1 # SARE "Adult" Ruleset for SpamAssassin
2 # Version: 01.02.08 # The Adult set has been renamed to match SARE's updated standards, the new name is 70_sare_adult.cf
5 # Changes: Fixed broken meta
6 # License: Artistic - see http://www.rulesemporium.com/license.txt
7 # Current Maintainer: Matt Yackley - adult@rulesemporium.com
8 # Maintainer: Doc Schneider - maddoc@maddoc.net
9 # Current Home: http://www.rulesemporium.com/rules/70_sare_adult.cf
14 ###############################
16 ###############################
19 header SARE_SUBJ_SLUT Subject =~ /\bslut\b/i
20 score SARE_SUBJ_SLUT 1.66
21 #counts SARE_SUBJ_SLUT 89s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
22 #counts SARE_SUBJ_SLUT 5s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
25 header __FPS_BREAST Subject =~ /\bbreasts?\b/i
26 header __FPS_COCK Subject =~ /\bcock\b/i
27 header __FPS_FUCK Subject =~ /\bfuck/i
28 header __FPS_GIRLS Subject =~ /\bgirls\b/i
29 header __FPS_HARDCORE Subject =~ /\bhard.?core\b/i
30 header __FPS_LITTLE Subject =~ /\blittle\b/i
31 header __FPS_MODEL Subject =~ /\bmodels?\b/i
32 header __FPS_NAKED Subject =~ /\bnaked\b/i
33 header __FPS_PENETRAT Subject =~ /\bpenetration\b/i
34 header __FPS_SEX Subject =~ /\bsex\b/i
35 header __FPS_SLUT Subject =~ /\bslut\b/i
36 header __FPS_TEEN Subject =~ /\bteen\b/i
37 header __FPS_VIRGIN Subject =~ /\bvirgins?\b/i
38 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
39 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
40 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
43 meta SARE_SUB_MULTI_PRN2 (__COUNT_FPORN2 && !__COUNT_FPORN3)
44 score SARE_SUB_MULTI_PRN2 1.66
45 #counts SARE_SUB_MULTI_PRN2 455s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
46 #counts SARE_SUB_MULTI_PRN2 93s/5h of 140226 corpus (90162s/50064h DOC) 04/19/06
49 meta SARE_SUB_MULTI_PRN3 (__COUNT_FPORN3 && !__COUNT_FPORN4)
50 score SARE_SUB_MULTI_PRN3 1.66
51 #counts SARE_SUB_MULTI_PRN3 93s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
52 #counts SARE_SUB_MULTI_PRN3 9s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
55 #meta SARE_SUB_MULTI_PRN4 (__COUNT_FPORN4)
56 #score SARE_SUB_MULTI_PRN4 3.333
57 #counts SARE_SUB_MULTI_PRN4 4s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
58 #counts SARE_SUB_MULTI_PRN4 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
66 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
67 describe SARE_ADLTSUB1 Contains OBFU and "strong" adult words
68 score SARE_ADLTSUB1 1.66
69 # Combined from M_K_PORN_BOGOSITY_SUBJ, L_s_porn, SUBJECT_XXX, RM_swp_porn4, RM_swp_porn5
70 # 266s/0h of 119325 corpus (98981s/20344h) 03/21/04
71 # 45s/0h of 15929 corpus (13729s/2200h) 03/23/04
72 #counts SARE_ADLTSUB1 503s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
73 #counts SARE_ADLTSUB1 145s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
76 header SARE_ADLTSUB2 Subject =~ /\b(?:blow|climax|enlarg(e|ment)|fuck|inter+acial|lick|porn|penis|pervert|pussy|tits|tight|vagina|virgins?)\b/i
77 describe SARE_ADLTSUB2 Contains possible adult words
78 score SARE_ADLTSUB2 1.23
79 # Combined from SUBJECT_XXX_2, L_s_porn, RM_swp_pervert, RM_swp_porn1, RM_swp_porn2
80 # 519s/1h of 119325 corpus (98981s/20344h) 03/21/04
81 # 58s/0h of 15929 corpus (13729s/2200h) 03/23/04
82 #counts SARE_ADLTSUB2 1967s/2h of 42056 corpus (34127s/7929h FVGT) 04/19/06
83 #counts SARE_ADLTSUB2 514s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
86 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
87 describe SARE_ADLTSUB3 Apparent spam seems to contain porn subject
88 score SARE_ADLTSUB3 1.66 # type=obfu
89 # Original name: RM_swp_porn1o1
90 # 58s/0h of 119325 corpus (98981s/20344h) 03/21/04
91 # 11s/0h of 15929 corpus (13729s/2200h) 03/23/04
92 #counts SARE_ADLTSUB3 11s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
93 #counts SARE_ADLTSUB3 15s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
96 header SARE_ADLTSUB4 Subject =~ /(?!\bpo(?:rn|ur))\bp.?o.?r.?n/i
97 describe SARE_ADLTSUB4 Apparent spam seems to contain porn subject
98 score SARE_ADLTSUB4 0.89 # type=obfu
99 # Original name: RM_swp_porn1o2
100 # 26s/0h of 119325 corpus (98981s/20344h) 03/21/04
101 # 3s/0h of 15929 corpus (13729s/2200h) 03/23/04
102 #counts SARE_ADLTSUB4 5s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
103 #counts SARE_ADLTSUB4 5s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
106 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
107 describe SARE_ADLTSUB5 Apparent spam seems to contain porn subject
108 score SARE_ADLTSUB5 1.66 # type=obfu
109 # Original name: RM_swp_porn2o1
