CPAN Algorithm::Diff method:

    time to compare same two files 1000 times:

    40.28 sec
    39.68 sec
    39.97 sec
    40.17 sec
    39.70 sec
    
    39.71 sec
    39.61 sec
    39.82 sec
    39.71 sec
    39.60 sec
    
    avg. = 39.83 sec

diffutils method:

    time to compare same two files 1000 times:
    
    11.68 sec
    11.72 sec
    11.63 sec
    11.69 sec
    11.78 sec
    
    11.62 sec
    11.62 sec
    11.78 sec
    11.66 sec
    11.62 sec
    
    avg. = 11.68 sec


##</code><code>##


CPAN Algorithm::Diff method:

    time to compare 105 file pairs, 10 times:
    
    926.7 sec
    924.2 sec
    
    time to compare 105 file pairs, 1 time:
    
    91.02 sec
    91.09 sec
    91.09 sec
    91.10 sec
    90.93 sec
    91.19 sec
    93.42 sec
    91.58 sec

    avg time for a single comparison of 105 file pairs:
    
    92.23 secs

diffutils method:

    time to compare 105 file pairs, 10 times:
    
    16.76 sec
    16.65 sec
    16.67 sec
    16.68 sec
    16.85 sec
    
    16.71 sec
    16.72 sec
    16.80 sec
    16.92 sec
    16.84 sec
    
    avg. time for single comparison of 105 file pairs:
    
    1.676 secs


##</code><code>##


repeatedly compare same two files 1000 times:

    average times:
    
    Algorithm::Diff    39.83  sec
    diffutils          11.68  sec

compare 105 different pairs of files 1 time:

    average times:
    
    Algorithm::Diff    92.23  sec
    diffutils           1.676 sec


##</code><code>##


## this is the framework:  
## One of the two code snippets below are
## substituted for ### DIFF ALGORITHM HERE..

#!/usr/bin/perl

use strict;
use lib "/Users/allasso/AWS/utility/cpan/lib/perl5/site_perl";
require Algorithm::Diff;
use Time::HiRes qw( time );

my($source_path_1, $source_path_2) = @ARGV;

my $holdRS = $/;
local $/;
if (! open(FH, $source_path_1)) {
    print "unable to open source file 1: $source_path_1\n";
}
my $filestring_1 = <FH>;
$/ = $holdRS;
close(FH);

$holdRS = $/;
local $/;
if (! open(FH, $source_path_2)) {
    print "unable to open source file 2: $source_path_2\n";
}
my $filestring_2 = <FH>;
$/ = $holdRS;
close(FH);

$filestring_1 =~ s@\s+@\n@g;
$filestring_2 =~ s@\s+@\n@g;

my $time = time();

for my $count (0..999) {
    
   ### DIFF ALGORITHM HERE..

}

my $time_4sig = time() - $time + .005;
$time_4sig =~ s@^(.....).*@$1@;
print STDERR "\n\net:  ".$time_4sig."\n";

exit;
    

## this is the CPAN Algorithm::Diff code:

    my @seq1 = split(/\n/, $filestring_1);
    my @seq2 = split(/\n/, $filestring_2);

    my $diff = Algorithm::Diff->new( \@seq1, \@seq2 );
    
    $diff->Base( 1 );   # Return line numbers, not indices
    while(  $diff->Next()  ) {
        next   if  $diff->Same();
        my $sep = '';
        if(  ! $diff->Items(2)  ) {
            printf "%d,%dd%d\n",
                $diff->Get(qw( Min1 Max1 Max2 ));
        } elsif(  ! $diff->Items(1)  ) {
            printf "%da%d,%d\n",
                $diff->Get(qw( Max1 Min2 Max2 ));
        } else {
            $sep = "\n---\n";
            printf "%d,%dc%d,%d\n",
                $diff->Get(qw( Min1 Max1 Min2 Max2 ));
        }
        print "< $_"   for  $diff->Items(1);
        print $sep;
        print "> $_\n"   for  $diff->Items(2);
    }


## this is the diffutils code:

    if (! open(FH, ">/tmp/diff_774885959483_1")) {
        print "unable to open temporary file\n";
    }
    print FH "$filestring_1";
    close (FH);
    
    if (! open(FH, ">/tmp/diff_774885959483_2")) {
        print "unable to open temporary file\n";
    }
    print FH "$filestring_2";
    close (FH);
    
    print "$source_path_1  :::  $source_path_2\n";

    print `diff --suppress-common-lines -y /tmp/diff_774885959483_1 /tmp/diff_774885959483_2`;
    

##</code><code>##


#!/usr/bin/perl

use strict;
use lib "/Users/allasso/AWS/utility/cpan/lib/perl5/site_perl";
require Algorithm::Diff;
use Time::HiRes qw( time );

my($source_path_1, $source_path_2) = @ARGV;

$source_path_1 =~ s@\x2f*$@@;
$source_path_2 =~ s@\x2f*$@@;

my @src_list_1 = `find $source_path_1 -name "*.htm*"`;
my @src_list_2 = `find $source_path_2 -name "*.htm*"`;

my $time = time();

for my $count (0..9) {
    
    my $list_cnt = 0;
    
    for my $file_src_1 (@src_list_1) {
    
        my $file_src_2 = $src_list_2[$list_cnt++];
       
        chomp $file_src_1;
        chomp $file_src_2;
    
        my $holdRS = $/;
        local $/;
        if (! open(FH, $file_src_1)) {
            print "unable to open source file 1: $file_src_1\n";
        }
        my $filestring_1 = <FH>;
        $/ = $holdRS;
        close(FH);
        
