnus-original-article-buffer): Add defvar.
Juanma Barranquero <lekktu@gmail.com>
parents:
64754
diff
changeset
|
127 |
56927
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
128 (defgroup spam-stat nil |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
129 "Statistical spam detection for Emacs. |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
130 Use the functions to build a dictionary of words and their statistical |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
131 distribution in spam and non-spam mails. Then use a function to determine |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
132 whether a buffer contains spam or not." |
59996
aac0a33f5772
Change release version from 21.4 to 22.1 throughout.
Kim F. Storm <storm@cua.dk>
parents:
57856
diff
changeset
|
133 :version "22.1" |
56927
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
134 :group 'gnus) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
135 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
136 (defcustom spam-stat-file "~/.spam-stat.el" |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
137 "File used to save and load the dictionary. |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
138 See `spam-stat-to-hash-table' for the format of the file." |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
139 :type 'file |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
140 :group 'spam-stat) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
141 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
142 (defcustom spam-stat-install-hooks t |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
143 "Whether spam-stat should install its hooks in Gnus. |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
144 This is set to nil if you use spam-stat through spam.el." |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
145 :type 'boolean |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
146 :group 'spam-stat) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
147 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
148 (defcustom spam-stat-unknown-word-score 0.2 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
149 "The score to use for unknown words. |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
150 Also used for words that don't appear often enough." |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
151 :type 'number |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
152 :group 'spam-stat) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
153 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
154 (defcustom spam-stat-max-word-length 15 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
155 "Only words shorter than this will be considered." |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
156 :type 'integer |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
157 :group 'spam-stat) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
158 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
159 (defcustom spam-stat-max-buffer-length 10240 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
160 "Only the beginning of buffers will be analyzed. |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
161 This variable says how many characters this will be." |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
162 :type 'integer |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
163 :group 'spam-stat) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
164 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
165 (defcustom spam-stat-split-fancy-spam-group "mail.spam" |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
166 "Name of the group where spam should be stored, if |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
167 `spam-stat-split-fancy' is used in fancy splitting rules. Has no |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
168 effect when spam-stat is invoked through spam.el." |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
169 :type 'string |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
170 :group 'spam-stat) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
171 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
172 (defcustom spam-stat-split-fancy-spam-threshhold 0.9 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
173 "Spam score threshhold in spam-stat-split-fancy." |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
174 :type 'number |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
175 :group 'spam-stat) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
176 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
177 (defvar spam-stat-syntax-table |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
178 (let ((table (copy-syntax-table text-mode-syntax-table))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
179 (modify-syntax-entry ?- "w" table) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
180 (modify-syntax-entry ?_ "w" table) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
181 (modify-syntax-entry ?. "w" table) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
182 (modify-syntax-entry ?! "w" table) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
183 (modify-syntax-entry ?? "w" table) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
184 (modify-syntax-entry ?+ "w" table) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
185 table) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
186 "Syntax table used when processing mails for statistical analysis. |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
187 The important part is which characters are word constituents.") |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
188 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
189 (defvar spam-stat-dirty nil |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
190 "Whether the spam-stat database needs saving.") |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
191 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
192 (defvar spam-stat-buffer nil |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
193 "Buffer to use for scoring while splitting. |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
194 This is set by hooking into Gnus.") |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
195 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
196 (defvar spam-stat-buffer-name " *spam stat buffer*" |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
197 "Name of the `spam-stat-buffer'.") |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
198 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
199 ;; Functions missing in Emacs 20 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
200 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
201 (when (memq nil (mapcar 'fboundp |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
202 '(gethash hash-table-count make-hash-table |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
203 mapc puthash))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
204 (require 'cl) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
205 (unless (fboundp 'puthash) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
206 ;; alias puthash is missing from Emacs 20 cl-extra.el |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
207 (defalias 'puthash 'cl-puthash))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
208 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
209 (eval-when-compile |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
210 (unless (fboundp 'with-syntax-table) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
211 ;; Imported from Emacs 21.2 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
212 (defmacro with-syntax-table (table &rest body) "\ |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
213 Evaluate BODY with syntax table of current buffer set to a copy of TABLE. |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
214 The syntax table of the current buffer is saved, BODY is evaluated, and the |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
215 saved table is restored, even in case of an abnormal exit. |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
216 Value is what BODY returns." |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
217 (let ((old-table (make-symbol "table")) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
218 (old-buffer (make-symbol "buffer"))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
219 `(let ((,old-table (syntax-table)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
220 (,old-buffer (current-buffer))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
221 (unwind-protect |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
222 (progn |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
