App-genstopwords

 view release on metacpan or  search on metacpan

script/gen-stopwords  view on Meta::CPAN

            }

            debug("  Processing: $File::Find::name");
            $processed++;

            open my $fh, '<', $name
                or do { warn_ "WARNING: Cannot open $File::Find::name: $!"; return };

            while (my $line = <$fh>) {
                # Strip POD formatting codes entirely (E<gt>, L<...>, C<...>, etc.)
                # Removing the whole tag prevents fragments like 'gt' or 'Egt' appearing.
                $line =~ s/[A-Z]<[^>]+>//g;

                my $result = aspell_list($line, $lang);
                next unless $result;

                for my $word (split /\n/, $result) {
                    $word =~ s/^\s+|\s+$//g;
                    next unless length($word) >= $opt{min_len};

                    my $clean = lc($word);



( run in 0.772 second using v1.01-cache-2.11-cpan-b16cb0d3907 )