[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 1.21, Fri Sep 9 20:40:41 2005 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 87  Line 86 
86          # 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
87          # the incoming data.          # the incoming data.
88          my $optionTable = Tracer::GetOptions({          my $optionTable = Tracer::GetOptions({
89                                             dbType               => 'mysql',                     # database type                         dbType       => $FIG_Config::dbms,
90                                             dataDir              => 'Data',                      # data file directory                                                          # database type
91                                             xmlFileName  => 'SproutDBD.xml', # database definition file name                         dataDir      => $FIG_Config::sproutData,
92                                             userData             => 'root/',                     # user name and password                                                          # data file directory
93                                             port                 => 0,                           # database connection port                         xmlFileName  => "$FIG_Config::sproutData/SproutDBD.xml",
94                                                            # database definition file name
95                           userData     => "$FIG_Config::dbuser/$FIG_Config::dbpass",
96                                                            # user name and password
97                           port         => $FIG_Config::dbport,
98                                                            # database connection port
99                                             maxSegmentLength => 4500,            # maximum feature segment length                                             maxSegmentLength => 4500,            # maximum feature segment length
100                                             maxSequenceLength => 8000,           # maximum contig sequence length                                             maxSequenceLength => 8000,           # maximum contig sequence length
101                                            }, $options);                                            }, $options);
# Line 125  Line 129 
129  =cut  =cut
130  #: Return Type $;  #: Return Type $;
131  sub MaxSegment {  sub MaxSegment {
132          my $self = shift @_;      my ($self) = @_;
133          return $self->{_options}->{maxSegmentLength};          return $self->{_options}->{maxSegmentLength};
134  }  }
135    
# Line 140  Line 144 
144  =cut  =cut
145  #: Return Type $;  #: Return Type $;
146  sub MaxSequence {  sub MaxSequence {
147          my $self = shift @_;      my ($self) = @_;
148          return $self->{_options}->{maxSequenceLength};          return $self->{_options}->{maxSequenceLength};
149  }  }
150    
# Line 233  Line 237 
237    
238  sub Get {  sub Get {
239          # Get the parameters.          # Get the parameters.
240          my $self = shift @_;      my ($self, $objectNames, $filterClause, $parameterList) = @_;
         my ($objectNames, $filterClause, $parameterList) = @_;  
241          # 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
242          # 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
243          # 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 273 
273    
274  sub GetEntity {  sub GetEntity {
275          # Get the parameters.          # Get the parameters.
276          my $self = shift @_;      my ($self, $entityType, $ID) = @_;
277          my ($entityType, $ID) = @_;      # Call the ERDB method.
278          # 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;  
279  }  }
280    
281  =head3 GetEntityValues  =head3 GetEntityValues
# Line 310  Line 308 
308  #: Return Type @;  #: Return Type @;
309  sub GetEntityValues {  sub GetEntityValues {
310          # Get the parameters.          # Get the parameters.
311          my $self = shift @_;      my ($self, $entityType, $ID, $fields) = @_;
312          my ($entityType, $ID, $fields) = @_;      # Call the ERDB method.
313          # 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;  
314  }  }
315    
316  =head3 ShowMetaData  =head3 ShowMetaData
# Line 342  Line 331 
331    
332  sub ShowMetaData {  sub ShowMetaData {
333          # Get the parameters.          # Get the parameters.
334          my $self = shift @_;      my ($self, $fileName) = @_;
         my ($fileName) = @_;  
335          # Compute the file name.          # Compute the file name.
336          my $options = $self->{_options};          my $options = $self->{_options};
337          # Call the show method on the underlying ERDB object.          # Call the show method on the underlying ERDB object.
# Line 383  Line 371 
371  #: Return Type %;  #: Return Type %;
372  sub Load {  sub Load {
373          # Get the parameters.          # Get the parameters.
374          my $self = shift @_;      my ($self, $rebuild) = @_;
         my ($rebuild) = @_;  
375          # Get the database object.          # Get the database object.
376          my $erdb = $self->{_erdb};          my $erdb = $self->{_erdb};
377          # Load the tables from the data directory.          # Load the tables from the data directory.
# Line 424  Line 411 
411  =back  =back
412    
413  =cut  =cut
414  #: Return Type %;  #: Return Type $%;
415  sub LoadUpdate {  sub LoadUpdate {
416          # Get the parameters.          # Get the parameters.
417          my $self = shift @_;      my ($self, $truncateFlag, $tableList) = @_;
         my ($truncateFlag, $tableList) = @_;  
418          # Get the database object.          # Get the database object.
419          my $erdb = $self->{_erdb};          my $erdb = $self->{_erdb};
420          # Declare the return value.          # Declare the return value.
# Line 439  Line 425 
425          # Loop through the incoming table names.          # Loop through the incoming table names.
426          for my $tableName (@{$tableList}) {          for my $tableName (@{$tableList}) {
427                  # Find the table's file.                  # Find the table's file.
428                  my $fileName = "$dataDir/$tableName";          my $fileName = LoadFileName($dataDir, $tableName);
429                  if (! -e $fileName) {          if (! $fileName) {
430                          $fileName = "$fileName.dtx";              Trace("No load file found for $tableName in $dataDir.") if T(0);
431                  }          } else {
432                  # Attempt to load this table.                  # Attempt to load this table.
433                  my $result = $erdb->LoadTable($fileName, $tableName, $truncateFlag);                  my $result = $erdb->LoadTable($fileName, $tableName, $truncateFlag);
434                  # Accumulate the resulting statistics.                  # Accumulate the resulting statistics.
435                  $retVal->Accumulate($result);                  $retVal->Accumulate($result);
436          }          }
437        }
438          # Return the statistics.          # Return the statistics.
439          return $retVal;          return $retVal;
440  }  }
# Line 464  Line 451 
451  #: Return Type ;  #: Return Type ;
452  sub Build {  sub Build {
453          # Get the parameters.          # Get the parameters.
454          my $self = shift @_;      my ($self) = @_;
455          # Create the tables.          # Create the tables.
456          $self->{_erdb}->CreateTables;          $self->{_erdb}->CreateTables;
457  }  }
# Line 479  Line 466 
466  #: Return Type @;  #: Return Type @;
467  sub Genomes {  sub Genomes {
468          # Get the parameters.          # Get the parameters.
469          my $self = shift @_;      my ($self) = @_;
470          # Get all the genomes.          # Get all the genomes.
471          my @retVal = $self->GetFlat(['Genome'], "", [], 'Genome(id)');          my @retVal = $self->GetFlat(['Genome'], "", [], 'Genome(id)');
472          # Return the list of IDs.          # Return the list of IDs.
# Line 509  Line 496 
496  #: Return Type $;  #: Return Type $;
497  sub GenusSpecies {  sub GenusSpecies {
498          # Get the parameters.          # Get the parameters.
499          my $self = shift @_;      my ($self, $genomeID) = @_;
         my ($genomeID) = @_;  
500          # Get the data for the specified genome.          # Get the data for the specified genome.
501          my @values = $self->GetEntityValues('Genome', $genomeID, ['Genome(genus)', 'Genome(species)',          my @values = $self->GetEntityValues('Genome', $genomeID, ['Genome(genus)', 'Genome(species)',
502                                                                                                                            'Genome(unique-characterization)']);                                                                                                                            'Genome(unique-characterization)']);
# Line 546  Line 532 
532  #: Return Type @;  #: Return Type @;
533  sub FeaturesOf {  sub FeaturesOf {
534          # Get the parameters.          # Get the parameters.
535          my $self = shift @_;      my ($self, $genomeID,$ftype) = @_;
         my ($genomeID,$ftype) = @_;  
536          # Get the features we want.          # Get the features we want.
537          my @features;          my @features;
538          if (!$ftype) {          if (!$ftype) {
# Line 591  Line 576 
576  =item RETURN  =item RETURN
577    
578  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
579  context and as a space-delimited string in a scalar context.  context and as a comma-delimited string in a scalar context.
580    
581  =back  =back
582    
# Line 600  Line 585 
585  #: Return Type $;  #: Return Type $;
586  sub FeatureLocation {  sub FeatureLocation {
587          # Get the parameters.          # Get the parameters.
588          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
589          # Create a query for the feature locations.          # Create a query for the feature locations.
590          my $query = $self->Get(['IsLocatedIn'], "IsLocatedIn(from-link) = ? ORDER BY IsLocatedIn(locN)",          my $query = $self->Get(['IsLocatedIn'], "IsLocatedIn(from-link) = ? ORDER BY IsLocatedIn(locN)",
591                                                     [$featureID]);                                                     [$featureID]);
# Line 635  Line 619 
619                  push @retVal, "${contigID}_$beg$dir$len";                  push @retVal, "${contigID}_$beg$dir$len";
620          }          }
621          # Return the list in the format indicated by the context.          # Return the list in the format indicated by the context.
