[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 1.51, Mon Jul 10 21:12:51 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 335  Line 370 
370              Trace("Processing PEG $peg1 for $genome.") if T(4);              Trace("Processing PEG $peg1 for $genome.") if T(4);
371              # Get a list of the coupled PEGs.              # Get a list of the coupled PEGs.
372              my @couplings = $fig->coupled_to($peg1);              my @couplings = $fig->coupled_to($peg1);
373                    Trace(scalar(@couplings) . " couplings found for $peg1.") if T(4);
374              # For each coupled PEG, we need to verify that a coupling already              # For each coupled PEG, we need to verify that a coupling already
375              # exists. If not, we have to create one.              # exists. If not, we have to create one.
376              for my $coupleData (@couplings) {              for my $coupleData (@couplings) {
377                  my ($peg2, $score) = @{$coupleData};                  my ($peg2, $score) = @{$coupleData};
378                  # Compute the coupling ID.                  # Compute the coupling ID.
379                  my $coupleID = Sprout::CouplingID($peg1, $peg2);                      my $coupleID = $self->{erdb}->CouplingID($peg1, $peg2);
380                  if (! exists $dupHash{$coupleID}) {                  if (! exists $dupHash{$coupleID}) {
381                      $loadCoupling->Add("couplingIn");                      $loadCoupling->Add("couplingIn");
382                      # 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 412 
412                          }                          }
413                      }                      }
414                      for my $evidenceID (keys %evidenceMap) {                      for my $evidenceID (keys %evidenceMap) {
415                                # Get the ID for this evidence.
416                                $pchID++;
417                          # Create the evidence record.                          # Create the evidence record.
418                          my ($peg3, $peg4, $usage) = @{$evidenceMap{$evidenceID}};                          my ($peg3, $peg4, $usage) = @{$evidenceMap{$evidenceID}};
419                          $loadPCH->Put($evidenceID, $usage);                              $loadPCH->Put($pchID, $usage);
420                          # Connect it to the coupling.                          # Connect it to the coupling.
421                          $loadIsEvidencedBy->Put($coupleID, $evidenceID);                              $loadIsEvidencedBy->Put($coupleID, $pchID);
422                          # Connect it to the features.                          # Connect it to the features.
423                          $loadUsesAsEvidence->Put($evidenceID, $peg3, 1);                              $loadUsesAsEvidence->Put($pchID, $peg3, 1);
424                          $loadUsesAsEvidence->Put($evidenceID, $peg4, 2);                              $loadUsesAsEvidence->Put($pchID, $peg4, 2);
425                            }
426                      }                      }
427                  }                  }
428              }              }
# Line 410  Line 449 
449      FeatureTranslation      FeatureTranslation
450      FeatureUpstream      FeatureUpstream
451      IsLocatedIn      IsLocatedIn
452        HasFeature
453    
454  =over 4  =over 4
455    
# Line 426  Line 466 
466      my ($self) = @_;      my ($self) = @_;
467      # Get the FIG object.      # Get the FIG object.
468      my $fig = $self->{fig};      my $fig = $self->{fig};
     # Find out if this is a limited run.  
     my $limited = $self->{options}->{limitedFeatures};  
469      # Get the table of genome IDs.      # Get the table of genome IDs.
470      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
     my $featureCount = $genomeCount * 4000;  
471      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
472      my $loadFeature = $self->_TableLoader('Feature', $featureCount);      my $loadFeature = $self->_TableLoader('Feature');
473      my $loadIsLocatedIn = $self->_TableLoader('IsLocatedIn', $featureCount);      my $loadIsLocatedIn = $self->_TableLoader('IsLocatedIn', $self->PrimaryOnly);
474      my $loadFeatureAlias = $self->_TableLoader('FeatureAlias', $featureCount * 6);      my $loadFeatureAlias = $self->_TableLoader('FeatureAlias');
475      my ($loadFeatureLink, $loadFeatureTranslation, $loadFeatureUpstream);      my $loadFeatureLink = $self->_TableLoader('FeatureLink');
476      if (! $limited) {      my $loadFeatureTranslation = $self->_TableLoader('FeatureTranslation');
477          $loadFeatureLink = $self->_TableLoader('FeatureLink', $featureCount * 10);      my $loadFeatureUpstream = $self->_TableLoader('FeatureUpstream');
478          $loadFeatureTranslation = $self->_TableLoader('FeatureTranslation', $featureCount);      my $loadHasFeature = $self->_TableLoader('HasFeature');
         $loadFeatureUpstream = $self->_TableLoader('FeatureUpstream', $featureCount);  
     }  
479      # 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
480      # locations.      # locations.
