# SARE "Adult" Ruleset for SpamAssassin # Version: 01.02.08 # The Adult set has been renamed to match SARE's updated standards, the new name is 70_sare_adult.cf # Created: 2004-03-23 # Modified: 2007-05-21 # Changes: Fixed broken meta # License: Artistic - see http://www.rulesemporium.com/license.txt # Current Maintainer: Matt Yackley - adult@rulesemporium.com # Maintainer: Doc Schneider - maddoc@maddoc.net # Current Home: http://www.rulesemporium.com/rules/70_sare_adult.cf # #### ############################### # subject rules # ############################### header SARE_SUBJ_SLUT Subject =~ /\bslut\b/i score SARE_SUBJ_SLUT 1.66 #counts SARE_SUBJ_SLUT 89s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_SUBJ_SLUT 5s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 header __FPS_BREAST Subject =~ /\bbreasts?\b/i header __FPS_COCK Subject =~ /\bcock\b/i header __FPS_FUCK Subject =~ /\bfuck/i header __FPS_GIRLS Subject =~ /\bgirls\b/i header __FPS_HARDCORE Subject =~ /\bhard.?core\b/i header __FPS_LITTLE Subject =~ /\blittle\b/i header __FPS_MODEL Subject =~ /\bmodels?\b/i header __FPS_NAKED Subject =~ /\bnaked\b/i header __FPS_PENETRAT Subject =~ /\bpenetration\b/i header __FPS_SEX Subject =~ /\bsex\b/i header __FPS_SLUT Subject =~ /\bslut\b/i header __FPS_TEEN Subject =~ /\bteen\b/i header __FPS_VIRGIN Subject =~ /\bvirgins?\b/i meta __COUNT_FPORN2 (__FPS_BREAST + __FPS_COCK + __FPS_FUCK + __FPS_GIRLS + __FPS_HARDCORE + __FPS_LITTLE + __FPS_MODEL + __FPS_NAKED + __FPS_PENETRAT + __FPS_SEX + __FPS_SLUT + __FPS_TEEN + __FPS_VIRGIN) > 1 meta __COUNT_FPORN3 (__FPS_BREAST + __FPS_COCK + __FPS_FUCK + __FPS_GIRLS + __FPS_HARDCORE + __FPS_LITTLE + __FPS_MODEL + __FPS_NAKED + __FPS_PENETRAT + __FPS_SEX + __FPS_SLUT + __FPS_TEEN + __FPS_VIRGIN) > 2 meta __COUNT_FPORN4 (__FPS_BREAST + __FPS_COCK + __FPS_FUCK + __FPS_GIRLS + __FPS_HARDCORE + __FPS_LITTLE + __FPS_MODEL + __FPS_NAKED + __FPS_PENETRAT + __FPS_SEX + __FPS_SLUT + __FPS_TEEN + __FPS_VIRGIN) > 3 meta SARE_SUB_MULTI_PRN2 (__COUNT_FPORN2 && !__COUNT_FPORN3) score SARE_SUB_MULTI_PRN2 1.66 #counts SARE_SUB_MULTI_PRN2 455s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_SUB_MULTI_PRN2 93s/5h of 140226 corpus (90162s/50064h DOC) 04/19/06 meta SARE_SUB_MULTI_PRN3 (__COUNT_FPORN3 && !__COUNT_FPORN4) score SARE_SUB_MULTI_PRN3 1.66 #counts SARE_SUB_MULTI_PRN3 93s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_SUB_MULTI_PRN3 9s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 #meta SARE_SUB_MULTI_PRN4 (__COUNT_FPORN4) #score SARE_SUB_MULTI_PRN4 3.333 #counts SARE_SUB_MULTI_PRN4 4s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_SUB_MULTI_PRN4 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 header SARE_ADLTSUB1 Subject =~ /\b(?:adu?1t|amb[1!]en|b0y|bl0w|c0cks?|c0re|ejaculation|f?r0+m|g(?:[1!]r[1l]|ir[!1])|h0t|ntercourse|jerk off|l1ttle|m0vie|manh00d|[0o]rg\@sm|p1ct|pen[1!]s|(?:ph|f)(?:[0\@]t|ot[0\@])|secks|sm00th|t1ny|t1ts|v(?:irg1|1rgi|1rg1)n|v[i1]de0|violenced|y0ung)/i describe SARE_ADLTSUB1 Contains OBFU and "strong" adult words score SARE_ADLTSUB1 1.66 # Combined from M_K_PORN_BOGOSITY_SUBJ, L_s_porn, SUBJECT_XXX, RM_swp_porn4, RM_swp_porn5 # 266s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 45s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_ADLTSUB1 503s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_ADLTSUB1 145s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 header SARE_ADLTSUB2 Subject =~ /\b(?:blow|climax|enlarg(e|ment)|fuck|inter+acial|lick|porn|penis|pervert|pussy|tits|tight|vagina|virgins?)\b/i describe SARE_ADLTSUB2 Contains possible adult words score SARE_ADLTSUB2 1.23 # Combined from SUBJECT_XXX_2, L_s_porn, RM_swp_pervert, RM_swp_porn1, RM_swp_porn2 # 519s/1h of 119325 corpus (98981s/20344h) 03/21/04 # 58s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_ADLTSUB2 1967s/2h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_ADLTSUB2 514s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 header SARE_ADLTSUB3 Subject =~ /(?!\bporn)(?:\bp|\B(?:[\xDE]|\xCE\xA1|\xCF\x81|\xD0\xA0|\xD1\x80))[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[o0\*\xB0\xBA\xD8\xF8\xD2-\xD6\xF2-\xF6]|\(\)|\[\]|\xC5[\x8C-\x91]|\xC6[\xA0-\xA1]|\xC7[\x91-\x92]|\xC7[\xBE-\xBF]|\xCE\x8C|\xCE\x98|\xCE\x9F|\xCE\xB8|\xCE\xBF|\xCF\x8C|\xD0\x9E|\xD0\xBE|\xD5\x95)[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[r\xAE]|\xC5[\x94-\x99]|\xD1\x93)[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[n\xD1\xF1]|\|\\\||\xC5[\x83-\x8B]|\xCE\x9D|\xCE\xA0|\xCE\xAE|\xCE\xB7|\xD5\xB2|\xD5\xB8)/i describe SARE_ADLTSUB3 Apparent spam seems to contain porn subject score SARE_ADLTSUB3 1.66 # type=obfu # Original name: RM_swp_porn1o1 # 58s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 11s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_ADLTSUB3 11s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_ADLTSUB3 15s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 header SARE_ADLTSUB4 Subject =~ /(?!\bpo(?:rn|ur))\bp.?o.?r.?n/i describe SARE_ADLTSUB4 Apparent spam seems to contain porn subject score SARE_ADLTSUB4 0.89 # type=obfu # Original name: RM_swp_porn1o2 # 26s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 3s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_ADLTSUB4 5s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_ADLTSUB4 5s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 header SARE_ADLTSUB5 Subject =~ /(?!\bfuck)(?:\bf|\B(?:\xC5\xBF|\xC6\x92|\xD2[\x92-\x93]))[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[uv\*\xB5\xD9-\xDC\xF9-\xFC]|\xC5[\xA8-\xB3]|\xC6[\xAF-\xB0]|\xC7[\x93-\x9C]|\xCE\xB0|\xCE\xBC|\xCF\x8B|\xCF\x8D|\xD4\xB1|\xD5\x84|\xD5\x8D)[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[c\*\xC7\xE7\xA2\xA9]|\xC4[\x86-\x8D]|\xD0\xA1|\xD1\x81)[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:k|\xC4[\xB6-\xB8]|\xCE\x9A|\xCE\xBA|\xD0\x8C|\xD0\x9A|\xD0\xBA|\xD1\x9C|\xD2[\x9A-\x9D]])/i describe SARE_ADLTSUB5 Apparent spam seems to contain porn subject score SARE_ADLTSUB5 1.66 # type=obfu # Original name: RM_swp_porn2o1 # 8s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 4s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_ADLTSUB5 12s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_ADLTSUB5 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 header SARE_ADLTSUB6 Subject =~ /(?!