110 # 8s/0h of 119325 corpus (98981s/20344h) 03/21/04
111 # 4s/0h of 15929 corpus (13729s/2200h) 03/23/04
112 #counts SARE_ADLTSUB5 12s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
113 #counts SARE_ADLTSUB5 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
116 header SARE_ADLTSUB6 Subject =~ /(?!\bfuck)\bf.?u.?c.?k/i
117 describe SARE_ADLTSUB6 Apparent spam seems to contain porn subject
118 score SARE_ADLTSUB6 1.51 # type=obfu
119 # Original name: RM_swp_porn2o2
120 # 3s/0h of 119325 corpus (98981s/20344h) 03/21/04
121 # 5s/0h of 15929 corpus (13729s/2200h) 03/23/04
122 #counts SARE_ADLTSUB6 32s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
123 #counts SARE_ADLTSUB6 13s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
126 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
127 describe SARE_ADLTSUB7 Apparent spam seems to contain porn subject
128 score SARE_ADLTSUB7 1.66 # type=obfu
129 # Original name: RM_swp_porn5o1
130 # 4s/0h of 119325 corpus (98981s/20344h) 03/21/04
131 # 2s/0h of 15929 corpus (13729s/2200h) 03/23/04
132 #counts SARE_ADLTSUB7 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
133 #counts SARE_ADLTSUB7 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
136 header SARE_ADLTSUB8 Subject =~ /(?!\bpuss(?:y|ies)\b)\bp.?u.?s.?s.?(?:y|i.?e.?s)\b/i
137 describe SARE_ADLTSUB8 Apparent spam seems to contain porn subject
138 score SARE_ADLTSUB8 1.66 # type=obfu
139 # Original name: RM_swp_porn5o2
140 # FPS SARE_ADLTSUB8="plus sizes"
141 # 7s/0h of 119325 corpus (98981s/20344h) 03/21/04
142 # 0s/0h of 15929 corpus (13729s/2200h) 03/23/04
143 #counts SARE_ADLTSUB8 6s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
144 #counts SARE_ADLTSUB8 6s/2h of 140226 corpus (90162s/50064h DOC) 04/19/06
147 #header SARE_ADLTSUB10 Subject =~ /(?!\b(?:rap(?:e[sd]?|ing|pel)|reaping)\b)\br.?a.?p.?(?:e.?[sd]?|i.?n.?g)\b/i
148 #describe SARE_ADLTSUB10 Apparent spam seems to contain porn subject
149 #score SARE_ADLTSUB10 2.500 # type=obfu
150 # Original name: RM_swp_Rapeo2
151 # 20s/0h of 119325 corpus (98981s/20344h) 03/21/04
152 # 0s/0h of 15929 corpus (13729s/2200h) 03/23/04
153 #counts SARE_ADLTSUB10 5s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
154 #counts SARE_ADLTSUB10 6s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
157 #header SARE_BEDROOMSEC Subject =~ /bedroom secret/i
158 #describe SARE_BEDROOMSEC Common spammer phrasing
159 #score SARE_BEDROOMSEC 0.611
160 # Original name: RM_spp_BedroomSec
161 # 10s/0h of 125078 corpus (104890s/20188h) 03/29/04
162 # 0s/0h of 15929 corpus (13729s/2200h) 03/29/04
163 #counts SARE_BEDROOMSEC 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
164 #counts SARE_BEDROOMSEC 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
167 ###############################
169 ###############################
172 body FB_SEXOHOL /sexoholics/i
173 score FB_SEXOHOL 1.66
174 #counts FB_SEXOHOL 7s/0h of 32370 corpus (24496s/7874h ML) 12/12/05
175 #counts FB_SEXOHOL 37s/0h of 40658 corpus (35364s/5294h MY) 12/12/05
176 #counts FB_SEXOHOL 33s/0h of 207630 corpus (200121s/7509h FT) 12/13/05
177 #counts FB_SEXOHOL 3s/0h of 9809 corpus (4905s/4904h FT) 12/12/05
178 #counts FB_SEXOHOL 11s/0h of 11532 corpus (6163s/5369h CT) 12/12/05
179 #counts FB_SEXOHOL 4s/0h of 70031 corpus (30720s/39311h DOC) 12/12/05
180 #counts FB_SEXOHOL 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
181 #counts FB_SEXOHOL 18s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
184 body FB_XUAL /\bxual\b/
186 #counts FB_XUAL 20s/0h of 6871 corpus (5500s/1371h AxB) 12/15/05
187 #counts FB_XUAL 67s/0h of 34342 corpus (25865s/8477h ML) 12/15/05
188 #counts FB_XUAL 22s/0h of 40631 corpus (35338s/5293h MY) 12/15/05
189 #counts FB_XUAL 62s/0h of 70858 corpus (31544s/39314h DOC) 12/15/05
190 #counts FB_XUAL 855s/0h of 107818 corpus (99658s/8160h FVGT) 03/11/06
191 #counts FB_XUAL 100s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
192 #counts FB_XUAL 360s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
195 #body FB_NOT_SEX / s[^afeiloprsuw]x\b/i
196 #score FB_NOT_SEX 1.003
197 #counts FB_NOT_SEX 7s/7h of 37297 corpus (31824s/5473h MY) 02/07/06
198 #counts FB_NOT_SEX 4s/4h of 6866 corpus (4638s/2228h AxB) 02/07/06
199 #counts FB_NOT_SEX 4s/5h of 11694 corpus (6132s/5562h CT) 02/07/06
200 #counts FB_NOT_SEX 204s/4h of 345244 corpus (337372s/7872h FT) 02/07/06
201 #counts FB_NOT_SEX 110s/0h of 107818 corpus (99658s/8160h FVGT) 03/11/06
202 #counts FB_NOT_SEX 23s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
203 #counts FB_NOT_SEX 108s/2h of 140226 corpus (90162s/50064h DOC) 04/19/06