        $holdRS = $/;
        local $/;
        if (! open(FH, $file_src_2)) {
            print "unable to open source file 2: $file_src_2\n";
        }
        my $filestring_2 = <FH>;
        $/ = $holdRS;
        close(FH);
        
        $filestring_1 =~ s@\s+@\n@g;
        $filestring_2 =~ s@\s+@\n@g;
    
        ### DIFF ALGORITHM HERE..

    }
}

my $time_4sig = time() - $time + .005;
$time_4sig =~ s@^(.....).*@$1@;
print STDERR "\n\net:  ".$time_4sig."\n";

exit;


##</code><code>##


## full recursive script using CPAN Algorithm::Diff :

#!/usr/bin/perl

use strict;
use lib "/Users/allasso/AWS/utility/cpan/lib/perl5/site_perl";
require Algorithm::Diff;
use Time::HiRes qw( time );

my($source_path_1, $source_path_2) = @ARGV;

$source_path_1 =~ s@\x2f*$@@;
$source_path_2 =~ s@\x2f*$@@;

my @src_list_1 = `find $source_path_1 -name "*.htm*"`;
my @src_list_2 = `find $source_path_2 -name "*.htm*"`;

my $time = time();

for my $count (0..9) {
    
    my $list_cnt = 0;
    
    for my $file_src_1 (@src_list_1) {
    
        my $file_src_2 = $src_list_2[$list_cnt++];
       
        chomp $file_src_1;
        chomp $file_src_2;
    
        my $holdRS = $/;
        local $/;
        if (! open(FH, $file_src_1)) {
            print "unable to open source file 1: $file_src_1\n";
        }
        my $filestring_1 = <FH>;
        $/ = $holdRS;
        close(FH);
        
        $holdRS = $/;
        local $/;
        if (! open(FH, $file_src_2)) {
            print "unable to open source file 2: $file_src_2\n";
        }
        my $filestring_2 = <FH>;
        $/ = $holdRS;
        close(FH);
        
        $filestring_1 =~ s@\s+@\n@g;
        $filestring_2 =~ s@\s+@\n@g;
        
            ## begin CPAN algorithm:
    
            my @seq1 = split(/\n/, $filestring_1);
            my @seq2 = split(/\n/, $filestring_2);
        
            my $diff = Algorithm::Diff->new( \@seq1, \@seq2 );
            
            $diff->Base( 1 );   # Return line numbers, not indices
            while(  $diff->Next()  ) {
                next   if  $diff->Same();
                my $sep = '';
                if(  ! $diff->Items(2)  ) {
                    printf "%d,%dd%d\n",
                        $diff->Get(qw( Min1 Max1 Max2 ));
                } elsif(  ! $diff->Items(1)  ) {
                    printf "%da%d,%d\n",
                        $diff->Get(qw( Max1 Min2 Max2 ));
                } else {
                    $sep = "\n---\n";
                    printf "%d,%dc%d,%d\n",
                        $diff->Get(qw( Min1 Max1 Min2 Max2 ));
                }
                print "< $_"   for  $diff->Items(1);
                print $sep;
                print "> $_\n"   for  $diff->Items(2);
            }
            
            ## end CPAN algorithm
    }
}

my $time_4sig = time() - $time + .005;
$time_4sig =~ s@^(.....).*@$1@;
print STDERR "\n\net:  ".$time_4sig."\n";

exit;
        

## full recursive script using diffutils :

#!/usr/bin/perl

use strict;
use lib "/Users/allasso/AWS/utility/cpan/lib/perl5/site_perl";
require Algorithm::Diff;
use Time::HiRes qw( time );

my($source_path_1, $source_path_2) = @ARGV;

$source_path_1 =~ s@\x2f*$@@;
$source_path_2 =~ s@\x2f*$@@;

my @src_list_1 = `find $source_path_1 -name "*.htm*"`;
my @src_list_2 = `find $source_path_2 -name "*.htm*"`;

my $time = time();

for my $count (0..9) {
    
    my $list_cnt = 0;
    
    for my $file_src_1 (@src_list_1) {
    
        my $file_src_2 = $src_list_2[$list_cnt++];
       
        chomp $file_src_1;
        chomp $file_src_2;
    
        my $holdRS = $/;
        local $/;
        if (! open(FH, $file_src_1)) {
            print "unable to open source file 1: $file_src_1\n";
        }
        my $filestring_1 = <FH>;
        $/ = $holdRS;
        close(FH);
        
        $holdRS = $/;
        local $/;
        if (! open(FH, $file_src_2)) {
            print "unable to open source file 2: $file_src_2\n";
        }
        my $filestring_2 = <FH>;
        $/ = $holdRS;
        close(FH);
        
        $filestring_1 =~ s@\s+@\n@g;
        $filestring_2 =~ s@\s+@\n@g;
    
            ## begin diffutils algorithm:
    
            if (! open(FH, ">/tmp/diff_774885959483_1")) {
                print "unable to open temporary file\n";
            }
            print FH "$filestring_1";
            close (FH);
            
            if (! open(FH, ">/tmp/diff_774885959483_2")) {
                print "unable to open temporary file\n";
            }
            print FH "$filestring_2";
            close (FH);
            
            #print "$file_src_1  :::  $file_src_1\n";
        
            print `diff --suppress-common-lines -y /tmp/diff_774885959483_1 /tmp/diff_774885959483_2`;
            
            ## end diffutils algorithm
    }
}

my $time_4sig = time() - $time + .005;
$time_4sig =~ s@^(.....).*@$1@;
print STDERR "\n\net:  ".$time_4sig."\n";

exit;