\bfuck)\bf.?u.?c.?k/i describe SARE_ADLTSUB6 Apparent spam seems to contain porn subject score SARE_ADLTSUB6 1.51 # type=obfu # Original name: RM_swp_porn2o2 # 3s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 5s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_ADLTSUB6 32s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_ADLTSUB6 13s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 header SARE_ADLTSUB7 Subject =~ /(?!\bpuss(?:y|ies)\b)(?:\bp|\B(?:[\xDE]|\xCE\xA1|\xCF\x81|\xD0\xA0|\xD1\x80))[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[uv\*\xB5\xD9-\xDC\xF9-\xFC]|\xC5[\xA8-\xB3]|\xC6[\xAF-\xB0]|\xC7[\x93-\x9C]|\xCE\xB0|\xCE\xBC|\xCF\x8B|\xCF\x8D|\xD4\xB1|\xD5\x84|\xD5\x8D)[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[s5\$\xA7]|\xC5[\x9A-\xA1]|\xD0\x85|\xD1\x95|\xD5\x8F)[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[s5\$\xA7]|\xC5[\x9A-\xA1]|\xD0\x85|\xD1\x95|\xD5\x8F)(?:(?:[y\xA5\xDD\xFD]|\xC5[\xB6-\xB8]|\xCE\x8E|\xCE\xA5|\xCE\xA8|\xCE\xAB|\xCE\xB3|\xD0\xA3|\xD1\x83|\xD1\x9E|\xD2[\xAE-\xB1])|(?:[il1:\|\*\xCC-\xCF\xEC-\xEF\xA6]|\xC4[\xA8-\xB0]|\xC4\xBA|\xC4\xBC|\xC4\xBE|\xC5\x80|\xC5\x82|\xC7[\x8F-\x90]|\xD0[\x86-\x87]|\xD1[\x96-\x97]|\xCE\x8A|\xCE\x90|\xCE\x99|\xCE\xAA|\xCE\xAF|\xCE\xB9|\xCF\x8A)[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[e3\*\xC8-\xCB\xE8-\xEB]|\xC4[\x92-\x9B]|\xCE\x88|\xCE\x95|\xCE\xA3|\xCE\xAD|\xCE\xB5|\xD0\x81|\xD0\x95|\xD0\xB5|\xD1\x91)[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[s5\$\xA7]|\xC5[\x9A-\xA1]|\xD0\x85|\xD1\x95|\xD5\x8F))\b/i describe SARE_ADLTSUB7 Apparent spam seems to contain porn subject score SARE_ADLTSUB7 1.66 # type=obfu # Original name: RM_swp_porn5o1 # 4s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 2s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_ADLTSUB7 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_ADLTSUB7 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 header SARE_ADLTSUB8 Subject =~ /(?!\bpuss(?:y|ies)\b)\bp.?u.?s.?s.?(?:y|i.?e.?s)\b/i describe SARE_ADLTSUB8 Apparent spam seems to contain porn subject score SARE_ADLTSUB8 1.66 # type=obfu # Original name: RM_swp_porn5o2 # FPS SARE_ADLTSUB8="plus sizes" # 7s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 0s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_ADLTSUB8 6s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_ADLTSUB8 6s/2h of 140226 corpus (90162s/50064h DOC) 04/19/06 #header SARE_ADLTSUB10 Subject =~ /(?!\b(?:rap(?:e[sd]?|ing|pel)|reaping)\b)\br.?a.?p.?(?:e.?[sd]?|i.?n.?g)\b/i #describe SARE_ADLTSUB10 Apparent spam seems to contain porn subject #score SARE_ADLTSUB10 2.500 # type=obfu # Original name: RM_swp_Rapeo2 # 20s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 0s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_ADLTSUB10 5s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_ADLTSUB10 6s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 #header SARE_BEDROOMSEC Subject =~ /bedroom secret/i #describe SARE_BEDROOMSEC Common spammer phrasing #score SARE_BEDROOMSEC 0.611 # Original name: RM_spp_BedroomSec # 10s/0h of 125078 corpus (104890s/20188h) 03/29/04 # 0s/0h of 15929 corpus (13729s/2200h) 03/29/04 #counts SARE_BEDROOMSEC 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_BEDROOMSEC 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 ############################### # body rules # ############################### body FB_SEXOHOL /sexoholics/i score FB_SEXOHOL 1.66 #counts FB_SEXOHOL 7s/0h of 32370 corpus (24496s/7874h ML) 12/12/05 #counts FB_SEXOHOL 37s/0h of 40658 corpus (35364s/5294h MY) 12/12/05 #counts FB_SEXOHOL 33s/0h of 207630 corpus (200121s/7509h FT) 12/13/05 #counts FB_SEXOHOL 3s/0h of 9809 corpus (4905s/4904h FT) 12/12/05 #counts FB_SEXOHOL 11s/0h of 11532 corpus (6163s/5369h CT) 12/12/05 #counts FB_SEXOHOL 4s/0h of 70031 corpus (30720s/39311h DOC) 12/12/05 #counts FB_SEXOHOL 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts FB_SEXOHOL 18s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 body FB_XUAL /\bxual\b/ score FB_XUAL 0.68 #counts FB_XUAL 20s/0h of 6871 corpus (5500s/1371h AxB) 12/15/05 #counts FB_XUAL 67s/0h of 34342 corpus (25865s/8477h ML) 12/15/05 #counts FB_XUAL 22s/0h of 40631 corpus (35338s/5293h MY) 12/15/05 #counts FB_XUAL 62s/0h of 70858 corpus (31544s/39314h DOC) 12/15/05 #counts FB_XUAL 855s/0h of 107818 corpus (99658s/8160h FVGT) 03/11/06 #counts FB_XUAL 100s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts FB_XUAL 360s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 #body FB_NOT_SEX / s[^afeiloprsuw]x\b/i #score FB_NOT_SEX 1.003 #counts FB_NOT_SEX 7s/7h of 37297 corpus (31824s/5473h MY) 02/07/06 #counts FB_NOT_SEX 4s/4h of 6866 corpus (4638s/2228h AxB) 02/07/06 #counts FB_NOT_SEX 4s/5h of 11694 corpus (6132s/5562h CT) 02/07/06 #counts FB_NOT_SEX 204s/4h of 345244 corpus (337372s/7872h FT) 02/07/06 #counts FB_NOT_SEX 110s/0h of 107818 corpus (99658s/8160h FVGT) 03/11/06 #counts FB_NOT_SEX 23s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts FB_NOT_SEX 108s/2h of 140226 corpus (90162s/50064h DOC) 04/19/06 #body FB_GIRLS_DOLLAR /girl\$/i #score FB_GIRLS_DOLLAR 1.992 #counts FB_GIRLS_DOLLAR 0s/0h of 37297 corpus (31824s/5473h MY) 02/07/06 #counts FB_GIRLS_DOLLAR 0s/0h of 6866 corpus (4638s/2228h AxB) 02/07/06 #counts FB_GIRLS_DOLLAR 0s/0h of 11694 corpus (6132s/5562h CT) 02/07/06 #counts FB_GIRLS_DOLLAR 36s/0h of 345244 corpus (337372s/7872h FT) 02/07/06 #counts FB_GIRLS_DOLLAR 8s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts FB_GIRLS_DOLLAR 2s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 # 1as$e$ #body FB_DOLLAR_ASS2 /(?:\b|[0-9])(?!ass)a[s\$][s\$](?:\b|e)/i #score FB_DOLLAR_ASS2 0.361 #counts FB_DOLLAR_ASS2 2s/1h of 9374 corpus (7151s/2223h AxB) 03/01/06 #counts