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

Diff of /Sprout/SproutLoad.pm

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

revision 1.21, Sat Nov 12 03:42:48 2005 UTC revision 1.50, Sun Jul 9 21:16:47 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 308  Line 340 
340      my $fig = $self->{fig};      my $fig = $self->{fig};
341      # Get the genome hash.      # Get the genome hash.
342      my $genomeFilter = $self->{genomes};      my $genomeFilter = $self->{genomes};
343      my $genomeCount = (keys %{$genomeFilter});      # Set up an ID counter for the PCHs.
344      my $featureCount = $genomeCount * 4000;      my $pchID = 0;
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 340  Line 375 
375              for my $coupleData (@couplings) {              for my $coupleData (@couplings) {
376                  my ($peg2, $score) = @{$coupleData};                  my ($peg2, $score) = @{$coupleData};
377                  # Compute the coupling ID.                  # Compute the coupling ID.
378                  my $coupleID = Sprout::CouplingID($peg1, $peg2);                      my $coupleID = $self->{erdb}->CouplingID($peg1, $peg2);
379                  if (! exists $dupHash{$coupleID}) {                  if (! exists $dupHash{$coupleID}) {
380                      $loadCoupling->Add("couplingIn");                      $loadCoupling->Add("couplingIn");
381                      # Here we have a new coupling to store in the load files.                      # Here we have a new coupling to store in the load files.
# Line 376  Line 411 
411                          }                          }
412                      }                      }
413                      for my $evidenceID (keys %evidenceMap) {                      for my $evidenceID (keys %evidenceMap) {
414                                # Get the ID for this evidence.
415                                $pchID++;
416                          # Create the evidence record.                          # Create the evidence record.
417                          my ($peg3, $peg4, $usage) = @{$evidenceMap{$evidenceID}};                          my ($peg3, $peg4, $usage) = @{$evidenceMap{$evidenceID}};
418                          $loadPCH->Put($evidenceID, $usage);                              $loadPCH->Put($pchID, $usage);
419                          # Connect it to the coupling.                          # Connect it to the coupling.
420                          $loadIsEvidencedBy->Put($coupleID, $evidenceID);                              $loadIsEvidencedBy->Put($coupleID, $pchID);
421                          # Connect it to the features.                          # Connect it to the features.
422                          $loadUsesAsEvidence->Put($evidenceID, $peg3, 1);                              $loadUsesAsEvidence->Put($pchID, $peg3, 1);
423                          $loadUsesAsEvidence->Put($evidenceID, $peg4, 2);                              $loadUsesAsEvidence->Put($pchID, $peg4, 2);
424                            }
425                      }                      }
426                  }                  }
427              }              }
# Line 410  Line 448 
448      FeatureTranslation      FeatureTranslation
449      FeatureUpstream      FeatureUpstream
450      IsLocatedIn      IsLocatedIn
451        HasFeature
452    
453  =over 4  =over 4
454    
# Line 426  Line 465 
465      my ($self) = @_;      my ($self) = @_;
466      # Get the FIG object.      # Get the FIG object.
467      my $fig = $self->{fig};      my $fig = $self->{fig};
     # Find out if this is a limited run.  
     my $limited = $self->{options}->{limitedFeatures};  
468      # Get the table of genome IDs.      # Get the table of genome IDs.
469      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
     my $featureCount = $genomeCount * 4000;  
470      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
471      my $loadFeature = $self->_TableLoader('Feature', $featureCount);      my $loadFeature = $self->_TableLoader('Feature');
472      my $loadIsLocatedIn = $self->_TableLoader('IsLocatedIn', $featureCount);      my $loadIsLocatedIn = $self->_TableLoader('IsLocatedIn', $self->PrimaryOnly);
473      my $loadFeatureAlias = $self->_TableLoader('FeatureAlias', $featureCount * 6);      my $loadFeatureAlias = $self->_TableLoader('FeatureAlias');
474      my ($loadFeatureLink, $loadFeatureTranslation, $loadFeatureUpstream);      my $loadFeatureLink = $self->_TableLoader('FeatureLink');
475      if (! $limited) {      my $loadFeatureTranslation = $self->_TableLoader('FeatureTranslation');
476          $loadFeatureLink = $self->_TableLoader('FeatureLink', $featureCount * 10);      my $loadFeatureUpstream = $self->_TableLoader('FeatureUpstream');
477          $loadFeatureTranslation = $self->_TableLoader('FeatureTranslation', $featureCount);      my $loadHasFeature = $self->_TableLoader('HasFeature');
         $loadFeatureUpstream = $self->_TableLoader('FeatureUpstream', $featureCount);  
     }  
478      # 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
479      # locations.      # locations.
