3 # Copyright (C) 2007-2013 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 # Merge pair-end sequences in the stream.
29 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
31 require 'maasha/biopieces'
35 def names_match(entry1, entry2)
36 if entry1.seq_name =~ /^([^ ]+) \d:/
38 elsif entry1.seq_name =~ /^(.+)\/\d$/
41 raise "Could not match sequence name: #{entry1.seq_name}"
44 if entry2.seq_name =~ /^([^ ]+) \d:/
46 elsif entry2.seq_name =~ /^(.+)\/\d$/
49 raise "Could not match sequence name: #{entry2.seq_name}"
55 options = Biopieces.options_parse(ARGV)
60 Biopieces.open(options[:stream_in], options[:stream_out]) do |input, output|
61 input.each_record do |record|
62 if record[:SEQ_NAME] and record[:SEQ]
64 entry1 = Seq.new_bp(record)
66 entry2 = Seq.new_bp(record)
70 if names_match(entry1, entry2)
71 seq_len_left = entry1.length
72 seq_len_right = entry2.length
76 new_record = entry1.to_bp
77 new_record[:SEQ_LEN_LEFT] = seq_len_left
78 new_record[:SEQ_LEN_RIGHT] = seq_len_right
79 output.puts new_record
81 raise "name mismatch: #{entry1.seq_name} != #{entry2.seq_name}"
94 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<