206 #body FB_GIRLS_DOLLAR /girl\$/i
207 #score FB_GIRLS_DOLLAR 1.992
208 #counts FB_GIRLS_DOLLAR 0s/0h of 37297 corpus (31824s/5473h MY) 02/07/06
209 #counts FB_GIRLS_DOLLAR 0s/0h of 6866 corpus (4638s/2228h AxB) 02/07/06
210 #counts FB_GIRLS_DOLLAR 0s/0h of 11694 corpus (6132s/5562h CT) 02/07/06
211 #counts FB_GIRLS_DOLLAR 36s/0h of 345244 corpus (337372s/7872h FT) 02/07/06
212 #counts FB_GIRLS_DOLLAR 8s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
213 #counts FB_GIRLS_DOLLAR 2s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
217 #body FB_DOLLAR_ASS2 /(?:\b|[0-9])(?!ass)a[s\$][s\$](?:\b|e)/i
218 #score FB_DOLLAR_ASS2 0.361
219 #counts FB_DOLLAR_ASS2 2s/1h of 9374 corpus (7151s/2223h AxB) 03/01/06
220 #counts FB_DOLLAR_ASS2 6s/0h of 12244 corpus (6572s/5672h CT) 03/01/06
221 #counts FB_DOLLAR_ASS2 0s/2h of 27495 corpus (21848s/5647h MY) 03/01/06
222 #counts FB_DOLLAR_ASS2 13s/0h of 34977 corpus (27086s/7891h FT) 03/01/06
223 #counts FB_DOLLAR_ASS2 10s/2h of 84470 corpus (67306s/17164h ML) 03/01/06
224 #counts FB_DOLLAR_ASS2 10s/1h of 103116 corpus (63731s/39385h DOC) 03/01/06
225 #counts FB_DOLLAR_ASS2 58s/0h of 107818 corpus (99658s/8160h FVGT) 03/11/06
226 #counts FB_DOLLAR_ASS2 21s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
227 #counts FB_DOLLAR_ASS2 13s/1h of 140226 corpus (90162s/50064h DOC) 04/19/06
230 body FB_HARD_ERECTION /hard(?:er)? (?:erection|penis)/i
231 score FB_HARD_ERECTION 1.66
232 #counts FB_HARD_ERECTION 2728s/0h of 211356 corpus (203977s/7379h FT) 11/23/05
233 #counts FB_HARD_ERECTION 393s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
234 #counts FB_HARD_ERECTION 573s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
237 #body FB_JACKRABBIT /Jack Rabbit Vibrat[o0]r/i
238 #score FB_JACKRABBIT 3.599
239 #counts FB_JACKRABBIT 640s/0h of 211356 corpus (203977s/7379h FT) 11/23/05
240 #counts FB_JACKRABBIT 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
241 #counts FB_JACKRABBIT 47s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
244 body FB_PENIS /\b(?!penis)p[3e]n[i1!][s5]\b/i
246 #counts FB_PENIS 170s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
247 #counts FB_PENIS 386s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
250 body FB_FEMALE_EJACU /female ejaculation/i
251 score FB_FEMALE_EJACU 1.66
252 #counts FB_FEMALE_EJACU 4s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
253 #counts FB_FEMALE_EJACU 1s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
256 body FB_INNOCENT /innocent (?:boy|girl|child)/i
257 score FB_INNOCENT 0.40
258 #counts FB_INNOCENT 14s/1h of 42056 corpus (34127s/7929h FVGT) 04/19/06
259 #counts FB_INNOCENT 7s/1h of 140226 corpus (90162s/50064h DOC) 04/19/06
262 #body LW_PORN_PHOTO /Tell our photographers what to do in their next photo session our video/
263 #score LW_PORN_PHOTO 5
264 #describe LW_PORN_PHOTO Standard 'hot chicks' line
265 #counts LW_PORN_PHOTO 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
266 #counts LW_PORN_PHOTO 3s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
269 #body LW_PORN_ONLINE /high quality photo's online/
270 #score LW_PORN_ONLINE 2
271 #describe LW_PORN_ONLINE Standard 'hot chicks' line
272 #counts LW_PORN_ONLINE 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
273 #counts LW_PORN_ONLINE 4s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
276 #body LW_PORN_MODELS /models getting nasty/
277 #score LW_PORN_MODELS 5
278 #describe LW_PORN_MODELS Standard 'hot chicks' line
279 #counts LW_PORN_MODELS 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
280 #counts LW_PORN_MODELS 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
283 body LW_PORN_HELLO /(?:Hey baby|Hello, stranger!) :\)/
284 score LW_PORN_HELLO 1.66
285 describe LW_PORN_HELLO Standard 'hot chicks' line
286 #counts LW_PORN_HELLO 2s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
287 #counts LW_PORN_HELLO 5s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
292 #$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$
293 # set of porn keywords / when these words appear, it's more likely porn. SET A.
294 body __FVGT_BREASTS /\bbreasts?\b/i
295 body __FVGT_FUCK /\bfuck/i
296 body __FVGT_RAPE /\braped?\b/i
297 body __FVGT_HORNY /\bhorny\b/i
298 body __FVGT_VIRGIN /\bvirgins?\b/i
299 body __FVGT_COCK /\bcock\b/i
300 body __FVGT_LOLITA /\blolita\b/i
301 body __FVGT_YOUNGGIRL /Young(?:est)? (?:girl|chick)/i
302 body __FVGT_PUSSY /\bpuss(?:y|ies)/i
303 body __FVGT_ASS /\sass\s/i
304 body __FVGT_SLUT /\bslut\b/i
306 # meta's to count how many porn words from Set A.
