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

Diff of /Sprout/Sprout.pm

Parent Directory Parent Directory | Revision Log Revision Log | View Patch Patch

revision 1.113, Tue Aug 12 06:01:49 2008 UTC revision 1.123, Fri Jan 23 13:44:51 2009 UTC
# Line 4  Line 4 
4      use strict;      use strict;
5      use DBKernel;      use DBKernel;
6      use XML::Simple;      use XML::Simple;
7      use DBQuery;      use ERDBQuery;
8      use ERDBObject;      use ERDBObject;
9      use Tracer;      use Tracer;
10      use FIGRules;      use FIGRules;
# Line 14  Line 14 
14      use BasicLocation;      use BasicLocation;
15      use CustomAttributes;      use CustomAttributes;
16      use RemoteCustomAttributes;      use RemoteCustomAttributes;
17      use CGI;      use CGI qw(-nosticky);
18      use WikiTools;      use WikiTools;
19        use BioWords;
20      use base qw(ERDB);      use base qw(ERDB);
21    
22  =head1 Sprout Database Manipulation Object  =head1 Sprout Database Manipulation Object
# Line 40  Line 41 
41    
42  =cut  =cut
43    
 #: Constructor SFXlate->new_sprout_only();  
   
44  =head2 Public Methods  =head2 Public Methods
45    
46  =head3 new  =head3 new
# Line 56  Line 55 
55    
56  =item dbName  =item dbName
57    
58  Name of the database.  Name of the database. If omitted, the default Sprout database name is used.
59    
60  =item options  =item options
61    
# Line 90  Line 89 
89    
90      my $sprout = Sprout->new('Sprout', { userData => 'fig/admin', dataDir => '/usr/fig/SproutData' });      my $sprout = Sprout->new('Sprout', { userData => 'fig/admin', dataDir => '/usr/fig/SproutData' });
91    
92    In order to work properly with [[ERDBGeneratorPl]], the constructor has an alternate
93    form.
94    
95        my $sprout = Sprout->new(dbd => $filename);
96    
97    Where I<$fileName> is the name of the DBD file. This enables us to specify an alternate
98    DBD for the loader, which is important when the database format changes.
99    
100  =cut  =cut
101    
102  sub new {  sub new {
103      # Get the parameters.      # Get the parameters.
104      my ($class, $dbName, $options) = @_;      my ($class, $dbName, $options) = @_;
105        # Check for the alternate signature, and default the database name if it is missing.
106        if ($dbName eq 'dbd') {
107            $dbName = $FIG_Config::sproutDB;
108            $options = { xmlFileName => $options };
109        } elsif (! defined $dbName) {
110            $dbName = $FIG_Config::sproutDB;
111        } elsif (ref $dbName eq 'HASH') {
112            $options = $dbName;
113            $dbName = $FIG_Config::sproutDB;
114        }
115      # Compute the DBD directory.      # Compute the DBD directory.
116      my $dbd_dir = (defined($FIG_Config::dbd_dir) ? $FIG_Config::dbd_dir :      my $dbd_dir = (defined($FIG_Config::dbd_dir) ? $FIG_Config::dbd_dir :
117                                                    $FIG_Config::fig );                                                    $FIG_Config::fig );
# Line 107  Line 124 
124                                                          # data file directory                                                          # data file directory
125                         xmlFileName  => "$dbd_dir/SproutDBD.xml",                         xmlFileName  => "$dbd_dir/SproutDBD.xml",
126                                                          # database definition file name                                                          # database definition file name
127                         userData     => "$FIG_Config::dbuser/$FIG_Config::dbpass",                         userData     => "$FIG_Config::sproutUser/$FIG_Config::sproutPass",
128                                                          # user name and password                                                          # user name and password
129                         port         => $FIG_Config::dbport,                         port         => $FIG_Config::sproutPort,
130                                                          # database connection port                                                          # database connection port
131                         sock         => $FIG_Config::dbsock,                         sock         => $FIG_Config::sproutSock,
132                         host         => $FIG_Config::sprout_host,                         host         => $FIG_Config::sprout_host,
133                         maxSegmentLength => 4500,        # maximum feature segment length                         maxSegmentLength => 4500,        # maximum feature segment length
134                         maxSequenceLength => 8000,       # maximum contig sequence length                         maxSequenceLength => 8000,       # maximum contig sequence length
135                         noDBOpen     => 0,               # 1 to suppress the database open                         noDBOpen     => 0,               # 1 to suppress the database open
136                           demandDriven => 0,               # 1 for forward-only queries
137                        }, $options);                        }, $options);
138      # Get the data directory.      # Get the data directory.
139      my $dataDir = $optionTable->{dataDir};      my $dataDir = $optionTable->{dataDir};
# Line 131  Line 149 
149      }      }
150      # Create the ERDB object.      # Create the ERDB object.
151      my $xmlFileName = "$optionTable->{xmlFileName}";      my $xmlFileName = "$optionTable->{xmlFileName}";
152      my $retVal = ERDB::new($class, $dbh, $xmlFileName);      my $retVal = ERDB::new($class, $dbh, $xmlFileName, %$optionTable);
153      # Add the option table and XML file name.      # Add the option table and XML file name.
154      $retVal->{_options} = $optionTable;      $retVal->{_options} = $optionTable;
155      $retVal->{_xmlName} = $xmlFileName;      $retVal->{_xmlName} = $xmlFileName;
156      # Set up space for the group file data.      # Set up space for the group file data.
157      $retVal->{groupHash} = undef;      $retVal->{groupHash} = undef;
158      # Set up space for the genome hash. We use this to identify NMPDR genomes.      # Set up space for the genome hash. We use this to identify NMPDR genomes
159      $retVal->{genomeHash} = undef;      # and remember genome data.
160      # Connect to the attributes.      $retVal->{genomeHash} = {};
161        $retVal->{genomeHashFilled} = 0;
162        # Remember the data directory name.
163        $retVal->{dataDir} = $dataDir;
164        # Return it.
165        return $retVal;
166    }
167    
168    =head3 ca
169    
170        my $ca = $sprout->ca():;
171    
172    Return the [[CustomAttributesPm]] object for retrieving object
173    properties.
174    
175    =cut
176    
177    sub ca {
178        # Get the parameters.
179        my ($self) = @_;
180        # Do we already have an attribute object?
181        my $retVal = $self->{_ca};
182        if (! defined $retVal) {
183            # No, create one. How we do it depends on the configuration.
184      if ($FIG_Config::attrURL) {      if ($FIG_Config::attrURL) {
185          Trace("Remote attribute server $FIG_Config::attrURL chosen.") if T(3);          Trace("Remote attribute server $FIG_Config::attrURL chosen.") if T(3);
186          $retVal->{_ca} = RemoteCustomAttributes->new($FIG_Config::attrURL);              $retVal = RemoteCustomAttributes->new($FIG_Config::attrURL);
187      } elsif ($FIG_Config::attrDbName) {      } elsif ($FIG_Config::attrDbName) {
188          Trace("Local attribute database $FIG_Config::attrDbName chosen.") if T(3);          Trace("Local attribute database $FIG_Config::attrDbName chosen.") if T(3);
189          my $user = ($FIG_Config::arch eq 'win' ? 'self' : scalar(getpwent()));          my $user = ($FIG_Config::arch eq 'win' ? 'self' : scalar(getpwent()));
190          $retVal->{_ca} = CustomAttributes->new(user => $user);              $retVal = CustomAttributes->new(user => $user);
191      }      }
192      # Insure we have access to the stem module.          # Save it for next time.
193      WikiUse('Lingua::Stem');          $self->{_ca} = $retVal;
194      $retVal->{stemmer} = Lingua::Stem->new();      }
195      $retVal->{stemmer}->stem_caching({ -level => 2 });      # Return the result.
     # Return it.  
196      return $retVal;      return $retVal;
197  }  }
198    
# Line 314  Line 354 
354  The files are loaded based on the presumption that each line of the file is a record in the  The files are loaded based on the presumption that each line of the file is a record in the
355  relation, and the individual fields are delimited by tabs. Tab and new-line characters inside  relation, and the individual fields are delimited by tabs. Tab and new-line characters inside
356  fields must be represented by the escape sequences C<\t> and C<\n>, respectively. The fields must  fields must be represented by the escape sequences C<\t> and C<\n>, respectively. The fields must
