#!/usr/bin/env bash

# @(#) s2	Demonstrate solve problem of unique values with collection.

# Infrastructure details, environment, commands for forum posts. 
set +o nounset
LC_ALL=C ; LANG=C ; export LC_ALL LANG
echo ; echo "Environment: LC_ALL = $LC_ALL, LANG = $LANG"
echo "(Versions displayed with local utility \"version\")"
c=$( ps | grep $$ | awk '{print $NF}' )
version >/dev/null 2>&1 && s=$(_eat $0 $1) || s=""
[ "$c" = "$s" ] && p="$s" || p="$c"
version >/dev/null 2>&1 && version "=o" $p awk
# set -o nounset

rm -f t1 t2
for file in data*
do
  sed "s/$/\t$file/" $file >> t1
done

echo
echo " Sample at beginning & end of $( wc -l < t1) lines in combined data file:"
head -3 t1
echo ...
tail -3 t1

echo
echo " Collector script:"
cat collect

echo
echo " Results for lines with 2 fields:"
sort t1 |
./collect |
tee t2 |
awk ' NF == 2 '

echo
echo " Intermediate file from awk collector script:"
cat t2

exit 0

% ./s2

Environment: LC_ALL = C, LANG = C
(Versions displayed with local utility "version")
OS, ker|rel, machine: Linux, 2.6.26-2-amd64, x86_64
Distribution        : Debian GNU/Linux 5.0 
GNU bash 3.2.39
GNU Awk 3.1.5

 Sample at beginning & end of 10 lines in combined data file:
a	data1
b	data1
c	data1
...
a	data3
c	data3
h	data3

 Collector script:
#!/usr/bin/env sh

# @(#) collect	Demonstrate collection script, awk.

FILE="$1"

# Use nawk or /usr/xpg4/bin/awk on Solaris.

awk '
BEGIN	{ FS = OFS = "\t" ; previous = "" ; line = "" ; first = "true"}
first == "true" { first = "false" ; previous = $1 ; line = $0 ; next }
$1 == previous	{ line = line "\t" $2 ; next }
		{ print line ; previous = $1 ; line = $0 }
END	{ print line }
' $FILE

exit 0

 Results for lines with 2 fields:
d	data1
h	data3
t	data2

 Intermediate file from awk collector script:
a	data1	data2	data3
b	data1	data2
c	data1	data3
d	data1
h	data3
t	data2