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

Diff of /Sprout/Sprout.pm

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

revision 1.4, Tue Jan 25 01:36:09 2005 UTC revision 1.56, Wed Apr 19 03:34:15 2006 UTC
# Line 36  Line 36 
36    
37  #: Constructor SFXlate->new_sprout_only();  #: Constructor SFXlate->new_sprout_only();
38    
   
39  =head2 Public Methods  =head2 Public Methods
40    
41  =head3 new  =head3 new
# Line 71  Line 70 
70    
71  * B<maxSequenceLength> maximum number of residues per sequence, (default C<8000>)  * B<maxSequenceLength> maximum number of residues per sequence, (default C<8000>)
72    
73    * B<noDBOpen> suppresses the connection to the database if TRUE, else FALSE
74    
75  =back  =back
76    
77  For example, the following constructor call specifies a database named I<Sprout> and a user name of  For example, the following constructor call specifies a database named I<Sprout> and a user name of
# Line 87  Line 88 
88          # Compute the options. We do this by starting with a table of defaults and overwriting with          # Compute the options. We do this by starting with a table of defaults and overwriting with
89          # the incoming data.          # the incoming data.
90          my $optionTable = Tracer::GetOptions({          my $optionTable = Tracer::GetOptions({
91                                             dbType               => 'mysql',                     # database type                         dbType       => $FIG_Config::dbms,
92                                             dataDir              => 'Data',                      # data file directory                                                          # database type
93                                             xmlFileName  => 'SproutDBD.xml', # database definition file name                         dataDir      => $FIG_Config::sproutData,
94                                             userData             => 'root/',                     # user name and password                                                          # data file directory
95                                             port                 => 0,                           # database connection port                         xmlFileName  => "$FIG_Config::fig/SproutDBD.xml",
96                                                            # database definition file name
97                           userData     => "$FIG_Config::dbuser/$FIG_Config::dbpass",
98                                                            # user name and password
99                           port         => $FIG_Config::dbport,
100                                                            # database connection port
101                                             maxSegmentLength => 4500,            # maximum feature segment length                                             maxSegmentLength => 4500,            # maximum feature segment length
102                                             maxSequenceLength => 8000,           # maximum contig sequence length                                             maxSequenceLength => 8000,           # maximum contig sequence length
103                           noDBOpen     => 0,               # 1 to suppress the database open
104                                            }, $options);                                            }, $options);
105          # Get the data directory.          # Get the data directory.
106          my $dataDir = $optionTable->{dataDir};          my $dataDir = $optionTable->{dataDir};
# Line 101  Line 108 
108          $optionTable->{userData} =~ m!([^/]*)/(.*)$!;          $optionTable->{userData} =~ m!([^/]*)/(.*)$!;
109          my ($userName, $password) = ($1, $2);          my ($userName, $password) = ($1, $2);
110          # Connect to the database.          # Connect to the database.
111          my $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName, $password, $optionTable->{port});      my $dbh;
112        if (! $optionTable->{noDBOpen}) {
113            $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName,
114                                    $password, $optionTable->{port});
115        }
116          # Create the ERDB object.          # Create the ERDB object.
117          my $xmlFileName = "$optionTable->{xmlFileName}";          my $xmlFileName = "$optionTable->{xmlFileName}";
118          my $erdb = ERDB->new($dbh, $xmlFileName);          my $erdb = ERDB->new($dbh, $xmlFileName);
# Line 125  Line 136 
136  =cut  =cut
137  #: Return Type $;  #: Return Type $;
138  sub MaxSegment {  sub MaxSegment {
139          my $self = shift @_;      my ($self) = @_;
140          return $self->{_options}->{maxSegmentLength};          return $self->{_options}->{maxSegmentLength};
141  }  }
142    
# Line 140  Line 151 
151  =cut  =cut
152  #: Return Type $;  #: Return Type $;
153  sub MaxSequence {  sub MaxSequence {
154          my $self = shift @_;      my ($self) = @_;
155          return $self->{_options}->{maxSequenceLength};          return $self->{_options}->{maxSequenceLength};
156  }  }
157    
# Line 233  Line 244 
244    
245  sub Get {  sub Get {
246          # Get the parameters.          # Get the parameters.
247          my $self = shift @_;      my ($self, $objectNames, $filterClause, $parameterList) = @_;
         my ($objectNames, $filterClause, $parameterList) = @_;  
248          # We differ from the ERDB Get method in that the parameter list is passed in as a list reference          # We differ from the ERDB Get method in that the parameter list is passed in as a list reference
249          # rather than a list of parameters. The next step is to convert the parameters from a reference          # rather than a list of parameters. The next step is to convert the parameters from a reference
250          # to a real list. We can only do this if the parameters have been specified.          # to a real list. We can only do this if the parameters have been specified.
# Line 270  Line 280 
280    
281  sub GetEntity {  sub GetEntity {
282          # Get the parameters.          # Get the parameters.
283          my $self = shift @_;      my ($self, $entityType, $ID) = @_;
284          my ($entityType, $ID) = @_;      # Call the ERDB method.
285          # Create a query.      return $self->{_erdb}->GetEntity($entityType, $ID);
         my $query = $self->Get([$entityType], "$entityType(id) = ?", [$ID]);  
         # Get the first (and only) object.  
         my $retVal = $query->Fetch();  
         # Return the result.  
         return $retVal;  
286  }  }
287    
288  =head3 GetEntityValues  =head3 GetEntityValues
# Line 310  Line 315 
315  #: Return Type @;  #: Return Type @;
316  sub GetEntityValues {  sub GetEntityValues {
317          # Get the parameters.          # Get the parameters.
318          my $self = shift @_;      my ($self, $entityType, $ID, $fields) = @_;
319          my ($entityType, $ID, $fields) = @_;      # Call the ERDB method.
320          # Get the specified entity.      return $self->{_erdb}->GetEntityValues($entityType, $ID, $fields);
         my $entity = $self->GetEntity($entityType, $ID);  
         # Declare the return list.  
         my @retVal = ();  
         # If we found the entity, push the values into the return list.  
         if ($entity) {  
                 push @retVal, $entity->Values($fields);  
         }  
         # Return the result.  
         return @retVal;  
321  }  }
322    
323  =head3 ShowMetaData  =head3 ShowMetaData
# Line 342  Line 338 
338    
339  sub ShowMetaData {  sub ShowMetaData {
340          # Get the parameters.          # Get the parameters.
341          my $self = shift @_;      my ($self, $fileName) = @_;
         my ($fileName) = @_;  
342          # Compute the file name.          # Compute the file name.
343          my $options = $self->{_options};          my $options = $self->{_options};
344          # Call the show method on the underlying ERDB object.          # Call the show method on the underlying ERDB object.
# Line 383  Line 378 
378  #: Return Type %;  #: Return Type %;
379  sub Load {  sub Load {
380          # Get the parameters.          # Get the parameters.
381          my $self = shift @_;      my ($self, $rebuild) = @_;
         my ($rebuild) = @_;  
382          # Get the database object.          # Get the database object.
383          my $erdb = $self->{_erdb};          my $erdb = $self->{_erdb};
384          # Load the tables from the data directory.          # Load the tables from the data directory.
# Line 395  Line 389 
389    
390  =head3 LoadUpdate  =head3 LoadUpdate
391    
392  C<< my %stats = $sprout->LoadUpdate($truncateFlag, \@tableList); >>  C<< my $stats = $sprout->LoadUpdate($truncateFlag, \@tableList); >>
393    
394  Load updates to one or more database tables. This method enables the client to make changes to one  Load updates to one or more database tables. This method enables the client to make changes to one
395  or two tables without reloading the whole database. For each table, there must be a corresponding  or two tables without reloading the whole database. For each table, there must be a corresponding
# Line 424  Line 418 
418  =back  =back
419    
420  =cut  =cut
421  #: Return Type %;  #: Return Type $%;
422  sub LoadUpdate {  sub LoadUpdate {
423          # Get the parameters.          # Get the parameters.
424          my $self = shift @_;      my ($self, $truncateFlag, $tableList) = @_;
         my ($truncateFlag, $tableList) = @_;  
425          # Get the database object.          # Get the database object.
426          my $erdb = $self->{_erdb};          my $erdb = $self->{_erdb};
427          # Declare the return value.          # Declare the return value.
# Line 439  Line 432 
432          # Loop through the incoming table names.          # Loop through the incoming table names.
433          for my $tableName (@{$tableList}) {          for my $tableName (@{$tableList}) {
434                  # Find the table's file.                  # Find the table's file.
435                  my $fileName = "$dataDir/$tableName";          my $fileName = LoadFileName($dataDir, $tableName);
436                  if (! -e $fileName) {          if (! $fileName) {
437                          $fileName = "$fileName.dtx";              Trace("No load file found for $tableName in $dataDir.") if T(0);
438                  }          } else {
439                  # Attempt to load this table.                  # Attempt to load this table.
440                  my $result = $erdb->LoadTable($fileName, $tableName, $truncateFlag);                  my $result = $erdb->LoadTable($fileName, $tableName, $truncateFlag);
441                  # Accumulate the resulting statistics.                  # Accumulate the resulting statistics.
442                  $retVal->Accumulate($result);                  $retVal->Accumulate($result);
443          }          }
444        }
445          # Return the statistics.          # Return the statistics.
446          return $retVal;          return $retVal;
447  }  }
# Line 464  Line 458 
458  #: Return Type ;  #: Return Type ;
459  sub Build {  sub Build {
460          # Get the parameters.          # Get the parameters.
461          my $self = shift @_;      my ($self) = @_;
462          # Create the tables.          # Create the tables.
463          $self->{_erdb}->CreateTables;          $self->{_erdb}->CreateTables;
464  }  }
# Line 479  Line 473 
473  #: Return Type @;  #: Return Type @;
474  sub Genomes {  sub Genomes {
475          # Get the parameters.          # Get the parameters.
476          my $self = shift @_;      my ($self) = @_;
477          # Get all the genomes.          # Get all the genomes.
478          my @retVal = $self->GetFlat(['Genome'], "", [], 'Genome(id)');          my @retVal = $self->GetFlat(['Genome'], "", [], 'Genome(id)');
479          # Return the list of IDs.          # Return the list of IDs.
# Line 509  Line 503 
503  #: Return Type $;  #: Return Type $;
504  sub GenusSpecies {  sub GenusSpecies {
505          # Get the parameters.          # Get the parameters.
506          my $self = shift @_;      my ($self, $genomeID) = @_;
         my ($genomeID) = @_;  
507          # Get the data for the specified genome.          # Get the data for the specified genome.
508          my @values = $self->GetEntityValues('Genome', $genomeID, ['Genome(genus)', 'Genome(species)',          my @values = $self->GetEntityValues('Genome', $genomeID, ['Genome(genus)', 'Genome(species)',
509                                                                                                                            'Genome(unique-characterization)']);                                                                                                                            'Genome(unique-characterization)']);
# Line 546  Line 539 
539  #: Return Type @;  #: Return Type @;
540  sub FeaturesOf {  sub FeaturesOf {
541          # Get the parameters.          # Get the parameters.
542          my $self = shift @_;      my ($self, $genomeID,$ftype) = @_;
         my ($genomeID,$ftype) = @_;  
543          # Get the features we want.          # Get the features we want.
544          my @features;          my @features;
545          if (!$ftype) {          if (!$ftype) {
# Line 591  Line 583 
583  =item RETURN  =item RETURN
584    
585  Returns a list of the feature's contig segments. The locations are returned as a list in a list  Returns a list of the feature's contig segments. The locations are returned as a list in a list
586  context and as a space-delimited string in a scalar context.  context and as a comma-delimited string in a scalar context.
587    
588  =back  =back
589    
# Line 600  Line 592 
592  #: Return Type $;  #: Return Type $;
593  sub FeatureLocation {  sub FeatureLocation {
594          # Get the parameters.          # Get the parameters.
595          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
596          # Create a query for the feature locations.          # Create a query for the feature locations.
