Если файлы удобно помещаются в памяти, это легко сделать с помощью хэшей в Perl. Например:
#!/bin/bash
# create test data files
>cmp.d1 cat <<'EOD'
abc 234 123
bcd 567 890
cde 678 789
EOD
>cmp.d2 cat <<'EOD'
abc 234 012
bcd 532 890
cdf 678 789
EOD
# create script
>dif.pl cat <<'EOD'
#!/usr/bin/perl -w
if ( $#ARGV!=0 or ! -f "$ARGV[0]" ) {
die "Usage: <file2 filter file1\n";
}
@KEYS = ( 0 ); # list of columns to use for primary key
# read file1 from filename given on commandline
while (<<>>) {
chomp;
@a1 = (split); # split line into individual fields
$k = join "\0", @a1[ @KEYS ];
# if $k is not unique, only final line is kept
warn "duplicate key: $k\n" if exists $h1{$k};
# store line in %h1 for later use
$h1{$k} = [ @a1 ];
}
# now read file2 from stdin
# process each line as we read it
while (<<>>) {
chomp;
@a2 = (split); # split line into individual fields
$k = join "\0", @a2[ @KEYS ];
if ( exists $h1{$k} ) {
# record exists in both files
# calculate differences
@a1 = @{ $h1{$k} }; # retrieve file1 version
# overwrite any difference fields in @a2
map {
$a1 = shift @a1;
$_ = "${a1}::$_" if $a1 ne $_;
} @a2;
# save difference records in %hd
$hd{$k} = [ @a2 ];
# this will not be an extra file1 record
delete $h1{$k};
}
else {
# this record only exists in file2
$h2{$k} = [ @a2 ];
}
}
# format record as csv line
sub print_csv {
print join(",", @{ $_ }), "\n";
}
print "differences file :\n";
print_csv for values %hd;
print "\n";
print "extra records in file1 :\n";
print_csv for values %h1;
print "\n";
print "extra records in file2\n";
print_csv for values %h2;
EOD
# try it out
perl dif.pl cmp.d1 <cmp.d2
Выход:
differences file :
bcd,567::532,890
abc,234,123::012
extra records in file1 :
cde,678,789
extra records in file2
cdf,678,789
Примечание: вывод csv обычно не нужно упорядочивать, поэтому этот код не выполняет никакой сортировки.