arbitron program for news readership survey (see net.news.group)

[reid at decwrl.UUCP]

#! /bin/sh
# 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, 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 last
# 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 at decwrl
# 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
#
# 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.
#
# copied to a certain extent from the "subscribers"
# script posted by Blonder, McCreery, and Herron.
###########################################################################
# Configuration information. Edit this section to reflect your site data. #
TMPDIR=/tmp
NEWS=/usr/lib/news
SPOOL=/usr/spool/news

# Range of /etc/passwd UID's that represent actual people (rather than
# maintenance accounts or daemons or whatever)
lowUID=5
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: {ihnp4, decvax, ucbvax}!decwrl!netsurvey
# summarypath="netsurvey at decwrl.dec.com $USER"
summarypath="ihnp4!decwrl!netsurvey"

# We need to find the uucp name of your host

# BSD way to do it:
hostname=`(hostname || uuname -l) 2>&-`

# USG way to do it:
#hostname=`(uname -n || uuname -l ||  hostname) 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`

# # ###### Scheme #4 (provided by Lindsay Cleveland)
# # ###### (Same idea as #1, but excludes various junk accounts)
#awk -F: "\$3 >= $lowUID && \$3 <= $highUID{printf \"if test -d %s ; then echo %s;egrep : %s/.newsrc; fi\n\",\$6,\$1,\$6}" \
#	</etc/passwd | sh 2>/dev/null | awk  -f $tmpdir/arb.sel.$$ >$tmpdir/arb.tmp.$$
#nusers=`awk "BEGIN {N=0} NF == 1{N=N+1}END{print N}" <$tmpdir/arb.tmp.$$`
################################
#
# Set up awk scripts;  these are too large to pass as arguments on most
# systems.  This one picks out the lines referring to net.* and mod.*
# groups. It also eliminates lines that have
# colons but no article numbers on them (usually due to new groups that
# haven't been posted to yet). As a side effect, this script removes the
# first colon from each line, which makes life easier for later awk scripts.
#
cat > $TMPDIR/arb.sel.$$ << 'CAT'
/^net\..*: *[0-9].*$/	{ split($0,n,":"); print n[1], n[2] }
/^mod\..*: *[0-9].*$/	{ split($0,n,":"); print n[1], n[2] }
NF == 1	&& $1 ~ /^[a-z]*$/{ print $1 }
CAT
#
# This second awk script generates the actual output report.
# We use 'sed' to substitute in the shell variables to save ourselves
# endless hassle trying to find quoting/backslashing problems.
#
# The input to this script consists of three types of lines:
#
#	(1) Active-file lines.  These have four fields:  newsgroup name,
#	    first existing article, last article number, 'y' or 'n'
#	    to allow/disallow posting.
#			mod.mac 00001 00001 y
#	    These all come first, which is important.
#	(2) User names.  These have one field.
#			usenet
#	(3) .newsrc lines.  These have two fields:  the newsgroup name,
#	    and the articles-read information.  The latter can be
#	    arbitrarily complex.  It can also be arbitrarily long;
#	    this can potentially break either awk or sed, in which
#	    case the script will not work.
#			mod.map  1-199
#			mod.sources  1-337
#
#	The script uses the type 1 lines to build a table of newsgroups
#	and their active article ranges.  The .newsrc (type 3) lines are
#	then used to deduce which groups are being read by a user (a group
#	is being read if the last article seen is in that group's active
#	article range).  The user names are used to keep track of who reads
#	each group, which isn't all that useful but is interesting.  When
#	all input has been read, a report is printed summarizing the results.
#
sed  -e "s/NUSERS/$nusers/g" -e "s/HOSTNAME/$hostname/g" \
     -e "s/DATE/$dat/g" \
  > $TMPDIR/arb.fmt.$$ << 'DOG'
# makereport -- utility for "arbitron". Shamelessly copied from the
# similar script distributed with "subscribers.sh" by Blonder, McCreery, and
# Herron.
# 
BEGIN	{ rdrcount = 0 ; reader = "" ; grpcount = 0 ; realusers = 0}

# Active file line:  count newsgroups, record and cross-index group, and
# record first and last article numbers.  Set group's reader count and list
# to none.
NF == 4	{
	  grpcount++
	  grpname[grpcount] = $1
	  grpnumber[$1] = grpcount
	  grplast[grpcount] = $2
	  grpfirst[grpcount] = $3
	  grpcounts[grpcount] = 0
	  grpreaders[grpcount] = ""
	}
# User name.  Count readers, record and cross-index reader.
			# 1 field means it's a user name
NF == 1 { rdrcount++; rdrname[rdrcount] = $1; rdrnumber[$1] = rdrcount
	  reader = $1}

# .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.
			# 2 fields means it's a .newsrc line
NF == 2 { gnum = grpnumber[$1] 
	  n1 = split($2, n2, "-")
	  n3 = split(n2[n1], n4, ",")
	  lastread = n4[n3]
	  if (lastread >= grpfirst[gnum]) {
# To exclude groups with no traffic, use the next line instead of previous
# 	  if ((grpfirst[gnum] != grplast[gnum]) && (lastread >= grpfirst[gnum]) && (lastread <= grplast[gnum])) {
		  grpcounts[gnum]++
		  if (realuser[rdrcount] == 0) {
		      realuser[rdrcount]=1
		      realusers++
		  }
	  }
	} 

#	End of file.  Print the report in 2 columns.
END	{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")

	 for (i = 1;  i <= grpcount;  i++) {
	    if (grpcounts[i] > 0) {
		printf("%d %s\n",grpcounts[i], grpname[i])
	    }
	}
    }
DOG

cat >$TMPDIR/arb.pwd.$$ <<'MOUSE'
BEGIN {seen["/"]=1; seen[""] = 1;}
{if (seen[$6]!=1) {
		printf("if [ -r %s/.newsrc ] ; then ", $6)
		printf("echo %s; egrep : < %s/.newsrc ; fi\n", $1, $6)
		seen[$6]=1;
                  }
}
MOUSE
# First get the list of .newsrc files with duplicates and unreadable files
# removed.
awk -F: -f $TMPDIR/arb.pwd.$$ \
	</etc/passwd | \
	 sh | \
	 awk -f $TMPDIR/arb.sel.$$ >$TMPDIR/arb.tmp.$$
# Check to make sure that we found some

# but first, make sure we have an active file
if test X$NEWSHOST = X
then
ACTIVE=$NEWS/active
else
ACTIVE=/tmp/arb.active.$$
rcp $NEWSHOST:$NEWS/active $ACTIVE
fi

if test -s $TMPDIR/arb.tmp.$$
then
    # See if "active" file has 4 fields or only two (pre-2.10.2)
    set `grep '^net.announce' $ACTIVE | sed 1q`
    if test $# -eq 2 ; \
      then	egrep  '^net\.|^mod\.' $ACTIVE | \
	    while read group last ; \
	    do	dir=`echo "$group" | sed 's;\.;/;g'`; \
		    first=`ls $SPOOL/$dir | grep '^[0-9]*' | sort -n | sed 1q`; \
		    echo "$group $last ${first:-$last} X"; \
	    done ; \
      else	egrep '^net\.|^mod\.' $ACTIVE ; \
    fi | sort | \
	sort | \
	awk -f $TMPDIR/arb.fmt.$$ - $TMPDIR/arb.tmp.$$ | sort -nr | \
	grep -v '^$' | \
	sed -e 's/^999[0-9] //' | $destination
else
    echo Unable to find any readable .newsrc files 2>&1
    exit 1
fi