Mailing List Archive

Author: quinlan
Date: Fri Mar 26 23:02:41 2004
New Revision: 9781

Modified:
incubator/spamassassin/trunk/rules/20_html_tests.cf
incubator/spamassassin/trunk/rules/70_testing.cf
Log:
remove HTML_COMMENT_EMAIL (low performer)
remove HTML_COMMENT_8BITS (locale-specific, 0.5 S/O)
promote T_HTML_COMMENT_TINY6 to HTML_COMMENT_SHORT (T_HTML_TINY_COMMENTS had
better accuracy, but seemed too specific/fragile)


Modified: incubator/spamassassin/trunk/rules/20_html_tests.cf
==============================================================================
--- incubator/spamassassin/trunk/rules/20_html_tests.cf (original)
+++ incubator/spamassassin/trunk/rules/20_html_tests.cf Fri Mar 26 23:02:41 2004
@@ -76,14 +76,11 @@
describe HTML_TABLE_THICK_BORD HTML table has thick border

# HTML comment tests
-body HTML_COMMENT_EMAIL eval:html_text('comment', '=~ /\S+\@\S+/')
-describe HTML_COMMENT_EMAIL HTML comment contains email address
+body HTML_COMMENT_SHORT eval:html_text('comment', '=~ /<!(?!-).{0,6}>/')
+describe HTML_COMMENT_SHORT HTML comment is very short

body HTML_COMMENT_SHOUTING eval:html_test('comment_shouting')
describe HTML_COMMENT_SHOUTING HTML comment inside of "shouting" markup
-
-body HTML_COMMENT_8BITS eval:html_text('comment', '=~ /[\x80-\xff]{3,}/')
-describe HTML_COMMENT_8BITS HTML comment has 3 consecutive 8-bit chars

body HTML_COMMENT_SAVED_URL eval:html_text('comment', '=~ /<!-- saved from url=\(\d{4}\)/')
describe HTML_COMMENT_SAVED_URL HTML message is a saved web page

Modified: incubator/spamassassin/trunk/rules/70_testing.cf
==============================================================================
--- incubator/spamassassin/trunk/rules/70_testing.cf (original)
+++ incubator/spamassassin/trunk/rules/70_testing.cf Fri Mar 26 23:02:41 2004
@@ -454,19 +454,6 @@
header T_SUBJ_2_NUM_PARENS Subject =~ /^\(\d+\).*\(\d+\)\s*$/
describe T_SUBJ_2_NUM_PARENS Subject contains common spam sign (2 numbers)

-rawbody T_HTML_TINY_COMMENTS /<![a-z0-9]>/i
-# these are here to make your life easier
-body T_HTML_COMMENT_TINY0 eval:html_text('comment', '=~ /<!>/i')
-body T_HTML_COMMENT_TINY1 eval:html_text('comment', '=~ /<!.?>/i')
-body T_HTML_COMMENT_TINY2 eval:html_text('comment', '=~ /<!.{0,2}>/i')
-body T_HTML_COMMENT_TINY3 eval:html_text('comment', '=~ /<!.{0,3}>/i')
-body T_HTML_COMMENT_TINY4 eval:html_text('comment', '=~ /<!(?!-).{0,4}>/i')
-body T_HTML_COMMENT_TINY5 eval:html_text('comment', '=~ /<!(?!-).{0,5}>/i')
-body T_HTML_COMMENT_TINY6 eval:html_text('comment', '=~ /<!(?!-).{0,6}>/i')
-body T_HTML_COMMENT_TINY7 eval:html_text('comment', '=~ /<!(?!-).{0,7}>/i')
-body T_HTML_COMMENT_TINY8 eval:html_text('comment', '=~ /<!(?!-).{0,8}>/i')
-body T_HTML_COMMENT_TINY9 eval:html_text('comment', '=~ /<!(?!-).{0,9}>/i')
-
# some SenderBase tests
header __SENDERBASE eval:check_rbl_txt('senderbase', 'sa.senderbase.org.')