357  be presented in the order given in the relation tables produced by the L</ShowMetaData> method.  be presented in the order given in the relation tables produced by the database documentation.
358    
359  =over 4  =over 4
360    
# Line 503  Line 543 
543  =item filter  =item filter
544    
545  If specified, a filter for the list of genomes to display. The filter should be in the form of a  If specified, a filter for the list of genomes to display. The filter should be in the form of a
546  list reference. The first element of the list should be the filter string, and the remaining elements  list reference, a string, or a hash reference. If it is a list reference, the first element
547  the filter parameters.  of the list should be the filter string, and the remaining elements the filter parameters. If it is a
548    string, it will be split into a list at each included tab. If it is a hash reference, it should be
549    a hash that maps genomes which should be included to a TRUE value.
550    
551  =item multiSelect  =item multiSelect
552    
# Line 536  Line 578 
578      # Get the parameters.      # Get the parameters.
579      my ($self, %options) = @_;      my ($self, %options) = @_;
580      # Get the control's name and ID.      # Get the control's name and ID.
581      my $menuName = $options{name} || 'myGenomeControl';      my $menuName = $options{name} || $options{id} || 'myGenomeControl';
582      my $menuID = $options{id} || $menuName;      my $menuID = $options{id} || $menuName;
583        Trace("Genome menu name = $menuName with ID $menuID.") if T(3);
584      # Compute the IDs for the status display.      # Compute the IDs for the status display.
585      my $divID = "${menuID}_status";      my $divID = "${menuID}_status";
586      my $urlID = "${menuID}_url";      my $urlID = "${menuID}_url";
587      # Compute the code to show selected genomes in the status area.      # Compute the code to show selected genomes in the status area.
588      my $showSelect = "showSelected('$menuID', '$divID', '$urlID', 1000)";      my $showSelect = "showSelected('$menuID', '$divID', '$urlID', $FIG_Config::genome_control_cap)";
589      # Check for single-select or multi-select.      # Check for single-select or multi-select.
590      my $multiSelect = $options{multiSelect} || 0;      my $multiSelect = $options{multiSelect} || 0;
591      # Get the style data.      # Get the style data.
# Line 554  Line 597 
597      }      }
598      my %selected = map { $_ => 1 } @{$selections};      my %selected = map { $_ => 1 } @{$selections};
599      # Extract the filter information. The default is no filtering. It can be passed as a tab-delimited      # Extract the filter information. The default is no filtering. It can be passed as a tab-delimited
600      # string or a list reference.      # string, a hash reference, or a list reference.
601        my ($filterHash, $filterString);
602      my $filterParms = $options{filter} || "";      my $filterParms = $options{filter} || "";
603        if (ref $filterParms eq 'HASH') {
604            $filterHash = $filterParms;
605            $filterParms = [];
606            $filterString = "";
607        } else {
608      if (! ref $filterParms) {      if (! ref $filterParms) {
609          $filterParms = [split /\t|\\t/, $filterParms];          $filterParms = [split /\t|\\t/, $filterParms];
610      }      }
611      my $filterString = shift @{$filterParms};          $filterString = shift @{$filterParms};
612        }
613        # Check for possible subsystem filtering. If there is one, we will tack the
614        # relationship onto the object name list.
615        my @objectNames = qw(Genome);
616        if ($filterString =~ /ParticipatesIn\(/) {
617            push @objectNames, 'ParticipatesIn';
618        }
619      # Get a list of all the genomes in group order. In fact, we only need them ordered      # Get a list of all the genomes in group order. In fact, we only need them ordered
620      # by name (genus,species,strain), but putting primary-group in front enables us to      # by name (genus,species,strain), but putting primary-group in front enables us to
621      # take advantage of an existing index.      # take advantage of an existing index.
622      my @genomeList = $self->GetAll(['Genome'], "$filterString ORDER BY Genome(primary-group), Genome(genus), Genome(species), Genome(unique-characterization)",      my @genomeList = $self->GetAll(\@objectNames, "$filterString ORDER BY Genome(primary-group), Genome(genus), Genome(species), Genome(unique-characterization)",
623                                     $filterParms,                                     $filterParms,
624                                     [qw(Genome(primary-group) Genome(id) Genome(genus) Genome(species) Genome(unique-characterization) Genome(taxonomy) Genome(contigs))]);                                     [qw(Genome(primary-group) Genome(id) Genome(genus) Genome(species) Genome(unique-characterization) Genome(taxonomy) Genome(contigs))]);
625        # Apply the hash filter (if any).
626        if (defined $filterHash) {
627            @genomeList = grep { $filterHash->{$_->[1]} } @genomeList;
628        }
629      # Create a hash to organize the genomes by group. Each group will contain a list of      # Create a hash to organize the genomes by group. Each group will contain a list of
630      # 2-tuples, the first element being the genome ID and the second being the genome      # 2-tuples, the first element being the genome ID and the second being the genome
631      # name.      # name.
# Line 595  Line 655 
655      my @groups = map { $sortGroups{$_} } sort keys %sortGroups;      my @groups = map { $sortGroups{$_} } sort keys %sortGroups;
656      # Remember the number of NMPDR groups.      # Remember the number of NMPDR groups.
657      my $nmpdrGroupCount = scalar @groups;      my $nmpdrGroupCount = scalar @groups;
658        # Are there any supporting genomes?
659        if (exists $gHash{$FIG_Config::otherGroup}) {
660      # Loop through the supporting genomes, classifying them by domain. We'll also keep a list      # Loop through the supporting genomes, classifying them by domain. We'll also keep a list
661      # of the domains found.      # of the domains found.
662      my @otherGenomes = @{$gHash{$FIG_Config::otherGroup}};      my @otherGenomes = @{$gHash{$FIG_Config::otherGroup}};
# Line 613  Line 675 
675      push @groups, sort @domains;      push @groups, sort @domains;
676      # Delete the supporting group.      # Delete the supporting group.
677      delete $gHash{$FIG_Config::otherGroup};      delete $gHash{$FIG_Config::otherGroup};
678        }
679      # Now it gets complicated. We need a way to mark all the NMPDR genomes. We take advantage      # Now it gets complicated. We need a way to mark all the NMPDR genomes. We take advantage
680      # of the fact they come first in the list. We'll accumulate a count of the NMPDR genomes      # of the fact they come first in the list. We'll accumulate a count of the NMPDR genomes
681      # and use that to make the selections.      # and use that to make the selections.
# Line 628  Line 691 
691      # Set up the style class.      # Set up the style class.
692      my $classTag = ($class ? " class=\"$class\"" : "" );      my $classTag = ($class ? " class=\"$class\"" : "" );
693      # Create the SELECT tag and stuff it into the output array.      # Create the SELECT tag and stuff it into the output array.
694      my @lines = ("<SELECT name=\"$menuID\" id=\"$menuID\" $onChangeTag$multipleTag$classTag size=\"$rows\">");      my @lines = ("<SELECT name=\"$menuName\" id=\"$menuID\" $onChangeTag$multipleTag$classTag size=\"$rows\">");
695      # Loop through the groups.      # Loop through the groups.
696      for my $group (@groups) {      for my $group (@groups) {
697          # Get the genomes in the group.          # Get the genomes in the group.
# Line 664  Line 727 
727          my $searchThingLabel = ($multiSelect ? "<INPUT type=\"button\" name=\"MacroSearch\" class=\"button\" value=\"Select genomes containing\" onClick=\"selectShowing('$menuID', '$searchThingName'); $showSelect;\" />"          my $searchThingLabel = ($multiSelect ? "<INPUT type=\"button\" name=\"MacroSearch\" class=\"button\" value=\"Select genomes containing\" onClick=\"selectShowing('$menuID', '$searchThingName'); $showSelect;\" />"
728                                               : "Show genomes containing");                                               : "Show genomes containing");
729          push @lines, "<br />$searchThingLabel&nbsp;" .          push @lines, "<br />$searchThingLabel&nbsp;" .
730                       "<INPUT type=\"text\" id=\"$searchThingName\" name=\"$searchThingName\" size=\"30\" onKeyup=\"showTyped('$menuID', '$searchThingName');\" />";                       "<INPUT type=\"text\" id=\"$searchThingName\" name=\"$searchThingName\" size=\"30\" onKeyup=\"showTyped('$menuID', '$searchThingName');\" />" .
731                         Hint("GenomeControl", "Type here to filter the genomes displayed.") . "<br />";
