123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266 |
- # SARE HTML Ruleset for SpamAssassin - ruleset 3
- # Version: 01.03.10
- # Created: 2004-03-31
- # Modified: 2006-06-03
- # Usage instructions, documentation, and change history in 70_sare_html0.cf
- #@@# Revision History: Full Revision History stored in 70_sare_html.log
- #@@# 01.03.10: June 3 2006
- #@@# Minor score tweaks based on recent mass-checks
- #@@# Modified "rule has been moved" meta flags
- #@@# Archive: SARE_HTML_URI_OPTPHP
- #@@# Moved file 1 to 3: SARE_HTML_URI_DEFASP
- # License: Artistic - see http://www.rulesemporium.com/license.txt
- # Current Maintainer: Bob Menschel - RMSA@Menschel.net
- # Current Home: http://www.rulesemporium.com/rules/70_sare_html3.cf
- #
- ######## ###################### ##################################################
- ######## ###################### ##################################################
- # Rules renamed or moved
- ######## ###################### ##################################################
- meta __SARE_HEAD_FALSE __FROM_AOL_COM && !__FROM_AOL_COM
- meta SARE_HTML_URI_OPTPHP __SARE_HEAD_FALSE
- ######## ###################### ##################################################
- body __NONEMPTY_BODY /\S/
- header __TOCC_EXISTS exists:ToCc
- rawbody __SARE_HTML_HAS_A eval:html_tag_exists('a')
- rawbody __SARE_HTML_HAS_BR eval:html_tag_exists('br')
- rawbody __SARE_HTML_HAS_DIV eval:html_tag_exists('div')
- rawbody __SARE_HTML_HAS_FONT eval:html_tag_exists('font')
- rawbody __SARE_HTML_HAS_IMG eval:html_tag_exists('img')
- rawbody __SARE_HTML_HAS_P eval:html_tag_exists('p')
- rawbody __SARE_HTML_HAS_PRE eval:html_tag_exists('pre')
- rawbody __SARE_HTML_HAS_TITLE eval:html_tag_exists('title')
- rawbody __SARE_HTML_HBODY m'<html><body>'i
- rawbody __SARE_HTML_BEHTML m'<body></html>'i
- rawbody __SARE_HTML_BEHTML2 m'^</?body></html>'i
- rawbody __SARE_HTML_EFONT m'^</font>'i
- rawbody __SARE_HTML_EHEB m'^</html></body>'i
- rawbody __SARE_HTML_CMT_CNTR /<center><!--/
- ######## ###################### ##################################################
- # Is there a message?
- ######## ###################### ##################################################
- meta SARE_HTML_EMPTY __CTYPE_HTML && !( __SARE_HTML_HAS_TITLE || __TAG_EXISTS_HTML || __SARE_HTML_HAS_FONT || __TAG_EXISTS_BODY || __SARE_HTML_HAS_PRE || __SARE_HTML_HAS_DIV || __SARE_HTML_HAS_P || __SARE_HTML_HAS_A || __SARE_HTML_HAS_BR )
- describe SARE_HTML_EMPTY Email is HTML format, but common tags not found
- score SARE_HTML_EMPTY 0.681