481      my $chunkSize = $self->{sprout}->MaxSegment();      my $chunkSize = $self->{sprout}->MaxSegment();
482      Trace("Beginning feature data load.") if T(2);      if ($self->{options}->{loadOnly}) {
483            Trace("Loading from existing files.") if T(2);
484        } else {
485            Trace("Generating feature data.") if T(2);
486      # Now we loop through the genomes, generating the data for each one.      # Now we loop through the genomes, generating the data for each one.
487      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
488          Trace("Loading features for genome $genomeID.") if T(3);          Trace("Loading features for genome $genomeID.") if T(3);
# Line 459  Line 496 
496              my ($featureID, $locations, undef, $type) = @{$featureData};              my ($featureID, $locations, undef, $type) = @{$featureData};
497              # Create the feature record.              # Create the feature record.
498              $loadFeature->Put($featureID, 1, $type);              $loadFeature->Put($featureID, 1, $type);
499                    # Link it to the parent genome.
500                    $loadHasFeature->Put($genomeID, $featureID, $type);
501              # Create the aliases.              # Create the aliases.
502              for my $alias ($fig->feature_aliases($featureID)) {              for my $alias ($fig->feature_aliases($featureID)) {
503                  $loadFeatureAlias->Put($featureID, $alias);                  $loadFeatureAlias->Put($featureID, $alias);
504              }              }
             # The next stuff is for a full load only.  
             if (! $limited) {  
505                  # Get the links.                  # Get the links.
506                  my @links = $fig->fid_links($featureID);                  my @links = $fig->fid_links($featureID);
507                  for my $link (@links) {                  for my $link (@links) {
# Line 483  Line 520 
520                          $loadFeatureUpstream->Put($featureID, $upstream);                          $loadFeatureUpstream->Put($featureID, $upstream);
521                      }                      }
522                  }                  }
             }  
523              # 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
524              # 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
525              # 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 548 
548              }              }
549          }          }
550      }      }
551        }
552      # Finish the loads.      # Finish the loads.
553      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
554      return $retVal;      return $retVal;
# Line 548  Line 585 
585      my $fig = $self->{fig};      my $fig = $self->{fig};
586      # Get the table of genome IDs.      # Get the table of genome IDs.
587      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
     my $featureCount = $genomeCount * 4000;  
588      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
589      my $loadIsBidirectionalBestHitOf = $self->_TableLoader('IsBidirectionalBestHitOf',      my $loadIsBidirectionalBestHitOf = $self->_TableLoader('IsBidirectionalBestHitOf');
590                                                             $featureCount * $genomeCount);      if ($self->{options}->{loadOnly}) {
591      Trace("Beginning BBH load.") if T(2);          Trace("Loading from existing files.") if T(2);
592        } else {
593            Trace("Generating BBH data.") if T(2);
594      # Now we loop through the genomes, generating the data for each one.      # Now we loop through the genomes, generating the data for each one.
595      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
596          $loadIsBidirectionalBestHitOf->Add("genomeIn");          $loadIsBidirectionalBestHitOf->Add("genomeIn");
# Line 579  Line 616 
616              }              }
617          }          }
618      }      }
619        }
620      # Finish the loads.      # Finish the loads.
621      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
622      return $retVal;      return $retVal;
# Line 599  Line 637 
637  The following relations are loaded by this method.  The following relations are loaded by this method.
638    
639      Subsystem      Subsystem
640        SubsystemClass
641      Role      Role
642      RoleEC      RoleEC
643      SSCell      SSCell
# Line 639  Line 678 
678      # Get the subsystem hash. This lists the subsystems we'll process.      # Get the subsystem hash. This lists the subsystems we'll process.
679      my $subsysHash = $self->{subsystems};      my $subsysHash = $self->{subsystems};
680      my @subsysIDs = sort keys %{$subsysHash};      my @subsysIDs = sort keys %{$subsysHash};
     my $subsysCount = @subsysIDs;  
     my $genomeCount = (keys %{$genomeHash});  
     my $featureCount = $genomeCount * 4000;  
681      # Get the map list.      # Get the map list.