732          # For multi-select mode, we also have buttons to set and clear selections.          # For multi-select mode, we also have buttons to set and clear selections.
733          if ($multiSelect) {          if ($multiSelect) {
734              push @lines, "<INPUT type=\"button\" name=\"ClearAll\" class=\"bigButton\"  value=\"Clear All\" onClick=\"clearAll('$menuID'); $showSelect\" />";              push @lines, "<INPUT type=\"button\" name=\"ClearAll\" class=\"bigButton\"  value=\"Clear All\" onClick=\"clearAll(getElementById('$menuID')); $showSelect\" />";
735              push @lines, "<INPUT type=\"button\" name=\"SelectAll\" class=\"bigButton\" value=\"Select All\" onClick=\"selectAll('$menuID'); $showSelect\" />";              push @lines, "<INPUT type=\"button\" name=\"SelectAll\" class=\"bigButton\" value=\"Select All\" onClick=\"selectAll(getElementById('$menuID')); $showSelect\" />";
736              push @lines, "<INPUT type=\"button\" name=\"NMPDROnly\" class=\"bigButton\"  value=\"Select NMPDR\" onClick=\"selectSome('$menuID', $nmpdrCount, true); $showSelect;\" />";              push @lines, "<INPUT type=\"button\" name=\"NMPDROnly\" class=\"bigButton\"  value=\"Select NMPDR\" onClick=\"selectSome(getElementById('$menuID'), $nmpdrCount, true); $showSelect;\" />";
737          }          }
738          # Add a hidden field we can use to generate organism page hyperlinks.          # Add a hidden field we can use to generate organism page hyperlinks.
739          push @lines, "<INPUT type=\"hidden\" id=\"$urlID\" value=\"$FIG_Config::cgi_url/seedviewer.cgi?page=Organism;organism=\" />";          push @lines, "<INPUT type=\"hidden\" id=\"$urlID\" value=\"$FIG_Config::cgi_url/wiki/rest.cgi/NmpdrPlugin/SeedViewer?page=Organism;organism=\" />";
740          # Add the status display. This tells the user what's selected no matter where the list is scrolled.          # Add the status display. This tells the user what's selected no matter where the list is scrolled.
741          push @lines, "<DIV id=\"$divID\" class=\"Panel\"></DIV>";          push @lines, "<DIV id=\"$divID\" class=\"Panel\"></DIV>";
742      }      }
# Line 709  Line 773 
773  sub Stem {  sub Stem {
774      # Get the parameters.      # Get the parameters.
775      my ($self, $word) = @_;      my ($self, $word) = @_;
776      # Declare the return variable.      # Get the stemmer object.
777      my $retVal;      my $stemmer = $self->{stemmer};
778      # See if it's stemmable.      if (! defined $stemmer) {
779      if ($word =~ /^[A-Za-z]+$/) {          # We don't have one pre-built, so we build and save it now.
780          # Compute the stem.          $stemmer = BioWords->new(exceptions => "$FIG_Config::sproutData/Exceptions.txt",
781          my $stemList = $self->{stemmer}->stem($word);                                   stops => "$FIG_Config::sproutData/StopWords.txt",
782          my $stem = $stemList->[0];                                   cache => 0);
783          # Check to see if it's long enough.          $self->{stemmer} = $stemmer;
         if (length $stem >= 3) {  
             # Yes, keep it.  
             $retVal = $stem;  
         } else {  
             # No, use the original word.  
             $retVal = $word;  
         }  
784      }      }
785        # Try to stem the word.
786        my $retVal = $stemmer->Process($word);
787      # Return the result.      # Return the result.
788      return $retVal;      return $retVal;
789  }  }
# Line 788  Line 847 
847  sub GenusSpecies {  sub GenusSpecies {
848      # Get the parameters.      # Get the parameters.
849      my ($self, $genomeID) = @_;      my ($self, $genomeID) = @_;
850      # Get the data for the specified genome.      # Declare the return value.
851      my @values = $self->GetEntityValues('Genome', $genomeID, ['Genome(genus)', 'Genome(species)',      my $retVal;
852                                                                'Genome(unique-characterization)']);      # Get the genome data.
853      # Format the result and return it.      my $genomeData = $self->_GenomeData($genomeID);
854      my $retVal = join(' ', @values);      # Only proceed if we found the genome.
855        if (defined $genomeData) {
856            $retVal = $genomeData->PrimaryValue('Genome(scientific-name)');
857        }
858        # Return it.
859      return $retVal;      return $retVal;
860  }  }
861    
# Line 1130  Line 1193 
1193      my ($self, $genomeID) = @_;      my ($self, $genomeID) = @_;
1194      # Declare the return variable.      # Declare the return variable.
1195      my $retVal = 0;      my $retVal = 0;
1196      # Get the genome's contig sequence lengths.      # Get the genome data.
1197      my @lens = $self->GetFlat(['HasContig', 'IsMadeUpOf'], 'HasContig(from-link) = ?',      my $genomeData = $self->_GenomeData($genomeID);
1198                         [$genomeID], 'IsMadeUpOf(len)');      # Only proceed if it exists.
1199      # Sum the lengths.      if (defined $genomeData) {
1200      map { $retVal += $_ } @lens;          $retVal = $genomeData->PrimaryValue('Genome(dna-size)');
1201        }
1202      # Return the result.      # Return the result.
1203      return $retVal;      return $retVal;
1204  }  }
# Line 1619  Line 1683 
1683  the specified user and FIG are considered trusted. If the user ID is omitted, only FIG  the specified user and FIG are considered trusted. If the user ID is omitted, only FIG
1684  is trusted.  is trusted.
1685    
1686  If the feature is B<not> identified by a FIG ID, then the functional assignment  If the feature is B<not> identified by a FIG ID, then we search the aliases for it.
1687  information is taken from the B<ExternalAliasFunc> table. If the table does  If no matching alias is found, we return an undefined value.
 not contain an entry for the feature, an undefined value is returned.  
1688    
1689  =over 4  =over 4
1690    
# Line 1647  Line 1710 
1710      my ($self, $featureID, $userID) = @_;      my ($self, $featureID, $userID) = @_;
1711      # Declare the return value.      # Declare the return value.
1712      my $retVal;      my $retVal;
1713      # Determine the ID type.      # Find a FIG ID for this feature.
1714      if ($featureID =~ m/^fig\|/) {      my ($fid) = $self->FeaturesByAlias($featureID);
1715        # Only proceed if we have an ID.
1716        if ($fid) {
1717          # Here we have a FIG feature ID.          # Here we have a FIG feature ID.
1718          if (!$userID) {          if (!$userID) {
1719              # Use the primary assignment.              # Use the primary assignment.
1720              ($retVal) = $self->GetEntityValues('Feature', $featureID, ['Feature(assignment)']);              ($retVal) = $self->GetEntityValues('Feature', $fid, ['Feature(assignment)']);
1721          } else {          } else {
1722              # We must build the list of trusted users.              # We must build the list of trusted users.
1723              my %trusteeTable = ();              my %trusteeTable = ();
# Line 1678  Line 1743 
1743              # Build a query for all of the feature's annotations, sorted by date.              # Build a query for all of the feature's annotations, sorted by date.
1744              my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],              my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1745                                     "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",                                     "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1746                                     [$featureID]);                                     [$fid]);
1747              my $timeSelected = 0;              my $timeSelected = 0;
1748              # Loop until we run out of annotations.              # Loop until we run out of annotations.
1749              while (my $annotation = $query->Fetch()) {              while (my $annotation = $query->Fetch()) {
# Line 1698  Line 1763 
1763                  }                  }
1764              }              }
1765          }          }
     } else {  
         # Here we have a non-FIG feature ID. In this case the user ID does not  
         # matter. We simply get the information from the External Alias Function  
         # table.  
         ($retVal) = $self->GetEntityValues('ExternalAliasFunc', $featureID, ['ExternalAliasFunc(func)']);  
1766      }      }
1767      # Return the assignment found.      # Return the assignment found.
1768      return $retVal;      return $retVal;
# Line 1721  Line 1781 
1781  annotation itself because it's a text field; however, this is not a big problem because  annotation itself because it's a text field; however, this is not a big problem because
1782  most features only have a small number of annotations.  most features only have a small number of annotations.
1783    
 If the feature is B<not> identified by a FIG ID, then the functional assignment  
 information is taken from the B<ExternalAliasFunc> table. If the table does  
 not contain an entry for the feature, an empty list is returned.  
   