480      my $chunkSize = $self->{sprout}->MaxSegment();      my $chunkSize = $self->{sprout}->MaxSegment();
481      Trace("Beginning feature data load.") if T(2);      if ($self->{options}->{loadOnly}) {
482            Trace("Loading from existing files.") if T(2);
483        } else {
484            Trace("Generating feature data.") if T(2);
485      # Now we loop through the genomes, generating the data for each one.      # Now we loop through the genomes, generating the data for each one.
486      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
487          Trace("Loading features for genome $genomeID.") if T(3);          Trace("Loading features for genome $genomeID.") if T(3);
# Line 459  Line 495 
495              my ($featureID, $locations, undef, $type) = @{$featureData};              my ($featureID, $locations, undef, $type) = @{$featureData};
496              # Create the feature record.              # Create the feature record.
497              $loadFeature->Put($featureID, 1, $type);              $loadFeature->Put($featureID, 1, $type);
498                    # Link it to the parent genome.
499                    $loadHasFeature->Put($genomeID, $featureID, $type);
500              # Create the aliases.              # Create the aliases.
501              for my $alias ($fig->feature_aliases($featureID)) {              for my $alias ($fig->feature_aliases($featureID)) {
502                  $loadFeatureAlias->Put($featureID, $alias);                  $loadFeatureAlias->Put($featureID, $alias);
503              }              }
             # The next stuff is for a full load only.  
             if (! $limited) {  
504                  # Get the links.                  # Get the links.
505                  my @links = $fig->fid_links($featureID);                  my @links = $fig->fid_links($featureID);
506                  for my $link (@links) {                  for my $link (@links) {
# Line 483  Line 519 
519                          $loadFeatureUpstream->Put($featureID, $upstream);                          $loadFeatureUpstream->Put($featureID, $upstream);
520                      }                      }
521                  }                  }
             }  
522              # 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
523              # 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
524              # 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 547 
547              }              }
548          }          }
549      }      }
550        }
551      # Finish the loads.      # Finish the loads.
552      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
553      return $retVal;      return $retVal;
# Line 548  Line 584 
584      my $fig = $self->{fig};      my $fig = $self->{fig};
585      # Get the table of genome IDs.      # Get the table of genome IDs.
586      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
     my $featureCount = $genomeCount * 4000;  
587      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
588      my $loadIsBidirectionalBestHitOf = $self->_TableLoader('IsBidirectionalBestHitOf',      my $loadIsBidirectionalBestHitOf = $self->_TableLoader('IsBidirectionalBestHitOf');
589                                                             $featureCount * $genomeCount);      if ($self->{options}->{loadOnly}) {
590      Trace("Beginning BBH load.") if T(2);          Trace("Loading from existing files.") if T(2);
591        } else {
592            Trace("Generating BBH data.") if T(2);
593      # Now we loop through the genomes, generating the data for each one.      # Now we loop through the genomes, generating the data for each one.
594      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
595          $loadIsBidirectionalBestHitOf->Add("genomeIn");          $loadIsBidirectionalBestHitOf->Add("genomeIn");
# Line 579  Line 615 
615              }              }
616          }          }
617      }      }
618        }
619      # Finish the loads.      # Finish the loads.
620      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
621      return $retVal;      return $retVal;
# Line 599  Line 636 
636  The following relations are loaded by this method.  The following relations are loaded by this method.
637    
638      Subsystem      Subsystem
639        SubsystemClass
640      Role      Role
641      RoleEC      RoleEC
642      SSCell      SSCell
# Line 639  Line 677 
677      # Get the subsystem hash. This lists the subsystems we'll process.      # Get the subsystem hash. This lists the subsystems we'll process.
678      my $subsysHash = $self->{subsystems};      my $subsysHash = $self->{subsystems};
679      my @subsysIDs = sort keys %{$subsysHash};      my @subsysIDs = sort keys %{$subsysHash};
     my $subsysCount = @subsysIDs;  
     my $genomeCount = (keys %{$genomeHash});  
     my $featureCount = $genomeCount * 4000;  
680      # Get the map list.      # Get the map list.