FB_DOLLAR_ASS2 6s/0h of 12244 corpus (6572s/5672h CT) 03/01/06 #counts FB_DOLLAR_ASS2 0s/2h of 27495 corpus (21848s/5647h MY) 03/01/06 #counts FB_DOLLAR_ASS2 13s/0h of 34977 corpus (27086s/7891h FT) 03/01/06 #counts FB_DOLLAR_ASS2 10s/2h of 84470 corpus (67306s/17164h ML) 03/01/06 #counts FB_DOLLAR_ASS2 10s/1h of 103116 corpus (63731s/39385h DOC) 03/01/06 #counts FB_DOLLAR_ASS2 58s/0h of 107818 corpus (99658s/8160h FVGT) 03/11/06 #counts FB_DOLLAR_ASS2 21s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts FB_DOLLAR_ASS2 13s/1h of 140226 corpus (90162s/50064h DOC) 04/19/06 body FB_HARD_ERECTION /hard(?:er)? (?:erection|penis)/i score FB_HARD_ERECTION 1.66 #counts FB_HARD_ERECTION 2728s/0h of 211356 corpus (203977s/7379h FT) 11/23/05 #counts FB_HARD_ERECTION 393s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts FB_HARD_ERECTION 573s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 #body FB_JACKRABBIT /Jack Rabbit Vibrat[o0]r/i #score FB_JACKRABBIT 3.599 #counts FB_JACKRABBIT 640s/0h of 211356 corpus (203977s/7379h FT) 11/23/05 #counts FB_JACKRABBIT 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts FB_JACKRABBIT 47s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 body FB_PENIS /\b(?!penis)p[3e]n[i1!][s5]\b/i score FB_PENIS 1.66 #counts FB_PENIS 170s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts FB_PENIS 386s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 body FB_FEMALE_EJACU /female ejaculation/i score FB_FEMALE_EJACU 1.66 #counts FB_FEMALE_EJACU 4s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts FB_FEMALE_EJACU 1s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 body FB_INNOCENT /innocent (?:boy|girl|child)/i score FB_INNOCENT 0.40 #counts FB_INNOCENT 14s/1h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts FB_INNOCENT 7s/1h of 140226 corpus (90162s/50064h DOC) 04/19/06 #body LW_PORN_PHOTO /Tell our photographers what to do in their next photo session our video/ #score LW_PORN_PHOTO 5 #describe LW_PORN_PHOTO Standard 'hot chicks' line #counts LW_PORN_PHOTO 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts LW_PORN_PHOTO 3s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 #body LW_PORN_ONLINE /high quality photo's online/ #score LW_PORN_ONLINE 2 #describe LW_PORN_ONLINE Standard 'hot chicks' line #counts LW_PORN_ONLINE 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts LW_PORN_ONLINE 4s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 #body LW_PORN_MODELS /models getting nasty/ #score LW_PORN_MODELS 5 #describe LW_PORN_MODELS Standard 'hot chicks' line #counts LW_PORN_MODELS 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts LW_PORN_MODELS 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 body LW_PORN_HELLO /(?:Hey baby|Hello, stranger!) :\)/ score LW_PORN_HELLO 1.66 describe LW_PORN_HELLO Standard 'hot chicks' line #counts LW_PORN_HELLO 2s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts LW_PORN_HELLO 5s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 #$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$ # set of porn keywords / when these words appear, it's more likely porn. SET A. body __FVGT_BREASTS /\bbreasts?\b/i body __FVGT_FUCK /\bfuck/i body __FVGT_RAPE /\braped?\b/i body __FVGT_HORNY /\bhorny\b/i body __FVGT_VIRGIN /\bvirgins?\b/i body __FVGT_COCK /\bcock\b/i body __FVGT_LOLITA /\blolita\b/i body __FVGT_YOUNGGIRL /Young(?:est)? (?:girl|chick)/i body __FVGT_PUSSY /\bpuss(?:y|ies)/i body __FVGT_ASS /\sass\s/i body __FVGT_SLUT /\bslut\b/i # meta's to count how many porn words from Set A. meta FM_PORN_A_4 ((__FVGT_BREASTS + __FVGT_FUCK + __FVGT_RAPE + __FVGT_HORNY + __FVGT_VIRGIN + __FVGT_COCK + __FVGT_LOLITA + __FVGT_YOUNGGIRL + __FVGT_PUSSY + __FVGT_ASS + __FVGT_SLUT) > 2) meta FM_PORN_A_5 ((__FVGT_BREASTS + __FVGT_FUCK + __FVGT_RAPE + __FVGT_HORNY + __FVGT_VIRGIN + __FVGT_COCK + __FVGT_LOLITA + __FVGT_YOUNGGIRL + __FVGT_PUSSY + __FVGT_ASS + __FVGT_SLUT) > 3) score FM_PORN_A_4 1.09 #counts FM_PORN_A_4 796s/2h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts FM_PORN_A_4 243s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 score FM_PORN_A_5 0.98 #counts FM_PORN_A_5 358s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts FM_PORN_A_5 172s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 body __HAS_COLLECTION /\bcollection\b/i body __HAS_HARDCORE /\bhardcore\b/i body __HAS_YOUNGGIRL /\byoung\s?girls?\b/i body __HAS_ADOLESCENT /\badolescents?\b/i body __HAS_CHICKS /\bchicks?\b/i meta FP_MIXED_PORN3 ((__HAS_COLLECTION + __HAS_HARDCORE + __HAS_YOUNGGIRL + __HAS_ADOLESCENT + __HAS_CHICKS) > 2) score FP_MIXED_PORN3 1.66 #counts FP_MIXED_PORN3 4s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts FP_MIXED_PORN3 5s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 body SARE_ADULT1 /(?:suck|l[i1]ck).{1,30}(c[o0]ck|d[i1]ck)/i describe SARE_ADULT1 Contains adult material score SARE_ADULT1 1.47 # Original name: FVGT_b_ADULT02 # 55s/2h of 119325 corpus (98981s/20344h) 03/21/04 # 18s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_ADULT1 512s/1h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_ADULT1 129s/1h of 140226 corpus (90162s/50064h DOC) 04/19/06 body SARE_ADULT2 /\b(?:sorority|rock hard|(adu?(l|1)t|XXX) movies?|climatique|orgas(mic|ims?|ms?)|climax|ejactulate|penis|pussy|cunt|blowjob|intercourse|lubricate)\b/i describe SARE_ADULT2 Contains adult material score SARE_ADULT2 1.42 # Original name: MY_XXX_BODY, was rawbody # 9985s/30h of 119325 corpus (98981s/20344h) 03/21/04 # 683s/2h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_ADULT2 4729s/9h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_ADULT2 2685s/34h of 140226 corpus (90162s/50064h DOC) 04/19/06 body SARE_BETTERORG /(?:boost|magnify|multipl[ey]|increase|frequent|intense|intensify).