223 (set-syntax-table (copy-syntax-table ,table)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
224 ,@body) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
225 (save-current-buffer |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
226 (set-buffer ,old-buffer) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
227 (set-syntax-table ,old-table)))))))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
228 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
229 ;; Hooking into Gnus |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
230 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
231 (defun spam-stat-store-current-buffer () |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
232 "Store a copy of the current buffer in `spam-stat-buffer'." |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
233 (save-excursion |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
234 (let ((str (buffer-string))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
235 (set-buffer (get-buffer-create spam-stat-buffer-name)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
236 (erase-buffer) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
237 (insert str) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
238 (setq spam-stat-buffer (current-buffer))))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
239 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
240 (defun spam-stat-store-gnus-article-buffer () |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
241 "Store a copy of the current article in `spam-stat-buffer'. |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
242 This uses `gnus-article-buffer'." |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
243 (save-excursion |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
244 (set-buffer gnus-original-article-buffer) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
245 (spam-stat-store-current-buffer))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
246 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
247 ;; Data -- not using defstruct in order to save space and time |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
248 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
249 (defvar spam-stat (make-hash-table :test 'equal) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
250 "Hash table used to store the statistics. |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
251 Use `spam-stat-load' to load the file. |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
252 Every word is used as a key in this table. The value is a vector. |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
253 Use `spam-stat-ngood', `spam-stat-nbad', `spam-stat-good', |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
254 `spam-stat-bad', and `spam-stat-score' to access this vector.") |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
255 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
256 (defvar spam-stat-ngood 0 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
257 "The number of good mails in the dictionary.") |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
258 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
259 (defvar spam-stat-nbad 0 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
260 "The number of bad mails in the dictionary.") |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
261 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
262 (defsubst spam-stat-good (entry) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
263 "Return the number of times this word belongs to good mails." |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
264 (aref entry 0)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
265 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
266 (defsubst spam-stat-bad (entry) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
267 "Return the number of times this word belongs to bad mails." |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
268 (aref entry 1)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
269 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
270 (defsubst spam-stat-score (entry) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
271 "Set the score of this word." |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
272 (if entry |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
273 (aref entry 2) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
274 spam-stat-unknown-word-score)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
275 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
276 (defsubst spam-stat-set-good (entry value) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
277 "Set the number of times this word belongs to good mails." |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
278 (aset entry 0 value)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
279 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
280 (defsubst spam-stat-set-bad (entry value) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
281 "Set the number of times this word belongs to bad mails." |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
282 (aset entry 1 value)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
283 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
284 (defsubst spam-stat-set-score (entry value) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
285 "Set the score of this word." |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
286 (aset entry 2 value)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
287 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
288 (defsubst spam-stat-make-entry (good bad) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
289 "Return a vector with the given properties." |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
290 (let ((entry (vector good bad nil))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
291 (spam-stat-set-score entry (spam-stat-compute-score entry)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
292 entry)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
293 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
294 ;; Computing |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
295 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
296 (defun spam-stat-compute-score (entry) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
297 "Compute the score of this word. 1.0 means spam." |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
298 ;; promote all numbers to floats for the divisions |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
299 (let* ((g (* 2.0 (spam-stat-good entry))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
300 (b (float (spam-stat-bad entry)))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
301 (cond ((< (+ g b) 5) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
302 .2) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
303 ((= 0 spam-stat-ngood) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
304 .99) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
305 ((= 0 spam-stat-nbad) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
306 .01) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
307 (t |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
308 (max .01 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
309 (min .99 (/ (/ b spam-stat-nbad) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
310 (+ (/ g spam-stat-ngood) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
311 (/ b spam-stat-nbad))))))))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
312 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
313 ;; Parsing |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
314 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
315 (defmacro with-spam-stat-max-buffer-size (&rest body) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
316 "Narrows the buffer down to the first 4k characters, then evaluates BODY." |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
317 `(save-restriction |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
318 (when (> (- (point-max) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
319 (point-min)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
320 spam-stat-max-buffer-length) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
321 (narrow-to-region (point-min) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
322 (+ (point-min) spam-stat-max-buffer-length))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
323 ,@body)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
324 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
325 (defun spam-stat-buffer-words () |
68931
d7445550220c
(spam-stat-buffer-words): Fix typo in docstring.