682      my @maps = $fig->all_maps;      my @maps = $fig->all_maps;
     my $mapCount = @maps;  
683      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
684      my $loadDiagram = $self->_TableLoader('Diagram', $mapCount);      my $loadDiagram = $self->_TableLoader('Diagram', $self->PrimaryOnly);
685      my $loadRoleOccursIn = $self->_TableLoader('RoleOccursIn', $featureCount * 6);      my $loadRoleOccursIn = $self->_TableLoader('RoleOccursIn', $self->PrimaryOnly);
686      my $loadSubsystem = $self->_TableLoader('Subsystem', $subsysCount);      my $loadSubsystem = $self->_TableLoader('Subsystem');
687      my $loadRole = $self->_TableLoader('Role', $featureCount * 6);      my $loadRole = $self->_TableLoader('Role', $self->PrimaryOnly);
688      my $loadRoleEC = $self->_TableLoader('RoleEC', $featureCount * 6);      my $loadRoleEC = $self->_TableLoader('RoleEC', $self->PrimaryOnly);
689      my $loadCatalyzes = $self->_TableLoader('Catalyzes', $genomeCount * $featureCount);      my $loadCatalyzes = $self->_TableLoader('Catalyzes', $self->PrimaryOnly);
690      my $loadSSCell = $self->_TableLoader('SSCell', $featureCount * $genomeCount);      my $loadSSCell = $self->_TableLoader('SSCell', $self->PrimaryOnly);
691      my $loadContainsFeature = $self->_TableLoader('ContainsFeature', $featureCount * $subsysCount);      my $loadContainsFeature = $self->_TableLoader('ContainsFeature', $self->PrimaryOnly);
692      my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf', $featureCount * $genomeCount);      my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf', $self->PrimaryOnly);
693      my $loadIsRoleOf = $self->_TableLoader('IsRoleOf', $featureCount * $genomeCount);      my $loadIsRoleOf = $self->_TableLoader('IsRoleOf', $self->PrimaryOnly);
694      my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem', $featureCount * 6);      my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem', $self->PrimaryOnly);
695      my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn', $subsysCount * $genomeCount);      my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn', $self->PrimaryOnly);
696      my $loadHasSSCell = $self->_TableLoader('HasSSCell', $featureCount * $genomeCount);      my $loadHasSSCell = $self->_TableLoader('HasSSCell', $self->PrimaryOnly);
697      my $loadRoleSubset = $self->_TableLoader('RoleSubset', $subsysCount * 50);      my $loadRoleSubset = $self->_TableLoader('RoleSubset', $self->PrimaryOnly);
698      my $loadGenomeSubset = $self->_TableLoader('GenomeSubset', $subsysCount * 50);      my $loadGenomeSubset = $self->_TableLoader('GenomeSubset', $self->PrimaryOnly);
699      my $loadConsistsOfRoles = $self->_TableLoader('ConsistsOfRoles', $featureCount * $genomeCount);      my $loadConsistsOfRoles = $self->_TableLoader('ConsistsOfRoles', $self->PrimaryOnly);
700      my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes', $featureCount * $genomeCount);      my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes', $self->PrimaryOnly);
701      my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset', $subsysCount * 50);      my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset', $self->PrimaryOnly);
702      my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset', $subsysCount * 50);      my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset', $self->PrimaryOnly);
703      # Create load objects for each of the tables we're loading.      my $loadSubsystemClass = $self->_TableLoader('SubsystemClass', $self->PrimaryOnly);
704      Trace("Beginning subsystem data load.") if T(2);      if ($self->{options}->{loadOnly}) {
705            Trace("Loading from existing files.") if T(2);
706        } else {
707            Trace("Generating subsystem data.") if T(2);
708      # 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
709      # information will be used to generate the Catalyzes table.      # information will be used to generate the Catalyzes table.
710      my %ecToRoles = ();      my %ecToRoles = ();
# Line 678  Line 716 
716      my ($genomeID, $roleID);      my ($genomeID, $roleID);
717      my %roleData = ();      my %roleData = ();
718      for my $subsysID (@subsysIDs) {      for my $subsysID (@subsysIDs) {
         Trace("Creating subsystem $subsysID.") if T(3);  
         $loadSubsystem->Add("subsystemIn");  
719          # Get the subsystem object.          # Get the subsystem object.
720          my $sub = $fig->get_subsystem($subsysID);          my $sub = $fig->get_subsystem($subsysID);
721                # Only proceed if the subsystem has a spreadsheet.