- #ham SARE_HTML_EMPTY An "html" format email, 30 Oct 2002, Microsoft Outlook Express 6.00.2600.0000, that used no tags, just one long textual paragraph
- #counts SARE_HTML_EMPTY 226s/7h of 333405 corpus (262498s/70907h RM) 05/12/06
- #max SARE_HTML_EMPTY 506s/33h of 689155 corpus (348140s/341015h RM) 09/18/05
- #counts SARE_HTML_EMPTY 28s/1h of 54067 corpus (16890s/37177h JH-3.01) 06/18/05
- #max SARE_HTML_EMPTY 32s/2h of 54283 corpus (17106s/37177h JH-3.01) 02/13/05
- #counts SARE_HTML_EMPTY 0s/0h of 57287 corpus (52272s/5015h MY) 09/22/05
- #max SARE_HTML_EMPTY 132s/2h of 26326 corpus (22886s/3440h MY) 02/15/05
- #counts SARE_HTML_EMPTY 0s/0h of 13284 corpus (7412s/5872h CT) 05/14/06
- #max SARE_HTML_EMPTY 12s/0h of 10826 corpus (6364s/4462h CT) 05/28/05
- #counts SARE_HTML_EMPTY 1s/173h of 7500 corpus (1767s/5733h ft) 09/18/05
- ######## ###################### ##################################################
- # <HTML> and <BODY> tag spamsign
- ######## ###################### ##################################################
- rawbody __SARE_HTML_BODY_END2 m'</body[^>]*>.*</body[^>]*>'i
- meta SARE_HTML_BODY_END2 __SARE_HTML_BODY_END2
- describe SARE_HTML_BODY_END2 Double </body>
- score SARE_HTML_BODY_END2 0.444
- #hist SARE_HTML_BODY_END2 Contrib by Matt Keller June 7 2004
- #note SARE_HTML_BODY_END2 Add/remove HTML_MESSAGE test has no effect
- #counts SARE_HTML_BODY_END2 15s/1h of 333405 corpus (262498s/70907h RM) 05/12/06
- #max SARE_HTML_BODY_END2 163s/13h of 281655 corpus (110173s/171482h RM) 05/05/05
- #counts SARE_HTML_BODY_END2 2s/1h of 9988 corpus (5657s/4331h AxB) 05/14/06
- #counts SARE_HTML_BODY_END2 1s/1h of 13284 corpus (7412s/5872h CT) 05/14/06
- #max SARE_HTML_BODY_END2 6s/0h of 10826 corpus (6364s/4462h CT) 05/28/05
- #counts SARE_HTML_BODY_END2 6s/0h of 155408 corpus (103805s/51603h DOC) 05/15/06
- #counts SARE_HTML_BODY_END2 0s/7h of 42328 corpus (34212s/8116h FVGT) 05/15/06
- #counts SARE_HTML_BODY_END2 15s/0h of 54067 corpus (16890s/37177h JH-3.01) 06/18/05
- #max SARE_HTML_BODY_END2 63s/0h of 38858 corpus (15368s/23490h JH-SA3.0rc1) 08/22/04
- #counts SARE_HTML_BODY_END2 13s/0h of 106399 corpus (73151s/33248h ML) 05/14/06
- #counts SARE_HTML_BODY_END2 52s/2h of 23053 corpus (17334s/5719h MY) 05/14/06
- #max SARE_HTML_BODY_END2 69s/2h of 57287 corpus (52272s/5015h MY) 09/22/05
- rawbody SARE_HTML_HTML_DBL /<html[^>]*><html[^>]*>/i
- describe SARE_HTML_HTML_DBL Message body has very strange HTML sequence
- score SARE_HTML_HTML_DBL 0.639
- #ham SARE_HTML_HTML_DBL Verified (several), common to various opt-in lists.