{1,15}orgasm/i describe SARE_BETTERORG Talks about getting better orgasms score SARE_BETTERORG 1.66 # Original name: YM_B_BETTER_ORG, RM_bpm_MultipleOrgasms # 592s/2h of 119325 corpus (98981s/20344h) 03/21/04 # 29s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_BETTERORG 249s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_BETTERORG 111s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 body SARE_ENLRGYOUR /enlarge your/i describe SARE_ENLRGYOUR Talks about "enlarging" something score SARE_ENLRGYOUR 1.02 # Original name: MY_EN_PENIS, was rawbody, RE_bpm_EnlargeYour # 1735s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 91s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_ENLRGYOUR 537s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_ENLRGYOUR 279s/1h of 140226 corpus (90162s/50064h DOC) 04/19/06 body SARE_LRGPNS /(?:bigger|larger|increase your) (?:member\b|rod)/i describe SARE_LRGPNS Talks about a "bigger" appendage score SARE_LRGPNS 1.66 # Original name: MY_MEMBER combined with MY_LRGROD # 50s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 0s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_LRGPNS 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_LRGPNS 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 body SARE_PNSSIZE /inch(?:es)? .{0,10}(?:cock|dick)/i describe SARE_PNSSIZE Talks about the size of male body part score SARE_PNSSIZE 1.66 # Original name: YM_B_BODYPART_1 # 3s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 6s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_PNSSIZE 5s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_PNSSIZE 2s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 body SARE_SXLIFE /(?:are you single|sex life|youre? partner)/i describe SARE_SXLIFE Talks about your sex life score SARE_SXLIFE 1.07 # 695s/15h of 119325 corpus (98981s/20344h) 03/21/04 # 212s/1h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_SXLIFE 991s/12h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_SXLIFE 637s/54h of 140226 corpus (90162s/50064h DOC) 04/19/06 body SARE_BEASTUD /be a stud/i describe SARE_BEASTUD common spammer phrasing score SARE_BEASTUD 0.26 # Original name: RM_bpm_BeAStud # 53s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 7s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_BEASTUD 73s/2h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_BEASTUD 20s/1h of 140226 corpus (90162s/50064h DOC) 04/19/06 body SARE_BIGRMEMBER /B.?i.?g.?g.?e.?r.{0,5}M.?e.?m.?b.?e.?r/i describe SARE_BIGRMEMBER mentions bigger body part score SARE_BIGRMEMBER 1.66 # Original name: RM_bpm_BiggerMember # 17s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 0s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_BIGRMEMBER 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_BIGRMEMBER 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 body SARE_INLENGTH /increase.? my length/i describe SARE_INLENGTH common spammer phrasing score SARE_INLENGTH 1.66 # Original name: RM_bpm_IncreaseLength # 40s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 8s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_INLENGTH 60s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_INLENGTH 20s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 #body SARE_LADYINLIFE /lady in your life/i #describe SARE_LADYINLIFE Contains phrasing used by spammers #score SARE_LADYINLIFE 0.166 # Original name: RM_bpm_LadyInLife # 3s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 0s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_LADYINLIFE 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_LADYINLIFE 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 #body SARE_MAGICLUBE /"Magic Lubricant"/i #describe SARE_MAGICLUBE Spammer phrasing in body of email #score SARE_MAGICLUBE 2.222 # type=spamgg # Original name: RM_bpm_MagicLubricant # 704s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 12s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_MAGICLUBE 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_MAGICLUBE 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 body SARE_NOEMBARRASS /no embarrassing/i describe SARE_NOEMBARRASS Wow, I won't be embarrassed anymore! score SARE_NOEMBARRASS 1.66 # Original name: RM_bpm_NoEmbarrassing # 30s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 6s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_NOEMBARRASS 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_NOEMBARRASS 1s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 body SARE_PLEASEPARTNR /Pleasure.{1,10}partner/i describe SARE_PLEASEPARTNR common spammer phrasing score SARE_PLEASEPARTNR 1.66 # Original name: RM_bpm_PleasurePartnr # 51s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 6s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_PLEASEPARTNR 60s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_PLEASEPARTNR 20s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 #body SARE_POWERBOTTLE /"Power Bottle"/i #describe SARE_POWERBOTTLE Spammer phrasing in body of email # score SARE_POWERBOTTLE 2.222 # type=spamgg # Original name: RM_bpm_PowerBottle # 708s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 12s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_POWERBOTTLE 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_POWERBOTTLE 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 #body SARE_PRODEREC /produce erections/i #describe SARE_PRODEREC Contains medical spam phrasing #score SARE_PRODEREC 0.055 # Original name: RE_bpm_ProdErec # 1s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 0s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_PRODEREC 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_PRODEREC 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 body SARE_SUPERVIAGRA /(?:super|weekend)[- ]viagra/i describe SARE_SUPERVIAGRA mentions drug which is often subject of spam score SARE_SUPERVIAGRA 1.66 # type=spamgg # Original name: RM_bpm_SuperViagra, RM_bpm_WeekendViagra # 299s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 11s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_SUPERVIAGRA 136s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_SUPERVIAGRA 704s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 body SARE_ADLTDATING /adult dating/i describe SARE_ADLTDATING Contains phrasing used by spammers