; this file contains advanced bayesit settings which may be not interested for all number of users. It must be placed either in the bayesit's working folder, either in the same folder as bayesit.tbp (in this case the new file with copy of settings will be created in the working folder). Values can be either solid (without spaces), either enclosed in quotes. In the case of solid values ';' required at the end of erevy line.
; You can also place the file "bayesit.ini" with basic settings which are available during GUI setup - the settings from the file will be used as default during filter's installation (first run).
; the names of values for bayesit.ini is there:
;working directory (string)
;filter log (string)
;list of ignoring kludges (string)
;show splash screen (1 or 0)
;log current process (1 or 0)
;log global state" (1 or 0)
;log grades (1 or 0)
;filter is logged (1 or 0)
;use white list of kludges (1 or 0)
;use partically translitting (1 or 0)
;sighificant tokens (integer - by default 15)
;spam transliteration table (string)
;local user alphabet (string)
; "THREAD_PRIORITY_LOWEST" - for usual recalculating thread.
working thread priority = 2;
; TREHAD_PRIORITY_NORMAL - for recalculating thread when exiting from The Bat! started.
onexit thread priority = 3;
; if 1, export "selective.txt", if 0 - don't export.
export selective download = 1;
; indicates how many times a header token must be met in spam headers to be included
; into "selective.txt" file. Lower value increases filesize and increases possibility
; of false positivies.
selective download spam threshold = 10;
; trait numeric HTML comments as marks of spam
simple digits spam marks = 1;
; trait any solid HTML comments as marks of spam
no spaces spam marks = 1;
; if token is longer than this value, store it in the base in form of hash
limit size to hash = 19;
; if header token is longer than this value, store it in the base in form of hash.
limit size to hash header = 96;
; It is "last chance" - if no TEMP environment variable defined and if no other temp paths exists, this path will be used.
temporary dictionary = "c:\\temp";
; not used in current version (must be 0)
use expiration = 0;
; not used in current version (no meaning, what you set here - only check that it is integer number)
age to expirate = 100;
; if 1, the filter can create it's base "from zero" - i.e. even if no "mark as" action were made for any dictionary, using only incoming mail, by marking only spam "as spam" and leaving non-spam. If 0, the filter can be trained ONLY if at least one letter was marked as spam and non-spam.
learn from zero = 1;
; if log file exceed this size, it will be renamed into same name with "~" added at the beginning of the name, and the logging will be continued into new file.
max size of log file = 131072;
; If it is integer number from 1 and more, recalculation is completed after filter collect more than this number of letters. If it is float value below 1 (as 0.001), recalculation is completed after filter collects the quantity of letters which is more than total number of letter which are already in base multiplied to this number (for example, if you have 1000 spams and 2000 hams and this parameter is set to 0.01, recalculation will be when you collect (1000+2000)*0.01 = 30 letters. But anyway in this case recalculation will be done if number of collected letters is more than 100.
recalculating strategy = 0.005;
; this number shows, how much "heavier" non-spam tokens than spam. It makes some kind of "guard" and keeps from false positives. Usual value is 2, but you can also try others...
regarding threshold = 2;
; if yes, the filter will automark all letters according assigned threshold for "move to junk folder" and result of working. If no, you must "mark as" ALL incoming letters in order to keep the filter's base healthy.
use autotrain = 1;
; if 1, and the filter can't found token during regarding, it will try some variations of the same token (from capital letter, all caps, same variations from header/body, same variations with added "!"). It helps to improve the quality of filtering. If 0, the filter will use default value for absent tokens. It helps to make the filter faster.
use degeneration = 1;
; The number of "!" which will be added subsequently to the token in order to check all it's variations (during degeneration). If previous parameter is 0, this one is ignored.
number of exclamations = 5;
; If this value is 0, the filter works usual way and calculate the final grade of a letter using a bayesian formula. If it is set to 1, the filter just calculates arithmetic average as the final result (which is linear and smooth).
