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

Diff of /Sprout/SproutLoad.pm

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

revision 1.23, Fri Jan 13 06:59:49 2006 UTC revision 1.40, Thu Jun 8 15:37:32 2006 UTC
# Line 30  Line 30 
30      $stats->Accumulate($spl->LoadFeatureData());      $stats->Accumulate($spl->LoadFeatureData());
31      print $stats->Show();      print $stats->Show();
32    
 This module makes use of the internal Sprout property C<_erdb>.  
   
33  It is worth noting that the FIG object does not need to be a real one. Any object  It is worth noting that the FIG object does not need to be a real one. Any object
34  that implements the FIG methods for data retrieval could be used. So, for example,  that implements the FIG methods for data retrieval could be used. So, for example,
35  this object could be used to copy data from one Sprout database to another, or  this object could be used to copy data from one Sprout database to another, or
# Line 80  Line 78 
78  =item subsysFile  =item subsysFile
79    
80  Either the name of the file containing the list of trusted subsystems or a reference  Either the name of the file containing the list of trusted subsystems or a reference
81  to a list of subsystem names. If nothing is specified, all known subsystems will be  to a list of subsystem names. If nothing is specified, all NMPDR subsystems will be
82  considered trusted. Only subsystem data related to the trusted subsystems is loaded.  considered trusted. (A subsystem is considered NMPDR if it has a file named C<NMPDR>
83    in its data directory.) Only subsystem data related to the trusted subsystems is loaded.
84    
85  =item options  =item options
86    
# Line 94  Line 93 
93  sub new {  sub new {
94      # Get the parameters.      # Get the parameters.
95      my ($class, $sprout, $fig, $genomeFile, $subsysFile, $options) = @_;      my ($class, $sprout, $fig, $genomeFile, $subsysFile, $options) = @_;
96      # Load the list of genomes into a hash.      # Create the genome hash.
97      my %genomes;      my %genomes = ();
98        # We only need it if load-only is NOT specified.
99        if (! $options->{loadOnly}) {
100      if (! defined($genomeFile) || $genomeFile eq '') {      if (! defined($genomeFile) || $genomeFile eq '') {
101          # Here we want all the complete genomes and an access code of 1.          # Here we want all the complete genomes and an access code of 1.
102          my @genomeList = $fig->genomes(1);          my @genomeList = $fig->genomes(1);
# Line 129  Line 130 
130              Confess("Invalid genome parameter ($type) in SproutLoad constructor.");              Confess("Invalid genome parameter ($type) in SproutLoad constructor.");
131          }          }
132      }      }
133        }
134      # Load the list of trusted subsystems.      # Load the list of trusted subsystems.
135      my %subsystems = ();      my %subsystems = ();
136        # We only need it if load-only is NOT specified.
137        if (! $options->{loadOnly}) {
138      if (! defined $subsysFile || $subsysFile eq '') {      if (! defined $subsysFile || $subsysFile eq '') {
139          # Here we want all the subsystems.              # Here we want all the NMPDR subsystems. First we get the whole list.
140          %subsystems = map { $_ => 1 } $fig->all_subsystems();              my @subs = $fig->all_subsystems();
141                # Loop through, checking for the NMPDR file.
142                for my $sub (@subs) {
143                    if (-e "$FIG_Config::data/Subsystems/$sub/NMPDR") {
144                        $subsystems{$sub} = 1;
145                    }
146                }
147      } else {      } else {
148          my $type = ref $subsysFile;          my $type = ref $subsysFile;
149          if ($type eq 'ARRAY') {          if ($type eq 'ARRAY') {
# Line 153  Line 163 
163              Confess("Invalid subsystem parameter in SproutLoad constructor.");              Confess("Invalid subsystem parameter in SproutLoad constructor.");
164          }          }
165      }      }
166        }
167      # Get the data directory from the Sprout object.      # Get the data directory from the Sprout object.
168      my ($directory) = $sprout->LoadInfo();      my ($directory) = $sprout->LoadInfo();
169      # Create the Sprout load object.      # Create the Sprout load object.
