/etc/bogofilter.cf is in bogofilter-common 1.2.4+dfsg1-4build1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 | ########### Sample BOGOFILTER Configuration File ###########################
# $Id: bogofilter.cf.example 6811 2009-02-21 20:32:50Z relson $
# Default settings (as defined in the bogofilter source code)
# have a single hash mark at the beginning of the line.
# Alternate values have two hash marks.
# Comment lines MUST have their hash mark in the leftmost column.
# Comments can be added at the end of any line (after whitespace and a '#').
# Blank lines are allowed.
########### General Settings ########################################
#### BOGOFILTER_DIR
#
# directory for wordlists
#
#bogofilter_dir=~/.bogofilter
##bogofilter_dir=/var/spool/bogofilter
#### name/location of user config file
#
#user_config_file=~/.bogofilter.cf
##user_config_file=~/.bogofilterrc
##user_config_file=~/.bogofilter/config
#### TRANSACTIONS: enable/disable database transactions
#
# boolean indicating whether transactions
# should be enabled (yes) or disabled (no)
#
#db_transaction=no # default
##db_transaction=yes # (alternate)
#### WORDLIST: define additional word lists
#
# char type: 'r' (regular) or 'i' (ignore)
# char *name: name of list, e.g. "system", "user", "ignore"
# char *path: absolute path to file or
# file name (relative to bogofilter_dir)
# int order - once found, skip higher numbered lists
#
##wordlist i,ignore,~/ignorelist.db,1
##wordlist r,wordlist,~/wordlist.db,2
#### SPAM_HEADER_NAME
#
# used in reporting spamicity and
# in removing already existing headers
#
#spam_header_name=X-Bogosity
#### SPAM_HEADER_PLACE
#
# used in placing the SPAM_HEADER_NAME line
#
#spam_header_place=DomainKey-Signature
#### SPAM_SUBJECT_TAG
#
# tag added to "Subject: " line for identifying spam or unsure
# default is to add nothing.
#
##spam_subject_tag=***SPAM***
##unsure_subject_tag=???UNSURE???
#### STATS_IN_HEADER
#
# non-zero (default): put spamicity info in message header
# zero: put spamicity info in message body
# can use "bool" values of True, False, Yes, No, 1, or 0
#
#stats_in_header=Yes # default
##stats_in_header=No # (alternate)
#### DB_CACHESIZE
#
# non-zero: set this as DB cache size (in Mbytes)
# zero: use DB default cache size (.25 Mbyte in 4.0.14)
#
# note that Berkeley DB increases any buffer size below 500 MB
# by 25%!
# This helps most when doing massive changes to the data base that
# involve a lot of overwrites, such as registering mail boxes,
# whereas it is mostly a waste of memory for read-only
# applications such as scoring.
# WARNING: If you set this too large, bogofilter will fail.
#
#db_cachesize=0 # default
##db_cachesize=16 # (alternate)
#### DB_LOG_AUTOREMOVE
#
# boolean indicating whether auto-removing of
# logs should be enabled (yes) or disabled (no)
#
#db_log_autoremove=yes # default
##db_log_autoremove=no # (alternate)
