Shell Programming and Scripting

awk -F \; 'NR==FNR{a[$1];next} !($1 in a)' flie1.txt file2.txt > missed_file1.txt

$ cat missing.sh

#!/bin/sh

FA="data1"
FB="data2"

# Create temp files data1.1/data2.1 containing only first column.
# This lets us feed it into the 'comm' utility, which produces
# output we can quickly and easily process in awk.
awk -v FS=";" '{ print $1 >FILENAME ".1" }' ${FA} ${FB}
comm ${FA}.1 ${FB}.1 |
        awk -v FA="${FA}" -v FB="${FB}" -f missing.awk

# Delete temporary files
rm -f ${FA}.1 ${FB}.1


$ cat missing.awk
# Two tabs means third column, $1 is a token common to both files
/^\t\t\047/     {
                        getline AS<FA;  split(AS, A, ";");
                        getline BS<FB;  split(BS, B, ";");

                        for(N=2; N<=3; N++)
                        if(A[N] != B[N])
                        printf("for %s field%d differs %s:%s %s:%s\n",
                                A[1], N, FA, A[N], FB, B[N]) > "common.txt"
                }
# One tab means second column, $1 is only found in FB
/^\t\047/       {       if(getline <FB) print > "missed_" FB       }
# No tabs means first column, $1 is only found in FA
/^\047/         {       if(getline <FA) print > "missed_" FA       }

$ ./missing.sh

$ cat missed_data1

'393200103059';'TIM';'20110111'
'393200103061';'TIM';'20060206'
'393200103064';'OPI';'20110623'

$ cat missed_data2

'393200103056';'TIM';'20110111'
'393200103088';'TIM';'20060206'

$ cat common.txt

for '393200103052' field2 differs data1:'H3G' data2:'HKG'

$