1784  =over 4  =over 4
1785    
1786  =item featureID  =item featureID
# Line 1745  Line 1801 
1801      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
1802      # Declare the return value.      # Declare the return value.
1803      my @retVal = ();      my @retVal = ();
1804      # Determine the ID type.      # Convert to a FIG ID.
1805      if ($featureID =~ m/^fig\|/) {      my ($fid) = $self->FeaturesByAlias($featureID);
1806        # Only proceed if we found one.
1807        if ($fid) {
1808          # Here we have a FIG feature ID. We must build the list of trusted          # Here we have a FIG feature ID. We must build the list of trusted
1809          # users.          # users.
1810          my %trusteeTable = ();          my %trusteeTable = ();
1811          # Build a query for all of the feature's annotations, sorted by date.          # Build a query for all of the feature's annotations, sorted by date.
1812          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1813                                 "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",                                 "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1814                                 [$featureID]);                                 [$fid]);
1815          my $timeSelected = 0;          my $timeSelected = 0;
1816          # Loop until we run out of annotations.          # Loop until we run out of annotations.
1817          while (my $annotation = $query->Fetch()) {          while (my $annotation = $query->Fetch()) {
# Line 1768  Line 1826 
1826                  push @retVal, [$actualUser, $function];                  push @retVal, [$actualUser, $function];
1827              }              }
1828          }          }
     } else {  
         # Here we have a non-FIG feature ID. In this case the user ID does not  
         # matter. We simply get the information from the External Alias Function  
         # table.  
         my @assignments = $self->GetEntityValues('ExternalAliasFunc', $featureID,  
                                                  ['ExternalAliasFunc(func)']);  
         push @retVal, map { ['master', $_] } @assignments;  
1829      }      }
1830      # Return the assignments found.      # Return the assignments found.
1831      return @retVal;      return @retVal;
# Line 1814  Line 1865 
1865      # Loop through the incoming features.      # Loop through the incoming features.
1866      for my $featureID (@{$featureList}) {      for my $featureID (@{$featureList}) {
1867          # Ask the server for the feature's best hit.          # Ask the server for the feature's best hit.
1868          my @bbhData = FIGRules::BBHData($featureID);          my $bbhData = FIGRules::BBHData($featureID);
1869          # Peel off the BBHs found.          # Peel off the BBHs found.
1870          my @found = ();          my @found = ();
1871          for my $bbh (@bbhData) {          for my $bbh (@$bbhData) {
1872              my $fid = $bbh->[0];              my $fid = $bbh->[0];
1873              my $bbGenome = $self->GenomeOf($fid);              my $bbGenome = $self->GenomeOf($fid);
1874              if ($bbGenome eq $genomeID) {              if ($bbGenome eq $genomeID) {
# Line 1856  Line 1907 
1907      # Get the parameters.      # Get the parameters.
1908      my ($self, $featureID, $count) = @_;      my ($self, $featureID, $count) = @_;
1909      # Ask for the best hits.      # Ask for the best hits.
1910      my @lists = FIGRules::BBHData($featureID);      my $lists = FIGRules::BBHData($featureID);
1911      # Create the return value.      # Create the return value.
1912      my %retVal = ();      my %retVal = ();
1913      for my $tuple (@lists) {      for my $tuple (@$lists) {
1914          $retVal{$tuple->[0]} = $tuple->[1];          $retVal{$tuple->[0]} = $tuple->[1];
1915      }      }
1916      # Return the result.      # Return the result.
# Line 1893  Line 1944 
1944      # Declare the return variable.      # Declare the return variable.
1945      my $retVal;      my $retVal;
1946      # Get the genome's data.      # Get the genome's data.
1947      my $genomeData = $self->GetEntity('Genome', $genomeID);      my $genomeData = $self->_GenomeData($genomeID);
1948      if ($genomeData) {      # Only proceed if it exists.
1949        if (defined $genomeData) {
1950          # The genome exists, so get the completeness flag.          # The genome exists, so get the completeness flag.
1951          $retVal = $genomeData->PrimaryValue('Genome(complete)');          $retVal = $genomeData->PrimaryValue('Genome(complete)');
1952      }      }
# Line 1966  Line 2018 
2018          my ($realFeatureID) = $self->FeaturesByAlias($featureID);          my ($realFeatureID) = $self->FeaturesByAlias($featureID);
2019          if ($realFeatureID && $realFeatureID =~ /^fig\|(\d+\.\d+)/) {          if ($realFeatureID && $realFeatureID =~ /^fig\|(\d+\.\d+)/) {
2020              $retVal = $1;              $retVal = $1;
         } else {  
             # Use the external table.  
             my ($org) = $self->GetFlat(['ExternalAliasOrg'], "ExternalAliasOrg(id) = ?",  
                                        [$featureID], "ExternalAliasOrg(org)");  
             if ($org) {  
                 $retVal = $org;  
             } else {  
                 Confess("Invalid feature ID $featureID.");  
             }  
2021          }          }
2022      }      }
2023      # Return the value found.      # Return the value found.
# Line 2019  Line 2062 
2062              $retVal{$featureID2} = $score;              $retVal{$featureID2} = $score;
2063          }          }
2064      }      }
     # Functional coupling is reflexive. If we found at least one coupled feature, we must add  
     # the incoming feature as well.  
     if (keys %retVal) {  
         $retVal{$featureID} = 9999;  
     }  
2065      # Return the hash.      # Return the hash.
2066      return %retVal;      return %retVal;
2067  }  }
# Line 2380  Line 2418 
2418  sub GetGenomeNameData {  sub GetGenomeNameData {
2419      # Get the parameters.      # Get the parameters.
2420      my ($self, $genomeID) = @_;      my ($self, $genomeID) = @_;
2421        # Declare the return variables.
2422        my ($genus, $species, $strain);
2423        # Get the genome's data.
2424        my $genomeData = $self->_GenomeData($genomeID);
2425        # Only proceed if the genome exists.
2426        if (defined $genomeData) {
2427      # Get the desired values.      # Get the desired values.
2428      my ($genus, $species, $strain) = $self->GetEntityValues('Genome', $genomeID =>          ($genus, $species, $strain) = $genomeData->Values(['Genome(genus)',
2429                                                              [qw(Genome(genus) Genome(species) Genome(unique-characterization))]);                                                             'Genome(species)',
2430      # Throw an error if they were not found.                                                             'Genome(unique-characterization)']);
2431      if (! defined $genus) {      } else {
2432            # Throw an error because they were not found.
2433          Confess("Genome $genomeID not found in database.");          Confess("Genome $genomeID not found in database.");
2434      }      }
2435      # Return the results.      # Return the results.
# Line 2685  Line 2730 
2730  sub Taxonomy {  sub Taxonomy {
2731      # Get the parameters.      # Get the parameters.
2732      my ($self, $genome) = @_;      my ($self, $genome) = @_;
     # Find the specified genome's taxonomy string.  
     my ($list) = $self->GetEntityValues('Genome', $genome, ['Genome(taxonomy)']);  
2733      # Declare the return variable.      # Declare the return variable.
2734      my @retVal = ();      my @retVal = ();
2735      # If we found the genome, return its taxonomy string.      # Get the genome data.
2736      if ($list) {      my $genomeData = $self->_GenomeData($genome);
2737          @retVal = split /\s*;\s*/, $list;      # Only proceed if it exists.
2738        if (defined $genomeData) {
2739            # Create the taxonomy from the taxonomy string.
2740            @retVal = split /\s*;\s*/, $genomeData->PrimaryValue('Genome(taxonomy)');
2741      } else {      } else {
2742            # Genome doesn't exist, so emit a warning.
2743          Trace("Genome \"$genome\" does not have a taxonomy in the database.\n") if T(0);          Trace("Genome \"$genome\" does not have a taxonomy in the database.\n") if T(0);
2744      }      }
2745      # Return the value found.      # Return the value found.
# Line 2737  Line 2784 
2784      }      }
2785      my @taxA = $self->Taxonomy($genomeA);      my @taxA = $self->Taxonomy($genomeA);
2786      my @taxB = $self->Taxonomy($genomeB);      my @taxB = $self->Taxonomy($genomeB);
2787      # Initialize the distance to 1. We'll reduce it each time we find a match between the      # Compute the distance.
2788      # taxonomies.      my $retVal = FIGRules::CrudeDistanceFormula(\@taxA, \@taxB);
     my $retVal = 1.0;  
     # Initialize the subtraction amount. This amount determines the distance reduction caused  
     # by a mismatch at the current level.  
     my $v = 0.5;  
     # Loop through the taxonomies.  
     for (my $i = 0; ($i < @taxA) && ($i < @taxB) && ($taxA[$i] eq $taxB[$i]); $i++) {  
         $retVal -= $v;  
         $v /= 2;  
     }  
2789      return $retVal;      return $retVal;
2790  }  }
2791    
# Line 2815  Line 2853 
2853      return @retVal;      return @retVal;
2854  }  }
2855    
 =head3 GetProperties  
   
