[Bio] / Sprout / PropertySproutLoader.pm Repository:
ViewVC logotype

Annotation of /Sprout/PropertySproutLoader.pm

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.1 - (view) (download) (as text)

1 : parrello 1.1 #!/usr/bin/perl -w
2 :    
3 :     #
4 :     # Copyright (c) 2003-2006 University of Chicago and Fellowship
5 :     # for Interpretations of Genomes. All Rights Reserved.
6 :     #
7 :     # This file is part of the SEED Toolkit.
8 :     #
9 :     # The SEED Toolkit is free software. You can redistribute
10 :     # it and/or modify it under the terms of the SEED Toolkit
11 :     # Public License.
12 :     #
13 :     # You should have received a copy of the SEED Toolkit Public License
14 :     # along with this program; if not write to the University of Chicago
15 :     # at info@ci.uchicago.edu or the Fellowship for Interpretation of
16 :     # Genomes at veronika@thefig.info or download a copy from
17 :     # http://www.theseed.org/LICENSE.TXT.
18 :     #
19 :    
20 :     package PropertySproutLoader;
21 :    
22 :     use strict;
23 :     use Tracer;
24 :     use ERDB;
25 :     use base 'BaseSproutLoader';
26 :    
27 :     =head1 Sprout Property Load Group Class
28 :    
29 :     =head2 Introduction
30 :    
31 :     The Load Group includes all of the major searchable attribute tables.
32 :    
33 :     =head3 new
34 :    
35 :     my $sl = SproutLoader->new($erdb, $source, $options, @tables);
36 :    
37 :     Construct a new SproutLoader object.
38 :    
39 :     =over 4
40 :    
41 :     =item erdb
42 :    
43 :     [[SproutPm]] object for the database being loaded.
44 :    
45 :     =item source
46 :    
47 :     [[FigPm]] object used to access the source data. If this parameter is undefined,
48 :     it will be created the first time the L</source> method is called.
49 :    
50 :     =item options
51 :    
52 :     Reference to a hash of command-line options.
53 :    
54 :     =item tables
55 :    
56 :     List of tables in this load group.
57 :    
58 :     =back
59 :    
60 :     =cut
61 :    
62 :     sub new {
63 :     # Get the parameters.
64 :     my ($class, $erdb, $source, $options) = @_;
65 :     # Create the table list.
66 :     my @tables = sort qw(Property HasProperty);
67 :     # Create the BaseSproutLoader object.
68 :     my $retVal = BaseSproutLoader::new($class, $erdb, $source, $options, @tables);
69 :     # Return it.
70 :     return $retVal;
71 :     }
72 :    
73 :     =head2 Public Methods
74 :    
75 :     =head3 Generate
76 :    
77 :     $sl->Generate();
78 :    
79 :     Generate the data for the searchable attribute files.
80 :    
81 :     =cut
82 :    
83 :     sub Generate {
84 :     # Get the parameters.
85 :     my ($self) = @_;
86 :     # Get the sprout object.
87 :     my $sprout = $self->db();
88 :     # Get the FIG object.
89 :     my $fig = $self->source();
90 :     # All of the property stuff is done globally.
91 :     if ($self->global()) {
92 :     # Get the list of attributes we need for these searches. Currently, it's only
93 :     # essentials.
94 :     my @keys = $fig->get_group_keys('essential');
95 :     # Get a hash of genome IDs.
96 :     my %genomes = map { $_ => 1 } $self->GetSectionList();
97 :     # This will be where we compute the property IDs.
98 :     my %propIDs = ();
99 :     my $nextID = 1;
100 :     # Loop through these keys, getting feature IDs.
101 :     for my $key (@keys) {
102 :     # Get all the attributes for this key.
103 :     my @attributes = $fig->get_attributes(undef, $key);
104 :     Trace(scalar(@attributes) . " attribute values found for $key.") if T(3);
105 :     $self->Add('attribute-keys' => 1);
106 :     # Loop through them, extracting the ones for genomes in the genome hash.
107 :     for my $attributeTuple (@attributes) {
108 :     # Extract the pieces.
109 :     my ($pegID, $key, $value, $url) = @{$attributeTuple};
110 :     # Default the URL to an empty string.
111 :     $url = "" if ! defined $url;
112 :     # Only proceed if the peg ID is valid and for a known genome.
113 :     if ($pegID =~ /^fig\|(\d+\.\d+)/ && $genomes{%1}) {
114 :     # It is. Compute the property ID.
115 :     my $propertyKeyValue = "$key::$value";
116 :     my $propID = $propIDs{$propertyKeyValue};
117 :     if (! defined $propID) {
118 :     # Here we have a new key/value pair, so it gets a new ID number.
119 :     $self->Add('attribute-pairs' => 1);
120 :     $propID = $nextID++;
121 :     $propIDs{$propertyKeyValue} = $propID;
122 :     # Add this ID to the property table.
123 :     $self->PutE(Property => $propID, 'property-name' => $key, 'property-value' => $value);
124 :     }
125 :     # Connect the feature to the property.
126 :     $self->PutR(HasProperty => $pegID, $propID, evidence => $url);
127 :     $self->Add('attributes-kept' => 1);
128 :     } else {
129 :     # The object isn't a feature, or it isn't for an NMPDR genome, so we skip it.
130 :     $self->Add('attributes-skipped' => 1);
131 :     }
132 :     }
133 :     }
134 :     }
135 :     }
136 :    
137 :    
138 :     1;

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3