# Line 162  Line 173 
173                    subsystems => \%subsystems,                    subsystems => \%subsystems,
174                    sprout => $sprout,                    sprout => $sprout,
175                    loadDirectory => $directory,                    loadDirectory => $directory,
176                    erdb => $sprout->{_erdb},                    erdb => $sprout,
177                    loaders => [],                    loaders => [],
178                    options => $options                    options => $options
179                   };                   };
# Line 184  Line 195 
195      return $self->{options}->{loadOnly};      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 211  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 231  Line 247 
247      my $genomeCount = (keys %{$genomeHash});      my $genomeCount = (keys %{$genomeHash});
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');      my $loadGenome = $self->_TableLoader('Genome');
250      my $loadHasContig = $self->_TableLoader('HasContig');      my $loadHasContig = $self->_TableLoader('HasContig', $self->PrimaryOnly);
251      my $loadContig = $self->_TableLoader('Contig');      my $loadContig = $self->_TableLoader('Contig', $self->PrimaryOnly);
252      my $loadIsMadeUpOf = $self->_TableLoader('IsMadeUpOf');      my $loadIsMadeUpOf = $self->_TableLoader('IsMadeUpOf', $self->PrimaryOnly);
253      my $loadSequence = $self->_TableLoader('Sequence');      my $loadSequence = $self->_TableLoader('Sequence', $self->PrimaryOnly);
254      if ($self->{options}->{loadOnly}) {      if ($self->{options}->{loadOnly}) {
255          Trace("Loading from existing files.") if T(2);          Trace("Loading from existing files.") if T(2);
256      } else {      } else {
# Line 245  Line 261 
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 329  Line 344 
344      my $featureCount = $genomeCount * 4000;      my $featureCount = $genomeCount * 4000;
345      # Start the loads.      # Start the loads.
346      my $loadCoupling = $self->_TableLoader('Coupling');      my $loadCoupling = $self->_TableLoader('Coupling');
347      my $loadIsEvidencedBy = $self->_TableLoader('IsEvidencedBy');      my $loadIsEvidencedBy = $self->_TableLoader('IsEvidencedBy', $self->PrimaryOnly);
348      my $loadPCH = $self->_TableLoader('PCH');      my $loadPCH = $self->_TableLoader('PCH', $self->PrimaryOnly);
349      my $loadParticipatesInCoupling = $self->_TableLoader('ParticipatesInCoupling');      my $loadParticipatesInCoupling = $self->_TableLoader('ParticipatesInCoupling', $self->PrimaryOnly);
350      my $loadUsesAsEvidence = $self->_TableLoader('UsesAsEvidence');      my $loadUsesAsEvidence = $self->_TableLoader('UsesAsEvidence', $self->PrimaryOnly);
351      if ($self->{options}->{loadOnly}) {      if ($self->{options}->{loadOnly}) {
352          Trace("Loading from existing files.") if T(2);          Trace("Loading from existing files.") if T(2);
353      } else {      } else {
# Line 431  Line 446 
446      FeatureTranslation      FeatureTranslation
447      FeatureUpstream      FeatureUpstream
448      IsLocatedIn      IsLocatedIn
449        HasFeature
450    
451  =over 4  =over 4
452    
# Line 451  Line 467 
467      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
468      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
469      my $loadFeature = $self->_TableLoader('Feature');      my $loadFeature = $self->_TableLoader('Feature');
470      my $loadIsLocatedIn = $self->_TableLoader('IsLocatedIn');      my $loadIsLocatedIn = $self->_TableLoader('IsLocatedIn', $self->PrimaryOnly);
471      my $loadFeatureAlias = $self->_TableLoader('FeatureAlias');      my $loadFeatureAlias = $self->_TableLoader('FeatureAlias');
472      my $loadFeatureLink = $self->_TableLoader('FeatureLink');      my $loadFeatureLink = $self->_TableLoader('FeatureLink');
473      my $loadFeatureTranslation = $self->_TableLoader('FeatureTranslation');      my $loadFeatureTranslation = $self->_TableLoader('FeatureTranslation');
474      my $loadFeatureUpstream = $self->_TableLoader('FeatureUpstream');      my $loadFeatureUpstream = $self->_TableLoader('FeatureUpstream');
475        my $loadHasFeature = $self->_TableLoader('HasFeature');
476      # Get the maximum sequence size. We need this later for splitting up the      # Get the maximum sequence size. We need this later for splitting up the
477      # locations.      # locations.