722                if (! $sub->{empty_ss}) {
723                    Trace("Creating subsystem $subsysID.") if T(3);
724                    $loadSubsystem->Add("subsystemIn");
725          # Create the subsystem record.          # Create the subsystem record.
726          my $curator = $sub->get_curator();          my $curator = $sub->get_curator();
727          my $notes = $sub->get_notes();          my $notes = $sub->get_notes();
728          $loadSubsystem->Put($subsysID, $curator, $notes);          $loadSubsystem->Put($subsysID, $curator, $notes);
729                    my $class = $fig->subsystem_classification($subsysID);
730                    if ($class) {
731                        $loadSubsystemClass->Put($subsysID, $class);
732                    }
733          # 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.
734          for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {          for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
735              # Connect to this role.              # Connect to this role.
# Line 729  Line 773 
773                  # part of the spreadsheet cell ID.                  # part of the spreadsheet cell ID.
774                  for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {                  for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
775                      # Get the features in the spreadsheet cell for this genome and role.                      # Get the features in the spreadsheet cell for this genome and role.
776                      my @pegs = $sub->get_pegs_from_cell($row, $col);                              my @pegs = grep { !$fig->is_deleted_fid($_) } $sub->get_pegs_from_cell($row, $col);
777                      # Only proceed if features exist.                      # Only proceed if features exist.
778                      if (@pegs > 0) {                      if (@pegs > 0) {
779                          # Create the spreadsheet cell.                          # Create the spreadsheet cell.
# Line 750  Line 794 
794                  if ($pegCount > 0) {                  if ($pegCount > 0) {
795                      Trace("$pegCount PEGs in $cellCount cells for $genomeID.") if T(3);                      Trace("$pegCount PEGs in $cellCount cells for $genomeID.") if T(3);
796                      $loadParticipatesIn->Put($genomeID, $subsysID, $variantCode);                      $loadParticipatesIn->Put($genomeID, $subsysID, $variantCode);
                     # Partition the PEGs found into clusters.  
                     my @clusters = $fig->compute_clusters(\@pegsFound, $sub);  
797                      # Create a hash mapping PEG IDs to cluster numbers.                      # Create a hash mapping PEG IDs to cluster numbers.
798                      # We default to -1 for all of them.                      # We default to -1 for all of them.
799                      my %clusterOf = map { $_ => -1 } @pegsFound;                      my %clusterOf = map { $_ => -1 } @pegsFound;
800                                # Partition the PEGs found into clusters.
801                                my @clusters = $fig->compute_clusters([keys %clusterOf], $sub);
802                      for (my $i = 0; $i <= $#clusters; $i++) {                      for (my $i = 0; $i <= $#clusters; $i++) {
803                          my $subList = $clusters[$i];                          my $subList = $clusters[$i];
804                          for my $peg (@{$subList}) {                          for my $peg (@{$subList}) {
# Line 782  Line 826 
826              # Connect the subset to the subsystem.              # Connect the subset to the subsystem.
827              $loadHasRoleSubset->Put($subsysID, $actualID);              $loadHasRoleSubset->Put($subsysID, $actualID);
828              # Connect the subset to its roles.              # Connect the subset to its roles.
829              my @roles = $sub->get_subset($subsetID);                      my @roles = $sub->get_subsetC_roles($subsetID);
830              for my $roleID (@roles) {              for my $roleID (@roles) {
831                  $loadConsistsOfRoles->Put($actualID, $roleID);                  $loadConsistsOfRoles->Put($actualID, $roleID);
832              }              }
# Line 834  Line 878 
878              }              }
879          }          }
880      }      }
881            }
882        }
883      # Finish the load.      # Finish the load.
884      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
885      return $retVal;      return $retVal;
# Line 875  Line 921 
921      my $fig = $self->{fig};      my $fig = $self->{fig};
922      # Get the genome hash.      # Get the genome hash.
923      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
924      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
925      my $loadProperty = $self->_TableLoader('Property', $genomeCount * 1500);      my $loadProperty = $self->_TableLoader('Property');
926      my $loadHasProperty = $self->_TableLoader('HasProperty', $genomeCount * 1500);      my $loadHasProperty = $self->_TableLoader('HasProperty', $self->PrimaryOnly);
927      Trace("Beginning property data load.") if T(2);      if ($self->{options}->{loadOnly}) {
928            Trace("Loading from existing files.") if T(2);
929        } else {
930            Trace("Generating property data.") if T(2);
931      # Create a hash for storing property IDs.      # Create a hash for storing property IDs.