597          my $query = $self->Get(['IsLocatedIn'], "IsLocatedIn(from-link) = ? ORDER BY IsLocatedIn(locN)",          my $query = $self->Get(['IsLocatedIn'], "IsLocatedIn(from-link) = ? ORDER BY IsLocatedIn(locN)",
598                                                     [$featureID]);                                                     [$featureID]);
# Line 619  Line 610 
610                  if ($prevContig eq $contigID && $dir eq $prevDir) {                  if ($prevContig eq $contigID && $dir eq $prevDir) {
611                          # Here the new segment is in the same direction on the same contig. Insure the                          # Here the new segment is in the same direction on the same contig. Insure the
612                          # new segment's beginning is next to the old segment's end.                          # new segment's beginning is next to the old segment's end.
613                          if (($dir eq "-" && $beg == $prevBeg - $prevLen) ||              if ($dir eq "-" && $beg + $len == $prevBeg) {
614                                  ($dir eq "+" && $beg == $prevBeg + $prevLen)) {                  # Here we're merging two backward blocks, so we keep the new begin point
615                                  # Here we need to merge two segments. Adjust the beginning and length values                  # and adjust the length.
616                                  # to include both segments.                  $len += $prevLen;
617                    # Pop the old segment off. The new one will replace it later.
618                    pop @retVal;
619                } elsif ($dir eq "+" && $beg == $prevBeg + $prevLen) {
620                    # Here we need to merge two forward blocks. Adjust the beginning and
621                    # length values to include both segments.
622                                  $beg = $prevBeg;                                  $beg = $prevBeg;
623                                  $len += $prevLen;                                  $len += $prevLen;
624                                  # Pop the old segment off. The new one will replace it later.                                  # Pop the old segment off. The new one will replace it later.
# Line 631  Line 627 
627                  }                  }
628                  # Remember this specifier for the adjacent-segment test the next time through.                  # Remember this specifier for the adjacent-segment test the next time through.
629                  ($prevContig, $prevBeg, $prevDir, $prevLen) = ($contigID, $beg, $dir, $len);                  ($prevContig, $prevBeg, $prevDir, $prevLen) = ($contigID, $beg, $dir, $len);
630            # Compute the initial base pair.
631            my $start = ($dir eq "+" ? $beg : $beg + $len - 1);
632                  # Add the specifier to the list.                  # Add the specifier to the list.
633                  push @retVal, "${contigID}_$beg$dir$len";          push @retVal, "${contigID}_$start$dir$len";
634          }          }
635          # Return the list in the format indicated by the context.          # Return the list in the format indicated by the context.
636          return (wantarray ? @retVal : join(' ', @retVal));      return (wantarray ? @retVal : join(',', @retVal));
637  }  }
638    
639  =head3 ParseLocation  =head3 ParseLocation
# Line 661  Line 659 
659  =cut  =cut
660  #: Return Type @;  #: Return Type @;
661  sub ParseLocation {  sub ParseLocation {
662          # Get the parameter.      # Get the parameter. Note that if we're called as an instance method, we ignore
663        # the first parameter.
664        shift if UNIVERSAL::isa($_[0],__PACKAGE__);
665          my ($location) = @_;          my ($location) = @_;
666          # Parse it into segments.          # Parse it into segments.
667          $location =~ /^(.*)_(\d*)([+-_])(\d*)$/;      $location =~ /^(.+)_(\d+)([+\-_])(\d+)$/;
668          my ($contigID, $start, $dir, $len) = ($1, $2, $3, $4);          my ($contigID, $start, $dir, $len) = ($1, $2, $3, $4);
669          # If the direction is an underscore, convert it to a + or -.          # If the direction is an underscore, convert it to a + or -.
670          if ($dir eq "_") {          if ($dir eq "_") {
# Line 680  Line 680 
680          return ($contigID, $start, $dir, $len);          return ($contigID, $start, $dir, $len);
681  }  }
682    
683    =head3 PointLocation
684    
685    C<< my $found = Sprout::PointLocation($location, $point); >>
686    
687    Return the offset into the specified location of the specified point on the contig. If
688    the specified point is before the location, a negative value will be returned. If it is
689    beyond the location, an undefined value will be returned. It is assumed that the offset
690    is for the location's contig. The location can either be new-style (using a C<+> or C<->
691    and a length) or old-style (using C<_> and start and end positions.
692    
693    =over 4
694    
695    =item location
696    
697    A location specifier (see L</FeatureLocation> for a description).
698    
699    =item point
700    
701    The offset into the contig of the point in which we're interested.
702    
703    =item RETURN
704    
705    Returns the offset inside the specified location of the specified point, a negative
706    number if the point is before the location, or an undefined value if the point is past
707    the location. If the length of the location is 0, this method will B<always> denote
708    that it is outside the location. The offset will always be relative to the left-most
709    position in the location.
710    
711    =back
712    
713    =cut
714    #: Return Type $;
715    sub PointLocation {
716        # Get the parameter. Note that if we're called as an instance method, we ignore
717        # the first parameter.
718        shift if UNIVERSAL::isa($_[0],__PACKAGE__);
719        my ($location, $point) = @_;
720        # Parse out the location elements. Note that this works on both old-style and new-style
721        # locations.
722        my ($contigID, $start, $dir, $len) = ParseLocation($location);
723        # Declare the return variable.
724        my $retVal;
725        # Compute the offset. The computation is dependent on the direction of the location.
726        my $offset = (($dir == '+') ? $point - $start : $point - ($start - $len + 1));
727        # Return the offset if it's valid.
728        if ($offset < $len) {
729            $retVal = $offset;
730        }
731        # Return the offset found.
732        return $retVal;
733    }
734    
735  =head3 DNASeq  =head3 DNASeq
736    
737  C<< my $sequence = $sprout->DNASeq(\@locationList); >>  C<< my $sequence = $sprout->DNASeq(\@locationList); >>
# Line 688  Line 740 
740  should be of the form returned by L</featureLocation> when in a list context. In other words,  should be of the form returned by L</featureLocation> when in a list context. In other words,
741  each location is of the form I<contigID>C<_>I<begin>I<dir>I<end>.  each location is of the form I<contigID>C<_>I<begin>I<dir>I<end>.
742    
743    For example, the following would return the DNA sequence for contig C<83333.1:NC_000913>
744    between positions 1401 and 1532, inclusive.
745    
746        my $sequence = $sprout->DNASeq('83333.1:NC_000913_1401_1532');
747    
748  =over 4  =over 4
749    
750  =item locationList  =item locationList
751    
752  List of location specifiers, each in the form I<contigID>C<_>I<begin>I<dir>I<end> (see  List of location specifiers, each in the form I<contigID>C<_>I<begin>I<dir>I<len> or
753  L</FeatureLocation> for more about this format).  I<contigID>C<_>I<begin>C<_>I<end> (see L</FeatureLocation> for more about this format).
754    
755  =item RETURN  =item RETURN
756    
# Line 705  Line 762 
762  #: Return Type $;  #: Return Type $;
763  sub DNASeq {  sub DNASeq {
764          # Get the parameters.          # Get the parameters.
765          my $self = shift @_;      my ($self, $locationList) = @_;
         my ($locationList) = @_;  
766          # Create the return string.          # Create the return string.
767          my $retVal = "";          my $retVal = "";
768          # Loop through the locations.          # Loop through the locations.
# Line 721  Line 777 
777                  # the start point is the ending. Note that in the latter case we must reverse the DNA string                  # the start point is the ending. Note that in the latter case we must reverse the DNA string
778                  # before putting it in the return value.                  # before putting it in the return value.
779                  my ($start, $stop);                  my ($start, $stop);
780            Trace("Parse of \"$location\" is $beg$dir$len.") if T(SDNA => 4);
781                  if ($dir eq "+") {                  if ($dir eq "+") {
782                          $start = $beg;                          $start = $beg;
783                          $stop = $beg + $len - 1;                          $stop = $beg + $len - 1;
784                  } else {                  } else {
785                          $start = $beg + $len + 1;              $start = $beg - $len + 1;
786                          $stop = $beg;                          $stop = $beg;
787                  }                  }
788            Trace("Looking for sequences containing $start through $stop.") if T(SDNA => 4);
789                  my $query = $self->Get(['IsMadeUpOf','Sequence'],                  my $query = $self->Get(['IsMadeUpOf','Sequence'],
790                          "IsMadeUpOf(from-link) = ? AND IsMadeUpOf(start-position) + IsMadeUpOf(len) > ? AND " .                          "IsMadeUpOf(from-link) = ? AND IsMadeUpOf(start-position) + IsMadeUpOf(len) > ? AND " .
791                          " IsMadeUpOf(start-position) <= ? ORDER BY IsMadeUpOf(start-position)",                          " IsMadeUpOf(start-position) <= ? ORDER BY IsMadeUpOf(start-position)",
# Line 739  Line 797 
797                                  $sequence->Values(['IsMadeUpOf(start-position)', 'Sequence(sequence)',                                  $sequence->Values(['IsMadeUpOf(start-position)', 'Sequence(sequence)',
798                                                                     'IsMadeUpOf(len)']);                                                                     'IsMadeUpOf(len)']);
799                          my $stopPosition = $startPosition + $sequenceLength;                          my $stopPosition = $startPosition + $sequenceLength;
800                Trace("Sequence is from $startPosition to $stopPosition.") if T(SDNA => 4);
801                          # Figure out the start point and length of the relevant section.                          # Figure out the start point and length of the relevant section.
802                          my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);                          my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);
803                          my $len = ($stopPosition <= $stop ? $stopPosition : $stop) - $startPosition - $pos1;              my $len1 = ($stopPosition < $stop ? $stopPosition : $stop) + 1 - $startPosition - $pos1;
804                Trace("Position is $pos1 for length $len1.") if T(SDNA => 4);
805                          # Add the relevant data to the location data.                          # Add the relevant data to the location data.
806                          $locationDNA .= substr($sequenceData, $pos1, $len);              $locationDNA .= substr($sequenceData, $pos1, $len1);
807                  }                  }
808                  # Add this location's data to the return string. Note that we may need to reverse it.                  # Add this location's data to the return string. Note that we may need to reverse it.
809                  if ($dir eq '+') {                  if ($dir eq '+') {
810                          $retVal .= $locationDNA;                          $retVal .= $locationDNA;
811                  } else {                  } else {
812                          $locationDNA = join('', reverse split //, $locationDNA);              $retVal .= FIG::reverse_comp($locationDNA);
                         $retVal .= $locationDNA;  
813                  }                  }
814          }          }
815          # Return the result.          # Return the result.
# Line 779  Line 838 
838  #: Return Type @;  #: Return Type @;
839  sub AllContigs {  sub AllContigs {
840          # Get the parameters.          # Get the parameters.
841          my $self = shift @_;      my ($self, $genomeID) = @_;
         my ($genomeID) = @_;  
842          # Ask for the genome's Contigs.          # Ask for the genome's Contigs.
843          my @retVal = $self->GetFlat(['HasContig'], "HasContig(from-link) = ?", [$genomeID],          my @retVal = $self->GetFlat(['HasContig'], "HasContig(from-link) = ?", [$genomeID],
844                                                                  'HasContig(to-link)');                                                                  'HasContig(to-link)');
# Line 810  Line 868 
868  #: Return Type $;  #: Return Type $;
869  sub ContigLength {  sub ContigLength {
870          # Get the parameters.          # Get the parameters.
871          my $self = shift @_;      my ($self, $contigID) = @_;
         my ($contigID) = @_;  
872          # Get the contig's last sequence.          # Get the contig's last sequence.
873          my $query = $self->Get(['IsMadeUpOf'],          my $query = $self->Get(['IsMadeUpOf'],
874                  "IsMadeUpOf(from-link) = ? ORDER BY IsMadeUpOf(start-position) DESC",                  "IsMadeUpOf(from-link) = ? ORDER BY IsMadeUpOf(start-position) DESC",
# Line 822  Line 879 
879          # Set it from the sequence data, if any.          # Set it from the sequence data, if any.
880          if ($sequence) {          if ($sequence) {
881                  my ($start, $len) = $sequence->Values(['IsMadeUpOf(start-position)', 'IsMadeUpOf(len)']);                  my ($start, $len) = $sequence->Values(['IsMadeUpOf(start-position)', 'IsMadeUpOf(len)']);
882                  $retVal = $start + $len;          $retVal = $start + $len - 1;
883        }
884        # Return the result.
