--- crm114-20070810.orig/maillib.crm +++ crm114-20070810/maillib.crm @@ -371,11 +371,13 @@ match (:found: :hd: :tail:) /^(:*:header:) (.*)/ alter (:tail:) /:*:tail: (:*:comment:)/ } - alius - { - # no such header. make one. - call /:mungmail_add:/ [:*:header: (:*:comment:)] - } +# Commented out by Milan Zamazal on 2007-01-28 as suggested on +# the crm114 mailing list. If this is wrong please let me know. +# alius +# { +# # no such header. make one. +# call /:mungmail_add:/ [:*:header: (:*:comment:)] +# } } return --- crm114-20070810.orig/mailreaver.crm +++ crm114-20070810/mailreaver.crm @@ -687,5 +687,5 @@ ######################################################################3 # # Library insertions start here. -insert maillib.crm +insert /usr/share/crm114/maillib.crm --- crm114-20070810.orig/Makefile +++ crm114-20070810/Makefile @@ -64,7 +64,9 @@ # Comment this out if you want dynamic linking # # BSD users - do NOT use -static-libgcc!!! -LDFLAGS += -static -static-libgcc +# 2005-04-22 Milan Zamazal : Do not link statically, to comply +# with Debian policies. +#LDFLAGS += -static -static-libgcc # # Any standard install flags? We nominally use protection 755 INSTALLFLAGS += -m 755 --- crm114-20070810.orig/debian/docs +++ crm114-20070810/debian/docs @@ -0,0 +1,9 @@ +README +*.cf +*.crm +*.dat +*.example +*.mfp +*.recipe +*.txt +megatest.sh --- crm114-20070810.orig/debian/rules +++ crm114-20070810/debian/rules @@ -0,0 +1,76 @@ +#!/usr/bin/make -f + +# Uncomment this to turn on verbose mode. +#export DH_VERBOSE=1 + +package=crm114 + +CFLAGS = -Wall -g +ifneq (,$(findstring noopt,$(DEB_BUILD_OPTIONS))) + CFLAGS += -O0 +else + CFLAGS += -O2 +endif +ifeq (,$(findstring nostrip,$(DEB_BUILD_OPTIONS))) + INSTALL_PROGRAM += -s +endif + +build: build-stamp +build-stamp: + dh_testdir + $(MAKE) CFLAGS="$(CFLAGS)" + touch build-stamp + +clean: + dh_testdir + dh_testroot + rm -f build-stamp + $(MAKE) clean + dh_clean + +install: build + dh_testdir + dh_testroot + dh_clean -k + dh_installdirs + $(MAKE) install prefix=`pwd`/debian/$(package)/usr + +# Build architecture-independent files here. +binary-indep: build install +# We have nothing to do by default. + +# Build architecture-dependent files here. +binary-arch: build install + dh_testdir + dh_testroot + dh_installchangelogs + dh_install + dh_installdocs + rm `pwd`/debian/crm114/usr/share/doc/$(package)/GPL-License.txt + mv `pwd`/debian/crm114/usr/share/doc/$(package)/*test* \ + `pwd`/debian/crm114/usr/share/doc/$(package)/examples/tests/ + set -e; for ext in cf crm dat example mfp recipe; do \ + mv `pwd`/debian/crm114/usr/share/doc/$(package)/*.$$ext \ + `pwd`/debian/crm114/usr/share/doc/$(package)/examples/; \ + done + dh_installexamples + set -e; for file in `pwd`/debian/crm114/usr/share/doc/$(package)/examples/* \ + `pwd`/debian/crm114/usr/share/doc/$(package)/examples/tests/*; do \ + if [ -f $$file ] && [ "`head -c 2 $$file`" != '#!' ]; then \ + chmod a-x $$file; \ + fi; \ + done + chmod a-x `pwd`/debian/crm114/usr/share/crm114/mailfilter.cf + chmod a-x `pwd`/debian/crm114/usr/share/emacs/site-lisp/* + dh_installman debian/*.1 + dh_strip + dh_compress + dh_fixperms + dh_installdeb + dh_shlibdeps + dh_gencontrol + dh_md5sums + dh_builddeb + +binary: binary-indep binary-arch +.PHONY: build clean binary-indep binary-arch binary install --- crm114-20070810.orig/debian/changelog +++ crm114-20070810/debian/changelog @@ -0,0 +1,265 @@ +crm114 (20070810-2~bpo40+1) etch-backports; urgency=low + + * Rebuilt for etch. + + -- martin f. krafft Mon, 22 Oct 2007 09:02:20 +0200 + +crm114 (20070810-2) unstable; urgency=low + + * Broken .css files compatibility on 32-bit architectures, introduced in + 20070810-1, fixed. + + -- Milan Zamazal Wed, 29 Aug 2007 10:31:55 +0200 + +crm114 (20070810-1) unstable; urgency=low + + * New upstream version; closes: #433112. + * Tried to make some variable types related to cssutil more specific to + prevent repeating problems on 64-bit architectures. + + -- Milan Zamazal Wed, 22 Aug 2007 07:51:49 +0200 + +crm114 (20070320-1) unstable; urgency=low + + * New upstream version; closes: #416446. + * Honor DEB_BUILD_OPTIONS. + * Make sure crm114-mode.el gets installed. + + -- Milan Zamazal Sun, 24 Jun 2007 12:35:53 +0200 + +crm114 (20061103-1) experimental; urgency=low + + * New upstream version; closes: #406089. + * Upload to experimental because etch is in freeze. + * Don't add Message-Id header if there's not any, information about + broken threading added to README.Debian; this attempts to solve bug + #406207. + + -- Milan Zamazal Sun, 28 Jan 2007 10:11:06 +0100 + +crm114 (20060704a-4) unstable; urgency=low + + * Use full path when loading maillib.crm in mailreaver.crm; + closes: #398078. + + -- Milan Zamazal Sun, 12 Nov 2006 10:08:53 +0100 + +crm114 (20060704a-3) unstable; urgency=low + + * Fixes of typos in mailfilter.cf, thanks to Martin Steigerwald + ; closes: #394476. + + -- Milan Zamazal Sun, 22 Oct 2006 09:05:52 +0200 + +crm114 (20060704a-2) unstable; urgency=low + + * Install all mail*.crm scripts into /usr/share/crm114/. + * Add upgrade warnings to NEWS.Debian and README.Debian; + closes: #377978, #378084, #378135. + + -- Milan Zamazal Fri, 14 Jul 2006 10:23:07 +0200 + +crm114 (20060704a-1) unstable; urgency=low + + * New upstream version. + * Standards 3.7.2 (no real change). + + -- Milan Zamazal Mon, 10 Jul 2006 23:19:34 +0200 + +crm114 (20060118-1) unstable; urgency=low + + * New upstream version; closes: #339393. + + -- Milan Zamazal Tue, 7 Feb 2006 09:52:03 +0100 + +crm114 (20050721-2) unstable; urgency=low + + * Missing :classify_status: declaration added in mailfilter.crm; + closes: #318720. + + -- Milan Zamazal Tue, 9 Aug 2005 17:36:41 +0200 + +crm114 (20050721-1) unstable; urgency=low + + * New upstream 'BlameNeilArmstrong' release; closes: #270315. + * Fix in Mutt instructions, thanks to Antti-Juhani Kaijanaho + ; closes: #307815. + + -- Milan Zamazal Sun, 7 Aug 2005 13:07:41 +0200 + +crm114 (20050628-1) unstable; urgency=low + + * New upstream 'BlameCochrane' release. + * Standards 3.6.2 (no real change). + + -- Milan Zamazal Fri, 1 Jul 2005 08:58:12 +0200 + +crm114 (20050415-4) unstable; urgency=low + + * Patched not to crash in cssdiff when the compared files don't exist + and not to require write access to them; closes: #306519. + * Man pages from the latest autoconfiscated version added; + closes: #306523. + * Don't depend on procmail, the scripts no longer require formail; + closes: #244167. + + -- Milan Zamazal Mon, 2 May 2005 10:09:00 +0200 + +crm114 (20050415-3) unstable; urgency=low + + * The important changes introduced by switching from the autoconfiscated + version to the upstream version are described in NEWS.Debian now; + closes: #305938. + * Tests still present in examples/ moved to examples/tests/. + * File permissions fixed. + * debian/rules: Don't call unnecessary debhelper commands. + + -- Milan Zamazal Mon, 25 Apr 2005 13:02:34 +0200 + +crm114 (20050415-2) unstable; urgency=low + + * Install most important directly usable sample files into + /usr/share/crm114/. + + -- Milan Zamazal Sat, 23 Apr 2005 20:44:43 +0200 + +crm114 (20050415-1) unstable; urgency=low + + * New upstream 'BlameTheIRS' release; closes: #275238, #281619. + * New maintainer; closes: #304762. + * Packaging switched (back?) to plain debhelper. + + -- Milan Zamazal Fri, 22 Apr 2005 19:44:22 +0200 + +crm114 (20040816.BlameClockworkOrange-auto.3-1) unstable; urgency=medium + + * Fix recent bug in upstream source, which was causing always success + error code. + + -- Ondřej Surý Thu, 19 Aug 2004 14:17:41 +0200 + +crm114 (20040816.BlameClockworkOrange-auto.2-1) unstable; urgency=medium + + * New autoconfiscated version. + * Fix FTBFS when compiled with gcc3.4. + + -- Ondřej Surý Wed, 18 Aug 2004 16:25:41 +0200 + +crm114 (20040816-1) unstable; urgency=medium + + * New upstream 'BlameClockworkOrange' release. + + -- Ondřej Surý Wed, 18 Aug 2004 12:10:26 +0200 + +crm114 (20040627-2) unstable; urgency=low + + * Add patch to fix infinite loop in mailfilter.crm (Closes: #259653) + + -- Ondřej Surý Fri, 16 Jul 2004 09:13:49 +0200 + +crm114 (20040627-1) unstable; urgency=low + + * New upstream 'BlameSeifkes' release. + + -- Ondřej Surý Mon, 12 Jul 2004 16:16:33 +0200 + +crm114 (20040419-1) unstable; urgency=low + + * New upstream release. + + -- Ondřej Surý Fri, 30 Apr 2004 15:12:37 +0200 + +crm114 (20040409-2) unstable; urgency=low + + * Add link from crm114 manpage to crm (Closes: #244739) + + -- Ondřej Surý Tue, 20 Apr 2004 09:38:53 +0200 + +crm114 (20040409-1) unstable; urgency=low + + * New upstream 'BlameMarys' release (Closes: #242469) + * Add procmail to dependencies (Closes: #240967) + * Re-add patch to HOWTO (Closes: #235955) + + -- Ondřej Surý Tue, 13 Apr 2004 11:41:32 +0200 + +crm114 (20040312-2) unstable; urgency=low + + * Previous release was not NMU. I have utfized my name and forgot + to change it in control. + + -- Ondřej Surý Sun, 14 Mar 2004 13:48:32 +0100 + +crm114 (20040312-1) unstable; urgency=low + + * New upstream 'BlameSnow' release. (Closes: #237868). + * autoconf dependency was probably added by patching to auto.2 + release (Closes: #237916). + + -- Ondřej Surý Sun, 14 Mar 2004 13:05:54 +0100 + +crm114 (20040221-2) unstable; urgency=low + + * Updated to auto.2 release (Closes: #235957) + * Included instruction to setup under maildrop. (Closes: #235955) + + -- Ondrej Sury Thu, 11 Mar 2004 17:38:17 +0100 + +crm114 (20040221-1) unstable; urgency=low + + * New upstream release. + * Switch to autoconfiscated version (this also adds man pages). + * Switch build system to cdbs. + * Add metamail | mew-bin recommends for mailfilter.crm function (Closes: #234793) + + -- Ondrej Sury Thu, 26 Feb 2004 09:52:59 +0100 + +crm114 (20040212-3) unstable; urgency=low + + * Add NEWS.Debian file to mention .css incompatibility with previous + release. + + -- Ondrej Sury Tue, 24 Feb 2004 16:37:43 +0100 + +crm114 (20040212-2) unstable; urgency=low + + * Moved .mfp files to examples directory (where they really belong). + * Included .cf files in examples directory (Closes: #234541). + + -- Ondrej Sury Tue, 24 Feb 2004 15:12:01 +0100 + +crm114 (20040212-1) unstable; urgency=low + + * New upstream release (Closes: #186589, #214149). + * According to info in bugs.debian.org/225146, this is fixed in new version (Closes: #225146) + * Upstream author says that this segfault bug is also fixed in new version (Closes: #225146) + * New maintainer (Closes: #206105) + * Don't include .css files, they are quite large and not neccessary + according to CRM114_Mailfilter_HOWTO.txt. + + -- Ondrej Sury Sat, 21 Feb 2004 18:42:46 +0100 + +crm114 (2002-11-26-3) unstable; urgency=low + + * QA Upload. + * Inverted logic on read/write vs. readonly file opening in crm114.c + (Closes: #226780, #177794) + * Section changed from unknown to admin. + * Upstream Author(s) -> Author in debian/copyright. + * debhelper build dependency changed to version 4 to reflect debhelper + compatibility version. + + -- Emanuele Rocca Mon, 19 Jan 2004 14:39:06 +0100 + +crm114 (2002-11-26-2) unstable; urgency=low + + * Orphaning this package. Reassigned maintainer to QA group. + + -- John Goerzen Mon, 18 Aug 2003 15:20:14 -0500 + +crm114 (2002-11-26-1) unstable; urgency=low + + * Initial Release. Closes: #177783. + + -- John Goerzen Tue, 21 Jan 2003 15:49:23 -0600 + --- crm114-20070810.orig/debian/README.Debian +++ crm114-20070810/debian/README.Debian @@ -0,0 +1,35 @@ +crm114 for Debian +----------------- + +crm114 is a case of "the source is the documentation"; please see +/usr/share/crm114 for additional examples and documentation. Many files +are well-commented. + + -- John Goerzen , Tue, 21 Jan 2003 15:49:23 -0600 + +crm114 provides scripts ready for immediate use in /usr/share/crm114/. Other +example scripts are available in /usr/share/doc/crm114/examples/. + +WARNING: Although the scripts in /usr/share/crm114/ can be used directly, I +don't recommend to do so if you use crm114 for mail filtering. You risk that +something breaks in your setup when crm114 gets upgraded. I recommend copying +the *.crm scripts you use to your private location and working with the copies. +Then you can upgrade the scripts only when you know what you are doing, +avoiding surprises on apt-get update. And of course, your mail delivery system +should always be set up in such a way that it doesn't stop working when crm114 +breaks. + + -- Milan Zamazal 2006-07-14 + +If you experience broken threading caused by Message-Id modifications performed +by crm114, this may happen because one of the following reasons: + +1. Your MUA is not RFC-compliant and should be fixed. + +2. crm114 scripts are not RFC-compliant and should be fixed. + +We expect 1. is the case, but if you think otherwise, please let me know. +Don't forget to attach detailed explanation so that crm114 developers know what +exactly is broken and how it should be fixed. See also bug #406207. + + -- Milan Zamazal 2007-01-28 --- crm114-20070810.orig/debian/crm.1 +++ crm114-20070810/debian/crm.1 @@ -0,0 +1,1115 @@ +.\" Copyright (c) 2004 William S\&. Yerazunis\&. Manpage typesetting by Joost van Baal and Shalendra Chhabra +.TH "crm" 1 "19 Aug 2004" "crm114 20040816\&.BlameClockworkOrange-auto\&.3" "CRM114" +.po 2m +.de ZI +.\" Zoem Indent/Itemize macro I. +.br +'in +\\$1 +.nr xa 0 +.nr xa -\\$1 +.nr xb \\$1 +.nr xb -\\w'\\$2' +\h'|\\n(xau'\\$2\h'\\n(xbu'\\ +.. +.de ZJ +.br +.\" Zoem Indent/Itemize macro II. +'in +\\$1 +'in +\\$2 +.nr xa 0 +.nr xa -\\$2 +.nr xa -\\w'\\$3' +.nr xb \\$2 +\h'|\\n(xau'\\$3\h'\\n(xbu'\\ +.. +.if n .ll -2m +.am SH +.ie n .in 4m +.el .in 8m +.. +.SH NAME +crm \- The Controllable Regex Mutilator +.SH SYNOPSIS + +\fBcrm\fP +\fB[-d\fP N (\fIenter debugger after running N cycles\&. Omitting N +means N equals 0\&.\fP)\fB]\fP +\fB[-e\fP (\fIdo not import any environment variables\fP)\fB]\fP +\fB[-h\fP (\fIprint help text\fP)\fB]\fP +\fB[-p\fP (\fIgenerate an execution-time-spent profile on exit\fP)\fB]\fP +\fB[-P\fP N (\fImax program lines\fP)\fB]\fP +\fB[-q\fP m (\fImathmode (0,1 = alg/RPN only in EVAL, 2,3 = alg/RPN +everywhere)\fP)\fB]\fP +\fB[-s\fP N (\fInew feature file (\&.css) size is N (default 1 meg+1 +featureslots)\fP)\fB]\fP +\fB[-S\fP N (\fInew feature file (\&.css) size is N rounded to 2^I+1 +featureslots\fP)\fB]\fP +\fB[-t\fP (\fIuser trace output\fP)\fB]\fP +\fB[-T\fP (\fIimplementors trace output (only for the masochistic!)