#!perl
use strict;
use Data::Dumper;
use Carp;
#
# This is a SAS Component
#
=head1 contigs_to_lengths
In some cases, one wishes to know just the lengths of the contigs, rather than their
actual DNA sequence (e.g., suppose that you wished to know if a gene boundary occured within
100 bp of the end of the contig). To avoid requiring a user to access the entire DNA sequence,
we offer the ability to retrieve just the contig lengths. Input to the routine is a list of contig IDs.
The routine returns a mapping from contig IDs to lengths
Example:
contigs_to_lengths [arguments] < input > output
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 identifer. If another column contains the identifier
use
-c N
where N is the column (from 1) that contains the subsystem.
This is a pipe command. The input is taken from the standard input, and the
output is to the standard output.
=head2 Documentation for underlying call
This script is a wrapper for the CDMI-API call contigs_to_lengths. It is documented as follows:
$return = $obj->contigs_to_lengths($contigs)
=over 4
=item Parameter and return types
=begin html
<pre>
$contigs is a contigs
$return is a reference to a hash where the key is a contig and the value is a length
contigs is a reference to a list where each element is a contig
contig is a string
length is an int
</pre>
=end html
=begin text
$contigs is a contigs
$return is a reference to a hash where the key is a contig and the value is a length
contigs is a reference to a list where each element is a contig
contig is a string
length is an int
=end text
=back
=head2 Command-Line Options
=over 4
=item -c Column
This is used only if the column containing the subsystem is not the last column.
=item -i InputFile [ use InputFile, rather than stdin ]
=back
=head2 Output Format
The standard output is a tab-delimited file. It consists of the input
file with an extra column (the contig length) added.
Input lines that cannot be extended are written to stderr.
=cut
my $usage = "usage: contigs_to_lengths [-c column] < input > output";
use Bio::KBase::CDMI::CDMIClient;
use Bio::KBase::Utilities::ScriptThing;
my $column;
my $input_file;
my $kbO = Bio::KBase::CDMI::CDMIClient->new_for_script('c=i' => \$column,
'i=s' => \$input_file);
if (! $kbO) { print STDERR $usage; exit }
my $ih;
if ($input_file)
{
open $ih, "<", $input_file or die "Cannot open input file $input_file: $!";
}
else
{
$ih = \*STDIN;
}
while (my @tuples = Bio::KBase::Utilities::ScriptThing::GetBatch($ih, undef, $column)) {
my @h = map { $_->[0] } @tuples;
my $h = $kbO->contigs_to_lengths(\@h);
for my $tuple (@tuples) {
#
# Process output here and print.
#
my ($id, $line) = @$tuple;
my $v = $h->{$id};
if (! defined($v))
{
print STDERR $line,"\n";
}
elsif (ref($v) eq 'ARRAY')
{
foreach $_ (@$v)
{
print "$line\t$_\n";
}
}
else
{
print "$line\t$v\n";
}
}
}