622          return (wantarray ? @retVal : join(' ', @retVal));      return (wantarray ? @retVal : join(',', @retVal));
623  }  }
624    
625  =head3 ParseLocation  =head3 ParseLocation
# Line 661  Line 645 
645  =cut  =cut
646  #: Return Type @;  #: Return Type @;
647  sub ParseLocation {  sub ParseLocation {
648          # Get the parameter.      # Get the parameter. Note that if we're called as an instance method, we ignore
649        # the first parameter.
650        shift if UNIVERSAL::isa($_[0],__PACKAGE__);
651          my ($location) = @_;          my ($location) = @_;
652          # Parse it into segments.          # Parse it into segments.
653          $location =~ /^(.*)_(\d*)([+-_])(\d*)$/;          $location =~ /^(.*)_(\d*)([+-_])(\d*)$/;
# Line 680  Line 666 
666          return ($contigID, $start, $dir, $len);          return ($contigID, $start, $dir, $len);
667  }  }
668    
669    =head3 PointLocation
670    
671    C<< my $found = Sprout::PointLocation($location, $point); >>
672    
673    Return the offset into the specified location of the specified point on the contig. If
674    the specified point is before the location, a negative value will be returned. If it is
675    beyond the location, an undefined value will be returned. It is assumed that the offset
676    is for the location's contig. The location can either be new-style (using a C<+> or C<->
677    and a length) or old-style (using C<_> and start and end positions.
678    
679    =over 4
680    
681    =item location
682    
683    A location specifier (see L</FeatureLocation> for a description).
684    
685    =item point
686    
687    The offset into the contig of the point in which we're interested.
688    
689    =item RETURN
690    
691    Returns the offset inside the specified location of the specified point, a negative
692    number if the point is before the location, or an undefined value if the point is past
693    the location. If the length of the location is 0, this method will B<always> denote
694    that it is outside the location. The offset will always be relative to the left-most
695    position in the location.
696    
697    =back
698    
699    =cut
700    #: Return Type $;
701    sub PointLocation {
702        # Get the parameter. Note that if we're called as an instance method, we ignore
703        # the first parameter.
704        shift if UNIVERSAL::isa($_[0],__PACKAGE__);
705        my ($location, $point) = @_;
706        # Parse out the location elements. Note that this works on both old-style and new-style
707        # locations.
708        my ($contigID, $start, $dir, $len) = ParseLocation($location);
709        # Declare the return variable.
710        my $retVal;
711        # Compute the offset. The computation is dependent on the direction of the location.
712        my $offset = (($dir == '+') ? $point - $start : $point - ($start - $len + 1));
713        # Return the offset if it's valid.
714        if ($offset < $len) {
715            $retVal = $offset;
716        }
717        # Return the offset found.
718        return $retVal;
719    }
720    
721  =head3 DNASeq  =head3 DNASeq
722    
723  C<< my $sequence = $sprout->DNASeq(\@locationList); >>  C<< my $sequence = $sprout->DNASeq(\@locationList); >>
# Line 705  Line 743 
743  #: Return Type $;  #: Return Type $;
744  sub DNASeq {  sub DNASeq {
745          # Get the parameters.          # Get the parameters.
746          my $self = shift @_;      my ($self, $locationList) = @_;
         my ($locationList) = @_;  
747          # Create the return string.          # Create the return string.
748          my $retVal = "";          my $retVal = "";
749          # Loop through the locations.          # Loop through the locations.
# Line 779  Line 816 
816  #: Return Type @;  #: Return Type @;
817  sub AllContigs {  sub AllContigs {
818          # Get the parameters.          # Get the parameters.
819          my $self = shift @_;      my ($self, $genomeID) = @_;
         my ($genomeID) = @_;  
820          # Ask for the genome's Contigs.          # Ask for the genome's Contigs.
821          my @retVal = $self->GetFlat(['HasContig'], "HasContig(from-link) = ?", [$genomeID],          my @retVal = $self->GetFlat(['HasContig'], "HasContig(from-link) = ?", [$genomeID],
822                                                                  'HasContig(to-link)');                                                                  'HasContig(to-link)');
# Line 810  Line 846 
846  #: Return Type $;  #: Return Type $;
847  sub ContigLength {  sub ContigLength {
848          # Get the parameters.          # Get the parameters.
849          my $self = shift @_;      my ($self, $contigID) = @_;
         my ($contigID) = @_;  
850          # Get the contig's last sequence.          # Get the contig's last sequence.
851          my $query = $self->Get(['IsMadeUpOf'],          my $query = $self->Get(['IsMadeUpOf'],
852                  "IsMadeUpOf(from-link) = ? ORDER BY IsMadeUpOf(start-position) DESC",                  "IsMadeUpOf(from-link) = ? ORDER BY IsMadeUpOf(start-position) DESC",
# Line 853  Line 888 
888  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
889  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
890  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
891  the start and stop values.  the start and stop values. The first element (that is, the list of features) is sorted
892    roughly by location.
893    
894  =back  =back
895    
896  =cut  =cut
897  #: Return Type @;  #: Return Type @@;
898  sub GenesInRegion {  sub GenesInRegion {
899          # Get the parameters.          # Get the parameters.
900          my $self = shift @_;      my ($self, $contigID, $start, $stop) = @_;
         my ($contigID, $start, $stop) = @_;  
901          # Get the maximum segment length.          # Get the maximum segment length.
902          my $maximumSegmentLength = $self->MaxSegment;          my $maximumSegmentLength = $self->MaxSegment;
903          # Create a hash to receive the feature list. We use a hash so that we can eliminate          # Create a hash to receive the feature list. We use a hash so that we can eliminate
904          # duplicates easily.      # duplicates easily. The hash key will be the feature ID. The value will be a two-element
905        # containing the minimum and maximum offsets. We will use the offsets to sort the results
906        # when we're building the result set.
907          my %featuresFound = ();          my %featuresFound = ();
908          # Prime the values we'll use for the returned beginning and end.          # Prime the values we'll use for the returned beginning and end.
909          my ($min, $max) = ($self->ContigLength($contigID), 0);      my @initialMinMax = ($self->ContigLength($contigID), 0);
910        my ($min, $max) = @initialMinMax;
911          # 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
912          # 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,
913          # 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 937 
937                                          $found = 1;                                          $found = 1;
938                                  }                                  }
939                          } elsif ($dir eq '-') {                          } elsif ($dir eq '-') {
940                                  $end = $beg - $len;                  # Note we switch things around so that the beginning is to the left of the
941                                  if ($end <= $stop) {                  # ending.
942                    ($beg, $end) = ($beg - $len, $beg);
943                    if ($beg <= $stop) {
944                                          # Denote we found a useful feature.                                          # Denote we found a useful feature.
945                                          $found = 1;                                          $found = 1;
946                                  }                                  }
947                          }                          }
948                          if ($found) {                          if ($found) {
949                                  # 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,
950                                  $featuresFound{$featureID} = 1;                  # get the current entry for the specified feature.
951                                  if ($beg < $min) { $min = $beg; }                  my ($loc1, $loc2) = (exists $featuresFound{$featureID} ? @{$featuresFound{$featureID}} :
952                                  if ($end < $min) { $min = $end; }                                       @initialMinMax);
953                                  if ($beg > $max) { $max = $beg; }                  # Merge the current segment's begin and end into the feature begin and end and the
954                                  if ($end > $max) { $max = $end; }                  # global min and max.
955                    if ($beg < $loc1) {
956                        $loc1 = $beg;
957                        $min = $beg if $beg < $min;
958                    }
959                    if ($end > $loc2) {
960                        $loc2 = $end;
961                        $max = $end if $end > $max;
962                    }
963                    # Store the entry back into the hash table.
964                    $featuresFound{$featureID} = [$loc1, $loc2];
965                          }                          }
966                  }                  }
967          }          }
968          # Compute a list of the IDs for the features found.      # Now we must compute the list of the IDs for the features found. We start with a list
969          my @list = (sort (keys %featuresFound));      # of midpoints / feature ID pairs. (It's not really a midpoint, it's twice the midpoint,
970        # but the result of the sort will be the same.)
971        my @list = map { [$featuresFound{$_}->[0] + $featuresFound{$_}->[1], $_] } keys %featuresFound;
972        # Now we sort by midpoint and yank out the feature IDs.
973        my @retVal = map { $_->[1] } sort { $a->[0] <=> $b->[0] } @list;
974          # Return it along with the min and max.          # Return it along with the min and max.
