#!/usr/bin/perl
# prune_newick - simple script to prune one or more from a newick formatted tree(s)
# 
# Usage: prune_newick <tree_file> <taxon_to_remove> [ <taxon2> ... ] 
# 
# prints tree to STDOUT

use strict;
use warnings;
use Bio::TreeIO;

# just handle printing out a help message
if (!@ARGV or grep /^-[hH]/, @ARGV) {
    open IN, $0 or die "Couldn't read source ($0): $!";
    $_ = <IN>;
    while (<IN>) {
        if (s/^#[ \t]?//) {
            print STDERR $_;
        } else {
            close(IN);
            exit(1);
        }
    }
}

# get the command line options
my $tree_file = shift;
my @taxa_to_remove = @ARGV;

# file to read
my $input = Bio::TreeIO->new(-file      => $tree_file,
                             -format    => 'newick');

my $output = Bio::TreeIO->new(-format => 'newick',
                              -fh     => \*STDOUT);  

# now remove the taxa and print out the trees
while (my $tree = $input->next_tree()) {
    foreach my $taxon (@taxa_to_remove) {
        $tree->remove_Node($taxon);
    }
    $output->write_tree($tree);
}


# Legal stuff I have to include:
#########################################################################
##                                                                     ##
##     PUBLIC DOMAIN NOTICE                                            ##
##                                                                     ##
##     This software/database is ``United States Government            ##
##     Work'' under the terms of the United States Copyright Act.      ##
##     It was written as part of the authors' official duties for      ##
##     the United States Government and thus cannot be                 ##
##     copyrighted. This software/database is freely available to      ##
##     the public for use without a copyright notice.                  ##
##     Restrictions cannot be placed on its present or future          ##
##     use.                                                            ##
##                                                                     ##
##     Although all reasonable efforts have been taken to ensure       ##
##     the accuracy and reliability of the software and data, the      ##
##     National Human Genome Research Institute (NHGRI) and the        ##
##     U.S. Government does not and cannot warrant the                 ##
##     performance or results that may be obtained by using this       ##
##     software or data.  NHGRI and the U.S. Government disclaims      ##
##     all warranties as to performance, merchantability or            ##
##     fitness for any particular purpose.                             ##
##                                                                     ##
##     In any work or product derived from this material, proper       ##
##     attribution of the authors as the source of the software        ##
##     or data should be made, using:                                  ##
##        Prasad, Arjun B. 2008 "prune_newick",                        ##
##        http://arjunprasad.net/scripts/prune_newick                  ##
##     as the citation.                                                ##
##                                                                     ##
#########################################################################