- #hist SARE_HTML_HTML_DBL Fred T: FR_HTML_HTML
- #hist SARE_HTML_HTML_DBL 2004-06-11: [^>]* added by Bob Menschel
- #counts SARE_HTML_HTML_DBL 7s/1h of 333405 corpus (262498s/70907h RM) 05/12/06
- #max SARE_HTML_HTML_DBL 168s/0h of 65984 corpus (40739s/25245h RM) 08/21/04
- #counts SARE_HTML_HTML_DBL 1s/0h of 9988 corpus (5657s/4331h AxB) 05/14/06
- #counts SARE_HTML_HTML_DBL 0s/0h of 13284 corpus (7412s/5872h CT) 05/14/06
- #max SARE_HTML_HTML_DBL 9s/0h of 6944 corpus (3188s/3756h CT) 05/19/04
- #counts SARE_HTML_HTML_DBL 3s/0h of 155408 corpus (103805s/51603h DOC) 05/15/06
- #counts SARE_HTML_HTML_DBL 25s/0h of 54283 corpus (17106s/37177h JH-3.01) 02/13/05
- #max SARE_HTML_HTML_DBL 75s/0h of 32906 corpus (9660s/23246h JH) 05/24/04
- #counts SARE_HTML_HTML_DBL 1s/0h of 106399 corpus (73151s/33248h ML) 05/14/06
- #counts SARE_HTML_HTML_DBL 8s/1h of 23053 corpus (17334s/5719h MY) 05/14/06
- #max SARE_HTML_HTML_DBL 10s/0h of 57287 corpus (52272s/5015h MY) 09/22/05
- ######## ###################### ##################################################
- # <TITLE> Tag Tests
- ######## ###################### ##################################################
- # Moved file 1 to 3: SARE_HTML_TITLE_MNY
- rawbody SARE_HTML_TITLE_MNY /<title>.{0,25}Money.{0,25}<\/title>/i
- describe SARE_HTML_TITLE_MNY HTML Title implies this may be spam
- score SARE_HTML_TITLE_MNY 0.458
- #ham SARE_HTML_TITLE_MNY confirmed
- #hist SARE_HTML_TITLE_MNY Fred T: FR_TITLE_MONEY
- #counts SARE_HTML_TITLE_MNY 16s/2h of 333405 corpus (262498s/70907h RM) 05/12/06
- #max SARE_HTML_TITLE_MNY 260s/11h of 689155 corpus (348140s/341015h RM) 09/18/05
- #counts SARE_HTML_TITLE_MNY 0s/0h of 13287 corpus (7414s/5873h CT) 05/14/06
- #max SARE_HTML_TITLE_MNY 0s/1h of 6944 corpus (3188s/3756h CT) 05/19/04
- #counts SARE_HTML_TITLE_MNY 0s/0h of 54283 corpus (17106s/37177h JH-3.01) 02/13/05
- #max SARE_HTML_TITLE_MNY 7s/0h of 38858 corpus (15368s/23490h JH-SA3.0rc1) 08/22/04
- #counts SARE_HTML_TITLE_MNY 2s/0h of 105856 corpus (72598s/33258h ML) 05/14/06
- #counts SARE_HTML_TITLE_MNY 15s/0h of 23074 corpus (17350s/5724h MY) 05/14/06
- #max SARE_HTML_TITLE_MNY 120s/0h of 57287 corpus (52272s/5015h MY) 09/22/05
- ######## ###################### ##################################################
- # <A> and HREF rules
- ######## ###################### ##################################################
- ######## ###################### ##################################################
- # Spamsign character sets and fonts
- ######## ###################### ##################################################
- rawbody SARE_HTML_COLOR_B /(?:style="?|<style[^>]*>)[^>"]*[^-]color\s*:\s*rgb\(\s*2[2-5][0-9]\s*,\s*2[2-5][0-9]\s*,\s*2[2-5][0-9]\s*\)[^>]*>/i
- describe SARE_HTML_COLOR_B BAD STYLE: color: too light (rgb(n))
