Shell Programming and Scripting

#!/bin/ksh
IAm=${0##*/}

InDir1='/home/cmccabe/Desktop/comparison/reference/10bp'
InDir2='/home/cmccabe/Desktop/comparison/validation/files'
OutDir='/home/cmccabe/Desktop/comparison/ref_val'

cd "$InDir1"
for file1 in *.txt
do	# Grab file prefix.
	p=${file1%%_*}

	# Find matching file2.
	file2=$(printf '%s' "$InDir2/$p"_*.vcf)
	if [ ! -f "$file2" ]
	then	printf '%s: No single file matching %s found.\n' "$IAm" \
		    "$file1" >&2
		continue
	fi

	# Create matching output filename.
	out=${file2##*/}
	out=${out%.vcf}_comparison.txt

	printf '%s\t%s\t%s\n' "$InDir1/$file1" "$file2" "$OutDir/$out"
done | awk '
BEGIN {	FS = OFS = "\t"
}
{	in1 = $1
	in2 = $2
	out = $3
	print "Reading from " in1
	while((getline < in1) == 1)
		f1[$2 OFS $4 OFS $5]
	close(in1)
	print "Reading from " in2
	while((getline < in2) == 1)
		f2[$2 OFS $4 OFS $5]
	close(in2)
	print "Writing to " out
	print "Match:" > out
	for(k in f1)
		if(k in f2) {
			print k > out
			delete f1[k]
			delete f2[k]
		}
	print "Missing in Reference but found in IDP:" > out
	for(k in f2) {
		print k > out
		delete f2[k]
	}
	print "Missing in IDP but found in Reference:" > out
	for(k in f1) {
		print k > out
		delete f1[k]
	}
	close(out)
	print "***"
}'