Author: jm
Date: Wed Dec 13 05:07:13 2006
New Revision: 486633
URL: http://svn.apache.org/viewvc?view=rev&rev=486633
Log:
bug 5242: resurrect previously-removed rules HTML_IMAGE_RATIO_04, HTML_IMAGE_RATIO_06, HTML_IMAGE_RATIO_08
Modified:
spamassassin/trunk/rules/20_html_tests.cf
spamassassin/trunk/rules/30_text_de.cf
spamassassin/trunk/rules/30_text_fr.cf
spamassassin/trunk/rules/30_text_nl.cf
spamassassin/trunk/rules/30_text_pl.cf
spamassassin/trunk/rules/50_scores.cf
Modified: spamassassin/trunk/rules/20_html_tests.cf
URL: http://svn.apache.org/viewvc/spamassassin/trunk/rules/20_html_tests.cf?view=diff&rev=486633&r1=486632&r2=486633
==============================================================================
--- spamassassin/trunk/rules/20_html_tests.cf (original)
+++ spamassassin/trunk/rules/20_html_tests.cf Wed Dec 13 05:07:13 2006
@@ -142,7 +142,13 @@
# HTML_IMAGE_RATIO - more image area than text (ratio)
body HTML_IMAGE_RATIO_02 eval:html_image_ratio('0.000','0.002')
-describe HTML_IMAGE_RATIO_02 HTML has a low ratio of text to image area
+body HTML_IMAGE_RATIO_04 eval:html_image_ratio('0.002','0.004')
+body HTML_IMAGE_RATIO_06 eval:html_image_ratio('0.004','0.006')
+body HTML_IMAGE_RATIO_08 eval:html_image_ratio('0.006','0.008')
+describe HTML_IMAGE_RATIO_02 HTML has a low ratio of text to image area
+describe HTML_IMAGE_RATIO_04 HTML has a low ratio of text to image area
+describe HTML_IMAGE_RATIO_06 HTML has a low ratio of text to image area
+describe HTML_IMAGE_RATIO_08 HTML has a low ratio of text to image area
# HTML obfuscation
body HTML_OBFUSCATE_05_10 eval:html_range('obfuscation_ratio','.05','.1')
Modified: spamassassin/trunk/rules/30_text_de.cf
URL: http://svn.apache.org/viewvc/spamassassin/trunk/rules/30_text_de.cf?view=diff&rev=486633&r1=486632&r2=486633
==============================================================================
--- spamassassin/trunk/rules/30_text_de.cf (original)
+++ spamassassin/trunk/rules/30_text_de.cf Wed Dec 13 05:07:13 2006
@@ -252,6 +252,9 @@
lang de describe HTML_IMAGE_ONLY_20 Außer Bildern nur 1600-2000 Zeichen Text
lang de describe HTML_IMAGE_ONLY_24 Außer Bildern nur 2000-2400 Zeichen Text
lang de describe HTML_IMAGE_RATIO_02 Verhältnis Bilderfläche zu Text ist klein
+lang de describe HTML_IMAGE_RATIO_04 Verhältnis Bilderfläche zu Text ist klein
+lang de describe HTML_IMAGE_RATIO_06 Verhältnis Bilderfläche zu Text ist klein
+lang de describe HTML_IMAGE_RATIO_08 Verhältnis Bilderfläche zu Text ist klein
lang de describe HTML_OBFUSCATE_05_10 Nachrichtentext enthält 0-10% wirres HTML
lang de describe HTML_OBFUSCATE_10_20 Nachrichtentext enthält 10-20% wirres HTML
lang de describe HTML_OBFUSCATE_20_30 Nachrichtentext enthält 20-30% wirres HTML
Modified: spamassassin/trunk/rules/30_text_fr.cf
URL: http://svn.apache.org/viewvc/spamassassin/trunk/rules/30_text_fr.cf?view=diff&rev=486633&r1=486632&r2=486633
==============================================================================
--- spamassassin/trunk/rules/30_text_fr.cf (original)
+++ spamassassin/trunk/rules/30_text_fr.cf Wed Dec 13 05:07:13 2006
@@ -166,6 +166,9 @@
lang fr describe HTML_IMAGE_ONLY_08 HTML contient images avec 600 Ã 800 octets de texte
lang fr describe HTML_IMAGE_ONLY_12 HTML contient images avec 1000 Ã 1200 octets de texte
lang fr describe HTML_IMAGE_RATIO_02 HTML Faible ratio de texte par rapport aux images
+lang fr describe HTML_IMAGE_RATIO_04 HTML Faible ratio de texte par rapport aux images