- score SARE_HTML_COLOR_B 0.621
- #ham SARE_HTML_COLOR_B Tickemaster ticket confirmation emails
- #hist SARE_HTML_COLOR_B From Jesse Houwing May 14 2004
- #counts SARE_HTML_COLOR_B 20s/4h of 333405 corpus (262498s/70907h RM) 05/12/06
- #counts SARE_HTML_COLOR_B 2s/8h of 9988 corpus (5657s/4331h AxB) 05/14/06
- #counts SARE_HTML_COLOR_B 1s/1h of 13284 corpus (7412s/5872h CT) 05/14/06
- #counts SARE_HTML_COLOR_B 47s/0h of 155408 corpus (103805s/51603h DOC) 05/15/06
- #counts SARE_HTML_COLOR_B 0s/1h of 42328 corpus (34212s/8116h FVGT) 05/15/06
- #counts SARE_HTML_COLOR_B 3s/0h of 54067 corpus (16890s/37177h JH-3.01) 06/18/05
- #max SARE_HTML_COLOR_B 5s/0h of 54283 corpus (17106s/37177h JH-3.01) 02/13/05
- #counts SARE_HTML_COLOR_B 12s/0h of 106399 corpus (73151s/33248h ML) 05/14/06
- #counts SARE_HTML_COLOR_B 8s/0h of 23053 corpus (17334s/5719h MY) 05/14/06
- rawbody SARE_HTML_LANG_PTBR /lang=(?:3D)?PT-BR/
- describe SARE_HTML_LANG_PTBR Odd language
- score SARE_HTML_LANG_PTBR 0.189
- #hist SARE_HTML_LANG_PTBR LW_PT_BR, Loren Wilton
- #counts SARE_HTML_LANG_PTBR 11s/0h of 333405 corpus (262498s/70907h RM) 05/12/06
- #max SARE_HTML_LANG_PTBR 213s/0h of 70693 corpus (43127s/27566h RM) 10/02/04
- #counts SARE_HTML_LANG_PTBR 0s/1h of 56020 corpus (51687s/4333h AxB2) 05/15/06
- #counts SARE_HTML_LANG_PTBR 9s/25h of 13284 corpus (7412s/5872h CT) 05/14/06
- #counts SARE_HTML_LANG_PTBR 1s/0h of 155408 corpus (103805s/51603h DOC) 05/15/06
- #counts SARE_HTML_LANG_PTBR 69s/0h of 54067 corpus (16890s/37177h JH-3.01) 06/18/05
- #counts SARE_HTML_LANG_PTBR 2s/0h of 106399 corpus (73151s/33248h ML) 05/14/06
- #counts SARE_HTML_LANG_PTBR 0s/0h of 47221 corpus (42968s/4253h MY) 06/18/05
- #max SARE_HTML_LANG_PTBR 10s/0h of 19448 corpus (16863s/2585h MY) 10/05/04
- ######## ###################### ##################################################
- # Invalid or Suspicious URI Tests
- ######## ###################### ##################################################
- uri SARE_HTML_URI_DEFASP m'/default.asp\?id='i
- describe SARE_HTML_URI_DEFASP URI to page name which suggests spammer's page
- score SARE_HTML_URI_DEFASP 0.093
- #hist SARE_HTML_URI_DEFASP Deleted SARE_HTML_URI_X1 = LW_URI_ID due to complete overlap: /\?id\x10\x30\x34\x35/i
- #counts SARE_HTML_URI_DEFASP 0s/8h of 333405 corpus (262498s/70907h RM) 05/12/06
- #max SARE_HTML_URI_DEFASP 130s/27h of 689155 corpus (348140s/341015h RM) 09/18/05
- #counts SARE_HTML_URI_DEFASP 0s/5h of 13287 corpus (7414s/5873h CT) 05/14/06
- #max SARE_HTML_URI_DEFASP 44s/0h of 6944 corpus (3188s/3756h CT) 05/19/04
- #counts SARE_HTML_URI_DEFASP 1s/1h of 42454 corpus (34336s/8118h FVGT) 05/15/06
- #counts SARE_HTML_URI_DEFASP 0s/0h of 54067 corpus (16890s/37177h JH-3.01) 06/18/05
- #max SARE_HTML_URI_DEFASP 361s/0h of 38858 corpus (15368s/23490h JH-SA3.0rc1) 08/22/04