Juanma Barranquero <lekktu@gmail.com>
parents:
68633
diff
changeset
|
326 "Return a hash table of words and number of occurrences in the buffer." |
56927
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
327 (with-spam-stat-max-buffer-size |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
328 (with-syntax-table spam-stat-syntax-table |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
329 (goto-char (point-min)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
330 (let ((result (make-hash-table :test 'equal)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
331 word count) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
332 (while (re-search-forward "\\w+" nil t) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
333 (setq word (match-string-no-properties 0) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
334 count (1+ (gethash word result 0))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
335 (when (< (length word) spam-stat-max-word-length) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
336 (puthash word count result))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
337 result)))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
338 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
339 (defun spam-stat-buffer-is-spam () |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
340 "Consider current buffer to be a new spam mail." |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
341 (setq spam-stat-nbad (1+ spam-stat-nbad)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
342 (maphash |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
343 (lambda (word count) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
344 (let ((entry (gethash word spam-stat))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
345 (if entry |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
346 (spam-stat-set-bad entry (+ count (spam-stat-bad entry))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
347 (setq entry (spam-stat-make-entry 0 count))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
348 (spam-stat-set-score entry (spam-stat-compute-score entry)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
349 (puthash word entry spam-stat))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
350 (spam-stat-buffer-words)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
351 (setq spam-stat-dirty t)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
352 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
353 (defun spam-stat-buffer-is-non-spam () |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
354 "Consider current buffer to be a new non-spam mail." |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
355 (setq spam-stat-ngood (1+ spam-stat-ngood)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
356 (maphash |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
357 (lambda (word count) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
358 (let ((entry (gethash word spam-stat))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
359 (if entry |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
360 (spam-stat-set-good entry (+ count (spam-stat-good entry))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
361 (setq entry (spam-stat-make-entry count 0))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
362 (spam-stat-set-score entry (spam-stat-compute-score entry)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
363 (puthash word entry spam-stat))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
364 (spam-stat-buffer-words)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
365 (setq spam-stat-dirty t)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
366 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
367 (defun spam-stat-buffer-change-to-spam () |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
368 "Consider current buffer no longer normal mail but spam." |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
369 (setq spam-stat-nbad (1+ spam-stat-nbad) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
370 spam-stat-ngood (1- spam-stat-ngood)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
371 (maphash |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
372 (lambda (word count) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
373 (let ((entry (gethash word spam-stat))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
374 (if (not entry) |
63419
025ea93d2596
(spam-stat-buffer-change-to-spam, spam-stat-buffer-change-to-non-spam):
Juanma Barranquero <lekktu@gmail.com>
parents:
59996
diff
changeset
|
375 (error "This buffer has unknown words in it") |
56927
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
376 (spam-stat-set-good entry (- (spam-stat-good entry) count)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
377 (spam-stat-set-bad entry (+ (spam-stat-bad entry) count)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
378 (spam-stat-set-score entry (spam-stat-compute-score entry)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
379 (puthash word entry spam-stat)))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
380 (spam-stat-buffer-words)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
381 (setq spam-stat-dirty t)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
382 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
383 (defun spam-stat-buffer-change-to-non-spam () |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
384 "Consider current buffer no longer spam but normal mail." |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
385 (setq spam-stat-nbad (1- spam-stat-nbad) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
386 spam-stat-ngood (1+ spam-stat-ngood)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
387 (maphash |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
388 (lambda (word count) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
389 (let ((entry (gethash word spam-stat))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
390 (if (not entry) |
63419
025ea93d2596
(spam-stat-buffer-change-to-spam, spam-stat-buffer-change-to-non-spam):
Juanma Barranquero <lekktu@gmail.com>
parents:
59996
diff
changeset
|
391 (error "This buffer has unknown words in it") |
56927
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
392 (spam-stat-set-good entry (+ (spam-stat-good entry) count)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
393 (spam-stat-set-bad entry (- (spam-stat-bad entry) count)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
394 (spam-stat-set-score entry (spam-stat-compute-score entry)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
395 (puthash word entry spam-stat)))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
396 (spam-stat-buffer-words)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
397 (setq spam-stat-dirty t)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
398 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
399 ;; Saving and Loading |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
400 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
401 (defun spam-stat-save (&optional force) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
402 "Save the `spam-stat' hash table as lisp file. |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
403 With a prefix argument save unconditionally." |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
404 (interactive "P") |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
405 (when (or force spam-stat-dirty) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
406 (with-temp-buffer |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
407 (let ((standard-output (current-buffer)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
408 (font-lock-maximum-size 0)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
409 (insert "(setq spam-stat-ngood " |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
410 (number-to-string spam-stat-ngood) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
411 " spam-stat-nbad " |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
412 (number-to-string spam-stat-nbad) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
413 " spam-stat (spam-stat-to-hash-table '(") |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
414 (maphash (lambda (word entry) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
415 (prin1 (list word |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
