3 # Copyright (C) 2007-2009 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
22 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> DESCRIPTION <<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
24 # Read nucleotide sequences in 2bit format from one or more files.
26 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
31 use Maasha::Biopieces;
36 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
39 my ( $options, $in, $out, $record, $file, $data_in, $mask, $toc, $line, $num );
41 $options = Maasha::Biopieces::parse_options(
43 { long => 'data_in', short => 'i', type => 'files!', mandatory => 'no', default => undef, allowed => undef, disallowed => undef },
44 { long => 'num', short => 'n', type => 'uint', mandatory => 'no', default => undef, allowed => undef, disallowed => '0' },
45 { long => 'no_mask', short => 'N', type => 'flag', mandatory => 'no', default => undef, allowed => undef, disallowed => undef },
49 $in = Maasha::Biopieces::read_stream( $options->{ "stream_in" } );
50 $out = Maasha::Biopieces::write_stream( $options->{ "stream_out" } );
52 while ( $record = Maasha::Biopieces::get_record( $in ) ) {
53 Maasha::Biopieces::put_record( $record, $out );
56 $mask = 1 if not $options->{ "no_mask" };
60 foreach $file ( @{ $options->{ "data_in" } } )
62 $data_in = Maasha::Filesys::file_read_open( $file );
64 $toc = Maasha::TwoBit::twobit_get_TOC( $data_in );
66 foreach $line ( @{ $toc } )
68 $record->{ "SEQ_NAME" } = $line->[ 0 ];
69 $record->{ "SEQ" } = Maasha::TwoBit::twobit_get_seq( $data_in, $line->[ 1 ], undef, undef, $mask );
70 $record->{ "SEQ_LEN" } = length $record->{ "SEQ" };
72 Maasha::Biopieces::put_record( $record, $out );
74 goto NUM if $options->{ "num" } and $num == $options->{ "num" };
84 close $data_in if $data_in;
86 Maasha::Biopieces::close_stream( $in );
87 Maasha::Biopieces::close_stream( $out );
90 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
95 Maasha::Biopieces::status_set();
101 Maasha::Biopieces::status_log();
105 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<