681      my @maps = $fig->all_maps;      my @maps = $fig->all_maps;
     my $mapCount = @maps;  
682      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
683      my $loadDiagram = $self->_TableLoader('Diagram', $mapCount);      my $loadDiagram = $self->_TableLoader('Diagram', $self->PrimaryOnly);
684      my $loadRoleOccursIn = $self->_TableLoader('RoleOccursIn', $featureCount * 6);      my $loadRoleOccursIn = $self->_TableLoader('RoleOccursIn', $self->PrimaryOnly);
685      my $loadSubsystem = $self->_TableLoader('Subsystem', $subsysCount);      my $loadSubsystem = $self->_TableLoader('Subsystem');
686      my $loadRole = $self->_TableLoader('Role', $featureCount * 6);      my $loadRole = $self->_TableLoader('Role', $self->PrimaryOnly);
687      my $loadRoleEC = $self->_TableLoader('RoleEC', $featureCount * 6);      my $loadRoleEC = $self->_TableLoader('RoleEC', $self->PrimaryOnly);
688      my $loadCatalyzes = $self->_TableLoader('Catalyzes', $genomeCount * $featureCount);      my $loadCatalyzes = $self->_TableLoader('Catalyzes', $self->PrimaryOnly);
689      my $loadSSCell = $self->_TableLoader('SSCell', $featureCount * $genomeCount);      my $loadSSCell = $self->_TableLoader('SSCell', $self->PrimaryOnly);
690      my $loadContainsFeature = $self->_TableLoader('ContainsFeature', $featureCount * $subsysCount);      my $loadContainsFeature = $self->_TableLoader('ContainsFeature', $self->PrimaryOnly);
691      my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf', $featureCount * $genomeCount);      my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf', $self->PrimaryOnly);
692      my $loadIsRoleOf = $self->_TableLoader('IsRoleOf', $featureCount * $genomeCount);      my $loadIsRoleOf = $self->_TableLoader('IsRoleOf', $self->PrimaryOnly);
693      my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem', $featureCount * 6);      my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem', $self->PrimaryOnly);
694      my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn', $subsysCount * $genomeCount);      my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn', $self->PrimaryOnly);
695      my $loadHasSSCell = $self->_TableLoader('HasSSCell', $featureCount * $genomeCount);      my $loadHasSSCell = $self->_TableLoader('HasSSCell', $self->PrimaryOnly);
696      my $loadRoleSubset = $self->_TableLoader('RoleSubset', $subsysCount * 50);      my $loadRoleSubset = $self->_TableLoader('RoleSubset', $self->PrimaryOnly);
697      my $loadGenomeSubset = $self->_TableLoader('GenomeSubset', $subsysCount * 50);      my $loadGenomeSubset = $self->_TableLoader('GenomeSubset', $self->PrimaryOnly);
698      my $loadConsistsOfRoles = $self->_TableLoader('ConsistsOfRoles', $featureCount * $genomeCount);      my $loadConsistsOfRoles = $self->_TableLoader('ConsistsOfRoles', $self->PrimaryOnly);
699      my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes', $featureCount * $genomeCount);      my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes', $self->PrimaryOnly);
700      my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset', $subsysCount * 50);      my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset', $self->PrimaryOnly);
701      my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset', $subsysCount * 50);      my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset', $self->PrimaryOnly);
702      # Create load objects for each of the tables we're loading.      my $loadSubsystemClass = $self->_TableLoader('SubsystemClass', $self->PrimaryOnly);
703      Trace("Beginning subsystem data load.") if T(2);      if ($self->{options}->{loadOnly}) {
704            Trace("Loading from existing files.") if T(2);
705        } else {
706            Trace("Generating subsystem data.") if T(2);
707      # 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
708      # information will be used to generate the Catalyzes table.      # information will be used to generate the Catalyzes table.
709      my %ecToRoles = ();      my %ecToRoles = ();
# Line 678  Line 715 
715      my ($genomeID, $roleID);      my ($genomeID, $roleID);
716      my %roleData = ();      my %roleData = ();
717      for my $subsysID (@subsysIDs) {      for my $subsysID (@subsysIDs) {
         Trace("Creating subsystem $subsysID.") if T(3);  
         $loadSubsystem->Add("subsystemIn");  
718          # Get the subsystem object.          # Get the subsystem object.
719          my $sub = $fig->get_subsystem($subsysID);          my $sub = $fig->get_subsystem($subsysID);
720                # Only proceed if the subsystem has a spreadsheet.
721                if (! $sub->{empty_ss}) {
722                    Trace("Creating subsystem $subsysID.") if T(3);
723                    $loadSubsystem->Add("subsystemIn");
724          # Create the subsystem record.          # Create the subsystem record.
