# -*- sh -*-

# Please check if all the paths in PATH are reachable, remove the ones that
# are not.

PATH=$HOME/bin:/usr/bin:/bin:/usr/local/bin:.
MAILDIR=$HOME/Mail	# You'd better make sure it exists
LOGFILE=$MAILDIR/procmaillog
LOCKFILE=$HOME/.lockmail
SHELL=/bin/bash
FORMAIL=/usr/bin/formail

# Order matters, up until at least the duplicate catching clause.

#   Pure newline; typical usage if you want to write
#   Something directly to procmail's active logfile:
#
#       LOG = "$NL message $NL"
NL = "
"

:0
* ^Subject:\/.*
{
    SUBJECT = $MATCH
}

# Catch duplicates.  I got this from some forgotten webpage...
MID_CACHE_LEN   = 8192
MID_CACHE_FILE  = $MAILDIR/msgid.cache
MID_CACHE_LOCK  = $MAILDIR/msgid.cache$LOCKEXT

LOCKFILE = $MID_CACHE_LOCK

# IF  the message has a message-id header
# AND formail -D is successful (exit status=0)
# THEN
#   log a message to the procmail log
#   sink the message
:0
* ^Message-Id:
* ? $FORMAIL -D $MID_CACHE_LEN $MID_CACHE_FILE
{
    LOG="dupecheck: discarded message, $SUBJECT $NL"

    :0              # Store duplicates, notice no lock!
    duplicates
}

LOCKFILE            # Release lock by killing variable    

# Colloquial stuff...
:0 w:
* ^Subject: .*olloquium.*
| /users/rreid/bin/collofilt >> $MAILDIR/colloquia

:0 w:
* ^TO<Addresses removed to slow down spammers.  Ask me.>
* ^Subject: .*ELF.*
| /users/rreid/bin/collofilt >> $MAILDIR/colloquia

# Sort away mailing lists that should *not* go straight in the main inbox.
# $LIST idea for handling a lot of different lists at once from David Champion
# and David W. Tamkin.
LISTS = "(casca|drao|HIAlights|NRCEveryone)"

:0
* $ ^TO_()\/$LISTS
* $ LISTS ?? ()\/$\MATCH
{
    LIST=$MATCH
}

:0
* LIST ?? .
{
    # List mail that goes to its own box doesn't need [LIST] in its Subject:
    :0 f
    | $FORMAIL -i "Subject: `echo $SUBJECT | sed -e \"s/\[${LIST}[^]]*\] *//i\"`" -i "X-Label: ${LIST}"

    # Dump unwanted threads by Subject:
    :0:
    * ? $FORMAIL -x Subject: | grep -isF -f ~/.mutt/killfiles/${LIST}
    dumpedthreads

    # Dump unwanted subthreads by message ID:
    :0:
    * ? $FORMAIL -x References: | grep -isF -f ~/.mutt/killfiles/msgids/${LIST}
    dumpedthreads

    # Send it to a list.
    :0:
    $LIST
}

# Make freshmeat manageable...

# Doesn't work on polaris because it doesn't find BerkeleyDB.pm.
#:0 w
#* ^Subject:.\[fm-news\].Newsletter.*
#* !^X-Loop:.*whatsnewfm
#| /users/rreid/bin/whatsnewfm.pl

:0 w
* ^Subject:.\[fm-news\].Newsletter.*
* ^X-Loop:.*whatsnewfm
| /users/rreid/bin/wnfmsplit >> /users/rreid/mail/meat

# Trim whatsnewfm's update subjects.
:0 w:
* ^Subject: whatsnewfm.pl: Update:.*
* ^X-Loop:.*whatsnewfm
| sed -e 's/^\(Subject: \)whatsnewfm.pl: Update: \(.*\)/\1\2 update/' >> $MAILDIR/meat

