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

Diff of /Sprout/SproutLoad.pm

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

revision 1.22, Mon Dec 12 21:48:22 2005 UTC revision 1.40, Thu Jun 8 15:37:32 2006 UTC
# Line 30  Line 30 
30      $stats->Accumulate($spl->LoadFeatureData());      $stats->Accumulate($spl->LoadFeatureData());
31      print $stats->Show();      print $stats->Show();
32    
 This module makes use of the internal Sprout property C<_erdb>.  
   
33  It is worth noting that the FIG object does not need to be a real one. Any object  It is worth noting that the FIG object does not need to be a real one. Any object
34  that implements the FIG methods for data retrieval could be used. So, for example,  that implements the FIG methods for data retrieval could be used. So, for example,
35  this object could be used to copy data from one Sprout database to another, or  this object could be used to copy data from one Sprout database to another, or
# Line 80  Line 78 
78  =item subsysFile  =item subsysFile
79    
80  Either the name of the file containing the list of trusted subsystems or a reference  Either the name of the file containing the list of trusted subsystems or a reference
81  to a list of subsystem names. If nothing is specified, all known subsystems will be  to a list of subsystem names. If nothing is specified, all NMPDR subsystems will be
82  considered trusted. Only subsystem data related to the trusted subsystems is loaded.  considered trusted. (A subsystem is considered NMPDR if it has a file named C<NMPDR>
83    in its data directory.) Only subsystem data related to the trusted subsystems is loaded.
84    
85  =item options  =item options
86    
# Line 94  Line 93 
93  sub new {  sub new {
94      # Get the parameters.      # Get the parameters.
95      my ($class, $sprout, $fig, $genomeFile, $subsysFile, $options) = @_;      my ($class, $sprout, $fig, $genomeFile, $subsysFile, $options) = @_;
96      # Load the list of genomes into a hash.      # Create the genome hash.
97      my %genomes;      my %genomes = ();
98        # We only need it if load-only is NOT specified.
99        if (! $options->{loadOnly}) {
100      if (! defined($genomeFile) || $genomeFile eq '') {      if (! defined($genomeFile) || $genomeFile eq '') {
101          # Here we want all the complete genomes and an access code of 1.          # Here we want all the complete genomes and an access code of 1.
102          my @genomeList = $fig->genomes(1);          my @genomeList = $fig->genomes(1);
# Line 129  Line 130 
130              Confess("Invalid genome parameter ($type) in SproutLoad constructor.");              Confess("Invalid genome parameter ($type) in SproutLoad constructor.");
131          }          }
132      }      }
133        }
134      # Load the list of trusted subsystems.      # Load the list of trusted subsystems.
135      my %subsystems = ();      my %subsystems = ();
136        # We only need it if load-only is NOT specified.
137        if (! $options->{loadOnly}) {
138      if (! defined $subsysFile || $subsysFile eq '') {      if (! defined $subsysFile || $subsysFile eq '') {
139          # Here we want all the subsystems.              # Here we want all the NMPDR subsystems. First we get the whole list.
140          %subsystems = map { $_ => 1 } $fig->all_subsystems();              my @subs = $fig->all_subsystems();
141                # Loop through, checking for the NMPDR file.
142                for my $sub (@subs) {
143                    if (-e "$FIG_Config::data/Subsystems/$sub/NMPDR") {
144                        $subsystems{$sub} = 1;
145                    }
146                }
147      } else {      } else {
148          my $type = ref $subsysFile;          my $type = ref $subsysFile;
149          if ($type eq 'ARRAY') {          if ($type eq 'ARRAY') {
# Line 153  Line 163 
163              Confess("Invalid subsystem parameter in SproutLoad constructor.");              Confess("Invalid subsystem parameter in SproutLoad constructor.");
164          }          }
165      }      }
166        }
167      # Get the data directory from the Sprout object.      # Get the data directory from the Sprout object.
168      my ($directory) = $sprout->LoadInfo();      my ($directory) = $sprout->LoadInfo();
169      # Create the Sprout load object.      # Create the Sprout load object.
# Line 162  Line 173 
173                    subsystems => \%subsystems,                    subsystems => \%subsystems,
174                    sprout => $sprout,                    sprout => $sprout,
175                    loadDirectory => $directory,                    loadDirectory => $directory,
176                    erdb => $sprout->{_erdb},                    erdb => $sprout,
177                    loaders => [],                    loaders => [],
178                    options => $options                    options => $options
179                   };                   };
# Line 171  Line 182 
182      return $retVal;      return $retVal;
183  }  }
184    
185    =head3 LoadOnly
186    
187    C<< my $flag = $spl->LoadOnly; >>
188    
189    Return TRUE if we are in load-only mode, else FALSE.
190    
191    =cut
192    
193    sub LoadOnly {
194        my ($self) = @_;
195        return $self->{options}->{loadOnly};
196    }
197    
198    =head3 PrimaryOnly
199    
200    C<< my $flag = $spl->PrimaryOnly; >>
201    
202    Return TRUE if only the main entity is to be loaded, else FALSE.
203    
204    =cut
205    
206    sub PrimaryOnly {
207        my ($self) = @_;
208        return $self->{options}->{primaryOnly};
209    }
210    
211  =head3 LoadGenomeData  =head3 LoadGenomeData
212    
213  C<< my $stats = $spl->LoadGenomeData(); >>  C<< my $stats = $spl->LoadGenomeData(); >>
# Line 198  Line 235 
235    
236  =back  =back
237    
 B<TO DO>  
   
 Real quality vectors instead of C<unknown> for everything.  
