-#!/usr/bin/env perl
+#!/usr/bin/env ruby
-# Copyright (C) 2007-2010 Martin A. Hansen.
+# Copyright (C) 2007-2011 Martin A. Hansen.
# This program is free software; you can redistribute it and/or
# modify it under the terms of the GNU General Public License
# http://www.gnu.org/copyleft/gpl.html
-
-# >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> DESCRIPTION <<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
-
-# USEARCH sequences in the stream against a specified database or genome.
-
# >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
+# This program is part of the Biopieces framework (www.biopieces.org).
-use warnings;
-use strict;
-use Data::Dumper;
-use Maasha::Biopieces;
-use Maasha::Common;
-use Maasha::Seq;
-use Maasha::Fasta;
+# >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> DESCRIPTION <<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
+# Usearch sequences in the stream against a specified database.
# >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
+require 'maasha/biopieces'
+require 'maasha/fasta'
+require 'maasha/usearch'
-my ( $TYPE_HASH, $options, $in, $out, $tmp_dir, $tmp_in, $tmp_out, $q_type, $record, $entry, $fh_in, $fh_out );
-
-$TYPE_HASH = {
- 'L' => 'LibSeed',
- 'S' => 'NewSeed',
- 'H' => 'Hit',
- 'R' => 'Reject',
- 'D' => 'LibCluster',
- 'C' => 'NewCluster',
- 'N' => 'NoHit'
-};
-
-$options = Maasha::Biopieces::parse_options(
- [
- { long => 'database', short => 'd', type => 'file', mandatory => 'no', default => undef, allowed => undef, disallowed => undef },
- { long => 'genome', short => 'g', type => 'genome', mandatory => 'no', default => undef, allowed => undef, disallowed => undef },
- { long => 'id', short => 'i', type => 'float', mandatory => 'no', default => '0.90', allowed => undef, disallowed => undef },
- ]
-);
-
-Maasha::Common::error( qq(both --database and --genome specified) ) if $options->{ "genome" } and $options->{ "database" };
-Maasha::Common::error( qq(no --database or --genome specified) ) if not $options->{ "genome" } and not $options->{ "database" };
-
-$in = Maasha::Biopieces::read_stream( $options->{ "stream_in" } );
-$out = Maasha::Biopieces::write_stream( $options->{ "stream_out" } );
-
-$options->{ "database" } = "$ENV{ 'BP_DATA' }/genomes/$options->{ 'genome' }/fasta/$options->{ 'genome' }.fna" if $options->{ 'genome' };
-
-$tmp_dir = Maasha::Biopieces::get_tmpdir();
-$tmp_in = "$tmp_dir/usearch_query.seq";
-$tmp_out = "$tmp_dir/usearch.uc";
-
-$fh_out = Maasha::Filesys::file_write_open( $tmp_in );
-
-while ( $record = Maasha::Biopieces::get_record( $in ) )
-{
- if ( $entry = Maasha::Fasta::biopiece2fasta( $record ) )
- {
- $q_type = Maasha::Seq::seq_guess_type( $record->{ 'SEQ' } ) if not $q_type;
-
- Maasha::Fasta::put_entry( $entry, $fh_out );
- }
-
- Maasha::Biopieces::put_record( $record, $out );
-}
-
-close $fh_out;
-
-
-if ( $options->{ 'verbose' } )
-{
- Maasha::Common::run(
- "uclust",
- join( " ",
- "--input $tmp_in",
- "--lib $options->{ 'database' }",
- "--libonly",
- "--uc $tmp_out",
- "--id $options->{ 'id' }",
- "--rev",
- ),
- 1
- );
-}
-else
-{
- Maasha::Common::run(
- "uclust",
- join( " ",
- "--input $tmp_in",
- "--lib $options->{ 'database' }",