725          my $curator = $sub->get_curator();          my $curator = $sub->get_curator();
726          my $notes = $sub->get_notes();          my $notes = $sub->get_notes();
727          $loadSubsystem->Put($subsysID, $curator, $notes);          $loadSubsystem->Put($subsysID, $curator, $notes);
728                    my $class = $fig->subsystem_classification($subsysID);
729                    if ($class) {
730                        $loadSubsystemClass->Put($subsysID, $class);
731                    }
732          # Connect it to its roles. Each role is a column in the subsystem spreadsheet.          # Connect it to its roles. Each role is a column in the subsystem spreadsheet.
733          for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {          for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
734              # Connect to this role.              # Connect to this role.
# Line 729  Line 772 
772                  # part of the spreadsheet cell ID.                  # part of the spreadsheet cell ID.
773                  for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {                  for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
774                      # Get the features in the spreadsheet cell for this genome and role.                      # Get the features in the spreadsheet cell for this genome and role.
775                      my @pegs = $sub->get_pegs_from_cell($row, $col);                              my @pegs = grep { !$fig->is_deleted_fid($_) } $sub->get_pegs_from_cell($row, $col);
776                      # Only proceed if features exist.                      # Only proceed if features exist.
777                      if (@pegs > 0) {                      if (@pegs > 0) {
778                          # Create the spreadsheet cell.                          # Create the spreadsheet cell.
# Line 750  Line 793 
793                  if ($pegCount > 0) {                  if ($pegCount > 0) {
794                      Trace("$pegCount PEGs in $cellCount cells for $genomeID.") if T(3);                      Trace("$pegCount PEGs in $cellCount cells for $genomeID.") if T(3);
795                      $loadParticipatesIn->Put($genomeID, $subsysID, $variantCode);                      $loadParticipatesIn->Put($genomeID, $subsysID, $variantCode);
                     # Partition the PEGs found into clusters.  
                     my @clusters = $fig->compute_clusters(\@pegsFound, $sub);  
796                      # Create a hash mapping PEG IDs to cluster numbers.                      # Create a hash mapping PEG IDs to cluster numbers.
797                      # We default to -1 for all of them.                      # We default to -1 for all of them.
798                      my %clusterOf = map { $_ => -1 } @pegsFound;                      my %clusterOf = map { $_ => -1 } @pegsFound;
799                                # Partition the PEGs found into clusters.
800                                my @clusters = $fig->compute_clusters([keys %clusterOf], $sub);
801                      for (my $i = 0; $i <= $#clusters; $i++) {                      for (my $i = 0; $i <= $#clusters; $i++) {
802                          my $subList = $clusters[$i];                          my $subList = $clusters[$i];
803                          for my $peg (@{$subList}) {                          for my $peg (@{$subList}) {
# Line 782  Line 825 
825              # Connect the subset to the subsystem.              # Connect the subset to the subsystem.
826              $loadHasRoleSubset->Put($subsysID, $actualID);              $loadHasRoleSubset->Put($subsysID, $actualID);
827              # Connect the subset to its roles.              # Connect the subset to its roles.
828              my @roles = $sub->get_subset($subsetID);                      my @roles = $sub->get_subsetC_roles($subsetID);
829              for my $roleID (@roles) {              for my $roleID (@roles) {
830                  $loadConsistsOfRoles->Put($actualID, $roleID);                  $loadConsistsOfRoles->Put($actualID, $roleID);
831              }              }
# Line 834  Line 877 
877              }              }
878          }          }
879      }      }
880            }
881        }
882      # Finish the load.      # Finish the load.
883      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
884      return $retVal;      return $retVal;
# Line 875  Line 920 
920      my $fig = $self->{fig};      my $fig = $self->{fig};
921      # Get the genome hash.      # Get the genome hash.
922      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
923      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
924      my $loadProperty = $self->_TableLoader('Property', $genomeCount * 1500);      my $loadProperty = $self->_TableLoader('Property');
925      my $loadHasProperty = $self->_TableLoader('HasProperty', $genomeCount * 1500);      my $loadHasProperty = $self->_TableLoader('HasProperty', $self->PrimaryOnly);
926      Trace("Beginning property data load.") if T(2);      if ($self->{options}->{loadOnly}) {
927            Trace("Loading from existing files.") if T(2);
928        } else {
929            Trace("Generating property data.") if T(2);
930      # Create a hash for storing property IDs.      # Create a hash for storing property IDs.
931      my %propertyKeys = ();      my %propertyKeys = ();
932      my $nextID = 1;      my $nextID = 1;
933      # Loop through the genomes.      # Loop through the genomes.