307 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)
308 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)
310 score FM_PORN_A_4 1.09
311 #counts FM_PORN_A_4 796s/2h of 42056 corpus (34127s/7929h FVGT) 04/19/06
312 #counts FM_PORN_A_4 243s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
316 score FM_PORN_A_5 0.98
317 #counts FM_PORN_A_5 358s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
318 #counts FM_PORN_A_5 172s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
325 body __HAS_COLLECTION /\bcollection\b/i
326 body __HAS_HARDCORE /\bhardcore\b/i
327 body __HAS_YOUNGGIRL /\byoung\s?girls?\b/i
328 body __HAS_ADOLESCENT /\badolescents?\b/i
329 body __HAS_CHICKS /\bchicks?\b/i
331 meta FP_MIXED_PORN3 ((__HAS_COLLECTION + __HAS_HARDCORE + __HAS_YOUNGGIRL + __HAS_ADOLESCENT + __HAS_CHICKS) > 2)
332 score FP_MIXED_PORN3 1.66
333 #counts FP_MIXED_PORN3 4s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
334 #counts FP_MIXED_PORN3 5s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
338 body SARE_ADULT1 /(?:suck|l[i1]ck).{1,30}(c[o0]ck|d[i1]ck)/i
339 describe SARE_ADULT1 Contains adult material
340 score SARE_ADULT1 1.47
341 # Original name: FVGT_b_ADULT02
342 # 55s/2h of 119325 corpus (98981s/20344h) 03/21/04
343 # 18s/0h of 15929 corpus (13729s/2200h) 03/23/04
344 #counts SARE_ADULT1 512s/1h of 42056 corpus (34127s/7929h FVGT) 04/19/06
345 #counts SARE_ADULT1 129s/1h of 140226 corpus (90162s/50064h DOC) 04/19/06
348 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
349 describe SARE_ADULT2 Contains adult material
350 score SARE_ADULT2 1.42
351 # Original name: MY_XXX_BODY, was rawbody
352 # 9985s/30h of 119325 corpus (98981s/20344h) 03/21/04
353 # 683s/2h of 15929 corpus (13729s/2200h) 03/23/04
354 #counts SARE_ADULT2 4729s/9h of 42056 corpus (34127s/7929h FVGT) 04/19/06
355 #counts SARE_ADULT2 2685s/34h of 140226 corpus (90162s/50064h DOC) 04/19/06
358 body SARE_BETTERORG /(?:boost|magnify|multipl[ey]|increase|frequent|intense|intensify).{1,15}orgasm/i
359 describe SARE_BETTERORG Talks about getting better orgasms
360 score SARE_BETTERORG 1.66
361 # Original name: YM_B_BETTER_ORG, RM_bpm_MultipleOrgasms
362 # 592s/2h of 119325 corpus (98981s/20344h) 03/21/04
363 # 29s/0h of 15929 corpus (13729s/2200h) 03/23/04
364 #counts SARE_BETTERORG 249s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
365 #counts SARE_BETTERORG 111s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
368 body SARE_ENLRGYOUR /enlarge your/i
369 describe SARE_ENLRGYOUR Talks about "enlarging" something
370 score SARE_ENLRGYOUR 1.02
371 # Original name: MY_EN_PENIS, was rawbody, RE_bpm_EnlargeYour
372 # 1735s/0h of 119325 corpus (98981s/20344h) 03/21/04
373 # 91s/0h of 15929 corpus (13729s/2200h) 03/23/04
374 #counts SARE_ENLRGYOUR 537s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
375 #counts SARE_ENLRGYOUR 279s/1h of 140226 corpus (90162s/50064h DOC) 04/19/06
378 body SARE_LRGPNS /(?:bigger|larger|increase your) (?:member\b|rod)/i
379 describe SARE_LRGPNS Talks about a "bigger" appendage
380 score SARE_LRGPNS 1.66
381 # Original name: MY_MEMBER combined with MY_LRGROD
382 # 50s/0h of 119325 corpus (98981s/20344h) 03/21/04
383 # 0s/0h of 15929 corpus (13729s/2200h) 03/23/04
384 #counts SARE_LRGPNS 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
385 #counts SARE_LRGPNS 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
388 body SARE_PNSSIZE /inch(?:es)? .{0,10}(?:cock|dick)/i
389 describe SARE_PNSSIZE Talks about the size of male body part
390 score SARE_PNSSIZE 1.66
391 # Original name: YM_B_BODYPART_1
392 # 3s/0h of 119325 corpus (98981s/20344h) 03/21/04
393 # 6s/0h of 15929 corpus (13729s/2200h) 03/23/04
394 #counts SARE_PNSSIZE 5s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
395 #counts SARE_PNSSIZE 2s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
398 body SARE_SXLIFE /(?:are you single|sex life|youre? partner)/i
399 describe SARE_SXLIFE Talks about your sex life
400 score SARE_SXLIFE 1.07
401 # 695s/15h of 119325 corpus (98981s/20344h) 03/21/04
402 # 212s/1h of 15929 corpus (13729s/2200h) 03/23/04
403 #counts SARE_SXLIFE 991s/12h of 42056 corpus (34127s/7929h FVGT) 04/19/06
404 #counts SARE_SXLIFE 637s/54h of 140226 corpus (90162s/50064h DOC) 04/19/06
407 body SARE_BEASTUD /be a stud/i
408 describe SARE_BEASTUD common spammer phrasing
409 score SARE_BEASTUD 0.26
410 # Original name: RM_bpm_BeAStud
411 # 53s/0h of 119325 corpus (98981s/20344h) 03/21/04
412 # 7s/0h of 15929 corpus (13729s/2200h) 03/23/04
413 #counts SARE_BEASTUD 73s/2h of 42056 corpus (34127s/7929h FVGT) 04/19/06
414 #counts SARE_BEASTUD 20s/1h of 140226 corpus (90162s/50064h DOC) 04/19/06
417 body SARE_BIGRMEMBER /B.?i.?g.?g.?e.?r.{0,5}M.?e.?m.?b.?e.?r/i
418 describe SARE_BIGRMEMBER mentions bigger body part
419 score SARE_BIGRMEMBER 1.66
420 # Original name: RM_bpm_BiggerMember
421 # 17s/0h of 119325 corpus (98981s/20344h) 03/21/04
422 # 0s/0h of 15929 corpus (13729s/2200h) 03/23/04
423 #counts SARE_BIGRMEMBER 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
424 #counts SARE_BIGRMEMBER 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
427 body SARE_INLENGTH /increase.? my length/i
428 describe SARE_INLENGTH common spammer phrasing
429 score SARE_INLENGTH 1.66
430 # Original name: RM_bpm_IncreaseLength
431 # 40s/0h of 119325 corpus (98981s/20344h) 03/21/04
432 # 8s/0h of 15929 corpus (13729s/2200h) 03/23/04
433 #counts SARE_INLENGTH 60s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
434 #counts SARE_INLENGTH 20s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
437 #body SARE_LADYINLIFE /lady in your life/i
438 #describe SARE_LADYINLIFE Contains phrasing used by spammers
439 #score SARE_LADYINLIFE 0.166
440 # Original name: RM_bpm_LadyInLife
441 # 3s/0h of 119325 corpus (98981s/20344h) 03/21/04
442 # 0s/0h of 15929 corpus (13729s/2200h) 03/23/04
443 #counts SARE_LADYINLIFE 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
444 #counts SARE_LADYINLIFE 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
447 #body SARE_MAGICLUBE /"Magic Lubricant"/i
448 #describe SARE_MAGICLUBE Spammer phrasing in body of email
449 #score SARE_MAGICLUBE 2.222 # type=spamgg
450 # Original name: RM_bpm_MagicLubricant
451 # 704s/0h of 119325 corpus (98981s/20344h) 03/21/04
452 # 12s/0h of 15929 corpus (13729s/2200h) 03/23/04
453 #counts SARE_MAGICLUBE 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
454 #counts SARE_MAGICLUBE 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
457 body SARE_NOEMBARRASS /no embarrassing/i
458 describe SARE_NOEMBARRASS Wow, I won't be embarrassed anymore!
