# gen-long-llil.pl
# Crude program to generate a LLiL test file with long names and counts
# perl gen-long-llil.pl long1.txt 600
use strict;
use warnings;
use autodie;
{
my $ordmin = ord('a');
my $ordmax = ord('z') + 1;
# Generate a random word
sub gen_random_word {
my $word = shift; # word prefix
my $nchar = shift; # the number of random chars to append
for my $i (1 .. $nchar) {
$word .= chr( $ordmin + int( rand($ordmax - $ordmin) ) );
}
return $word;
}
}
my $longworda = join '', 'a' .. 'z';
my $longwordz = join '', reverse('a' .. 'z');
my $longcount = 1_000_000;
sub create_long_test_file {
my $fname = shift;
my $howmany = shift;
open( my $fh_out, '>', $fname );
# Some with no randomness
for my $h ( 1 .. $howmany ) {
for my $i ( 1 .. 8 ) {
my $cnt = $longcount + $i - 1;
my $worda = $longworda x $i;
my $wordz = $longwordz x $i;
print {$fh_out} "$worda\t$cnt\n$wordz\t$cnt\n";
}
}
# Some with randomness
my $wordlen = 1;
for my $h ( 1 .. $howmany ) {
for my $i ( 1 .. 8 ) {
my $cnt = $longcount + $i - 1;
my $worda = $longworda x $i;
my $wordz = $longwordz x $i;
for my $c ( 'a' .. 'z' ) {
for my $z ( 1 .. 2 ) {
print {$fh_out} $worda . gen_random_word( $c, $wordlen ) . "\t" . (1000000 + $z) . "\n";
print {$fh_out} $wordz . gen_random_word( $c, $wordlen ) . "\t" . (1000000 + $z) . "\n";
}
}
}
}
}
my $outfile = shift;
my $count = shift;
$outfile or die "usage: $0 outfile count\n";
$count or die "usage: $0 outfile count\n";
$count =~ /^\d+$/ or die "error: count '$count' is not a number\n";
print "generating short long test file '$outfile' with count '$count'\n";
create_long_test_file( $outfile, $count );
print "file size=", -s $outfile, "\n";
####
> perl gen-long-llil.pl long1.txt 600
generating short long test file 'long1.txt' with count '600'
file size=65616000
> perl gen-long-llil.pl long2.txt 600
generating short long test file 'long2.txt' with count '600'
file size=65616000
> perl gen-long-llil.pl long3.txt 600
generating short long test file 'long3.txt' with count '600'
file size=65616000
##
##
> perl llil2d.pl big1.txt big2.txt big3.txt long1.txt long2.txt long3.txt >perl2.tmp
llil2d start
get_properties : 11 secs
sort + output : 23 secs
total : 34 secs
> llil2a big1.txt big2.txt big3.txt long1.txt long2.txt long3.txt >cpp2.tmp
llil2 start
get_properties : 6 secs
sort + output : 5 secs
total : 11 secs
> diff cpp2.tmp perl2.tmp
##
##
# gen-llil.pl
# Crude program to generate a big LLiL test file to use in benchmarks
# On Windows running:
# perl gen-llil.pl big2.txt 200 3 - produces a test file with size = 35,152,000 bytes
# (lines terminated with "\r\n")
# perl gen-llil.pl big2.txt 200 3 1 - produces a test file with size = 31,636,800 bytes
# (lines terminated with "\n")
# On Unix, lines are terminated with "\n" and the file size is always 31,636,800 bytes
use strict;
use warnings;
use autodie;
{
my $ordmin = ord('a');
my $ordmax = ord('z') + 1;
# Generate a random word
sub gen_random_word {
my $word = shift; # word prefix
my $nchar = shift; # the number of random chars to append
for my $i (1 .. $nchar) {
$word .= chr( $ordmin + int( rand($ordmax - $ordmin) ) );
}
return $word;
}
}
sub create_test_file {
my $fname = shift;
my $count = shift;
my $wordlen = shift;
my $fbin = shift;
open( my $fh_out, '>', $fname );
$fbin and binmode($fh_out);
for my $c ( 'aaa' .. 'zzz' ) {
for my $i (1 .. $count) {
print {$fh_out} gen_random_word( $c, $wordlen ) . "\t" . 1 . "\n";
}
}
}
my $outfile = shift;
my $count = shift;
my $wordlen = shift;
my $fbin = shift; # default is to use text stream (not a binary stream)
defined($fbin) or $fbin = 0;
$outfile or die "usage: $0 outfile count wordlen\n";
$count or die "usage: $0 outfile count wordlen\n";
print "generating test file '$outfile' with count '$count' (binmode=$fbin)\n";
create_test_file($outfile, $count, $wordlen, $fbin);
print "file size=", -s $outfile, "\n";
##
##
# gen-long-llil.pl
# Crude program to generate a LLiL test file with long names and counts
# perl gen-long-llil.pl long1.txt 600
# On Windows running:
# perl gen-long-llil.pl long1.txt 600 - produces a test file with size = 65,616,000 bytes
# (lines terminated with "\r\n")
# perl gen-long-llil.pl long1.txt 600 - produces a test file with size = 65,107,200 bytes
# (lines terminated with "\n")
# On Unix, lines are terminated with "\n" and the file size is always 65,107,200 bytes
use strict;
use warnings;
use autodie;
{
my $ordmin = ord('a');
my $ordmax = ord('z') + 1;
# Generate a random word
sub gen_random_word {
my $word = shift; # word prefix
my $nchar = shift; # the number of random chars to append
for my $i (1 .. $nchar) {
$word .= chr( $ordmin + int( rand($ordmax - $ordmin) ) );
}
return $word;
}
}
my $longworda = join '', 'a' .. 'z';
my $longwordz = join '', reverse('a' .. 'z');
my $longcount = 1_000_000;
sub create_long_test_file {
my $fname = shift;
my $howmany = shift;
my $fbin = shift;
open( my $fh_out, '>', $fname );
$fbin and binmode($fh_out);
# Some with no randomness
for my $h ( 1 .. $howmany ) {
for my $i ( 1 .. 8 ) {
my $cnt = $longcount + $i - 1;
my $worda = $longworda x $i;
my $wordz = $longwordz x $i;
print {$fh_out} "$worda\t$cnt\n$wordz\t$cnt\n";
}
}
# Some with randomness
my $wordlen = 1;
for my $h ( 1 .. $howmany ) {
for my $i ( 1 .. 8 ) {
my $cnt = $longcount + $i - 1;
my $worda = $longworda x $i;
my $wordz = $longwordz x $i;
for my $c ( 'a' .. 'z' ) {
for my $z ( 1 .. 2 ) {
print {$fh_out} $worda . gen_random_word( $c, $wordlen ) . "\t" . (1000000 + $z) . "\n";
print {$fh_out} $wordz . gen_random_word( $c, $wordlen ) . "\t" . (1000000 + $z) . "\n";
}
}
}
}
}
my $outfile = shift;
my $count = shift;
my $fbin = shift; # default is to use text stream (not a binary stream)
defined($fbin) or $fbin = 0;
$outfile or die "usage: $0 outfile count\n";
$count or die "usage: $0 outfile count\n";
$count =~ /^\d+$/ or die "error: count '$count' is not a number\n";
print "generating short long test file '$outfile' with count '$count' (binmode=$fbin)\n";
create_long_test_file( $outfile, $count, $fbin );
print "file size=", -s $outfile, "\n";