885        return $retVal;
886    }
887    
888    =head3 ClusterPEGs
889    
890    C<< my $clusteredList = $sprout->ClusterPEGs($sub, \@pegs); >>
891    
892    Cluster the PEGs in a list according to the cluster coding scheme of the specified
893    subsystem. In order for this to work properly, the subsystem object must have
894    been used recently to retrieve the PEGs using the B<get_pegs_from_cell> method.
895    This causes the cluster numbers to be pulled into the subsystem's color hash.
896    If a PEG is not found in the color hash, it will not appear in the output
897    sequence.
898    
899    =over 4
900    
901    =item sub
902    
903    Sprout subsystem object for the relevant subsystem, from the L</get_subsystem>
904    method.
905    
906    =item pegs
907    
908    Reference to the list of PEGs to be clustered.
909    
910    =item RETURN
911    
912    Returns a list of the PEGs, grouped into smaller lists by cluster number.
913    
914    =back
915    
916    =cut
917    #: Return Type $@@;
918    sub ClusterPEGs {
919        # Get the parameters.
920        my ($self, $sub, $pegs) = @_;
921        # Declare the return variable.
922        my $retVal = [];
923        # Loop through the PEGs, creating arrays for each cluster.
924        for my $pegID (@{$pegs}) {
925            my $clusterNumber = $sub->get_cluster_number($pegID);
926            # Only proceed if the PEG is in a cluster.
927            if ($clusterNumber >= 0) {
928                # Push this PEG onto the sub-list for the specified cluster number.
929                push @{$retVal->[$clusterNumber]}, $pegID;
930            }
931          }          }
932          # Return the result.          # Return the result.
933          return $retVal;          return $retVal;
# Line 853  Line 958 
958  Returns a three-element list. The first element is a list of feature IDs for the features that  Returns a three-element list. The first element is a list of feature IDs for the features that
959  overlap the region of interest. The second and third elements are the minimum and maximum  overlap the region of interest. The second and third elements are the minimum and maximum
960  locations of the features provided on the specified contig. These may extend outside  locations of the features provided on the specified contig. These may extend outside
961  the start and stop values.  the start and stop values. The first element (that is, the list of features) is sorted
962    roughly by location.
963    
964  =back  =back
965    
966  =cut  =cut
967  #: Return Type @;  #: Return Type @@;
968  sub GenesInRegion {  sub GenesInRegion {
969          # Get the parameters.          # Get the parameters.
970          my $self = shift @_;      my ($self, $contigID, $start, $stop) = @_;
         my ($contigID, $start, $stop) = @_;  
971          # Get the maximum segment length.          # Get the maximum segment length.
972          my $maximumSegmentLength = $self->MaxSegment;          my $maximumSegmentLength = $self->MaxSegment;
973          # Create a hash to receive the feature list. We use a hash so that we can eliminate          # Create a hash to receive the feature list. We use a hash so that we can eliminate
974          # duplicates easily.      # duplicates easily. The hash key will be the feature ID. The value will be a two-element
975        # containing the minimum and maximum offsets. We will use the offsets to sort the results
976        # when we're building the result set.
977          my %featuresFound = ();          my %featuresFound = ();
978          # Prime the values we'll use for the returned beginning and end.          # Prime the values we'll use for the returned beginning and end.
979          my ($min, $max) = ($self->ContigLength($contigID), 0);      my @initialMinMax = ($self->ContigLength($contigID), 0);
980        my ($min, $max) = @initialMinMax;
981          # Create a table of parameters for each query. Each query looks for features travelling in          # Create a table of parameters for each query. Each query looks for features travelling in
982          # a particular direction. The query parameters include the contig ID, the feature direction,          # a particular direction. The query parameters include the contig ID, the feature direction,
983          # the lowest possible start position, and the highest possible start position. This works          # the lowest possible start position, and the highest possible start position. This works
# Line 899  Line 1007 
1007                                          $found = 1;                                          $found = 1;
1008                                  }                                  }
1009                          } elsif ($dir eq '-') {                          } elsif ($dir eq '-') {
1010                                  $end = $beg - $len;                  # Note we switch things around so that the beginning is to the left of the
1011                                  if ($end <= $stop) {                  # ending.
1012                    ($beg, $end) = ($beg - $len, $beg);
1013                    if ($beg <= $stop) {
1014                                          # Denote we found a useful feature.                                          # Denote we found a useful feature.
1015                                          $found = 1;                                          $found = 1;
1016                                  }                                  }
1017                          }                          }
1018                          if ($found) {                          if ($found) {
1019                                  # Here we need to record the feature and update the minimum and maximum.                  # Here we need to record the feature and update the minima and maxima. First,
1020                                  $featuresFound{$featureID} = 1;                  # get the current entry for the specified feature.
1021                                  if ($beg < $min) { $min = $beg; }                  my ($loc1, $loc2) = (exists $featuresFound{$featureID} ? @{$featuresFound{$featureID}} :
1022                                  if ($end < $min) { $min = $end; }                                       @initialMinMax);
1023                                  if ($beg > $max) { $max = $beg; }                  # Merge the current segment's begin and end into the feature begin and end and the
1024                                  if ($end > $max) { $max = $end; }                  # global min and max.
1025                    if ($beg < $loc1) {
1026                        $loc1 = $beg;
1027                        $min = $beg if $beg < $min;
1028                    }
1029                    if ($end > $loc2) {
1030                        $loc2 = $end;
1031                        $max = $end if $end > $max;
1032                    }
1033                    # Store the entry back into the hash table.
1034                    $featuresFound{$featureID} = [$loc1, $loc2];
1035                          }                          }
1036                  }                  }
1037          }          }
1038          # Compute a list of the IDs for the features found.      # Now we must compute the list of the IDs for the features found. We start with a list
1039          my @list = (sort (keys %featuresFound));      # of midpoints / feature ID pairs. (It's not really a midpoint, it's twice the midpoint,
1040        # but the result of the sort will be the same.)
1041        my @list = map { [$featuresFound{$_}->[0] + $featuresFound{$_}->[1], $_] } keys %featuresFound;
1042        # Now we sort by midpoint and yank out the feature IDs.
1043        my @retVal = map { $_->[1] } sort { $a->[0] <=> $b->[0] } @list;
1044          # Return it along with the min and max.          # Return it along with the min and max.
1045          return (\@list, $min, $max);      return (\@retVal, $min, $max);
1046  }  }
1047    
1048  =head3 FType  =head3 FType
# Line 944  Line 1068 
1068  #: Return Type $;  #: Return Type $;
1069  sub FType {  sub FType {
1070          # Get the parameters.          # Get the parameters.
1071          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1072          # Get the specified feature's type.          # Get the specified feature's type.
1073          my ($retVal) = $self->GetEntityValues('Feature', $featureID, ['Feature(feature-type)']);          my ($retVal) = $self->GetEntityValues('Feature', $featureID, ['Feature(feature-type)']);
1074          # Return the result.          # Return the result.
# Line 954  Line 1077 
1077    
1078  =head3 FeatureAnnotations  =head3 FeatureAnnotations
1079    
1080  C<< my @descriptors = $sprout->FeatureAnnotations($featureID); >>  C<< my @descriptors = $sprout->FeatureAnnotations($featureID, $rawFlag); >>
1081    
1082  Return the annotations of a feature.  Return the annotations of a feature.
1083    
# Line 964  Line 1087 
1087    
1088  ID of the feature whose annotations are desired.  ID of the feature whose annotations are desired.
1089    
1090    =item rawFlag
1091    
1092    If TRUE, the annotation timestamps will be returned in raw form; otherwise, they
1093    will be returned in human-readable form.
1094    
1095  =item RETURN  =item RETURN
1096    
1097  Returns a list of annotation descriptors. Each descriptor is a hash with the following fields.  Returns a list of annotation descriptors. Each descriptor is a hash with the following fields.
1098    
1099  * B<featureID> ID of the relevant feature.  * B<featureID> ID of the relevant feature.
1100    
1101  * B<timeStamp> time the annotation was made, in user-friendly format.  * B<timeStamp> time the annotation was made.
1102    
1103  * B<user> ID of the user who made the annotation  * B<user> ID of the user who made the annotation
1104    
# Line 982  Line 1110 
1110  #: Return Type @%;  #: Return Type @%;
1111  sub FeatureAnnotations {  sub FeatureAnnotations {
1112          # Get the parameters.          # Get the parameters.
1113          my $self = shift @_;      my ($self, $featureID, $rawFlag) = @_;
         my ($featureID) = @_;  
1114          # Create a query to get the feature's annotations and the associated users.          # Create a query to get the feature's annotations and the associated users.
1115          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1116                                                     "IsTargetOfAnnotation(from-link) = ?", [$featureID]);                                                     "IsTargetOfAnnotation(from-link) = ?", [$featureID]);
# Line 996  Line 1123 
1123                          $annotation->Values(['IsTargetOfAnnotation(from-link)',                          $annotation->Values(['IsTargetOfAnnotation(from-link)',
1124                                                                   'Annotation(time)', 'MadeAnnotation(from-link)',                                                                   'Annotation(time)', 'MadeAnnotation(from-link)',
1125                                                                   'Annotation(annotation)']);                                                                   'Annotation(annotation)']);
1126            # Convert the time, if necessary.
1127            if (! $rawFlag) {
1128                $timeStamp = FriendlyTimestamp($timeStamp);
1129            }
1130                  # Assemble them into a hash.                  # Assemble them into a hash.
1131          my $annotationHash = { featureID => $featureID,          my $annotationHash = { featureID => $featureID,
1132                                 timeStamp => FriendlyTimestamp($timeStamp),                                 timeStamp => $timeStamp,
1133                                                             user => $user, text => $text };                                                             user => $user, text => $text };
1134                  # Add it to the return list.                  # Add it to the return list.
1135                  push @retVal, $annotationHash;                  push @retVal, $annotationHash;
# Line 1012  Line 1143 
1143  C<< my %functions = $sprout->AllFunctionsOf($featureID); >>  C<< my %functions = $sprout->AllFunctionsOf($featureID); >>
1144    
1145  Return all of the functional assignments for a particular feature. The data is returned as a  Return all of the functional assignments for a particular feature. The data is returned as a
1146  hash of functional assignments to user IDs. A functional assignment is a type of annotation.  hash of functional assignments to user IDs. A functional assignment is a type of annotation,
1147  It has the format "XXXX\nset XXXX function to\nYYYYY". In this instance, XXXX is the user ID  Functional assignments are described in the L</ParseAssignment> function. Its worth noting that
1148  and YYYYY is the functional assignment text. Its worth noting that we cannot filter on the content  we cannot filter on the content of the annotation itself because it's a text field; however,
1149  of the annotation itself because it's a text field; however, this is not a big problem because most  this is not a big problem because most features only have a small number of annotations.
1150  features only have a small number of annotations.  Finally, if a single user has multiple functional assignments, we will only keep the most
1151    recent one.
1152    
1153  =over 4  =over 4
1154    
# Line 1026  Line 1158 
1158    
1159  =item RETURN  =item RETURN
1160    
1161  Returns a hash mapping the functional assignment IDs to user IDs.  Returns a hash mapping the user IDs to functional assignment IDs.
1162    
1163  =back  =back
1164    
# Line 1034  Line 1166 
1166  #: Return Type %;  #: Return Type %;
1167  sub AllFunctionsOf {  sub AllFunctionsOf {
1168          # Get the parameters.          # Get the parameters.
1169          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1170          # Get all of the feature's annotations.          # Get all of the feature's annotations.
1171          my @query = $self->GetFlat(['IsTargetOfAnnotation', 'Annotation'],      my @query = $self->GetAll(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1172                                                      "IsTargetOfAnnotation(from-link) = ?",                                                      "IsTargetOfAnnotation(from-link) = ?",
1173                                                          [$featureID], 'Annotation(annotation)');                              [$featureID], ['Annotation(time)', 'Annotation(annotation)',
1174                                               'MadeAnnotation(from-link)']);
1175          # Declare the return hash.          # Declare the return hash.
1176          my %retVal;          my %retVal;
1177        # Now we sort the assignments by timestamp in reverse.
1178        my @sortedQuery = sort { -($a->[0] <=> $b->[0]) } @query;
1179          # Loop until we run out of annotations.          # Loop until we run out of annotations.