932      my %propertyKeys = ();      my %propertyKeys = ();
933      my $nextID = 1;      my $nextID = 1;
934      # Loop through the genomes.      # Loop through the genomes.
935      for my $genomeID (keys %{$genomeHash}) {      for my $genomeID (keys %{$genomeHash}) {
936          $loadProperty->Add("genomeIn");          $loadProperty->Add("genomeIn");
937                Trace("Generating properties for $genomeID.") if T(3);
938          # 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
939          # tuples returned by "all_features_detailed". We use "all_features_detailed"          # tuples returned by "all_features_detailed". We use "all_features_detailed"
940          # rather than "all_features" because we want all features regardless of type.          # rather than "all_features" because we want all features regardless of type.
941          my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};          my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};
942                my $featureCount = 0;
943                my $propertyCount = 0;
944          # Loop through the features, creating HasProperty records.          # Loop through the features, creating HasProperty records.
945          for my $fid (@features) {          for my $fid (@features) {
             $loadProperty->Add("featureIn");  
946              # 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
947              # to insure we do not get any genome attributes.              # to insure we do not get any genome attributes.
948              my @attributeList = $fig->get_attributes($fid, '', '', '');              my @attributeList = $fig->get_attributes($fid, '', '', '');
949                    if (scalar @attributeList) {
950                        $featureCount++;
951                    }
952              # Loop through the attributes.              # Loop through the attributes.
953              for my $tuple (@attributeList) {              for my $tuple (@attributeList) {
954                        $propertyCount++;
955                  # Get this attribute value's data. Note that we throw away the FID,                  # Get this attribute value's data. Note that we throw away the FID,
956                  # since it will always be the same as the value if "$fid".                  # since it will always be the same as the value if "$fid".
957                  my (undef, $key, $value, $url) = @{$tuple};                  my (undef, $key, $value, $url) = @{$tuple};
# Line 919  Line 973 
973                  $loadHasProperty->Put($fid, $propertyID, $url);                  $loadHasProperty->Put($fid, $propertyID, $url);
974              }              }
975          }          }
976                # Update the statistics.
977                Trace("$propertyCount attributes processed for $featureCount features.") if T(3);
978                $loadHasProperty->Add("featuresIn", $featureCount);
979                $loadHasProperty->Add("propertiesIn", $propertyCount);
980            }
981      }      }
982      # Finish the load.      # Finish the load.
983      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
# Line 959  Line 1018 
1018      my $fig = $self->{fig};      my $fig = $self->{fig};
1019      # Get the genome hash.      # Get the genome hash.
1020      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1021      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1022      my $loadAnnotation = $self->_TableLoader('Annotation', $genomeCount * 4000);      my $loadAnnotation = $self->_TableLoader('Annotation');
1023      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation', $genomeCount * 4000);      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation', $self->PrimaryOnly);
1024      my $loadSproutUser = $self->_TableLoader('SproutUser', 100);      my $loadSproutUser = $self->_TableLoader('SproutUser', $self->PrimaryOnly);
1025      my $loadUserAccess = $self->_TableLoader('UserAccess', 1000);      my $loadUserAccess = $self->_TableLoader('UserAccess', $self->PrimaryOnly);
1026      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation', $genomeCount * 4000);      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation', $self->PrimaryOnly);
1027      Trace("Beginning annotation data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1028            Trace("Loading from existing files.") if T(2);
1029        } else {
1030            Trace("Generating annotation data.") if T(2);
1031      # 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
1032      # user records.      # user records.
1033      my %users = ( FIG => 1, master => 1 );      my %users = ( FIG => 1, master => 1 );
# Line 980  Line 1041 
1041      # Loop through the genomes.      # Loop through the genomes.
1042      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
1043          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);  
1044              # 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
1045              # from showing up for a single PEG's annotations.              # from showing up for a single PEG's annotations.
1046              my %seenTimestamps = ();              my %seenTimestamps = ();
1047              # Check for a functional assignment.              # Get the genome's annotations.
1048              my $func = $fig->function_of($peg);              my @annotations = $fig->read_all_annotations($genomeID);
1049              if ($func) {              Trace("Processing annotations.") if T(2);
1050                  # If this is NOT a hypothetical assignment, we create an              for my $tuple (@annotations) {
1051                  # assignment annotation for it.                  # Get the annotation tuple.
