3 # Copyright (C) 2007-2011 Martin A. Hansen.
5 # This program is free software; you can redistribute it and/or
6 # modify it under the terms of the GNU General Public License
7 # as published by the Free Software Foundation; either version 2
8 # of the License, or (at your option) any later version.
10 # This program is distributed in the hope that it will be useful,
11 # but WITHOUT ANY WARRANTY; without even the implied warranty of
12 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
13 # GNU General Public License for more details.
15 # You should have received a copy of the GNU General Public License
16 # along with this program; if not, write to the Free Software
17 # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
19 # http://www.gnu.org/copyleft/gpl.html
21 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
23 # This program is part of the Biopieces framework (www.biopieces.org).
25 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> DESCRIPTION <<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
27 # Write sequence type records to FASTQ files according to a specified key.
29 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
31 require 'maasha/biopieces'
32 require 'maasha/fastq'
35 allowed_enc = 'base_33,base_64'
38 casts << {long: 'key', short: 'k', type: 'string', mandatory: true, default: nil, allowed: nil, disallowed: nil}
39 casts << {long: 'dir', short: 'd', type: 'dir!', mandatory: true, default: nil, allowed: nil, disallowed: nil}
40 casts << {long: 'prefix', short: 'p', type: 'string', mandatory: false, default: nil, allowed: nil, disallowed: nil}
41 casts << {long: 'no_stream', short: 'x', type: 'flag', mandatory: false, default: nil, allowed: nil, disallowed: nil}
42 casts << {long: 'compress', short: 'Z', type: 'string', mandatory: false, default: nil, allowed: "gzip,bzip,bzip2", disallowed: nil}
43 casts << {long: 'encoding', short: 'e', type: 'string', mandatory: false, default: 'base_33', allowed: allowed_enc, disallowed: nil}
45 options = Biopieces.options_parse(ARGV, casts)
47 encoding = options[:encoding].to_sym
48 compress = options[:compress] ? options[:compress].to_sym : nil
50 key = options[:key].to_sym
54 Biopieces.open(options[:stream_in], options[:stream_out]) do |input, output|
55 input.each_record do |record|
56 if record[:SEQ_NAME] and record[:SEQ] and record[:SCORES] and record[key]
57 entry = Seq.new_bp(record)
58 entry.qual_convert!(:base_33, encoding)
60 if fh_hash[record[key].to_sym]
61 fastq_io = fh_hash[record[key].to_sym]
64 fastq_file = File.join(options[:dir], [options[:prefix], record[key]].join("_") + ".fastq")
66 fastq_file = File.join(options[:dir], record[key] + ".fastq")
69 fastq_file << ".gz" if compress == :gzip
70 fastq_file << ".bz2" if compress == :bzip or compress == :bzip2
71 fastq_io = Fastq.open(fastq_file, "w", compress: compress)
72 fh_hash[record[key].to_sym] = fastq_io
75 fastq_io.puts entry.to_fastq
78 output.puts record unless options[:no_stream]
82 fh_hash.each_value { |val| val.close }
84 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<