1180          for my $text (@query) {      for my $annotation (@sortedQuery) {
1181            # Get the annotation fields.
1182            my ($timeStamp, $text, $user) = @{$annotation};
1183                  # Check to see if this is a functional assignment.                  # Check to see if this is a functional assignment.
1184                  my ($user, $function) = ParseAssignment($text);          my ($actualUser, $function) = _ParseAssignment($user, $text);
1185                  if ($user) {          if ($actualUser && ! exists $retVal{$actualUser}) {
1186                          # Here it is, so stuff it in the return hash.              # Here it is a functional assignment and there has been no
1187                          $retVal{$function} = $user;              # previous assignment for this user, so we stuff it in the
1188                # return hash.
1189                $retVal{$actualUser} = $function;
1190                  }                  }
1191          }          }
1192          # Return the hash of assignments found.          # Return the hash of assignments found.
# Line 1063  Line 1201 
1201    
1202  The functional assignment is handled differently depending on the type of feature. If  The functional assignment is handled differently depending on the type of feature. If
1203  the feature is identified by a FIG ID (begins with the string C<fig|>), then a functional  the feature is identified by a FIG ID (begins with the string C<fig|>), then a functional
1204  assignment is a type of annotation. It has the format "XXXX\nset XXXX function to\nYYYYY". In this  assignment is a type of annotation. The format of an assignment is described in
1205  instance, XXXX is the user ID and YYYYY is the functional assignment text. Its worth noting that  L</ParseAssignment>. Its worth noting that we cannot filter on the content of the
1206  we cannot filter on the content of the annotation itself because it's a text field; however, this  annotation itself because it's a text field; however, this is not a big problem because
1207  is not a big problem because most features only have a small number of annotations.  most features only have a small number of annotations.
1208    
1209  Each user has an associated list of trusted users. The assignment returned will be the most  Each user has an associated list of trusted users. The assignment returned will be the most
1210  recent one by at least one of the trusted users. If no trusted user list is available, then  recent one by at least one of the trusted users. If no trusted user list is available, then
# Line 1098  Line 1236 
1236  #: Return Type $;  #: Return Type $;
1237  sub FunctionOf {  sub FunctionOf {
1238          # Get the parameters.          # Get the parameters.
1239          my $self = shift @_;      my ($self, $featureID, $userID) = @_;
         my ($featureID, $userID) = @_;  
1240      # Declare the return value.      # Declare the return value.
1241      my $retVal;      my $retVal;
1242      # Determine the ID type.      # Determine the ID type.
# Line 1127  Line 1264 
1264              }              }
1265          }          }
1266          # 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.
1267          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation'],          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1268                                 "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",                                 "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1269                                 [$featureID]);                                 [$featureID]);
1270          my $timeSelected = 0;          my $timeSelected = 0;
1271          # Loop until we run out of annotations.          # Loop until we run out of annotations.
1272          while (my $annotation = $query->Fetch()) {          while (my $annotation = $query->Fetch()) {
1273              # Get the annotation text.              # Get the annotation text.
1274              my ($text, $time) = $annotation->Values(['Annotation(annotation)','Annotation(time)']);              my ($text, $time, $user) = $annotation->Values(['Annotation(annotation)',
1275                                                         'Annotation(time)', 'MadeAnnotation(from-link)']);
1276              # Check to see if this is a functional assignment for a trusted user.              # Check to see if this is a functional assignment for a trusted user.
1277              my ($user, $type, $function) = split(/\n/, $text);              my ($actualUser, $function) = _ParseAssignment($user, $text);
1278              if ($type =~ m/^set $user function to$/i) {              Trace("Assignment user is $actualUser, text is $function.") if T(4);
1279                if ($actualUser) {
1280                  # Here it is a functional assignment. Check the time and the user                  # Here it is a functional assignment. Check the time and the user
1281                  # name. The time must be recent and the user must be trusted.                  # name. The time must be recent and the user must be trusted.
1282                  if ((exists $trusteeTable{$user}) && ($time > $timeSelected)) {                  if ((exists $trusteeTable{$actualUser}) && ($time > $timeSelected)) {
1283                      $retVal = $function;                      $retVal = $function;
1284                      $timeSelected = $time;                      $timeSelected = $time;
1285                  }                  }
# Line 1156  Line 1295 
1295          return $retVal;          return $retVal;
1296  }  }
1297    
1298    =head3 FunctionsOf
1299    
1300    C<< my @functionList = $sprout->FunctionOf($featureID, $userID); >>
1301    
1302    Return the functional assignments of a particular feature.
1303    
1304    The functional assignment is handled differently depending on the type of feature. If
1305    the feature is identified by a FIG ID (begins with the string C<fig|>), then a functional
1306    assignment is a type of annotation. The format of an assignment is described in
1307    L</ParseAssignment>. Its worth noting that we cannot filter on the content of the
1308    annotation itself because it's a text field; however, this is not a big problem because
1309    most features only have a small number of annotations.
1310    
1311    If the feature is B<not> identified by a FIG ID, then the functional assignment
1312    information is taken from the B<ExternalAliasFunc> table. If the table does
1313    not contain an entry for the feature, an empty list is returned.
1314    
1315    =over 4
1316    
1317    =item featureID
1318    
1319    ID of the feature whose functional assignments are desired.
1320    
1321    =item RETURN
1322    
1323    Returns a list of 2-tuples, each consisting of a user ID and the text of an assignment by
1324    that user.
1325    
1326    =back
1327    
1328    =cut
1329    #: Return Type @@;
1330    sub FunctionsOf {
1331        # Get the parameters.
1332        my ($self, $featureID) = @_;
1333        # Declare the return value.
1334        my @retVal = ();
1335        # Determine the ID type.
1336        if ($featureID =~ m/^fig\|/) {
1337            # Here we have a FIG feature ID. We must build the list of trusted
1338            # users.
1339            my %trusteeTable = ();
1340            # Build a query for all of the feature's annotations, sorted by date.
1341            my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1342                                   "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1343                                   [$featureID]);
1344            my $timeSelected = 0;
1345            # Loop until we run out of annotations.
1346            while (my $annotation = $query->Fetch()) {
1347                # Get the annotation text.
1348                my ($text, $time, $user) = $annotation->Values(['Annotation(annotation)',
1349                                                                'Annotation(time)',
1350                                                                'MadeAnnotation(user)']);
1351                # Check to see if this is a functional assignment for a trusted user.
1352                my ($actualUser, $function) = _ParseAssignment($user, $text);
1353                if ($actualUser) {
1354                    # Here it is a functional assignment.
1355                    push @retVal, [$actualUser, $function];
1356                }
1357            }
1358        } else {
1359            # Here we have a non-FIG feature ID. In this case the user ID does not
1360            # matter. We simply get the information from the External Alias Function
1361            # table.
1362            my @assignments = $self->GetEntityValues('ExternalAliasFunc', $featureID,
1363                                                     ['ExternalAliasFunc(func)']);
1364            push @retVal, map { ['master', $_] } @assignments;
1365        }
1366        # Return the assignments found.
1367        return @retVal;
1368    }
1369    
1370  =head3 BBHList  =head3 BBHList
1371    
1372  C<< my $bbhHash = $sprout->BBHList($genomeID, \@featureList); >>  C<< my $bbhHash = $sprout->BBHList($genomeID, \@featureList); >>
# Line 1175  Line 1386 
1386    
1387  =item RETURN  =item RETURN
1388    
1389  Returns a reference to a hash that maps the IDs of the incoming features to the IDs of  Returns a reference to a hash that maps the IDs of the incoming features to the best hits
1390  their best hits.  on the target genome.
1391    
1392  =back  =back
1393    
# Line 1184  Line 1395 
1395  #: Return Type %;  #: Return Type %;
1396  sub BBHList {  sub BBHList {
1397          # Get the parameters.          # Get the parameters.
1398          my $self = shift @_;      my ($self, $genomeID, $featureList) = @_;
         my ($genomeID, $featureList) = @_;  
1399          # Create the return structure.          # Create the return structure.
1400          my %retVal = ();          my %retVal = ();
1401          # Loop through the incoming features.          # Loop through the incoming features.
# Line 1194  Line 1404 
1404                  my $query = $self->Get(['IsBidirectionalBestHitOf'],                  my $query = $self->Get(['IsBidirectionalBestHitOf'],
1405                                                             "IsBidirectionalBestHitOf(from-link) = ? AND IsBidirectionalBestHitOf(genome) = ?",                                                             "IsBidirectionalBestHitOf(from-link) = ? AND IsBidirectionalBestHitOf(genome) = ?",
1406                                                             [$featureID, $genomeID]);                                                             [$featureID, $genomeID]);
1407                  # Look for the best hit.          # Peel off the BBHs found.
1408                  my $bbh = $query->Fetch;          my @found = ();
1409                  if ($bbh) {          while (my $bbh = $query->Fetch) {
1410                          my ($targetFeature) = $bbh->Value('IsBidirectionalBestHitOf(to-link)');              push @found, $bbh->Value('IsBidirectionalBestHitOf(to-link)');
                         $retVal{$featureID} = $targetFeature;  
1411                  }                  }
1412            $retVal{$featureID} = \@found;
1413          }          }
1414          # Return the mapping.          # Return the mapping.
1415          return \%retVal;          return \%retVal;
1416  }  }
1417    
1418    =head3 SimList
1419    
1420    C<< my %similarities = $sprout->SimList($featureID, $count); >>
1421    
1422    Return a list of the similarities to the specified feature.
1423    
1424    Sprout does not support real similarities, so this method just returns the bidirectional
1425    best hits.
1426    
1427    =over 4
1428    
1429    =item featureID
1430    
1431    ID of the feature whose similarities are desired.
1432    
1433    =item count
1434    
1435    Maximum number of similar features to be returned, or C<0> to return them all.
1436    
1437    =back
1438    
1439    =cut
1440    #: Return Type %;
1441    sub SimList {
1442        # Get the parameters.
1443        my ($self, $featureID, $count) = @_;
1444        # Ask for the best hits.
1445        my @lists = $self->GetAll(['IsBidirectionalBestHitOf'],
1446                                  "IsBidirectionalBestHitOf(from-link) = ? ORDER BY IsBidirectionalBestHitOf(score) DESC",
1447                                  [$featureID], ['IsBidirectionalBestHitOf(to-link)', 'IsBidirectionalBestHitOf(score)'],
1448                                  $count);
1449        # Create the return value.
1450        my %retVal = ();
1451        for my $tuple (@lists) {
1452            $retVal{$tuple->[0]} = $tuple->[1];
1453        }
1454        # Return the result.
1455        return %retVal;
1456    }
1457    
1458    
1459    
1460    =head3 IsComplete
1461    
1462    C<< my $flag = $sprout->IsComplete($genomeID); >>
1463    
1464    Return TRUE if the specified genome is complete, else FALSE.
1465    
1466    =over 4
1467    
1468    =item genomeID
1469    
1470    ID of the genome whose completeness status is desired.
1471    
1472    =item RETURN
1473    
1474    Returns TRUE if the genome is complete, FALSE if it is incomplete, and C<undef> if it is
1475    not found.
1476    
1477    =back
1478    
1479    =cut
1480    #: Return Type $;
1481    sub IsComplete {
1482        # Get the parameters.
1483        my ($self, $genomeID) = @_;
1484        # Declare the return variable.
1485        my $retVal;
1486        # Get the genome's data.
1487        my $genomeData = $self->GetEntity('Genome', $genomeID);
1488        if ($genomeData) {
1489            # The genome exists, so get the completeness flag.
1490            ($retVal) = $genomeData->Value('Genome(complete)');
1491        }
1492        # Return the result.
1493        return $retVal;
1494    }
1495    
1496  =head3 FeatureAliases  =head3 FeatureAliases
1497    
1498  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>
# Line 1228  Line 1516 
1516  #: Return Type @;  #: Return Type @;
1517  sub FeatureAliases {  sub FeatureAliases {
1518          # Get the parameters.          # Get the parameters.
1519          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1520          # Get the desired feature's aliases          # Get the desired feature's aliases
1521          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(alias)']);          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(alias)']);
1522          # Return the result.          # Return the result.