score SARE_ADLTDATING 0.32 # Original name: RM_bpp_Adultdating # 3s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 0s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_ADLTDATING 1s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_ADLTDATING 32s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 body SARE_ADLTPRSNLS /adult personals/i describe SARE_ADLTPRSNLS Contains phrasing used by spammers score SARE_ADLTPRSNLS 1.66 # Original name: RM_bpp_AdultPersonals # 3s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 2s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_ADLTPRSNLS 1s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_ADLTPRSNLS 13s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 #body SARE_AREUBORED /Are you bored of/i #describe SARE_AREUBORED Contains phrasing used by spammers #score SARE_AREUBORED 0.111 # Original name: RM_bpp_AreYouBored # 2s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 3s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_AREUBORED 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_AREUBORED 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 body SARE_CHILDPRN1 /child porn/i describe SARE_CHILDPRN1 contains reference to child porn score SARE_CHILDPRN1 1.15 # ham: news, FBI auto-responder # Original name: ChildPorn # 64s/3h of 119325 corpus (98981s/20344h) 03/21/04 # 5s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_CHILDPRN1 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_CHILDPRN1 1s/1h of 140226 corpus (90162s/50064h DOC) 04/19/06 #body SARE_CHILDPRN2 /child pornography webmaster/i #describe SARE_CHILDPRN2 contains reference to a child porn webmaster #score SARE_CHILDPRN2 2.222 # type=spamg # Original name: RM_bpp_ChildPorn2 # 9s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 0s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_CHILDPRN2 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_CHILDPRN2 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 #body SARE_CHILDPRN3 /underage porn/i #describe SARE_CHILDPRN3 contains reference to child porn #score SARE_CHILDPRN3 2.222 # type=spamg # Original name: RM_bpp_ChildPorn3 # 28s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 5s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_CHILDPRN3 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_CHILDPRN3 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 body SARE_TOWRITE /decided to write/i describe SARE_TOWRITE Contains phrasing used by spammers score SARE_TOWRITE 1.05 # Original name: RM_bpp_DecidedToWrite # 41s/2h of 119325 corpus (98981s/20344h) 03/21/04 # 2s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_TOWRITE 6s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_TOWRITE 11s/3h of 140226 corpus (90162s/50064h DOC) 04/19/06 #body SARE_DRMWOMAN /your dream woman/i #describe SARE_DRMWOMAN Contains phrasing used by spammers #score SARE_DRMWOMAN 0.055 # Original name: RM_bpp_DreamWoman # 1s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 0s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_DRMWOMAN 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_DRMWOMAN 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 body SARE_GETFCK /get fuck/i describe SARE_GETFCK Contains phrasing used by spammers score SARE_GETFCK 1.66 # type=spamp # Original name: RM_bpp_GetFucked # 22s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 8s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_GETFCK 71s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_GETFCK 32s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 #body SARE_GIRLSDOANY /girls will do anything/i #describe SARE_GIRLSDOANY Contains phrasing used by spammers #score SARE_GIRLSDOANY 0.166 # Original name: RM_bpp_GirlsDoAny # 3s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 3s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_GIRLSDOANY 1s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_GIRLSDOANY 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 #body SARE_HORNY2 /horny as hell/i #describe SARE_HORNY2 Contains phrasing used by spammers #score SARE_HORNY2 0.222 # Original name: RM_bpp_HornyAsHell # 4s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 3s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_HORNY2 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_HORNY2 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 #body SARE_MOMBLOW /mother blows/i #describe SARE_MOMBLOW textual phrase implies porn spam #score SARE_MOMBLOW 0.111 # Original name: RM_bpp_MotherBlows # 2s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 0s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_MOMBLOW 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_MOMBLOW 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 body SARE_BADGIRLS /(?:amateur|horny|asian) girls/i describe SARE_BADGIRLS Contains phrasing used by spammers score SARE_BADGIRLS 0.52 # Original name: RM_bpp_PornGirls # 12s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 9s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_BADGIRLS 21s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_BADGIRLS 5s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 body SARE_QLTYSINGLES /quality singles/i describe SARE_QLTYSINGLES Contains phrasing seen in spam score SARE_QLTYSINGLES 1.66 # Original name: RM_bpp_QualitySingles # 3s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 0s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_QLTYSINGLES 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_QLTYSINGLES 1s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 #body SARE_HORNY1 /so hoo+rny/i #describe SARE_HORNY1 Contains phrasing used by spammers #score SARE_HORNY1 1.000 # type=spamp # Original name: SoHorny # 1s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 0s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_HORNY1 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_HORNY1 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 #body SARE_SONSDICK /son's dick/i #describe SARE_SONSDICK