   
 GenomeGroup relation. (The original script took group information from the C<NMPDR> file  
 in each genome's main directory, but no such file exists anywhere in my version of the  
 data store.)  
   
238  =cut  =cut
239  #: Return Type $%;  #: Return Type $%;
240  sub LoadGenomeData {  sub LoadGenomeData {
# Line 216  Line 245 
245      # Get the genome count.      # Get the genome count.
246      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
247      my $genomeCount = (keys %{$genomeHash});      my $genomeCount = (keys %{$genomeHash});
     Trace("Beginning genome data load.") if T(2);  
248      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
249      my $loadGenome = $self->_TableLoader('Genome', $genomeCount);      my $loadGenome = $self->_TableLoader('Genome');
250      my $loadHasContig = $self->_TableLoader('HasContig', $genomeCount * 300);      my $loadHasContig = $self->_TableLoader('HasContig', $self->PrimaryOnly);
251      my $loadContig = $self->_TableLoader('Contig', $genomeCount * 300);      my $loadContig = $self->_TableLoader('Contig', $self->PrimaryOnly);
252      my $loadIsMadeUpOf = $self->_TableLoader('IsMadeUpOf', $genomeCount * 60000);      my $loadIsMadeUpOf = $self->_TableLoader('IsMadeUpOf', $self->PrimaryOnly);
253      my $loadSequence = $self->_TableLoader('Sequence', $genomeCount * 60000);      my $loadSequence = $self->_TableLoader('Sequence', $self->PrimaryOnly);
254        if ($self->{options}->{loadOnly}) {
255            Trace("Loading from existing files.") if T(2);
256        } else {
257            Trace("Generating genome data.") if T(2);
258      # Now we loop through the genomes, generating the data for each one.      # Now we loop through the genomes, generating the data for each one.
259      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
260          Trace("Loading data for genome $genomeID.") if T(3);              Trace("Generating data for genome $genomeID.") if T(3);
261          $loadGenome->Add("genomeIn");          $loadGenome->Add("genomeIn");
262          # The access code comes in via the genome hash.          # The access code comes in via the genome hash.
263          my $accessCode = $genomeHash->{$genomeID};          my $accessCode = $genomeHash->{$genomeID};
264          # Get the genus, species, and strain from the scientific name. Note that we append              # Get the genus, species, and strain from the scientific name.
         # the genome ID to the strain. In some cases this is the totality of the strain name.  
265          my ($genus, $species, @extraData) = split / /, $self->{fig}->genus_species($genomeID);          my ($genus, $species, @extraData) = split / /, $self->{fig}->genus_species($genomeID);
266          my $extra = join " ", @extraData, "[$genomeID]";              my $extra = join " ", @extraData;
267          # Get the full taxonomy.          # Get the full taxonomy.
268          my $taxonomy = $fig->taxonomy_of($genomeID);          my $taxonomy = $fig->taxonomy_of($genomeID);
269          # Output the genome record.          # Output the genome record.
# Line 268  Line 299 
299              }              }
300          }          }
301      }      }
302        }
303      # Finish the loads.      # Finish the loads.
304      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
305      # Return the result.      # Return the result.
# Line 311  Line 343 
343      my $genomeCount = (keys %{$genomeFilter});      my $genomeCount = (keys %{$genomeFilter});
344      my $featureCount = $genomeCount * 4000;      my $featureCount = $genomeCount * 4000;
345      # Start the loads.      # Start the loads.
346      my $loadCoupling = $self->_TableLoader('Coupling', $featureCount * $genomeCount);      my $loadCoupling = $self->_TableLoader('Coupling');
347      my $loadIsEvidencedBy = $self->_TableLoader('IsEvidencedBy', $featureCount * 8000);      my $loadIsEvidencedBy = $self->_TableLoader('IsEvidencedBy', $self->PrimaryOnly);
348      my $loadPCH = $self->_TableLoader('PCH', $featureCount * 2000);      my $loadPCH = $self->_TableLoader('PCH', $self->PrimaryOnly);
349      my $loadParticipatesInCoupling = $self->_TableLoader('ParticipatesInCoupling', $featureCount * 2000);      my $loadParticipatesInCoupling = $self->_TableLoader('ParticipatesInCoupling', $self->PrimaryOnly);
350      my $loadUsesAsEvidence = $self->_TableLoader('UsesAsEvidence', $featureCount * 8000);      my $loadUsesAsEvidence = $self->_TableLoader('UsesAsEvidence', $self->PrimaryOnly);
351      Trace("Beginning coupling data load.") if T(2);      if ($self->{options}->{loadOnly}) {
352            Trace("Loading from existing files.") if T(2);
353        } else {
354            Trace("Generating coupling data.") if T(2);
355      # Loop through the genomes found.      # Loop through the genomes found.