# Line 1240  Line 1527 
1527    
1528  C<< my $genomeID = $sprout->GenomeOf($featureID); >>  C<< my $genomeID = $sprout->GenomeOf($featureID); >>
1529    
1530  Return the genome that contains a specified feature.  Return the genome that contains a specified feature or contig.
1531    
1532  =over 4  =over 4
1533    
1534  =item featureID  =item featureID
1535    
1536  ID of the feature whose genome is desired.  ID of the feature or contig whose genome is desired.
1537    
1538  =item RETURN  =item RETURN
1539    
1540  Returns the ID of the genome for the specified feature. If the feature is not found, returns  Returns the ID of the genome for the specified feature or contig. If the feature or contig is not
1541  an undefined value.  found, returns an undefined value.
1542    
1543  =back  =back
1544    
# Line 1259  Line 1546 
1546  #: Return Type $;  #: Return Type $;
1547  sub GenomeOf {  sub GenomeOf {
1548          # Get the parameters.          # Get the parameters.
1549          my $self = shift @_;      my ($self, $featureID) = @_;
1550          my ($featureID) = @_;      # Create a query to find the genome associated with the incoming ID.
1551          # Create a query to find the genome associated with the feature.      my $query = $self->Get(['IsLocatedIn', 'HasContig'], "IsLocatedIn(from-link) = ? OR HasContig(to-link) = ?",
1552          my $query = $self->Get(['IsLocatedIn', 'HasContig'], "IsLocatedIn(from-link) = ?", [$featureID]);                             [$featureID, $featureID]);
1553          # Declare the return value.          # Declare the return value.
1554          my $retVal;          my $retVal;
1555          # Get the genome ID.          # Get the genome ID.
# Line 1296  Line 1583 
1583  #: Return Type %;  #: Return Type %;
1584  sub CoupledFeatures {  sub CoupledFeatures {
1585          # Get the parameters.          # Get the parameters.
1586          my $self = shift @_;      my ($self, $featureID) = @_;
1587          my ($featureID) = @_;      # Create a query to retrieve the functionally-coupled features.
1588          # Create a query to retrieve the functionally-coupled features. Note that we depend on the      my $query = $self->Get(['ParticipatesInCoupling', 'Coupling'],
1589          # fact that the functional coupling is physically paired. If (A,B) is in the database, then                             "ParticipatesInCoupling(from-link) = ?", [$featureID]);
         # (B,A) will also be found.  
         my $query = $self->Get(['IsClusteredOnChromosomeWith'],  
                                                    "IsClusteredOnChromosomeWith(from-link) = ?", [$featureID]);  
1590          # This value will be set to TRUE if we find at least one coupled feature.          # This value will be set to TRUE if we find at least one coupled feature.
1591          my $found = 0;          my $found = 0;
1592          # Create the return hash.          # Create the return hash.
1593          my %retVal = ();          my %retVal = ();
1594          # Retrieve the relationship records and store them in the hash.          # Retrieve the relationship records and store them in the hash.
1595          while (my $clustering = $query->Fetch()) {          while (my $clustering = $query->Fetch()) {
1596                  my ($otherFeatureID, $score) = $clustering->Values(['IsClusteredOnChromosomeWith(to-link)',          # Get the ID and score of the coupling.
1597                                                                      'IsClusteredOnChromosomeWith(score)']);          my ($couplingID, $score) = $clustering->Values(['Coupling(id)',
1598                                                            'Coupling(score)']);
1599            # The coupling ID contains the two feature IDs separated by a space. We use
1600            # this information to find the ID of the other feature.
1601            my ($fid1, $fid2) = split / /, $couplingID;
1602            my $otherFeatureID = ($featureID eq $fid1 ? $fid2 : $fid1);
1603            # Attach the other feature's score to its ID.
1604                  $retVal{$otherFeatureID} = $score;                  $retVal{$otherFeatureID} = $score;
1605                  $found = 1;                  $found = 1;
1606          }          }
# Line 1323  Line 1613 
1613          return %retVal;          return %retVal;
1614  }  }
1615    
1616    =head3 CouplingEvidence
1617    
1618    C<< my @evidence = $sprout->CouplingEvidence($peg1, $peg2); >>
1619    
1620    Return the evidence for a functional coupling.
1621    
1622    A pair of features is considered evidence of a coupling between two other
1623    features if they occur close together on a contig and both are similar to
1624    the coupled features. So, if B<A1> and B<A2> are close together on a contig,
1625    B<B1> and B<B2> are considered evidence for the coupling if (1) B<B1> and
1626    B<B2> are close together, (2) B<B1> is similar to B<A1>, and (3) B<B2> is
1627    similar to B<A2>.
1628    
1629    The score of a coupling is determined by the number of pieces of evidence
1630    that are considered I<representative>. If several evidence items belong to
1631    a group of genomes that are close to each other, only one of those items
1632    is considered representative. The other evidence items are presumed to be
1633    there because of the relationship between the genomes rather than because
1634    the two proteins generated by the features have a related functionality.
1635    
1636    Each evidence item is returned as a three-tuple in the form C<[>I<$peg1a>C<,>
1637    I<$peg2a>C<,> I<$rep>C<]>, where I<$peg1a> is similar to I<$peg1>, I<$peg2a>
1638    is similar to I<$peg2>, and I<$rep> is TRUE if the evidence is representative
1639    and FALSE otherwise.
1640    
1641    =over 4
1642    
1643    =item peg1
1644    
1645    ID of the feature of interest.
1646    
1647    =item peg2
1648    
1649    ID of a feature functionally coupled to the feature of interest.
1650    
1651    =item RETURN
1652    
1653    Returns a list of 3-tuples. Each tuple consists of a feature similar to the feature
1654    of interest, a feature similar to the functionally coupled feature, and a flag
1655    that is TRUE for a representative piece of evidence and FALSE otherwise.
1656    
1657    =back
1658    
1659    =cut
1660    #: Return Type @@;
1661    sub CouplingEvidence {
1662        # Get the parameters.
1663        my ($self, $peg1, $peg2) = @_;
1664        # Declare the return variable.
1665        my @retVal = ();
1666        # Our first task is to find out the nature of the coupling: whether or not
1667        # it exists, its score, and whether the features are stored in the same
1668        # order as the ones coming in.
1669        my ($couplingID, $inverted, $score) = $self->GetCoupling($peg1, $peg2);
1670        # Only proceed if a coupling exists.
1671        if ($couplingID) {
1672            # Determine the ordering to place on the evidence items. If we're
1673            # inverted, we want to see feature 2 before feature 1 (descending); otherwise,
1674            # we want feature 1 before feature 2 (normal).
1675            Trace("Coupling evidence for ($peg1, $peg2) with inversion flag $inverted.") if T(Coupling => 4);
1676            my $ordering = ($inverted ? "DESC" : "");
1677            # Get the coupling evidence.
1678            my @evidenceList = $self->GetAll(['IsEvidencedBy', 'PCH', 'UsesAsEvidence'],
1679                                              "IsEvidencedBy(from-link) = ? ORDER BY PCH(id), UsesAsEvidence(pos) $ordering",
1680                                              [$couplingID],
1681                                              ['PCH(used)', 'UsesAsEvidence(to-link)']);
1682            # Loop through the evidence items. Each piece of evidence is represented by two
1683            # positions in the evidence list, one for each feature on the other side of the
1684            # evidence link. If at some point we want to generalize to couplings with
1685            # more than two positions, this section of code will need to be re-done.
1686            while (@evidenceList > 0) {
1687                my $peg1Data = shift @evidenceList;
1688                my $peg2Data = shift @evidenceList;
1689                Trace("Peg 1 is " . $peg1Data->[1] . " and Peg 2 is " . $peg2Data->[1] . ".") if T(Coupling => 4);
1690                push @retVal, [$peg1Data->[1], $peg2Data->[1], $peg1Data->[0]];
1691            }
1692            Trace("Last index in evidence result is is $#retVal.") if T(Coupling => 4);
1693        }
1694        # Return the result.
1695        return @retVal;
1696    }
1697    
1698    =head3 GetCoupling
1699    
1700    C<< my ($couplingID, $inverted, $score) = $sprout->GetCoupling($peg1, $peg2); >>
1701    
1702    Return the coupling (if any) for the specified pair of PEGs. If a coupling
1703    exists, we return the coupling ID along with an indicator of whether the
1704    coupling is stored as C<(>I<$peg1>C<, >I<$peg2>C<)> or C<(>I<$peg2>C<, >I<$peg1>C<)>.
1705    In the second case, we say the coupling is I<inverted>. The importance of an
1706    inverted coupling is that the PEGs in the evidence will appear in reverse order.
1707    
1708    =over 4
1709    
1710    =item peg1
1711    
1712    ID of the feature of interest.
1713    
1714    =item peg2
1715    
1716    ID of the potentially coupled feature.
1717    
1718    =item RETURN
1719    
1720    Returns a three-element list. The first element contains the database ID of
1721    the coupling. The second element is FALSE if the coupling is stored in the
1722    database in the caller specified order and TRUE if it is stored in the
1723    inverted order. The third element is the coupling's score. If the coupling
1724    does not exist, all three list elements will be C<undef>.
1725    
1726    =back
1727    
1728    =cut
1729    #: Return Type $%@;
1730    sub GetCoupling {
1731        # Get the parameters.
1732        my ($self, $peg1, $peg2) = @_;
1733        # Declare the return values. We'll start with the coupling ID and undefine the
1734        # flag and score until we have more information.
1735        my ($retVal, $inverted, $score) = (CouplingID($peg1, $peg2), undef, undef);
1736        # Find the coupling data.
1737        my @pegs = $self->GetAll(['Coupling', 'ParticipatesInCoupling'],
1738                                     "Coupling(id) = ? ORDER BY ParticipatesInCoupling(pos)",
1739                                     [$retVal], ["ParticipatesInCoupling(from-link)", "Coupling(score)"]);
1740        # Check to see if we found anything.
1741        if (!@pegs) {
1742            Trace("No coupling found.") if T(Coupling => 4);
1743            # No coupling, so undefine the return value.
1744            $retVal = undef;
1745        } else {
1746            # We have a coupling! Get the score and check for inversion.
1747            $score = $pegs[0]->[1];
1748            my $firstFound = $pegs[0]->[0];
1749            $inverted = ($firstFound ne $peg1);
1750            Trace("Coupling score is $score. First peg is $firstFound, peg 1 is $peg1.") if T(Coupling => 4);
1751        }
1752        # Return the result.
1753        return ($retVal, $inverted, $score);
1754    }
1755    
1756    =head3 CouplingID
1757    
1758    C<< my $couplingID = Sprout::CouplingID($peg1, $peg2); >>
1759    
1760    Return the coupling ID for a pair of feature IDs.
1761    
1762    The coupling ID is currently computed by joining the feature IDs in
1763    sorted order with a space. Client modules (that is, modules which
1764    use Sprout) should not, however, count on this always being the
1765    case. This method provides a way for abstracting the concept of a
1766    coupling ID. All that we know for sure about it is that it can be
1767    generated easily from the feature IDs and the order of the IDs
1768    in the parameter list does not matter (i.e. C<CouplingID("a1", "b1")>
1769    will have the same value as C<CouplingID("b1", "a1")>.
1770    
1771    =over 4
1772    
1773    =item peg1
1774    
1775    First feature of interest.
1776    
1777    =item peg2
1778    
1779    Second feature of interest.
1780    
1781    =item RETURN
1782    
1783    Returns the ID that would be used to represent a functional coupling of
1784    the two specified PEGs.
1785    
1786    =back
1787    
1788    =cut
1789    #: Return Type $;
1790    sub CouplingID {
1791        return join " ", sort @_;
1792    }
1793    
1794  =head3 GetEntityTypes  =head3 GetEntityTypes
1795    
1796  C<< my @entityList = $sprout->GetEntityTypes(); >>  C<< my @entityList = $sprout->GetEntityTypes(); >>
# Line 1333  Line 1801 
1801  #: Return Type @;  #: Return Type @;
1802  sub GetEntityTypes {  sub GetEntityTypes {
1803          # Get the parameters.          # Get the parameters.
1804          my $self = shift @_;      my ($self) = @_;
1805          # Get the underlying database object.          # Get the underlying database object.