:0h:
* ^X-Loop:.*whatsnewfm
meat

# Shuffle off known frequent perpetrators of boring email.
:0w:
* ? $FORMAIL -x"From" -x"From:" -x"Sender:" -x"Reply-To:" -x"Return-Path:" \
  | /bin/grep -isF -f $MAILDIR/boring.list 
boring

# Test if the email's sender is a V.I.P..  If so, don't frisk it!
# Warning! egrep is a CPU hog!
:0w: 
* ? $FORMAIL -x"From" -x"From:" -x"Sender:" -x"Reply-To:" -x"Return-Path:" \
  | /bin/grep -isF -f $MAILDIR/good.list 
/var/spool/mail/rreid

# Test if the email's sender is blacklisted; if so, send it to $CRAPFILE 
:0
* ? $FORMAIL -x"From" -x"From	:" -x"Sender:" -x"Reply-To:" -x"Return-Path:" \
  -x"To:" | /bin/grep -isF -f $MAILDIR/spammers.list 
{
    :0fwh
    | sed -e 's/^\(Subject: \)/\1BLACKLISTED! /'
    :0:
    $CRAPFILE
}

## Check with Vipul's Razor.
#:0 Wc
#| razor-check
#:0 faw:
#| sed -e 's/^\(Subject: \)/\1Razored! /'
#:0fw
#| spamassassin -P
#| sed -e 's/^\(Subject: \)/\1Razored!  /' >> $CRAPFILE

# Fsck Micro$oft!
# Their hotmail ads seem to end in </div><br clear=all><hr>spam<br></html>
# Getting rid of the ads also makes them less spammish before their trip
# through spamassassin.  Do NOT do this before razoring!
#:0 fwb
#* ^From .*@hotmail\..*
#| sed -e 's/<\/div><br clear=all><hr>.*<br><\/html>/<\/div><\/html>/'

## I don't want spam to go through w3m.
#:0 fwh
#* ^X-Spam-Flag: YES
#* ^Content-Type:.*text/html.*
#| $FORMAIL -I Content-Type:

#CPRE=`cat | grep '^Content preview' | cut -c 18-42 | sed 's/^/\'/' |sed 's/$/\'/'`
#* ^Content preview: .{,24}
#$CRAPFILE

#:0
#* ^X-Spam-Flag: YES
#{
#    CPRE=`cat | grep '^Content preview' | head -1 |cut -c 18-42|sed 's/%/S5/;s/This message is in MIME/MIME/'`
#
#    :0fhw
#    | sed -e "s%^\(Subject:\)%\1 ${CPRE} #Was:%"
## >> $CRAPFILE
#    :0:
#    $CRAPFILE
#}

# snag the To: and From: headers
#TO=`$FORMAIL -zx To:`
#CC=`$FORMAIL -zx Cc:`
#FROM=`$FORMAIL -zX From: | $FORMAIL -zrx To:`

:0:
* ^TOreid\+junk@
| sed -e 's/^\(Subject: \)/\1JUNK! /' >> $SPAMFILE

# This address seems to attract a lot of spam.
#:0:
#* ^TOda@astro\.utoronto\.ca
#| sed -e 's/^\(Subject: \)/\1DA! /' >> $SPAMFILE

# Killing header and footer ads
# if you know that the header is X lines long [let's say 5 for this example]
# and that the first line of the footer contains some string or pattern that
# will not occur in the significant part of the post,
#
#:0 fbwi
#      * conditions
#      | sed -ne 1,5d -e '/pattern/q' -e p

#If you recognize the end by the last line that you want to keep instead of the
#first line that you want to delete, omit the n option and the p instruction:
#
#| sed -e 1,5d -e '/pattern/q'

#Finally, if the only reliable way to spot the footer is by reaching so many
#lines from the end (because any search pattern might occur in the real text as
#well), we can score as you've been doing to get the number of the last
#significant line. Let's say the footer is three lines long; because ^.*$
#always counts one line too many (long story), we subtract four instead of
#three:

#:0 fbwi
#      * conditions
#      * 1^1 B ?? ^.*$
#      * -4^0
#      | sed -e 1,5d -e "$="q