\fP)\fB]\fP +\fB[-u\fP dir (\fIchdir to directory dir before starting execution\fP)\fB]\fP +\fB[-v\fP (\fIprint CRM114 version identification and exit\fP)\fB]\fP +\fB[-w\fP N (\fImax data window (bytes, default 16 megs)\fP)\fB]\fP +\fB[--\fP (\fIsignals the end CRM114 flags; prior flags are not seen by +the user program; subsequent args are not processed by CRM114\fP)\fB]\fP +\fB[--foo\fP (\fIcreates the user variable :foo: with the value SET\fP)\fB]\fP +\fB[--x=y\fP (\fIcreates the user variable :x: with the value y\fP)\fB]\fP +\fB[-{\fP stmts} (\fIexecute the statements inside the {} brackets\fP)\fB]\fP +\fBcrmfile\fP (\fI\&.crm file name\fP) +.SH WARNING +This man page is taken from an older CRM114 version. It is provided as a +convenience to Debian users and may not be up-to-date. If you would like to +update it, please send appropriate patches to the Debian bug tracking system. +.SH DESCRIPTION +CRM114 is a language designed to write filters in\&. It caters to +filtering email, system log streams, html, and other marginally +human-readable ASCII that may occasion to grace your computer\&. + +CRM114\&'s unique strengths are the data structure (everything is +a string and a string can overlap another string), it\&'s ability +to work on truly infinitely long input streams, it\&'s ability to +use extremely advanced classifiers to sort text, and the ability +to do approximate regular expressions (that is, regexes that +don\&'t quite match) via the TRE regex library\&. + +CRM114 also sports a very powerful subprocess control facility, and +a unique syntax and program structure that puts the fun back in +programming (OK, you can run away screaming now)\&. The syntax is +declensional rather than positional; the type of quote marks around +an argument determine what that argument will be used for\&. + +The typical CRM114 program uses regex operations more often +than addition (in fact, math was only added to TRE in the waning +days of 2003, well after CRM114 had been in daily use for over +a year and a half)\&. + +In other words, crm114 is a very \fBvery\fP powerful mutagenic filter that +happens to be a programming language as well\&. + +The filtering style of the CRM-114 discriminator is based on the fact +that most spam, normal log file messages, or other uninteresting data +is easily categorized by a few characteristic patterns (such as +"Mortgage leads", "advertise on the internet", and "mail-order toner +cartridges"\&.) CRM114 may also be useful to folks who are on multiple +interlocking mailing lists\&. + +In a bow to Unix-style flexibility, by default CRM114 reads it\&'s +input from standard input, and by default sends it\&'s output to +standard output\&. Note that the default action has a zero-length +output\&. Redirection and use of other input or output files is +possible, as well as the use of windowing, either delimiter-based or +time-based, for real-time continuous applications\&. + +CRM114 can be used for other than mail filtering; consider it to be a version +of \fIgrep\fP with super powers\&. If perl is a seventy-bladed swiss army knife, +CRM114 is a razor-sharp katana that can talk\&. +.SH INVOCATION +Absent the -{ program } flag, the first argument is taken to be the name of +a file containing a crm114 program, subsequent arguments are merely supplied +as :_argN: values\&. Use single quotes around commandline programs +\&'-{ like this }\&' to prevent the shell from doing odd things to your +command-line programs\&. + +CRM114 can be directly invoked by the shell if the first line of your +program file uses the shell standard, as in: + +.di ZV +.in 0 +.nf \fC +#! /usr/bin/crm +.fi \fR +.in +.di +.ne \n(dnu +.nf \fC +.ZV +.fi \fR + +You can use CRM114 flags on the shell-standard invocation line, and +hide them with \&'--\&' from the program itself; \&'--\&' incidentally prevents +the invoking user from changing any CRM114 invocation flags\&. + +Flags should be located after any positional variables on the command +line\&. Flags \fIare\fP visible as :_argN: variables, so you can create +your own flags for your own programs (separate CRM114 and user flags +with \&'--\&')\&. +Two examples on how to do this: + +.di ZV +.in 0 +.nf \fC +\&./foo\&.crm bar mugga < baz -t -w 150000 +.fi \fR +.in +.di +.ne \n(dnu +.nf \fC +.ZV +.fi \fR + +.di ZV +.in 0 +.nf \fC +\&./foo\&.crm -t -w 1500000 -- bar < baz mugga +.fi \fR +.in +.di +.ne \n(dnu +.nf \fC +.ZV +.fi \fR + +One example on how \fBnot\fP to do this: + +.di ZV +.in 0 +.nf \fC +\&./foo\&.crm -t -w 150000 bar < baz mugga +.fi \fR +.in +.di +.ne \n(dnu +.nf \fC +.ZV +.fi \fR + +(That\&'s WRONG!) + +You can put a list of user-settable vars on the \fC#!/usr/bin/crm\fR +invocation line\&. CRM114 will print these out when a program is +invoked directly (e\&.g\&. "\&./myprog\&.crm -h", not "crm myprog\&.crm -h") +with the -h (for help) flag\&. (note that this works ONLY on bash +on Linux- *BSD\&'s have a different bash interpretation and this +doesn\&'t work) + +Example: + +.di ZV +.in 0 +.nf \fC +#!/usr/bin/crm -( var1 var2=A var2=B var2=C ) +.fi \fR +.in +.di +.ne \n(dnu +.nf \fC +.ZV +.fi \fR + +This allows only \fCvar1\fR and \fCvar2\fR be set on the command line\&. If a +variable is not assigned a value, the user can set any value desired\&. If the +variable is equated to a set of values, those are the \fIonly\fP values allowed\&. + +Another example: + +.di ZV +.in 0 +.nf \fC +#!/usr/bin/crm -( var1 var2=foo ) -- +.fi \fR +.in +.di +.ne \n(dnu +.nf \fC +.ZV +.fi \fR + +This allows \fCvar1\fR to +be set to any value, \fCvar2\fR may only be set to either \fCfoo\fR or not at all, +and no other variables may be set nor may invocation flags be changed (because +of the trailing "--")\&. Since "--" also blocks \&'-h\&' for help, such programs +should provide their own help facility\&. +.SH VARIABLES +Variable names and locations start with a : , end with a : , and may +contain only characters that have ink (i\&.e\&. the [:graph:] class) with +few exceptions\&. + +Examples \fC:here:\fR, \fC:ThErE:\fR, \fC:every-where_0123+45%6789:\fR, +\fC:this_is_a_very_very_long_var_name_that_does_not_tell_us_much:\fR\&. +Builtin variables: + +.ZI 21m ":_nl:" +newline +.in -21m +.ZI 21m ":_ht:" +horizontal tab +.in -21m +.ZI 21m ":_bs:" +backspace +.in -21m +.ZI 21m ":_sl:" +a slash +.in -21m +.ZI 21m ":_sc:" +a semicolon +.in -21m +.ZI 21m ":_arg0: thru :_argN:" +command-line args, including \fIall\fP flags +.in -21m +.ZI 21m ":_argc:" +how many command line arguments there were +.in -21m +.ZI 21m ":_pos0: thru :_posN:" +positional args (\&'-\&' or \&'--\&' args deleted) +.in -21m +.ZI 21m ":_posc:" +how many positional arguments there were +.in -21m +.ZI 21m ":_pos_str:" +all positional arguments concatented +.in -21m +.ZI 21m ":_env_whatever:" +environment value \&'whatever\&' +.in -21m +.ZI 21m ":_env_string:" +all environmental arguments concatenated +.in -21m +.ZI 21m ":_crm_version:" +the version of the CRM system +.in -21m +.ZI 21m ":_dw:" +the current data window contents +.in -21m +.SH VARIABLE EXPANSION +Variables are expanded by the \fC:*:\fR var-expansion operator, +e\&.g\&. \fC:*:_nl:\fR expands to a newline character\&. Uninitialized vars +evaluate to their text name (and the colons stay)\&. + +You can also use the standard constant C \&'\e\&' characters, such as "\en" +for newline, as well as excaped hexadecimal and octal characters like +\exHH and \eoOOO but these are constants, not variables, and cannot be +redefined\&. + +Depending on the value of "math mode" (flag -q)\&. you can also use +\fC:#:string_or_var:\fR to get the length of a string, and \fC:@:string_or_var:\fR +to do basic mathematics and inequality testing, either only in EVALs +or for all var-expanded expressions\&. See "Sequence of Evaluation" +below for more details\&. +.SH PROGRAM BEHAVIOR +Default behavior is to read all of standard input till EOF into the +default data window (named \fC:_dw:\fR), then execute the program (this is +overridden if first executable statement is a WINDOW statement)\&. + +Variables don\&'t get their own storage unless you ISOLATE them (see +below), instead variables are start/length pairs indexing into the +default data window\&. Thus, ALTERing an unISOLATEd variable changes +the value of the default data buffer itself\&. This is a great power, +so use it only for good, and never for evil\&. +.SH