1806          my $erdb = $self->{_erdb};          my $erdb = $self->{_erdb};
1807          # Get its entity type list.          # Get its entity type list.
# Line 1384  Line 1852 
1852                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {
1853                          # Here we have a new header. Store the current sequence if we have one.                          # Here we have a new header. Store the current sequence if we have one.
1854                          if ($id) {                          if ($id) {
1855                                  $retVal{$id} = $sequence;                  $retVal{$id} = lc $sequence;
1856                          }                          }
1857                          # Clear the sequence accumulator and save the new ID.                          # Clear the sequence accumulator and save the new ID.
1858                          ($id, $sequence) = ("$prefix$1", "");                          ($id, $sequence) = ("$prefix$1", "");
1859                  } else {                  } else {
1860                          # Here we have a data line, so we add it to the sequence accumulator.                          # Here we have a data line, so we add it to the sequence accumulator.
1861                          # First, we get the actual data out.              # First, we get the actual data out. Note that we normalize to lower
1862                # case.
1863                          $line =~ /^\s*(.*?)(\s|\n)/;                          $line =~ /^\s*(.*?)(\s|\n)/;
1864                          $sequence .= $1;                          $sequence .= $1;
1865                  }                  }
1866          }          }
1867          # Flush out the last sequence (if any).          # Flush out the last sequence (if any).
1868          if ($sequence) {          if ($sequence) {
1869                  $retVal {$id} = $sequence;          $retVal{$id} = lc $sequence;
1870          }          }
1871        # Close the file.
1872        close FASTAFILE;
1873          # Return the hash constructed from the file.          # Return the hash constructed from the file.
1874          return %retVal;          return %retVal;
1875  }  }
# Line 1409  Line 1880 
1880    
1881  Insure that a list of feature locations is in the Sprout format. The Sprout feature location  Insure that a list of feature locations is in the Sprout format. The Sprout feature location
1882  format is I<contig>_I<beg*len> where I<*> is C<+> for a forward gene and C<-> for a backward  format is I<contig>_I<beg*len> where I<*> is C<+> for a forward gene and C<-> for a backward
1883  gene. The old format is I<contig>_I<beg>_I<end>.  gene. The old format is I<contig>_I<beg>_I<end>. If a feature is in the new format already,
1884    it will not be changed; otherwise, it will be converted. This method can also be used to
1885    perform the reverse task-- insuring that all the locations are in the old format.
1886    
1887  =over 4  =over 4
1888    
# Line 1436  Line 1909 
1909  #: Return Type @;  #: Return Type @;
1910  sub FormatLocations {  sub FormatLocations {
1911          # Get the parameters.          # Get the parameters.
1912          my $self = shift @_;      my ($self, $prefix, $locations, $oldFormat) = @_;
         my ($prefix, $locations, $oldFormat) = @_;  
1913          # Create the return list.          # Create the return list.
1914          my @retVal = ();          my @retVal = ();
1915          # Check to see if any locations were passed in.          # Check to see if any locations were passed in.
1916          if ($locations eq '') {          if ($locations eq '') {
1917              confess "No locations specified.";          Confess("No locations specified.");
1918          } else {          } else {
1919                  # Loop through the locations, converting them to the new format.                  # Loop through the locations, converting them to the new format.
1920                  for my $location (@{$locations}) {                  for my $location (@{$locations}) {
# Line 1477  Line 1949 
1949    
1950  sub DumpData {  sub DumpData {
1951          # Get the parameters.          # Get the parameters.
1952          my $self = shift @_;      my ($self) = @_;
1953          # Get the data directory name.          # Get the data directory name.
1954          my $outputDirectory = $self->{_options}->{dataDir};          my $outputDirectory = $self->{_options}->{dataDir};
1955          # Dump the relations.          # Dump the relations.
# Line 1493  Line 1965 
1965  =cut  =cut
1966  #: Return Type $;  #: Return Type $;
1967  sub XMLFileName {  sub XMLFileName {
1968          my $self = shift @_;      my ($self) = @_;
1969          return $self->{_xmlName};          return $self->{_xmlName};
1970  }  }
1971    
# Line 1513  Line 1985 
1985  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and
1986  property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.  property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.
1987    
1988  C<< $sprout->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence = 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>  C<< $sprout->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>
1989    
1990  =over 4  =over 4
1991    
# Line 1531  Line 2003 
2003  #: Return Type ;  #: Return Type ;
2004  sub Insert {  sub Insert {
2005          # Get the parameters.          # Get the parameters.
2006          my $self = shift @_;      my ($self, $objectType, $fieldHash) = @_;
         my ($objectType, $fieldHash) = @_;  
2007          # Call the underlying method.          # Call the underlying method.
2008          $self->{_erdb}->InsertObject($objectType, $fieldHash);          $self->{_erdb}->InsertObject($objectType, $fieldHash);
2009  }  }
# Line 1573  Line 2044 
2044  #: Return Type $;  #: Return Type $;
2045  sub Annotate {  sub Annotate {
2046          # Get the parameters.          # Get the parameters.
2047          my $self = shift @_;      my ($self, $fid, $timestamp, $user, $text) = @_;
         my ($fid, $timestamp, $user, $text) = @_;  
2048          # Create the annotation ID.          # Create the annotation ID.
2049          my $aid = "$fid:$timestamp";          my $aid = "$fid:$timestamp";
2050          # Insert the Annotation object.          # Insert the Annotation object.
# Line 1594  Line 2064 
2064    
2065  =head3 AssignFunction  =head3 AssignFunction
2066    
2067  C<< my $ok = $sprout->AssignFunction($featureID, $user, $function); >>  C<< my $ok = $sprout->AssignFunction($featureID, $user, $function, $assigningUser); >>
2068    
2069  This method assigns a function to a feature. Functions are a special type of annotation. The general  This method assigns a function to a feature. Functions are a special type of annotation. The general
2070  format is "XXXX\nset XXXX function to\nYYYYY" where XXXX is the feature type and YYYY is the functional  format is described in L</ParseAssignment>.
 assignment text.  
2071    
2072  =over 4  =over 4
2073    
# Line 1608  Line 2077 
2077    
2078  =item user  =item user
2079    
2080  Name of the user making the assignment. This is frequently a group name, like C<kegg> or C<fig>.  Name of the user group making the assignment, such as C<kegg> or C<fig>.
2081    
2082  =item function  =item function
2083    
2084  Text of the function being assigned.  Text of the function being assigned.
2085    
2086    =item assigningUser (optional)
2087    
2088    Name of the individual user making the assignment. If omitted, defaults to the user group.
2089    
2090  =item RETURN  =item RETURN
2091    
2092  Returns 1 if successful, 0 if an error occurred.  Returns 1 if successful, 0 if an error occurred.
# Line 1624  Line 2097 
2097  #: Return Type $;  #: Return Type $;
2098  sub AssignFunction {  sub AssignFunction {
2099          # Get the parameters.          # Get the parameters.
2100          my $self = shift @_;      my ($self, $featureID, $user, $function, $assigningUser) = @_;
2101          my ($featureID, $user, $function) = @_;      # Default the assigning user.
2102        if (! $assigningUser) {
2103            $assigningUser = $user;
2104        }
2105          # Create an annotation string from the parameters.          # Create an annotation string from the parameters.
2106          my $annotationText = "$user\nset $user function to\n$function";      my $annotationText = "$assigningUser\nset $user function to\n$function";
2107          # Get the current time.          # Get the current time.
2108          my $now = time;          my $now = time;
2109          # Declare the return variable.          # Declare the return variable.
# Line 1672  Line 2148 
2148  #: Return Type @;  #: Return Type @;
2149  sub FeaturesByAlias {  sub FeaturesByAlias {
2150          # Get the parameters.          # Get the parameters.
2151          my $self = shift @_;      my ($self, $alias) = @_;
         my ($alias) = @_;  
2152          # Declare the return variable.          # Declare the return variable.
2153          my @retVal = ();          my @retVal = ();
2154          # Parse the alias.          # Parse the alias.
# Line 1715  Line 2190 
2190  #: Return Type $;  #: Return Type $;
2191  sub Exists {  sub Exists {
2192          # Get the parameters.          # Get the parameters.
2193          my $self = shift @_;      my ($self, $entityName, $entityID) = @_;
         my ($entityName, $entityID) = @_;  
2194          # Check for the entity instance.          # Check for the entity instance.
2195        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
2196          my $testInstance = $self->GetEntity($entityName, $entityID);          my $testInstance = $self->GetEntity($entityName, $entityID);
2197          # Return an existence indicator.          # Return an existence indicator.
2198          my $retVal = ($testInstance ? 1 : 0);          my $retVal = ($testInstance ? 1 : 0);
# Line 1746  Line 2221 
2221  #: Return Type $;  #: Return Type $;
2222  sub FeatureTranslation {  sub FeatureTranslation {
2223          # Get the parameters.          # Get the parameters.
2224          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
2225          # Get the specified feature's translation.          # Get the specified feature's translation.
2226          my ($retVal) = $self->GetEntityValues("Feature", $featureID, ['Feature(translation)']);          my ($retVal) = $self->GetEntityValues("Feature", $featureID, ['Feature(translation)']);
2227          return $retVal;          return $retVal;
# Line 1779  Line 2253 
2253  #: Return Type @;  #: Return Type @;
2254  sub Taxonomy {  sub Taxonomy {
2255          # Get the parameters.          # Get the parameters.
2256          my $self = shift @_;      my ($self, $genome) = @_;
         my ($genome) = @_;  
2257          # Find the specified genome's taxonomy string.          # Find the specified genome's taxonomy string.
2258          my ($list) = $self->GetEntityValues('Genome', $genome, ['Genome(taxonomy)']);          my ($list) = $self->GetEntityValues('Genome', $genome, ['Genome(taxonomy)']);
2259          # Declare the return variable.          # Declare the return variable.
# Line 1823  Line 2296 
2296  #: Return Type $;  #: Return Type $;
2297  sub CrudeDistance {  sub CrudeDistance {
2298          # Get the parameters.          # Get the parameters.
2299          my $self = shift @_;      my ($self, $genome1, $genome2) = @_;
         my ($genome1, $genome2) = @_;  
2300          # Insure that the distance is commutative by sorting the genome IDs.          # Insure that the distance is commutative by sorting the genome IDs.
2301          my ($genomeA, $genomeB);          my ($genomeA, $genomeB);
2302          if ($genome2 < $genome2) {          if ($genome2 < $genome2) {
# Line 1871  Line 2343 
2343  #: Return Type $;  #: Return Type $;
2344  sub RoleName {  sub RoleName {
2345          # Get the parameters.          # Get the parameters.
2346          my $self = shift @_;      my ($self, $roleID) = @_;
         my ($roleID) = @_;  
2347          # Get the specified role's name.          # Get the specified role's name.
2348          my ($retVal) = $self->GetEntityValues('Role', $roleID, ['Role(name)']);          my ($retVal) = $self->GetEntityValues('Role', $roleID, ['Role(name)']);
2349          # Use the ID if the role has no name.          # Use the ID if the role has no name.
# Line 1905  Line 2376 
2376  #: Return Type @;  #: Return Type @;
2377  sub RoleDiagrams {  sub RoleDiagrams {
2378          # Get the parameters.          # Get the parameters.
2379          my $self = shift @_;      my ($self, $roleID) = @_;
         my ($roleID) = @_;  
2380          # Query for the diagrams.          # Query for the diagrams.
2381          my @retVal = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],          my @retVal = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],
2382                                                                  'RoleOccursIn(to-link)');                                                                  'RoleOccursIn(to-link)');
# Line 1914  Line 2384 
2384          return @retVal;          return @retVal;
2385  }  }
2386    
2387    =head3 GetProperties
2388    
2389    C<< my @list = $sprout->GetProperties($fid, $key, $value, $url); >>
2390    
2391    Return a list of the properties with the specified characteristics.
2392    
2393    Properties are arbitrary key-value pairs associated with a feature. (At some point they
2394    will also be associated with genomes.) A property value is represented by a 4-tuple of
2395    the form B<($fid, $key, $value, $url)>. These exactly correspond to the parameter
2396    
2397    =over 4
2398    
2399    =item fid
2400    
2401    ID of the feature possessing the property.
2402    
2403    =item key
2404    
2405    Name or key of the property.
2406    
2407    =item value
2408    
2409    Value of the property.
2410    
2411    =item url
2412    
2413    URL of the document that indicated the property should have this particular value, or an
2414    empty string if no such document exists.
