This file is indexed.

/usr/share/perl5/Bio/ClusterIO/unigene.pm is in libbio-perl-perl 1.6.923-1.

This file is owned by root:root, with mode 0o644.

The actual contents of the file can be viewed below.

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
# BioPerl module for Bio::ClusterIO::unigene
#
# Please direct questions and support issues to <bioperl-l@bioperl.org> 
#
# Cared for by Andrew Macgregor <andrew at cbbc.murdoch.edu.au>
#
# Copyright Andrew Macgregor, Jo-Ann Stanton, David Green
# Molecular Embryology Group, Anatomy & Structural Biology, University of Otago
# http://meg.otago.ac.nz
#
# You may distribute this module under the same terms as perl itself
#
# _history
# April 17, 2002 - Initial implementation by Andrew Macgregor

# POD documentation - main docs before the code

=head1 NAME

Bio::ClusterIO::unigene - UniGene input stream

=head1 SYNOPSIS

Do not use this module directly.  Use it via the Bio::ClusterIO class.

=head1 DESCRIPTION

This object reads from Unigene *.data files downloaded from
ftp://ftp.ncbi.nih.gov/repository/UniGene/.  It does not download and
decompress the file, you have to do that yourself.

=head1 FEEDBACK

=head2 Mailing Lists

User feedback is an integral part of the evolution of this and other
Bioperl modules. Send your comments and suggestions preferably to one
of the Bioperl mailing lists.  Your participation is much appreciated.

  bioperl-l@bioperl.org                  - General discussion
  http://bioperl.org/wiki/Mailing_lists  - About the mailing lists

=head2 Support 

Please direct usage questions or support issues to the mailing list:

I<bioperl-l@bioperl.org>

rather than to the module maintainer directly. Many experienced and 
reponsive experts will be able look at the problem and quickly 
address it. Please include a thorough description of the problem 
with code and data examples if at all possible.

=head2 Reporting Bugs

Report bugs to the Bioperl bug tracking system to help us keep track
the bugs and their resolution.  Bug reports can be submitted via the
web:

  https://redmine.open-bio.org/projects/bioperl/

=head1 AUTHORS - Andrew Macgregor

Email: andrew at cbbc.murdoch.edu.au


=head1 APPENDIX

The rest of the documentation details each of the object
methods. Internal methods are usually preceded with a _

=cut

#'
# Let the code begin...

package Bio::ClusterIO::unigene;
use strict;

use Bio::Cluster::UniGene;
use Bio::Cluster::ClusterFactory;

use base qw(Bio::ClusterIO);

my %line_is = (
		ID			=>	q/ID\s+(\w{2,3}\.\d+)/,
		TITLE			=>	q/TITLE\s+(\S.*)/,
		GENE			=>	q/GENE\s+(\S.*)/,
		CYTOBAND		=>	q/CYTOBAND\s+(\S.*)/,
		MGI			=>	q/MGI\s+(\S.*)/,
		LOCUSLINK		=>	q/LOCUSLINK\s+(\S.*)/,
		HOMOL		=>	q/HOMOL\s+(\S.*)/,
		EXPRESS			=>	q/EXPRESS\s+(\S.*)/,
		RESTR_EXPR		=>	q/RESTR_EXPR\s+(\S.*)/,
		GNM_TERMINUS		=>	q/GNM_TERMINUS\s+(\S.*)/,
		CHROMOSOME		=>	q/CHROMOSOME\s+(\S.*)/,
		STS			=>	q/STS\s+(\S.*)/,
		TXMAP			=>	q/TXMAP\s+(\S.*)/,
		PROTSIM			=>	q/PROTSIM\s+(\S.*)/,
		SCOUNT			=>	q/SCOUNT\s+(\S.*)/,
		SEQUENCE		=>	q/SEQUENCE\s+(\S.*)/,
		ACC			=>	q/ACC=(\w+)(\.\d+)?/,
		NID			=>	q/NID=\s*(\S.*)/,
		PID			=>	q/PID=\s*(\S.*)/,
		CLONE			=>	q/CLONE=\s*(\S.*)/,
		END			=>	q/END=\s*(\S.*)/,
		LID			=>	q/LID=\s*(\S.*)/,
		MGC			=>	q/MGC=\s*(\S.*)/,
		SEQTYPE		=>	q/SEQTYPE=\s*(\S.*)/,
		TRACE			=>	q/TRACE=\s*(\S.*)/,
		PERIPHERAL		=>	q/PERIPHERAL=\s*(\S.*)/,
		DELIMITER		=>	q{^//},
);

# we set the right factory here
sub _initialize {
	my($self, @args) = @_;

	$self->SUPER::_initialize(@args);
	if(! $self->cluster_factory()) {
	$self->cluster_factory(Bio::Cluster::ClusterFactory->new(
						-type => 'Bio::Cluster::UniGene'));
	}
}

=head2 next_cluster

 Title	 : next_cluster
 Usage	 : $unigene = $stream->next_cluster()
 Function: returns the next unigene in the stream
 Returns : Bio::Cluster::UniGene object
 Args	 : NONE

=cut

sub next_cluster {
	my( $self) = @_;
	local $/ = "\n//";
	return unless my $entry = $self->_readline;
	
