wget http://www.astro.sunysb.edu/fwalter/AST389/TEXTS/Nightfall.htm
html2text-cpp Nightfall.htm >nightfall.txt
mkdir 00; for i in `seq -w 0 3456`; do head -$((RANDOM/128)) nightfall.txt >00/data-$i; done
####
#!/usr/bin/perl
use strict;
use warnings;
use 5.36.0;
use Env;
use utf8;
use POSIX "sys_wait_h"; #for waitpid FLAGS
use Time::HiRes qw(gettimeofday tv_interval);
use open ':std', ':encoding(UTF-8)';
my $benchmark = 1; # print timings for loops
my $TMP='/tmp';
my $HOME = $ENV{HOME};
my $IN;
my $OUT;
my @data = glob("data-* ??/data-*");
my $filecount = scalar(@data);
die if $filecount < 0;
say "Parsing $filecount files";
my $wordfile="data.dat";
truncate $wordfile, 0;
#$|=1;
# substitute whole words
my %whole = qw{
going go
getting get
goes go
knew know
trying try
tried try
told tell
coming come
saying say
men man
women woman
took take
lying lie
dying die
};
# substitute on prefix
my %prefix = qw{
need need
talk talk
tak take
used use
using use
};
# substitute on substring
my %substring = qw{
mean mean
work work
read read
allow allow
gave give
bought buy
want want
hear hear
came come
destr destroy
paid pay
selve self
cities city
fight fight
creat create
makin make
includ include
};
my $re1 = qr{\b(@{[ join '|', reverse sort keys %whole ]})\b}i;
my $re2 = qr{\b(@{[ join '|', reverse sort keys %prefix ]})\w*}i;
my $re3 = qr{\b\w*?(@{[ join '|', reverse sort keys %substring ]})\w*}i;
truncate $wordfile, 0;
my $maxforks = 64;
print "maxforks: $maxforks\n";
my $forkcount = 0;
my $infile;
my $subdir = 0;
my $subdircount = 255;
my $tempdir = "temp";
mkdir "$tempdir";
mkdir "$tempdir/$subdir" while ($subdir++ <= $subdircount);
$subdir = 0;
my $i = 0;
my $t0 = [gettimeofday];
my $elapsed;
foreach $infile(@data) {
$forkcount -= waitpid(-1, WNOHANG) > 0 while $forkcount >= $maxforks;
# do { $elapsed=tv_interval($t0); print "elapsed: $elapsed\n"; die; } if $i++ >1000; # 1000 files test
$i++; # comment out if you uncomment the above line
$subdir = 1 if $subdir++ > $subdircount;
if (my $pid = fork) { # $pid defined and !=0 -->parent
++$forkcount;
} else { # $pid==0 -->child
open my $IN, '<', $infile or exit(0);
open my $OUT, '>', "$tempdir/$subdir/text-$i" or exit(0);
while (<$IN>) {
tr/-!"#%&()*',.\/:;?@\[\\\]”_“{’}><^)(|/ /; # no punct "
s/^/ /;
s/\n/ \n/;
s/[[:digit:]]{1,12}//g;
s/w(as|ere)/be/gi;
s{$re2}{ $prefix{lc $1} }g; # prefix
s{$re3}{ $substring{lc $1} }g; # part
s{$re1}{ $whole{lc $1} }g; # whole
print $OUT "$_";
}
close $OUT;
close $IN;
defined $pid and exit(0); # $pid==0 -->child, must exit itself
}
}
### now wait for all children to finish, no matter who they are
1 while wait != -1; # avoid zombies this is a blocking operation
local @ARGV = glob("$tempdir/*/*");
my @text = <>;
unlink glob "$tempdir/*/*";
open $OUT, '>', $wordfile or die "Error opening $wordfile";
print $OUT @text;
close $OUT;
$elapsed = tv_interval($t0);
print "regex: $elapsed\n" if $benchmark;
##
##
for dir in $(seq -w 01 10); do cp -a 00 $dir; done