add subject cleaner

[etc/mailfilter.git] / crm114 / mailfilter.cf

#  mailfilter.cf  -- Config file for mailfilter, mailreaver, mailtrainer
#  
#    You MUST edit the fileds for "Secret Password", "mime decoder", and
#    "cache_dupe_command".  Just those THREE things.  
#
#     Changes to all other values are optional.
#
#    Many of the options here have two or three alternatives; for your
#     convenience, we have put all of the reasonable alternatives 
#      on sequential lines.  Uncomment the one you want, and leave the
#       others commented out.  If you leave more than one uncommented, the
#       last one is the one that's used.  Don't do that; it's ugly.
#
#   After you edit this file, don't forget to edit 'rewrites.mfp' 

#     --------->>>  You MUST set the following correctly! <<<-------
#
#    If you leave it as "DEFAULT-PASSWORD", you will not be able to 
#    access the mail-to-myself commanding system, as "DEFAULT-PASSWORD"
#    is specifically _disabled_ as a legal password.  Just pick something, eh?
#
:spw: /DEFAULT_PASSWORD/

# ----- If you want a verbose startup, turn this on.  Note that this is
#  ----- intentionally _after_ the password is set, so a verbose startup
#   ----- will not reveal your password.  
#
#:verbose_startup: /SET/
:verbose_startup: //

#
#     --------->>>  You MUST set the following correctly! <<<-------
#
#     --- Some mail systems do mime decoding with "mimencode -d" or "-u".
#     --- Others (such as Red Hat 8.0) use "mewdecode" .
#     --- Yet others (such as Fedora Core 3) use "openssl base64 -d" .
#     --- Yet Others (i.e. *BSDs) can use "base64" .
#     --- See which one is on your system and use that one- comment
#     --- the others out.  If you can't figure out what your base64 mime
#     --- decoder is, or don't want mime decoding, set :do_base64: to /no/
#     --- but expect a significant accuracy decrease if you do this.
#
#:do_base64: /no/
:do_base64: /yes/
#
#:mime_decoder: /mewdecode/
#:mime_decoder: /mimencode -d/
#:mime_decoder: /mimencode -u/
#:mime_decoder: /base64 -d/
:mime_decoder: /openssl base64 -d/
#:mime_decoder: /normalizemime/


#     --------->>>  You MUST set the following correctly! <<<-------
#
#    --- Linux (and Unix) systems use "hardlinks" to make a file 
#    --- appear in more than one place, while not actually using up 
#    --- extra disk space.  Sadly, it is the case that most 
#    --- Windows systems have no such feature.  So, you must set the
#    --- following for what kind of system you are actually using.
#    --  Note to other developers: here's where to put other system-dependent
#    --  syscall commands.
#
#    --- Use the default /ln/ for LINUX and UNIX systems (does a hard-link,
#    --- does not use up disk space or inodes).  Change this to the /copy/
#    --- command for WINDOWS systems (95, 98, NT, XP)
#
#    --- Mild security issue: to avoid a theoretical exploit where a user
#    --- gets their commands re-aliased, make sure you use the fully qualified
#    --- commandname (that is, starting in the root directory).
#
:cache_dupe_command: /\/bin\/ln/
#:cache_dupe_command: /copy/



###########################################################################
#
#                END of things you absolutely MUST set.  Feel free
#            to keep reading though...
#
###########################################################################

###########################################################################
#
#             START of things you might likely want to set.  These 
#            are probably OK for you, but many users change these things.
#
##########################################################################
          
#  ----------- define an optional target for where to send spam (that is,
#   ------------ emails that we want to "fail", or reject to another
#    ------------ address.  Note that this is NOT a "program fault" address,
#     ------------ but where to send "bad" email to in the general case.
#      ------------ You can specify tightly controlled conditions too,
#  ----------- define an optional target for where to send spam,  
#   ----------- To NOT forward this to another account, just leave the
#    ----------- address as the empty string, which is '//'.
#     ----------- This works fine especially if your mail reader program
#      ----------- can sort based on the ADV and UNS (or whatever you choose
#       ----------- to use as flagging strings) in the "Subject:" field.
#     ------- CAUTION- some systems are buggy and _REQUIRE_ a user@host.domain
#    ----- in the following to forward spammy mail correctly.  WTF??? :-(
#
#:general_fails_to: /somebody@somewhere.net/
:general_fails_to: //


