#!perl
use strict;
use Data::Dumper;
use Bio::KBase::Utilities::ScriptThing;
use Carp;

#
# This is a SAS Component
#


=head1 get_entity_Genome

The Kbase houses a large and growing set of genomes.  We often have multiple
genomes that have identical DNA.  These usually have distinct gene calls and
annotations, but not always.  We consider the Kbase to be a framework for
managing hundreds of thousands of genomes and offering the tools needed to
support compartive analysis on large sets of genomes, some of which are
virtually identical.
Each genome has an MD5 value computed from the DNA that is associated with the genome.
Hence, it is easy to recognize when you have identical genomes, perhaps annotated
by distinct groups.


Example:

    get_entity_Genome -a < ids > table.with.fields.added

would read in a file of ids and add a column for each filed in the entity.

The standard input should be a tab-separated table (i.e., each line
is a tab-separated set of fields).  Normally, the last field in each
line would contain the id. If some other column contains the id,
use

    -c N

where N is the column (from 1) that contains the id.

This is a pipe command. The input is taken from the standard input, and the
output is to the standard output.

=head2 Related entities

The Genome entity has the following relationship links:

=over 4
    
=item HadResultsProducedBy ProbeSet

=item HasRepresentativeOf Family

=item IsCollectedInto OTU

=item IsComposedOf Contig

=item IsConfiguredBy AtomicRegulon

=item IsInTaxa TaxonomicGrouping

=item IsModeledBy Model

=item IsOwnerOf Feature

=item IsReferencedBy ObservationalUnit

=item Uses SSRow

=item WasSubmittedBy Source


=back

=head2 Command-Line Options

=over 4

=item -c Column

Use the specified column to define the id of the entity to retrieve.

=item -h

Display a list of the fields available for use.

=item -fields field-list

Choose a set of fields to return. Field-list is a comma-separated list of 
strings. The following fields are available:

=over 4

=item pegs

=item rnas

=item scientific_name

=item complete

=item prokaryotic

=item dna_size

=item contigs

=item domain

=item genetic_code

=item gc_content

=item phenotype

=item md5

=item source_id

=back    

=back

=head2 Output Format

The standard output is a tab-delimited file. It consists of the input
file with an extra column added for each requested field.  Input lines that cannot
be extended are written to stderr.  

=cut

use Bio::KBase::CDMI::CDMIClient;
use Getopt::Long;

#Default fields

my @all_fields = ( 'pegs', 'rnas', 'scientific_name', 'complete', 'prokaryotic', 'dna_size', 'contigs', 'domain', 'genetic_code', 'gc_content', 'phenotype', 'md5', 'source_id' );
my %all_fields = map { $_ => 1 } @all_fields;

my $usage = "usage: get_entity_Genome [-h] [-c column] [-a | -f field list] < ids > extended.by.a.column(s)";

my $column;
my $a;
my $f;
my $i = "-";
my @fields;
my $show_fields;
my $geO = Bio::KBase::CDMI::CDMIClient->new_get_entity_for_script('c=i'	   	=> \$column,
								  "a"	   	=> \$a,
								  "h"	   	=> \$show_fields,
								  "show-fields"	=> \$show_fields,
								  "fields=s" 	=> \$f,
								  'i=s'	   	=> \$i);
if ($show_fields)
{
    print STDERR "Available fields: @all_fields\n";
    exit 0;
}
if ($a && $f) { print STDERR $usage; exit 1 }
if ($a)
{
    @fields = @all_fields;
}
elsif ($f) {
    my @err;
    for my $field (split(",", $f))
    {
	if (!$all_fields{$field})
	{
	    push(@err, $field);
	}
	else
	{
	    push(@fields, $field);
	}
    }
    if (@err)
    {
	print STDERR "get_entity_Genome: unknown fields @err. Valid fields are: @all_fields\n";
	exit 1;
    }
} else {
    print STDERR $usage;
    exit 1;
}

my $ih;
if ($i eq '-')
{
    $ih = \*STDIN;
}
else
{
    open($ih, "<", $i) or die "Cannot open input file $i: $!\n";
}

while (my @tuples = Bio::KBase::Utilities::ScriptThing::GetBatch($ih, undef, $column)) {
    my @h = map { $_->[0] } @tuples;
    my $h = $geO->get_entity_Genome(\@h, \@fields);
    for my $tuple (@tuples) {
        my @values;
        my ($id, $line) = @$tuple;
        my $v = $h->{$id};
	if (! defined($v))
	{
	    #nothing found for this id
	    print STDERR $line,"\n";
     	} else {
	    foreach $_ (@fields) {
		my $val = $v->{$_};
		push (@values, ref($val) eq 'ARRAY' ? join(",", @$val) : $val);
	    }
	    my $tail = join("\t", @values);
	    print "$line\t$tail\n";
        }
    }
}