+lang fr describe HTML_IMAGE_RATIO_06 HTML Faible ratio de texte par rapport aux images
+lang fr describe HTML_IMAGE_RATIO_08 HTML Faible ratio de texte par rapport aux images
lang fr describe HTML_MESSAGE HTML inclus dans le message
lang fr describe HTML_MIME_NO_HTML_TAG Message en HTML seul, mais sans tags HTML
lang fr describe HTML_TAG_BALANCE_BODY Le tag de fermeture de "body" HTML est manquant
Modified: spamassassin/trunk/rules/30_text_nl.cf
URL: http://svn.apache.org/viewvc/spamassassin/trunk/rules/30_text_nl.cf?view=diff&rev=486633&r1=486632&r2=486633
==============================================================================
--- spamassassin/trunk/rules/30_text_nl.cf (original)
+++ spamassassin/trunk/rules/30_text_nl.cf Wed Dec 13 05:07:13 2006
@@ -152,6 +152,9 @@
lang nl describe HTML_IMAGE_ONLY_08 HTML: plaatjes met 600-800 bytes aan woorden
lang nl describe HTML_IMAGE_ONLY_12 HTML: plaatjes met 1000-1200 bytes aan woorden
lang nl describe HTML_IMAGE_RATIO_02 HTML heeft een lage verhouding tussen tekst en plaatjes
+lang nl describe HTML_IMAGE_RATIO_04 HTML heeft een lage verhouding tussen tekst en plaatjes
+lang nl describe HTML_IMAGE_RATIO_06 HTML heeft een lage verhouding tussen tekst en plaatjes
+lang nl describe HTML_IMAGE_RATIO_08 HTML heeft een lage verhouding tussen tekst en plaatjes
lang nl describe HTML_OBFUSCATE_10_20 Bericht bevat 10% tot 20% HTML verdoezeling
lang nl describe HTML_OBFUSCATE_20_30 Bericht bevat 20% tot 30% HTML verdoezeling
lang nl describe HTML_OBFUSCATE_30_40 Bericht bevat 30% tot 40% HTML verdoezeling
Modified: spamassassin/trunk/rules/30_text_pl.cf
URL: http://svn.apache.org/viewvc/spamassassin/trunk/rules/30_text_pl.cf?view=diff&rev=486633&r1=486632&r2=486633
==============================================================================
--- spamassassin/trunk/rules/30_text_pl.cf (original)
+++ spamassassin/trunk/rules/30_text_pl.cf Wed Dec 13 05:07:13 2006
@@ -150,6 +150,9 @@
lang pl describe HTML_IMAGE_ONLY_08 HTML: grafika i 600-800 bajtów s³ów
lang pl describe HTML_IMAGE_ONLY_12 HTML: grafika i 1000-1200 bajtów s³ów
lang pl describe HTML_IMAGE_RATIO_02 HTML posiada niski stosunek objêto¶ci tekstu do obrazu
+lang pl describe HTML_IMAGE_RATIO_04 HTML posiada niski stosunek objêto¶ci tekstu do obrazu
+lang pl describe HTML_IMAGE_RATIO_06 HTML posiada niski stosunek objêto¶ci tekstu do obrazu
+lang pl describe HTML_IMAGE_RATIO_08 HTML posiada niski stosunek objêto¶ci tekstu do obrazu
lang pl describe HTML_MESSAGE Wiadomo¶æ zawiera kod HTML
lang pl describe HTML_MIME_NO_HTML_TAG Wiadomo¶æ ca³kowicie w HTML, lecz bez odpowiedniego oznaczenia
lang pl describe HTML_TAG_BALANCE_BODY HTML posiada niepozamykane znaczniki w "body"
Modified: spamassassin/trunk/rules/50_scores.cf
URL: http://svn.apache.org/viewvc/spamassassin/trunk/rules/50_scores.cf?view=diff&rev=486633&r1=486632&r2=486633
==============================================================================
--- spamassassin/trunk/rules/50_scores.cf (original)
+++ spamassassin/trunk/rules/50_scores.cf Wed Dec 13 05:07:13 2006
@@ -325,6 +325,9 @@
score HTML_IMAGE_ONLY_28 1.438 1.014 1.732 1.900
score HTML_IMAGE_ONLY_32 1.423 0.836 1.610 1.052
score HTML_IMAGE_RATIO_02 1.245 0.192 1.800 0.463
+score HTML_IMAGE_RATIO_04 0.877 0.001 1.057 0.001
+score HTML_IMAGE_RATIO_06 0.001 0.001 0.139 0.001
+score HTML_IMAGE_RATIO_08 0.001
score HTML_OBFUSCATE_05_10 1.421 1.169 1.522 1.449
score HTML_OBFUSCATE_10_20 1.936 1.397 2.371 1.770
score HTML_OBFUSCATE_20_30 2.720 2.720 3.145 3.400