     my @list = $sprout->GetProperties($fid, $key, $value, $url);  
   
 Return a list of the properties with the specified characteristics.  
   
 Properties are the Sprout analog of the FIG attributes. The call is  
 passed directly to the CustomAttributes or RemoteCustomAttributes object  
 contained in this object.  
   
 This method returns a series of tuples that match the specified criteria. Each tuple  
 will contain an object ID, a key, and one or more values. The parameters to this  
 method therefore correspond structurally to the values expected in each tuple. In  
 addition, you can ask for a generic search by suffixing a percent sign (C<%>) to any  
 of the parameters. So, for example,  
   
     my @attributeList = $sprout->GetProperties('fig|100226.1.peg.1004', 'structure%', 1, 2);  
   
 would return something like  
   
     ['fig}100226.1.peg.1004', 'structure', 1, 2]  
     ['fig}100226.1.peg.1004', 'structure1', 1, 2]  
     ['fig}100226.1.peg.1004', 'structure2', 1, 2]  
     ['fig}100226.1.peg.1004', 'structureA', 1, 2]  
   
 Use of C<undef> in any position acts as a wild card (all values). You can also specify  
 a list reference in the ID column. Thus,  
   
     my @attributeList = $sprout->GetProperties(['100226.1', 'fig|100226.1.%'], 'PUBMED');  
   
 would get the PUBMED attribute data for Streptomyces coelicolor A3(2) and all its  
 features.  
   
 In addition to values in multiple sections, a single attribute key can have multiple  
 values, so even  
   
     my @attributeList = $sprout->GetProperties($peg, 'virulent');  
   
 which has no wildcard in the key or the object ID, may return multiple tuples.  
   
 =over 4  
   
 =item objectID  
   
 ID of object whose attributes are desired. If the attributes are desired for multiple  
 objects, this parameter can be specified as a list reference. If the attributes are  
 desired for all objects, specify C<undef> or an empty string. Finally, you can specify  
 attributes for a range of object IDs by putting a percent sign (C<%>) at the end.  
   
 =item key  
   
 Attribute key name. A value of C<undef> or an empty string will match all  
 attribute keys. If the values are desired for multiple keys, this parameter can be  
 specified as a list reference. Finally, you can specify attributes for a range of  
 keys by putting a percent sign (C<%>) at the end.  
   
