news@becker.UUCP (UseNet News) (07/20/89)
I have decided to post a revised version of
"arbitron" for News statistics gathering due to
the recent discussion about "unix-pc" and other
groups being under-reported due to bugs in the
script.
--------- 8< --------- 8< --------- 8< --------- 8< --------- 8< ---------
#! /bin/sh
# @(#)arbitron 2.4.3 Mon Jun 5 05:03:55 EDT 1989
# arbitron -- this program produces rating sweeps for USENET.
#
# Usage: arbitron
#
# To use this program, edit the "configuration" section below so that the
# information is correct for your site, and then run it. It will produce a
# readership survey for your machine and mail that survey to decwrl.dec.com,
# with a cc to you.
#
# To participate in the international monthly ratings sweeps,
# run "arbitron" every month. I will run the statistics program on the first
# day of each month; it will include any report that has reached it by that
# time. To make sure your site's data is included, run the survey program no
# later than the 20th day of each month.
#
# Brian Reid, DEC Western Research Lab, reid@decwrl.dec.com
# Updated and bugfixed by
# Spencer Thomas, U.of Utah
# Geoff Kuenning, SAH Consulting
# Updated to work with 2.10.1 and older news systems by
# Lindsay Cleveland, AT&T Technologies/Bell Labs
# Made to work with 16-bit address spaces by
# Andy Walker, Maths Dept., University of Nottingham, UK
# Nagging Bourne shell bug fixed by
# Tom Donahue, Rabbit Software Corp
# Newsgroup inclusion bug fix by
# Bruce Becker, G.T.S.
#
# Note that the results of this program are dependent on the rate at which
# you expire news. If you are a small site that expires news rapidly, the
# results may indicate fewer active readers than you actually have.
#
###########################################################################
# Configuration information. Edit this section to reflect your site data. #
TMPDIR=/tmp
NEWS=/usr/lib/news
SPOOL=/usr/spool/news
# Make a crude stab at determining the system type. If your installation has
# only one type of system, you can edit out the "if" statement and just turn
# this into an assignment statement of the correct value.
if [ -d /usr/ucb ]; then
STYPE="bsd"
else
STYPE="usg"
fi
# Range of /etc/passwd UID's that represent actual people (rather than
# maintenance accounts or daemons or whatever)
lowUID=100
highUID=9999
# If you aren't running a distributed news system (nntpd & rrn, usually),
# leave NEWSHOST blank. Else set it to the name of the host from which you
# can rcp a copy of the active file.
NEWSHOST=
# uucp path: {sun, hplabs, pyramid, decvax, ucbvax}!decwrl!netsurvey
summarypath="netsurvey@decwrl.dec.com $USER"
# We need to find the uucp name of your host. If this code doesn't work,
# then just put it in literally like this:
# hostname="ihnp4"
case $STYPE in
bsd) cmd='hostname || uuname -l';;
sysv) cmd='uname -n || uuname -l || hostname';;
*) cmd='uuname -l';;
esac
hostname=`sh -c "$cmd" 2>&-`
PATH=$NEWS:/usr/local/bin:/usr/ucb:/usr/bin:/bin
############################################################################
export PATH
# ---------------------------------------------------------------------------
trap "rm -f $TMPDIR/arb.*.$$; exit" 0 1 2 3 15
set `date`
dat="$2$6"
destination="${MAILER-mail} $summarypath"
################################
# Here are several expressions, each of which figures out approximately how
# many people use this machine. Comment out all but 1 of them; pick the one
# you like best. Initially the most universal but least reliable of them is
# uncommented.
# # ###### Scheme #1: fast but usually returns too big a number
nusers=`awk -F: '