#   -------- If you would prefer to send specific kinds of spam to 
#    -------- different mailboxes, here's where to do it.
#     -------- (be sure to uncomment the line!).  Again, these are
#      --------- not "program fault" conditions, just different filter results.
#
# :fail_priority_mail_to:  /where_priority_fails_go/
# :fail_blacklist_mail_to:  /where_blacklist_fails_go/
# :fail_SSM_mail_to:  /where_Classifier_fails_go_for_mailFILTER/
# :fail_classify_mail_to: /where_classifier_fails_go_for_mailREAVER/


#  ---------  Do we give nonspam, spam, and unsure an exitcode of 0 
#  ---------    (for most standalone apps) or something else?
#  ---------     Usually we use an exit code of 1 for "program fault",
#  ---------      but change it if you need to use 0/1 for good/spam 
#  ---------       Don't use an exit code greater than 128 (it breaks BASH!)
#  ---------     If you use exit codes (procmail doesn't) change it here.
:rejected_mail_exit_code: /0/
:accepted_mail_exit_code: /0/
:unsure_mail_exit_code: /0/
:program_fault_exit_code: /1/

#######################################################################
#
#         END of things you are likely to want to change.  
#
#         Anything following is starting to approach true customization.
#        Feel free to explore and poke around.
######################################################################

# -----------Do we want to add the optional headers to the mail?
# -----------If turned on, will add X-CRM114-Whatever: headers on each
# -----------incoming email.  (note- this does NOT turn off the cache-id header
#
:add_headers: /yes/
#:add_headers: /no/


# ---------  do we add the statistics report?
:add_verbose_stats: /no/
#:add_verbose_stats: /no/


# ---------  do we add the mailtrainer report to the top of the message body
# ---------  after training?
:add_mailtrainer_report: /no/
#:add_mailtrainer_report: /no/


#  ---------  Do we enable long-form explains (with lots of text)?
#  -- you can have no extra stuff, add it as text, or add it as an attachment.
#  -- (only available in mailfilter, not mailreaver)
#
:add_extra_stuff: /no/
# :add_extra_stuff: /text/
# :add_extra_stuff: /attachment/


#  ---------  Do we prevent crm114 from adding multiple sfid tags?
#  -- every time mailreaver or mailfilter process a message, they add an sfid
#  -- tag to the Message-Id field, even if such a tag already exists.
#  -- by setting the following, crm114 knows not to add the tag if one already
#  -- exists.
#
:unique_sfid: /SET/


#  ---------  Do we want to insert a "flagging" string on the subject line, 
#  ---------  perhaps to insert an 'ADV:'  ?  Whatever string we put here
#  ---------  will be inserted at the front of the subject if we think the
#  ---------  mail is spam.
#
# :spam_flag_subject_string: //
:spam_flag_subject_string: //

#  ---------  Do we want to insert a "flagging" string on the subject line
#  ---------  for good email?  Usually we don't.... so we set this to the
#  ---------  null string - that is, //
:good_flag_subject_string: //

#  ------------Similarly, do we want to insert a "flagging" string on 
#  -------------the subject line of an "unsure" email?  This way we know
#  --------------we need to train it even if "headers" is turned off.
# :unsure_flag_subject_string: //
:unsure_flag_subject_string: //

# ------------- Do we want Training ConFirmation flags on the results of
# ------------- a message to be learned?  Default is "TCF:".
:confirm_flag_subject_string: //
#:confirm_flag_subject_string: //


# ---------  Do we want to do any "rewrites" to increase generality and
#  ---------- (usually) accuracy?  IF 'yes', be sure to edit rewrites.mfp!
#    --------- NOTE: this option is somewhat slow.  If your mailserver is
#      --------- maxed out on CPU, you might want to turn this off.
#
:rewrites_enabled: /yes/
#:rewrites_enabled: /no/


#  ---------  Do we copy incoming text into allmail.txt ?  default is yes, but
#   ---------  experienced users will probably set this to 'no' after testing
#    ---------  their configuration for functionality.
#
:log_to_allmail.txt:  /no/
# :log_to_allmail.txt: /no/

#   -------  Another logging option - log all mail to somewhere else
#    -------  entirely.  Whatever pathname is given here will be prefixed
#     -------  by :fileprefix: 
#      -------  To not use this, set it to the null string .. //   
#       -------  Remember to backslash-escape path slashes!
:log_all_mail_to_file: //
#:log_all_mail_to_file: /my_personal_mail_log_file_name.txt/

#     --------- When we log messages, should we use a mail separator?
#      --------- And, if so, what?
:mail_separator: /\n-=-=-=-=-=-=- cut here -=-=-=-=-=-=-\n/