 =item values  
   
 List of the desired attribute values, section by section. If C<undef>  
 or an empty string is specified, all values in that section will match. A  
 generic match can be requested by placing a percent sign (C<%>) at the end.  
 In that case, all values that match up to and not including the percent sign  
 will match. You may also specify a regular expression enclosed  
 in slashes. All values that match the regular expression will be returned. For  
 performance reasons, only values have this extra capability.  
   
 =item RETURN  
   
 Returns a list of tuples. The first element in the tuple is an object ID, the  
 second is an attribute key, and the remaining elements are the sections of  
 the attribute value. All of the tuples will match the criteria set forth in  
 the parameter list.  
   
 =back  
   
 =cut  
   
 sub GetProperties {  
     # Get the parameters.  
     my ($self, @parms) = @_;  
     # Declare the return variable.  
     my @retVal = $self->{_ca}->GetAttributes(@parms);  
     # Return the result.  
     return @retVal;  
 }  
   
2856  =head3 FeatureProperties  =head3 FeatureProperties
2857    
2858      my @properties = $sprout->FeatureProperties($featureID);      my @properties = $sprout->FeatureProperties($featureID);
# Line 2929  Line 2881 
2881      # Get the parameters.      # Get the parameters.
2882      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
2883      # Get the properties.      # Get the properties.
2884      my @attributes = $self->{_ca}->GetAttributes($featureID);      my @attributes = $self->ca->GetAttributes($featureID);
2885      # Strip the feature ID off each tuple.      # Strip the feature ID off each tuple.
2886      my @retVal = ();      my @retVal = ();
2887      for my $attributeRow (@attributes) {      for my $attributeRow (@attributes) {
# Line 3201  Line 3153 
3153  sub SubsystemList {  sub SubsystemList {
3154      # Get the parameters.      # Get the parameters.
3155      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
3156      # Get the list of names.      # Get the list of names. We do a join to the Subsystem table because we have missing subsystems in
3157      my @retVal = $self->GetFlat(['HasRoleInSubsystem'], "HasRoleInSubsystem(from-link) = ?",      # the Sprout database!
3158        my @retVal = $self->GetFlat(['HasRoleInSubsystem', 'Subsystem'], "HasRoleInSubsystem(from-link) = ?",
3159                                  [$featureID], 'HasRoleInSubsystem(to-link)');                                  [$featureID], 'HasRoleInSubsystem(to-link)');
3160      # Return the result, sorted.      # Return the result, sorted.
3161      return sort @retVal;      return sort @retVal;
# Line 3235  Line 3188 
3188      # Declare the return variable.      # Declare the return variable.
3189      my %retVal = ();      my %retVal = ();
3190      # Get a list of the genome features that participate in subsystems. For each      # Get a list of the genome features that participate in subsystems. For each
3191      # feature we get its spreadsheet cells and the corresponding roles.      # feature we get its subsystem ID and the corresponding roles.
3192      my @roleData = $self->GetAll(['HasFeature', 'ContainsFeature', 'IsRoleOf'],      my @roleData = $self->GetAll(['HasFeature', 'ContainsFeature', 'IsRoleOf', 'HasSSCell'],
3193                               "HasFeature(from-link) = ?", [$genomeID],                               "HasFeature(from-link) = ?", [$genomeID],
3194                               ['HasFeature(to-link)', 'IsRoleOf(to-link)', 'IsRoleOf(from-link)']);                                   ['HasFeature(to-link)', 'IsRoleOf(from-link)',  'HasSSCell(from-link)']);
3195      # Now we get a list of the spreadsheet cells and their associated subsystems. Subsystems      # Now we get a list of valid subsystems. These are the subsystems connected to the genome with
3196      # with an unknown variant code (-1) are skipped. Note the genome ID is at both ends of the      # a non-negative variant code.
3197      # list. We use it at the beginning to get all the spreadsheet cells for the genome and      my %subs = map { $_ => 1 } $self->GetFlat(['ParticipatesIn'],
3198      # again at the end to filter out participation in subsystems with a negative variant code.                                                  "ParticipatesIn(from-link) = ? AND ParticipatesIn(variant-code) >= 0",
3199      my @cellData = $self->GetAll(['IsGenomeOf', 'HasSSCell', 'ParticipatesIn'],                                                  [$genomeID], 'ParticipatesIn(to-link)');
3200                                   "IsGenomeOf(from-link) = ? AND ParticipatesIn(variant-code) >= 0 AND ParticipatesIn(from-link) = ?",      # We loop through @roleData to build the hash.
                                  [$genomeID, $genomeID], ['HasSSCell(to-link)', 'HasSSCell(from-link)']);  
     # Now "@roleData" lists the spreadsheet cell and role for each of the genome's features.  
     # "@cellData" lists the subsystem name for each of the genome's spreadsheet cells. We  
     # link these two lists together to create the result. First, we want a hash mapping  
     # spreadsheet cells to subsystem names.  
     my %subHash = map { $_->[0] => $_->[1] } @cellData;  
     # We loop through @cellData to build the hash.  
3201      for my $roleEntry (@roleData) {      for my $roleEntry (@roleData) {
3202          # Get the data for this feature and cell.          # Get the data for this feature and cell.
3203          my ($fid, $cellID, $role) = @{$roleEntry};          my ($fid, $role, $subsys) = @{$roleEntry};
3204          # Check for a subsystem name.          Trace("Subsystem for $fid is $subsys.") if T(4);
3205          my $subsys = $subHash{$cellID};          # Check the subsystem;
3206          if ($subsys) {          if ($subs{$subsys}) {
3207                Trace("Subsystem found.") if T(4);
3208              # Insure this feature has an entry in the return hash.              # Insure this feature has an entry in the return hash.
3209              if (! exists $retVal{$fid}) { $retVal{$fid} = []; }              if (! exists $retVal{$fid}) { $retVal{$fid} = []; }
3210              # Merge in this new data.              # Merge in this new data.
# Line 3303  Line 3250 
3250      # Get the parameters.      # Get the parameters.
3251      my ($self, $featureID, $function, $userID) = @_;      my ($self, $featureID, $function, $userID) = @_;
3252      # Get a list of the features that are BBHs of the incoming feature.      # Get a list of the features that are BBHs of the incoming feature.
3253      my @bbhFeatures = map { $_->[0] } FIGRules::BBHData($featureID);      my $bbhData = FIGRules::BBHData($featureID);
3254        my @bbhFeatures = map { $_->[0] } @$bbhData;
3255      # Now we loop through the features, pulling out the ones that have the correct      # Now we loop through the features, pulling out the ones that have the correct
3256      # functional assignment.      # functional assignment.
3257      my @retVal = ();      my @retVal = ();
# Line 3476  Line 3424 
3424    
3425  =head3 BBHMatrix  =head3 BBHMatrix
3426    
3427      my %bbhMap = $sprout->BBHMatrix($genomeID, $cutoff, @targets);      my $bbhMap = $sprout->BBHMatrix($genomeID, $cutoff, @targets);
3428    
3429  Find all the bidirectional best hits for the features of a genome in a  Find all the bidirectional best hits for the features of a genome in a