934      for my $genomeID (keys %{$genomeHash}) {      for my $genomeID (keys %{$genomeHash}) {
935          $loadProperty->Add("genomeIn");          $loadProperty->Add("genomeIn");
936                Trace("Generating properties for $genomeID.") if T(3);
937          # 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
938          # tuples returned by "all_features_detailed". We use "all_features_detailed"          # tuples returned by "all_features_detailed". We use "all_features_detailed"
939          # rather than "all_features" because we want all features regardless of type.          # rather than "all_features" because we want all features regardless of type.
940          my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};          my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};
941                my $featureCount = 0;
942                my $propertyCount = 0;
943          # Loop through the features, creating HasProperty records.          # Loop through the features, creating HasProperty records.
944          for my $fid (@features) {          for my $fid (@features) {
             $loadProperty->Add("featureIn");  
945              # 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
946              # to insure we do not get any genome attributes.              # to insure we do not get any genome attributes.
947              my @attributeList = $fig->get_attributes($fid, '', '', '');              my @attributeList = $fig->get_attributes($fid, '', '', '');
948                    if (scalar @attributeList) {
949                        $featureCount++;
950                    }
951              # Loop through the attributes.              # Loop through the attributes.
952              for my $tuple (@attributeList) {              for my $tuple (@attributeList) {
953                        $propertyCount++;
954                  # Get this attribute value's data. Note that we throw away the FID,                  # Get this attribute value's data. Note that we throw away the FID,
955                  # since it will always be the same as the value if "$fid".                  # since it will always be the same as the value if "$fid".
956                  my (undef, $key, $value, $url) = @{$tuple};                  my (undef, $key, $value, $url) = @{$tuple};
# Line 919  Line 972 
972                  $loadHasProperty->Put($fid, $propertyID, $url);                  $loadHasProperty->Put($fid, $propertyID, $url);
973              }              }
974          }          }
975                # Update the statistics.
976                Trace("$propertyCount attributes processed for $featureCount features.") if T(3);
977                $loadHasProperty->Add("featuresIn", $featureCount);
978                $loadHasProperty->Add("propertiesIn", $propertyCount);
979            }
980      }      }
981      # Finish the load.      # Finish the load.
982      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
# Line 959  Line 1017 
1017      my $fig = $self->{fig};      my $fig = $self->{fig};
1018      # Get the genome hash.      # Get the genome hash.
1019      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1020      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1021      my $loadAnnotation = $self->_TableLoader('Annotation', $genomeCount * 4000);      my $loadAnnotation = $self->_TableLoader('Annotation');
1022      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation', $genomeCount * 4000);      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation', $self->PrimaryOnly);
1023      my $loadSproutUser = $self->_TableLoader('SproutUser', 100);      my $loadSproutUser = $self->_TableLoader('SproutUser', $self->PrimaryOnly);
1024      my $loadUserAccess = $self->_TableLoader('UserAccess', 1000);      my $loadUserAccess = $self->_TableLoader('UserAccess', $self->PrimaryOnly);
1025      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation', $genomeCount * 4000);      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation', $self->PrimaryOnly);
1026      Trace("Beginning annotation data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1027            Trace("Loading from existing files.") if T(2);
1028        } else {
1029            Trace("Generating annotation data.") if T(2);
1030      # 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
1031      # user records.      # user records.
1032      my %users = ( FIG => 1, master => 1 );      my %users = ( FIG => 1, master => 1 );
# Line 980  Line 1040 
1040      # Loop through the genomes.      # Loop through the genomes.
1041      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
1042          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);  
1043              # 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
1044              # from showing up for a single PEG's annotations.              # from showing up for a single PEG's annotations.
1045              my %seenTimestamps = ();              my %seenTimestamps = ();
1046              # Check for a functional assignment.              # Get the genome's annotations.
1047              my $func = $fig->function_of($peg);              my @annotations = $fig->read_all_annotations($genomeID);
1048              if ($func) {              Trace("Processing annotations.") if T(2);
1049                  # If this is NOT a hypothetical assignment, we create an              for my $tuple (@annotations) {
1050                  # assignment annotation for it.                  # Get the annotation tuple.