textual phrase implies porn spam #score SARE_SONSDICK 1.000 # type=spamp # Original name: SonsDick # 2s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 0s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_SONSDICK 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_SONSDICK 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 body SARE_STILLSINGLE /still single/i describe SARE_STILLSINGLE Contains phrasing used by spammers score SARE_STILLSINGLE 1.66 # Original name: RM_bpp_StillSingle # 11s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 5s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_STILLSINGLE 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_STILLSINGLE 71s/1h of 140226 corpus (90162s/50064h DOC) 04/19/06 #body SARE_UNDRESSMTHR /undressed mother/i #describe SARE_UNDRESSMTHR textual phrase implies porn spam #score SARE_UNDRESSMTHR 0.200 # Original name: RM_bpp_UndressedMother # 2s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 0s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_UNDRESSMTHR 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_UNDRESSMTHR 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 body SARE_HOUSEWIVES /housewives/i describe SARE_HOUSEWIVES Mentions housewives, as in porn or in-home biz score SARE_HOUSEWIVES 0.99 # Original name: RM_bwp_housewives # 138s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 18s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_HOUSEWIVES 13s/3h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_HOUSEWIVES 37s/6h of 140226 corpus (90162s/50064h DOC) 04/19/06 body SARE_SCHLGRL /schoolgirls/i describe SARE_SCHLGRL mentions schoolgirls, as in porn score SARE_SCHLGRL 1.29 # Original name: RM_bwp_schoolgirls # 11s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 6s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_SCHLGRL 15s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_SCHLGRL 19s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 ############################### # OBFU body rules # ############################### body SARE_ADLTOBFU /\b(?:adu?1t|amb[1!]en|b0y|bl0w|c0cks?|c0re|d0main|f?r0m|g(?:[1!]r[1l]|ir[!1])|[1!]ntercourse|l1ttle|l0se|mai1|manh00d|m0vie|[0o]rg\@sm|p[0\@]rn|p1ct|pen[1!]s|(?:ph|f)(?:[0\@]t|ot[0\@])|pu[s5]{1,2}[1!]e[s5]|secks|sm00th|t1ny|t1ts|v(?:irg1|1rgi|1rg1)n|v[i1]de0|y0ung|y0ur)/i describe SARE_ADLTOBFU Contains OBFU adult material score SARE_ADLTOBFU 0.68 # Combined from FVGT_b_N0N0_WORDS, OACYS_DISGUISED_P0RN, M_K_N0N0_WORDS_BODY # 768s/1h of 119325 corpus (98981s/20344h) 03/21/04 # 89s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_ADLTOBFU 930s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_ADLTOBFU 663s/10h of 140226 corpus (90162s/50064h DOC) 04/19/06 body SARE_OBFUENLARGE /\b(?!enlarge)e.?n.?l.?a.?r.?g.?e/i describe SARE_OBFUENLARGE masked spam word(s) score SARE_OBFUENLARGE 1.66 # type=obfu # Original name: RM_bwo_Enlarge # 478s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 18s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_OBFUENLARGE 15s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_OBFUENLARGE 466s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 #body SARE_OBFUFCK1 /(?!\bfuck)(?:\bf|\B(?:\xC5\xBF|\xC6\x92|\xD2[\x92-\x93]))[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[uv\xB5\xD9-\xDC\xF9-\xFC]|\xC5[\xA8-\xB3]|\xC6[\xAF-\xB0]|\xC7[\x93-\x9C]|\xCE\xB0|\xCE\xBC|\xCF\x8B|\xCF\x8D|\xD4\xB1|\xD5\x84|\xD5\x8D)[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[c\xC7\xE7\xA2\xA9]|\xC4[\x86-\x8D]|\xD0\xA1|\xD1\x81)[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:k|\xC4[\xB6-\xB8]|\xCE\x9A|\xCE\xBA|\xD0\x8C|\xD0\x9A|\xD0\xBA|\xD1\x9C|\xD2[\x9A-\x9D]])/i #describe SARE_OBFUFCK1 Apparent spam seems to contain porn subject #score SARE_OBFUFCK1 1.666 # type=obfu # Original name: RM_bwo_Fucko1 # 42s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 23s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_OBFUFCK1 19s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_OBFUFCK1 35s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 body SARE_OBFUFCK2 /(?!\bfun?ck)\bf.?u.?c.?k/i describe SARE_OBFUFCK2 Apparent spam seems to contain porn subject score SARE_OBFUFCK2 1.00 # type=obfu # Original name: RM_bwo_Fucko2 # 70s/1h of 119325 corpus (98981s/20344h) 03/21/04 # 29s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_OBFUFCK2 56s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_OBFUFCK2 73s/3h of 140226 corpus (90162s/50064h DOC) 04/19/06 #body SARE_OBFUGNGBNG /(?!\bgangbang(ed)?\b)(?:\b[g6]|\B(?:\xC4[\x9C-\xA3]))[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[a4\*\@\xC0-\xC5\xAA\xE0-\xE5]|\/\\|\xC4[\x80-\x85]|\xC7[\x8D-\x8E]|\xC7[\xBA-\xBB]|\xCE\x86|\xCE\x91|\xCE\x94|\xCE\x9B|\xCE\xAC|\xCE\xB1|\xD0\x90|\xD0\xB0)[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[n\xD1\xF1]|\|\\\||\xC5[\x83-\x8B]|\xCE\x9D|\xCE\xA0|\xCE\xAE|\xCE\xB7|\xD5\xB2|\xD5\xB8)[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[g6]|\xC4[\x9C-\xA3]])[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[b8\xDF]|\xCE\x92|\xCE\xB2|\xD0\x92|\xD0\xB2)[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[a4\*\@\xC0-\xC5\xAA\xE0-\xE5]|\/\\|\xC4[\x80-\x85]|\xC7[\x8D-\x8E]|\xC7[\xBA-\xBB]|\xCE\x86|\xCE\x91|\xCE\x94|\xCE\x9B|\xCE\xAC|\xCE\xB1|\xD0\x90|\xD0\xB0)[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[n\xD1\xF1]|\|\\\||\xC5[\x83-\x8B]|\xCE\x9D|\xCE\xA0|\xCE\xAE|\xCE\xB7|\xD5\xB2|\xD5\xB8)[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[g6]|\xC4[\x9C-\xA3]])((?:[e3\*\xC8-\xCB\xE8-\xEB]|\xC4[\x92-\x9B]|\xCE\x88|\xCE\x95|\xCE\xA3|\xCE\xAD|\xCE\xB5|\xD0\x81|\xD0\x95|\xD0\xB5|\xD1\x91)[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[d\xD0]|\xC4[\x8E-\x91]))?\b/i #describe SARE_OBFUGNGBNG masked spam word(s) #score SARE_OBFUGNGBNG 2.5 # type=obfu # Original name: RM_bwo_Gangbang # 2s/0h of 15929 corpus (13729s/2200h) 03/23/04 # 3s/0h of 119325 corpus (98981s/20344h) 03/21/04 #counts SARE_OBFUGNGBNG 11s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_OBFUGNGBNG 1s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 #body SARE_OBFUGIRLS /(?!