975          return (\@list, $min, $max);      return (\@retVal, $min, $max);
976  }  }
977    
978  =head3 FType  =head3 FType
# Line 944  Line 998 
998  #: Return Type $;  #: Return Type $;
999  sub FType {  sub FType {
1000          # Get the parameters.          # Get the parameters.
1001          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1002          # Get the specified feature's type.          # Get the specified feature's type.
1003          my ($retVal) = $self->GetEntityValues('Feature', $featureID, ['Feature(feature-type)']);          my ($retVal) = $self->GetEntityValues('Feature', $featureID, ['Feature(feature-type)']);
1004          # Return the result.          # Return the result.
# Line 982  Line 1035 
1035  #: Return Type @%;  #: Return Type @%;
1036  sub FeatureAnnotations {  sub FeatureAnnotations {
1037          # Get the parameters.          # Get the parameters.
1038          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1039          # 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.
1040          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1041                                                     "IsTargetOfAnnotation(from-link) = ?", [$featureID]);                                                     "IsTargetOfAnnotation(from-link) = ?", [$featureID]);
# Line 1012  Line 1064 
1064  C<< my %functions = $sprout->AllFunctionsOf($featureID); >>  C<< my %functions = $sprout->AllFunctionsOf($featureID); >>
1065    
1066  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
1067  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,
1068  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
1069  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,
1070  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.
1071  features only have a small number of annotations.  Finally, if a single user has multiple functional assignments, we will only keep the most
1072    recent one.
1073    
1074  =over 4  =over 4
1075    
# Line 1034  Line 1087 
1087  #: Return Type %;  #: Return Type %;
1088  sub AllFunctionsOf {  sub AllFunctionsOf {
1089          # Get the parameters.          # Get the parameters.
1090          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1091          # Get all of the feature's annotations.          # Get all of the feature's annotations.
1092          my @query = $self->GetFlat(['IsTargetOfAnnotation', 'Annotation'],      my @query = $self->GetAll(['IsTargetOfAnnotation', 'Annotation'],
1093                                                      "IsTargetOfAnnotation(from-link) = ?",                                                      "IsTargetOfAnnotation(from-link) = ?",
1094                                                          [$featureID], 'Annotation(annotation)');                              [$featureID], ['Annotation(time)', 'Annotation(annotation)']);
1095          # Declare the return hash.          # Declare the return hash.
1096          my %retVal;          my %retVal;
1097        # Declare a hash for insuring we only make one assignment per user.
1098        my %timeHash = ();
1099        # Now we sort the assignments by timestamp in reverse.
1100        my @sortedQuery = sort { -($a->[0] <=> $b->[0]) } @query;
1101          # Loop until we run out of annotations.          # Loop until we run out of annotations.
1102          for my $text (@query) {      for my $annotation (@sortedQuery) {
1103            # Get the annotation fields.
1104            my ($timeStamp, $text) = @{$annotation};
1105                  # Check to see if this is a functional assignment.                  # Check to see if this is a functional assignment.
1106                  my ($user, $function) = ParseAssignment($text);          my ($user, $function) = _ParseAssignment($text);
1107                  if ($user) {          if ($user && ! exists $timeHash{$user}) {
1108                          # Here it is, so stuff it in the return hash.              # Here it is a functional assignment and there has been no
1109                # previous assignment for this user, so we stuff it in the
1110                # return hash.
1111                          $retVal{$function} = $user;                          $retVal{$function} = $user;
1112                # Insure we don't assign to this user again.
1113                $timeHash{$user} = 1;
1114                  }                  }
1115          }          }
1116          # Return the hash of assignments found.          # Return the hash of assignments found.
# Line 1063  Line 1125 
1125    
1126  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
1127  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
1128  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
1129  instance, XXXX is the user ID and YYYYY is the functional assignment text. Its worth noting that  L</ParseLocation>. Its worth noting that we cannot filter on the content of the
1130  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
1131  is not a big problem because most features only have a small number of annotations.  most features only have a small number of annotations.
1132    
1133  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
1134  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 1160 
1160  #: Return Type $;  #: Return Type $;
1161  sub FunctionOf {  sub FunctionOf {
1162          # Get the parameters.          # Get the parameters.
1163          my $self = shift @_;      my ($self, $featureID, $userID) = @_;
         my ($featureID, $userID) = @_;  
1164      # Declare the return value.      # Declare the return value.
1165      my $retVal;      my $retVal;
1166      # Determine the ID type.      # Determine the ID type.
# Line 1136  Line 1197 
1197              # Get the annotation text.              # Get the annotation text.
1198              my ($text, $time) = $annotation->Values(['Annotation(annotation)','Annotation(time)']);              my ($text, $time) = $annotation->Values(['Annotation(annotation)','Annotation(time)']);
1199              # Check to see if this is a functional assignment for a trusted user.              # Check to see if this is a functional assignment for a trusted user.
1200              my ($user, $type, $function) = split(/\n/, $text);              my ($user, $function) = _ParseAssignment($text);
1201              if ($type =~ m/^set $user function to$/i) {              if ($user) {
1202                  # Here it is a functional assignment. Check the time and the user                  # Here it is a functional assignment. Check the time and the user
1203                  # name. The time must be recent and the user must be trusted.                  # name. The time must be recent and the user must be trusted.
1204                  if ((exists $trusteeTable{$user}) && ($time > $timeSelected)) {                  if ((exists $trusteeTable{$user}) && ($time > $timeSelected)) {
# Line 1175  Line 1236 
1236    
1237  =item RETURN  =item RETURN
1238    
1239  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
1240  their best hits.  on the target genome.
1241    
1242  =back  =back
1243    
# Line 1184  Line 1245 
1245  #: Return Type %;  #: Return Type %;
1246  sub BBHList {  sub BBHList {
1247          # Get the parameters.          # Get the parameters.
1248          my $self = shift @_;      my ($self, $genomeID, $featureList) = @_;
         my ($genomeID, $featureList) = @_;  
1249          # Create the return structure.          # Create the return structure.
1250          my %retVal = ();          my %retVal = ();
1251          # Loop through the incoming features.          # Loop through the incoming features.
# Line 1205  Line 1265 
1265          return \%retVal;          return \%retVal;
1266  }  }
1267    
1268    =head3 SimList
1269    
1270    C<< my %similarities = $sprout->SimList($featureID, $count); >>
1271    
1272    Return a list of the similarities to the specified feature.
1273    
1274    Sprout does not support real similarities, so this method just returns the bidirectional
1275    best hits.
1276    
1277    =over 4
1278    
1279    =item featureID
1280    
1281    ID of the feature whose similarities are desired.
1282    
1283    =item count
1284    
1285    Maximum number of similar features to be returned, or C<0> to return them all.
1286    
1287    =back
1288    
1289    =cut
1290    #: Return Type %;
1291    sub SimList {
1292        # Get the parameters.
1293        my ($self, $featureID, $count) = @_;
1294        # Ask for the best hits.
1295        my @lists = $self->GetAll(['IsBidirectionalBestHitOf'],
1296                                  "IsBidirectionalBestHitOf(from-link) = ? ORDER BY IsBidirectionalBestHitOf(score) DESC",
1297                                  [$featureID], ['IsBidirectionalBestHitOf(to-link)', 'IsBidirectionalBestHitOf(score)'],
1298                                  $count);
1299        # Create the return value.
1300        my %retVal = ();
1301        for my $tuple (@lists) {
1302            $retVal{$tuple->[0]} = $tuple->[1];
1303        }
1304        # Return the result.
1305        return %retVal;
1306    }
1307    
1308    
1309    
1310    =head3 IsComplete
1311    
1312    C<< my $flag = $sprout->IsComplete($genomeID); >>
1313    
1314    Return TRUE if the specified genome is complete, else FALSE.
1315    
1316    =over 4
1317    
1318    =item genomeID
1319    
1320    ID of the genome whose completeness status is desired.
1321    
1322    =item RETURN
1323    
1324    Returns TRUE if the genome is complete, FALSE if it is incomplete, and C<undef> if it is
1325    not found.
1326    
1327    =back
1328    
1329    =cut
1330    #: Return Type $;
1331    sub IsComplete {
1332        # Get the parameters.
1333        my ($self, $genomeID) = @_;
1334        # Declare the return variable.
1335        my $retVal;
1336        # Get the genome's data.
1337        my $genomeData = $self->GetEntity('Genome', $genomeID);
1338        if ($genomeData) {
1339            # The genome exists, so get the completeness flag.
1340            ($retVal) = $genomeData->Value('complete');
1341        }
1342        # Return the result.
1343        return $retVal;
1344    }
1345    
1346  =head3 FeatureAliases  =head3 FeatureAliases
1347    
1348  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>
# Line 1228  Line 1366 
1366  #: Return Type @;  #: Return Type @;
1367  sub FeatureAliases {  sub FeatureAliases {
1368          # Get the parameters.          # Get the parameters.