1052                  if (! FIG::hypo($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};  
1053                  # Here we fix up the annotation text. "\r" is removed,                  # Here we fix up the annotation text. "\r" is removed,
1054                  # and "\t" and "\n" are escaped. Note we use the "s"                  # and "\t" and "\n" are escaped. Note we use the "gs"
1055                  # modifier so that new-lines inside the text do not                  # modifier so that new-lines inside the text do not
1056                  # stop the substitution search.                  # stop the substitution search.
1057                  $text =~ s/\r//gs;                  $text =~ s/\r//gs;
# Line 1019  Line 1064 
1064                      # 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
1065                      # the key is unique.                      # the key is unique.
1066                      my $keyStamp = $timestamp;                      my $keyStamp = $timestamp;
1067                      while ($seenTimestamps{$keyStamp}) {                      while ($seenTimestamps{"$peg:$keyStamp"}) {
1068                          $keyStamp++;                          $keyStamp++;
1069                      }                      }
                     $seenTimestamps{$keyStamp} = 1;  
1070                      my $annotationID = "$peg:$keyStamp";                      my $annotationID = "$peg:$keyStamp";
1071                        $seenTimestamps{$annotationID} = 1;
1072                      # Insure the user exists.                      # Insure the user exists.
1073                      if (! $users{$user}) {                      if (! $users{$user}) {
1074                          $loadSproutUser->Put($user, "SEED user");                          $loadSproutUser->Put($user, "SEED user");
# Line 1081  Line 1126 
1126      my $fig = $self->{fig};      my $fig = $self->{fig};
1127      # Get the genome hash.      # Get the genome hash.
1128      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1129      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1130      my $loadComesFrom = $self->_TableLoader('ComesFrom', $genomeCount * 4);      my $loadComesFrom = $self->_TableLoader('ComesFrom', $self->PrimaryOnly);
1131      my $loadSource = $self->_TableLoader('Source', $genomeCount * 4);      my $loadSource = $self->_TableLoader('Source');
1132      my $loadSourceURL = $self->_TableLoader('SourceURL', $genomeCount * 8);      my $loadSourceURL = $self->_TableLoader('SourceURL');
1133      Trace("Beginning source data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1134            Trace("Loading from existing files.") if T(2);
1135        } else {
1136            Trace("Generating annotation data.") if T(2);
1137      # Create hashes to collect the Source information.      # Create hashes to collect the Source information.
1138      my %sourceURL = ();      my %sourceURL = ();
1139      my %sourceDesc = ();      my %sourceDesc = ();
# Line 1116  Line 1163 
1163      for my $sourceID (keys %sourceDesc) {      for my $sourceID (keys %sourceDesc) {
1164          $loadSource->Put($sourceID, $sourceDesc{$sourceID});          $loadSource->Put($sourceID, $sourceDesc{$sourceID});
1165      }      }
1166        }
1167      # Finish the load.      # Finish the load.
1168      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1169      return $retVal;      return $retVal;
# Line 1155  Line 1203 
1203      my $fig = $self->{fig};      my $fig = $self->{fig};
1204      # Get the genome hash.      # Get the genome hash.
1205      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1206      # 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
1207      # it the key.      # it the key.
1208      my %speciesHash = map { $fig->genus_species($_) => $_ } (keys %{$genomeHash});      my %speciesHash = map { $fig->genus_species($_) => $_ } (keys %{$genomeHash});
1209      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1210      my $loadExternalAliasFunc = $self->_TableLoader('ExternalAliasFunc', $genomeCount * 4000);      my $loadExternalAliasFunc = $self->_TableLoader('ExternalAliasFunc');
1211      my $loadExternalAliasOrg = $self->_TableLoader('ExternalAliasOrg', $genomeCount * 4000);      my $loadExternalAliasOrg = $self->_TableLoader('ExternalAliasOrg');
1212      Trace("Beginning external data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1213            Trace("Loading from existing files.") if T(2);
1214        } else {
1215            Trace("Generating external data.") if T(2);
1216      # 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.
1217      Open(\*ORGS, "<$FIG_Config::global/ext_org.table");      Open(\*ORGS, "<$FIG_Config::global/ext_org.table");
1218      my $orgLine;      my $orgLine;
# Line 1192  Line 1242 
1242              $loadExternalAliasFunc->Put(@funcFields[0,1]);              $loadExternalAliasFunc->Put(@funcFields[0,1]);
1243          }          }
1244      }      }
1245        }
1246      # Finish the load.      # Finish the load.
