Shell Programming and Scripting

#!/bin/bash
# write headers to the files for readability.
# Remove or comment these 3 lines and uncomment the 3 others if you don't want headers
echo -e "\n-----------\nshared\n" > shared
echo -e "\n-----------\nunique1\n" > unique1
echo -e "\n-----------\nunique2\n" > unique2
# :>shared
# :>unique1
# :>unique2

while read P1
do
   read S
   P2=$(grep -wB1 "$S" file2 | head -n1)
   if [ -n "$P2" ]
   then	echo -e ">File 1 ${P1#>}; File2 ${P2#>}\n$S" >> shared
   else echo -e "$P1\n$S" >> unique1
   fi
done < file1

while read P2
do
   read S
   grep -qw "$S" file1 || echo -e "$P2\n$S" >> unique2
done < file2

cat shared unique1 unique2 # to display the generated files

#!/usr/bin/env bash

# @(#) s1	Demonstrate sequence matching.

# Utility functions: print-as-echo, print-line-with-visual-space.
pe() { for i;do printf "%s" "$i";done; printf "\n"; }
pl() { pe;pe "-----" ;pe "$*"; }

FILE1=data1
FILE2=data2

# Remove debris from previous runs.
rm -f t1 t2 t3 shared uniq_1 uniq_2

# Paste lines together in both files, add source file indicator.
paste - - < $FILE1 |
sed "s/^/1 /" > t1
paste - - < $FILE2 |
sed "s/^/2 /" > t2

# Join the files based on sequence.
join -a 1 -a 2 -j 3 t1 t2 > t3

# Comb and distibute results.
awk '
NF > 3	{ print > "shared" ; next }
$2 == 1	{ print > "uniq_1" ; next }
$2 == 2	{ print > "uniq_2" ; next }
' t3

pl " Shared sequences:"
cat shared

pl " Sequences unique to file 1:"
cat uniq_1

pl " Sequences unique to file 2:"
cat uniq_2

exit 0

% ./s1

-----
 Shared sequences:
TTGATGTCGTGGGTTTCCCG 1 >Pat1_s60_c01_T400_s30_c08_10_3845 2 >Pat1_s60_c01_T400_s30_c08_1_3845
TTGATGTGCCAGTTTCCCGT 1 >Pat1_s60_c01_T400_s30_c08_23_28 2 >Pat1_s60_c01_T400_s30_c08_3_28

-----
 Sequences unique to file 1:
TAGATGTGCCCGTGGGTTTC 1 >Pat1_s60_c01_T400_s30_c08_0_1610
TTGATGTGTCCCGTCGACAC 1 >Pat1_s60_c01_T400_s30_c08_33_2588

-----
 Sequences unique to file 2:
TAGATGTGCCCGTGGGTTAC 2 >Pat1_s60_c01_T400_s30_c08_0_1610
TTGATGTGTCCCGTCGACGC 2 >Pat1_s60_c01_T400_s30_c08_53_2588