diff options
| -rw-r--r-- | mail/Makefile | 1 | ||||
| -rw-r--r-- | mail/spamprobe/Makefile | 23 | ||||
| -rw-r--r-- | mail/spamprobe/distinfo | 1 | ||||
| -rw-r--r-- | mail/spamprobe/files/Makefile | 11 | ||||
| -rw-r--r-- | mail/spamprobe/files/spamprobe.1 | 265 | ||||
| -rw-r--r-- | mail/spamprobe/pkg-comment | 1 | ||||
| -rw-r--r-- | mail/spamprobe/pkg-descr | 7 | ||||
| -rw-r--r-- | mail/spamprobe/pkg-plist | 2 |
8 files changed, 311 insertions, 0 deletions
diff --git a/mail/Makefile b/mail/Makefile index 7af1a81fcb43..5a93bf9097f4 100644 --- a/mail/Makefile +++ b/mail/Makefile @@ -236,6 +236,7 @@ SUBDIR += sonicmail SUBDIR += spamass-milter SUBDIR += spambnc + SUBDIR += spamprobe SUBDIR += spruce SUBDIR += squirrelmail SUBDIR += sqwebmail diff --git a/mail/spamprobe/Makefile b/mail/spamprobe/Makefile new file mode 100644 index 000000000000..1e2d4f632fdc --- /dev/null +++ b/mail/spamprobe/Makefile @@ -0,0 +1,23 @@ +# New ports collection makefile for: spamprobe +# Whom: Matthew N. Dodd <mdodd@FreeBSD.org> +# Date created: 05 September 2002 +# +# $FreeBSD$ +# + +PORTNAME= spamprobe +PORTVERSION= 0.6 +CATEGORIES= mail +MASTER_SITES= ${MASTER_SITE_SOURCEFORGE} +MASTER_SITE_SUBDIR=${PORTNAME} + +MAINTAINER= mdodd@freebsd.org + +MAKEFILE= ${FILESDIR}/Makefile + +.include <bsd.port.pre.mk> + +post-extract: + @${CP} ${FILESDIR}/spamprobe.1 ${WRKSRC}/ + +.include <bsd.port.post.mk> diff --git a/mail/spamprobe/distinfo b/mail/spamprobe/distinfo new file mode 100644 index 000000000000..f8e6d3ffc6d4 --- /dev/null +++ b/mail/spamprobe/distinfo @@ -0,0 +1 @@ +MD5 (spamprobe-0.6.tar.gz) = d277ec6ab4fc2501db99a2e1cc6cc2e8 diff --git a/mail/spamprobe/files/Makefile b/mail/spamprobe/files/Makefile new file mode 100644 index 000000000000..08eff50c9d64 --- /dev/null +++ b/mail/spamprobe/files/Makefile @@ -0,0 +1,11 @@ +# $FreeBSD$ +# +PREFIX?= /usr/local +BINDIR= ${PREFIX}/bin +MANDIR= ${PREFIX}/man/man +PROG_CXX= spamprobe +SRCS= File.cc FrequencyDB.cc LockFile.cc Message.cc \ + MessageFactory.cc MimeHeader.cc MimeLineReader.cc \ + MimeMessageReader.cc SpamFilter.cc spamprobe.cc util.cc + +.include <bsd.prog.mk> diff --git a/mail/spamprobe/files/spamprobe.1 b/mail/spamprobe/files/spamprobe.1 new file mode 100644 index 000000000000..775a210cdaf5 --- /dev/null +++ b/mail/spamprobe/files/spamprobe.1 @@ -0,0 +1,265 @@ +.\" +.\" $Id$ +.\" +.\" Note: The date here should be updated whenever a non-trivial +.\" change is made to the manual page. +.Dd September 5, 2002 +.Dt SPAMPROBE 1 +.Os +.Sh NAME +.Nm spamprobe +.Nd "Spam detector using Bayesian analysis of word counts." +.Sh SYNOPSIS +.Nm +.Op Fl a Ar char +.Op Fl c +.Op Fl d Ar directory +.Op Fl h +.Op Fl H Ar option +.Op Fl m +.Op Fl n Ar number +.Op Fl r Ar number +.Op Fl v +.Op Fl 7 +.Op Fl 8 +.Ar command Op ... +.Nm +.Ar receive Op filename ... +.Nm +.Ar score Op filename ... +.Nm +.Ar find-spam Op filename ... +.Nm +.Ar find-good Op filename ... +.Nm +.Ar good Op filename ... +.Nm +.Ar spam Op filename ... +.Nm +.Ar remove Op filename ... +.Sh DESCRIPTION +Welcome to +.Nm SpamProbe ! +Are you tired of the constant bombardment of your inbox by unwanted +email pushing everything from porn to get rich quick schemes? Have you +tried other spam filters but become disenchanted with them when you +realized that their manually generated rule sets weren't updated fast +enough to keep up with spammers wording changes? Or that they generated +unwanted false positive scores? +.Pp +.Nm SpamProbe +operates on a different basis entirely. Instead of using pattern matching +and a set of human generated rules +.Nm SpamProbe +relies on a Bayesian analysis +of the frequency of words used in spam and non-spam emails received by an +individual person. The process is completely automatic and tailors itself +to the kinds of emails that each person receives. +.Ss FEATURES +.Bl -bullet -offset indent -compact +.It +Spam detection using Bayesian analysis of terms contained in each email. +Words used often in