2415    
2416    =back
2417    
2418    The parameters act as a filter for the desired data. Any non-null parameter will
2419    automatically match all the tuples returned. So, specifying just the I<$fid> will
2420    return all the properties of the specified feature; similarly, specifying the I<$key>
2421    and I<$value> parameters will return all the features having the specified property
2422    value.
2423    
2424    A single property key can have many values, representing different ideas about the
2425    feature in question. For example, one paper may declare that a feature C<fig|83333.1.peg.10> is
2426    virulent, and another may declare that it is not virulent. A query about the virulence of
2427    C<fig|83333.1.peg.10> would be coded as
2428    
2429        my @list = $sprout->GetProperties('fig|83333.1.peg.10', 'virulence', '', '');
2430    
2431    Here the I<$value> and I<$url> fields are left blank, indicating that those fields are
2432    not to be filtered. The tuples returned would be
2433    
2434        ('fig|83333.1.peg.10', 'virulence', 'yes', 'http://www.somewhere.edu/first.paper.pdf')
2435        ('fig|83333.1.peg.10', 'virulence', 'no', 'http://www.somewhere.edu/second.paper.pdf')
2436    
2437    =cut
2438    #: Return Type @@;
2439    sub GetProperties {
2440        # Get the parameters.
2441        my ($self, @parms) = @_;
2442        # Declare the return variable.
2443        my @retVal = ();
2444        # Now we need to create a WHERE clause that will get us the data we want. First,
2445        # we create a list of the columns containing the data for each parameter.
2446        my @colNames = ('HasProperty(from-link)', 'Property(property-name)',
2447                        'Property(property-value)', 'HasProperty(evidence)');
2448        # Now we build the WHERE clause and the list of parameter values.
2449        my @where = ();
2450        my @values = ();
2451        for (my $i = 0; $i <= $#colNames; $i++) {
2452            my $parm = $parms[$i];
2453            if (defined $parm && ($parm ne '')) {
2454                push @where, "$colNames[$i] = ?";
2455                push @values, $parm;
2456            }
2457        }
2458        # Format the WHERE clause.
2459        my $filter = (@values > 0 ? (join " AND ", @where) : undef);
2460        # Ask for all the propertie values with the desired characteristics.
2461        my $query = $self->Get(['HasProperty', 'Property'], $filter, \@values);
2462        while (my $valueObject = $query->Fetch()) {
2463            my @tuple = $valueObject->Values(\@colNames);
2464            push @retVal, \@tuple;
2465        }
2466        # Return the result.
2467        return @retVal;
2468    }
2469    
2470  =head3 FeatureProperties  =head3 FeatureProperties
2471    
2472  C<< my @properties = $sprout->FeatureProperties($featureID); >>  C<< my @properties = $sprout->FeatureProperties($featureID); >>
# Line 1943  Line 2496 
2496  #: Return Type @@;  #: Return Type @@;
2497  sub FeatureProperties {  sub FeatureProperties {
2498          # Get the parameters.          # Get the parameters.
2499          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
2500          # Get the properties.          # Get the properties.
2501          my @retVal = $self->GetAll(['HasProperty', 'Property'], "HasProperty(from-link) = ?", [$featureID],          my @retVal = $self->GetAll(['HasProperty', 'Property'], "HasProperty(from-link) = ?", [$featureID],
2502                                                          ['Property(property-name)', 'Property(property-value)',                                                          ['Property(property-name)', 'Property(property-value)',
# Line 1975  Line 2527 
2527  #: Return Type $;  #: Return Type $;
2528  sub DiagramName {  sub DiagramName {
2529          # Get the parameters.          # Get the parameters.
2530          my $self = shift @_;      my ($self, $diagramID) = @_;
         my ($diagramID) = @_;  
2531          # Get the specified diagram's name and return it.          # Get the specified diagram's name and return it.
2532          my ($retVal) = $self->GetEntityValues('Diagram', $diagramID, ['Diagram(name)']);          my ($retVal) = $self->GetEntityValues('Diagram', $diagramID, ['Diagram(name)']);
2533          return $retVal;          return $retVal;
# Line 2008  Line 2559 
2559  #: Return Type @;  #: Return Type @;
2560  sub MergedAnnotations {  sub MergedAnnotations {
2561          # Get the parameters.          # Get the parameters.
2562          my $self = shift @_;      my ($self, $list) = @_;
         my ($list) = @_;  
2563          # Create a list to hold the annotation tuples found.          # Create a list to hold the annotation tuples found.
2564          my @tuples = ();          my @tuples = ();
2565          # Loop through the features in the input list.          # Loop through the features in the input list.
# Line 2057  Line 2607 
2607  #: Return Type @;  #: Return Type @;
2608  sub RoleNeighbors {  sub RoleNeighbors {
2609          # Get the parameters.          # Get the parameters.
2610          my $self = shift @_;      my ($self, $roleID) = @_;
         my ($roleID) = @_;  
2611          # Get all the diagrams containing this role.          # Get all the diagrams containing this role.
2612          my @diagrams = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],          my @diagrams = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],
2613                                                                    'RoleOccursIn(to-link)');                                                                    'RoleOccursIn(to-link)');
# Line 2100  Line 2649 
2649  #: Return Type @;  #: Return Type @;
2650  sub FeatureLinks {  sub FeatureLinks {
2651          # Get the parameters.          # Get the parameters.
2652          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
2653          # Get the feature's links.          # Get the feature's links.
2654          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(link)']);          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(link)']);
2655          # Return the feature's links.          # Return the feature's links.
# Line 2113  Line 2661 
2661  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>
2662    
2663  Return a hash describing all the subsystems in which a feature participates. Each subsystem is mapped  Return a hash describing all the subsystems in which a feature participates. Each subsystem is mapped
2664  to the role the feature performs.  to the roles the feature performs.
2665    
2666  =over 4  =over 4
2667    
# Line 2123  Line 2671 
2671    
2672  =item RETURN  =item RETURN
2673    
2674  Returns a hash mapping all the feature's subsystems to the feature's role.  Returns a hash mapping all the feature's subsystems to a list of the feature's roles.
2675    
2676  =back  =back
2677    
2678  =cut  =cut
2679  #: Return Type %;  #: Return Type %@;
2680  sub SubsystemsOf {  sub SubsystemsOf {
2681          # Get the parameters.          # Get the parameters.
2682          my $self = shift @_;      my ($self, $featureID) = @_;
2683          my ($featureID) = @_;      # Get the subsystem list.
         # Use the SSCell to connect features to subsystems.  
2684          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],
2685                                                                          "ContainsFeature(to-link) = ?", [$featureID],                                                                          "ContainsFeature(to-link) = ?", [$featureID],
2686                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);
2687          # Create the return value.          # Create the return value.
2688          my %retVal = ();          my %retVal = ();
2689        # Build a hash to weed out duplicates. Sometimes the same PEG and role appears
2690        # in two spreadsheet cells.
2691        my %dupHash = ();
2692          # Loop through the results, adding them to the hash.          # Loop through the results, adding them to the hash.
2693          for my $record (@subsystems) {          for my $record (@subsystems) {
2694                  $retVal{$record->[0]} = $record->[1];          # Get this subsystem and role.
2695            my ($subsys, $role) = @{$record};
2696            # Insure it's the first time for both.
2697            my $dupKey = "$subsys\n$role";
2698            if (! exists $dupHash{"$subsys\n$role"}) {
2699                $dupHash{$dupKey} = 1;
2700                push @{$retVal{$subsys}}, $role;
2701            }
2702          }          }
2703          # Return the hash.          # Return the hash.
2704          return %retVal;          return %retVal;
2705  }  }
2706    
2707    =head3 SubsystemList
2708    
2709    C<< my @subsystems = $sprout->SubsystemList($featureID); >>
2710    
2711    Return a list containing the names of the subsystems in which the specified
2712    feature participates. Unlike L</SubsystemsOf>, this method only returns the
2713    subsystem names, not the roles.
2714    
2715    =over 4
2716    
2717    =item featureID
2718    
2719    ID of the feature whose subsystem names are desired.
2720    
2721    =item RETURN
2722    
2723    Returns a list of the names of the subsystems in which the feature participates.
2724    
2725    =back
2726    
2727    =cut
2728    #: Return Type @;
2729    sub SubsystemList {
2730        # Get the parameters.
2731        my ($self, $featureID) = @_;
2732        # Get the list of names.
2733        my @retVal = $self->GetFlat(['ContainsFeature', 'HasSSCell'], "ContainsFeature(to-link) = ?",
2734                                    [$featureID], 'HasSSCell(from-link)');
2735        # Return the result.
2736        return @retVal;
2737    }
2738    
2739    
2740    
2741  =head3 RelatedFeatures  =head3 RelatedFeatures
2742    
2743  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>
# Line 2180  Line 2771 
2771  #: Return Type @;  #: Return Type @;
2772  sub RelatedFeatures {  sub RelatedFeatures {
2773          # Get the parameters.          # Get the parameters.
2774          my $self = shift @_;      my ($self, $featureID, $function, $userID) = @_;
         my ($featureID, $function, $userID) = @_;  
2775          # 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.
2776          my @bbhFeatures = $self->GetFlat(['IsBidirectionalBestHitOf'],          my @bbhFeatures = $self->GetFlat(['IsBidirectionalBestHitOf'],
2777                                                                           "IsBidirectionalBestHitOf(from-link) = ?", [$featureID],                                                                           "IsBidirectionalBestHitOf(from-link) = ?", [$featureID],
# Line 2229  Line 2819 
2819  #: Return Type @;  #: Return Type @;
2820  sub TaxonomySort {  sub TaxonomySort {
2821          # Get the parameters.          # Get the parameters.
2822          my $self = shift @_;      my ($self, $featureIDs) = @_;
         my ($featureIDs) = @_;  
2823          # Create the working hash table.          # Create the working hash table.
2824          my %hashBuffer = ();          my %hashBuffer = ();
2825          # Loop through the features.          # Loop through the features.
# Line 2239  Line 2828 
2828                  my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",                  my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",
2829                                                                                  [$fid], 'Genome(taxonomy)');                                                                                  [$fid], 'Genome(taxonomy)');
2830                  # Add this feature to the hash buffer.                  # Add this feature to the hash buffer.
2831                  if (exists $hashBuffer{$taxonomy}) {          Tracer::AddToListMap(\%hashBuffer, $taxonomy, $fid);
                         push @{$hashBuffer{$taxonomy}}, $fid;  
                 } else {  
                         $hashBuffer{$taxonomy} = [$fid];  
                 }  
2832          }          }
2833          # Sort the keys and get the elements.          # Sort the keys and get the elements.
2834          my @retVal = ();          my @retVal = ();
# Line 2312  Line 2897 
2897  #: Return Type @@;  #: Return Type @@;
2898  sub GetAll {  sub GetAll {
2899          # Get the parameters.          # Get the parameters.
2900          my $self = shift @_;      my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;
2901          my ($objectNames, $filterClause, $parameterList, $fields, $count) = @_;      # Call the ERDB method.
2902          # Create the query.      my @retVal = $self->{_erdb}->GetAll($objectNames, $filterClause, $parameterList,
2903          my $query = $self->Get($objectNames, $filterClause, $parameterList);                                          $fields, $count);
         # Set up a counter of the number of records read.  
         my $fetched = 0;  
         # Insure the counter has a value.  
         if (!defined $count) {  
                 $count = 0;  
         }  
         # Loop through the records returned, extracting the fields. Note that if the  
         # counter is non-zero, we stop when the number of records read hits the count.  
         my @retVal = ();  
         while (($count == 0 || $fetched < $count) && (my $row = $query->Fetch())) {  
                 my @rowData = $row->Values($fields);  
                 push @retVal, \@rowData;  
                 $fetched++;  
         }  
2904          # Return the resulting list.          # Return the resulting list.
2905          return @retVal;          return @retVal;
2906  }  }
# Line 2374  Line 2945 
2945  #: Return Type @;  #: Return Type @;
2946  sub GetFlat {  sub GetFlat {
2947          # Get the parameters.          # Get the parameters.