3430  specified list of target genomes. The return value will be a hash mapping  specified list of target genomes. The return value will be a hash mapping
# Line 3500  Line 3448 
3448    
3449  =item RETURN  =item RETURN
3450    
3451  Returns a hash mapping each feature in the original genome to a hash mapping its  Returns a reference to a hash mapping each feature in the original genome
3452  BBH pegs in the target genomes to their scores.  to a sub-hash mapping its BBH pegs in the target genomes to their scores.
3453    
3454  =back  =back
3455    
# Line 3514  Line 3462 
3462      my %retVal = ();      my %retVal = ();
3463      # Ask for the BBHs.      # Ask for the BBHs.
3464      my @bbhList = FIGRules::BatchBBHs("fig|$genomeID.%", $cutoff, @targets);      my @bbhList = FIGRules::BatchBBHs("fig|$genomeID.%", $cutoff, @targets);
3465        Trace("Retrieved " . scalar(@bbhList) . " BBH results.") if T(3);
3466      # We now have a set of 4-tuples that we need to convert into a hash of hashes.      # We now have a set of 4-tuples that we need to convert into a hash of hashes.
3467      for my $bbhData (@bbhList) {      for my $bbhData (@bbhList) {
3468          my ($peg1, $peg2, $score) = @{$bbhData};          my ($peg1, $peg2, $score) = @{$bbhData};
# Line 3524  Line 3473 
3473          }          }
3474      }      }
3475      # Return the result.      # Return the result.
3476      return %retVal;      return \%retVal;
3477  }  }
3478    
3479    
# Line 3630  Line 3579 
3579      # Create the return hash.      # Create the return hash.
3580      my %retVal = ();      my %retVal = ();
3581      # Query for the desired BBHs.      # Query for the desired BBHs.
3582      my @bbhList = FIGRules::BBHData($featureID, $cutoff);      my $bbhList = FIGRules::BBHData($featureID, $cutoff);
3583      # Form the results into the return hash.      # Form the results into the return hash.
3584      for my $pair (@bbhList) {      for my $pair (@$bbhList) {
3585          my $fid = $pair->[0];          my $fid = $pair->[0];
3586          if ($self->Exists('Feature', $fid)) {          if ($self->Exists('Feature', $fid)) {
3587              $retVal{$fid} = $pair->[1];              $retVal{$fid} = $pair->[1];
# Line 4010  Line 3959 
3959      # Get the parameters.      # Get the parameters.
3960      my ($self, $featureID, $key, @values) = @_;      my ($self, $featureID, $key, @values) = @_;
3961      # Add the property using the attached attributes object.      # Add the property using the attached attributes object.
3962      $self->{_ca}->AddAttribute($featureID, $key, @values);      $self->ca->AddAttribute($featureID, $key, @values);
3963  }  }
3964    
3965  =head3 CheckGroupFile  =head3 CheckGroupFile
# Line 4097  Line 4046 
4046  sub CleanKeywords {  sub CleanKeywords {
4047      # Get the parameters.      # Get the parameters.
4048      my ($self, $searchExpression) = @_;      my ($self, $searchExpression) = @_;
4049      # Perform the standard cleanup.      # Get the stemmer.
4050      my $words = $self->ERDB::CleanKeywords($searchExpression);      my $stemmer = $self->GetStemmer();
4051      # Fix the periods in EC and TC numbers.      # Convert the search expression using the stemmer.
4052      $words =~ s/(\d+|\-)\.(\d+|-)\.(\d+|-)\.(\d+|-)/$1_$2_$3_$4/g;      my $retVal = $stemmer->PrepareSearchExpression($searchExpression);
     # Fix non-trailing periods.  
     $words =~ s/\.(\w)/_$1/g;  
     # Fix non-leading minus signs.  
     $words =~ s/(\w)[\-]/$1_/g;  
     # Fix the vertical bars and colons  
     $words =~ s/(\w)[|:](\w)/$1'$2/g;  
     # Now split up the list so that each keyword is in its own string. We keep the delimiters  
     # because they may contain boolean expression data.  
     my @words = split /([^A-Za-z'0-9_]+)/, $words;  
     # We'll convert the stemmable words into stems and re-assemble the result.  
     my $retVal = "";  
     for my $word (@words) {  
         my $stem = $self->Stem($word);  
         if (defined $stem) {  
             $retVal .= $stem;  
         } else {  
             $retVal .= $word;  
         }  
     }  
4053      Trace("Cleaned keyword list for \"$searchExpression\" is \"$retVal\".") if T(3);      Trace("Cleaned keyword list for \"$searchExpression\" is \"$retVal\".") if T(3);
4054      # Return the result.      # Return the result.
4055      return $retVal;      return $retVal;
4056  }  }
4057    
4058    =head3 GetSourceObject
4059    
4060        my $source = $erdb->GetSourceObject();
4061    
4062    Return the object to be used in creating load files for this database.
4063    
4064    =cut
4065    
4066    sub GetSourceObject {
4067        # Get the parameters.
4068        my ($self) = @_;
4069        # Check to see if we already have a source object.
4070        my $retVal = $self->{_fig};
4071        if (! defined $retVal) {
4072            # No, so create one.
4073            require FIG;
4074            $retVal = FIG->new();
4075        }
4076        # Return the object.
4077        return $retVal;
4078    }
4079    
4080    =head3 SectionList
4081    
4082        my @sections = $erdb->SectionList();
4083    
4084    Return a list of the names for the different data sections used when loading this database.
4085    The default is a single string, in which case there is only one section representing the
4086    entire database.
4087    
4088    =cut
4089    
4090    sub SectionList {
4091        # Get the parameters.
4092        my ($self, $source) = @_;
4093        # Ask the BaseSproutLoader for a section list.
4094        require BaseSproutLoader;
4095        my @retVal = BaseSproutLoader::GetSectionList($self);
4096        # Return the list.
4097        return @retVal;
4098    }
4099    
4100    =head3 Loader
4101    
4102        my $groupLoader = $erdb->Loader($groupName, $options);
4103    
4104    Return an [[ERDBLoadGroupPm]] object for the specified load group. This method is used
4105    by [[ERDBGeneratorPl]] to create the load group objects. If you are not using
4106    [[ERDBGeneratorPl]], you don't need to override this method.
4107    
4108    =over 4
4109    
4110    =item groupName
4111    
4112    Name of the load group whose object is to be returned. The group name is
4113    guaranteed to be a single word with only the first letter capitalized.
4114    
4115    =item options
4116    
4117    Reference to a hash of command-line options.
4118    
4119    =item RETURN
4120    
4121    Returns an [[ERDBLoadGroupPm]] object that can be used to process the specified load group
4122    for this database.
4123    
4124    =back
4125    
4126    =cut
4127    
4128    sub Loader {
4129        # Get the parameters.
4130        my ($self, $groupName, $options) = @_;
4131        # Compute the loader name.
4132        my $loaderClass = "${groupName}SproutLoader";
4133        # Pull in its definition.
4134        require "$loaderClass.pm";
4135        # Create an object for it.
4136        my $retVal = eval("$loaderClass->new(\$self, \$options)");
4137        # Insure it worked.
4138        Confess("Could not create $loaderClass object: $@") if $@;
4139        # Return it to the caller.
4140        return $retVal;
4141    }
4142    
4143    
4144    =head3 LoadGroupList
4145    
4146        my @groups = $erdb->LoadGroupList();
4147    
4148    Returns a list of the names for this database's load groups. This method is used
