]> git.madduck.net Git - etc/mailfilter.git/blobdiff - procmail/defines

madduck's git repository

Every one of the projects in this repository is available at the canonical URL git://git.madduck.net/madduck/pub/<projectpath> — see each project's metadata for the exact URL.

All patches and comments are welcome. Please squash your changes to logical commits before using git-format-patch and git-send-email to patches@git.madduck.net. If you'd read over the Git project's submission guidelines and adhered to them, I'd be especially grateful.

SSH access, as well as push access can be individually arranged.

If you use my repositories frequently, consider adding the following snippet to ~/.gitconfig and using the third clone URL listed for each project:

[url "git://git.madduck.net/madduck/"]
  insteadOf = madduck:

lower SA limit for autotraining ham to unsure crm
[etc/mailfilter.git] / procmail / defines
index 93efda83ccdbc2689f7f65380b6534eb5e0ff6c3..43945cdb9c89492f13ec6c1c85def19e27383982 100644 (file)
@@ -25,6 +25,7 @@ PROCMAIL="$NICE /usr/bin/procmail -p $PMDIR/procmailrc"
 FORMAIL="$NICE /usr/bin/formail -f"
 EGREP="$NICE /bin/egrep"
 SED="$NICE /bin/sed"
+BIN_DATE="/bin/date"
 DELIVER="$NICE /usr/lib/dovecot/deliver"
 
 CRM114="$NICE /usr/share/crm114/mailreaver.crm -u $MAILFILT/crm114/"
@@ -32,10 +33,9 @@ SA_PREFS="$MAILFILT/spamassassin/user_prefs"
 SPAMASSASSIN="$NICE /usr/bin/spamassassin --prefs-file=$SA_PREFS"
 SPAMC="$NICE /usr/bin/spamc --log-to-stderr --no-safe-fallback"
 #SPAMC="$SPAMASSASSIN"
-TRAINER="$MAILFILT/bin/train"
+TRAINER="$NICE $MAILFILT/bin/train"
 
-OURDATE=`date -R`
-OURDATE_SHORT=`date +%Y.%m.%d.%H.%M.%N`
+SQLITE="$NICE /usr/bin/sqlite3"
 
 BASE=$HOME/.maildir
 
@@ -48,7 +48,7 @@ SPAMCHECK_MAX_MESSAGE_SIZE=512000
 
 # if crm114 is unsure and SA returns a score less-than-or-equal to this,
 # autotrain crm114 with ham
-CRM_UNSURE_SA_AUTOTRAIN_LIMIT_HAM=2.0
+CRM_UNSURE_SA_AUTOTRAIN_LIMIT_HAM=0.0
 # if crm114 classifies a message as spam but SA returns a score
 # less-than-or-equal to this, retrain crm114
 CRM_MISCLASSIFY_SA_AUTOTRAIN_LIMIT_HAM=-1.0
@@ -64,17 +64,36 @@ NL="
 "
 RE_MYDOMAIN="(.+\.)*madduck\.net"
 RE_MAILRELAYS="(seamus|clegg)\.madduck\.net"
-RE_SPACE_NEWLINE="(^|[         ])"
+RE_SPACE="[    ]"
+RE_NOT_SPACE="[^       ]"
+RE_SPACE_NEWLINE="(^|$RE_SPACE)"
 RE_FIRSTNAME="martin($RE_SPACE_NEWLINE+f(\.?|elix))?"
 RE_LASTNAME="kraff?t"
-RE_EXTRACT_HEADER_VALUE="[     ]*\/[^  ].*"
+RE_EXTRACT_HEADER_VALUE="$RE_SPACE*\/$RE_NOT_SPACE.*"
 
 DEJAVU_HEADER=X-Deja-Vu
 
 NULL=/dev/null
+DELAYED_QUEUE=$BASE/.delayed/
+TICKLER_QUEUE=$BASE/.store/
 DISCARD=$BASE/.discard/
+SPAM=$BASE/.spam/
 #DISCARD="'|$DELIVER -m BASE.discard'"
 
+DELAY_NEXT_WEEKEND='next sunday 28 hours ago' # fri night, 20:00
+DELAY_TONIGHT='tomorrow 00:00 4 hours ago' # tonight at 20:00
+
+OURDATE="`$BIN_DATE +'%s %Y.%m.%d.%H.%M.%N %a, %d %b %Y %T %z'`"
+:0
+*$ OURDATE ?? ^\/${RE_NOT_SPACE}+
+{ OURDATE_TS="$MATCH" }
+:0
+*$ OURDATE ?? ^[0-9]+${RE_SPACE}+\/${RE_NOT_SPACE}+
+{ OURDATE_SHORT="$MATCH" }
+:0
+*$ OURDATE ?? ^[0-9]+${RE_SPACE}+[0-9.]+${RE_SPACE}+\/.+
+{ OURDATE="$MATCH" }
+
 ### variables from the message
 
 ### local recipient data
@@ -111,14 +130,35 @@ INCLUDERC=$PMDIR/get-msgid
 
 :0
 *$ ^Subject:$RE_EXTRACT_HEADER_VALUE
-{ SUBJECT="$MATCH" }
+{
+  SUBJECT=$MATCH
+
+  # mimedecode.c: * Disclaimer: We only handle charset of iso-8859-1
+  :0
+  * SUBJECT ?? ^=\?iso-8859-1\?[QB]\?.+\?=$
+  {
+    DECODED="`echo Subject: $SUBJECT | mimedecode | iconv -f latin1 -t utf-8`"
+    :0
+    *$ DECODED ?? ^Subject:$RE_EXTRACT_HEADER_VALUE
+    { SUBJECT=$MATCH }
+  }
+}
 
 :0
 *$ ^X-Original-To:$RE_EXTRACT_HEADER_VALUE
 { ORIGINAL_TO="$MATCH" }
 :0 E
+* ^Received:
 { LOG="NO ORIGINAL_TO: $MSGID" }
 
+:0
+*$ ^X-Trained-As:$RE_EXTRACT_HEADER_VALUE
+{ TRAINED_AS="$MATCH" }
+
+:0
+*$ ^X-Postponed:$RE_EXTRACT_HEADER_VALUE
+{ POSTPONED="$MATCH" }
+
 # fix variable values for special cases
 INCLUDERC=$PMDIR/normalise
 
@@ -180,6 +220,6 @@ RETRAIN
 # if set, contains reason why justme message was passed
 JUSTME
 
-# TRAINED_AS
-# if set, contains category with which this message has just been trained
-TRAINED_AS
+# DISABLE_DELAYS
+# if set, disables delaying messages
+DISABLE_DELAYS