This file is indexed.

/usr/bin/go-dag-summary is in libgo-perl 0.13-3.

This file is owned by root:root, with mode 0o755.

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
#!/usr/bin/perl

eval 'exec /usr/bin/perl  -S $0 ${1+"$@"}'
    if 0; # not running under some shell

# POD docs at end of file

use strict;
use Getopt::Long;
use FileHandle;
use GO::Parser;
use Data::Stag;

$|=1;

my $opt = {};
GetOptions($opt,
	   "help|h",
           "format|p=s",
	   "err|e=s",
           "use_cache",
	  );

if ($opt->{help}) {
    system("perldoc $0");
    exit;
}

my $errf = $opt->{err};
my $errhandler = Data::Stag->getformathandler('xml');
if ($errf) {
    $errhandler->file($errf);
}
else {
    $errhandler->fh(\*STDERR);
}

my @files = GO::Parser->new->normalize_files(@ARGV);
while (my $fn = shift @files) {
    eval {
        summarise_file($fn);
    };
    if ($@) {
        $errhandler->err_event(exception=>"$@");
    }
}

sub summarise_file {
    my $fn = shift;
    my %h = %$opt;
    my $fmt;
    if ($fn =~ /\.obo/) {
        $fmt = 'obo_text';
    }
    if ($fn =~ /\.ont/) {
        $fmt = 'go_ont';
    }
    if ($fmt && !$h{format}) {
        $h{format} = $fmt;
    }
    $h{handler} = 'obj';
    my $parser = new GO::Parser(%h);
    $parser->litemode(1);
    $parser->use_cache(1) if $opt->{use_cache};
    $parser->errhandler($errhandler);
    $parser->parse($fn);
    my $g = $parser->handler->graph;
    my %counts = ();
    my %ns_h=();
    foreach my $t (@{$g->get_all_terms}) {
        next if $t->is_obsolete;
        my $ns = $t->term_type;
        if (!$ns) {
            if ($fn =~ /\/(.*)\.\w+/) {
                $ns = $1;
            }
            else {
                $ns = $fn;
            }
        }
        $ns_h{$ns}=1;
        my $acc = $t->acc;
        $counts{term}->{$ns}++;
        my $parent_rels = $g->get_parent_relationships($acc);
        $counts{relationship}->{$ns} += scalar(@$parent_rels);
        my $paths = $g->paths_to_top($acc);
        my $n_paths = scalar(@$paths);
        $counts{path}->{$ns} += $n_paths;
        if ($n_paths >= $counts{pathmax}->{$ns}) {
            $counts{pathmax}->{$ns} = $n_paths;            
            $counts{pathmaxacc}->{$ns} = $acc;            
            $counts{pathmaxname}->{$ns} = $t->name;            
        }


    }
    foreach my $ns (keys %ns_h) {
        printf "%s\n",
          join("\t",
               $fn,
               $ns,
               (map {$counts{$_}->{$ns}} qw(term relationship path)),
               $counts{path}->{$ns}/$counts{term}->{$ns},
               (map {$counts{$_}->{$ns}} qw(pathmax pathmaxacc pathmaxname)),
              );
    }
}
$errhandler->finish;
exit 0;


__END__

=head1 NAME

go-dag-summary - summarises an ontology

=head1 SYNOPSIS

  go-dag-summary ontology/gene_ontology.obo

=head1 DESCRIPTION

Summarises an ontology

=head1 ARGUMENTS

=head3 -e ERRFILE

writes parse errors in XML - defaults to STDERR
(there should be no parse errors in well formed files)

=head3 -p FORMAT

determines which parser to use; if left unspecified, will make a guess
based on file suffix. See below for formats

=head2 -use_cache

If this switch is specified, then caching mode is turned on.

With caching mode, the first time you parse a file, then an additional
file will be exported in a special format that is fast to parse. This
file will have the same filename as the original file, except it will
have the ".cache" suffix.

The next time you parse the file, this program will automatically
check for the existence of the ".cache" file. If it exists, and is
more recent than the file you specified, this is parsed instead. If it
does not exist, it is rebuilt.


=head1 OUTPUT

One row per ontology

Each row has the following columns

=over

=item input filename

=item total no of terms

=item total no of relationships

=item total no of paths

=item avg no of paths per term (p/t)

=item maximum no of paths for any term

=item ID of term with maximum no of paths

NOTE: obsolete terms are not included

=back

=head2 DOCUMENTATION

L<http://www.godatabase.org/dev>

=head2 SEE ALSO

L<http://www.fruitfly.org/~cjm/obol/doc/go-complexity.html>

=cut