STATEMENTS AND STUFF +Statements are separated with a \&';\&' or with a newline\&. + +.ZI 8m "\e" +\& +.br +\&'\e\&' is the string-text escape character\&. You only \fIneed\fP to +escape the literal representation of closing delimiters inside var-expanded +arguments\&. + +You can use the classic C/C++ \e-escapes, such as \en, \er, +\et, \ea, \eb, \ev, \ef, \e0, and also \exHH and \eoOOO for hex and +octal characters, respectively\&. + +A \&'\e\&' as the \fIlast\fP character of a line means the next line +is just a continuation of this one\&. + +A \e-escape that isn\&'t recognized as something special isn\&'t +an error; you may \fIoptionally\fP escape any of the delimiters +\fC>\fR, \fC)\fR \fC]\fR \fC}\fR \fC;\fR \fC/\fR \fC#\fR \fC\e\fR and get just +that character\&. + +A \&'\e\&' anywhere else is just a literal backslash, so the regex +([abc])\e1 is written just that way; there is no need to +double-backslash the \e1 (although it will work if you do)\&. +.in -8m +.ZI 8m "# this is a comment" +\& +'in -8m +.ZI 8m "# and this too \e#" +\& +'in -8m +'in +8m +\& +.br +A comment is not a piece of preprocessor +sugar -- it is a \fIstatement\fP and ends at the newline or at "\e#"\&. +.in -8m +.ZI 8m "insert filename" +\& +.br +inserts the file verbatim at this line at compile +time\&. +.in -8m +.ZI 8m ";" +\& +.br +statement separator - must ALWAYS be escaped as \e; unless it\&'s +inside delimiters or else it will mark the end of the statement\&. +.in -8m +.ZI 8m "{ and }" +\& +.br +start and end blocks of statements\&. Must always be \&'\e\&' +escaped or inside delimiters or these will mark the start/end of a +block\&. +.in -8m +.ZI 8m "noop" +\& +.br +no-op statement +.in -8m +.ZI 8m ":label:" +\& +.br +define a GOTOable label +.in -8m +.ZI 8m "accept" +\& +.br +writes the current data window to standard output; execution +continues\&. +.in -8m +.ZI 8m "alius" +\& +.br +if the last bracket-group succeeded, ALIUS skips to end of {} +block (a skip, not a FAIL); if the prior group FAILed, ALIUS does +nothing\&. Thus, ALIUS is both an ELSE clause and a CASE statement\&. +.in -8m +.ZI 8m "alter (:var:) /new-val/" +\& +.br +destructively change value of var to newval; +(:var:) is var to change (var-expanded); /new-val/ is value to change +to (var-expanded)\&. +.in -8m +.ZI 8m "classify (:c1:\&.\&.\&.|\&.\&.\&.:cN:) (:stats:) [:in:] /word-pat/" +\& +.br +compare the statistics of the current data window buffer with classfiles +c1\&.\&.\&.cN\&. + +.ZI 17m "" +If is set to , ignore case in +word-pat, does not change case in hash (use tr() to do that on +:in: if you want it)\&. +.in -17m +.ZI 17m "(:c1: \&.\&.\&." +file or files to consider "success" files\&. The +CLASSIFY succeeds if these files as a group match best\&. If not, +the CLASSIFY does a FAIL\&. +.in -17m +.ZI 17m "|" +optional separator\&. Spaces on each side of the " | " are +required\&. +.in -17m +.ZI 17m "\&.\&.\&.\&. :cN:)" +optional files to the right of " | " are considered +as a group to "fail"\&. If statement fails, execution skips to end +of enclosing {\&.\&.} block, which exits with a FAIL status (see +ALIUS for why this is useful)\&. +.in -17m +.ZI 17m "(:stats:)" +optional var that will get a text formatted matching +summary +.in -17m +.ZI 17m "[:in:]" +restrict statistical measure to the string inside :in: +.in -17m +.ZI 17m "/word-pat/" +regex to describe what a parseable word is\&. +.in -17m +.in -8m +.ZI 8m "eval (:result:) /instring/" +\& +.br +repeatedly evaluates /instring/ until it +ceases to change, then places that result +as the value of :result: \&. EVAL uses +smart (but foolable) heuristics to avoid +infinite loops, like evaluating a string +that evaluates to a request to evaluate +itself again\&. The error rate is about +1 / 2^62 and will detect chain groups of +length 255 or less\&. +If the instring uses math evaluation +(see section below on math operations) +and the evaluation has an inequality +test, (>, < or =) then if the inequality +fails, the EVAL will FAIL to the end of +block\&. If the evaluation has a numeric +fault (e\&.g\&. divide-by-zero) the EVAL will +do a TRAPpable FAULT\&. +.in -8m +.ZI 8m "exit /:retval:/" +\& +.br +ends program execution\&. If supplied, the +return value is converted to an integer +and returned as the exit code of the +crm114 program\&. If no retval is supplied, +the return value is 0\&. +.in -8m +.ZI 8m "fail" +\& +.br +skips down to end of the current { } block +and causes that block to exit with a FAIL +status (see ALIUS for why this is useful) +.in -8m +.ZI 8m "fault /faultstr/" +\& +.br +forces a FAULT with the given string as +the reason\&. The fault string is +val-expanded\&. +.in -8m +.ZI 8m "goto /:label:/" +\& +.br +unconditional branch (you can use a variable as the +goal, e\&.g\&. /:*:there:/ ) +.in -8m +.ZI 8m "hash (:result:) /input/" +\& +.br +compute a fast 32-bit hash of the /input/, +and ALTER :result: to the +hexadecimal hash value\&. HASH is +\fInot\fP warranted to be constant across +major releases of CRM114, nor is it +cryptographically secure\&. + +.ZI 17m "(:result:)" +value that gets result\&. +.in -17m +.ZI 17m "/input/" +string to be hashed (can contain expanded :*:vars:, +defaults to the data window :_dw:) +.in -17m +.in -8m +.ZI 8m "intersect (:out:) [:var1: :var2: \&.\&.\&.]" +\& +.br +makes :out: contain the part of +the data window that is the intersection of +:var1 :var2: \&.\&.\&. ISOLATEd vars are ignored\&. +This only resets the value of the captured +variable, and does NOT alter any text in +the data window\&. +.in -8m +.ZI 8m "isolate (:var:) /initial-value/" +\& +.br +puts :var: into a data area outside of +the data buffer; subsequent changes to this +var don\&'t change the data buffer (though +they may change the value of any var +subsequently set inside of this var)\&. +If the var already was ISOLATED, this is +a noop\&. + +.ZI 17m "(:var:)" +name of ISOLATEd var (var-expanded) +.in -17m +.ZI 17m "/initial-value/" +optional initial value for :var: +(var-expanded)\&. If no value is supplied, +the previous value is retained/copied\&. +.in -17m +.in -8m +.ZI 8m "input (:result:) [:filename:]" +\& +.br +read in the content of filename\&. +If no filename, then read stdin + +.ZI 17m "" +read one line only +.in -17m +.ZI 17m "(:result:)" +var that gets the input value +.in -17m +.ZI 17m "[:filename:]" +the file to read +.in -17m +.in -8m +.ZI 8m "learn (:class:) [:in:] /word-pat/" +\& +.br +learn the statistics of +the :in: var (or the input window if no +var) as an example of class :class: + +.ZI 17m "" +can be any of , and \&. +: ignore case in matching word-pat (does not ignore case in +hash- use tr() to do that on :in: if you want it)\&. : this is +an anti-example of this class- unlearn it! : enable the +microgroomer to purge less-important information automatically +whenever the statistics file gets to crowded\&. +.in -17m +.ZI 17m "(:class:)" +name of file holding hashed results; nominal file +extension is \&.css +.in -17m +.ZI 17m "[:in:]" +captured var containing the text to be learned (if +omitted, the full contents of the data window is used) +.in -17m +.ZI 17m "/word-pat/" +regex that defines a "word"\&. Things that aren\&'t +"words" are ignored\&. +.in -17m +.in -8m +.ZI 8m "liaf" +\& +.br +skips UP to START of the current {} block (LIAF is FAIL +spelled backwards) +.in -8m +.ZI 8m "match (:var1: \&.\&.