1247      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1248      return $retVal;      return $retVal;
# Line 1232  Line 1283 
1283      my ($self) = @_;      my ($self) = @_;
1284      # Get the FIG object.      # Get the FIG object.
1285      my $fig = $self->{fig};      my $fig = $self->{fig};
     # Get the genome hash.  
     my $genomeHash = $self->{genomes};  
     my $genomeCount = (keys %{$genomeHash});  
1286      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1287      my $loadReaction = $self->_TableLoader('Reaction', $genomeCount * 4000);      my $loadReaction = $self->_TableLoader('Reaction');
1288      my $loadReactionURL = $self->_TableLoader('ReactionURL', $genomeCount * 4000);      my $loadReactionURL = $self->_TableLoader('ReactionURL', $self->PrimaryOnly);
1289      my $loadCompound = $self->_TableLoader('Compound', $genomeCount * 4000);      my $loadCompound = $self->_TableLoader('Compound', $self->PrimaryOnly);
1290      my $loadCompoundName = $self->_TableLoader('CompoundName', $genomeCount * 8000);      my $loadCompoundName = $self->_TableLoader('CompoundName', $self->PrimaryOnly);
1291      my $loadCompoundCAS = $self->_TableLoader('CompoundCAS', $genomeCount * 4000);      my $loadCompoundCAS = $self->_TableLoader('CompoundCAS', $self->PrimaryOnly);
1292      my $loadIsAComponentOf = $self->_TableLoader('IsAComponentOf', $genomeCount * 12000);      my $loadIsAComponentOf = $self->_TableLoader('IsAComponentOf', $self->PrimaryOnly);
1293      Trace("Beginning reaction/compound data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1294            Trace("Loading from existing files.") if T(2);
1295        } else {
1296            Trace("Generating annotation data.") if T(2);
1297      # First we create the compounds.      # First we create the compounds.
1298      my @compounds = $fig->all_compounds();      my @compounds = $fig->all_compounds();
1299      for my $cid (@compounds) {      for my $cid (@compounds) {
# Line 1291  Line 1342 
1342              }              }
1343          }          }
1344      }      }
1345        }
1346      # Finish the load.      # Finish the load.
1347      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1348      return $retVal;      return $retVal;
# Line 1326  Line 1378 
1378      my $fig = $self->{fig};      my $fig = $self->{fig};
1379      # Get the genome hash.      # Get the genome hash.
1380      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1381      # Create a load object for the table we're loading.      # Create a load object for the table we're loading.
1382      my $loadGenomeGroups = $self->_TableLoader('GenomeGroups', $genomeCount * 4);      my $loadGenomeGroups = $self->_TableLoader('GenomeGroups');
1383      Trace("Beginning group data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1384            Trace("Loading from existing files.") if T(2);
1385        } else {
1386            Trace("Generating group data.") if T(2);
1387      # Loop through the genomes.      # Loop through the genomes.
1388      my $line;      my $line;
1389      for my $genomeID (keys %{$genomeHash}) {      for my $genomeID (keys %{$genomeHash}) {
# Line 1345  Line 1399 
1399          }          }
1400          close TMP;          close TMP;
1401      }      }
1402        }
1403        # Finish the load.
1404        my $retVal = $self->_FinishAll();
1405        return $retVal;
1406    }
1407    
1408    =head3 LoadSynonymData
1409    
1410    C<< my $stats = $spl->LoadSynonymData(); >>
1411    
1412    Load the synonym groups into Sprout.
1413    
1414    The following relations are loaded by this method.
1415    
1416        SynonymGroup
1417        IsSynonymGroupFor
1418    
1419    The source information for these relations is taken from the C<maps_to_id> method
1420    of the B<FIG> object. The process starts from the features, so it is possible
1421    that there will be duplicates in the SynonymGroup load file, since the relationship
1422    is one-to-many toward the features. The automatic sort on primary entity relations
1423    will fix this for us.
1424    
1425    =over 4
1426    
1427    =item RETURNS
1428    
1429    Returns a statistics object for the loads.
1430    
1431    =back
1432    
1433    =cut
1434    #: Return Type $%;
1435    sub LoadSynonymData {
1436        # Get this object instance.
1437        my ($self) = @_;
1438        # Get the FIG object.