1369          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1370          # Get the desired feature's aliases          # Get the desired feature's aliases
1371          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(alias)']);          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(alias)']);
1372          # Return the result.          # Return the result.
# Line 1259  Line 1396 
1396  #: Return Type $;  #: Return Type $;
1397  sub GenomeOf {  sub GenomeOf {
1398          # Get the parameters.          # Get the parameters.
1399          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1400          # Create a query to find the genome associated with the feature.          # Create a query to find the genome associated with the feature.
1401          my $query = $self->Get(['IsLocatedIn', 'HasContig'], "IsLocatedIn(from-link) = ?", [$featureID]);          my $query = $self->Get(['IsLocatedIn', 'HasContig'], "IsLocatedIn(from-link) = ?", [$featureID]);
1402          # Declare the return value.          # Declare the return value.
# Line 1296  Line 1432 
1432  #: Return Type %;  #: Return Type %;
1433  sub CoupledFeatures {  sub CoupledFeatures {
1434          # Get the parameters.          # Get the parameters.
1435          my $self = shift @_;      my ($self, $featureID) = @_;
1436          my ($featureID) = @_;      # Create a query to retrieve the functionally-coupled features.
1437          # Create a query to retrieve the functionally-coupled features. Note that we depend on the      my $query = $self->Get(['ParticipatesInCoupling', 'Coupling'],
1438          # fact that the functional coupling is physically paired. If (A,B) is in the database, then                             "ParticipatesInCoupling(from-link) = ?", [$featureID]);
         # (B,A) will also be found.  
         my $query = $self->Get(['IsClusteredOnChromosomeWith'],  
                                                    "IsClusteredOnChromosomeWith(from-link) = ?", [$featureID]);  
1439          # 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.
1440          my $found = 0;          my $found = 0;
1441          # Create the return hash.          # Create the return hash.
1442          my %retVal = ();          my %retVal = ();
1443          # Retrieve the relationship records and store them in the hash.          # Retrieve the relationship records and store them in the hash.
1444          while (my $clustering = $query->Fetch()) {          while (my $clustering = $query->Fetch()) {
1445                  my ($otherFeatureID, $score) = $clustering->Values(['IsClusteredOnChromosomeWith(to-link)',          # Get the ID and score of the coupling.
1446                                                                      'IsClusteredOnChromosomeWith(score)']);          my ($couplingID, $score) = $clustering->Values(['Coupling(id)',
1447                                                            'Coupling(score)']);
1448            # The coupling ID contains the two feature IDs separated by a space. We use
1449            # this information to find the ID of the other feature.
1450            my ($fid1, $fid2) = split / /, $couplingID;
1451            my $otherFeatureID = ($featureID eq $fid1 ? $fid2 : $fid1);
1452            # Attach the other feature's score to its ID.
1453                  $retVal{$otherFeatureID} = $score;                  $retVal{$otherFeatureID} = $score;
1454                  $found = 1;                  $found = 1;
1455          }          }
# Line 1323  Line 1462 
1462          return %retVal;          return %retVal;
1463  }  }
1464    
1465    =head3 CouplingEvidence
1466    
1467    C<< my @evidence = $sprout->CouplingEvidence($peg1, $peg2); >>
1468    
1469    Return the evidence for a functional coupling.
1470    
1471    A pair of features is considered evidence of a coupling between two other
1472    features if they occur close together on a contig and both are similar to
1473    the coupled features. So, if B<A1> and B<A2> are close together on a contig,
1474    B<B1> and B<B2> are considered evidence for the coupling if (1) B<B1> and
1475    B<B2> are close together, (2) B<B1> is similar to B<A1>, and (3) B<B2> is
1476    similar to B<A2>.
1477    
1478    The score of a coupling is determined by the number of pieces of evidence
1479    that are considered I<representative>. If several evidence items belong to
1480    a group of genomes that are close to each other, only one of those items
1481    is considered representative. The other evidence items are presumed to be
1482    there because of the relationship between the genomes rather than because
1483    the two proteins generated by the features have a related functionality.
1484    
1485    Each evidence item is returned as a three-tuple in the form C<[>I<$peg1a>C<,>
1486    I<$peg2a>C<,> I<$rep>C<]>, where I<$peg1a> is similar to I<$peg1>, I<$peg2a>
1487    is similar to I<$peg2>, and I<$rep> is TRUE if the evidence is representative
1488    and FALSE otherwise.
1489    
1490    =over 4
1491    
1492    =item peg1
1493    
1494    ID of the feature of interest.
1495    
1496    =item peg2
1497    
1498    ID of a feature functionally coupled to the feature of interest.
1499    
1500    =item RETURN
1501    
1502    Returns a list of 3-tuples. Each tuple consists of a feature similar to the feature
1503    of interest, a feature similar to the functionally coupled feature, and a flag
1504    that is TRUE for a representative piece of evidence and FALSE otherwise.
1505    
1506    =back
1507    
1508    =cut
1509    #: Return Type @@;
1510    sub CouplingEvidence {
1511        # Get the parameters.
1512        my ($self, $peg1, $peg2) = @_;
1513        # Declare the return variable.
1514        my @retVal = ();
1515        # Our first task is to find out the nature of the coupling: whether or not
1516        # it exists, its score, and whether the features are stored in the same
1517        # order as the ones coming in.
1518        my ($couplingID, $inverted, $score) = $self->GetCoupling($peg1, $peg2);
1519        # Only proceed if a coupling exists.
1520        if ($couplingID) {
1521            # Determine the ordering to place on the evidence items. If we're
1522            # inverted, we want to see feature 2 before feature 1 (descending); otherwise,
1523            # we want feature 1 before feature 2 (normal).
1524            Trace("Coupling evidence for ($peg1, $peg2) with inversion flag $inverted.") if T(Coupling => 4);
1525            my $ordering = ($inverted ? "DESC" : "");
1526            # Get the coupling evidence.
1527            my @evidenceList = $self->GetAll(['IsEvidencedBy', 'PCH', 'UsesAsEvidence'],
1528                                              "IsEvidencedBy(from-link) = ? ORDER BY PCH(id), UsesAsEvidence(pos) $ordering",
1529                                              [$couplingID],
1530                                              ['PCH(used)', 'UsesAsEvidence(to-link)']);
1531            # Loop through the evidence items. Each piece of evidence is represented by two
1532            # positions in the evidence list, one for each feature on the other side of the
1533            # evidence link. If at some point we want to generalize to couplings with
1534            # more than two positions, this section of code will need to be re-done.
1535            while (@evidenceList > 0) {
1536                my $peg1Data = shift @evidenceList;
1537                my $peg2Data = shift @evidenceList;
1538                Trace("Peg 1 is " . $peg1Data->[1] . " and Peg 2 is " . $peg2Data->[1] . ".") if T(Coupling => 4);
1539                push @retVal, [$peg1Data->[1], $peg2Data->[1], $peg1Data->[0]];
1540            }
1541        }
1542        # Return the result.
1543        return @retVal;
1544    }
1545    
1546    =head3 GetCoupling
1547    
1548    C<< my ($couplingID, $inverted, $score) = $sprout->GetCoupling($peg1, $peg2); >>
1549    
1550    Return the coupling (if any) for the specified pair of PEGs. If a coupling
1551    exists, we return the coupling ID along with an indicator of whether the
1552    coupling is stored as C<(>I<$peg1>C<, >I<$peg2>C<)> or C<(>I<$peg2>C<, >I<$peg1>C<)>.
1553    In the second case, we say the coupling is I<inverted>. The importance of an
1554    inverted coupling is that the PEGs in the evidence will appear in reverse order.
1555    
1556    =over 4
1557    
1558    =item peg1
1559    
1560    ID of the feature of interest.
1561    
1562    =item peg2
1563    
1564    ID of the potentially coupled feature.
1565    
1566    =item RETURN
1567    
1568    Returns a three-element list. The first element contains the database ID of
1569    the coupling. The second element is FALSE if the coupling is stored in the
1570    database in the caller specified order and TRUE if it is stored in the
1571    inverted order. The third element is the coupling's score. If the coupling
1572    does not exist, all three list elements will be C<undef>.
1573    
1574    =back
1575    
1576    =cut
1577    #: Return Type $%@;
1578    sub GetCoupling {
1579        # Get the parameters.
1580        my ($self, $peg1, $peg2) = @_;
1581        # Declare the return values. We'll start with the coupling ID and undefine the
1582        # flag and score until we have more information.
1583        my ($retVal, $inverted, $score) = (CouplingID($peg1, $peg2), undef, undef);
1584        # Find the coupling data.