\&.) [:in:] /regex/" +\& +.br +Attempt to match the given +regex; if match succeds, variables are bound; if match fails, program +skips to the closing \&'}\&' of this block + +.ZI 17m "" +flags can be any of + +.ZI 3m "" +statement succeeds if match not present +.in -3m +.ZI 3m "" +ignore case when matching +.in -3m +.ZI 3m "" +start match at start of the [:in:] var +.in -3m +.ZI 3m "" +start match at start of previous successful +match on the [:in:] var +.in -3m +.ZI 3m "" +start match at one character past the start of +the previous successful match on the [:in:] var +.in -3m +.ZI 3m "" +start match at one character past the end of +prev\&. match on this [:in:] var +.in -3m +.ZI 3m "" +require match to end after end of prev\&. match on +this [:in:] var +.in -3m +.ZI 3m "" +search backward in the [:in:] variable from the +last successful match\&. +.in -3m +.ZI 3m "" +don\&'t allow this match to span lines +.in -3m +.in -17m +.ZI 17m "(:var1: \&.\&.\&.)" +optional variables to bind to regex result and +\&'(\&' \&')\&' subregexes +.in -17m +.ZI 17m "[:in:]" +search only in the variable specified; if omitted, :_dw: +(the full input data window) is used +.in -17m +.ZI 17m "/regex/" +POSIX regex (with \e escapes as needed) +.in -17m +If you build CRM114 to use the GNU regex library for MATCHing, +be warned that GNU REGEX has numerous issues\&. See the +KNOWN_BUGS file for a detailed listing\&. +.in -8m +.ZI 8m "output [filename] /output-text/" +\& +.br +output an arbitrary string +with captured values expanded\&. + +.ZI 17m "" +: append to the file (otherwise, overwrites) +.in -17m +.ZI 17m "[filename]" +filename to send output (var-expanded), default output +is to stdout +.in -17m +.ZI 17m "/output-text/" +string to output (var-expanded) +.in -17m +.in -8m +.ZI 8m "syscall (:in:) (:out:) (:status:) /command/" +\& +.br +execute a shell +command + +.ZI 17m "" +can be any of and \&. : keep this +process around; if kept, then a syscall with the same :keep: var will +continue feeding to and reading from the kept proc\&. : don\&'t +wait for process to send an EOF; just grab what\&'s available in +the process\&'s output pipe and proceed (limit per syscall is 256 Kbytes) +.in -17m +.ZI 17m "(:in:)" +var-expanded string to feed to command as input (can be +null if you don\&'t want to send the process something\&.) You \fBmust\fP +specify this if you want to specify an :out: variable\&. +.in -17m +.ZI 17m "(:out:)" +var-expanded varname to place results into (\fBmust\fP +pre-exist, can be null if you don\&'t want to read the process\&'s +output (yet, or at all)\&. Limit per syscall is 256 Kbytes\&. You +\fBmust\fP specify this if you want to use the :status: variable) +.in -17m +.ZI 17m "(:status:)" +if you want to keep a minion proc around, or catch the +exit status of the process, specify a var here\&. The minion process\&'s +PID and pipes will be stored here\&. The program can access the proc +again with another syscall by using this var again\&. When the process +exits, it\&'s exit code will be stored here\&. +.in -17m +.in -8m +.ZI 8m "trap (:reason:) /trap_regex/" +\& +.br +traps faults from both FAULT statements +and program errors occurring anywhere in the preceding bracket-block\&. If +no fault exists, TRAP does a SKIP to end of block\&. If there is a fault +and the fault reason string matches the trap_regex, the fault is trapped, +and execution continues with the line after the TRAP, otherwise the fault +is passed up to the next surrounding trapped bracket block\&. + +.ZI 17m "(:reason:)" +the fault message that caused this FAULT\&. If it was a +user fault, this is the text the user supplied in the FAULT statement\&. +.in -17m +.ZI 17m "/trap_regex/" +the regex that determines what kind of faults this +TRAP will accept\&. Putting a wildcard here (e\&.g\&. /\&.*/ means that ALL +faults will be trapped here\&. +.in -17m +.in -8m +.ZI 8m "union (:out:) [:var1: :var2: \&.\&.\&.]" +\& +.br +makes :out: contain the union of +the data window segments that contains var1, var2\&.\&.\&. plus any intervening +text as well\&. Any ISOLATEd var is ignored\&. This is non-surgical, and +does not alter the data window +.in -8m +.ZI 8m "window (:w-var:) (:s-var:) /cut-regex/ /add-regex/" +\& +.br +window +slider\&. This deletes to and including the cut-regex from :var: (default: +use the data window), then reads adds from std\&. input till add-regex +(inclusive)\&. + +.ZI 17m "" +flags can be any of + +.ZI 17m "" +ignore case when matching cut- and add- regexes +.in -17m +.ZI 17m "" +check input for add-regex every character +.in -17m +.ZI 17m "" +check input for add-regex every line +.in -17m +.ZI 17m "" +wait for EOF to check for add-regex (extra characters +are kept around for later) +.in -17m +.ZI 17m "" +read lots of input; the input is up to the regex +match OR the contents till EOF +.in -17m +.in -17m +.ZI 17m "(:w-var:)" +what var to window +.in -17m +.ZI 17m "(:s-var:)" +what var to use for source (defaults to stdin, if you +use a source var you \fBmust\fP specify the windowed var\&. +.in -17m +.ZI 17m "/cut-regex/" +var-expanded cut pattern +.in -17m +.ZI 17m "/add-regex/" +var-expanded add pattern, if absent reads till EOF +.in -17m +If both cut-regex and add-regex are omitted, and this window statement is +the \fIfirst executable\fP statement in the program, then CRM114 does +\fInot\fP wait to read a anything from standard input input before starting +program execution\&. +.in -8m +.SH A QUICK REGEX INTRO +A regex is a pattern match\&. Do a "man 7 regex" for details\&. + +Matches are, by default "first starting point that matches, then +longest match possible that can fit"\&. + +.ZI 8m "a through z" +\& +'in -8m +.ZI 8m "A through Z" +\& +'in -8m +.ZI 8m "0 through 9" +\& +'in -8m +'in +8m +\& +.br +all match themselves\&. +.in -8m +.ZI 8m "most punctuation" +\& +.br +matches itself, but check below! +.in -8m +.ZI 8m "*" +\& +.br +repeat preceding 0 or more times +.in -8m +.ZI 8m "+" +\& +.br +repeat preceding 1 or more times +.in -8m +.ZI 8m "?" +\& +.br +repeat preceding 0 or 1 time +.in -8m +.ZI 8m "*?, +?, ??" +\& +.br +repeat preceding, but \fIshortest\fP match that fits, given +the already-selected start point of the regex\&. (only +supported by TRE regex, not GNU regex) +.in -8m +.ZI 8m "[abcde]" +\& +.br +any one of the letters a, b, c, d, or e +.in -8m +.ZI 8m "[a-q]" +\& +.br +the letters a through q (just one of them) +.in -8m +.ZI 8m "{n,m}" +\& +.br +repetition count: match the preceding at least n and no more +than m times (POSIX restricts this to a maximum of 255 +repeats) +.in -8m +.ZI 8m "[[:<:]]" +\& +.br +matches at the start of a word (GNU regex only) +.in -8m +.ZI 8m "[[:>:]]" +\& +.br +matches the end of a word (GNU regex only) +.in -8m +.ZI 8m "^" +\& +.br +as first char of a match, matches the start of a line (ONLY in + matches\&. +.in -8m +.ZI 8m "$" +\& +.br +as last char of a match, matches at the end of a line (ONLY in + matches) +.in -8m +.ZI 8m "\&." +\& +.br +(a period) matches any single character (except start-of-line or +end of line "virtual characters", but it does match a newline)\&. +.in -8m +.ZI 8m "a|b" +\& +.br +match a or b +.in -8m +.ZI 8m "(match)" +\& +.br +the () go away, and the string that matched inside is +available for capturing\&. Use \e\e( and \e\e) to match actual +parenthesis (the first \&'\e\&' tells "show the second \&'\e\&' to +the regex engine, the second \&'\e\&' forces a literalization +onto the parenthesis character\&. +.in -8m +.ZI 8m "\en" +\& +.br +matches the N\&'th parenthesized subexpression\&. Remember to +backslash-escape the backslash (e\&.g\&. write this as \e\e1) +This is only if you\&'re using TRE, not GNU regex\&. +.in -8m +The following are other POSIX expressions, which mostly do what you\&'d +guess they\&'d do from their names\&. + +.di