459 score SARE_NOEMBARRASS 1.66
460 # Original name: RM_bpm_NoEmbarrassing
461 # 30s/0h of 119325 corpus (98981s/20344h) 03/21/04
462 # 6s/0h of 15929 corpus (13729s/2200h) 03/23/04
463 #counts SARE_NOEMBARRASS 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
464 #counts SARE_NOEMBARRASS 1s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
467 body SARE_PLEASEPARTNR /Pleasure.{1,10}partner/i
468 describe SARE_PLEASEPARTNR common spammer phrasing
469 score SARE_PLEASEPARTNR 1.66
470 # Original name: RM_bpm_PleasurePartnr
471 # 51s/0h of 119325 corpus (98981s/20344h) 03/21/04
472 # 6s/0h of 15929 corpus (13729s/2200h) 03/23/04
473 #counts SARE_PLEASEPARTNR 60s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
474 #counts SARE_PLEASEPARTNR 20s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
477 #body SARE_POWERBOTTLE /"Power Bottle"/i
478 #describe SARE_POWERBOTTLE Spammer phrasing in body of email
479 # score SARE_POWERBOTTLE 2.222 # type=spamgg
480 # Original name: RM_bpm_PowerBottle
481 # 708s/0h of 119325 corpus (98981s/20344h) 03/21/04
482 # 12s/0h of 15929 corpus (13729s/2200h) 03/23/04
483 #counts SARE_POWERBOTTLE 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
484 #counts SARE_POWERBOTTLE 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
487 #body SARE_PRODEREC /produce erections/i
488 #describe SARE_PRODEREC Contains medical spam phrasing
489 #score SARE_PRODEREC 0.055
490 # Original name: RE_bpm_ProdErec
491 # 1s/0h of 119325 corpus (98981s/20344h) 03/21/04
492 # 0s/0h of 15929 corpus (13729s/2200h) 03/23/04
493 #counts SARE_PRODEREC 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
494 #counts SARE_PRODEREC 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
497 body SARE_SUPERVIAGRA /(?:super|weekend)[- ]viagra/i
498 describe SARE_SUPERVIAGRA mentions drug which is often subject of spam
499 score SARE_SUPERVIAGRA 1.66 # type=spamgg
500 # Original name: RM_bpm_SuperViagra, RM_bpm_WeekendViagra
501 # 299s/0h of 119325 corpus (98981s/20344h) 03/21/04
502 # 11s/0h of 15929 corpus (13729s/2200h) 03/23/04
503 #counts SARE_SUPERVIAGRA 136s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
504 #counts SARE_SUPERVIAGRA 704s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
507 body SARE_ADLTDATING /adult dating/i
508 describe SARE_ADLTDATING Contains phrasing used by spammers
509 score SARE_ADLTDATING 0.32
510 # Original name: RM_bpp_Adultdating
511 # 3s/0h of 119325 corpus (98981s/20344h) 03/21/04
512 # 0s/0h of 15929 corpus (13729s/2200h) 03/23/04
513 #counts SARE_ADLTDATING 1s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
514 #counts SARE_ADLTDATING 32s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
517 body SARE_ADLTPRSNLS /adult personals/i
518 describe SARE_ADLTPRSNLS Contains phrasing used by spammers
519 score SARE_ADLTPRSNLS 1.66
520 # Original name: RM_bpp_AdultPersonals
521 # 3s/0h of 119325 corpus (98981s/20344h) 03/21/04
522 # 2s/0h of 15929 corpus (13729s/2200h) 03/23/04
523 #counts SARE_ADLTPRSNLS 1s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
524 #counts SARE_ADLTPRSNLS 13s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
527 #body SARE_AREUBORED /Are you bored of/i
528 #describe SARE_AREUBORED Contains phrasing used by spammers
529 #score SARE_AREUBORED 0.111
530 # Original name: RM_bpp_AreYouBored
531 # 2s/0h of 119325 corpus (98981s/20344h) 03/21/04
532 # 3s/0h of 15929 corpus (13729s/2200h) 03/23/04
533 #counts SARE_AREUBORED 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
534 #counts SARE_AREUBORED 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
537 body SARE_CHILDPRN1 /child porn/i
538 describe SARE_CHILDPRN1 contains reference to child porn
539 score SARE_CHILDPRN1 1.15 # ham: news, FBI auto-responder
540 # Original name: ChildPorn
541 # 64s/3h of 119325 corpus (98981s/20344h) 03/21/04
542 # 5s/0h of 15929 corpus (13729s/2200h) 03/23/04
543 #counts SARE_CHILDPRN1 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
544 #counts SARE_CHILDPRN1 1s/1h of 140226 corpus (90162s/50064h DOC) 04/19/06
547 #body SARE_CHILDPRN2 /child pornography webmaster/i
548 #describe SARE_CHILDPRN2 contains reference to a child porn webmaster
549 #score SARE_CHILDPRN2 2.222 # type=spamg
550 # Original name: RM_bpp_ChildPorn2
551 # 9s/0h of 119325 corpus (98981s/20344h) 03/21/04
552 # 0s/0h of 15929 corpus (13729s/2200h) 03/23/04
553 #counts SARE_CHILDPRN2 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
554 #counts SARE_CHILDPRN2 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
557 #body SARE_CHILDPRN3 /underage porn/i
558 #describe SARE_CHILDPRN3 contains reference to child porn
559 #score SARE_CHILDPRN3 2.222 # type=spamg
560 # Original name: RM_bpp_ChildPorn3
561 # 28s/0h of 119325 corpus (98981s/20344h) 03/21/04
562 # 5s/0h of 15929 corpus (13729s/2200h) 03/23/04
563 #counts SARE_CHILDPRN3 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
564 #counts SARE_CHILDPRN3 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
567 body SARE_TOWRITE /decided to write/i
568 describe SARE_TOWRITE Contains phrasing used by spammers
569 score SARE_TOWRITE 1.05