#### TIMESTAMP
#
# enables or disables token timestamps
#
#timestamp=Yes
#### Format of spamicity output
#
# for two-state output the third entry is not needed and not used
#
#spamicity_tags = Spam, Ham, Unsure
#spamicity_formats = %0.6f, %0.6f, %0.6f
#
##spamicity_tags = Yes, No, Unsure
##spamicity_formats = %0.6f, %0.6f, %0.6f
#### Format of SPAM_HEADER
#
# formatting characters:
#
# h - spam_header_name, e.g. "X-Bogosity"
#
# c - classification, e.g. Yes/No, Spam/Ham/Unsure, +/-/?
#
# D - date, fixed ISO-8601 format for Universal Time ("GMT")
#
# e - spamicity as 'e' format
# f - spamicity as 'f' format
# g - spamicity as 'g' format
#
# A - IP address (from first Received: statement having one)
# Not guaranteed to be the originating address of the message.
# I - Message ID
# Q - Queue ID (from first id tag found in Received: headers)
#
# l - logging tag (from '-l' option)
#
# o - spam_cutoff, ex. cutoff=%o
#
# p - spamicity value
# d - if ham or unsure, the spamicity
# if spam, difference of spamicity from 1.0
#
# r - runtype
# w - word count
# m - message count
#
# u - username - this will either be the login from getlogin(),
# if that is empty, the pw_name obtained from
# the password database, or the user id
# prefixed by #, for instance, #1003
#
# v - version
#
# customizable messages:
#
# header_format - the "X-Bogosity" line that '-p' adds to
# the message header and '-v' outputs.
# terse_format - an abbreviated form of header_format;
# selected by command line option '-t'
# log_header_format - written to syslog by '-u' option
# when classifying messages.
# log_update_format - written to syslog by '-u' option
# when registering messages.
#
#
#header_format = %h: %c, tests=bogofilter, spamicity=%p, version=%v
#terse_format = %1.1c %f
#log_header_format = %h: %c, spamicity=%p, version=%v
#log_update_format = register-%r, %w words, %m messages
##log_header_format = %h: %c, spamicity=%f, ipaddr=%A, queueID=%Q, msgID=%I, version=%v
#### TERSE
#
# if enabled, format the X-Bogosity using the 'terse_format' specificaton.
#
#terse=no # default
##terse=yes # (alternate)
########### Tokenizer Settings ######################################
#### BLOCK ON SUBNETS
#
# convert IPADDRs into a special token, url:1.2.3.4,
# and also return url:1.2.3, url:1.2, and url:1
# to allow identifying spammers by ip address / subnets.
#
#block_on_subnets=no
#### CHARSET handling
#
# specify default charset
#
#charset_default=iso-8859-1 # default
#charset_default=us-ascii # (alternate)
##charset_default=cp866 # for Russian
#### REPLACE_NONASCII_CHARACTERS
#
# replace non-7bit chars with '?'
#
#replace_nonascii_characters=N # default
##replace_nonascii_characters=Y # (alternate)
#### UNICODE handling
#
# boolean indicating whether raw storage (no) or unicode (yes)
# is the default encoding for the wordlist
#
#unicode=yes # default
##unicode=no # (alternate)
#### lexer parameters
#
# minimum and maximum lengths for single tokens
#
#min-token-len=3 # default
#max-token-len=30 # default
#
# count and length for multi-word tokens
# Note: if length not specified, defaults to
# multi-token-count * max-token-len (approx)
#
#multi-token-count=1 # default
#max-multi-token-len=0 # default
########### Classification Constants Settings #######################
#
# See man page for a more detailled description of the parameters.
#### MINIMUM DEVIATION
#
# if token spamicity closer to EVEN_ODDS (0.5)
# than MIN_DEV, don't use the word in the
# spamicity calculation
#
#min_dev=0.375 # default
#### Robinson Constants
#
# floating point values for
# Robinson S and X coefficients.
#
#robs=0.0178 # default
#robx=0.52 # default
#### CUTOFF Values
#
# both ham_cutoff and spam_cutoff are allowed.
# setting ham_cutoff to a non-zero value will
# enable tri-state results (Spam/Ham/Unsure).
#
#ham_cutoff = 0.45 # default
#spam_cutoff= 0.99 # default
#
# for two-state classification:
#
##ham_cutoff = 0.00 # default
##spam_cutoff = 0.99 # default
#### Effective Size Factor Values
#
#ns_esf = 1.000 # default
#sp_esf = 1.000 # default
#### Auto-update threshold
#
# Skip autoupdating if the spamicity is within this value
# of 0.000000 (surely ham) or 1.000000 (surely spam).
#
## thresh_update=0.01 # (optional)
#### token count parameters
#
# coerce the number of tokens used to score a message
# Note: zero means no coercing
#
##token_count=0 # default
##token_count_min=0 # default
##token_count_max=0 # default
|