1585        my @pegs = $self->GetAll(['Coupling', 'ParticipatesInCoupling'],
1586                                     "Coupling(id) = ? ORDER BY ParticipatesInCoupling(pos)",
1587                                     [$retVal], ["ParticipatesInCoupling(from-link)", "Coupling(score)"]);
1588        # Check to see if we found anything.
1589        if (!@pegs) {
1590            # No coupling, so undefine the return value.
1591            $retVal = undef;
1592        } else {
1593            # We have a coupling! Get the score and check for inversion.
1594            $score = $pegs[0]->[1];
1595            $inverted = ($pegs[0]->[0] eq $peg1);
1596        }
1597        # Return the result.
1598        return ($retVal, $inverted, $score);
1599    }
1600    
1601    =head3 CouplingID
1602    
1603    C<< my $couplingID = Sprout::CouplingID($peg1, $peg2); >>
1604    
1605    Return the coupling ID for a pair of feature IDs.
1606    
1607    The coupling ID is currently computed by joining the feature IDs in
1608    sorted order with a space. Client modules (that is, modules which
1609    use Sprout) should not, however, count on this always being the
1610    case. This method provides a way for abstracting the concept of a
1611    coupling ID. All that we know for sure about it is that it can be
1612    generated easily from the feature IDs and the order of the IDs
1613    in the parameter list does not matter (i.e. C<CouplingID("a1", "b1")>
1614    will have the same value as C<CouplingID("b1", "a1")>.
1615    
1616    =over 4
1617    
1618    =item peg1
1619    
1620    First feature of interest.
1621    
1622    =item peg2
1623    
1624    Second feature of interest.
1625    
1626    =item RETURN
1627    
1628    Returns the ID that would be used to represent a functional coupling of
1629    the two specified PEGs.
1630    
1631    =back
1632    
1633    =cut
1634    #: Return Type $;
1635    sub CouplingID {
1636        return join " ", sort @_;
1637    }
1638    
1639  =head3 GetEntityTypes  =head3 GetEntityTypes
1640    
1641  C<< my @entityList = $sprout->GetEntityTypes(); >>  C<< my @entityList = $sprout->GetEntityTypes(); >>
# Line 1333  Line 1646 
1646  #: Return Type @;  #: Return Type @;
1647  sub GetEntityTypes {  sub GetEntityTypes {
1648          # Get the parameters.          # Get the parameters.
1649          my $self = shift @_;      my ($self) = @_;
1650          # Get the underlying database object.          # Get the underlying database object.
1651          my $erdb = $self->{_erdb};          my $erdb = $self->{_erdb};
1652          # Get its entity type list.          # Get its entity type list.
# Line 1384  Line 1697 
1697                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {
1698                          # Here we have a new header. Store the current sequence if we have one.                          # Here we have a new header. Store the current sequence if we have one.
1699                          if ($id) {                          if ($id) {
1700                                  $retVal{$id} = $sequence;                  $retVal{$id} = uc $sequence;
1701                          }                          }
1702                          # Clear the sequence accumulator and save the new ID.                          # Clear the sequence accumulator and save the new ID.
1703                          ($id, $sequence) = ("$prefix$1", "");                          ($id, $sequence) = ("$prefix$1", "");
1704                  } else {                  } else {
1705                          # 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.
1706                          # First, we get the actual data out.              # First, we get the actual data out. Note that we normalize to upper
1707                # case.
1708                          $line =~ /^\s*(.*?)(\s|\n)/;                          $line =~ /^\s*(.*?)(\s|\n)/;
1709                          $sequence .= $1;                          $sequence .= $1;
1710                  }                  }
1711          }          }
1712          # Flush out the last sequence (if any).          # Flush out the last sequence (if any).
1713          if ($sequence) {          if ($sequence) {
1714                  $retVal {$id} = $sequence;          $retVal{$id} = uc $sequence;
1715          }          }
1716        # Close the file.
1717        close FASTAFILE;
1718          # Return the hash constructed from the file.          # Return the hash constructed from the file.
1719          return %retVal;          return %retVal;
1720  }  }
# Line 1409  Line 1725 
1725    
1726  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
1727  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
1728  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,
1729    it will not be changed; otherwise, it will be converted. This method can also be used to
1730    perform the reverse task-- insuring that all the locations are in the old format.
1731    
1732  =over 4  =over 4
1733    
# Line 1436  Line 1754 
1754  #: Return Type @;  #: Return Type @;
1755  sub FormatLocations {  sub FormatLocations {
1756          # Get the parameters.          # Get the parameters.
1757          my $self = shift @_;      my ($self, $prefix, $locations, $oldFormat) = @_;
         my ($prefix, $locations, $oldFormat) = @_;  
1758          # Create the return list.          # Create the return list.
1759          my @retVal = ();          my @retVal = ();
1760          # Check to see if any locations were passed in.          # Check to see if any locations were passed in.
1761          if ($locations eq '') {          if ($locations eq '') {
1762              confess "No locations specified.";          Confess("No locations specified.");
1763          } else {          } else {
1764                  # Loop through the locations, converting them to the new format.                  # Loop through the locations, converting them to the new format.
1765                  for my $location (@{$locations}) {                  for my $location (@{$locations}) {
# Line 1477  Line 1794 
1794    
1795  sub DumpData {  sub DumpData {
1796          # Get the parameters.          # Get the parameters.
1797          my $self = shift @_;      my ($self) = @_;
1798          # Get the data directory name.          # Get the data directory name.
1799          my $outputDirectory = $self->{_options}->{dataDir};          my $outputDirectory = $self->{_options}->{dataDir};
1800          # Dump the relations.          # Dump the relations.
# Line 1493  Line 1810 
1810  =cut  =cut
1811  #: Return Type $;  #: Return Type $;
1812  sub XMLFileName {  sub XMLFileName {
1813          my $self = shift @_;      my ($self) = @_;
1814          return $self->{_xmlName};          return $self->{_xmlName};
1815  }  }
1816    
# Line 1513  Line 1830 
1830  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
1831  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>.
1832    
1833  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'}); >>
1834    
1835  =over 4  =over 4
1836    
# Line 1531  Line 1848 
1848  #: Return Type ;  #: Return Type ;
1849  sub Insert {  sub Insert {
1850          # Get the parameters.          # Get the parameters.
1851          my $self = shift @_;      my ($self, $objectType, $fieldHash) = @_;
         my ($objectType, $fieldHash) = @_;  
1852          # Call the underlying method.          # Call the underlying method.
1853          $self->{_erdb}->InsertObject($objectType, $fieldHash);          $self->{_erdb}->InsertObject($objectType, $fieldHash);
1854  }  }
# Line 1573  Line 1889 
1889  #: Return Type $;  #: Return Type $;
1890  sub Annotate {  sub Annotate {
1891          # Get the parameters.          # Get the parameters.
1892          my $self = shift @_;      my ($self, $fid, $timestamp, $user, $text) = @_;
         my ($fid, $timestamp, $user, $text) = @_;  
1893          # Create the annotation ID.          # Create the annotation ID.
1894          my $aid = "$fid:$timestamp";          my $aid = "$fid:$timestamp";
1895          # Insert the Annotation object.          # Insert the Annotation object.
# Line 1594  Line 1909 
1909    
1910  =head3 AssignFunction  =head3 AssignFunction
1911    
1912  C<< my $ok = $sprout->AssignFunction($featureID, $user, $function); >>  C<< my $ok = $sprout->AssignFunction($featureID, $user, $function, $assigningUser); >>
1913    
1914  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
1915  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.  
1916    
1917  =over 4  =over 4
1918    
# Line 1608  Line 1922 
1922    
1923  =item user  =item user
1924    
1925  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>.
1926    
1927  =item function  =item function
1928    
1929  Text of the function being assigned.  Text of the function being assigned.
1930    
1931    =item assigningUser (optional)
1932    
1933    Name of the individual user making the assignment. If omitted, defaults to the user group.
1934    
1935  =item RETURN  =item RETURN
1936    
1937  Returns 1 if successful, 0 if an error occurred.  Returns 1 if successful, 0 if an error occurred.
# Line 1624  Line 1942 
1942  #: Return Type $;  #: Return Type $;
1943  sub AssignFunction {  sub AssignFunction {
1944          # Get the parameters.          # Get the parameters.
1945          my $self = shift @_;      my ($self, $featureID, $user, $function, $assigningUser) = @_;
1946          my ($featureID, $user, $function) = @_;      # Default the assigning user.
1947        if (! $assigningUser) {
1948            $assigningUser = $user;
1949        }
1950          # Create an annotation string from the parameters.          # Create an annotation string from the parameters.
1951          my $annotationText = "$user\nset $user function to\n$function";      my $annotationText = "$assigningUser\nset $user function to\n$function";
1952          # Get the current time.          # Get the current time.