570 # Original name: RM_bpp_DecidedToWrite
571 # 41s/2h of 119325 corpus (98981s/20344h) 03/21/04
572 # 2s/0h of 15929 corpus (13729s/2200h) 03/23/04
573 #counts SARE_TOWRITE 6s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
574 #counts SARE_TOWRITE 11s/3h of 140226 corpus (90162s/50064h DOC) 04/19/06
577 #body SARE_DRMWOMAN /your dream woman/i
578 #describe SARE_DRMWOMAN Contains phrasing used by spammers
579 #score SARE_DRMWOMAN 0.055
580 # Original name: RM_bpp_DreamWoman
581 # 1s/0h of 119325 corpus (98981s/20344h) 03/21/04
582 # 0s/0h of 15929 corpus (13729s/2200h) 03/23/04
583 #counts SARE_DRMWOMAN 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
584 #counts SARE_DRMWOMAN 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
587 body SARE_GETFCK /get fuck/i
588 describe SARE_GETFCK Contains phrasing used by spammers
589 score SARE_GETFCK 1.66 # type=spamp
590 # Original name: RM_bpp_GetFucked
591 # 22s/0h of 119325 corpus (98981s/20344h) 03/21/04
592 # 8s/0h of 15929 corpus (13729s/2200h) 03/23/04
593 #counts SARE_GETFCK 71s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
594 #counts SARE_GETFCK 32s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
597 #body SARE_GIRLSDOANY /girls will do anything/i
598 #describe SARE_GIRLSDOANY Contains phrasing used by spammers
599 #score SARE_GIRLSDOANY 0.166
600 # Original name: RM_bpp_GirlsDoAny
601 # 3s/0h of 119325 corpus (98981s/20344h) 03/21/04
602 # 3s/0h of 15929 corpus (13729s/2200h) 03/23/04
603 #counts SARE_GIRLSDOANY 1s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
604 #counts SARE_GIRLSDOANY 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
607 #body SARE_HORNY2 /horny as hell/i
608 #describe SARE_HORNY2 Contains phrasing used by spammers
609 #score SARE_HORNY2 0.222
610 # Original name: RM_bpp_HornyAsHell
611 # 4s/0h of 119325 corpus (98981s/20344h) 03/21/04
612 # 3s/0h of 15929 corpus (13729s/2200h) 03/23/04
613 #counts SARE_HORNY2 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
614 #counts SARE_HORNY2 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
617 #body SARE_MOMBLOW /mother blows/i
618 #describe SARE_MOMBLOW textual phrase implies porn spam
619 #score SARE_MOMBLOW 0.111
620 # Original name: RM_bpp_MotherBlows
621 # 2s/0h of 119325 corpus (98981s/20344h) 03/21/04
622 # 0s/0h of 15929 corpus (13729s/2200h) 03/23/04
623 #counts SARE_MOMBLOW 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
624 #counts SARE_MOMBLOW 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
627 body SARE_BADGIRLS /(?:amateur|horny|asian) girls/i
628 describe SARE_BADGIRLS Contains phrasing used by spammers
629 score SARE_BADGIRLS 0.52
630 # Original name: RM_bpp_PornGirls
631 # 12s/0h of 119325 corpus (98981s/20344h) 03/21/04
632 # 9s/0h of 15929 corpus (13729s/2200h) 03/23/04
633 #counts SARE_BADGIRLS 21s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
634 #counts SARE_BADGIRLS 5s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
637 body SARE_QLTYSINGLES /quality singles/i
638 describe SARE_QLTYSINGLES Contains phrasing seen in spam
639 score SARE_QLTYSINGLES 1.66
640 # Original name: RM_bpp_QualitySingles
641 # 3s/0h of 119325 corpus (98981s/20344h) 03/21/04
642 # 0s/0h of 15929 corpus (13729s/2200h) 03/23/04
643 #counts SARE_QLTYSINGLES 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
644 #counts SARE_QLTYSINGLES 1s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
647 #body SARE_HORNY1 /so hoo+rny/i
648 #describe SARE_HORNY1 Contains phrasing used by spammers
649 #score SARE_HORNY1 1.000 # type=spamp
650 # Original name: SoHorny
651 # 1s/0h of 119325 corpus (98981s/20344h) 03/21/04
652 # 0s/0h of 15929 corpus (13729s/2200h) 03/23/04
653 #counts SARE_HORNY1 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
654 #counts SARE_HORNY1 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
657 #body SARE_SONSDICK /son's dick/i
658 #describe SARE_SONSDICK textual phrase implies porn spam
659 #score SARE_SONSDICK 1.000 # type=spamp
660 # Original name: SonsDick
661 # 2s/0h of 119325 corpus (98981s/20344h) 03/21/04
662 # 0s/0h of 15929 corpus (13729s/2200h) 03/23/04
663 #counts SARE_SONSDICK 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
664 #counts SARE_SONSDICK 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
667 body SARE_STILLSINGLE /still single/i
668 describe SARE_STILLSINGLE Contains phrasing used by spammers
669 score SARE_STILLSINGLE 1.66
670 # Original name: RM_bpp_StillSingle
671 # 11s/0h of 119325 corpus (98981s/20344h) 03/21/04
672 # 5s/0h of 15929 corpus (13729s/2200h) 03/23/04
673 #counts SARE_STILLSINGLE 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
674 #counts SARE_STILLSINGLE 71s/1h of 140226 corpus (90162s/50064h DOC) 04/19/06
677 #body SARE_UNDRESSMTHR /undressed mother/i
678 #describe SARE_UNDRESSMTHR textual phrase implies porn spam
679 #score SARE_UNDRESSMTHR 0.200
680 # Original name: RM_bpp_UndressedMother
681 # 2s/0h of 119325 corpus (98981s/20344h) 03/21/04
682 # 0s/0h of 15929 corpus (13729s/2200h) 03/23/04
683 #counts SARE_UNDRESSMTHR 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
