parse_mega_asr.pl

use strict;
use warnings;

my %sequences;
my %names;

while (<>) {
  my ($node_number, $node_name, $seq) = /^(\d+)\.\s+([^:]+):\s*(.+)$/ or next;
  printf "appending %s to %s (node %s)\n", $seq, $node_name, $node_number;
  $sequences{$node_number} .= $seq;
  $names{$node_number} = $node_name;
}

for my $node_number (sort { $a <=> $b } keys %sequences) {
  # strip -'s
  $sequences{$node_number} =~ s/-//g;
  printf "%s. %s: %s\n", $node_number, $names{$node_number}, $sequences{$node_number};
}