- #counts SARE_HTML_URI_DEFASP 24s/0h of 23074 corpus (17350s/5724h MY) 05/14/06
- #max SARE_HTML_URI_DEFASP 24s/0h of 57287 corpus (52272s/5015h MY) 09/22/05
- ######## ###################### ##################################################
- # Image tag tests
- ######## ###################### ##################################################
- ######## ###################### ##################################################
- # Paragraphs, breaks, and spacings
- ######## ###################### ##################################################
- rawbody SARE_HTML_P_MANY3 /<P><P><P>/i
- describe SARE_HTML_P_MANY3 Too many empty paragraph tags in a row
- score SARE_HTML_P_MANY3 1.108
- #hist SARE_HTML_P_MANY3 04/02/2004 http://www.rulesemporium.com/rules/99_FVGT_rawbody.cf
- #overlap SARE_HTML_P_MANY3 Total overlap within SARE_HTML_URI_MANYP2, but no ham hits here (until Feb 2005)
- #ham SARE_HTML_P_MANY3 From: Ticketmaster <support@reply.ticketmaster.com>, Tuesday, January 25, 2005, 4:00:27 PM
- #counts SARE_HTML_P_MANY3 78s/6h of 333405 corpus (262498s/70907h RM) 05/12/06
- #max SARE_HTML_P_MANY3 458s/28h of 689155 corpus (348140s/341015h RM) 09/18/05
- #counts SARE_HTML_P_MANY3 143s/0h of 56020 corpus (51687s/4333h AxB2) 05/15/06
- #counts SARE_HTML_P_MANY3 0s/0h of 11260 corpus (6568s/4692h CT) 06/17/05
- #max SARE_HTML_P_MANY3 9s/0h of 6944 corpus (3188s/3756h CT) 05/19/04
- #counts SARE_HTML_P_MANY3 412s/0h of 155408 corpus (103805s/51603h DOC) 05/15/06
- #counts SARE_HTML_P_MANY3 50s/0h of 42328 corpus (34212s/8116h FVGT) 05/15/06
- #counts SARE_HTML_P_MANY3 4s/0h of 54067 corpus (16890s/37177h JH-3.01) 06/18/05
- #max SARE_HTML_P_MANY3 15s/0h of 32260 corpus (8983s/23277h JH) 05/14/04
- #counts SARE_HTML_P_MANY3 9s/0h of 23053 corpus (17334s/5719h MY) 05/14/06
- #max SARE_HTML_P_MANY3 41s/0h of 57287 corpus (52272s/5015h MY) 09/22/05
- ######## ###################### ##################################################
- # Javascript and object tests
- ######## ###################### ##################################################
- ######## ###################### ##################################################
- # Useless tags (tag structures that do nothing)
- # Largely submitted by Matt Yackley, with contributions by
- # Carl Friend, Jennifer Wheeler, Scott Sprunger, Larry Gilson
- ######## ###################### ##################################################
- rawbody SARE_HTML_USL_1CHAR m'(?!<[biopu]></[biopu]>)<([a-z])></\1>'i
- describe SARE_HTML_USL_1CHAR Invalid and empty 1-char tag - /tag combination
- score SARE_HTML_USL_1CHAR 0.029
- #counts SARE_HTML_USL_1CHAR 6s/14h of 333405 corpus (262498s/70907h RM) 05/12/06
- #max SARE_HTML_USL_1CHAR 46s/6h of 196718 corpus (96193s/100525h RM) 02/22/05
- #counts SARE_HTML_USL_1CHAR 3s/0h of 56020 corpus (51687s/4333h AxB2) 05/15/06