ZV +.in 0 +.nf \fC + + [[:alnum:]] + [[:alpha:]] + [[:blank:]] + [[:cntrl:]] + [[:digit:]] + [[:lower:]] + [[:upper:]] + [[:graph:]] + [[:print:]] + [[:punct:]] + [[:space:]] + [[:xdigit:]] +.fi \fR +.in +.di +.ne \n(dnu +.nf \fC +.ZV +.fi \fR + +[[:graph:]] matches any character that puts ink on paper or lights a pixel\&. +[[:print:]] matches any character that moves the "print head" or cursor\&. +.SH NOTES ON SEQUENCE OF EVALUTATION +By default, CRM114 supports string length and mathematical evaluation +only in an EVAL statement, although it can be set to allow these in +any place where a var-expanded variable is allowed (see the -q flag)\&. +The default value ( zero ) allows stringlength and math evaluation +only in EVAL statements, and uses non-precedence (that is, strict +left-to-right unless parenthesis are used) algebraic notation\&. -q 1 +uses RPN instead of algebraic, again allowing stringlength and math +evaluation only in EVAL expressions\&. Modes 2 and 3 allow stringlength +and math evaluation in \fIany\fP var-expanded expression, with +non-precedence algebraic notation and RPN notation respectively\&. +Evaluation is always left-to-right; there is no precedence of +operators beyond the sequential passes noted below\&. +The evaluation is done in four sequential passes: + +.ZI 3m "1" +\e-constants like \en, \eo377 and \ex3F are substituted +.in -3m +.ZI 3m "2" +:*:var: variables are substituted (note the difference between +a constant like \&'\en\&' and a variable like ":*:_nl:" here - constants +are substituted first, then variables are substituted\&.) +.in -3m +.ZI 3m "3" +:#:var: string-length operations are performed +.in -3m +.ZI 3m "4" +:@:expression: mathematical expressions are performed; syntax is +either RPN or non-precedenced (parens required) algebraic +notation\&. Embedded non-evaluated strings in a mathematical +expression is currently a no-no\&. + +Allowed operators are: + - * / % > < = only\&. + +Only >, <, and = set logical results; they also evaluate to +1 and 0 for continued chain operations - e\&.g\&. + +.di ZV +.in 0 +.nf \fC +((:*:a: > 3) + (:*:b: > 5) + (:*:c: > 9) > 2) +.fi \fR +.in +.di +.ne \n(dnu +.nf \fC +.ZV +.fi \fR + +is true IFF any of the following is true + +.ZI 3m "\(bu" +a > 3 and b > 5 +.in -3m +.ZI 3m "\(bu" +a > 3 and c > 9 +.in -3m +.ZI 3m "\(bu" +b > 5 and c > 9 +.in -3m +.in -3m +.SH NOTES ON APPROXIMATE REGEX MATCHING +Only the TRE engine supports approximate matching\&. The GNU engine does +not support approximate matching\&. + +Approximate matching is specified similarly to a "repetition count" in +a regular regex, using brackets\&. This approximation applies to the +previous parenthesized expression (again, just like repetion counts)\&. +You can specify maximum total changes, and how many inserts, deletes, +and substitutions you wish to allow\&. The minimum-error match is found +and reported, if it exists within the bounds you state\&. + +The basic syntax is: + +.di ZV +.in 0 +.nf \fC +(text-to-match){~[maxerrs] [#maxsubsts] [+maxinserts] [-maxdeletes]} +.fi \fR +.in +.di +.ne \n(dnu +.nf \fC +.ZV +.fi \fR + +Note that the \&'~\&' (with an optional maxerr count) is \fIrequired\fP (that\&'s how +we know it\&'s an approximate regex rather than just a rep-count); if you +don\&'t specify a max error count, you will get the best match, if you do, +the match will have at most that many errors\&. + +Remember that you specify the changes to the text in the \fIpattern\fP +necessary to make it match the text in the string being searched\&. + +You cannot use approximate regexes and backrefs (like \e1) in the same +regex\&. This is a limitation of in TRE at this point\&. + +You can also use an inequality in addition to the basic syntax above: + +.di ZV +.in 0 +.nf \fC +(text-to-match){~[maxerrs] [basic-syntax] [nI + mD + oS < K] } +.fi \fR +.in +.di +.ne \n(dnu +.nf \fC +.ZV +.fi \fR + +where n, m, and o are the costs per insertion, deletion, and substitution +respectively, \&'I\&', \&'D\&', and \&'S\&' are indicators to tell which cost goes +with which kind of error, and K is the total cost of the errors; the cost +of the errors is always strictly less than K\&. +Here are some examples\&. + +.ZI 8m "(foobar)" +\& +.br +exactly matches "foobar" +.in -8m +.ZI 8m "(foobar){~}" +\& +.br +finds the closest match to "foobar", with the minimum +number of inserts, deletes, and substitutions\&. Always succeeds\&. +.in -8m +.ZI 8m "(foobar){~3}" +\& +.br +finds the closest match to "foobar", with no more than +3 inserts, deletes, or substitutions +.in -8m +.ZI 8m "(foobar){~2 +2 -1 #1)" +\& +.br +find the closest match to "foobar", with at +most two errors total, and at most two inserts, one delete, and one +substitution\&. +.in -8m +.ZI 8m "(foobar){~4 #1 1i + 2d < 5 }" +\& +.br +find the closest match to "foobar", +with at most four errors total, at most one substitution, and with the +number of insertions plus 2x the number of deletions less than 5\&. +.in -8m +.ZI 8m "(foo){~1}(bar){~1)" +\& +.br +find the closest match to "foobar", with at +most one error in the "foo" and one error in the "bar"\&. +.in -8m +.SH OVERALL LANGUAGE NOTES +Here\&'s how to remember what goes where in the CRM114 language\&. + +Unlike most computer languages, CRM114 uses inflection (or declension) +rather than position to describe what role each part of a statement +plays\&. The declensions are marked by the delimiters- the /, ( and ), < +and >, and [ and ]\&. + +By and large, you can mix up the arguments to each kind of statement +without changing their meaning\&. Only the ACTION needs to be first\&. +Other parts of the statement can occur in any order, save that +multiple (paren_args) and /pattern_args/ must stay in their nominal +order but can go anywhere in the statement\&. They do not need to be +consecutive\&. + +The parts of a CRM114 statement are: + +.ZI 17m "ACTION" +the verb\&. This is at the start of the statement\&. +.in -17m +.ZI 17m "/pattern/" +the overall pattern the verb should use, analogous to the +"subject" of the statement\&. +.in -17m +.ZI 17m "" +modifies how the ACTION does the work\&. You\&'d call these +"adverbs" in human languages\&. +.in -17m +.ZI 17m "(vars)" +what variables to use as adjuncts in the action (what would +be called the "direct objects")\&. These can get changed when the action +happens\&. +.in -17m +.ZI 17m "[limited-to]" +where the action is allowed to take place (think of it +as the "indirect object")\&. These are not directly changed by the action\&. +.in -17m +.SH SEE ALSO +\fBcssmerge(1)\fP, \fBcssdiff(1)\fP, \fBcssutil(1)\fP + +The CRM114 homepage is at http://crm114\&.sf\&.net/ \&. +.SH VERSION +This manpage: $Id: crm114\&.azm,v 1\&.12 2004/08/19 11:10:49 vanbaal Exp $ + +This manpage describes the crm114 utility as it has been described by +QUICKREF\&.txt, shipped with crm114-20040212-BlameJetlag\&.src\&.tar\&.gz\&. The +DESCRIPTION section is copy-and-pasted from INTRO\&.txt as distributed with the +same source tarball\&. + +Converted from plain ascii to zoem by Joost van Baal\&. +.SH COPYRIGHT +Copyright (C) 2001, 2002, 2003, 2004 William S\&. Yerazunis + +This program is free software; you can redistribute it and/or modify +it under the terms of the GNU General Public License as published by +the Free Software Foundation; either version 2 of the License, or +(at your option) any later version\&. + +This program is distributed in the hope that it will be useful, +but WITHOUT ANY WARRANTY; without even the implied warranty of +MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE\&. See the +GNU General Public