$ perl time_to_add_doc.plx
          s/iter   size_4M   size_2M   size_1M size_500k size_250k
size_4M     16.4        --      -51%      -77%      -87%      -94%
size_2M     8.00      105%        --      -53%      -73%      -87%
size_1M     3.73      340%      114%        --      -41%      -72%
size_500k   2.20      646%      264%       70%        --      -52%
size_250k   1.06     1450%      656%      253%      108%        --
$ 

##</code><code>##

#!/usr/bin/perl
use strict;
use warnings;

use KinoSearch::InvIndexer;
use KinoSearch::Analysis::PolyAnalyzer;
use Benchmark qw( cmpthese );

my $invindexer;
my $one_k_of_content = 'xxx ' x 256;

sub refresh_invindexer {
    undef $invindexer;
    my $analyzer
        = KinoSearch::Analysis::PolyAnalyzer->new( language => 'en' );
    $invindexer = KinoSearch::InvIndexer->new(
        analyzer => $analyzer,
        invindex => 'test_invindex',
        create   => 1,
    );
    $invindexer->spec_field( name => 'content' );
}

cmpthese(
    5,
    {   size_250k => sub { refresh_invindexer; add_a_doc(250)  for 1 .. 3 },
        size_500k => sub { refresh_invindexer; add_a_doc(500)  for 1 .. 3 },
        size_1M   => sub { refresh_invindexer; add_a_doc(1000) for 1 .. 3 },
        size_2M   => sub { refresh_invindexer; add_a_doc(2000) for 1 .. 3 },
        size_4M   => sub { refresh_invindexer; add_a_doc(4000) for 1 .. 3 },
    }
);

sub add_a_doc {
    my $repeat  = shift;
    my $doc     = $invindexer->new_doc;
    my $content = $one_k_of_content x $repeat;
    $doc->set_value( content => $content );
    $invindexer->add_doc($doc);
}