use strict;
use warnings;

# substitute whole word only
my %w1 = 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
  made make
};
# substitute on prefix
my %w2 = qw{
  need need
  talk talk
  tak take
  used use
  using use
};
# substitute on substring
my %w3 = 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 %w1 ]})\b}i;       
my $re2 = qr{\b(@{[ join '|', reverse sort keys %w2 ]})\w*}i;      
my $re3 = qr{\b\w*?(@{[ join '|', reverse sort keys %w3 ]})\w*}i;  #see discussion
#my $re3 = qr{\w*?(@{[ join '|', reverse sort keys %w3 ]})\w*}i;    

#print "$re3\n";  #for debugging

my $out='out-perl.dat';
open my $OUT, '>', $out or die "unable to open $out $!";

my $start = time();
my $finish;

open my $IN, '<', "nightfall.txt" or die " $!";  #75 MB file

while (<$IN>)
{
    tr/-!"#%&'()*,.\/:;?@\[\\\]_{}0123456789//d; # no punct no digits
                                                 # other formulations possible
      s/w(as|ere)/be/gi;
      s{$re1}{ $w1{lc $1} }g;  #this ~2-3 sec
      s{$re2}{ $w2{lc $1} }g;  #this ~3 sec
      s{$re3}{ $w3{lc $1} }g;  #this ~6 (best) - 14 sec
      print $OUT "$_";  
}

$finish = time();

my $total_seconds = $finish-$start;
my $minutes = int ($total_seconds/60);
my $seconds = $total_seconds - ($minutes*60);

print "minutes: $minutes  seconds: $seconds\n";

__END__
Time to completion with \b added to begin of $re3
minutes: 0  seconds: 12