684 #counts SARE_UNDRESSMTHR 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
687 body SARE_HOUSEWIVES /housewives/i
688 describe SARE_HOUSEWIVES Mentions housewives, as in porn or in-home biz
689 score SARE_HOUSEWIVES 0.99
690 # Original name: RM_bwp_housewives
691 # 138s/0h of 119325 corpus (98981s/20344h) 03/21/04
692 # 18s/0h of 15929 corpus (13729s/2200h) 03/23/04
693 #counts SARE_HOUSEWIVES 13s/3h of 42056 corpus (34127s/7929h FVGT) 04/19/06
694 #counts SARE_HOUSEWIVES 37s/6h of 140226 corpus (90162s/50064h DOC) 04/19/06
697 body SARE_SCHLGRL /schoolgirls/i
698 describe SARE_SCHLGRL mentions schoolgirls, as in porn
699 score SARE_SCHLGRL 1.29
700 # Original name: RM_bwp_schoolgirls
701 # 11s/0h of 119325 corpus (98981s/20344h) 03/21/04
702 # 6s/0h of 15929 corpus (13729s/2200h) 03/23/04
703 #counts SARE_SCHLGRL 15s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
704 #counts SARE_SCHLGRL 19s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
707 ###############################
709 ###############################
711 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
712 describe SARE_ADLTOBFU Contains OBFU adult material
713 score SARE_ADLTOBFU 0.68
714 # Combined from FVGT_b_N0N0_WORDS, OACYS_DISGUISED_P0RN, M_K_N0N0_WORDS_BODY
715 # 768s/1h of 119325 corpus (98981s/20344h) 03/21/04
716 # 89s/0h of 15929 corpus (13729s/2200h) 03/23/04
717 #counts SARE_ADLTOBFU 930s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
718 #counts SARE_ADLTOBFU 663s/10h of 140226 corpus (90162s/50064h DOC) 04/19/06
721 body SARE_OBFUENLARGE /\b(?!enlarge)e.?n.?l.?a.?r.?g.?e/i
722 describe SARE_OBFUENLARGE masked spam word(s)
723 score SARE_OBFUENLARGE 1.66 # type=obfu
724 # Original name: RM_bwo_Enlarge
725 # 478s/0h of 119325 corpus (98981s/20344h) 03/21/04
726 # 18s/0h of 15929 corpus (13729s/2200h) 03/23/04
727 #counts SARE_OBFUENLARGE 15s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
728 #counts SARE_OBFUENLARGE 466s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
731 #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
732 #describe SARE_OBFUFCK1 Apparent spam seems to contain porn subject
733 #score SARE_OBFUFCK1 1.666 # type=obfu
734 # Original name: RM_bwo_Fucko1
735 # 42s/0h of 119325 corpus (98981s/20344h) 03/21/04
736 # 23s/0h of 15929 corpus (13729s/2200h) 03/23/04
737 #counts SARE_OBFUFCK1 19s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
738 #counts SARE_OBFUFCK1 35s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
741 body SARE_OBFUFCK2 /(?!\bfun?ck)\bf.?u.?c.?k/i
742 describe SARE_OBFUFCK2 Apparent spam seems to contain porn subject
743 score SARE_OBFUFCK2 1.00 # type=obfu
744 # Original name: RM_bwo_Fucko2
745 # 70s/1h of 119325 corpus (98981s/20344h) 03/21/04
746 # 29s/0h of 15929 corpus (13729s/2200h) 03/23/04
747 #counts SARE_OBFUFCK2 56s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
748 #counts SARE_OBFUFCK2 73s/3h of 140226 corpus (90162s/50064h DOC) 04/19/06
751 #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
752 #describe SARE_OBFUGNGBNG masked spam word(s)
753 #score SARE_OBFUGNGBNG 2.5 # type=obfu
754 # Original name: RM_bwo_Gangbang
755 # 2s/0h of 15929 corpus (13729s/2200h) 03/23/04
756 # 3s/0h of 119325 corpus (98981s/20344h) 03/21/04
757 #counts SARE_OBFUGNGBNG 11s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
758 #counts SARE_OBFUGNGBNG 1s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
761 #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
762 #describe SARE_OBFUGIRLS masked spam word(s)
763 #score SARE_OBFUGIRLS 3.222 # type=obfu # ham: jpg
764 # Original name: RM_bwo_Girls
765 # 25s/1h of 15929 corpus (13729s/2200h) 03/23/04
766 # 318s/1h of 119325 corpus (98981s/20344h) 03/21/04
767 #counts SARE_OBFUGIRLS 112s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
768 #counts SARE_OBFUGIRLS 13s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
771 #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
772 #describe SARE_OBFUPENIS masked spam word(s)
773 #score SARE_OBFUPENIS 2.333 # type=obfu
774 # Original name: RM_bwo_Penis
775 # 1027s/0h of 119325 corpus (98981s/20344h) 03/21/04
776 # 91s/1h of 15929 corpus (13729s/2200h) 03/23/04
777 #counts SARE_OBFUPENIS 516s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
778 #counts SARE_OBFUPENIS 578s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
781 #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
782 #describe SARE_OBFUPORNO masked spam word(s)
783 # score SARE_OBFUPORNO 2.500 # type=obfu
784 # Original name: RM_bwo_Porno
785 # 266s/0h of 119325 corpus (98981s/20344h) 03/21/04
786 # 36s/0h of 15929 corpus (13729s/2200h) 03/23/04
787 #counts SARE_OBFUPORNO 43s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
788 #counts SARE_OBFUPORNO 22s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
791 #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
792 #describe SARE_OBFUPUSS masked spam word(s)
793 #score SARE_OBFUPUSS 2.500 # type=obfu
794 # Original name: RM_bwo_Pussies
795 # 28s/0h of 119325 corpus (98981s/20344h) 03/21/04
796 # 27s/0h of 15929 corpus (13729s/2200h) 03/23/04
