#!/usr/bin/perl -w
# About the fairest comparison I could think of at the moment
use strict;
use Benchmark;

my $file = "tst1.txt";

open(OUT, ">$file") or die "Can't open $file for output: $!";
for ("000000".."020000") {
 print OUT "$_=abc|def|ghi|jkl\n";
 print OUT "Ignore this line\n";
}

open(FH1, $file) or die "1 Can't open $file: $!";
open(FH2, $file) or die "2 Can't open $file: $!";

timethese(1, {
 MAPIT=>\&map_it,
 LOOPIT=>\&loop_it,
});
close FH1;
close FH2;
sub map_it {
 my %author = map {/^\d{6}$/ ? $_ : [ split (/\|/, $_, 2 ]}
              map { split( /=/, $_, 2 ) }
              grep { /^\d{6}=[^|]+\|/ } <FH1>;
}

sub loop_it {
 my %author;
 while (<FH2>) {
  next unless /^(\d{6})=(.+)\|/;
  # Hmm, the above should really be:
  # next unless /^(\d{6})=([^|].*)\|/;
  # Whoops, forgot to limit the split to 2 elements here
  # No big deal, results are still similar
  $author{$1} = [ split(/\|/, $2) ];
 }
}

# interesting different results
#Under activestate perl
Benchmark: timing 1 iterations of LOOPIT, MAPIT...
    LOOPIT:  5 wallclock secs ( 4.62 usr +  0.00 sys =  4.62 CPU) @  0.22/s (n=
)
            (warning: too few iterations for a reliable count)
     MAPIT: 28 wallclock secs (28.73 usr +  0.00 sys = 28.73 CPU) @  0.03/s (n=
)
            (warning: too few iterations for a reliable count)

#under Cygwin perl
$ ./tst
Benchmark: timing 1 iterations of LOOPIT, MAPIT...
    LOOPIT:  4 wallclock secs ( 4.67 usr +  0.00 sys =  4.67 CPU) @  0.21/s (n=
)
            (warning: too few iterations for a reliable count)
     MAPIT:  5 wallclock secs ( 5.22 usr +  0.00 sys =  5.22 CPU) @  0.19/s (n=
)
            (warning: too few iterations for a reliable count)