1051                  if (! FIG::hypo($peg)) {                  my ($peg, $timestamp, $user, $text) = @{$tuple};
                     # Note that we double the slashes so that what goes into the database is  
                     # a new-line escape sequence rather than an actual new-line.  
                     $loadAnnotation->Put("$peg:$time", $time, "FIG\\nSet function to\\n$func");  
                     $loadIsTargetOfAnnotation->Put($peg, "$peg:$time");  
                     $loadMadeAnnotation->Put("FIG", "$peg:$time");  
                     # Denote we've seen this timestamp.  
                     $seenTimestamps{$time} = 1;  
                 }  
             }  
             # Now loop through the real annotations.  
             for my $tuple ($fig->feature_annotations($peg, "raw")) {  
                 my ($fid, $timestamp, $user, $text) = @{$tuple};  
1052                  # Here we fix up the annotation text. "\r" is removed,                  # Here we fix up the annotation text. "\r" is removed,
1053                  # and "\t" and "\n" are escaped. Note we use the "s"                  # and "\t" and "\n" are escaped. Note we use the "gs"
1054                  # modifier so that new-lines inside the text do not                  # modifier so that new-lines inside the text do not
1055                  # stop the substitution search.                  # stop the substitution search.
1056                  $text =~ s/\r//gs;                  $text =~ s/\r//gs;
# Line 1019  Line 1063 
1063                      # 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
1064                      # the key is unique.                      # the key is unique.
1065                      my $keyStamp = $timestamp;                      my $keyStamp = $timestamp;
1066                      while ($seenTimestamps{$keyStamp}) {                      while ($seenTimestamps{"$peg:$keyStamp"}) {
1067                          $keyStamp++;                          $keyStamp++;
1068                      }                      }
                     $seenTimestamps{$keyStamp} = 1;  
1069                      my $annotationID = "$peg:$keyStamp";                      my $annotationID = "$peg:$keyStamp";
1070                        $seenTimestamps{$annotationID} = 1;
1071                      # Insure the user exists.                      # Insure the user exists.
1072                      if (! $users{$user}) {                      if (! $users{$user}) {
1073                          $loadSproutUser->Put($user, "SEED user");                          $loadSproutUser->Put($user, "SEED user");
# Line 1081  Line 1125 
1125      my $fig = $self->{fig};      my $fig = $self->{fig};
1126      # Get the genome hash.      # Get the genome hash.
1127      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1128      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1129      my $loadComesFrom = $self->_TableLoader('ComesFrom', $genomeCount * 4);      my $loadComesFrom = $self->_TableLoader('ComesFrom', $self->PrimaryOnly);
1130      my $loadSource = $self->_TableLoader('Source', $genomeCount * 4);      my $loadSource = $self->_TableLoader('Source');
1131      my $loadSourceURL = $self->_TableLoader('SourceURL', $genomeCount * 8);      my $loadSourceURL = $self->_TableLoader('SourceURL');
1132      Trace("Beginning source data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1133            Trace("Loading from existing files.") if T(2);
1134        } else {
1135            Trace("Generating annotation data.") if T(2);
1136      # Create hashes to collect the Source information.      # Create hashes to collect the Source information.
1137      my %sourceURL = ();      my %sourceURL = ();
1138      my %sourceDesc = ();      my %sourceDesc = ();
# Line 1116  Line 1162 
1162      for my $sourceID (keys %sourceDesc) {      for my $sourceID (keys %sourceDesc) {
1163          $loadSource->Put($sourceID, $sourceDesc{$sourceID});          $loadSource->Put($sourceID, $sourceDesc{$sourceID});
1164      }      }
1165        }
1166      # Finish the load.      # Finish the load.
1167      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1168      return $retVal;      return $retVal;
# Line 1155  Line 1202 
1202      my $fig = $self->{fig};      my $fig = $self->{fig};
1203      # Get the genome hash.      # Get the genome hash.
1204      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1205      # 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
1206      # it the key.      # it the key.
1207      my %speciesHash = map { $fig->genus_species($_) => $_ } (keys %{$genomeHash});      my %speciesHash = map { $fig->genus_species($_) => $_ } (keys %{$genomeHash});
1208      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1209      my $loadExternalAliasFunc = $self->_TableLoader('ExternalAliasFunc', $genomeCount * 4000);      my $loadExternalAliasFunc = $self->_TableLoader('ExternalAliasFunc');
1210      my $loadExternalAliasOrg = $self->_TableLoader('ExternalAliasOrg', $genomeCount * 4000);      my $loadExternalAliasOrg = $self->_TableLoader('ExternalAliasOrg');
1211      Trace("Beginning external data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1212            Trace("Loading from existing files.") if T(2);
1213        } else {
1214            Trace("Generating external data.") if T(2);
1215      # 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.
1216      Open(\*ORGS, "<$FIG_Config::global/ext_org.table");      Open(\*ORGS, "<$FIG_Config::global/ext_org.table");
1217      my $orgLine;      my $orgLine;
# Line 1192  Line 1241 
1241              $loadExternalAliasFunc->Put(@funcFields[0,1]);              $loadExternalAliasFunc->Put(@funcFields[0,1]);
1242          }          }
1243      }      }
1244        }
1245      # Finish the load.      # Finish the load.