478      my $chunkSize = $self->{sprout}->MaxSegment();      my $chunkSize = $self->{sprout}->MaxSegment();
# Line 476  Line 493 
493                  my ($featureID, $locations, undef, $type) = @{$featureData};                  my ($featureID, $locations, undef, $type) = @{$featureData};
494                  # Create the feature record.                  # Create the feature record.
495                  $loadFeature->Put($featureID, 1, $type);                  $loadFeature->Put($featureID, 1, $type);
496                    # Link it to the parent genome.
497                    $loadHasFeature->Put($genomeID, $featureID, $type);
498                  # Create the aliases.                  # Create the aliases.
499                  for my $alias ($fig->feature_aliases($featureID)) {                  for my $alias ($fig->feature_aliases($featureID)) {
500                      $loadFeatureAlias->Put($featureID, $alias);                      $loadFeatureAlias->Put($featureID, $alias);
# Line 658  Line 677 
677      # Get the map list.      # Get the map list.
678      my @maps = $fig->all_maps;      my @maps = $fig->all_maps;
679      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
680      my $loadDiagram = $self->_TableLoader('Diagram');      my $loadDiagram = $self->_TableLoader('Diagram', $self->PrimaryOnly);
681      my $loadRoleOccursIn = $self->_TableLoader('RoleOccursIn');      my $loadRoleOccursIn = $self->_TableLoader('RoleOccursIn', $self->PrimaryOnly);
682      my $loadSubsystem = $self->_TableLoader('Subsystem');      my $loadSubsystem = $self->_TableLoader('Subsystem');
683      my $loadRole = $self->_TableLoader('Role');      my $loadRole = $self->_TableLoader('Role', $self->PrimaryOnly);
684      my $loadRoleEC = $self->_TableLoader('RoleEC');      my $loadRoleEC = $self->_TableLoader('RoleEC', $self->PrimaryOnly);
685      my $loadCatalyzes = $self->_TableLoader('Catalyzes');      my $loadCatalyzes = $self->_TableLoader('Catalyzes', $self->PrimaryOnly);
686      my $loadSSCell = $self->_TableLoader('SSCell');      my $loadSSCell = $self->_TableLoader('SSCell', $self->PrimaryOnly);
687      my $loadContainsFeature = $self->_TableLoader('ContainsFeature');      my $loadContainsFeature = $self->_TableLoader('ContainsFeature', $self->PrimaryOnly);
688      my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf');      my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf', $self->PrimaryOnly);
689      my $loadIsRoleOf = $self->_TableLoader('IsRoleOf');      my $loadIsRoleOf = $self->_TableLoader('IsRoleOf', $self->PrimaryOnly);
690      my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem');      my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem', $self->PrimaryOnly);
691      my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn');      my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn', $self->PrimaryOnly);
692      my $loadHasSSCell = $self->_TableLoader('HasSSCell');      my $loadHasSSCell = $self->_TableLoader('HasSSCell', $self->PrimaryOnly);
693      my $loadRoleSubset = $self->_TableLoader('RoleSubset');      my $loadRoleSubset = $self->_TableLoader('RoleSubset', $self->PrimaryOnly);
694      my $loadGenomeSubset = $self->_TableLoader('GenomeSubset');      my $loadGenomeSubset = $self->_TableLoader('GenomeSubset', $self->PrimaryOnly);
695      my $loadConsistsOfRoles = $self->_TableLoader('ConsistsOfRoles');      my $loadConsistsOfRoles = $self->_TableLoader('ConsistsOfRoles', $self->PrimaryOnly);
696      my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes');      my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes', $self->PrimaryOnly);
697      my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset');      my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset', $self->PrimaryOnly);
698      my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset');      my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset', $self->PrimaryOnly);
699      if ($self->{options}->{loadOnly}) {      if ($self->{options}->{loadOnly}) {
700          Trace("Loading from existing files.") if T(2);          Trace("Loading from existing files.") if T(2);
701      } else {      } else {
# Line 692  Line 711 
711          my ($genomeID, $roleID);          my ($genomeID, $roleID);
712          my %roleData = ();          my %roleData = ();
713          for my $subsysID (@subsysIDs) {          for my $subsysID (@subsysIDs) {
             Trace("Creating subsystem $subsysID.") if T(3);  
             $loadSubsystem->Add("subsystemIn");  
714              # Get the subsystem object.              # Get the subsystem object.