416 (spam-stat-good entry) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
417 (spam-stat-bad entry)))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
418 spam-stat) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
419 (insert ")))") |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
420 (write-file spam-stat-file))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
421 (setq spam-stat-dirty nil))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
422 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
423 (defun spam-stat-load () |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
424 "Read the `spam-stat' hash table from disk." |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
425 ;; TODO: maybe we should warn the user if spam-stat-dirty is t? |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
426 (load-file spam-stat-file) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
427 (setq spam-stat-dirty nil)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
428 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
429 (defun spam-stat-to-hash-table (entries) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
430 "Turn list ENTRIES into a hash table and store as `spam-stat'. |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
431 Every element in ENTRIES has the form \(WORD GOOD BAD) where WORD is |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
432 the word string, NGOOD is the number of good mails it has appeared in, |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
433 NBAD is the number of bad mails it has appeared in, GOOD is the number |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
434 of times it appeared in good mails, and BAD is the number of times it |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
435 has appeared in bad mails." |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
436 (let ((table (make-hash-table :test 'equal))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
437 (mapc (lambda (l) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
438 (puthash (car l) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
439 (spam-stat-make-entry (nth 1 l) (nth 2 l)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
440 table)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
441 entries) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
442 table)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
443 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
444 (defun spam-stat-reset () |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
445 "Reset `spam-stat' to an empty hash-table. |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
446 This deletes all the statistics." |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
447 (interactive) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
448 (setq spam-stat (make-hash-table :test 'equal) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
449 spam-stat-ngood 0 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
450 spam-stat-nbad 0) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
451 (setq spam-stat-dirty t)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
452 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
453 ;; Scoring buffers |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
454 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
455 (defvar spam-stat-score-data nil |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
456 "Raw data used in the last run of `spam-stat-score-buffer'.") |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
457 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
458 (defsubst spam-stat-score-word (word) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
459 "Return score for WORD. |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
460 The default score for unknown words is stored in |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
461 `spam-stat-unknown-word-score'." |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
462 (spam-stat-score (gethash word spam-stat))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
463 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
464 (defun spam-stat-buffer-words-with-scores () |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
465 "Process current buffer, return the 15 most conspicuous words. |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
466 These are the words whose spam-stat differs the most from 0.5. |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
467 The list returned contains elements of the form \(WORD SCORE DIFF), |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
468 where DIFF is the difference between SCORE and 0.5." |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
469 (with-spam-stat-max-buffer-size |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
470 (with-syntax-table spam-stat-syntax-table |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
471 (let (result word score) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
472 (maphash (lambda (word ignore) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
473 (setq score (spam-stat-score-word word) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
474 result (cons (list word score (abs (- score 0.5))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
475 result))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
476 (spam-stat-buffer-words)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
477 (setq result (sort result (lambda (a b) (< (nth 2 b) (nth 2 a))))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
478 (setcdr (nthcdr 14 result) nil) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
479 result)))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
480 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
481 (defun spam-stat-score-buffer () |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
482 "Return a score describing the spam-probability for this buffer." |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
483 (setq spam-stat-score-data (spam-stat-buffer-words-with-scores)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
484 (let* ((probs (mapcar (lambda (e) (cadr e)) spam-stat-score-data)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
485 (prod (apply #'* probs))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
486 (/ prod (+ prod (apply #'* (mapcar #'(lambda (x) (- 1 x)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
487 probs)))))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
488 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
489 (defun spam-stat-split-fancy () |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
490 "Return the name of the spam group if the current mail is spam. |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
491 Use this function on `nnmail-split-fancy'. If you are interested in |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
492 the raw data used for the last run of `spam-stat-score-buffer', |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
493 check the variable `spam-stat-score-data'." |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
494 (condition-case var |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
495 (progn |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
496 (set-buffer spam-stat-buffer) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
497 (goto-char (point-min)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
498 (when (> (spam-stat-score-buffer) spam-stat-split-fancy-spam-threshhold) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
499 (when (boundp 'nnmail-split-trace) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
500 (mapc (lambda (entry) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
501 (push entry nnmail-split-trace)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
502 spam-stat-score-data)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
503 spam-stat-split-fancy-spam-group)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
504 (error (message "Error in spam-stat-split-fancy: %S" var) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
505 nil))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
506 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
507 ;; Testing |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
508 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
509 (defun spam-stat-process-directory (dir func) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