Date: Wed Dec 13 05:07:13 2006
New Revision: 486633
URL: http://svn.apache.org/viewvc?view=rev&rev=486633
Log:
bug 5242: resurrect previously-removed rules HTML_IMAGE_RATIO_04, HTML_IMAGE_RATIO_06, HTML_IMAGE_RATIO_08
Modified:
spamassassin/trunk/rules/20_html_tests.cf
spamassassin/trunk/rules/30_text_de.cf
spamassassin/trunk/rules/30_text_fr.cf
spamassassin/trunk/rules/30_text_nl.cf
spamassassin/trunk/rules/30_text_pl.cf
spamassassin/trunk/rules/50_scores.cf
Modified: spamassassin/trunk/rules/20_html_tests.cf
URL: http://svn.apache.org/viewvc/spamassassin/trunk/rules/20_html_tests.cf?view=diff&rev=486633&r1=486632&r2=486633
==============================================================================
--- spamassassin/trunk/rules/20_html_tests.cf (original)
+++ spamassassin/trunk/rules/20_html_tests.cf Wed Dec 13 05:07:13 2006
@@ -142,7 +142,13 @@
# HTML_IMAGE_RATIO - more image area than text (ratio)
body HTML_IMAGE_RATIO_02 eval:html_image_ratio('0.000','0.002')
-describe HTML_IMAGE_RATIO_02 HTML has a low ratio of text to image area
+body HTML_IMAGE_RATIO_04 eval:html_image_ratio('0.002','0.004')
+body HTML_IMAGE_RATIO_06 eval:html_image_ratio('0.004','0.006')
+body HTML_IMAGE_RATIO_08 eval:html_image_ratio('0.006','0.008')
+describe HTML_IMAGE_RATIO_02 HTML has a low ratio of text to image area
+describe HTML_IMAGE_RATIO_04 HTML has a low ratio of text to image area
+describe HTML_IMAGE_RATIO_06 HTML has a low ratio of text to image area
+describe HTML_IMAGE_RATIO_08 HTML has a low ratio of text to image area
# HTML obfuscation
body HTML_OBFUSCATE_05_10 eval:html_range('obfuscation_ratio','.05','.1')
Modified: spamassassin/trunk/rules/30_text_de.cf
URL: http://svn.apache.org/viewvc/spamassassin/trunk/rules/30_text_de.cf?view=diff&rev=486633&r1=486632&r2=486633
==============================================================================
--- spamassassin/trunk/rules/30_text_de.cf (original)
+++ spamassassin/trunk/rules/30_text_de.cf Wed Dec 13 05:07:13 2006
@@ -252,6 +252,9 @@
lang de describe HTML_IMAGE_ONLY_20 Außer Bildern nur 1600-2000 Zeichen Text
lang de describe HTML_IMAGE_ONLY_24 Außer Bildern nur 2000-2400 Zeichen Text
lang de describe HTML_IMAGE_RATIO_02 Verhältnis Bilderfläche zu Text ist klein
+lang de describe HTML_IMAGE_RATIO_04 Verhältnis Bilderfläche zu Text ist klein
+lang de describe HTML_IMAGE_RATIO_06 Verhältnis Bilderfläche zu Text ist klein
+lang de describe HTML_IMAGE_RATIO_08 Verhältnis Bilderfläche zu Text ist klein
lang de describe HTML_OBFUSCATE_05_10 Nachrichtentext enthält 0-10% wirres HTML
lang de describe HTML_OBFUSCATE_10_20 Nachrichtentext enthält 10-20% wirres HTML
lang de describe HTML_OBFUSCATE_20_30 Nachrichtentext enthält 20-30% wirres HTML
Modified: spamassassin/trunk/rules/30_text_fr.cf
URL: http://svn.apache.org/viewvc/spamassassin/trunk/rules/30_text_fr.cf?view=diff&rev=486633&r1=486632&r2=486633
==============================================================================
--- spamassassin/trunk/rules/30_text_fr.cf (original)
+++ spamassassin/trunk/rules/30_text_fr.cf Wed Dec 13 05:07:13 2006
@@ -166,6 +166,9 @@
lang fr describe HTML_IMAGE_ONLY_08 HTML contient images avec 600 Ã 800 octets de texte
lang fr describe HTML_IMAGE_ONLY_12 HTML contient images avec 1000 Ã 1200 octets de texte
lang fr describe HTML_IMAGE_RATIO_02 HTML Faible ratio de texte par rapport aux images
+lang fr describe HTML_IMAGE_RATIO_04 HTML Faible ratio de texte par rapport aux images
