Mailing List Archive

Author: quinlan
Date: Fri Mar 26 23:44:34 2004
New Revision: 9787

Modified:
incubator/spamassassin/trunk/rules/20_html_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
Log:
HTML tests


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 23:44:34 2004
@@ -260,9 +260,6 @@
body HTML_TAG_BALANCE_HEAD eval:html_tag_balance('head', '!= 0')
describe HTML_TAG_BALANCE_HEAD HTML has unbalanced "head" tags

-body HTML_TAG_BALANCE_TABLE eval:html_tag_balance('table', '> 0')
-describe HTML_TAG_BALANCE_TABLE HTML is missing "table" close tags
-
body HTML_TAG_EXIST_MARQUEE eval:html_tag_exists('marquee')
describe HTML_TAG_EXIST_MARQUEE HTML has "marquee" tag


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 Fri Mar 26 23:44:34 2004
@@ -383,7 +383,6 @@
lang de describe HTML_TAG_BALANCE_HTML Anzahl "html"-Markierungen nicht ausgeglichen
lang de describe HTML_TAG_BALANCE_BODY Anzahl "body"-Markierungen nicht ausgeglichen
lang de describe HTML_TAG_BALANCE_HEAD Anzahl "head"-Markierungen nicht ausgeglichen
-lang de describe HTML_TAG_BALANCE_TABLE fehlender Tabellenabschluß in HTML-Nachricht
lang de describe HTML_TITLE_EMPTY HTML-Nachricht mit leerem Titel
lang de describe HTML_TITLE_UNTITLED HTML-Nachricht mit Titel "Untitled"
lang de describe HTML_CHARSET_FARAWAY Fremdsprachlicher Zeichensatz für HTML benutzt

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 Fri Mar 26 23:44:34 2004
@@ -356,7 +356,6 @@
lang fr describe HTML_TAG_BALANCE_BODY Le tag de fermeture de "body" HTML est manquant
lang fr describe HTML_TAG_BALANCE_HEAD Le tag de fermeture de "head" HTML est manquant
lang fr describe HTML_TAG_BALANCE_HTML Le tag de fermeture "html" est manquant
-lang fr describe HTML_TAG_BALANCE_TABLE Le tag de fermeture de table HTML est manquant
lang fr describe HTML_TITLE_EMPTY Le titre HTML ne contient aucun texte
lang fr describe HTML_TITLE_UNTITLED Le titre HTML contient "untitled" (sans-titre)
lang fr describe HTML_WEB_BUGS Tag image HTML avec un code ID permettant de vous identifier

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 Fri Mar 26 23:44:34 2004
@@ -383,7 +383,6 @@
lang pl describe HTML_TAG_BALANCE_BODY HTML posiada niepozamykane znaczniki w "body"
lang pl describe HTML_TAG_BALANCE_HEAD HTML posiada niepozamykane znaczniki w "head"
lang pl describe HTML_TAG_BALANCE_HTML HTML posiada niepozamykane znaczniki "html"
-lang pl describe HTML_TAG_BALANCE_TABLE HTML posiada niepozamykane znaczniki "table"
lang pl describe HTML_TITLE_EMPTY Tytu³ HTML nie zawiera tekstu
lang pl describe HTML_TITLE_UNTITLED Tytu³ HTML zawiera "bez tytu³u" (ang.)
lang pl describe HTML_WEB_BUGS Znacznik grafiki maj±cy na celu identyfikacjê osobow±

Modified: incubator/spamassassin/trunk/rules/50_scores.cf
==============================================================================
--- incubator/spamassassin/trunk/rules/50_scores.cf (original)
+++ incubator/spamassassin/trunk/rules/50_scores.cf Fri Mar 26 23:44:34 2004
@@ -265,7 +265,6 @@
score HTML_TABLE_THICK_BORD 0.580 0.699 0.001 0.001
score HTML_TAG_BALANCE_BODY 0.353 0.257 0.233 0.001
score HTML_TAG_BALANCE_HTML 0.671 0.411 0.099 0.001
-score HTML_TAG_BALANCE_TABLE 0.667 0.196 0.154 0.001
score HTML_TITLE_EMPTY 0.449 0.544 0.200 0.119
score HTML_TITLE_UNTITLED 0.501 0.699 0.360 0.430
score HTML_WEB_BUGS 1.116 0.587 0.279 0.336

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 23:44:34 2004
@@ -176,25 +176,18 @@
header T_FRAGMENTED_MESSAGE Content-Type =~ /message\/partial/i

# some HTML rules to try
-body T_HTML_TAG_BALANCE_FONT_0 eval:html_tag_balance('font', '!= 0')
-describe T_HTML_TAG_BALANCE_FONT_0 HTML has unbalanced "font" tags
-
-body T_HTML_TAG_BALANCE_FONT_1 eval:html_tag_balance('font', '> 0')
-describe T_HTML_TAG_BALANCE_FONT_1 HTML is missing "font" close tags
-
-body T_HTML_TAG_BALANCE_FONT_2 eval:html_tag_balance('font', '> 1')
-describe T_HTML_TAG_BALANCE_FONT_2 HTML is missing some "font" close tags
-
-body T_HTML_TAG_BALANCE_DIV_1 eval:html_tag_balance('div', '!= 0')
-describe T_HTML_TAG_BALANCE_DIV_1 HTML has unbalanced "font" tags
-
-body T_HTML_TAG_BALANCE_DIV_2 eval:html_tag_balance('div', '> 0')
-describe T_HTML_TAG_BALANCE_DIV_2 HTML is missing "div" tags
-
body T_HTML_FONT_SMALL_SIZE_1 eval:html_eval('min_size', '< 1')
body T_HTML_FONT_SMALL_SIZE_2 eval:html_eval('min_size', '< 0')
body T_HTML_FONT_SMALL_SIZE_3 eval:html_eval('min_size', '< -1')

+body T_HTML_FONT_SIZE_BIG eval:html_range('max_size', '4', '5')
+body T_HTML_FONT_SIZE_LARGE eval:html_range('max_size', '5', '6')
+body T_HTML_FONT_SIZE_HUGE eval:html_range('max_size', '6', 'undef')
+
+body T_HTML_FONT_SIZE_BIGGER eval:html_range('max_size', '4.5', '5.5')
+body T_HTML_FONT_SIZE_LARGER eval:html_range('max_size', '5.5', '6.5')
+body T_HTML_FONT_SIZE_HUGER eval:html_range('max_size', '6.5', 'undef')
+
body T_HTML_FONT_LARGE_SIZE eval:html_eval('max_size', '> 3')
body T_HTML_FONT_LARGE_SIZE_0 eval:html_eval('max_size', '> 4')
body T_HTML_FONT_LARGE_SIZE_1 eval:html_eval('max_size', '> 5')
@@ -209,6 +202,7 @@

# bug 2950
# both look promotable
+# really? low hit rates...
uri T_GOOGLE_IMAGES m{^http://images\.google(\.\S+)?\.[a-z]{2,3}/imgres\?}i
uri T_GOOGLE_REDIR m{^http://www\.google(\.\S+)?\.[a-z]{2,3}/url\?}i