#
#     ---------- Message Cacheing for retraining - do we keep a cache of
#    ---------- messages we've classified recently "in the wild" as retrain
#   ---------- texts?  This uses up some disk space, but means that we can
#  ---------- use mailtrainer.crm on these messages to autotune the classifier.
# ---------- Default is to cache into the directory reaver_cache ; 
#  ---------- if you don't want this, set it to // .  If you don't use this,
#   ---------- you can't really use mailtrainer.crm, and you must keep your
#    ---------- headers scrupulously clean in all train messages.  Recommended
#     ---------- to leave this unchanged unless you are VERY short of disk.
#
:text_cache: /../../../.var/crm114/reaver_cache/
# :text_cache: //


#   ----- How do we invoke the trainer (as in, just the invocation 
#   ------ of CRM114 on mailtrainer.crm.  Usually this is just obvious,
#   ------- but if you don't have CRM114 installed in the search path, here's
#   -------- where you can set trainer invocation to be via whatever path
#   --------- you want it (the second example is if you haven't installed
#   ---------- CRM114 at all, but are running the crm114_tre static binary
#   ----------- right out of the local directory.)
#      
#     -- use this next one if you have installed CRM114 with "make install"
#     -- (This is preferred and is the default)
:trainer_invoke_command: /\/usr\/share\/crm114\/mailtrainer.crm/
#
#     -- use this one if you can't do a "make install" and so must run the
#     --- crm114_tre binary directly out of the current working directory.
# :trainer_invoke_command: /.\/crm114_tre mailtrainer.crm /


#    ------  If we're cacheing for retraining, we're probably using
#     ------  mailtrainer.crm or some other variant.  In that case,
#      ------  you will want a "randomizer" to present the training
#       ------  examples to the classifier in some random but balanced order.
#        ------  You have two choices - you can either use the "sort"
#         ------  command on some random character in the filename (this
#          ------  is NOT recommended) or use the "shuffle.crm" program.
#           ------  We _strongly_ recommend using shuffle.crm; the default
#            ------  options to shuffle.crm will work fine.  Alternatively,
#             ------  you can use the "sort --key 1.2" on date-named files to
#              -----   achieve chronological training
:trainer_randomizer_command: /.\/shuffle.crm/
#:trainer_randomizer_command: /.\/crm114 shuffle.crm/
#:trainer_randomizer_command: /sort --key 1.2/


#  ---------  Do we log rejected mail to a file?  default yes, but most
#   ---------  users should set this to no after testing their 
#    ---------  configuration to verify that rejected mail goes to the 
#     ---------  reject address.  Only works in mailfilter.crm
#
:log_rejections: /yes/
#:log_rejections: /no/

#  ------- alternate rejection logging - set this pathname to non-null
#   ------  to log rejections elsewhere.  Only for mailreaver.crm.
#    -----   Set to NULL ( // ) to turn this off.
:log_rejections_to_file: //
#:log_rejections_to_file /this_is_my_rejected_email_log_file.txt/
 

#   ----------Do we want to enable "inoculation by email"?
#   --------(leave this off unless you want RFC inoculations)
#
:inoculations_enabled: /no/
#:inoculations_enabled: /yes/


#  --------- How many characters of the input do we really trust to be 
#  ---------- worthy of classification?  Usually the first few thousand
#  ----------- bytes of the message tell more than enough (though we've 
#  ------------ been "noticed" by spammers, who are now packing 4K of 
#  ------------- innocuous text into their headers.  No problemo... :) )
#
#:decision_length: /4096/
#:decision_length: /64000/
:decision_length: /16000/
#  -----  for entropy users ONLY - 4K is plenty!
#:decision_length: /4096/



#  ------------ Do we want to expand URLs (that is, fetching the contents
#  ------------- of a URL and inserting that after the url itself?)
#  -------------- By default this is off, but turn it on if you want
#  --------------- to experiment.  
:expand_urls: /no/
# :expand_urls: /yes/
#                 
#         WGET options - 30-second timeout, output to stdout. 
#         HACK - use the proper --user-agent="IEblahblah" for max effect!
:url_fetch_cmd:  /wget -T 30 -O -  /
#         and trim the URL text to not more than 16bytes of text.
:url_trim_cmd:  / head -c 16000 /