+lang fr describe HTML_IMAGE_RATIO_06 HTML Faible ratio de texte par rapport aux images
+lang fr describe HTML_IMAGE_RATIO_08 HTML Faible ratio de texte par rapport aux images
lang fr describe HTML_MESSAGE HTML inclus dans le message
lang fr describe HTML_MIME_NO_HTML_TAG Message en HTML seul, mais sans tags HTML
lang fr describe HTML_TAG_BALANCE_BODY Le tag de fermeture de "body" HTML est manquant
Modified: spamassassin/trunk/rules/30_text_nl.cf
URL: http://svn.apache.org/viewvc/spamassassin/trunk/rules/30_text_nl.cf?view=diff&rev=486633&r1=486632&r2=486633
==============================================================================
--- spamassassin/trunk/rules/30_text_nl.cf (original)
+++ spamassassin/trunk/rules/30_text_nl.cf Wed Dec 13 05:07:13 2006
@@ -152,6 +152,9 @@
lang nl describe HTML_IMAGE_ONLY_08 HTML: plaatjes met 600-800 bytes aan woorden
lang nl describe HTML_IMAGE_ONLY_12 HTML: plaatjes met 1000-1200 bytes aan woorden
lang nl describe HTML_IMAGE_RATIO_02 HTML heeft een lage verhouding tussen tekst en plaatjes
+lang nl describe HTML_IMAGE_RATIO_04 HTML heeft een lage verhouding tussen tekst en plaatjes
+lang nl describe HTML_IMAGE_RATIO_06 HTML heeft een lage verhouding tussen tekst en plaatjes
+lang nl describe HTML_IMAGE_RATIO_08 HTML heeft een lage verhouding tussen tekst en plaatjes
lang nl describe HTML_OBFUSCATE_10_20 Bericht bevat 10% tot 20% HTML verdoezeling
lang nl describe HTML_OBFUSCATE_20_30 Bericht bevat 20% tot 30% HTML verdoezeling
lang nl describe HTML_OBFUSCATE_30_40 Bericht bevat 30% tot 40% HTML verdoezeling
Modified: spamassassin/trunk/rules/30_text_pl.cf
URL: http://svn.apache.org/viewvc/spamassassin/trunk/rules/30_text_pl.cf?view=diff&rev=486633&r1=486632&r2=486633
==============================================================================
--- spamassassin/trunk/rules/30_text_pl.cf (original)
+++ spamassassin/trunk/rules/30_text_pl.cf Wed Dec 13 05:07:13 2006
@@ -150,6 +150,9 @@
lang pl describe HTML_IMAGE_ONLY_08 HTML: grafika i 600-800 bajtów s³ów
lang pl describe HTML_IMAGE_ONLY_12 HTML: grafika i 1000-1200 bajtów s³ów
lang pl describe HTML_IMAGE_RATIO_02 HTML posiada niski stosunek objêto¶ci tekstu do obrazu
+lang pl describe HTML_IMAGE_RATIO_04 HTML posiada niski stosunek objêto¶ci tekstu do obrazu
+lang pl describe HTML_IMAGE_RATIO_06 HTML posiada niski stosunek objêto¶ci tekstu do obrazu
+lang pl describe HTML_IMAGE_RATIO_08 HTML posiada niski stosunek objêto¶ci tekstu do obrazu
lang pl describe HTML_MESSAGE Wiadomo¶æ zawiera kod HTML
lang pl describe HTML_MIME_NO_HTML_TAG Wiadomo¶æ ca³kowicie w HTML, lecz bez odpowiedniego oznaczenia
lang pl describe HTML_TAG_BALANCE_BODY HTML posiada niepozamykane znaczniki w "body"
Modified: spamassassin/trunk/rules/50_scores.cf
URL: http://svn.apache.org/viewvc/spamassassin/trunk/rules/50_scores.cf?view=diff&rev=486633&r1=486632&r2=486633
==============================================================================
--- spamassassin/trunk/rules/50_scores.cf (original)
+++ spamassassin/trunk/rules/50_scores.cf Wed Dec 13 05:07:13 2006
@@ -325,6 +325,9 @@
score HTML_IMAGE_ONLY_28 1.438 1.014 1.732 1.900
score HTML_IMAGE_ONLY_32 1.423 0.836 1.610 1.052
score HTML_IMAGE_RATIO_02 1.245 0.192 1.800 0.463
+score HTML_IMAGE_RATIO_04 0.877 0.001 1.057 0.001
+score HTML_IMAGE_RATIO_06 0.001 0.001 0.139 0.001
+score HTML_IMAGE_RATIO_08 0.001
score HTML_OBFUSCATE_05_10 1.421 1.169 1.522 1.449
score HTML_OBFUSCATE_10_20 1.936 1.397 2.371 1.770
score HTML_OBFUSCATE_20_30 2.720 2.720 3.145 3.400