########### Sample BOGOFILTER Configuration File ###########################

# 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