1439        my $fig = $self->{fig};
1440        # Get the genome hash.
1441        my $genomeHash = $self->{genomes};
1442        # Create a load object for the table we're loading.
1443        my $loadSynonymGroup = $self->_TableLoader('SynonymGroup');
1444        my $loadIsSynonymGroupFor = $self->_TableLoader('IsSynonymGroupFor');
1445        if ($self->{options}->{loadOnly}) {
1446            Trace("Loading from existing files.") if T(2);
1447        } else {
1448            Trace("Generating synonym group data.") if T(2);
1449            # Loop through the genomes.
1450            for my $genomeID (sort keys %{$genomeHash}) {
1451                Trace("Processing $genomeID.") if T(3);
1452                # Get all of the features for this genome. The only method that does this is
1453                # all_features_detailed, which returns extra baggage that we discard.
1454                my $featureData = $fig->all_features_detailed($genomeID);
1455                my @fids = map { $_->[0] } @{$featureData};
1456                Trace(scalar(@fids) . " features found for genome $genomeID.") if T(3);
1457                # Loop through the feature IDs.
1458                for my $fid (@fids) {
1459                    # Get the group for this feature.
1460                    my $synonym = $fig->maps_to_id($fid);
1461                    # Only proceed if the synonym is a real group.
1462                    if ($synonym ne $fid) {
1463                        $loadSynonymGroup->Put($synonym);
1464                        $loadIsSynonymGroupFor->Put($synonym, $fid);
1465                    }
1466                }
1467            }
1468        }
1469      # Finish the load.      # Finish the load.
1470      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1471      return $retVal;      return $retVal;
1472  }  }
1473    
1474    
1475  =head2 Internal Utility Methods  =head2 Internal Utility Methods
1476    
1477  =head3 TableLoader  =head3 TableLoader
# Line 1366  Line 1488 
1488    
1489  Name of the table (relation) being loaded.  Name of the table (relation) being loaded.
1490    
1491  =item rowCount (optional)  =item ignore
1492    
1493  Estimated maximum number of rows in the table.  TRUE if the table should be ignored entirely, else FALSE.
1494    
1495  =item RETURN  =item RETURN
1496    
# Line 1380  Line 1502 
1502    
1503  sub _TableLoader {  sub _TableLoader {
1504      # Get the parameters.      # Get the parameters.
1505      my ($self, $tableName, $rowCount) = @_;      my ($self, $tableName, $ignore) = @_;
1506      # Create the load object.      # Create the load object.
1507      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $rowCount);      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $self->LoadOnly,
1508                                   $ignore);
1509      # Cache it in the loader list.      # Cache it in the loader list.
1510      push @{$self->{loaders}}, $retVal;      push @{$self->{loaders}}, $retVal;
1511      # Return it to the caller.      # Return it to the caller.
# Line 1416  Line 1539 
1539      my $retVal = Stats->new();      my $retVal = Stats->new();
1540      # Get the loader list.      # Get the loader list.
1541      my $loadList = $self->{loaders};      my $loadList = $self->{loaders};
1542        # Create a hash to hold the statistics objects, keyed on relation name.
1543        my %loaderHash = ();
1544      # 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
1545      # 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.
1546      while (my $loader = pop @{$loadList}) {      while (my $loader = pop @{$loadList}) {
1547          # Trace the fact that we're cleaning up.          # Get the relation name.
1548          my $relName = $loader->RelName;          my $relName = $loader->RelName;
1549          Trace("Finishing load for $relName.") if T(2);          # Check the ignore flag.
1550            if ($loader->Ignore) {
1551                Trace("Relation $relName not loaded.") if T(2);
1552            } else {
1553                # Here we really need to finish.
1554                Trace("Finishing $relName.") if T(2);
1555          my $stats = $loader->Finish();          my $stats = $loader->Finish();
1556                $loaderHash{$relName} = $stats;
1557            }
1558        }
1559        # Now we loop through again, actually loading the tables. We want to finish before
1560        # loading so that if something goes wrong at this point, all the load files are usable
1561        # and we don't have to redo all that work.
1562        for my $relName (sort keys %loaderHash) {
1563            # Get the statistics for this relation.
1564            my $stats = $loaderHash{$relName};
1565            # Check for a database load.
1566          if ($self->{options}->{dbLoad}) {          if ($self->{options}->{dbLoad}) {
1567              # 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.
1568              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.1.51

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3