356      for my $genome (sort keys %{$genomeFilter}) {      for my $genome (sort keys %{$genomeFilter}) {
357          Trace("Generating coupling data for $genome.") if T(3);          Trace("Generating coupling data for $genome.") if T(3);
# Line 389  Line 424 
424              }              }
425          }          }
426      }      }
427        }
428      # All done. Finish the load.      # All done. Finish the load.
429      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
430      return $retVal;      return $retVal;
# Line 410  Line 446 
446      FeatureTranslation      FeatureTranslation
447      FeatureUpstream      FeatureUpstream
448      IsLocatedIn      IsLocatedIn
449        HasFeature
450    
451  =over 4  =over 4
452    
# Line 426  Line 463 
463      my ($self) = @_;      my ($self) = @_;
464      # Get the FIG object.      # Get the FIG object.
465      my $fig = $self->{fig};      my $fig = $self->{fig};
     # Find out if this is a limited run.  
     my $limited = $self->{options}->{limitedFeatures};  
466      # Get the table of genome IDs.      # Get the table of genome IDs.
467      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
     my $featureCount = $genomeCount * 4000;  
468      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
469      my $loadFeature = $self->_TableLoader('Feature', $featureCount);      my $loadFeature = $self->_TableLoader('Feature');
470      my $loadIsLocatedIn = $self->_TableLoader('IsLocatedIn', $featureCount);      my $loadIsLocatedIn = $self->_TableLoader('IsLocatedIn', $self->PrimaryOnly);
471      my $loadFeatureAlias = $self->_TableLoader('FeatureAlias', $featureCount * 6);      my $loadFeatureAlias = $self->_TableLoader('FeatureAlias');
472      my ($loadFeatureLink, $loadFeatureTranslation, $loadFeatureUpstream);      my $loadFeatureLink = $self->_TableLoader('FeatureLink');
473      if (! $limited) {      my $loadFeatureTranslation = $self->_TableLoader('FeatureTranslation');
474          $loadFeatureLink = $self->_TableLoader('FeatureLink', $featureCount * 10);      my $loadFeatureUpstream = $self->_TableLoader('FeatureUpstream');
475          $loadFeatureTranslation = $self->_TableLoader('FeatureTranslation', $featureCount);      my $loadHasFeature = $self->_TableLoader('HasFeature');
         $loadFeatureUpstream = $self->_TableLoader('FeatureUpstream', $featureCount);  
     }  
476      # Get the maximum sequence size. We need this later for splitting up the      # Get the maximum sequence size. We need this later for splitting up the
477      # locations.      # locations.
478      my $chunkSize = $self->{sprout}->MaxSegment();      my $chunkSize = $self->{sprout}->MaxSegment();
479      Trace("Beginning feature data load.") if T(2);      if ($self->{options}->{loadOnly}) {
480            Trace("Loading from existing files.") if T(2);
481        } else {
482            Trace("Generating feature data.") if T(2);
483      # Now we loop through the genomes, generating the data for each one.      # Now we loop through the genomes, generating the data for each one.
484      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
485          Trace("Loading features for genome $genomeID.") if T(3);          Trace("Loading features for genome $genomeID.") if T(3);
# Line 459  Line 493 
493              my ($featureID, $locations, undef, $type) = @{$featureData};              my ($featureID, $locations, undef, $type) = @{$featureData};
494              # Create the feature record.              # Create the feature record.
495              $loadFeature->Put($featureID, 1, $type);              $loadFeature->Put($featureID, 1, $type);
496                    # Link it to the parent genome.
497                    $loadHasFeature->Put($genomeID, $featureID, $type);
498              # Create the aliases.              # Create the aliases.
499              for my $alias ($fig->feature_aliases($featureID)) {              for my $alias ($fig->feature_aliases($featureID)) {
500                  $loadFeatureAlias->Put($featureID, $alias);                  $loadFeatureAlias->Put($featureID, $alias);
501              }              }
             # The next stuff is for a full load only.  
             if (! $limited) {  
502                  # Get the links.                  # Get the links.
503                  my @links = $fig->fid_links($featureID);                  my @links = $fig->fid_links($featureID);
504                  for my $link (@links) {                  for my $link (@links) {
# Line 483  Line 517 
517                          $loadFeatureUpstream->Put($featureID, $upstream);                          $loadFeatureUpstream->Put($featureID, $upstream);
518                      }                      }
519                  }                  }
             }  
520              # This part is the roughest. We need to relate the features to contig              # This part is the roughest. We need to relate the features to contig
521              # locations, and the locations must be split so that none of them exceed              # locations, and the locations must be split so that none of them exceed
522              # the maximum segment size. This simplifies the genes_in_region processing              # the maximum segment size. This simplifies the genes_in_region processing
# Line 512  Line 545 
545              }              }
546          }          }
547      }      }
548        }
549      # Finish the loads.      # Finish the loads.