797 #counts SARE_OBFUPUSS 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
798 #counts SARE_OBFUPUSS 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
801 body SARE_OBFUSEXUAL /\b(?!Sexual)S.?e.?x.?u.?a.?l/i
802 describe SARE_OBFUSEXUAL masked spam word(s)
803 score SARE_OBFUSEXUAL 1.66 # type=obfu
805 # 409s/0h of 119325 corpus (98981s/20344h) 03/21/04
806 # 27s/0h of 15929 corpus (13729s/2200h) 03/23/04
807 #counts SARE_OBFUSEXUAL 676s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
808 #counts SARE_OBFUSEXUAL 373s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
811 #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
812 #describe SARE_OBFUTEENS masked spam word(s)
813 #score SARE_OBFUTEENS 2.500 # type=obfu
814 # Original name: RM_bwo_Teens
815 # 28s/0h of 119325 corpus (98981s/20344h) 03/21/04
816 # 4s/0h of 15929 corpus (13729s/2200h) 03/23/04
817 #counts SARE_OBFUTEENS 1s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
818 #counts SARE_OBFUTEENS 1s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
821 body SARE_OBFUTESTO /\b(?!testosterone)t.?e.?s.?t.?o.?s.?t.?e.?r.?o.?n.?e/i
822 describe SARE_OBFUTESTO masked spam word(s)
823 score SARE_OBFUTESTO 1.66 # type=obfu
824 # Original name: RM_bwo_Testosterone
825 # 10s/0h of 119325 corpus (98981s/20344h) 03/21/04
826 # 0s/0h of 15929 corpus (13729s/2200h) 03/23/04
827 #counts SARE_OBFUTESTO 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
828 #counts SARE_OBFUTESTO 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
831 #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
832 #describe SARE_OBFUVRGN masked spam word(s)
833 #score SARE_OBFUVRGN 2.500 # type=obfu
834 # Original name: RM_bwo_Virgins
835 # 25s/0h of 119325 corpus (98981s/20344h) 03/21/04
836 # 16s/0h of 15929 corpus (13729s/2200h) 03/23/04
837 #counts SARE_OBFUVRGN 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
838 #counts SARE_OBFUVRGN 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
841 #body SARE_SPRDLGS /spread(?:ing)? their leg/i
842 #describe SARE_SPRDLGS Contains possible adult phrase
843 #score SARE_SPRDLGS 0.222
844 # 4s/0h of 125078 corpus (104890s/20188h) 03/29/04
845 # 0s/0h of 15929 corpus (13729s/2200h) 03/29/04
846 #counts SARE_SPRDLGS 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
847 #counts SARE_SPRDLGS 2s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
850 body SARE_RPTLETTERS /(?!\b(?:ass|cock|pussy)\b)\b(?:a+s+s+|c+o+c+k+|p+u+s+s+y+)\b/i
851 describe SARE_RPTLETTERS Contains mis-spelled adult phrase(s)
852 score SARE_RPTLETTERS 1.66
853 # 5s/0h of 125078 corpus (104890s/20188h) 03/29/04
854 # 2s/0h of 15929 corpus (13729s/2200h) 03/29/04
855 #counts SARE_RPTLETTERS 15s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
856 #counts SARE_RPTLETTERS 1s/1h of 140226 corpus (90162s/50064h DOC) 04/19/06
859 body SARE_SEXDRIVE /\bSex(?:ual)? Drive/i
860 describe SARE_SEXDRIVE Talks about sex drive
861 score SARE_SEXDRIVE 1.66
862 # Original name: RM_bpm_SexDrive
863 # 589s/0h of 125078 corpus (104890s/20188h) 03/29/04
864 # 141s/0h of 15929 corpus (13729s/2200h) 03/29/04
865 #counts SARE_SEXDRIVE 239s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
866 #counts SARE_SEXDRIVE 531s/5h of 140226 corpus (90162s/50064h DOC) 04/19/06
869 body SARE_BETTERSEX /better sex/i
870 describe SARE_BETTERSEX Spammer phrasing in body of email
871 score SARE_BETTERSEX 1.66
872 # Original name: RM_bpm_BetterSex
873 # 157s/0h of 125078 corpus (104890s/20188h) 03/29/04
874 # 8s/0h of 15929 corpus (13729s/2200h) 03/29/04
875 #counts SARE_BETTERSEX 292s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
876 #counts SARE_BETTERSEX 262s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
879 body SARE_SEXENHANCER /sex(?:ual)? enhancer/i
880 describe SARE_SEXENHANCER mentions spam topic
881 score SARE_SEXENHANCER 1.66 # type=spamp
882 # Original name: RM_bpm_SexEnhancer
883 # 11s/0h of 125078 corpus (104890s/20188h) 03/29/04
884 # 11s/0h of 15929 corpus (13729s/2200h) 03/29/04
885 #counts SARE_SEXENHANCER 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
886 #counts SARE_SEXENHANCER 7s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
889 #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
890 #describe SARE_OBFUHARDCORE masked spam word(s)
891 #score SARE_OBFUHARDCORE 1.433 # type=obfu
892 # Original name: RM_bwo_hardcore
893 # 32s/0h of 98440 corpus (76828s/21612h) 05/09/04
894 #counts SARE_OBFUHARDCORE 4s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
895 #counts SARE_OBFUHARDCORE 3s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06
899 ###############################
901 ###############################
903 #uri SARE_PNSPTCH /\bbolik34\b/i
904 #describe SARE_PNSPTCH Terra.es penil patch spammer
905 #score SARE_PNSPTCH 1.5 # was .33
906 # Original name: MAKEPENIBIG
907 # 277s/0h of 119325 corpus (98981s/20344h) 03/21/04
908 # 0s/0h of 15929 corpus (13729s/2200h) 03/23/04
909 #counts SARE_PNSPTCH 0s/0h of 42056 corpus (34127s/7929h FVGT) 04/19/06
910 #counts SARE_PNSPTCH 0s/0h of 140226 corpus (90162s/50064h DOC) 04/19/06