3 # Copyright (C) 2007-2012 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 # Order records with pair end sequence data.
29 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
31 require 'maasha/biopieces'
34 options = Biopieces.options_parse(ARGV)
39 Biopieces.open(options[:stream_in], options[:stream_out]) do |input, output|
40 input.each_record do |record|
42 case record[:SEQ_NAME]
43 when /^(.+)\/(\d)$/ # Illumina 1.5
46 when /^(.+) (\d):/ # Illumina 1.8
50 $stderr.puts "WARNING: Unmatched sequence name: #{record[:SEQ_NAME]}" if options[:verbose]
56 output.puts hash2[name]
64 output.puts hash1[name]
77 $stderr.puts "Unmatched names with 1st read pair: #{hash1.size}"
78 $stderr.puts "Unmatched names with 2nd read pair: #{hash2.size}"
81 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<