Mailing List Archive

Author: jm
Date: Tue Jan 23 11:16:04 2007
New Revision: 499101

URL: http://svn.apache.org/viewvc?view=rev&rev=499101
Log:
add NO_HEADERS_MESSAGE, rule to detect corrupt corpora

Modified:
spamassassin/trunk/rules/20_head_tests.cf
spamassassin/trunk/rules/20_meta_tests.cf
spamassassin/trunk/rules/50_scores.cf

Modified: spamassassin/trunk/rules/20_head_tests.cf
URL: http://svn.apache.org/viewvc/spamassassin/trunk/rules/20_head_tests.cf?view=diff&rev=499101&r1=499100&r2=499101
==============================================================================
--- spamassassin/trunk/rules/20_head_tests.cf (original)
+++ spamassassin/trunk/rules/20_head_tests.cf Tue Jan 23 11:16:04 2007
@@ -254,7 +254,8 @@
header NONEXISTENT_CHARSET Content-Type =~ /charset=.?DEFAULT/
describe NONEXISTENT_CHARSET Character set doesn't exist

-
+header MISSING_MID Message-Id =~ /^UNSET$/ [if-unset: UNSET]
+describe MISSING_MID Missing Message-Id: header

header MISSING_DATE Date =~ /^UNSET$/ [if-unset: UNSET]
describe MISSING_DATE Missing Date: header

Modified: spamassassin/trunk/rules/20_meta_tests.cf
URL: http://svn.apache.org/viewvc/spamassassin/trunk/rules/20_meta_tests.cf?view=diff&rev=499101&r1=499100&r2=499101
==============================================================================
--- spamassassin/trunk/rules/20_meta_tests.cf (original)
+++ spamassassin/trunk/rules/20_meta_tests.cf Tue Jan 23 11:16:04 2007
@@ -61,6 +61,9 @@
meta EMPTY_MESSAGE !__MIME_ATTACHMENT && !__NONEMPTY_BODY
describe EMPTY_MESSAGE Message appears to have no textual parts and no Subject: text

+meta NO_HEADERS_MESSAGE (MISSING_DATE && MISSING_HEADERS && NO_RECEIVED && NO_RELAYS && MISSING_MID)
+describe NO_HEADERS_MESSAGE Message appears to be missing most RFC-822 headers
+
###########################################################################

ifplugin Mail::SpamAssassin::Plugin::MIMEEval

Modified: spamassassin/trunk/rules/50_scores.cf
URL: http://svn.apache.org/viewvc/spamassassin/trunk/rules/50_scores.cf?view=diff&rev=499101&r1=499100&r2=499101
==============================================================================
--- spamassassin/trunk/rules/50_scores.cf (original)
+++ spamassassin/trunk/rules/50_scores.cf Tue Jan 23 11:16:04 2007
@@ -494,6 +494,9 @@
# Informational rules about Received header parsing
score NO_RECEIVED -0.001

+# Informational rule, typically means corrupt corpus/input
+score NO_HEADERS_MESSAGE 0.001
+
# ok_locales
score HTML_CHARSET_FARAWAY 0.500
score MIME_CHARSET_FARAWAY 2.450