\bgirls?\b)(?:\b[g6]|\B(?:\xC4[\x9C-\xA3]))[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[il1:\|\*\xCC-\xCF\xEC-\xEF\xA6]|\xC4[\xA8-\xB0]|\xC4\xBA|\xC4\xBC|\xC4\xBE|\xC5\x80|\xC5\x82|\xC7[\x8F-\x90]|\xD0[\x86-\x87]|\xD1[\x96-\x97]|\xCE\x8A|\xCE\x90|\xCE\x99|\xCE\xAA|\xCE\xAF|\xCE\xB9|\xCF\x8A)[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[r\xAE]|\xC5[\x94-\x99]|\xD1\x93)[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[l1I\|\xA3]|(?:\xC5[\x80-\x82]|\xC4[\xB9-\xBF]))[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[s5\$\xA7]|\xC5[\x9A-\xA1]|\xD0\x85|\xD1\x95|\xD5\x8F)?\b/i #describe SARE_OBFUGIRLS masked spam word(s) #score SARE_OBFUGIRLS 3.222 # type=obfu # ham: jpg # Original name: RM_bwo_Girls # 25s/1h of 15929 corpus (13729s/2200h) 03/23/04 # 318s/1h of 119325 corpus (98981s/20344h) 03/21/04 #counts SARE_OBFUGIRLS 112s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_OBFUGIRLS 13s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 #body SARE_OBFUPENIS /(?!\bpen ?is\b)(?:\bp|\B(?:[\xDE]|\xCE\xA1|\xCF\x81|\xD0\xA0|\xD1\x80))[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[e3\*\xC8-\xCB\xE8-\xEB]|\xC4[\x92-\x9B]|\xCE\x88|\xCE\x95|\xCE\xA3|\xCE\xAD|\xCE\xB5|\xD0\x81|\xD0\x95|\xD0\xB5|\xD1\x91)[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[n\xD1\xF1]|\|\\\||\xC5[\x83-\x8B]|\xCE\x9D|\xCE\xA0|\xCE\xAE|\xCE\xB7|\xD5\xB2|\xD5\xB8)[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[il1:\|\*\xCC-\xCF\xEC-\xEF\xA6]|\xC4[\xA8-\xB0]|\xC4\xBA|\xC4\xBC|\xC4\xBE|\xC5\x80|\xC5\x82|\xC7[\x8F-\x90]|\xD0[\x86-\x87]|\xD1[\x96-\x97]|\xCE\x8A|\xCE\x90|\xCE\x99|\xCE\xAA|\xCE\xAF|\xCE\xB9|\xCF\x8A)[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[s5]\b|(?:[\$\xA7]|\xC5[\x9A-\xA1]|\xD0\x85|\xD1\x95|\xD5\x8F)\B)/i #describe SARE_OBFUPENIS masked spam word(s) #score SARE_OBFUPENIS 2.333 # type=obfu # Original name: RM_bwo_Penis # 1027s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 91s/1h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_OBFUPENIS 516s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_OBFUPENIS 578s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 #body SARE_OBFUPORNO /(?!\bporno?\b)(?:\bp|\B(?:[\xDE]|\xCE\xA1|\xCF\x81|\xD0\xA0|\xD1\x80))[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[o0\*\xB0\xBA\xD8\xF8\xD2-\xD6\xF2-\xF6]|\(\)|\[\]|\xC5[\x8C-\x91]|\xC6[\xA0-\xA1]|\xC7[\x91-\x92]|\xC7[\xBE-\xBF]|\xCE\x8C|\xCE\x98|\xCE\x9F|\xCE\xB8|\xCE\xBF|\xCF\x8C|\xD0\x9E|\xD0\xBE|\xD5\x95)[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[r\xAE]|\xC5[\x94-\x99]|\xD1\x93)[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[n\xD1\xF1]|\|\\\||\xC5[\x83-\x8B]|\xCE\x9D|\xCE\xA0|\xCE\xAE|\xCE\xB7|\xD5\xB2|\xD5\xB8)[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[o0\*\xB0\xBA\xD8\xF8\xD2-\xD6\xF2-\xF6]|\(\)|\[\]|\xC5[\x8C-\x91]|\xC6[\xA0-\xA1]|\xC7[\x91-\x92]|\xC7[\xBE-\xBF]|\xCE\x8C|\xCE\x98|\xCE\x9F|\xCE\xB8|\xCE\xBF|\xCF\x8C|\xD0\x9E|\xD0\xBE|\xD5\x95)?\b/i #describe SARE_OBFUPORNO masked spam word(s) # score SARE_OBFUPORNO 2.500 # type=obfu # Original name: RM_bwo_Porno # 266s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 36s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_OBFUPORNO 43s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_OBFUPORNO 22s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 #body SARE_OBFUPUSS /(?!\bpussies\b)(?:\bp|\B(?:[\xDE]|\xCE\xA1|\xCF\x81|\xD0\xA0|\xD1\x80))[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[uv\*\xB5\xD9-\xDC\xF9-\xFC]|\xC5[\xA8-\xB3]|\xC6[\xAF-\xB0]|\xC7[\x93-\x9C]|\xCE\xB0|\xCE\xBC|\xCF\x8B|\xCF\x8D|\xD4\xB1|\xD5\x84|\xD5\x8D)[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[s5\$\xA7]|\xC5[\x9A-\xA1]|\xD0\x85|\xD1\x95|\xD5\x8F)[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[s5\$\xA7]|\xC5[\x9A-\xA1]|\xD0\x85|\xD1\x95|\xD5\x8F)[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[il1:\|\*\xCC-\xCF\xEC-\xEF\xA6]|\xC4[\xA8-\xB0]|\xC4\xBA|\xC4\xBC|\xC4\xBE|\xC5\x80|\xC5\x82|\xC7[\x8F-\x90]|\xD0[\x86-\x87]|\xD1[\x96-\x97]|\xCE\x8A|\xCE\x90|\xCE\x99|\xCE\xAA|\xCE\xAF|\xCE\xB9|\xCF\x8A)[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[e3\*\xC8-\xCB\xE8-\xEB]|\xC4[\x92-\x9B]|\xCE\x88|\xCE\x95|\xCE\xA3|\xCE\xAD|\xCE\xB5|\xD0\x81|\xD0\x95|\xD0\xB5|\xD1\x91)[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[s5]\b|(?:[\$\xA7]|\xC5[\x9A-\xA1]|\xD0\x85|\xD1\x95|\xD5\x8F)\B)/i #describe SARE_OBFUPUSS masked spam word(s) #score SARE_OBFUPUSS 2.500 # type=obfu # Original name: RM_bwo_Pussies # 28s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 27s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_OBFUPUSS 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_OBFUPUSS 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 body SARE_OBFUSEXUAL /\b(?!Sexual)S.?e.?x.?u.?a.?l/i describe SARE_OBFUSEXUAL masked spam word(s) score SARE_OBFUSEXUAL 1.66 # type=obfu # Original name: # 409s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 27s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_OBFUSEXUAL 676s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_OBFUSEXUAL 373s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 #body SARE_OBFUTEENS /(?!\bteens?\b)(?:\bt|\B(?:[\+]|\xC5[\xA2-\xA7]|\xCE\xA4|\xCF\x84|\xD0\xA2|\xD1\x82))[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[e3\*\xC8-\xCB\xE8-\xEB]|\xC4[\x92-\x9B]|\xCE\x88|\xCE\x95|\xCE\xA3|\xCE\xAD|\xCE\xB5|\xD0\x81|\xD0\x95|\xD0\xB5|\xD1\x91)[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[e3\*\xC8-\xCB\xE8-\xEB]|\xC4[\x92-\x9B]|\xCE\x88|\xCE\x95|\xCE\xA3|\xCE\xAD|\xCE\xB5|\xD0\x81|\xD0\x95|\xD0\xB5|\xD1\x91)[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[n\xD1\xF1]|\|\\\||\xC5[\x83-\x8B]|\xCE\x9D|\xCE\xA0|\xCE\xAE|\xCE\xB7|\xD5\xB2|\xD5\xB8)[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[s5\$\xA7]|\xC5[\x9A-\xA1]|\xD0\x85|\xD1\x95|\xD5\x8F)?