1953          my $now = time;          my $now = time;
1954          # Declare the return variable.          # Declare the return variable.
# Line 1672  Line 1993 
1993  #: Return Type @;  #: Return Type @;
1994  sub FeaturesByAlias {  sub FeaturesByAlias {
1995          # Get the parameters.          # Get the parameters.
1996          my $self = shift @_;      my ($self, $alias) = @_;
         my ($alias) = @_;  
1997          # Declare the return variable.          # Declare the return variable.
1998          my @retVal = ();          my @retVal = ();
1999          # Parse the alias.          # Parse the alias.
# Line 1715  Line 2035 
2035  #: Return Type $;  #: Return Type $;
2036  sub Exists {  sub Exists {
2037          # Get the parameters.          # Get the parameters.
2038          my $self = shift @_;      my ($self, $entityName, $entityID) = @_;
         my ($entityName, $entityID) = @_;  
2039          # Check for the entity instance.          # Check for the entity instance.
2040          my $testInstance = $self->GetEntity($entityName, $entityID);          my $testInstance = $self->GetEntity($entityName, $entityID);
2041          # Return an existence indicator.          # Return an existence indicator.
# Line 1746  Line 2065 
2065  #: Return Type $;  #: Return Type $;
2066  sub FeatureTranslation {  sub FeatureTranslation {
2067          # Get the parameters.          # Get the parameters.
2068          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
2069          # Get the specified feature's translation.          # Get the specified feature's translation.
2070          my ($retVal) = $self->GetEntityValues("Feature", $featureID, ['Feature(translation)']);          my ($retVal) = $self->GetEntityValues("Feature", $featureID, ['Feature(translation)']);
2071          return $retVal;          return $retVal;
# Line 1779  Line 2097 
2097  #: Return Type @;  #: Return Type @;
2098  sub Taxonomy {  sub Taxonomy {
2099          # Get the parameters.          # Get the parameters.
2100          my $self = shift @_;      my ($self, $genome) = @_;
         my ($genome) = @_;  
2101          # Find the specified genome's taxonomy string.          # Find the specified genome's taxonomy string.
2102          my ($list) = $self->GetEntityValues('Genome', $genome, ['Genome(taxonomy)']);          my ($list) = $self->GetEntityValues('Genome', $genome, ['Genome(taxonomy)']);
2103          # Declare the return variable.          # Declare the return variable.
# Line 1823  Line 2140 
2140  #: Return Type $;  #: Return Type $;
2141  sub CrudeDistance {  sub CrudeDistance {
2142          # Get the parameters.          # Get the parameters.
2143          my $self = shift @_;      my ($self, $genome1, $genome2) = @_;
         my ($genome1, $genome2) = @_;  
2144          # Insure that the distance is commutative by sorting the genome IDs.          # Insure that the distance is commutative by sorting the genome IDs.
2145          my ($genomeA, $genomeB);          my ($genomeA, $genomeB);
2146          if ($genome2 < $genome2) {          if ($genome2 < $genome2) {
# Line 1871  Line 2187 
2187  #: Return Type $;  #: Return Type $;
2188  sub RoleName {  sub RoleName {
2189          # Get the parameters.          # Get the parameters.
2190          my $self = shift @_;      my ($self, $roleID) = @_;
         my ($roleID) = @_;  
2191          # Get the specified role's name.          # Get the specified role's name.
2192          my ($retVal) = $self->GetEntityValues('Role', $roleID, ['Role(name)']);          my ($retVal) = $self->GetEntityValues('Role', $roleID, ['Role(name)']);
2193          # Use the ID if the role has no name.          # Use the ID if the role has no name.
# Line 1905  Line 2220 
2220  #: Return Type @;  #: Return Type @;
2221  sub RoleDiagrams {  sub RoleDiagrams {
2222          # Get the parameters.          # Get the parameters.
2223          my $self = shift @_;      my ($self, $roleID) = @_;
         my ($roleID) = @_;  
2224          # Query for the diagrams.          # Query for the diagrams.
2225          my @retVal = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],          my @retVal = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],
2226                                                                  'RoleOccursIn(to-link)');                                                                  'RoleOccursIn(to-link)');
# Line 1914  Line 2228 
2228          return @retVal;          return @retVal;
2229  }  }
2230    
2231    =head3 GetProperties
2232    
2233    C<< my @list = $sprout->GetProperties($fid, $key, $value, $url); >>
2234    
2235    Return a list of the properties with the specified characteristics.
2236    
2237    Properties are arbitrary key-value pairs associated with a feature. (At some point they
2238    will also be associated with genomes.) A property value is represented by a 4-tuple of
2239    the form B<($fid, $key, $value, $url)>. These exactly correspond to the parameter
2240    
2241    =over 4
2242    
2243    =item fid
2244    
2245    ID of the feature possessing the property.
2246    
2247    =item key
2248    
2249    Name or key of the property.
2250    
2251    =item value
2252    
2253    Value of the property.
2254    
2255    =item url
2256    
2257    URL of the document that indicated the property should have this particular value, or an
2258    empty string if no such document exists.
2259    
2260    =back
2261    
2262    The parameters act as a filter for the desired data. Any non-null parameter will
2263    automatically match all the tuples returned. So, specifying just the I<$fid> will
2264    return all the properties of the specified feature; similarly, specifying the I<$key>
2265    and I<$value> parameters will return all the features having the specified property
2266    value.
2267    
2268    A single property key can have many values, representing different ideas about the
2269    feature in question. For example, one paper may declare that a feature C<fig|83333.1.peg.10> is
2270    virulent, and another may declare that it is not virulent. A query about the virulence of
2271    C<fig|83333.1.peg.10> would be coded as
2272    
2273        my @list = $sprout->GetProperties('fig|83333.1.peg.10', 'virulence', '', '');
2274    
2275    Here the I<$value> and I<$url> fields are left blank, indicating that those fields are
2276    not to be filtered. The tuples returned would be
2277    
2278        ('fig|83333.1.peg.10', 'virulence', 'yes', 'http://www.somewhere.edu/first.paper.pdf')
2279        ('fig|83333.1.peg.10', 'virulence', 'no', 'http://www.somewhere.edu/second.paper.pdf')
2280    
2281    =cut
2282    #: Return Type @@;
2283    sub GetProperties {
2284        # Get the parameters.
2285        my ($self, @parms) = @_;
2286        # Declare the return variable.
2287        my @retVal = ();
2288        # Now we need to create a WHERE clause that will get us the data we want. First,
2289        # we create a list of the columns containing the data for each parameter.
2290        my @colNames = ('HasProperty(from-link)', 'Property(property-name)',
2291                        'Property(property-value)', 'HasProperty(evidence)');
2292        # Now we build the WHERE clause and the list of parameter values.
2293        my @where = ();
2294        my @values = ();
2295        for (my $i = 0; $i <= $#colNames; $i++) {
2296            my $parm = $parms[$i];
2297            if (defined $parm && ($parm ne '')) {
2298                push @where, "$colNames[$i] = ?";
2299                push @values, $parm;
2300            }
2301        }
2302        # Format the WHERE clause.
2303        my $filter = (@values > 0 ? (join " AND ", @where) : undef);
2304        # Ask for all the propertie values with the desired characteristics.
2305        my $query = $self->Get(['HasProperty', 'Property'], $filter, \@values);
2306        while (my $valueObject = $query->Fetch()) {
2307            my @tuple = $valueObject->Values(\@colNames);
2308            push @retVal, \@tuple;
2309        }
2310        # Return the result.
2311        return @retVal;
2312    }
2313    
2314  =head3 FeatureProperties  =head3 FeatureProperties
2315    
2316  C<< my @properties = $sprout->FeatureProperties($featureID); >>  C<< my @properties = $sprout->FeatureProperties($featureID); >>
# Line 1943  Line 2340 
2340  #: Return Type @@;  #: Return Type @@;
2341  sub FeatureProperties {  sub FeatureProperties {
2342          # Get the parameters.          # Get the parameters.
2343          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
2344          # Get the properties.          # Get the properties.
2345          my @retVal = $self->GetAll(['HasProperty', 'Property'], "HasProperty(from-link) = ?", [$featureID],          my @retVal = $self->GetAll(['HasProperty', 'Property'], "HasProperty(from-link) = ?", [$featureID],
2346                                                          ['Property(property-name)', 'Property(property-value)',                                                          ['Property(property-name)', 'Property(property-value)',
# Line 1975  Line 2371 
2371  #: Return Type $;  #: Return Type $;
2372  sub DiagramName {  sub DiagramName {
2373          # Get the parameters.          # Get the parameters.