spams but not in good email tend to indicate that a +message is spam. +.It +Written in C++ for good performance. Database access using GDBM for quick +startup and fast term count retrieval. +.It +Recognition and decoding of MIME attachments in quoted-printable and +base64 encoding. Automatically skips non-text attachments. +.It +Counts two word phrases as well as single words for higher precision. +.It +Ignores HTML tags in emails for scoring purposes unless the -h command +line option is used. Many spams use HTML and few humans do so HTML tends +to become a powerful recognizer of spams. However in the author's opinion +this also substantially increases the likelihood of false positives if +someone does send a non-spam email containing HTML tags. +.Nm SpamProbe +does pull urls from inside of html tags however since those tend to be +spammer specific. +.It +Locks mboxes and databases using fcntl file locking to avoid problems when +multiple emails arrive simultaneously. +.It +Scores only the Received, Subject, To, From, and Cc headers. All other +headers are ignored to make it hard for spammers to hide non-spammy words +in X- headers to fool the filter. +.El +.Ss OPTIONS +.Bl -tag -width ".Fl d Ar directory" +.It Fl a Ar char +By default +.Nm +converts non-ascii characters (characters with the most significant bit +set to 1) into the letter 'z'. This is useful for lumping all Asian +characters into a single word for easy recognition. The +.Fl a +option allows you to change the character to something else if you don't +like the letter 'z' for some reason. +.It Fl c +Create the database directory if it does not already exist. Normally +.Nm +exits with a usage error if the database directory does not already exist. +.It Fl d Ar directory +By default +.Nm +stores its database in a directory named .spamprobe under your home +directory. The +.Fl d +option allows you to specify a different directory to use. This is +necessary if your home directory is NFS mounted for example. +.It Fl h +By default +.Nm +removes HTML markup from the text in emails to help avoid false positives. +The +.Fl h +option allows you to override this behavior and force +.Nm +to include words from within HTML tags in its word counts. Note that +.Nm +always counts any URLs in hrefs within tags whether +.Fl h +is used or not. Use of this option is discouraged. It can increase the +rate of spam detection slightly but unless the user receives a significant +amount of HTML emails it also tends to increase the number of false +positives. +.It Fl H Ar option +By default +.Nm +only scans a meaningful subset of headers from the email message when +searching for words to score. The +.Fl H +option allows the user to specify additional headers to scan. Legal values +are "all", "nox", or "normal". "all" scans all headers, "nox" scans all +headers except those starting with X-, and "normal" scans the normal set +of headers. +.It Fl m +Use mbox format for reading emails in receive mode. Normally +.Nm +assumes that the input to receive mode contains a single message so it +doesn't look for message breaks. +.It Fl n Ar number +Changes the number of most significant words/phrases used by +.Nm +to calculate the score for each message. Generally this is changed only +for optimization purposes. +.It Fl r Ar number +Changes the number of times that a single word/phrase can occurr in the +top words array used to calculate the score for each message. Allowing +repeats reduces the number of words overall (since a single word occupies +more than one slot) but allows words which occur frequently in the message +to have a higher weight. Generally this is changed only for optimization +purposes. +.It Fl v +Write debugging information to stderr. This can be useful for debugging +or for seeing which terms +.Nm +used to score each email. +.It Fl 7 +Ignore any characters with the most significant bit set to 1 instead of +mapping them to the letter 'z'. +.It Fl 8 +Store all characters even if