You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spamassassin.apache.org by qu...@apache.org on 2004/04/22 08:52:17 UTC

svn commit: rev 10168 - in incubator/spamassassin/trunk: rules t

Author: quinlan
Date: Wed Apr 21 23:52:16 2004
New Revision: 10168

Modified:
   incubator/spamassassin/trunk/rules/20_head_tests.cf
   incubator/spamassassin/trunk/rules/30_text_de.cf
   incubator/spamassassin/trunk/rules/30_text_fr.cf
   incubator/spamassassin/trunk/rules/30_text_pl.cf
   incubator/spamassassin/trunk/rules/50_scores.cf
   incubator/spamassassin/trunk/rules/70_testing.cf
   incubator/spamassassin/trunk/t/recips.t
Log:
merge VERY_SUSP_RECIPS into SUSPICIOUS_RECIPS (hit rate for
  VERY_SUSP_RECIPS is too low and scores were close to each other anyway)
test different thresholds for new SUSPICIOUS_RECIPS code


Modified: incubator/spamassassin/trunk/rules/20_head_tests.cf
==============================================================================
--- incubator/spamassassin/trunk/rules/20_head_tests.cf	(original)
+++ incubator/spamassassin/trunk/rules/20_head_tests.cf	Wed Apr 21 23:52:16 2004
@@ -397,11 +397,8 @@
 meta MISSING_SUBJECT		!__HAS_SUBJECT
 describe MISSING_SUBJECT	Missing Subject: header
 
-header SUSPICIOUS_RECIPS	eval:similar_recipients('0.6','1.2')
+header SUSPICIOUS_RECIPS	eval:similar_recipients('0.6','undef')
 describe SUSPICIOUS_RECIPS	Similar addresses in recipient list
-
-header VERY_SUSP_RECIPS		eval:similar_recipients('1.2','undef')
-describe VERY_SUSP_RECIPS	Very similar addresses in recipient list 
 
 header SORTED_RECIPS		eval:sorted_recipients()
 describe SORTED_RECIPS		Recipient list is sorted by address

Modified: incubator/spamassassin/trunk/rules/30_text_de.cf
==============================================================================
--- incubator/spamassassin/trunk/rules/30_text_de.cf	(original)
+++ incubator/spamassassin/trunk/rules/30_text_de.cf	Wed Apr 21 23:52:16 2004
@@ -230,7 +230,6 @@
 lang de describe ROUND_THE_WORLD "Received"-Kopfzeilen belegen Versand rund um die Welt (DNS)
 lang de describe MISSING_HEADERS Empf�ngeradresse ("To") fehlt
 lang de describe SUSPICIOUS_RECIPS Empf�ngeradressen sind sich �hnlich
-lang de describe VERY_SUSP_RECIPS Empf�ngeradressen sind sich sehr �hnlich
 lang de describe SORTED_RECIPS Empf�nger sind nach Adressen sortiert
 lang de describe USER_IN_BLACKLIST_TO Empf�ngeradresse ist in Parameter "blacklist_to" aufgelistet
 lang de describe USER_IN_WHITELIST_TO Empf�ngeradresse ist in Parameter "whitelist_to" aufgelistet

Modified: incubator/spamassassin/trunk/rules/30_text_fr.cf
==============================================================================
--- incubator/spamassassin/trunk/rules/30_text_fr.cf	(original)
+++ incubator/spamassassin/trunk/rules/30_text_fr.cf	Wed Apr 21 23:52:16 2004
@@ -674,7 +674,6 @@
 lang fr describe US_DOLLARS_2           Escroq. nig�rienne, version modifi�e, phrase cl� ($NNN.N m/USDNNN.N m)
 lang fr describe US_DOLLARS_3           Escroq. nig�rienne, version modifi�e, phrase cl� ($NN,NNN,NNN.NN)
 lang fr describe VAR_REF_IN_RECEIVED    Un en-t�te Received contient une r�f�rence $variable
-lang fr describe VERY_SUSP_RECIPS	L'en-t�te To: contient plus de dix fois le m�me nom de destinataire
 lang fr describe DRUG_ED_COMBO           Viagra et autres produits pharmaceutiques
 lang fr describe DRUG_ED_ONLINE          Vente de Viagra par correspondance
 lang fr describe WALAA			Les spammeurs illettr�s ne savent pas �crire "voil�"

Modified: incubator/spamassassin/trunk/rules/30_text_pl.cf
==============================================================================
--- incubator/spamassassin/trunk/rules/30_text_pl.cf	(original)
+++ incubator/spamassassin/trunk/rules/30_text_pl.cf	Wed Apr 21 23:52:16 2004
@@ -683,7 +683,6 @@
 lang pl describe USERNAME_IN_SUBJECT	Do: u�ytkownika - na pocz�tku tematu
 lang pl describe USERPASS		URL zawiera nazw� u�ytkownika i (opcjonalnie) has�o
 lang pl describe VAR_REF_IN_RECEIVED	Received: zawiera $zmienn� 'reference'
-lang pl describe VERY_SUSP_RECIPS	Do: zawiera podobn� domen� przynajmniej 10 razy.
 lang pl describe WALAA			Niepi�mienny spamer nie potrafi napisa� 'voila'
 lang pl describe WEALTH			Zdob�d� bogactwo
 lang pl describe WE_HATE_SPAM2		Nadawca jest przeciwko spamowi -- a my nie?