550      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
551      return $retVal;      return $retVal;
# Line 548  Line 582 
582      my $fig = $self->{fig};      my $fig = $self->{fig};
583      # Get the table of genome IDs.      # Get the table of genome IDs.
584      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
     my $featureCount = $genomeCount * 4000;  
585      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
586      my $loadIsBidirectionalBestHitOf = $self->_TableLoader('IsBidirectionalBestHitOf',      my $loadIsBidirectionalBestHitOf = $self->_TableLoader('IsBidirectionalBestHitOf');
587                                                             $featureCount * $genomeCount);      if ($self->{options}->{loadOnly}) {
588      Trace("Beginning BBH load.") if T(2);          Trace("Loading from existing files.") if T(2);
589        } else {
590            Trace("Generating BBH data.") if T(2);
591      # Now we loop through the genomes, generating the data for each one.      # Now we loop through the genomes, generating the data for each one.
592      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
593          $loadIsBidirectionalBestHitOf->Add("genomeIn");          $loadIsBidirectionalBestHitOf->Add("genomeIn");
# Line 579  Line 613 
613              }              }
614          }          }
615      }      }
616        }
617      # Finish the loads.      # Finish the loads.
618      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
619      return $retVal;      return $retVal;
# Line 639  Line 674 
674      # Get the subsystem hash. This lists the subsystems we'll process.      # Get the subsystem hash. This lists the subsystems we'll process.
675      my $subsysHash = $self->{subsystems};      my $subsysHash = $self->{subsystems};
676      my @subsysIDs = sort keys %{$subsysHash};      my @subsysIDs = sort keys %{$subsysHash};
     my $subsysCount = @subsysIDs;  
     my $genomeCount = (keys %{$genomeHash});  
     my $featureCount = $genomeCount * 4000;  
677      # Get the map list.      # Get the map list.
678      my @maps = $fig->all_maps;      my @maps = $fig->all_maps;
     my $mapCount = @maps;  
679      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
680      my $loadDiagram = $self->_TableLoader('Diagram', $mapCount);      my $loadDiagram = $self->_TableLoader('Diagram', $self->PrimaryOnly);
681      my $loadRoleOccursIn = $self->_TableLoader('RoleOccursIn', $featureCount * 6);      my $loadRoleOccursIn = $self->_TableLoader('RoleOccursIn', $self->PrimaryOnly);
682      my $loadSubsystem = $self->_TableLoader('Subsystem', $subsysCount);      my $loadSubsystem = $self->_TableLoader('Subsystem');
683      my $loadRole = $self->_TableLoader('Role', $featureCount * 6);      my $loadRole = $self->_TableLoader('Role', $self->PrimaryOnly);
684      my $loadRoleEC = $self->_TableLoader('RoleEC', $featureCount * 6);      my $loadRoleEC = $self->_TableLoader('RoleEC', $self->PrimaryOnly);
685      my $loadCatalyzes = $self->_TableLoader('Catalyzes', $genomeCount * $featureCount);      my $loadCatalyzes = $self->_TableLoader('Catalyzes', $self->PrimaryOnly);
686      my $loadSSCell = $self->_TableLoader('SSCell', $featureCount * $genomeCount);      my $loadSSCell = $self->_TableLoader('SSCell', $self->PrimaryOnly);
687      my $loadContainsFeature = $self->_TableLoader('ContainsFeature', $featureCount * $subsysCount);      my $loadContainsFeature = $self->_TableLoader('ContainsFeature', $self->PrimaryOnly);
688      my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf', $featureCount * $genomeCount);      my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf', $self->PrimaryOnly);
689      my $loadIsRoleOf = $self->_TableLoader('IsRoleOf', $featureCount * $genomeCount);      my $loadIsRoleOf = $self->_TableLoader('IsRoleOf', $self->PrimaryOnly);
690      my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem', $featureCount * 6);      my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem', $self->PrimaryOnly);
691      my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn', $subsysCount * $genomeCount);      my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn', $self->PrimaryOnly);
692      my $loadHasSSCell = $self->_TableLoader('HasSSCell', $featureCount * $genomeCount);      my $loadHasSSCell = $self->_TableLoader('HasSSCell', $self->PrimaryOnly);
693      my $loadRoleSubset = $self->_TableLoader('RoleSubset', $subsysCount * 50);      my $loadRoleSubset = $self->_TableLoader('RoleSubset', $self->PrimaryOnly);
694      my $loadGenomeSubset = $self->_TableLoader('GenomeSubset', $subsysCount * 50);      my $loadGenomeSubset = $self->_TableLoader('GenomeSubset', $self->PrimaryOnly);
695      my $loadConsistsOfRoles = $self->_TableLoader('ConsistsOfRoles', $featureCount * $genomeCount);      my $loadConsistsOfRoles = $self->_TableLoader('ConsistsOfRoles', $self->PrimaryOnly);
696      my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes', $featureCount * $genomeCount);      my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes', $self->PrimaryOnly);
697      my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset', $subsysCount * 50);      my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset', $self->PrimaryOnly);
698      my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset', $subsysCount * 50);      my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset', $self->PrimaryOnly);
699      # Create load objects for each of the tables we're loading.      if ($self->{options}->{loadOnly}) {
700      Trace("Beginning subsystem data load.") if T(2);          Trace("Loading from existing files.") if T(2);
701        } else {
702            Trace("Generating subsystem data.") if T(2);
703      # This hash will contain the role for each EC. When we're done, this      # This hash will contain the role for each EC. When we're done, this
704      # information will be used to generate the Catalyzes table.      # information will be used to generate the Catalyzes table.
