Path: utzoo!utgpu!attcan!uunet!lll-winken!lll-lcc!ames!mailrus!tut.cis.ohio-state.edu!rutgers!apple!fair
From: fair@Apple.COM (Erik E. Fair)
Newsgroups: comp.mail.misc
Subject: Re: Getting the most out of pathalias
Summary: mkglue script (part 2 of 4)
Message-ID: <23432@apple.Apple.COM>
Date: 6 Jan 89 08:21:14 GMT
References: <601@ur-cc.UUCP>
Organization: USENET Protocol Police, Western Gateway Division
Lines: 179

#!/bin/awk -f
# MKGLUE: UUCP map post processor
# Idea from Mel Pleasant via Eliot Lear
# Erik E. Fair <fair@apple.com>, August, 1988
#
# What we have here is a UUCP map postprocessor. To use:
#	pathalias uucpmaps > /tmp/paths.raw
#	mkglue /tmp/paths.raw > /tmp/glue
#	pathalias uucpmaps /tmp/glue > /tmp/paths.refined
#	do whatever you do with the maps here
#
# what this does is find Internet EQUIVALENCES for UUCP sites, e.g.
#
#	ucbvax=	ucbvax.berkeley.edu
#	apple= apple.com
#
# and then it reverses them, and puts all the domain names it finds into
# a completely connected network called "INTERNET", with COST defined
# below. That cost was determined experimentally on a Cray X/MP-48
# (pathalias will run on such a beast. It takes only 24 seconds to
# process all the maps and the glue file. It's amazing what you can do
# with a supercomputer). Your milage may vary.
#
# The effect of this is to cause nearly all your paths to take their
# first hop through the Internet. DO NOT USE THIS POSTPROCESSOR, unless
# you're actually on the Internet, or you have multiple UUCP neighbors
# who are on the Internet of equivalent call cost to you.
#
# This script will NOT do anything with domain gateway declarations, e.g.
#
#	foo	.bar.com
#
# because these do not provide a mapping between the Internet name and
# the UUCP name of the UUCP host involved. This script makes no
# distinction between "real" Internet hosts and "fake" (MX'd) ones (how
# can I? The information isn't there). Even with an MX host, someone on
# the Internet is accepting mail for them (that's what MX is all about).
#
# Encourage your Internet friends and neighbors to put all the right
# information into the UUCP maps.
#
# Also, your mailer must be able to transform thusly:
#
#	do.main!foo!bar!bazz -> foo!bar!bazz@do.main
#
# since that's what the database will generate. I do it with sendmail,
# and I installed the uunet hacks to 5.59 sendmail to look stuff up in a
# DBM database. I expect that the IDA sendmail stuff can be similarly
# coerced to do this.
#
# If nothing else, you might find the report at the end of the glue file
# interesting.
#
BEGIN{
	COST = "DEMAND+LOW";
#
	domain["arpa"] = 1;
	domain["com"] = 1;	domain["gov"] = 1;
	domain["mil"] = 1;	domain["org"] = 1;
	domain["edu"] = 1;	domain["net"] = 1;
#
#	domain["ac"] = 1;	these aren't really real
#	domain["co"] = 1;
#	domain["gs"] = 1;
#	domain["or"] = 1;
#	domain["re"] = 1;
#
	domain["ar"] = 1;
	domain["at"] = 1;
	domain["au"] = 1;
	domain["ca"] = 1;
	domain["ch"] = 1;
	domain["cl"] = 1;
	domain["de"] = 1;
	domain["dk"] = 1;
	domain["du"] = 1;
	domain["es"] = 1;
	domain["fi"] = 1;
	domain["fr"] = 1;
	domain["il"] = 1;
	domain["is"] = 1;
	domain["jp"] = 1;
	domain["kr"] = 1;
	domain["my"] = 1;
	domain["nl"] = 1;
	domain["no"] = 1;
	domain["nz"] = 1;
	domain["pt"] = 1;
	domain["se"] = 1;
	domain["sg"] = 1;
	domain["uk"] = 1;
	domain["us"] = 1;

	nbad = 0;
	imon_inet = 0;
}

# ignore domain gateways (no clean mapping - we must know the internet name)
/^\./ {next}

$2 == "%s" {
# hopefully only one of these
	if ( $1 !~ /\./ ) {
		localuucpname = $1;
		next;
	}
}

# here's the meat of the matter - find real domains and reverse the
# equivalences so that pathalias will give us paths with internet
# names in them.
$1 ~ /\./ {
	hostname= $1;
	curbad = 0;
# check top of domain name for validity
	i = split(hostname, parts, ".");
	top = parts[i];
	if (domain[top] != 1) {
		printf("# bad domain - %s\n", hostname);
		badtop[top]++;
		nbad++;
		curbad = 1;
	} else domtop[top]++;
	n = split($2, path, "!");
	if (n > 1) {
		uucpname= path[n - 1];
		if (hostname == uucpname)
			next;
# skip two sided dot aliases
		i = split(uucpname, parts, ".");
		if (i < 2) {
			if (! curbad) {
				print hostname "=" uucpname;
				internet[hostname]++;
			}
		} else if (domain[parts[i]] == 1) {
			print uucpname "=" hostname;
			internet[uucpname]++;
		}
	} else if ($2 == "%s") {
		if (imon_inet && localuucpname != "" && !curbad) {
			print localinetname "=" localuucpname;
			internet[localinetname]++;
		}
		if (!curbad) {
			localinetname= $1;
			internet[localinetname]++;
			imon_inet++
		}
	}
}

# now create a completely connected network of the domain names,
# with a low cost, so that we mostly use the Internet in preference
# to any other path
END{
	if (imon_inet) {
		print localinetname "=" localuucpname;
	}
	print "INTERNET={"
	for(hostname in internet) {
		printf("\t%s,\n", hostname);
	}
	printf("\t}(%s)\n", COST);
#
# report on what we found while perusing the map data
#
	printf("# top level domains\n");
	for(top in domtop) {
		printf("#\t%s\t%d\n", top, domtop[top]);
	}
#
	if (nbad > 0) {
		printf("\n# unrecognized summary:\n");
		for(dom in badtop) {
			printf("#\t%s\t%d\n", dom, badtop[dom]);
		}
	}
}