-#!/usr/bin/env perl
+#!/usr/bin/env ruby
-# Copyright (C) 2007-2009 Martin A. Hansen.
+# Copyright (C) 2007-2010 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 <<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
-
-# Read FASTQ entries from one or more files.
-
# >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
+# This program is part of the Biopieces framework (www.biopieces.org).
-use warnings;
-use strict;
-use Maasha::Biopieces;
-use Maasha::Filesys;
-use Maasha::Fastq;
+# >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> DESCRIPTION <<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
+# Read FASTQ entries from one or more files.
# >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
+require 'biopieces'
+require 'fastq'
-my ( $options, $in, $out, $record, $data_in, $num, $entry );
-
-$options = Maasha::Biopieces::parse_options(
- [
- { long => 'data_in', short => 'i', type => 'files!', mandatory => 'no', default => undef, allowed => undef, disallowed => undef },
- { long => 'num', short => 'n', type => 'uint', mandatory => 'no', default => undef, allowed => undef, disallowed => 0 },
- { long => 'convert2dec', short => 'c', type => 'flag', mandatory => 'no', default => undef, allowed => undef, disallowed => undef },
- { long => 'cutoff', short => 'C', type => 'int', mandatory => 'no', default => 20, allowed => undef, disallowed => undef },
- { long => 'soft_mask', short => 's', type => 'flag', mandatory => 'no', default => undef, allowed => undef, disallowed => undef },
- ]
-);
-
-$in = Maasha::Biopieces::read_stream( $options->{ "stream_in" } );
-$out = Maasha::Biopieces::write_stream( $options->{ "stream_out" } );
+casts = []
+casts << {:long=>'data_in', :short=>'i', :type=>'files!', :mandatory=>false, :default=>nil, :allowed=>nil, :disallowed=>nil}
+casts << {:long=>'num', :short=>'n', :type=>'uint', :mandatory=>false, :default=>nil, :allowed=>nil, :disallowed=>'0'}
-while ( $record = Maasha::Biopieces::get_record( $in ) ) {
- Maasha::Biopieces::put_record( $record, $out );
-}
+PHRED_SCORES = Regexp.new('[!"#$%&\'()*+,-./0123456789:]')
-if ( $options->{ 'data_in' } )
-{
- $data_in = Maasha::Filesys::files_read_open( $options->{ 'data_in' } );
+bp = Biopieces.new
- $num = 1;
+options = bp.parse(ARGV, casts)
- while ( $entry = Maasha::Fastq::get_entry( $data_in ) )
- {
- if ( $record = Maasha::Fastq::fastq2biopiece( $entry ) )
- {
- Maasha::Fastq::softmask_phred_str( $record->{ 'SEQ' }, $record->{ 'SCORES' }, $options->{ 'cutoff' } ) if $options->{ 'soft_mask' };
- $record->{ 'SCORES' } = Maasha::Fastq::phred_str2dec_str( $record->{ 'SCORES' } ) if $options->{ 'convert2dec' };
-
- Maasha::Biopieces::put_record( $record, $out );
- }
-
- last if $options->{ "num" } and $num == $options->{ "num" };
-
- $num++;
- }
-
- close $data_in;
-}
-
-Maasha::Biopieces::close_stream( $in );
-Maasha::Biopieces::close_stream( $out );
-
-
-# >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
+bp.each_record do |record|
+ bp.puts record
+end
+num = 0
+last = false
-BEGIN
-{
- Maasha::Biopieces::status_set();
-}
+if options.has_key? :data_in
+ options[:data_in].each do |file|
+ Fastq.open(file, mode='r') do |fastq|
+ fastq.each do |entry|
+ entry.convert! if entry.qual.match PHRED_SCORES
+ bp.puts entry.to_bp
+ num += 1
+ if options.has_key? :num and options[:num] == num
+ last = true
+ break
+ end
+ end
+ end
-END
-{
- Maasha::Biopieces::status_log();
-}
+ break if last
+ end
+end
# >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<