1246      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1247      return $retVal;      return $retVal;
# Line 1232  Line 1282 
1282      my ($self) = @_;      my ($self) = @_;
1283      # Get the FIG object.      # Get the FIG object.
1284      my $fig = $self->{fig};      my $fig = $self->{fig};
     # Get the genome hash.  
     my $genomeHash = $self->{genomes};  
     my $genomeCount = (keys %{$genomeHash});  
1285      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1286      my $loadReaction = $self->_TableLoader('Reaction', $genomeCount * 4000);      my $loadReaction = $self->_TableLoader('Reaction');
1287      my $loadReactionURL = $self->_TableLoader('ReactionURL', $genomeCount * 4000);      my $loadReactionURL = $self->_TableLoader('ReactionURL', $self->PrimaryOnly);
1288      my $loadCompound = $self->_TableLoader('Compound', $genomeCount * 4000);      my $loadCompound = $self->_TableLoader('Compound', $self->PrimaryOnly);
1289      my $loadCompoundName = $self->_TableLoader('CompoundName', $genomeCount * 8000);      my $loadCompoundName = $self->_TableLoader('CompoundName', $self->PrimaryOnly);
1290      my $loadCompoundCAS = $self->_TableLoader('CompoundCAS', $genomeCount * 4000);      my $loadCompoundCAS = $self->_TableLoader('CompoundCAS', $self->PrimaryOnly);
1291      my $loadIsAComponentOf = $self->_TableLoader('IsAComponentOf', $genomeCount * 12000);      my $loadIsAComponentOf = $self->_TableLoader('IsAComponentOf', $self->PrimaryOnly);
1292      Trace("Beginning reaction/compound data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1293            Trace("Loading from existing files.") if T(2);
1294        } else {
1295            Trace("Generating annotation data.") if T(2);
1296      # First we create the compounds.      # First we create the compounds.
1297      my @compounds = $fig->all_compounds();      my @compounds = $fig->all_compounds();
1298      for my $cid (@compounds) {      for my $cid (@compounds) {
# Line 1291  Line 1341 
1341              }              }
1342          }          }
1343      }      }
1344        }
1345      # Finish the load.      # Finish the load.
1346      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1347      return $retVal;      return $retVal;
# Line 1326  Line 1377 
1377      my $fig = $self->{fig};      my $fig = $self->{fig};
1378      # Get the genome hash.      # Get the genome hash.
1379      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1380      # Create a load object for the table we're loading.      # Create a load object for the table we're loading.
1381      my $loadGenomeGroups = $self->_TableLoader('GenomeGroups', $genomeCount * 4);      my $loadGenomeGroups = $self->_TableLoader('GenomeGroups');
1382      Trace("Beginning group data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1383            Trace("Loading from existing files.") if T(2);
1384        } else {
1385            Trace("Generating group data.") if T(2);
1386      # Loop through the genomes.      # Loop through the genomes.
1387      my $line;      my $line;
1388      for my $genomeID (keys %{$genomeHash}) {      for my $genomeID (keys %{$genomeHash}) {
# Line 1345  Line 1398 
1398          }          }
1399          close TMP;          close TMP;
1400      }      }
1401        }
1402        # Finish the load.
1403        my $retVal = $self->_FinishAll();
1404        return $retVal;
1405    }
1406    
1407    =head3 LoadSynonymData
1408    
1409    C<< my $stats = $spl->LoadSynonymData(); >>
1410    
1411    Load the synonym groups into Sprout.
1412    
1413    The following relations are loaded by this method.
1414    
1415        SynonymGroup
1416        IsSynonymGroupFor
1417    
1418    The source information for these relations is taken from the C<maps_to_id> method
1419    of the B<FIG> object. The process starts from the features, so it is possible
1420    that there will be duplicates in the SynonymGroup load file, since the relationship
1421    is one-to-many toward the features. The automatic sort on primary entity relations
1422    will fix this for us.
1423    
1424    =over 4
1425    
1426    =item RETURNS
1427    
1428    Returns a statistics object for the loads.
1429    
1430    =back
1431    
1432    =cut
1433    #: Return Type $%;
1434    sub LoadSynonymData {
1435        # Get this object instance.
1436        my ($self) = @_;
1437        # Get the FIG object.
1438        my $fig = $self->{fig};
1439        # Get the genome hash.