License for more details\&. + +You should have received a copy of the GNU General Public License +along with this program (see COPYING); if not, check with +http://www\&.gnu\&.org/copyleft/gpl\&.html or write to the Free Software +Foundation, Inc\&., 59 Temple Place - Suite 330, Boston, MA 02111, USA\&. +.SH AUTHOR +William S\&. Yerazunis\&. Manpage typesetting by Joost van Baal and Shalendra Chhabra --- crm114-20070810.orig/debian/install +++ crm114-20070810/debian/install @@ -0,0 +1 @@ +classifymail.crm mailfilter.cf mail*.crm rewriteutil.crm usr/share/crm114 --- crm114-20070810.orig/debian/compat +++ crm114-20070810/debian/compat @@ -0,0 +1 @@ +4 --- crm114-20070810.orig/debian/control +++ crm114-20070810/debian/control @@ -0,0 +1,28 @@ +Source: crm114 +Section: mail +Priority: optional +Maintainer: Milan Zamazal +Build-Depends: debhelper (>= 4.2), libtre-dev (>= 0.6.8) +Standards-Version: 3.7.2 + +Package: crm114 +Architecture: any +Depends: ${shlibs:Depends}, ${misc:Depends} +Recommends: metamail | mew-bin +Description: The Controllable Regex Mutilator and Spam Filter + CRM114 is a system to examine incoming e-mail, system log streams, data + files or other data streams, and to sort, filter, or alter the incoming + files or data streams according to whatever the user desires. Criteria for + categorization of data can be by satisfaction of regexes, by sparse binary + polynomial matching with a Bayesian Chain Rule evaluator, or by other means. + Accuracy of the SBPH/BCR classifier has been seen in excess of 99 per cent, + for 1/4 megabyte of learning text. In other words, CRM114 learns, and it + learns fast. + . + CRM114 is compatible with SpamAssassin or other spam-flagging software; it + can also be pipelined in front of or behind procmail. CRM114 is also useful + as a syslog or firewall log filter, to alert you to important events but + ignore the ones that aren't meaningful. + . + For mailfiltering you need to install metamail or mew-bin package to have + some tool to decode mime attachments. --- crm114-20070810.orig/debian/copyright +++ crm114-20070810/debian/copyright @@ -0,0 +1,26 @@ +This package was debianized by John Goerzen on +Tue, 21 Jan 2003 15:49:23 -0600. + +This package was redebianized by Ondřej Surý on +Sat, 21 Feb 2004 19:05:34 +0100. + +This package was redebianized again by Milan Zamazal in 2005. + +It was downloaded from http://crm114.sourceforge.net/ + +Upstream Author: Bill Yerazunis, wsy at users dot sourceforge dot net + +Copyright: + + Copyright 2001-2006 William S. Yerazunis, all rights reserved. + + This software is licensed to the public under the Free Software + Foundation's GNU GPL, version 2. You may obtain a copy of the + GPL by visiting the Free Software Foundations web site at + www.fsf.org, and a copy is included in this distribution. + + Other licenses may be negotiated; contact the + author for details. + +On Debian GNU/Linux systems, the complete text of the GNU General +Public License can be found in `/usr/share/common-licenses/GPL'. --- crm114-20070810.orig/debian/cssdiff.1 +++ crm114-20070810/debian/cssdiff.1 @@ -0,0 +1,104 @@ +.\" Copyright (c) 2004 William S\&. Yerazunis\&. Manpage typesetting by Joost van Baal and Shalendra Chhabra +.TH "cssdiff" 1 "19 Aug 2004" "cssdiff 20040816\&.BlameClockworkOrange-auto\&.3" "CRM114" +.po 2m +.de ZI +.\" Zoem Indent/Itemize macro I. +.br +'in +\\$1 +.nr xa 0 +.nr xa -\\$1 +.nr xb \\$1 +.nr xb -\\w'\\$2' +\h'|\\n(xau'\\$2\h'\\n(xbu'\\ +.. +.de ZJ +.br +.\" Zoem Indent/Itemize macro II. +'in +\\$1 +'in +\\$2 +.nr xa 0 +.nr xa -\\$2 +.nr xa -\\w'\\$3' +.nr xb \\$2 +\h'|\\n(xau'\\$3\h'\\n(xbu'\\ +.. +.if n .ll -2m +.am SH +.ie n .in 4m +.el .in 8m +.. +.SH NAME +\fBcssdiff\fP \- generate a difference summary of two \&.css files +.SH SYNOPSIS + +\fBcssdiff\fP +[cssfile 1] +[cssfile 2] +.SH WARNING +This man page is taken from an older CRM114 version. It is provided as a +convenience to Debian users and may not be up-to-date. If you would like to +update it, please send appropriate patches to the Debian bug tracking system. +.SH DESCRIPTION +\fBcssdiff\fP is a special-purpose utility to measure the distance +between the classes represented by cssfile1 and cssfile2\&. +The summary result output tells how many features were in each +of the \&.css files, how many features appeared in both (balanced overlap), +how many features appeared only in one (or unbalanced overlaps), and +how often the feature set of one \&.css file strictly dominated the +feature set of another \&.css file\&. +This set of metrics provides an intuitive way to determine the +similarity (or dissimilarity) of two classes represented as +\&.css files\&. +When using the CRM114 spamfilter, it can be used to find out how easy it will +be for CRM114 to differentiate spam from nonspam with your \&.css files\&. +\fBcssdiff\fP prints a report like e\&.g\&. + +.di ZV +.in 0 +.nf \fC + Sparse spectra file spam\&.css has 1048577 bins total + Sparse spectra file nonspam\&.css has 1048577 bins total + + File 1 total features : 1605968 + File 2 total features : 1045152 + + Similarities between files : 142039 + Differences between files : 1279964 + + File 1 dominates file 2 : 1463929 + File 2 dominates file 1 : 903113 +.fi \fR +.in +.di +.ne \n(dnu +.nf \fC +.ZV +.fi \fR + +Note that in this case there\&'s a big difference between the two files; in this +case there are about 10 times as many differences between the two files as +there are similarities\&. +.SH OPTIONS +There are no options to cssdiff\&. +.SH SHORTCOMINGS +Note that \fBcssdiff\fP as of version 20040816 is NOT capable of dealing +with the CRM114 Winnow classifier\&'s floating-point \&.cow files\&. Worse, +\fBcssdiff\fP is unaware of it\&'s shortcomings, and will try anyway\&. The only +recourse is to be aware of this issue and not use \fBcssdiff\fP on Winnow +classifier floating point \&.cow format files\&. +.SH HOMEPAGE AND REPORTING BUGS +http://crm114\&.sourceforge\&.net/ +.SH VERSION +This manpage: $Id: cssdiff\&.azm,v 1\&.5 2004/08/19 09:06:44 vanbaal Exp $ +This manpage describes cssdiff as shipped with crm114 version +20040816\&.BlameClockworkOrange\&. +.SH AUTHOR +William S\&. Yerazunis\&. Manpage typesetting by Joost van Baal and Shalendra Chhabra +.SH COPYRIGHT +Copyright (C) 2001, 2002, 2003, 2004 William S\&. Yerazunis\&. +This is free software, copyrighted under the FSF\&'s GPL\&. +There is NO warranty; not even for MERCHANTABILITY or FITNESS FOR A +PARTICULAR PURPOSE\&. See the file COPYING for more details\&. +.SH SEE ALSO +\fBcssutil(1)\fP, \fBcssmerge(1)\fP, +\fBcrm(1)\fP, \fBcssmerge(1)\fP --- crm114-20070810.orig/debian/cssutil.1 +++ crm114-20070810/debian/cssutil.1 @@ -0,0 +1,240 @@ +.\" Copyright (c) 2004 William S\&. Yerazunis\&. Manpage typesetting by Joost van Baal and Shalendra Chhabra +.TH "cssutil" 1 "19 Aug 2004" "cssutil 20040816\&.BlameClockworkOrange-auto\&.3" "CRM114" +.po 2m +.de ZI +.\" Zoem Indent/Itemize macro I. +.br +'in +\\$1 +.nr xa 0 +.nr xa -\\$1 +.nr xb \\$1 +.nr xb -\\w'\\$2' +\h'|\\n(xau'\\$2\h'\\n(xbu'\\ +.. +.de ZJ +.br +.