705      my %ecToRoles = ();      my %ecToRoles = ();
# Line 678  Line 711 
711      my ($genomeID, $roleID);      my ($genomeID, $roleID);
712      my %roleData = ();      my %roleData = ();
713      for my $subsysID (@subsysIDs) {      for my $subsysID (@subsysIDs) {
         Trace("Creating subsystem $subsysID.") if T(3);  
         $loadSubsystem->Add("subsystemIn");  
714          # Get the subsystem object.          # Get the subsystem object.
715          my $sub = $fig->get_subsystem($subsysID);          my $sub = $fig->get_subsystem($subsysID);
716                # Only proceed if the subsystem has a spreadsheet.
717                if (! $sub->{empty_ss}) {
718                    Trace("Creating subsystem $subsysID.") if T(3);
719                    $loadSubsystem->Add("subsystemIn");
720          # Create the subsystem record.          # Create the subsystem record.
721          my $curator = $sub->get_curator();          my $curator = $sub->get_curator();
722          my $notes = $sub->get_notes();          my $notes = $sub->get_notes();
# Line 729  Line 764 
764                  # part of the spreadsheet cell ID.                  # part of the spreadsheet cell ID.
765                  for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {                  for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
766                      # Get the features in the spreadsheet cell for this genome and role.                      # Get the features in the spreadsheet cell for this genome and role.
767                      my @pegs = $sub->get_pegs_from_cell($row, $col);                              my @pegs = grep { !$fig->is_deleted_fid($_) } $sub->get_pegs_from_cell($row, $col);
768                      # Only proceed if features exist.                      # Only proceed if features exist.
769                      if (@pegs > 0) {                      if (@pegs > 0) {
770                          # Create the spreadsheet cell.                          # Create the spreadsheet cell.
# Line 782  Line 817 
817              # Connect the subset to the subsystem.              # Connect the subset to the subsystem.
818              $loadHasRoleSubset->Put($subsysID, $actualID);              $loadHasRoleSubset->Put($subsysID, $actualID);
819              # Connect the subset to its roles.              # Connect the subset to its roles.
820              my @roles = $sub->get_subset($subsetID);                      my @roles = $sub->get_subsetC_roles($subsetID);
821              for my $roleID (@roles) {              for my $roleID (@roles) {
822                  $loadConsistsOfRoles->Put($actualID, $roleID);                  $loadConsistsOfRoles->Put($actualID, $roleID);
823              }              }
# Line 834  Line 869 
869              }              }
870          }          }
871      }      }
872            }
873        }
874      # Finish the load.      # Finish the load.
875      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
876      return $retVal;      return $retVal;
# Line 875  Line 912 
912      my $fig = $self->{fig};      my $fig = $self->{fig};
913      # Get the genome hash.      # Get the genome hash.
914      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
915      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
916      my $loadProperty = $self->_TableLoader('Property', $genomeCount * 1500);      my $loadProperty = $self->_TableLoader('Property');
917      my $loadHasProperty = $self->_TableLoader('HasProperty', $genomeCount * 1500);      my $loadHasProperty = $self->_TableLoader('HasProperty', $self->PrimaryOnly);
918      Trace("Beginning property data load.") if T(2);      if ($self->{options}->{loadOnly}) {
919            Trace("Loading from existing files.") if T(2);
920        } else {
921            Trace("Generating property data.") if T(2);
922      # Create a hash for storing property IDs.      # Create a hash for storing property IDs.
923      my %propertyKeys = ();      my %propertyKeys = ();
924      my $nextID = 1;      my $nextID = 1;
925      # Loop through the genomes.      # Loop through the genomes.
926      for my $genomeID (keys %{$genomeHash}) {      for my $genomeID (keys %{$genomeHash}) {
927          $loadProperty->Add("genomeIn");          $loadProperty->Add("genomeIn");
928                Trace("Generating properties for $genomeID.") if T(3);
929          # Get the genome's features. The feature ID is the first field in the          # Get the genome's features. The feature ID is the first field in the
930          # tuples returned by "all_features_detailed". We use "all_features_detailed"          # tuples returned by "all_features_detailed". We use "all_features_detailed"
931          # rather than "all_features" because we want all features regardless of type.          # rather than "all_features" because we want all features regardless of type.