1440        my $genomeHash = $self->{genomes};
1441        # Create a load object for the table we're loading.
1442        my $loadSynonymGroup = $self->_TableLoader('SynonymGroup');
1443        my $loadIsSynonymGroupFor = $self->_TableLoader('IsSynonymGroupFor');
1444        if ($self->{options}->{loadOnly}) {
1445            Trace("Loading from existing files.") if T(2);
1446        } else {
1447            Trace("Generating synonym group data.") if T(2);
1448            # Loop through the genomes.
1449            for my $genomeID (sort keys %{$genomeHash}) {
1450                Trace("Processing $genomeID.") if T(3);
1451                # Get all of the features for this genome. The only method that does this is
1452                # all_features_detailed, which returns extra baggage that we discard.
1453                my $featureData = $fig->all_features_detailed($genomeID);
1454                my @fids = map { $_->[0] } @{$featureData};
1455                Trace(scalar(@fids) . " features found for genome $genomeID.") if T(3);
1456                # Loop through the feature IDs.
1457                for my $fid (@fids) {
1458                    # Get the group for this feature.
1459                    my $synonym = $fig->maps_to_id($fid);
1460                    # Only proceed if the synonym is a real group.
1461                    if ($synonym ne $fid) {
1462                        $loadSynonymGroup->Put($synonym);
1463                        $loadIsSynonymGroupFor->Put($synonym, $fid);
1464                    }
1465                }
1466            }
1467        }
1468      # Finish the load.      # Finish the load.
1469      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1470      return $retVal;      return $retVal;
1471  }  }
1472    
1473    
1474  =head2 Internal Utility Methods  =head2 Internal Utility Methods
1475    
1476  =head3 TableLoader  =head3 TableLoader
# Line 1366  Line 1487 
1487    
1488  Name of the table (relation) being loaded.  Name of the table (relation) being loaded.
1489    
1490  =item rowCount (optional)  =item ignore
1491    
1492  Estimated maximum number of rows in the table.  TRUE if the table should be ignored entirely, else FALSE.
1493    
1494  =item RETURN  =item RETURN
1495    
# Line 1380  Line 1501 
1501    
1502  sub _TableLoader {  sub _TableLoader {
1503      # Get the parameters.      # Get the parameters.
1504      my ($self, $tableName, $rowCount) = @_;      my ($self, $tableName, $ignore) = @_;
1505      # Create the load object.      # Create the load object.
1506      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $rowCount);      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $self->LoadOnly,
1507                                   $ignore);
1508      # Cache it in the loader list.      # Cache it in the loader list.
1509      push @{$self->{loaders}}, $retVal;      push @{$self->{loaders}}, $retVal;
1510      # Return it to the caller.      # Return it to the caller.
# Line 1416  Line 1538 
1538      my $retVal = Stats->new();      my $retVal = Stats->new();
1539      # Get the loader list.      # Get the loader list.
1540      my $loadList = $self->{loaders};      my $loadList = $self->{loaders};
1541        # Create a hash to hold the statistics objects, keyed on relation name.
1542        my %loaderHash = ();
1543      # 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
1544      # ignominiously. At some future point, we want to make the loads restartable.      # ignominiously. At some future point, we want to make the loads more restartable.
1545      while (my $loader = pop @{$loadList}) {      while (my $loader = pop @{$loadList}) {
1546          # Trace the fact that we're cleaning up.          # Get the relation name.
1547          my $relName = $loader->RelName;          my $relName = $loader->RelName;
1548          Trace("Finishing load for $relName.") if T(2);          # Check the ignore flag.
1549            if ($loader->Ignore) {
1550                Trace("Relation $relName not loaded.") if T(2);
1551            } else {
1552                # Here we really need to finish.
1553                Trace("Finishing $relName.") if T(2);
1554          my $stats = $loader->Finish();          my $stats = $loader->Finish();
1555                $loaderHash{$relName} = $stats;
1556            }
1557        }
1558        # Now we loop through again, actually loading the tables. We want to finish before
1559        # loading so that if something goes wrong at this point, all the load files are usable
1560        # and we don't have to redo all that work.
1561        for my $relName (sort keys %loaderHash) {
1562            # Get the statistics for this relation.
1563            my $stats = $loaderHash{$relName};
1564            # Check for a database load.
1565          if ($self->{options}->{dbLoad}) {          if ($self->{options}->{dbLoad}) {
1566              # 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.
1567              Trace("Loading relation $relName.") if T(2);              Trace("Loading relation $relName.") if T(2);

Legend:
Removed from v.1.21  
changed lines
  Added in v.1.50

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3