4149    by [[ERDBGeneratorPl]] when the user wishes to load all table groups. The default
4150    is a single group called 'All' that loads everything.
4151    
4152    =cut
4153    
4154    sub LoadGroupList {
4155        # Return the list.
4156        return qw(Genome Subsystem Annotation Property Source Reaction Synonym Feature Drug);
4157    }
4158    
4159    =head3 LoadDirectory
4160    
4161        my $dirName = $erdb->LoadDirectory();
4162    
4163    Return the name of the directory in which load files are kept. The default is
4164    the FIG temporary directory, which is a really bad choice, but it's always there.
4165    
4166    =cut
4167    
4168    sub LoadDirectory {
4169        # Get the parameters.
4170        my ($self) = @_;
4171        # Return the directory name.
4172        return $self->{dataDir};
4173    }
4174    
4175  =head2 Internal Utility Methods  =head2 Internal Utility Methods
4176    
4177    =head3 GetStemmer
4178    
4179        my $stermmer = $sprout->GetStemmer();
4180    
4181    Return the stemmer object for this database.
4182    
4183    =cut
4184    
4185    sub GetStemmer {
4186        # Get the parameters.
4187        my ($self) = @_;
4188        # Declare the return variable.
4189        my $retVal = $self->{stemmer};
4190        if (! defined $retVal) {
4191            # We don't have one pre-built, so we build and save it now.
4192            $retVal = BioWords->new(exceptions => "$FIG_Config::sproutData/Exceptions.txt",
4193                                     stops => "$FIG_Config::sproutData/StopWords.txt",
4194                                     cache => 0);
4195            $self->{stemmer} = $retVal;
4196        }
4197        # Return the result.
4198        return $retVal;
4199    }
4200    
4201  =head3 ParseAssignment  =head3 ParseAssignment
4202    
4203  Parse annotation text to determine whether or not it is a functional assignment. If it is,  Parse annotation text to determine whether or not it is a functional assignment. If it is,
# Line 4213  Line 4284 
4284      # Get the parameters.      # Get the parameters.
4285      my ($self, $fid) = @_;      my ($self, $fid) = @_;
4286      # Insure we have a genome hash.      # Insure we have a genome hash.
4287      if (! defined $self->{genomeHash}) {      my $genomes = $self->_GenomeHash();
         my %genomeHash = map { $_ => 1 } $self->GetFlat(['Genome'], "", [], 'Genome(id)');  
         $self->{genomeHash} = \%genomeHash;  
     }  
4288      # Get the feature's genome ID.      # Get the feature's genome ID.
4289      my ($genomeID) = FIGRules::ParseFeatureID($fid);      my ($genomeID) = FIGRules::ParseFeatureID($fid);
4290      # Return an indicator of whether or not the genome ID is in the hash.      # Return an indicator of whether or not the genome ID is in the hash.
# Line 4250  Line 4318 
4318  }  }
4319    
4320    
4321    =head3 Hint
4322    
4323        my $htmlText = SearchHelper::Hint($wikiPage, $hintText);
4324    
4325    Return the HTML for a small question mark that displays the specified hint text when it is clicked.
4326    This HTML can be put in forms to provide a useful hinting mechanism.
4327    
4328    =over 4
4329    
4330    =item wikiPage
4331    
4332    Name of the wiki page to be popped up when the hint mark is clicked.
4333    
4334    =item hintText
4335    
4336    Text to display for the hint. It is raw html, but may not contain any double quotes.
4337    
4338    =item RETURN
4339    
4340    Returns the html for the hint facility. The resulting html shows a small button-like thing that
4341    uses the standard FIG popup technology.
4342    
4343    =back
4344    
4345    =cut
4346    
4347    sub Hint {
4348        # Get the parameters.
4349        my ($wikiPage, $hintText) = @_;
4350        # Escape the single quotes in the hint text.
4351        my $quotedText = $hintText;
4352        $quotedText =~ s/'/\\'/g;
4353        # Convert the wiki page name to a URL.
4354        my $wikiURL = join("", map { ucfirst $_ } split /\s+/, $wikiPage);
4355        $wikiURL = "$FIG_Config::cgi_url/wiki/view.cgi/FIG/$wikiURL";
4356        # Compute the mouseover script.
4357        my $mouseOver = "doTooltip(this, '$quotedText')";
4358        # Create the html.
4359        my $retVal = "&nbsp;<a href=\"$wikiURL\"><img src=\"$FIG_Config::cgi_url/Html/button-h.png\" class=\"helpicon\" onmouseover=\"$mouseOver\"/></a>";
4360        # Return it.
4361        return $retVal;
4362    }
4363    
4364    =head3 _GenomeHash
4365    
4366        my $gHash = $sprout->_GenomeHash();
4367    
4368    Return a hash mapping all NMPDR genome IDs to [[ERDBObjectPm]] genome objects.
4369    
4370    =cut
4371    
4372    sub _GenomeHash {
4373        # Get the parameters.
4374        my ($self) = @_;
4375        # Do we already have a filled hash?
4376        if (! $self->{genomeHashFilled}) {
4377            # No, create it.
4378            my %gHash = map { $_->PrimaryValue('id') => $_ } $self->GetList("Genome", "", []);
4379            $self->{genomeHash} = \%gHash;
4380            # Denote we have it.
4381            $self->{genomeHashFilled} = 1;
4382        }
4383        # Return the hash.
4384        return $self->{genomeHash};
4385    }
4386    
4387    =head3 _GenomeData
4388    
4389        my $genomeData = $sprout->_GenomeData($genomeID);
4390    
4391    Return an [[ERDBObjectPm]] object for the specified genome, or an undefined
4392    value if the genome does not exist.
4393    
4394    =over 4
4395    
4396    =item genomeID
4397    
4398    ID of the desired genome.
4399    
4400    =item RETURN
4401    
4402    Returns either an [[ERDBObjectPm]] containing the genome, or an undefined value.
4403    If the genome exists, it will have been read into the genome cache.
4404    
4405    =back
4406    
4407    =cut
4408    
4409    sub _GenomeData {
4410        # Get the parameters.
4411        my ($self, $genomeID) = @_;
4412        # Are we in the genome hash?
4413        if (! exists $self->{genomeHash}->{$genomeID} && ! $self->{genomeHashFilled}) {
4414            # The genome isn't in the hash, and the hash is not complete, so we try to
4415            # read it.
4416            $self->{genomeHash}->{$genomeID} = $self->GetEntity(Genome => $genomeID);
4417        }
4418        # Return the result.
4419        return $self->{genomeHash}->{$genomeID};
4420    }
4421    
4422    =head3 _CacheGenome
4423    
4424        $sprout->_CacheGenome($genomeID, $genomeData);
4425    
4426    Store the specified genome object in the genome cache if it is already there.
4427    
4428    =over 4
4429    
4430    =item genomeID
4431    
4432    ID of the genome to store in the cache.
4433    
4434    =item genomeData
4435    
4436    An [[ERDBObjectPm]] containing at least the data for the specified genome.
4437    Note that the Genome may not be the primary object in it, so a fully-qualified
4438    field name has to be used to retrieve data from it.
4439    
4440    =back
4441    
4442    =cut
4443    
4444    sub _CacheGenome {
4445        # Get the parameters.
4446        my ($self, $genomeID, $genomeData) = @_;
4447        # Only proceed if we don't already have the genome.
4448        if (! exists $self->{genomeHash}->{$genomeID}) {
4449            $self->{genomeHash}->{$genomeID} = $genomeData;
4450        }
4451    }
4452    
4453  1;  1;

Legend:
Removed from v.1.113  
changed lines
  Added in v.1.123

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3