932          my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};          my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};
933                my $featureCount = 0;
934                my $propertyCount = 0;
935          # Loop through the features, creating HasProperty records.          # Loop through the features, creating HasProperty records.
936          for my $fid (@features) {          for my $fid (@features) {
             $loadProperty->Add("featureIn");  
937              # Get all attributes for this feature. We do this one feature at a time              # Get all attributes for this feature. We do this one feature at a time
938              # to insure we do not get any genome attributes.              # to insure we do not get any genome attributes.
939              my @attributeList = $fig->get_attributes($fid, '', '', '');              my @attributeList = $fig->get_attributes($fid, '', '', '');
940                    if (scalar @attributeList) {
941                        $featureCount++;
942                    }
943              # Loop through the attributes.              # Loop through the attributes.
944              for my $tuple (@attributeList) {              for my $tuple (@attributeList) {
945                        $propertyCount++;
946                  # Get this attribute value's data. Note that we throw away the FID,                  # Get this attribute value's data. Note that we throw away the FID,
947                  # since it will always be the same as the value if "$fid".                  # since it will always be the same as the value if "$fid".
948                  my (undef, $key, $value, $url) = @{$tuple};                  my (undef, $key, $value, $url) = @{$tuple};
# Line 919  Line 964 
964                  $loadHasProperty->Put($fid, $propertyID, $url);                  $loadHasProperty->Put($fid, $propertyID, $url);
965              }              }
966          }          }
967                # Update the statistics.
968                Trace("$propertyCount attributes processed for $featureCount features.") if T(3);
969                $loadHasProperty->Add("featuresIn", $featureCount);
970                $loadHasProperty->Add("propertiesIn", $propertyCount);
971            }
972      }      }
973      # Finish the load.      # Finish the load.
974      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
# Line 959  Line 1009 
1009      my $fig = $self->{fig};      my $fig = $self->{fig};
1010      # Get the genome hash.      # Get the genome hash.
1011      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1012      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1013      my $loadAnnotation = $self->_TableLoader('Annotation', $genomeCount * 4000);      my $loadAnnotation = $self->_TableLoader('Annotation');
1014      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation', $genomeCount * 4000);      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation', $self->PrimaryOnly);
1015      my $loadSproutUser = $self->_TableLoader('SproutUser', 100);      my $loadSproutUser = $self->_TableLoader('SproutUser', $self->PrimaryOnly);
1016      my $loadUserAccess = $self->_TableLoader('UserAccess', 1000);      my $loadUserAccess = $self->_TableLoader('UserAccess', $self->PrimaryOnly);
1017      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation', $genomeCount * 4000);      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation', $self->PrimaryOnly);
1018      Trace("Beginning annotation data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1019            Trace("Loading from existing files.") if T(2);
1020        } else {
1021            Trace("Generating annotation data.") if T(2);
1022      # Create a hash of user names. We'll use this to prevent us from generating duplicate      # Create a hash of user names. We'll use this to prevent us from generating duplicate
1023      # user records.      # user records.
1024      my %users = ( FIG => 1, master => 1 );      my %users = ( FIG => 1, master => 1 );
# Line 980  Line 1032 
1032      # Loop through the genomes.      # Loop through the genomes.
1033      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
1034          Trace("Processing $genomeID.") if T(3);          Trace("Processing $genomeID.") if T(3);
         # Get the genome's PEGs.  
         my @pegs = $fig->pegs_of($genomeID);  
         for my $peg (@pegs) {  
             Trace("Processing $peg.") if T(4);  
1035              # Create a hash of timestamps. We use this to prevent duplicate time stamps              # Create a hash of timestamps. We use this to prevent duplicate time stamps
1036              # from showing up for a single PEG's annotations.              # from showing up for a single PEG's annotations.
1037              my %seenTimestamps = ();              my %seenTimestamps = ();
1038              # Loop through the annotations.              # Get the genome's annotations.
1039              for my $tuple ($fig->feature_annotations($peg, "raw")) {              my @annotations = $fig->read_all_annotations($genomeID);
1040                  my ($fid, $timestamp, $user, $text) = @{$tuple};              Trace("Processing annotations.") if T(2);
1041                for my $tuple (@annotations) {
1042                    # Get the annotation tuple.
1043                    my ($peg, $timestamp, $user, $text) = @{$tuple};
1044                  # Here we fix up the annotation text. "\r" is removed,                  # Here we fix up the annotation text. "\r" is removed,
1045                  # and "\t" and "\n" are escaped. Note we use the "s"                  # and "\t" and "\n" are escaped. Note we use the "s"
1046                  # modifier so that new-lines inside the text do not                  # modifier so that new-lines inside the text do not
# Line 1004  Line 1055 
1055                      # Here it's a number. We need to insure the one we use to form                      # Here it's a number. We need to insure the one we use to form
1056                      # the key is unique.                      # the key is unique.
