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

#
# This is a SAS Component
#


=head1 get_entity_Contig

A contig is thought of as composing a part of the DNA associated with a specific
genome.  It is represented as an ID (including the genome ID) and a ContigSequence.
We do not think of strings of DNA from, say, a metgenomic sample as "contigs",
since there is no associated genome (these would be considered ContigSequences).
This use of the term "ContigSequence", rather than just "DNA sequence", may turn out
to be a bad idea.  For now, you should just realize that a Contig has an associated
genome, but a ContigSequence does not.


Example:

    get_entity_Contig -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 Contig entity has the following relationship links:

=over 4
    
=item HasAsSequence ContigSequence

=item HasVariationIn ObservationalUnit

=item IsComponentOf Genome

=item IsImpactedBy Trait

=item IsLocusFor Feature

=item IsSummarizedBy AlleleFrequency


=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 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 = ( 'source_id' );
my %all_fields = map { $_ => 1 } @all_fields;

my $usage = "usage: get_entity_Contig [-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_Contig: 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_Contig(\@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";
        }
    }
}