BEGIN { N = 0 }
$3 >= '"$lowUID"' && $3 <= '"$highUID"' { N = N + 1 }
END { print N }' </etc/passwd`
# # ###### Scheme #2 (works with BSD systems)
#nusers=`last | sort -u +0 -1 | wc -l`
# # ###### Scheme #3 (works with USG systems)
#nusers=`who /etc/wtmp | sort -u +0 -1 | wc -l`
################################
#
# Set up awk scripts; these are too large to pass as arguments on most
# systems.
#
# This awk script generates the actual output report.
# We use 'sed' to substitute in the shell variables to save ourselves
# endless hassle trying to find quoting/backslashing problems.
#
# The input to this script consists of two types of lines (pre-sorted):
#
# (1) Active-file lines. These have four fields: newsgroup name,
# first existing article, last article number, 'y' or 'n'
# to allow/disallow posting.
# mod.mac 00001 00001 y
#
# (2) .newsrc-derived lines. These have three fields: the newsgroup
# name, the user name and the articles-read information. The latter
# can be arbitrarily complex. It can also be arbitrarily long;
# this can potentially break either awk or sed, in which
# case the script will not work.
# mod.map joe 1-199
#
# The script uses the type 1 lines to define the newsgroups
# and their active article ranges. The .newsrc (type 2) lines are
# then used to deduce which users are reading that group (a group
# is being read if the last article seen is in that group's active
# article range).
#
sed "/^#/d
s/NUSERS/$nusers/g
s/HOSTNAME/$hostname/g
s/DATE/$dat/g" > $TMPDIR/arb.fmt.$$ << 'DOG'
# makereport -- utility for "arbitron". Early versions were copied from a
# similar script distributed with "subscribers.sh" by Blonder, McCreery, and
# Herron.
#
BEGIN {
grpcount = 0
realusers = 0
}
#
# Active file line: dispose of previous group (if any), record group, and
# record first and last article numbers. Set group's reader count to none.
NF == 4 {
if (grpname != "") {
printf("%d %s\n", grpcount, grpname)
}
grpname = $1
grpfirst = $3
grplast = $2
grpcount = 0
}
#
# .newsrc line. Break out the final number, which is the last article that
# has actually been read. This is a pretty good indicator of the person's
# true interest in the group. If 'lastread' for the group is a current
# (unexpired) article, record a reader for that group. Finally, record
# the user as a "real" user of the news system.
#
NF == 3 {
if ($1 != grpname) next;
n1 = split($3, n2, "-")
n3 = split(n2[n1], n4, ",")
lastread = n4[n3]
if ((grpfirst != grplast) && (lastread >= grpfirst) && \
(lastread <= grplast)) {
grpcount++
if (realuser[$2] != 1) {
realuser[$2] = 1
realusers++
}
}
}
#
# End of file. Print the report in 2 columns.
END {
# For reorganized network, report a group even if nobody reads it.
# This will help us keep track of where the groups propagate.
if (grpname != "") {
printf("%d %s\n", grpcount, grpname)
}
printf("9999 Host\t\t%s\n", "HOSTNAME")
printf("9998 Users\t\t%d\n", NUSERS)
printf("9997 NetReaders\t%d\n", realusers)
printf("9996 ReportDate\t%s\n", "DATE")
printf("9995 SystemType\tnews-arbitron-2.4.3\n")
}
DOG
cat >$TMPDIR/arb.pwd.$$ <<'MOUSE'
BEGIN {
seen["/"] = 1
seen[""] = 1
}
{
if (seen[$6] != 1) {
printf("if [ -r %s/.newsrc ] ; then ", $6)
printf("sed -n '/: [0-9]/s/:/ %s/p' <%s/.newsrc; fi\n", $1, $6)
seen[$6] = 1
}
}
MOUSE
# First, make sure we have an active file
if [ -z "$NEWSHOST" ]; then
ACTIVE=$NEWS/active
else
ACTIVE=/tmp/arb.active.$$
rcp $NEWSHOST:$NEWS/active $ACTIVE
fi
if [ ! -s $ACTIVE ]; then
echo arbitron: ACTIVE file missing or empty. Cannot continue.
exit 1
fi
# Next, get the list of .newsrc files with duplicates and unreadable files
# removed.
awk -F: -f $TMPDIR/arb.pwd.$$ </etc/passwd | sh >$TMPDIR/arb.tmp.$$
# Check to make sure that we found some
if [ -s $TMPDIR/arb.tmp.$$ ]; then
# See if "active" file has 4 fields or only two (pre-2.10.2)
set `sed 1q < $ACTIVE`
if [ $# -eq 2 ]; then
egrep '^[a-z][-0-9_a-z]*\.' $ACTIVE |
while read group last; do
dir=`echo "$group" | sed 's;\.;/;g'`
first=`ls $SPOOL/$dir | grep '^[0-9]*' | sort -n | sed 1q`
case $STYPE in
usg) echo "$group $last ${first:-$last} X";;
*) echo "$group $last ${first-$last} X";;
esac
done
else
egrep '^[a-z][-0-9_a-z]*\.' $ACTIVE
fi |
sort - $TMPDIR/arb.tmp.$$ |
awk -f $TMPDIR/arb.fmt.$$ |
sort -nr |
sed '/^$/d
/^[0-9]* to\./d
s/^999[0-9] //' |
$destination
else
echo Unable to find any readable .newsrc files 2>&1
exit 1
fi
--------- 8< --------- 8< --------- 8< --------- 8< --------- 8< ---------
Cheers,
--
Bruce Becker Toronto, Ont.
Internet: news@becker.UUCP UUCP: ...!uunet!mnetor!becker!news
"'Comefrom' considered useful" - the Anti-Dijkstraepsilon@wet.UUCP (Eric P. Scott) (07/23/89)
I'll be happy to run this ... once Brian Reid endorses it. I'm not about to "break" his assumptions. -=EPS=-