- "--libonly",
- "--uc $tmp_out",
- "--id $options->{ 'id' }",
- "--rev",
- "> /dev/null 2>&1"
- ),
- 1
- );
-}
-
-unlink $tmp_in;
-
-$fh_in = Maasha::Filesys::file_read_open( $tmp_out );
-
-while ( $entry = get_tab_entry( $fh_in ) )
-{
- $record = uclust_tab2biopiece( $entry );
-
- Maasha::Biopieces::put_record( $record, $out ) if $record->{ 'TYPE' } eq 'Hit';
-}
-
-close $fh_out;
+casts = []
+casts << {:long=>'database', :short=>'d', :type=>'file!', :mandatory=>false, :default=>nil, :allowed=>nil, :disallowed=>nil}
+casts << {:long=>'identity', :short=>'i', :type=>'float', :mandatory=>false, :default=>nil, :allowed=>nil, :disallowed=>nil}
+casts << {:long=>'e_val', :short=>'e', :type=>'float', :mandatory=>false, :default=>nil, :allowed=>nil, :disallowed=>nil}
-unlink $tmp_out;
+options = Biopieces.options_parse(ARGV, casts)
-Maasha::Biopieces::close_stream( $in );
-Maasha::Biopieces::close_stream( $out );
+raise ArgumentError, "--identity or --e_val must be specified" unless options[:identity] or options[:e_val]
+tmpdir = Biopieces.mktmpdir
+infile = File.join(tmpdir, "in.fna")
+outfile = File.join(tmpdir, "out.uc")
-# >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> SUBROUTINES <<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
-
-
-sub get_tab_entry
-{
- # Martin A. Hansen, May 2009.
-
- # Get the next tabular entry from a filehandle to a USEARCH file.
-
- my ( $fh, # filehandle
- ) = @_;
-
- # Returns a list
-
- my ( $line, @fields );
-
- while ( $line = <$fh> )
- {
- next if $line =~ /^#/;
-
- @fields = split /\s+/, $line;
-
- return wantarray ? @fields : \@fields;
- }
-
- return undef;
-}
-
-
-sub uclust_tab2biopiece
-{
- # Martin A. Hansen, May 2009.
-
- # Get the next USEARCH tabular entry and convert it to
- # a biopiece record that is returned.
-
- my ( $entry, # USEARCH tabular entry
- ) = @_;
-
- # Returns a hashref.
-
- my ( %record );
-
- $record{ "REC_TYPE" } = "USEARCH";
- $record{ "TYPE" } = $TYPE_HASH->{ $entry->[ 0 ] };
- $record{ "CLUSTER" } = $entry->[ 1 ];
- $record{ "ALIGN_LEN" } = $entry->[ 2 ];
- $record{ "ID" } = $entry->[ 3 ];
- $record{ "STRAND" } = $entry->[ 4 ];
- $record{ "Q_BEG" } = $entry->[ 5 ];
- $record{ "S_BEG" } = $entry->[ 6 ];
- $record{ "CIGAR" } = $entry->[ 7 ];
- $record{ "Q_ID" } = $entry->[ 8 ];
- $record{ "S_ID" } = $entry->[ 9 ];
-
- if ( $record{ 'TYPE' } eq 'Hit' )
- {
- $record{ "Q_END" } = $record{ "Q_BEG" } + $record{ "ALIGN_LEN" } - 1;
- $record{ "S_END" } = $record{ "S_BEG" } + $record{ "ALIGN_LEN" } - 1;
- }
-
- return wantarray ? %record : \%record;
-}
-
-
-
-# >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
+Biopieces.open(options[:stream_in], options[:stream_out]) do |input, output|
+ Fasta.open(infile, mode="w") do |fasta_io|
+ input.each_record do |record|
+ output.puts record
+ if record.has_key? :SEQ_NAME and record.has_key? :SEQ
+ fasta_io.puts Seq.new_bp(record).to_fasta
+ end
+ end
+ end
-BEGIN
-{
- Maasha::Biopieces::status_set();
-}
+ us = Usearch.new(infile, outfile, options)
+ us.usearch
-END
-{
- Maasha::Biopieces::status_log();
-}
+ us.each_hit do |record|
+ output.puts record
+ end
+end
# >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<