- #counts SARE_HTML_USL_1CHAR 0s/0h of 10826 corpus (6364s/4462h CT) 05/28/05
- #max SARE_HTML_USL_1CHAR 3s/0h of 6944 corpus (3188s/3756h CT) 05/19/04
- #counts SARE_HTML_USL_1CHAR 8s/30h of 155408 corpus (103805s/51603h DOC) 05/15/06
- #counts SARE_HTML_USL_1CHAR 2s/1h of 42328 corpus (34212s/8116h FVGT) 05/15/06
- #counts SARE_HTML_USL_1CHAR 3s/0h of 54067 corpus (16890s/37177h JH-3.01) 06/18/05
- #max SARE_HTML_USL_1CHAR 6s/0h of 54283 corpus (17106s/37177h JH-3.01) 02/13/05
- #counts SARE_HTML_USL_1CHAR 2s/0h of 23053 corpus (17334s/5719h MY) 05/14/06
- ######## ###################### ##################################################
- # Miscellaneous tag tests
- ######## ###################### ##################################################
- rawbody SARE_HTML_BODY_2SP /<body /i
- describe SARE_HTML_BODY_2SP HTML tag is strangely formed
- score SARE_HTML_BODY_2SP 0.665
- #hist SARE_HTML_BODY_2SP FR_BODY_2SPACES
- #counts SARE_HTML_BODY_2SP 682s/152h of 333405 corpus (262498s/70907h RM) 05/12/06
- #counts SARE_HTML_BODY_2SP 678s/2h of 9988 corpus (5657s/4331h AxB) 05/14/06
- #counts SARE_HTML_BODY_2SP 48s/0h of 13284 corpus (7412s/5872h CT) 05/14/06
- #counts SARE_HTML_BODY_2SP 215s/0h of 155408 corpus (103805s/51603h DOC) 05/15/06
- #counts SARE_HTML_BODY_2SP 1455s/8h of 42328 corpus (34212s/8116h FVGT) 05/15/06
- #counts SARE_HTML_BODY_2SP 62s/5h of 54067 corpus (16890s/37177h JH-3.01) 06/18/05
- #max SARE_HTML_BODY_2SP 94s/0h of 38858 corpus (15368s/23490h JH-SA3.0rc1) 08/22/04
- #counts SARE_HTML_BODY_2SP 361s/2h of 106399 corpus (73151s/33248h ML) 05/14/06
- #counts SARE_HTML_BODY_2SP 21s/2h of 23053 corpus (17334s/5719h MY) 05/14/06
- #max SARE_HTML_BODY_2SP 66s/2h of 47221 corpus (42968s/4253h MY) 06/18/05
- full SARE_HTML_TD_BR m'<td.{10,400}<br>.{1,7}<br>.{1,7}<br>.{1,7}<br>.{0,400}</td>'is
- describe SARE_HTML_TD_BR Multiple line breaks in spammer pattern
- score SARE_HTML_TD_BR 0.934
- #hist SARE_HTML_TD_BR Fred T: FR_WICKED_SPAM_??
- #counts SARE_HTML_TD_BR 2757s/33h of 333405 corpus (262498s/70907h RM) 05/12/06
- #counts SARE_HTML_TD_BR 368s/0h of 56020 corpus (51687s/4333h AxB2) 05/15/06
- #counts SARE_HTML_TD_BR 40s/10h of 13284 corpus (7412s/5872h CT) 05/14/06
- #counts SARE_HTML_TD_BR 471s/0h of 155408 corpus (103805s/51603h DOC) 05/15/06
- #counts SARE_HTML_TD_BR 190s/10h of 42328 corpus (34212s/8116h FVGT) 05/15/06
- #counts SARE_HTML_TD_BR 36s/0h of 54067 corpus (16890s/37177h JH-3.01) 06/18/05
- #max SARE_HTML_TD_BR 182s/0h of 38858 corpus (15368s/23490h JH-SA3.0rc1) 08/22/04
- #counts SARE_HTML_TD_BR 700s/0h of 106399 corpus (73151s/33248h ML) 05/14/06
- #counts SARE_HTML_TD_BR 68s/14h of 23053 corpus (17334s/5719h MY) 05/14/06
- #max SARE_HTML_TD_BR 184s/15h of 47221 corpus (42968s/4253h MY) 06/18/05
- # EOF
|