\b/i #describe SARE_OBFUTEENS masked spam word(s) #score SARE_OBFUTEENS 2.500 # type=obfu # Original name: RM_bwo_Teens # 28s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 4s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_OBFUTEENS 1s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_OBFUTEENS 1s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 body SARE_OBFUTESTO /\b(?!testosterone)t.?e.?s.?t.?o.?s.?t.?e.?r.?o.?n.?e/i describe SARE_OBFUTESTO masked spam word(s) score SARE_OBFUTESTO 1.66 # type=obfu # Original name: RM_bwo_Testosterone # 10s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 0s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_OBFUTESTO 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_OBFUTESTO 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 #body SARE_OBFUVRGN /(?!\bvirgins?\b)(?:\b[vu]|\B(?:\\\/|\xCE\xBD))[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[il1:\|\*\xCC-\xCF\xEC-\xEF\xA6]|\xC4[\xA8-\xB0]|\xC4\xBA|\xC4\xBC|\xC4\xBE|\xC5\x80|\xC5\x82|\xC7[\x8F-\x90]|\xD0[\x86-\x87]|\xD1[\x96-\x97]|\xCE\x8A|\xCE\x90|\xCE\x99|\xCE\xAA|\xCE\xAF|\xCE\xB9|\xCF\x8A)[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[r\xAE]|\xC5[\x94-\x99]|\xD1\x93)[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[g6]|\xC4[\x9C-\xA3]])[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[il1:\|\*\xCC-\xCF\xEC-\xEF\xA6]|\xC4[\xA8-\xB0]|\xC4\xBA|\xC4\xBC|\xC4\xBE|\xC5\x80|\xC5\x82|\xC7[\x8F-\x90]|\xD0[\x86-\x87]|\xD1[\x96-\x97]|\xCE\x8A|\xCE\x90|\xCE\x99|\xCE\xAA|\xCE\xAF|\xCE\xB9|\xCF\x8A)[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[n\xD1\xF1]|\|\\\||\xC5[\x83-\x8B]|\xCE\x9D|\xCE\xA0|\xCE\xAE|\xCE\xB7|\xD5\xB2|\xD5\xB8)[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[s5\$\xA7]|\xC5[\x9A-\xA1]|\xD0\x85|\xD1\x95|\xD5\x8F)?\b/i #describe SARE_OBFUVRGN masked spam word(s) #score SARE_OBFUVRGN 2.500 # type=obfu # Original name: RM_bwo_Virgins # 25s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 16s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_OBFUVRGN 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_OBFUVRGN 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 #body SARE_SPRDLGS /spread(?:ing)? their leg/i #describe SARE_SPRDLGS Contains possible adult phrase #score SARE_SPRDLGS 0.222 # 4s/0h of 125078 corpus (104890s/20188h) 03/29/04 # 0s/0h of 15929 corpus (13729s/2200h) 03/29/04 #counts SARE_SPRDLGS 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_SPRDLGS 2s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 body SARE_RPTLETTERS /(?!\b(?:ass|cock|pussy)\b)\b(?:a+s+s+|c+o+c+k+|p+u+s+s+y+)\b/i describe SARE_RPTLETTERS Contains mis-spelled adult phrase(s) score SARE_RPTLETTERS 1.66 # 5s/0h of 125078 corpus (104890s/20188h) 03/29/04 # 2s/0h of 15929 corpus (13729s/2200h) 03/29/04 #counts SARE_RPTLETTERS 15s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_RPTLETTERS 1s/1h of 140226 corpus (90162s/50064h DOC) 04/19/06 body SARE_SEXDRIVE /\bSex(?:ual)? Drive/i describe SARE_SEXDRIVE Talks about sex drive score SARE_SEXDRIVE 1.66 # Original name: RM_bpm_SexDrive # 589s/0h of 125078 corpus (104890s/20188h) 03/29/04 # 141s/0h of 15929 corpus (13729s/2200h) 03/29/04 #counts SARE_SEXDRIVE 239s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_SEXDRIVE 531s/5h of 140226 corpus (90162s/50064h DOC) 04/19/06 body SARE_BETTERSEX /better sex/i describe SARE_BETTERSEX Spammer phrasing in body of email score SARE_BETTERSEX 1.66 # Original name: RM_bpm_BetterSex # 157s/0h of 125078 corpus (104890s/20188h) 03/29/04 # 8s/0h of 15929 corpus (13729s/2200h) 03/29/04 #counts SARE_BETTERSEX 292s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_BETTERSEX 262s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 body SARE_SEXENHANCER /sex(?:ual)? enhancer/i describe SARE_SEXENHANCER mentions spam topic score SARE_SEXENHANCER 1.66 # type=spamp # Original name: RM_bpm_SexEnhancer # 11s/0h of 125078 corpus (104890s/20188h) 03/29/04 # 11s/0h of 15929 corpus (13729s/2200h) 03/29/04 #counts SARE_SEXENHANCER 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_SEXENHANCER 7s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 #body SARE_OBFUHARDCORE /(?!hard[ -]?core)(?:\bh|\B(?:\xC4[\xA4-\xA7]|\xCE\x89|\xCE\x97|\xD0\x9D|\xD0\xBD|\xD1\x92|\xD2[\xA2-\xA3]|\xD2[\xBA-\xBB]|\xD5\xB0))[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[a4\*\@\xC0-\xC5\xAA\xE0-\xE5]|\/\\|\xC4[\x80-\x85]|\xC7[\x8D-\x8E]|\xC7[\xBA-\xBB]|\xCE\x86|\xCE\x91|\xCE\x94|\xCE\x9B|\xCE\xAC|\xCE\xB1|\xD0\x90|\xD0\xB0)[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[r\xAE]|\xC5[\x94-\x99]|\xD1\x93)[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[d\xD0]|\xC4[\x8E-\x91])[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[c\*\xC7\xE7\xA2\xA9]|\xC4[\x86-\x8D]|\xD0\xA1|\xD1\x81)[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[o0\*\xB0\xBA\xD8\xF8\xD2-\xD6\xF2-\xF6]|\(\)|\[\]|\xC5[\x8C-\x91]|\xC6[\xA0-\xA1]|\xC7[\x91-\x92]|\xC7[\xBE-\xBF]|\xCE\x8C|\xCE\x98|\xCE\x9F|\xCE\xB8|\xCE\xBF|\xCF\x8C|\xD0\x9E|\xD0\xBE|\xD5\x95)[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[r\xAE]|\xC5[\x94-\x99]|\xD1\x93)[\x01-\x2F\\\^_`\|\x7F-\xA1\xA4-\xA8\xAB-\xAD\xAF-\xB1\xB4\xB7-\xBB\xBF\xF7]?(?:[e3]\b|(?:[\*\xC8-\xCB\xE8-\xEB]|\xC4[\x92-\x9B]|\xCE\x88|\xCE\x95|\xCE\xA3|\xCE\xAD|\xCE\xB5|\xD0\x81|\xD0\x95|\xD0\xB5|\xD1\x91)\B)/i #describe SARE_OBFUHARDCORE masked spam word(s) #score SARE_OBFUHARDCORE 1.433 # type=obfu # Original name: RM_bwo_hardcore # 32s/0h of 98440 corpus (76828s/21612h) 05/09/04 #counts SARE_OBFUHARDCORE 4s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_OBFUHARDCORE 3s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 ############################### # uri rules # ############################### #uri SARE_PNSPTCH /\bbolik34\b/i #describe SARE_PNSPTCH Terra.es penil patch spammer #score SARE_PNSPTCH 1.5 # was .33 # Original name: MAKEPENIBIG # 277s/0h of 119325 corpus (98981s/20344h) 03/21/04 # 0s/0h of 15929 corpus (13729s/2200h) 03/23/04 #counts SARE_PNSPTCH 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06 #counts SARE_PNSPTCH 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06 # EOF