1057                      my $keyStamp = $timestamp;                      my $keyStamp = $timestamp;
1058                      while ($seenTimestamps{$keyStamp}) {                      while ($seenTimestamps{"$peg:$keyStamp"}) {
1059                          $keyStamp++;                          $keyStamp++;
1060                      }                      }
                     $seenTimestamps{$keyStamp} = 1;  
1061                      my $annotationID = "$peg:$keyStamp";                      my $annotationID = "$peg:$keyStamp";
1062                        $seenTimestamps{$annotationID} = 1;
1063                      # Insure the user exists.                      # Insure the user exists.
1064                      if (! $users{$user}) {                      if (! $users{$user}) {
1065                          $loadSproutUser->Put($user, "SEED user");                          $loadSproutUser->Put($user, "SEED user");
# Line 1066  Line 1117 
1117      my $fig = $self->{fig};      my $fig = $self->{fig};
1118      # Get the genome hash.      # Get the genome hash.
1119      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1120      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1121      my $loadComesFrom = $self->_TableLoader('ComesFrom', $genomeCount * 4);      my $loadComesFrom = $self->_TableLoader('ComesFrom', $self->PrimaryOnly);
1122      my $loadSource = $self->_TableLoader('Source', $genomeCount * 4);      my $loadSource = $self->_TableLoader('Source');
1123      my $loadSourceURL = $self->_TableLoader('SourceURL', $genomeCount * 8);      my $loadSourceURL = $self->_TableLoader('SourceURL');
1124      Trace("Beginning source data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1125            Trace("Loading from existing files.") if T(2);
1126        } else {
1127            Trace("Generating annotation data.") if T(2);
1128      # Create hashes to collect the Source information.      # Create hashes to collect the Source information.
1129      my %sourceURL = ();      my %sourceURL = ();
1130      my %sourceDesc = ();      my %sourceDesc = ();
# Line 1101  Line 1154 
1154      for my $sourceID (keys %sourceDesc) {      for my $sourceID (keys %sourceDesc) {
1155          $loadSource->Put($sourceID, $sourceDesc{$sourceID});          $loadSource->Put($sourceID, $sourceDesc{$sourceID});
1156      }      }
1157        }
1158      # Finish the load.      # Finish the load.
1159      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1160      return $retVal;      return $retVal;
# Line 1140  Line 1194 
1194      my $fig = $self->{fig};      my $fig = $self->{fig};
1195      # Get the genome hash.      # Get the genome hash.
1196      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1197      # Convert the genome hash. We'll get the genus and species for each genome and make      # Convert the genome hash. We'll get the genus and species for each genome and make
1198      # it the key.      # it the key.
1199      my %speciesHash = map { $fig->genus_species($_) => $_ } (keys %{$genomeHash});      my %speciesHash = map { $fig->genus_species($_) => $_ } (keys %{$genomeHash});
1200      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1201      my $loadExternalAliasFunc = $self->_TableLoader('ExternalAliasFunc', $genomeCount * 4000);      my $loadExternalAliasFunc = $self->_TableLoader('ExternalAliasFunc');
1202      my $loadExternalAliasOrg = $self->_TableLoader('ExternalAliasOrg', $genomeCount * 4000);      my $loadExternalAliasOrg = $self->_TableLoader('ExternalAliasOrg');
1203      Trace("Beginning external data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1204            Trace("Loading from existing files.") if T(2);
1205        } else {
1206            Trace("Generating external data.") if T(2);
1207      # We loop through the files one at a time. First, the organism file.      # We loop through the files one at a time. First, the organism file.
1208      Open(\*ORGS, "<$FIG_Config::global/ext_org.table");      Open(\*ORGS, "<$FIG_Config::global/ext_org.table");
1209      my $orgLine;      my $orgLine;
# Line 1177  Line 1233 
1233              $loadExternalAliasFunc->Put(@funcFields[0,1]);              $loadExternalAliasFunc->Put(@funcFields[0,1]);
1234          }          }
1235      }      }
1236        }
1237      # Finish the load.      # Finish the load.
1238      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1239      return $retVal;      return $retVal;
# Line 1217  Line 1274 
1274      my ($self) = @_;      my ($self) = @_;
1275      # Get the FIG object.      # Get the FIG object.