510 "Process all the regular files in directory DIR using function FUNC." |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
511 (let* ((files (directory-files dir t "^[^.]")) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
512 (max (/ (length files) 100.0)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
513 (count 0)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
514 (with-temp-buffer |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
515 (dolist (f files) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
516 (when (and (file-readable-p f) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
517 (file-regular-p f) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
518 (> (nth 7 (file-attributes f)) 0)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
519 (setq count (1+ count)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
520 (message "Reading %s: %.2f%%" dir (/ count max)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
521 (insert-file-contents f) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
522 (funcall func) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
523 (erase-buffer)))))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
524 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
525 (defun spam-stat-process-spam-directory (dir) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
526 "Process all the regular files in directory DIR as spam." |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
527 (interactive "D") |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
528 (spam-stat-process-directory dir 'spam-stat-buffer-is-spam)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
529 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
530 (defun spam-stat-process-non-spam-directory (dir) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
531 "Process all the regular files in directory DIR as non-spam." |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
532 (interactive "D") |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
533 (spam-stat-process-directory dir 'spam-stat-buffer-is-non-spam)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
534 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
535 (defun spam-stat-count () |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
536 "Return size of `spam-stat'." |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
537 (interactive) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
538 (hash-table-count spam-stat)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
539 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
540 (defun spam-stat-test-directory (dir) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
541 "Test all the regular files in directory DIR for spam. |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
542 If the result is 1.0, then all files are considered spam. |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
543 If the result is 0.0, non of the files is considered spam. |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
544 You can use this to determine error rates." |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
545 (interactive "D") |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
546 (let* ((files (directory-files dir t "^[^.]")) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
547 (total (length files)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
548 (score 0.0); float |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
549 (max (/ total 100.0)); float |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
550 (count 0)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
551 (with-temp-buffer |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
552 (dolist (f files) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
553 (when (and (file-readable-p f) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
554 (file-regular-p f) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
555 (> (nth 7 (file-attributes f)) 0)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
556 (setq count (1+ count)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
557 (message "Reading %.2f%%, score %.2f%%" |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
558 (/ count max) (/ score count)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
559 (insert-file-contents f) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
560 (when (> (spam-stat-score-buffer) 0.9) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
561 (setq score (1+ score))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
562 (erase-buffer)))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
563 (message "Final score: %d / %d = %f" score total (/ score total)))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
564 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
565 ;; Shrinking the dictionary |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
566 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
567 (defun spam-stat-reduce-size (&optional count) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
568 "Reduce the size of `spam-stat'. |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
569 This removes all words that occur less than COUNT from the dictionary. |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
570 COUNT defaults to 5" |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
571 (interactive) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
572 (setq count (or count 5)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
573 (maphash (lambda (key entry) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
574 (when (< (+ (spam-stat-good entry) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
575 (spam-stat-bad entry)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
576 count) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
577 (remhash key spam-stat))) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
578 spam-stat) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
579 (setq spam-stat-dirty t)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
580 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
581 (defun spam-stat-install-hooks-function () |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
582 "Install the spam-stat function hooks" |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
583 (interactive) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
584 (add-hook 'nnmail-prepare-incoming-message-hook |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
585 'spam-stat-store-current-buffer) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
586 (add-hook 'gnus-select-article-hook |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
587 'spam-stat-store-gnus-article-buffer)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
588 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
589 (when spam-stat-install-hooks |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
590 (spam-stat-install-hooks-function)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
591 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
592 (defun spam-stat-unload-hook () |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
593 "Uninstall the spam-stat function hooks" |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
594 (interactive) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
595 (remove-hook 'nnmail-prepare-incoming-message-hook |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
596 'spam-stat-store-current-buffer) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
597 (remove-hook 'gnus-select-article-hook |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
598 'spam-stat-store-gnus-article-buffer)) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
599 |
57550
a19498f00f9a
(spam-stat-unload-hook): Set as a variable w/ add-hook.
Richard M. Stallman <rms@gnu.org>
parents:
56927
diff
changeset
|
600 (add-hook 'spam-stat-unload-hook 'spam-stat-unload-hook) |
a19498f00f9a
(spam-stat-unload-hook): Set as a variable w/ add-hook.
Richard M. Stallman <rms@gnu.org>
parents:
56927
diff
changeset
|
601 |
56927
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
602 (provide 'spam-stat) |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
603 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
604 ;;; arch-tag: ff1d2200-8ddb-42fb-bb7b-1b5e20448554 |
55fd4f77387a
Revision: miles@gnu.org--gnu-2004/emacs--cvs-trunk--0--patch-523
Miles Bader <miles@gnu.org>
parents:
diff
changeset
|
605 ;;; spam-stat.el ends here |