2374          my $self = shift @_;      my ($self, $diagramID) = @_;
         my ($diagramID) = @_;  
2375          # Get the specified diagram's name and return it.          # Get the specified diagram's name and return it.
2376          my ($retVal) = $self->GetEntityValues('Diagram', $diagramID, ['Diagram(name)']);          my ($retVal) = $self->GetEntityValues('Diagram', $diagramID, ['Diagram(name)']);
2377          return $retVal;          return $retVal;
# Line 2008  Line 2403 
2403  #: Return Type @;  #: Return Type @;
2404  sub MergedAnnotations {  sub MergedAnnotations {
2405          # Get the parameters.          # Get the parameters.
2406          my $self = shift @_;      my ($self, $list) = @_;
         my ($list) = @_;  
2407          # Create a list to hold the annotation tuples found.          # Create a list to hold the annotation tuples found.
2408          my @tuples = ();          my @tuples = ();
2409          # Loop through the features in the input list.          # Loop through the features in the input list.
# Line 2057  Line 2451 
2451  #: Return Type @;  #: Return Type @;
2452  sub RoleNeighbors {  sub RoleNeighbors {
2453          # Get the parameters.          # Get the parameters.
2454          my $self = shift @_;      my ($self, $roleID) = @_;
         my ($roleID) = @_;  
2455          # Get all the diagrams containing this role.          # Get all the diagrams containing this role.
2456          my @diagrams = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],          my @diagrams = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],
2457                                                                    'RoleOccursIn(to-link)');                                                                    'RoleOccursIn(to-link)');
# Line 2100  Line 2493 
2493  #: Return Type @;  #: Return Type @;
2494  sub FeatureLinks {  sub FeatureLinks {
2495          # Get the parameters.          # Get the parameters.
2496          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
2497          # Get the feature's links.          # Get the feature's links.
2498          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(link)']);          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(link)']);
2499          # Return the feature's links.          # Return the feature's links.
# Line 2113  Line 2505 
2505  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>
2506    
2507  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
2508  to the role the feature performs.  to the roles the feature performs.
2509    
2510  =over 4  =over 4
2511    
# Line 2123  Line 2515 
2515    
2516  =item RETURN  =item RETURN
2517    
2518  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.
2519    
2520  =back  =back
2521    
2522  =cut  =cut
2523  #: Return Type %;  #: Return Type %@;
2524  sub SubsystemsOf {  sub SubsystemsOf {
2525          # Get the parameters.          # Get the parameters.
2526          my $self = shift @_;      my ($self, $featureID) = @_;
2527          my ($featureID) = @_;      # Get the subsystem list.
         # Use the SSCell to connect features to subsystems.  
2528          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],
2529                                                                          "ContainsFeature(to-link) = ?", [$featureID],                                                                          "ContainsFeature(to-link) = ?", [$featureID],
2530                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);
# Line 2141  Line 2532 
2532          my %retVal = ();          my %retVal = ();
2533          # Loop through the results, adding them to the hash.          # Loop through the results, adding them to the hash.
2534          for my $record (@subsystems) {          for my $record (@subsystems) {
2535                  $retVal{$record->[0]} = $record->[1];          my ($subsys, $role) = @{$record};
2536            if (exists $retVal{$subsys}) {
2537                push @{$retVal{$subsys}}, $role;
2538            } else {
2539                $retVal{$subsys} = [$role];
2540            }
2541          }          }
2542          # Return the hash.          # Return the hash.
2543          return %retVal;          return %retVal;
2544  }  }
2545    
2546    =head3 SubsystemList
2547    
2548    C<< my @subsystems = $sprout->SubsystemList($featureID); >>
2549    
2550    Return a list containing the names of the subsystems in which the specified
2551    feature participates. Unlike L</SubsystemsOf>, this method only returns the
2552    subsystem names, not the roles.
2553    
2554    =over 4
2555    
2556    =item featureID
2557    
2558    ID of the feature whose subsystem names are desired.
2559    
2560    =item RETURN
2561    
2562    Returns a list of the names of the subsystems in which the feature participates.
2563    
2564    =back
2565    
2566    =cut
2567    #: Return Type @;
2568    sub SubsystemList {
2569        # Get the parameters.
2570        my ($self, $featureID) = @_;
2571        # Get the list of names.
2572        my @retVal = $self->GetFlat(['ContainsFeature', 'HasSSCell'], "ContainsFeature(to-link) = ?",
2573                                    [$featureID], 'HasSSCell(from-link)');
2574        # Return the result.
2575        return @retVal;
2576    }
2577    
2578  =head3 RelatedFeatures  =head3 RelatedFeatures
2579    
2580  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>
# Line 2180  Line 2608 
2608  #: Return Type @;  #: Return Type @;
2609  sub RelatedFeatures {  sub RelatedFeatures {
2610          # Get the parameters.          # Get the parameters.
2611          my $self = shift @_;      my ($self, $featureID, $function, $userID) = @_;
         my ($featureID, $function, $userID) = @_;  
2612          # 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.
2613          my @bbhFeatures = $self->GetFlat(['IsBidirectionalBestHitOf'],          my @bbhFeatures = $self->GetFlat(['IsBidirectionalBestHitOf'],
2614                                                                           "IsBidirectionalBestHitOf(from-link) = ?", [$featureID],                                                                           "IsBidirectionalBestHitOf(from-link) = ?", [$featureID],
# Line 2229  Line 2656 
2656  #: Return Type @;  #: Return Type @;
2657  sub TaxonomySort {  sub TaxonomySort {
2658          # Get the parameters.          # Get the parameters.
2659          my $self = shift @_;      my ($self, $featureIDs) = @_;
         my ($featureIDs) = @_;  
2660          # Create the working hash table.          # Create the working hash table.
2661          my %hashBuffer = ();          my %hashBuffer = ();
2662          # Loop through the features.          # Loop through the features.
# Line 2239  Line 2665 
2665                  my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",                  my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",
2666                                                                                  [$fid], 'Genome(taxonomy)');                                                                                  [$fid], 'Genome(taxonomy)');
2667                  # Add this feature to the hash buffer.                  # Add this feature to the hash buffer.
2668                  if (exists $hashBuffer{$taxonomy}) {          Tracer::AddToListMap(\%hashBuffer, $taxonomy, $fid);
                         push @{$hashBuffer{$taxonomy}}, $fid;  
                 } else {  
                         $hashBuffer{$taxonomy} = [$fid];  
                 }  
2669          }          }
2670          # Sort the keys and get the elements.          # Sort the keys and get the elements.
2671          my @retVal = ();          my @retVal = ();
# Line 2312  Line 2734 
2734  #: Return Type @@;  #: Return Type @@;
2735  sub GetAll {  sub GetAll {
2736          # Get the parameters.          # Get the parameters.
2737          my $self = shift @_;      my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;
2738          my ($objectNames, $filterClause, $parameterList, $fields, $count) = @_;      # Call the ERDB method.
2739          # Create the query.      my @retVal = $self->{_erdb}->GetAll($objectNames, $filterClause, $parameterList,
2740          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++;  
         }  
2741          # Return the resulting list.          # Return the resulting list.
2742          return @retVal;          return @retVal;
2743  }  }
# Line 2374  Line 2782 
2782  #: Return Type @;  #: Return Type @;
2783  sub GetFlat {  sub GetFlat {
2784          # Get the parameters.          # Get the parameters.
2785          my $self = shift @_;      my ($self, $objectNames, $filterClause, $parameterList, $field) = @_;
         my ($objectNames, $filterClause, $parameterList, $field) = @_;  
2786          # Construct the query.          # Construct the query.
2787          my $query = $self->Get($objectNames, $filterClause, $parameterList);          my $query = $self->Get($objectNames, $filterClause, $parameterList);
2788          # Create the result list.          # Create the result list.
# Line 2485  Line 2892 
2892  #: Return Type @;  #: Return Type @;
2893  sub LoadInfo {  sub LoadInfo {
2894          # Get the parameters.          # Get the parameters.
2895          my $self = shift @_;      my ($self) = @_;
2896          # 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.
2897          my @retVal = ($self->{_options}->{dataDir});          my @retVal = ($self->{_options}->{dataDir});
2898          # Concatenate the table names.          # Concatenate the table names.
# Line 2522  Line 2929 
2929  #: Return Type %;  #: Return Type %;
2930  sub LowBBHs {  sub LowBBHs {
2931          # Get the parsameters.          # Get the parsameters.
2932          my $self = shift @_;      my ($self, $featureID, $cutoff) = @_;
         my ($featureID, $cutoff) = @_;  
2933          # Create the return hash.          # Create the return hash.
2934          my %retVal = ();          my %retVal = ();
2935          # Create a query to get the desired BBHs.          # Create a query to get the desired BBHs.
