In <this text> there are <some in marks>,
but there are more lines in this file and there
are more <such symbols>. How can someone match sentences?
A sentence - in our case, starts with a capital letter
and ends with a dot.
#!/usr/bin/perl
use strict;
use warnings;
my $filename = 'sentences.txt';
my $content = slurp($filename);
if ($content =~ /<.*>/) {
print "$&\n";
print "-----------\n";
}
# If we want the smallest:
if ($content =~ /<[^>]*>/) {
print "$&\n";
print "-----------\n";
}
# If we want the biggest
if ($content =~ /<.*>/s) {
print "$&\n";
print "-----------\n";
}
sub slurp {
my $file = shift;
open my $fh, '<', $file or die "Could not open '$file' $!";
local $/ = undef;
my $all = <$fh>;
close $fh;
return $all;
}