2948          my $self = shift @_;      my ($self, $objectNames, $filterClause, $parameterList, $field) = @_;
         my ($objectNames, $filterClause, $parameterList, $field) = @_;  
2949          # Construct the query.          # Construct the query.
2950          my $query = $self->Get($objectNames, $filterClause, $parameterList);          my $query = $self->Get($objectNames, $filterClause, $parameterList);
2951          # Create the result list.          # Create the result list.
# Line 2485  Line 3055 
3055  #: Return Type @;  #: Return Type @;
3056  sub LoadInfo {  sub LoadInfo {
3057          # Get the parameters.          # Get the parameters.
3058          my $self = shift @_;      my ($self) = @_;
3059          # Create the return list, priming it with the name of the data directory.          # Create the return list, priming it with the name of the data directory.
3060          my @retVal = ($self->{_options}->{dataDir});          my @retVal = ($self->{_options}->{dataDir});
3061          # Concatenate the table names.          # Concatenate the table names.
# Line 2522  Line 3092 
3092  #: Return Type %;  #: Return Type %;
3093  sub LowBBHs {  sub LowBBHs {
3094          # Get the parsameters.          # Get the parsameters.
3095          my $self = shift @_;      my ($self, $featureID, $cutoff) = @_;
         my ($featureID, $cutoff) = @_;  
3096          # Create the return hash.          # Create the return hash.
3097          my %retVal = ();          my %retVal = ();
3098          # Create a query to get the desired BBHs.          # Create a query to get the desired BBHs.
# Line 2539  Line 3108 
3108          return %retVal;          return %retVal;
3109  }  }
3110    
3111    =head3 GetGroups
3112    
3113    C<< my %groups = $sprout->GetGroups(\@groupList); >>
3114    
3115    Return a hash mapping each group to the IDs of the genomes in the group.
3116    A list of groups may be specified, in which case only those groups will be
3117    shown. Alternatively, if no parameter is supplied, all groups will be
3118    included. Genomes that are not in any group are omitted.
3119    
3120    =cut
3121    #: Return Type %@;
3122    sub GetGroups {
3123        # Get the parameters.
3124        my ($self, $groupList) = @_;
3125        # Declare the return value.
3126        my %retVal = ();
3127        # Determine whether we are getting all the groups or just some.
3128        if (defined $groupList) {
3129            # Here we have a group list. Loop through them individually,
3130            # getting a list of the relevant genomes.
3131            for my $group (@{$groupList}) {
3132                my @genomeIDs = $self->GetFlat(['Genome'], "Genome(group-name) = ?",
3133                    [$group], "Genome(id)");
3134                $retVal{$group} = \@genomeIDs;
3135            }
3136        } else {
3137            # Here we need all of the groups. In this case, we run through all
3138            # of the genome records, putting each one found into the appropriate
3139            # group. Note that we use a filter clause to insure that only genomes
3140            # in groups are included in the return set.
3141            my @genomes = $self->GetAll(['Genome'], "Genome(group-name) > ' '", [],
3142                                        ['Genome(id)', 'Genome(group-name)']);
3143            # Loop through the genomes found.
3144            for my $genome (@genomes) {
3145                # Pop this genome's ID off the current list.
3146                my @groups = @{$genome};
3147                my $genomeID = shift @groups;
3148                # Loop through the groups, adding the genome ID to each group's
3149                # list.
3150                for my $group (@groups) {
3151                    Tracer::AddToListMap(\%retVal, $group, $genomeID);
3152                }
3153            }
3154        }
3155        # Return the hash we just built.
3156        return %retVal;
3157    }
3158    
3159    =head3 MyGenomes
3160    
3161    C<< my @genomes = Sprout::MyGenomes($dataDir); >>
3162    
3163    Return a list of the genomes to be included in the Sprout.
3164    
3165    This method is provided for use during the Sprout load. It presumes the Genome load file has
3166    already been created. (It will be in the Sprout data directory and called either C<Genome>
3167    or C<Genome.dtx>.) Essentially, it reads in the Genome load file and strips out the genome
3168    IDs.
3169    
3170    =over 4
3171    
3172    =item dataDir
3173    
3174    Directory containing the Sprout load files.
3175    
3176    =back
3177    
3178    =cut
3179    #: Return Type @;
3180    sub MyGenomes {
3181        # Get the parameters.
3182        my ($dataDir) = @_;
3183        # Compute the genome file name.
3184        my $genomeFileName = LoadFileName($dataDir, "Genome");
3185        # Extract the genome IDs from the files.
3186        my @retVal = map { $_ =~ /^(\S+)/; $1 } Tracer::GetFile($genomeFileName);
3187        # Return the result.
3188        return @retVal;
3189    }
3190    
3191    =head3 LoadFileName
3192    
3193    C<< my $fileName = Sprout::LoadFileName($dataDir, $tableName); >>
3194    
3195    Return the name of the load file for the specified table in the specified data
3196    directory.
3197    
3198    =over 4
3199    
3200    =item dataDir
3201    
3202    Directory containing the Sprout load files.
3203    
3204    =item tableName
3205    
3206    Name of the table whose load file is desired.
3207    
3208    =item RETURN
3209    
3210    Returns the name of the file containing the load data for the specified table, or
3211    C<undef> if no load file is present.
3212    
3213    =back
3214    
3215    =cut
3216    #: Return Type $;
3217    sub LoadFileName {
3218        # Get the parameters.
3219        my ($dataDir, $tableName) = @_;
3220        # Declare the return variable.
3221        my $retVal;
3222        # Check for the various file names.
3223        if (-e "$dataDir/$tableName") {
3224            $retVal = "$dataDir/$tableName";
3225        } elsif (-e "$dataDir/$tableName.dtx") {
3226            $retVal = "$dataDir/$tableName.dtx";
3227        }
3228        # Return the result.
3229        return $retVal;
3230    }
3231    
3232    =head3 DeleteGenome
3233    
3234    C<< my $stats = $sprout->DeleteGenome($genomeID, $testFlag); >>
3235    
3236    Delete a genome from the database.
3237    
3238    =over 4
3239    
3240    =item genomeID
3241    
3242    ID of the genome to delete
3243    
3244    =item testFlag
3245    
3246    If TRUE, then the DELETE statements will be traced, but no deletions will occur.
3247    
3248    =item RETURN
3249    
3250    Returns a statistics object describing the rows deleted.
3251    
3252    =back
3253    
3254    =cut
3255    #: Return Type $%;
3256    sub DeleteGenome {
3257        # Get the parameters.
3258        my ($self, $genomeID, $testFlag) = @_;
3259        # Perform the delete for the genome's features.
3260        my $retVal = $self->{_erdb}->Delete('Feature', "fig|$genomeID.%", $testFlag);
3261        # Perform the delete for the primary genome data.
3262        my $stats = $self->{_erdb}->Delete('Genome', $genomeID, $testFlag);
3263        $retVal->Accumulate($stats);
3264        # Return the result.
3265        return $retVal;
3266    }
3267    
3268  =head2 Internal Utility Methods  =head2 Internal Utility Methods
3269    
3270  =head3 ParseAssignment  =head3 ParseAssignment
3271    
3272  Parse annotation text to determine whether or not it is a functional assignment. If it is,  Parse annotation text to determine whether or not it is a functional assignment. If it is,
3273  the user and function text will be returned as a 2-element list. If it isn't, an empty list  the user, function text, and assigning user will be returned as a 3-element list. If it
3274  will be returned.  isn't, an empty list will be returned.
3275    
3276    A functional assignment is always of the form
3277    
3278        C<set >I<YYYY>C< function to\n>I<ZZZZZ>
3279    
3280    where I<YYYY> is the B<user>, and I<ZZZZ> is the actual functional role. In most cases,
3281    the user and the assigning user (from MadeAnnotation) will be the same, but that is
3282    not always the case.
3283    
3284    In addition, the functional role may contain extra data that is stripped, such as
3285    terminating spaces or a comment separated from the rest of the text by a tab.
3286    
3287  This is a static method.  This is a static method.
3288    
3289  =over 4  =over 4
3290    
3291    =item user
3292    
3293    Name of the assigning user.
3294    
3295  =item text  =item text
3296    
3297  Text of the annotation.  Text of the annotation.
# Line 2564  Line 3305 
3305    
3306  =cut  =cut
3307    
3308  sub ParseAssignment {  sub _ParseAssignment {
3309          # Get the parameters.          # Get the parameters.
3310          my ($text) = @_;      my ($user, $text) = @_;
3311          # Declare the return value.          # Declare the return value.
3312          my @retVal = ();          my @retVal = ();
3313          # Check to see if this is a functional assignment.          # Check to see if this is a functional assignment.
3314          my ($user, $type, $function) = split(/\n/, $text);      my ($type, $function) = split(/\n/, $text);
3315          if ($type =~ m/^set $user function to$/i) {      if ($type =~ m/^set function to$/i) {
3316                  # Here it is, so we return the user name and function text.          # Here we have an assignment without a user, so we use the incoming user ID.
3317                  @retVal = ($user, $function);                  @retVal = ($user, $function);
3318        } elsif ($type =~ m/^set (\S+) function to$/i) {
3319            # Here we have an assignment with a user that is passed back to the caller.
3320            @retVal = ($1, $function);
3321        }
3322        # If we have an assignment, we need to clean the function text. There may be
3323        # extra junk at the end added as a note from the user.
3324        if (@retVal) {
3325            $retVal[1] =~ s/(\t\S)?\s*$//;
3326          }          }
3327          # Return the result list.          # Return the result list.
3328          return @retVal;          return @retVal;
# Line 2601  Line 3350 
3350    
3351  sub FriendlyTimestamp {  sub FriendlyTimestamp {
3352      my ($timeValue) = @_;      my ($timeValue) = @_;
3353      my $retVal = strftime("%a %b %e %H:%M:%S %Y", localtime($timeValue));      my $retVal = localtime($timeValue);
3354      return $retVal;      return $retVal;
3355  }  }
3356    
3357    =head3 AddProperty
3358    
3359    C<< my  = $sprout->AddProperty($featureID, $key, $value, $url); >>
3360    
3361    Add a new attribute value (Property) to a feature. In the SEED system, attributes can
3362    be added to almost any object. In Sprout, they can only be added to features. In
3363    Sprout, attributes are implemented using I<properties>. A property represents a key/value
3364    pair. If the particular key/value pair coming in is not already in the database, a new
3365    B<Property> record is created to hold it.
3366    
3367    =over 4
3368    
3369    =item peg
3370    
3371    ID of the feature to which the attribute is to be replied.
3372    
3373    =item key
3374    
3375    Name of the attribute (key).
3376    
3377    =item value
3378    
3379    Value of the attribute.
3380    
3381    =item url
3382    
3383    URL or text citation from which the property was obtained.
3384    
3385    =back
3386    
3387    =cut
3388    #: Return Type ;
3389    sub AddProperty {
3390        # Get the parameters.
3391        my ($self, $featureID, $key, $value, $url) = @_;
3392        # Declare the variable to hold the desired property ID.
3393        my $propID;
3394        # Attempt to find a property record for this key/value pair.
3395        my @properties = $self->GetFlat(['Property'],
3396                                       "Property(property-name) = ? AND Property(property-value) = ?",
3397                                       [$key, $value], 'Property(id)');
3398        if (@properties) {
3399            # Here the property is already in the database. We save its ID.
3400            $propID = $properties[0];
3401            # Here the property value does not exist. We need to generate an ID. It will be set
3402            # to a number one greater than the maximum value in the database. This call to
3403            # GetAll will stop after one record.
3404            my @maxProperty = $self->GetAll(['Property'], "ORDER BY Property(id) DESC", [], ['Property(id)'],
3405                                            1);
3406            $propID = $maxProperty[0]->[0] + 1;
3407            # Insert the new property value.
3408            $self->Insert('Property', { 'property-name' => $key, 'property-value' => $value, id => $propID });
3409        }
3410        # Now we connect the incoming feature to the property.
3411        $self->Insert('HasProperty', { 'from-link' => $featureID, 'to-link' => $propID, evidence => $url });
3412    }
3413    
3414    
3415  1;  1;

Legend:
Removed from v.1.4  
changed lines
  Added in v.1.56

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3