1276      my $fig = $self->{fig};      my $fig = $self->{fig};
     # Get the genome hash.  
     my $genomeHash = $self->{genomes};  
     my $genomeCount = (keys %{$genomeHash});  
1277      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1278      my $loadReaction = $self->_TableLoader('Reaction', $genomeCount * 4000);      my $loadReaction = $self->_TableLoader('Reaction');
1279      my $loadReactionURL = $self->_TableLoader('ReactionURL', $genomeCount * 4000);      my $loadReactionURL = $self->_TableLoader('ReactionURL', $self->PrimaryOnly);
1280      my $loadCompound = $self->_TableLoader('Compound', $genomeCount * 4000);      my $loadCompound = $self->_TableLoader('Compound', $self->PrimaryOnly);
1281      my $loadCompoundName = $self->_TableLoader('CompoundName', $genomeCount * 8000);      my $loadCompoundName = $self->_TableLoader('CompoundName', $self->PrimaryOnly);
1282      my $loadCompoundCAS = $self->_TableLoader('CompoundCAS', $genomeCount * 4000);      my $loadCompoundCAS = $self->_TableLoader('CompoundCAS', $self->PrimaryOnly);
1283      my $loadIsAComponentOf = $self->_TableLoader('IsAComponentOf', $genomeCount * 12000);      my $loadIsAComponentOf = $self->_TableLoader('IsAComponentOf', $self->PrimaryOnly);
1284      Trace("Beginning reaction/compound data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1285            Trace("Loading from existing files.") if T(2);
1286        } else {
1287            Trace("Generating annotation data.") if T(2);
1288      # First we create the compounds.      # First we create the compounds.
1289      my @compounds = $fig->all_compounds();      my @compounds = $fig->all_compounds();
1290      for my $cid (@compounds) {      for my $cid (@compounds) {
# Line 1276  Line 1333 
1333              }              }
1334          }          }
1335      }      }
1336        }
1337      # Finish the load.      # Finish the load.
1338      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1339      return $retVal;      return $retVal;
# Line 1311  Line 1369 
1369      my $fig = $self->{fig};      my $fig = $self->{fig};
1370      # Get the genome hash.      # Get the genome hash.
1371      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1372      # Create a load object for the table we're loading.      # Create a load object for the table we're loading.
1373      my $loadGenomeGroups = $self->_TableLoader('GenomeGroups', $genomeCount * 4);      my $loadGenomeGroups = $self->_TableLoader('GenomeGroups');
1374      Trace("Beginning group data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1375            Trace("Loading from existing files.") if T(2);
1376        } else {
1377            Trace("Generating group data.") if T(2);
1378      # Loop through the genomes.      # Loop through the genomes.
1379      my $line;      my $line;
1380      for my $genomeID (keys %{$genomeHash}) {      for my $genomeID (keys %{$genomeHash}) {
# Line 1330  Line 1390 
1390          }          }
1391          close TMP;          close TMP;
1392      }      }
1393        }
1394      # Finish the load.      # Finish the load.
1395      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1396      return $retVal;      return $retVal;
# Line 1351  Line 1412 
1412    
1413  Name of the table (relation) being loaded.  Name of the table (relation) being loaded.
1414    
1415  =item rowCount (optional)  =item ignore
1416    
1417  Estimated maximum number of rows in the table.  TRUE if the table should be ignored entirely, else FALSE.
1418    
1419  =item RETURN  =item RETURN
1420    
# Line 1365  Line 1426 
1426    
1427  sub _TableLoader {  sub _TableLoader {
1428      # Get the parameters.      # Get the parameters.
1429      my ($self, $tableName, $rowCount) = @_;      my ($self, $tableName, $ignore) = @_;
1430      # Create the load object.      # Create the load object.
1431      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $rowCount);      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $self->LoadOnly,
1432                                   $ignore);
1433      # Cache it in the loader list.      # Cache it in the loader list.
1434      push @{$self->{loaders}}, $retVal;      push @{$self->{loaders}}, $retVal;
1435      # Return it to the caller.      # Return it to the caller.
# Line 1404  Line 1466 
1466      # Loop through the list, finishing the loads. Note that if the finish fails, we die      # Loop through the list, finishing the loads. Note that if the finish fails, we die
1467      # ignominiously. At some future point, we want to make the loads restartable.      # ignominiously. At some future point, we want to make the loads restartable.
1468      while (my $loader = pop @{$loadList}) {      while (my $loader = pop @{$loadList}) {
1469          # Trace the fact that we're cleaning up.          # Get the relation name.
1470          my $relName = $loader->RelName;          my $relName = $loader->RelName;
1471          Trace("Finishing load for $relName.") if T(2);          # Check the ignore flag.
1472            if ($loader->Ignore) {
1473                Trace("Relation $relName not loaded.") if T(2);
1474            } else {
1475                # Here we really need to finish.
1476                Trace("Finishing $relName.") if T(2);
1477          my $stats = $loader->Finish();          my $stats = $loader->Finish();
1478          if ($self->{options}->{dbLoad}) {          if ($self->{options}->{dbLoad}) {
1479              # Here we want to use the load file just created to load the database.              # Here we want to use the load file just created to load the database.
# Line 1418  Line 1485 
1485          $retVal->Accumulate($stats);          $retVal->Accumulate($stats);
1486          Trace("Statistics for $relName:\n" . $stats->Show()) if T(2);          Trace("Statistics for $relName:\n" . $stats->Show()) if T(2);
1487      }      }
1488        }
1489      # Return the load statistics.      # Return the load statistics.
1490      return $retVal;      return $retVal;
1491  }  }

Legend:
Removed from v.1.22  
changed lines
  Added in v.1.40

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3