Code to identify data files that Stata loads or saves

stata_files_used.pl

#!/usr/bin/env perl
# Get do file
@lines = <STDIN>;

# Get files used
foreach my $line (@lines) {
    if ($line =~ /(?:use|(?:merge|joinby).*using)\s+"?(\w+)/) {
        push @stata_files, $1;
    }
}
    
my %hash   = map { $_ => 1 } @stata_files;
my @unique = keys %hash;    
  
print "**Files used**:\n";
foreach my $stata_file (sort @unique) {
    print "$stata_file\n";
}

# Get files saved
foreach my $line (@lines) {
    if ($line =~ /(?:save|saveold)\s+(\w+)/) {
        # print($line);
        push @stata_files_saved, $1;
    }
}

my %hash   = map { $_ => 1 } @stata_files_saved;
my @unique = keys %hash;    
  
print "\n**Files created**:\n";
foreach my $stata_file (sort @unique) {
    print "$stata_file\n";
}