#######################################################################
#
#   -------------------  YOU REALLY SHOULD STOP HERE -------------------
#   ---------  values below this line are usually OK for almost all 
#   ---------  users to use unchanged - Gurus only beyond this point.
#
#######################################################################
#
#   If you want to change things here, go ahead, but realize you are
#   playing with things that can really hurt accuracy.  
#
#   This being open source, if you don't *think* about changing it,
#   what would be the use of it being open source?  That said, this
#   _is_ open source- you break it, you get to keep _both_ pieces!
#
#
#   ------------ CLF - The Classifier Flags ----------
#
#   ---------  Which classifier flags do we use?  Default for 20060101 has 
#   ---------  been changed to OSB UNIQUE MICROGROOM.  
#
#   ---------  A null setting gets you straight Markovian, without
#   ---------  microgrooming.   OSB uses less memory, is faster,
#   ---------  and is usually more accurate.  Correlative matching is 
#   ---------  100x - 1000x slower, but can match anything (binaries,
#   ---------  wide chars, unicode, virii, _anything_.  Winnow is a
#   ---------  non-statistical learning classificer with very nice 
#   ---------  accuracy (up to 2x SBPH).  Hyperspace is a pseudogaussian
#   ---------  KNN (K-nearest-neighbor) matcher.
#
#   ---------  This is also where we set whether to use microgrooming
#   ---------  or Arne optimization (they're currently mutually exclusive).
#   ---------  If you turn off microgrooming you get Arne optimization
#   ---------  automatically.
#
#   ---------  If you _change_ this, you _must_ empty out your .css or
#   ---------  .cow files and build fresh ones, because these
#   ---------  classifiers do NOT use compatible data storage formats!
#
#:clf: /microgroom/
#:clf: /osb/
#:clf: /osb microgroom/
:clf: /osb unique microgroom/
#:clf: /correlate/
#:clf: /winnow/
#:clf: /osbf/
#:clf: /osbf microgroom/
#:clf: /hyperspace/
#:clf: /hyperspace unique/
#
#
#
#     --------Thresholds for GOOD/UNSURE/SPAM thick-threshold training
#     -------
#     ------ A very small thick threshold (or zero!) works for Markovian.
#     ----- A thick threshold of 5 to 20 seems good for OSB, OSBF, 
#     ---- Hyperspace, Bit-Entropy, and Winnow.  If you want an asymmetric
#     --- threshold system, you can do that by having :good_threshold:
#     -- be different from :spam_threshold:.  The defaults are +/- 10.0
#
#
#   ---- Things rated equal to or better than this are GOOD email
#:good_threshold: /0.01/
#:good_threshold: /5.0/
:good_threshold: /10.0/
#:good_threshold: /20.0/
#
#   ---- Things rated less than or equal to this are SPAM
#:spam_threshold: /-0.01/
#:spam_threshold: /-5.0/
:spam_threshold: /-10.0/
#:spam_threshold: /-20.0/
  
#   ---- mailfilter uses a single threshold and operates symmetrically.
#   --- (this is only to provide backward compatibility)
:thick_threshold: /10.0/

#   ---- What regex do we use for LEARN/CLASSIFY?  the first is the
#   ---- "old standard".  Other ones are handy for different spam
#   ---- mixes.  The last one is for people who get a great deal of
#   ---- packed HTML spam, which is almost everybody in 2003, so it
#   ---- used to be the default.  But since spammers have shifted away
#   ---- from this, it isn't the default any longer.  IF you change
#   ---- this, you MUST rebuild your .css files with decent
#   ---- amounts of locally-grown spam and nonspam ( if you've been
#   ---- following instructions and using the "reaver" cache, this is
#   ---- easily done! )
#
:lcr: /[[:graph:]]+/
#:lcr: /[[:alnum:]]+/
#:lcr: /[-.,:[:alnum:]]+/
#:lcr: /[[:graph:]][-[:alnum:]]*[[:graph:]]?/
#:lcr: /[[:graph:]][-.,:[:alnum:]]*[[:graph:]]?/
#
#  this next one is pretty incomprehensible, and probably wrong...
#:lcr: /[[:print:]][/!?\#]?[-[[:alnum:]][[:punct:]]]*(?:[*'=;]|/?>|:/*)?
#
#
#     Expansions for antispamming.  You almost _always_ want these on,
#     unless you're debugging something really bizarre.

#  ---------  Do we enable spammus interruptus undo?  
:undo_interruptus: /no/
#:undo_interruptus: /yes/
#
#
#
# ------------ HIGHLY EXPERIMENTAL - automatic training!
#             enable this only if you really want to live VERY dangerously!
#              "Do you feel lucky today, punk?  Well, do ya?"
#
:automatic_training: /no/
#
#       ---- if you are living dangerously and have turned on autotraining,
#            you should also set the following to point to an address that
#            will get read on a quick basis, becuause this is where autotrain
#            verifications will go.
# 
#:autotrain_address: /root/


:datadir: /..\/..\/.var\/.crm114/