root/tags/FuzzyOcr-2.3j/FuzzyOcr.cf

loadplugin FuzzyOcr FuzzyOcr.pm
body FUZZY_OCR eval:fuzzyocr_check()
describe FUZZY_OCR Mail contains an image with common spam text inside
body FUZZY_OCR_WRONG_CTYPE eval:dummy_check()
describe FUZZY_OCR_WRONG_CTYPE Mail contains an image with wrong content-type set
body FUZZY_OCR_CORRUPT_IMG eval:dummy_check()
describe FUZZY_OCR_CORRUPT_IMG Mail contains a corrupted image
body FUZZY_OCR_KNOWN_HASH eval:dummy_check()
describe FUZZY_OCR_KNOWN_HASH Mail contains an image with known hash

priority FUZZY_OCR             900

########### Plugin Configuration #############

#### Logging options #####
# Verbosity level (see manual) Attention: Don't set to 0, but to 0.0 for quiet operation. (Default value: 1)
#focr_verbose 2
#
# Logfile (make sure it is writable by the plugin) (Default value: /etc/mail/spamassassin/FuzzyOcr.log)
#focr_logfile /etc/mail/spamassassin/FuzzyOcr.log
##########################

##### Wordlists #####
# Here we defined the words to scan for (Default value: /etc/mail/spamassassin/FuzzyOcr.words)
#focr_global_wordlist /etc/mail/spamassassin/FuzzyOcr.words
#
# This is the path RELATIVE to the respektive home directory for the personalized list
# This list is merged with the global word list on execution (Default value: .spamassassin/fuzzyocr.words)
# If focr_personal_wordlist begins with '/', treats option as fixed path and does not search HOME
#focr_personal_wordlist .spamassassin/fuzzyocr.words
#####################

# These parameters can be used to change other detection settings
# If you leave these commented out, the defaults will be used.
# Do not use " " around any parameters!
#
##### Location of helper applications (path + binary) (Default values: /usr/bin/<app>) #####
#focr_bin_giffix /usr/bin/giffix
#focr_bin_giftext /usr/bin/giftext
#focr_bin_gifinter /usr/bin/gifinter
#focr_bin_giftopnm /usr/bin/giftopnm
#focr_bin_jpegtopnm /usr/bin/jpegtopnm
#focr_bin_pngtopnm /usr/bin/pngtopnm
#focr_bin_bmptopnm /usr/bin/bmptopnm
#focr_bin_ppmhist /usr/bin/ppmhist
#focr_bin_gocr /usr/bin/gocr
#
#focr_path_bin /usr/local/netpbm/bin:/usr/local/bin:/usr/bin
#
############################################################################################

##### Scansets, comma seperated (Default value: $gocr -i -, $gocr -l 180 -d 2 -i -) #####
# Each scanset consists of one or more commands which make text out of pnm input.
# Each scanset is run seperately on the PNM data, results are combined in scoring.
focr_scansets $gocr -i $pfile, $gocr -l 180 -d 2 -i $pfile, $gocr -l 140 -d 2 -i $pfile
#
# To use only one scan with default values, uncomment the next line instead
#focr_scansets $gocr -i $pfile
#
# Some example for more advanced sets
# Thisone uses the first the standard scan, then a scanset which first reduces the image to 3 colors and then scans it with custom settings
# and then it scans again only with these custom settings
# NOTE: This is for advanced users only, if you have questions how to use this, ask on the ML or on IRC
#focr_scansets $gocr -i $pfile, pnmnorm $pfile 2>$efile | pnmquant 3 2>>$efile | pnmnorm 2>>$efile | $gocr -l 180 -d 2 -i -, $gocr -l 180 -d 2 -i $pfile
#########################################################################################

##### Various Score/Scan settings #####
# Timeout for the plugin, in seconds. (Maximum runtime of the plugin) (Default value: 10)
#focr_timeout 15
#
# Default detection treshold (see manual) (Default value: 0.3) (Can be changed on a per word basis in the wordlist).
#focr_threshold 0.3
#
# This is the score for a hit after focr_counts_required matches
#focr_base_score 5
#
# This is the additional score for every additional match after focr_counts_required matches (Default value: 1)
#focr_add_score 0.375
#
# This is the score to give for a wrong content-type (e.g. JPEG image but content type says GIF) (Default value: 1.5)
#focr_wrongctype_score 1.5
#
# This is the score to give for a corrupted image (This currently affects only GIF images) (Default value: 2.5)
#focr_corrupt_score 2.5
#
# This is the score to give for a corrupted unfixable image (This currently affects only GIF images) (Default value: 5)
#focr_corrupt_unfixable_score 5
#
# This is used to disable the OCR engine if the message has already more points than this value (Default value: 10)
#focr_autodisable_score 20
#
# Number of minimum matches before the rule scores (Default value: 2)
#focr_counts_required 3
#
# Specifies, how many frames an animated gif must contain, so the second (less resource consuming) animated gif test is used. (Default value: 5)
#focr_gif_max_frames 5
#
# For animated-gif images:
# Specifies the threshold for the delay of a frame in an animated-gif image (Default value: 100)
# + If the delay is greater than threshold, the frame is considered otherwise, the frame is skipped.
#focr_anim_delay 100
#
# Specifies the number of frames to consider (Default value: 2)
# + Keeps at least the largest N frames.
#focr_anim_max_frames 2
#
#######################################

##### Image Hash Database settings (Experimental, disabled by default) #####
#
# Set this to 1 to enable the Image Hash database feature (Default value: 0.0)
# Value = 1 ... use digest_hash only
# Value = 2 ... use digest_db w/digest_hash import
#focr_enable_image_hashing 2
#
# The score is saved with the hash in the database, so no extra scoring for a db hit is required.
#
# If the image hash database feature is enabled, specify the file here to use as database
# (Default value: /etc/mail/spamassassin/FuzzyOcr.hashdb)
#focr_digest_db /etc/mail/spamassassin/FuzzyOcr.hashdb
#
# If the image hash db feature is enabled, specify the file here to use as database
# (Default value: /etc/mail/spamassassin/FuzzyOcr.db)
#focr_db_hash /etc/mail/spamassassin/FuzzyOcr.db
#
# If the image hash db feature is enabled, specify the file here to use as database
# (Default value: /etc/mail/spamassassin/FuzzyOcr.safe.db)
#focr_db_safe /etc/mail/spamassassin/FuzzyOcr.safe.db
#
# Expire records from focr_digest_db after (Default: 35) days
#focr_db_max_days 15
#
# Automatically add hashes of spam images recognized by OCR to the Image Hash database, to disable, set to 0.0 (Default value: 1)
#focr_hashing_learn_scanned 1
#
# Keep files that generate errors
#  0 = always cleanup
#  1 = keep only if error
#  2 = always keep
#focr_keep_bad_images 1
#
# Score images who's global word count is below focr_counts_required using focr_add_score * word count as score.
#focr_score_ham 1
######################################################################