# set up the variables we'll need
	my (%unigene,@express,@locuslink,@chromosome,
		@sts,@txmap,@protsim,@sequence);
	my $UGobj;
	
# set up the regexes

# add whitespace parsing and precompile regexes
#foreach (values %line_is) {
#	$_ =~ s/\s+/\\s+/g;
#	print STDERR "Regex is $_\n";
#	#$_ = qr/$_/x;
#}

#$line_is{'TITLE'} = qq/TITLE\\s+(\\S.+)/;

# run each line in an entry against the regexes
	foreach my $line (split /\n/, $entry) {
	  #print STDERR "Wanting to match $line\n";
		if ($line =~ /$line_is{ID}/gcx) {
			$unigene{ID} = $1;
		}
		elsif ($line =~ /$line_is{TITLE}/gcx ) {
		  #print STDERR "MATCHED with [$1]\n";
			$unigene{TITLE} = $1;
		}
		elsif ($line =~ /$line_is{GENE}/gcx) {
			$unigene{GENE} = $1;
		}
		elsif ($line =~ /$line_is{CYTOBAND}/gcx) {
			$unigene{CYTOBAND} = $1;
		}
		elsif ($line =~ /$line_is{MGI}/gcx) {
			$unigene{MGI} = $1;
		}
		elsif ($line =~ /$line_is{LOCUSLINK}/gcx) {
			@locuslink = split /;/, $1;
		}
		elsif ($line =~ /$line_is{HOMOL}/gcx) {
			$unigene{HOMOL} = $1;
		}
		elsif ($line =~ /$line_is{EXPRESS}/gcx) {
			my $express = $1;
			# remove initial semicolon if present
			$express =~ s/^;//; 
			@express = split /\s*;/, $express;
		}
		elsif ($line =~ /$line_is{RESTR_EXPR}/gcx) {
			$unigene{RESTR_EXPR} = $1;
		}
		elsif ($line =~ /$line_is{GNM_TERMINUS}/gcx) {
			$unigene{GNM_TERMINUS} = $1;
		}
		elsif ($line =~ /$line_is{CHROMOSOME}/gcx) {
			push @chromosome, $1;
		}
		elsif ($line =~ /$line_is{TXMAP}/gcx) {
			push @txmap, $1;
		}
		elsif ($line =~ /$line_is{STS}/gcx) {
			push @sts, $1;
		}
		elsif ($line =~ /$line_is{PROTSIM}/gcx) {
			push @protsim, $1;
		}
		elsif ($line =~ /$line_is{SCOUNT}/gcx) {
			$unigene{SCOUNT} = $1;
		}
		elsif ($line =~ /$line_is{SEQUENCE}/gcx) { 
			# parse into each sequence line
			my $seq = {};
			# add unigene id to each seq
			#$seq->{unigene_id} = $unigene{ID}; 
			my @items = split(/;/, $1);
			foreach (@items) {
                            if (/$line_is{ACC}/gcx) {
                                $seq->{acc} = $1;
                                # remove leading dot if version pattern matched
                                $seq->{version} = substr($2,1) if defined $2;
                            }
                            elsif (/$line_is{NID}/gcx) {
                                $seq->{nid} = $1;
                            }
                            elsif (/$line_is{PID}/gcx) {
                                $seq->{pid} = $1;
                            }
                            elsif (/$line_is{CLONE}/gcx) {
                                $seq->{clone} = $1;
                            }
                            elsif (/$line_is{END}/gcx) {
                                $seq->{end} = $1;
                            }
                            elsif (/$line_is{LID}/gcx) {
                                $seq->{lid} = $1;
                            }
                            elsif (/$line_is{MGC}/gcx) {
                                $seq->{mgc} = $1;
                            }
                            elsif (/$line_is{SEQTYPE}/gcx) {
                                $seq->{seqtype} = $1;
                            }
                            elsif (/$line_is{TRACE}/gcx) {
                                $seq->{trace} = $1;
                            }
                            elsif (/$line_is{PERIPHERAL}/gcx) {
                                $seq->{peripheral} = $1;
                            }
			}
			push @sequence, $seq;			
		}
		elsif ($line =~ /$line_is{DELIMITER}/gcx) {
			# at the end of the record, add data to the object
			$UGobj = $self->cluster_factory->create_object(
				  -display_id  => $unigene{ID},
				  -description => $unigene{TITLE},
				  -size		   => $unigene{SCOUNT},
				  -members	   => \@sequence);
			$UGobj->gene($unigene{GENE}) if defined ($unigene{GENE});
			$UGobj->cytoband($unigene{CYTOBAND}) if defined($unigene{CYTOBAND});
			$UGobj->mgi($unigene{MGI}) if defined ($unigene{MGI});
			$UGobj->locuslink(\@locuslink);
			$UGobj->homol($unigene{HOMOL}) if defined ($unigene{HOMOL});
			$UGobj->express(\@express);
			$UGobj->restr_expr($unigene{RESTR_EXPR}) if defined ($unigene{RESTR_EXPR});
			$UGobj->gnm_terminus($unigene{GNM_TERMINUS}) if defined ($unigene{GNM_TERMINUS});
			$UGobj->chromosome(\@chromosome);
			$UGobj->sts(\@sts);
			$UGobj->txmap(\@txmap);
			$UGobj->protsim(\@protsim);
		}
	}
	return $UGobj;
}

1;