\" Zoem Indent/Itemize macro II. +'in +\\$1 +'in +\\$2 +.nr xa 0 +.nr xa -\\$2 +.nr xa -\\w'\\$3' +.nr xb \\$2 +\h'|\\n(xau'\\$3\h'\\n(xbu'\\ +.. +.if n .ll -2m +.am SH +.ie n .in 4m +.el .in 8m +.. +.SH NAME +\fBcssutil\fP \- utility to measure and manipulate CRM114 statistics files\&. +.SH SYNOPSIS + +\fBcssutil\fP +[\&.css file] +[OPTIONS] +.SH WARNING +This man page is taken from an older CRM114 version. It is provided as a +convenience to Debian users and may not be up-to-date. If you would like to +update it, please send appropriate patches to the Debian bug tracking system. +.SH OPTIONS + +.ZI 3m "\fB-h\fP" +\& +.br +print basic help +.in -3m + +.ZI 3m "\fB-b\fP" +\& +.br +brief - print only a summary of the statistics of the +\&.css file (otherwise, prints a full list of how many bins are in each counter +state) +.in -3m + +.ZI 3m "\fB-q\fP" +\& +.br +quiet mode; no warning messages +.in -3m + +.ZI 3m "\fB-r\fP" +\& +.br +report then exit (no menu)\&. The default if -r is not +specified is to drop into a command-menu based system\&. +.in -3m + +.ZI 3m "\fB-s\fP" +\& +.br +if no css file found, create new one with this +many buckets\&. Default is 1 million + 1 buckets +.in -3m + +.ZI 3m "\fB-S\fP" +\& +.br +same as -s, but round up to next 2^n + 1 boundary\&. +.in -3m + +.ZI 3m "\fB-v\fP" +\& +.br +print version and exit +.in -3m + +.ZI 3m "\fB-D\fP" +\& +.br +dump css file to stdout in the architecture-independent +CSV format, suitable for reloading with -R in an architecture\&. (note that \&.css +files are a hardware-architecture dependent format) +.in -3m + +.ZI 3m "\fB-R\fP" +\& +.br +create and restore css from the +hardware-architecture independent CSV format file (reads from stdin if csv-file +is not supplied\&. +.in -3m +.SH THE COMMAND MENU +If -r is not supplied, a menu appears with the following options\&. Note that +all of these operations are "in place" and surgical- there is NO undo +functionality\&. Wise users will make a backup copy of all \&.css files before +using cssutil to alter values\&. + +.ZI 3m "\fB-Z\fP" +\& +.br +zero all bins at or below a value\&. This is useful for +deleting all small-count features from the \&.css statistics files leaving +higher-count features untouched\&. +.in -3m + +.ZI 3m "\fB-S\fP" +\& +.br +subtract a constant from all bins - this rolls all +features back a constant amount\&. +.in -3m + +.ZI 3m "\fB-D\fP" +\& +.br +divide all bins by a constant - this rolls features back +linearly, rather than in scalar fashion\&. +.in -3m + +.ZI 3m "\fB-R\fP" +\& +.br +rescan - regenerate the statistics output that was +initially printed\&. +.in -3m + +.ZI 3m "\fB-P\fP" +\& +.br +pack - re-slot features to optimize access time\&. +.in -3m + +.ZI 3m "\fB-Q\fP" +\& +.br +- gracefully exit, saving changes\&. (note that since these +operations are in-place and surgical, there is no option to exit without saving +changes\&. +.in -3m +.SH DESCRIPTION +\fBcssutil\fP is a general utility to manipulate and measure the \&.css format +statistics files used by CRM114\&'s Markovian and OSB classifiers\&. The biggest +uses are to check the available space remaining in a \&.css file, to selectively +groom a \&.css file, and to port architecture-dependent \&.css files to and from an +ASCII CSV format, which is architecture independent\&. +The \fBcssutil\fP program can be used to create information-less +\&.css files: + +.di ZV +.in 0 +.nf \fC + cssutil -b -r spam\&.css + cssutil -b -r nonspam\&.css +.fi \fR +.in +.di +.ne \n(dnu +.nf \fC +.ZV +.fi \fR + +\&. This creates the full-size files \&./spam\&.css and \&./nonspam\&.css, +holding no information\&. +The \fBcssutil\fP program can be used check that the \&.css files are reasonable\&. +Invoke \fBcssutil\fP as: + +.di ZV +.in 0 +.nf \fC + cssutil -b -r spam\&.css + cssutil -b -r nonspam\&.css +.fi \fR +.in +.di +.ne \n(dnu +.nf \fC +.ZV +.fi \fR + +You should get back a report something like this: + +.di ZV +.in 0 +.nf \fC + Sparse spectra file spam\&.css statistics: + + Total available buckets : 1048576 + Total buckets in use : 506987 + Total hashed datums in file : 1605968 + Average datums per bucket : 3\&.17 + Maximum length of overflow chain : 39 + Average length of overflow chain : 1\&.84 + Average packing density : 0\&.48 +.fi \fR +.in +.di +.ne \n(dnu +.nf \fC +.ZV +.fi \fR + +Note that the packing density is 0\&.48; this means that this \&.css file is about +half full of features\&. Once the packing density gets above about 0\&.9, you will +notice that CRM114 will take longer to process text\&. The penalty is small +below packing densities below about 0\&.95 and only about a factor of 2 at 0\&.97 \&. +Best is to keep it below \&.7 to \&.8\&. +.SH SHORTCOMINGS +Note that \fBcssutil\fP as of version 20040816 is NOT capable of dealing with the +CRM114 Winnow classifier\&'s floating-point \&.cow files\&. Worse, \fBcssutil\fP is +unaware of it\&'s shortcomings, and will try anyway\&. The only recourse is to be +aware of this issue and not use \fBcssutil\fP on a Winnow classifier floating point +\&.cow format file\&. +.SH HOMEPAGE AND REPORTING BUGS +http://crm114\&.sourceforge\&.net/ +.SH VERSION +This manpage: $Id: cssutil\&.azm,v 1\&.4 2004/08/19 09:23:24 vanbaal Exp $ +This manpage describes cssutil as shipped with crm114 version +20040816\&.BlameClockworkOrange\&. +.SH AUTHOR +William S\&. Yerazunis\&. Manpage typesetting by Joost van Baal and Shalendra Chhabra +.SH COPYRIGHT +Copyright (C) 2001, 2002, 2003, 2004 William S\&. Yerazunis\&. This is free +software, copyrighted under the FSF\&'s GPL\&. There is NO warranty; not even for +MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE\&. See the file COPYING for +more details\&. +.SH SEE ALSO +\fBcssmerge(1)\fP, \fBcssdiff(1)\fP, +\fBcrm(1)\fP --- crm114-20070810.orig/debian/dirs +++ crm114-20070810/debian/dirs @@ -0,0 +1,4 @@ +usr/bin +usr/share/crm114 +usr/share/doc/crm114/examples/tests +usr/share/emacs/site-lisp --- crm114-20070810.orig/debian/NEWS +++ crm114-20070810/debian/NEWS @@ -0,0 +1,46 @@ +crm114 (20070810-2) unstable; urgency=low + + crm114 20070810 introduces incompatibility of older .css files on 64-bit + architectures. If you use a 64-bit system, your current .css files will + stop working correctly after the upgrade. You need to recreate them from + scratch (possibly using your mailreaver cache). + + -- Milan Zamazal Wed, 22 Aug 2007 07:58:04 +0200 + +crm114 (20060704a-1) unstable; urgency=low + + New versions of the scripts in /usr/share/crm114/ require changes in the + configuration file mailfilter.cf. If you use your own configuration file + with the shared scripts then you must add new variables from the default + configuration file to your configuration. And next time you should use + copies of the *.crm scripts instead of using them directly to avoid similar + problems on the next upgrade. + + Some users have reported that this version of crm114 stopped working with + their *.css files and the *.css files had to be rebuilt from scratch. + + -- Milan Zamazal Fri, 14 Jul 2006 10:14:54 +0200 + +crm114 (20060118-1) unstable; urgency=low + + The default classification method has changed from Markovian to OSB. + If you use the default script and configuration files + /usr/share/crm114/mailfilter.crm and /usr/share/crm114/mailfilter.cf (which + is a bad idea anyway -- copy them the next time and use the copies + instead), either copy them before the upgrade and switch your mail + classifier to using the copies, or save your old .css files and retrain + CRM114 after the upgrade. See /usr/share/doc/crm114/README.gz for more + details. + + -- Milan Zamazal Tue, 7 Feb 2006 09:52:03 +0100 + +crm114 (20050415-1) unstable; urgency=low + + The package switched from the autoconfiscated version to the main + upstream CRM114 version. This means, among other changes, that the + main CRM114 binary is no longer called /usr/bin/crm114, it is called + /usr/bin/crm instead. If you or the users of your system used to use + the `crm114' name in their mail processing scripts, please update them + to use `crm'. + + -- Milan Zamazal Mon, 25 Apr 2005 12:07:15 +0200