# Line 2539  Line 2945 
2945          return %retVal;          return %retVal;
2946  }  }
2947    
2948    =head3 GetGroups
2949    
2950    C<< my %groups = $sprout->GetGroups(\@groupList); >>
2951    
2952    Return a hash mapping each group to the IDs of the genomes in the group.
2953    A list of groups may be specified, in which case only those groups will be
2954    shown. Alternatively, if no parameter is supplied, all groups will be
2955    included. Genomes that are not in any group are omitted.
2956    
2957    =cut
2958    #: Return Type %@;
2959    sub GetGroups {
2960        # Get the parameters.
2961        my ($self, $groupList) = @_;
2962        # Declare the return value.
2963        my %retVal = ();
2964        # Determine whether we are getting all the groups or just some.
2965        if (defined $groupList) {
2966            # Here we have a group list. Loop through them individually,
2967            # getting a list of the relevant genomes.
2968            for my $group (@{$groupList}) {
2969                my @genomeIDs = $self->GetFlat(['Genome'], "Genome(group-name) = ?",
2970                    [$group], "Genome(id)");
2971                $retVal{$group} = \@genomeIDs;
2972            }
2973        } else {
2974            # Here we need all of the groups. In this case, we run through all
2975            # of the genome records, putting each one found into the appropriate
2976            # group. Note that we use a filter clause to insure that only genomes
2977            # in groups are included in the return set.
2978            my @genomes = $self->GetAll(['Genome'], "Genome(group-name) > ' '", [],
2979                                        ['Genome(id)', 'Genome(group-name)']);
2980            # Loop through the genomes found.
2981            for my $genome (@genomes) {
2982                # Pop this genome's ID off the current list.
2983                my @groups = @{$genome};
2984                my $genomeID = shift @groups;
2985                # Loop through the groups, adding the genome ID to each group's
2986                # list.
2987                for my $group (@groups) {
2988                    Tracer::AddToListMap(\%retVal, $group, $genomeID);
2989                }
2990            }
2991        }
2992        # Return the hash we just built.
2993        return %retVal;
2994    }
2995    
2996    =head3 MyGenomes
2997    
2998    C<< my @genomes = Sprout::MyGenomes($dataDir); >>
2999    
3000    Return a list of the genomes to be included in the Sprout.
3001    
3002    This method is provided for use during the Sprout load. It presumes the Genome load file has
3003    already been created. (It will be in the Sprout data directory and called either C<Genome>
3004    or C<Genome.dtx>.) Essentially, it reads in the Genome load file and strips out the genome
3005    IDs.
3006    
3007    =over 4
3008    
3009    =item dataDir
3010    
3011    Directory containing the Sprout load files.
3012    
3013    =back
3014    
3015    =cut
3016    #: Return Type @;
3017    sub MyGenomes {
3018        # Get the parameters.
3019        my ($dataDir) = @_;
3020        # Compute the genome file name.
3021        my $genomeFileName = LoadFileName($dataDir, "Genome");
3022        # Extract the genome IDs from the files.
3023        my @retVal = map { $_ =~ /^(\S+)/; $1 } Tracer::GetFile($genomeFileName);
3024        # Return the result.
3025        return @retVal;
3026    }
3027    
3028    =head3 LoadFileName
3029    
3030    C<< my $fileName = Sprout::LoadFileName($dataDir, $tableName); >>
3031    
3032    Return the name of the load file for the specified table in the specified data
3033    directory.
3034    
3035    =over 4
3036    
3037    =item dataDir
3038    
3039    Directory containing the Sprout load files.
3040    
3041    =item tableName
3042    
3043    Name of the table whose load file is desired.
3044    
3045    =item RETURN
3046    
3047    Returns the name of the file containing the load data for the specified table, or
3048    C<undef> if no load file is present.
3049    
3050    =back
3051    
3052    =cut
3053    #: Return Type $;
3054    sub LoadFileName {
3055        # Get the parameters.
3056        my ($dataDir, $tableName) = @_;
3057        # Declare the return variable.
3058        my $retVal;
3059        # Check for the various file names.
3060        if (-e "$dataDir/$tableName") {
3061            $retVal = "$dataDir/$tableName";
3062        } elsif (-e "$dataDir/$tableName.dtx") {
3063            $retVal = "$dataDir/$tableName.dtx";
3064        }
3065        # Return the result.
3066        return $retVal;
3067    }
3068    
3069  =head2 Internal Utility Methods  =head2 Internal Utility Methods
3070    
3071  =head3 ParseAssignment  =head3 ParseAssignment
3072    
3073  Parse annotation text to determine whether or not it is a functional assignment. If it is,  Parse annotation text to determine whether or not it is a functional assignment. If it is,
3074  the user and function text will be returned as a 2-element list. If it isn't, an empty list  the user, function text, and assigning user will be returned as a 3-element list. If it
3075  will be returned.  isn't, an empty list will be returned.
3076    
3077    A functional assignment is always of the form
3078    
3079        I<XXXX>C<\nset >I<YYYY>C< function to\n>I<ZZZZZ>
3080    
3081    where I<XXXX> is the B<assigning user>, I<YYYY> is the B<user>, and I<ZZZZ> is the
3082    actual functional role. In most cases, the user and the assigning user will be the
3083    same, but that is not always the case.
3084    
3085  This is a static method.  This is a static method.
3086    
# Line 2564  Line 3099 
3099    
3100  =cut  =cut
3101    
3102  sub ParseAssignment {  sub _ParseAssignment {
3103          # Get the parameters.          # Get the parameters.
3104          my ($text) = @_;          my ($text) = @_;
3105          # Declare the return value.          # Declare the return value.
3106          my @retVal = ();          my @retVal = ();
3107          # Check to see if this is a functional assignment.          # Check to see if this is a functional assignment.
3108          my ($user, $type, $function) = split(/\n/, $text);          my ($user, $type, $function) = split(/\n/, $text);
3109          if ($type =~ m/^set $user function to$/i) {      if ($type =~ m/^set ([^ ]+) function to$/i) {
3110                  # Here it is, so we return the user name and function text.          # Here it is, so we return the user name (which is in $1), the functional role text,
3111                  @retVal = ($user, $function);          # and the assigning user.
3112            @retVal = ($1, $function, $user);
3113          }          }
3114          # Return the result list.          # Return the result list.
3115          return @retVal;          return @retVal;
# Line 2605  Line 3141 
3141      return $retVal;      return $retVal;
3142  }  }
3143    
3144    =head3 AddProperty
3145    
3146    C<< my  = $sprout->AddProperty($featureID, $key, $value, $url); >>
3147    
3148    Add a new attribute value (Property) to a feature. In the SEED system, attributes can
3149    be added to almost any object. In Sprout, they can only be added to features. In
3150    Sprout, attributes are implemented using I<properties>. A property represents a key/value
3151    pair. If the particular key/value pair coming in is not already in the database, a new
3152    B<Property> record is created to hold it.
3153    
3154    =over 4
3155    
3156    =item peg
3157    
3158    ID of the feature to which the attribute is to be replied.
3159    
3160    =item key
3161    
3162    Name of the attribute (key).
3163    
3164    =item value
3165    
3166    Value of the attribute.
3167    
3168    =item url
3169    
3170    URL or text citation from which the property was obtained.
3171    
3172    =back
3173    
3174    =cut
3175    #: Return Type ;
3176    sub AddProperty {
3177        # Get the parameters.
3178        my ($self, $featureID, $key, $value, $url) = @_;
3179        # Declare the variable to hold the desired property ID.
3180        my $propID;
3181        # Attempt to find a property record for this key/value pair.
3182        my @properties = $self->GetFlat(['Property'],
3183                                       "Property(property-name) = ? AND Property(property-value) = ?",
3184                                       [$key, $value], 'Property(id)');
3185        if (@properties) {
3186            # Here the property is already in the database. We save its ID.
3187            $propID = $properties[0];
3188            # Here the property value does not exist. We need to generate an ID. It will be set
3189            # to a number one greater than the maximum value in the database. This call to
3190            # GetAll will stop after one record.
3191            my @maxProperty = $self->GetAll(['Property'], "ORDER BY Property(id) DESC", [], ['Property(id)'],
3192                                            1);
3193            $propID = $maxProperty[0]->[0] + 1;
3194            # Insert the new property value.
3195            $self->Insert('Property', { 'property-name' => $key, 'property-value' => $value, id => $propID });
3196        }
3197        # Now we connect the incoming feature to the property.
3198        $self->Insert('HasProperty', { 'from-link' => $featureID, 'to-link' => $propID, evidence => $url });
3199    }
3200    
3201    
3202    
3203  1;  1;

Legend:
Removed from v.1.4  
changed lines
  Added in v.1.21

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3