Modified: incubator/spamassassin/trunk/rules/50_scores.cf
==============================================================================
--- incubator/spamassassin/trunk/rules/50_scores.cf	(original)
+++ incubator/spamassassin/trunk/rules/50_scores.cf	Wed Apr 21 23:52:16 2004
@@ -519,7 +519,6 @@
 score TO_TXT 2.900 2.800 2.800 2.700
 score USERNAME_IN_SUBJECT 2.900 2.800 2.800 2.700
 score USE_IDENTITY 2.900 2.800 2.800 2.700
-score VERY_SUSP_RECIPS 2.900 2.800 2.800 2.700
 score DRUG_ED_COMBO 2.900 2.800 2.800 2.700
 score WITH_LC_SMTP 4.300 4.300 2.800 2.700
 score WRINKLES 4.300 4.300 4.100 4.100

Modified: incubator/spamassassin/trunk/rules/70_testing.cf
==============================================================================
--- incubator/spamassassin/trunk/rules/70_testing.cf	(original)
+++ incubator/spamassassin/trunk/rules/70_testing.cf	Wed Apr 21 23:52:16 2004
@@ -1,6 +1,6 @@
 # SpamAssassin rules file: rules under test, $Rev$
 #
-# This file is a placeholder for rules "under probation", ie. checked into
+# This file is a placeholder for rules "under probation", i.e. checked into
 # SVN for testing. It should not be distributed; if the rules have good
 # stats after a mass-check or two, then fold them into the distributed
 # rules files.
@@ -91,7 +91,7 @@
 # 0.683   1.3791   0.0134    0.990   0.90    0.01  T_URI_UNPRINTABLE:quinlan
 # 0.956   1.1479   0.5948    0.659   0.26    0.01  T_URI_UNPRINTABLE:rODbegbie
 # 0.734   0.7756   0.0885    0.898   0.66    0.01  T_URI_UNPRINTABLE:theo
-# FPs?  wierd
+# FPs?  weird
 uri	T_URI_UNPRINTABLE	/\%0/
 describe T_URI_UNPRINTABLE	URI contains unprintable characters
 
@@ -754,3 +754,10 @@
 meta T_DRUGS_MANYKINDS	(T_DRUGS_ERECTILE + T_DRUGS_DIET + T_DRUGS_PAIN + T_DRUGS_SLEEP + T_DRUGS_MUSCLE + T_DRUGS_ANXIETY + T_DRUGS_DEPRESSION >3)
 describe T_DRUGS_MANYKINDS 	contains refs to four different kinds of drugs
 
+# possible replacements for SUSPICIOUS_RECIPS
+header T_SUSPICIOUS_RECIPS_55	eval:similar_recipients('0.55','undef')
+header T_SUSPICIOUS_RECIPS_60	eval:similar_recipients('0.60','undef')
+header T_SUSPICIOUS_RECIPS_65	eval:similar_recipients('0.65','undef')
+header T_SUSPICIOUS_RECIPS_70	eval:similar_recipients('0.70','undef')
+header T_SUSPICIOUS_RECIPS_75	eval:similar_recipients('0.75','undef')
+header T_SUSPICIOUS_RECIPS_80	eval:similar_recipients('0.80','undef')

Modified: incubator/spamassassin/trunk/t/recips.t
==============================================================================
--- incubator/spamassassin/trunk/t/recips.t	(original)
+++ incubator/spamassassin/trunk/t/recips.t	Wed Apr 21 23:52:16 2004
@@ -2,28 +2,26 @@
 
 use lib '.'; use lib 't';
 use SATest; sa_t_init("recips");
-use Test; BEGIN { plan tests => 9 };
+use Test; BEGIN { plan tests => 6 };
 
 # ---------------------------------------------------------------------------
 
 %patterns = ( q{ SORTED_RECIPS } => 'SORTED_RECIPS',
-	      q{ VERY_SUSP_RECIPS } => 'VERY_SUSP_RECIPS');
-%anti_patterns = ( q{ SUSPICIOUS_RECIPS } => 'SUSPICIOUS_RECIPS',);
+	      q{ SUSPICIOUS_RECIPS } => 'SUSPICIOUS_RECIPS');
+%anti_patterns = ( );
 
 sarun ("-L -t < data/spam/010", \&patterns_run_cb);
 ok_all_patterns();
 
 %patterns = ( q{ SUSPICIOUS_RECIPS } => 'SUSPICIOUS_RECIPS');
-%anti_patterns = ( q{ SORTED_RECIPS } => 'SORTED_RECIPS',
-		   q{ VERY_SUSP_RECIPS } => 'VERY_SUSP_RECIPS',);
+%anti_patterns = ( q{ SORTED_RECIPS } => 'SORTED_RECIPS');
 
 sarun ("-L -t < data/spam/011", \&patterns_run_cb);
 ok_all_patterns();
 
 %patterns = ( );
 %anti_patterns = ( q{ SORTED_RECIPS } => 'SORTED_RECIPS',
-		   q{ SUSPICIOUS_RECIPS } => 'SUSPICIOUS_RECIPS',
-		   q{ VERY_SUSP_RECIPS } => 'VERY_SUSP_RECIPS',);
+		   q{ SUSPICIOUS_RECIPS } => 'SUSPICIOUS_RECIPS');
 
 sarun ("-L -t < data/nice/006", \&patterns_run_cb);
 ok_all_patterns();