their most significant bit is set to 1. +.El +.Pp +.Ss COMMANDS +.Bl -tag -width ".Ar find-spam Op filename ..." +.It Ar receive Op filename ... +Tells +.Nm +to read its standard input (or a file specified after the receive command) +and score it using the current databases. Once the message has been +scored the message is classified as either spam or non-spam and its word +counts are written to the appropriate database. The message's score is +written to stdout along with a single word. For example: +.Pp + SPAM 0.99 + or + GOOD 0.02 +.It Ar score Op filename ... +Similar to receive except that the databases are not modified in any way +and only the score is printed to stdout. +.It Ar find-spam Op filename ... +Similar to score except that it prints a short summary and score for each +message that is determined to be spam. This can be useful when testing. +.It Ar find-good Op filename ... +Similar to score except that it prints a short summary and score for each +message that is determined to be good. This can be useful when testing. +.It Ar good Op filename ... +Scans each file (or stdin if no file is specified) and reclassifies every +email in the file as non-spam. The databases are updated appropriately. +Previously processed messages (recognized using their message ids) are +ignored. +.It Ar spam Op filename ... +Scans each file (or stdin if no file is specified) and reclassifies every +email in the file as spam. The databases are updated appropriately. +Previously processed messages (recognized using their message ids) are +ignored. +.It Ar remove Op filename ... +Scans each file (or stdin if no file is specified) and removes its term +counts from the database. Messages which are not in the database +(recognized using their message ids) are ignored. +.El +.Sh ENVIRONMENT +The +.Nm +command looks for the database directory in the users home directory +specified by the +.Ev HOME +environment variable. Use the +.Fl d +flag to specify a different database directory. +.Sh FILES +.Bl -tag -width ".Pa $HOME/. Ns Nm" -compact +.It Pa $HOME/. Ns Nm +The default database directory. +.El +.Sh EXAMPLES +Typically one would use +.Nm +with +.Nm procmail +and +.Nm formail +to flag and filter incoming email. +.Pp +.Dl "# SpamProbe rule." +.Dl ":0" +.Dl "{" +.Dl " # Generate a score for the message." +.Dl " SCORE=`spamprobe receive`" +.Dl " # Add a X-SpamProbe header to the message." +.Dl " :0 fhW" +.Dl " | formail -I ""X-SpamProbe: $SCORE""" +.Dl "}" +.Pp +.Dl "# Filter matching messages to their own mailbox." +.Dl ":0:" +.Dl "*^X-SpamProbe: SPAM" +.Dl "spamprobe" +.Sh DIAGNOSTICS +Exit status is 0 on success, and 1 if +.Nm +encounters an invalid command. +.Sh COMPATIBILITY +The +.Nm +command has no known compatibility issues. +.Sh SEE ALSO +.Xr formail 1 , +.Xr procmail 1 , +.Rs +.%A "Paul Graham" +.%T "A Plan for Spam" +.%O http://www.paulgraham.com/spam.html +.%D "August 2002" +.Re +.Sh AUTHORS +This +manual page was written by +.An Matthew N. Dodd Aq mdodd@FreeBSD.org . +.Nm +was written by +.An Brian Burton Aq bburton@users.sourceforge.net diff --git a/mail/spamprobe/pkg-comment b/mail/spamprobe/pkg-comment new file mode 100644 index 000000000000..dfd8ee247392 --- /dev/null +++ b/mail/spamprobe/pkg-comment @@ -0,0 +1 @@ +Spam detector using Bayesian analysis of word counts diff --git a/mail/spamprobe/pkg-descr b/mail/spamprobe/pkg-descr new file mode 100644 index 000000000000..defc38ffb8c5 --- /dev/null +++ b/mail/spamprobe/pkg-descr @@ -0,0 +1,7 @@ +SpamProbe + +Fast, intelligent, automatic spam detector using Bayesian analysis of word +counts in spam and non-spam email. Intended for use with procmail to +filter inbound email. No manual rule creation required. + +WWW: http://sourceforge.net/projects/spamprobe/ diff --git a/mail/spamprobe/pkg-plist b/mail/spamprobe/pkg-plist new file mode 100644 index 000000000000..39a83231119f --- /dev/null +++ b/mail/spamprobe/pkg-plist @@ -0,0 +1,2 @@ +bin/spamprobe +man/man1/spamprobe.1.gz |