715              my $sub = $fig->get_subsystem($subsysID);              my $sub = $fig->get_subsystem($subsysID);
716                # Only proceed if the subsystem has a spreadsheet.
717                if (! $sub->{empty_ss}) {
718                    Trace("Creating subsystem $subsysID.") if T(3);
719                    $loadSubsystem->Add("subsystemIn");
720              # Create the subsystem record.              # Create the subsystem record.
721              my $curator = $sub->get_curator();              my $curator = $sub->get_curator();
722              my $notes = $sub->get_notes();              my $notes = $sub->get_notes();
# Line 743  Line 764 
764                      # part of the spreadsheet cell ID.                      # part of the spreadsheet cell ID.
765                      for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {                      for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
766                          # Get the features in the spreadsheet cell for this genome and role.                          # Get the features in the spreadsheet cell for this genome and role.
767                          my @pegs = $sub->get_pegs_from_cell($row, $col);                              my @pegs = grep { !$fig->is_deleted_fid($_) } $sub->get_pegs_from_cell($row, $col);
768                          # Only proceed if features exist.                          # Only proceed if features exist.
769                          if (@pegs > 0) {                          if (@pegs > 0) {
770                              # Create the spreadsheet cell.                              # Create the spreadsheet cell.
# Line 796  Line 817 
817                  # Connect the subset to the subsystem.                  # Connect the subset to the subsystem.
818                  $loadHasRoleSubset->Put($subsysID, $actualID);                  $loadHasRoleSubset->Put($subsysID, $actualID);
819                  # Connect the subset to its roles.                  # Connect the subset to its roles.
820                  my @roles = $sub->get_subset($subsetID);                      my @roles = $sub->get_subsetC_roles($subsetID);
821                  for my $roleID (@roles) {                  for my $roleID (@roles) {
822                      $loadConsistsOfRoles->Put($actualID, $roleID);                      $loadConsistsOfRoles->Put($actualID, $roleID);
823                  }                  }
# Line 849  Line 870 
870              }              }
871          }          }
872      }      }
873        }
874      # Finish the load.      # Finish the load.
875      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
876      return $retVal;      return $retVal;
# Line 892  Line 914 
914      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
915      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
916      my $loadProperty = $self->_TableLoader('Property');      my $loadProperty = $self->_TableLoader('Property');
917      my $loadHasProperty = $self->_TableLoader('HasProperty');      my $loadHasProperty = $self->_TableLoader('HasProperty', $self->PrimaryOnly);
918      if ($self->{options}->{loadOnly}) {      if ($self->{options}->{loadOnly}) {
919          Trace("Loading from existing files.") if T(2);          Trace("Loading from existing files.") if T(2);
920      } else {      } else {
# Line 903  Line 925 
925          # Loop through the genomes.          # Loop through the genomes.
926          for my $genomeID (keys %{$genomeHash}) {          for my $genomeID (keys %{$genomeHash}) {
927              $loadProperty->Add("genomeIn");              $loadProperty->Add("genomeIn");
928                Trace("Generating properties for $genomeID.") if T(3);
929              # Get the genome's features. The feature ID is the first field in the              # Get the genome's features. The feature ID is the first field in the
930              # tuples returned by "all_features_detailed". We use "all_features_detailed"              # tuples returned by "all_features_detailed". We use "all_features_detailed"
931              # rather than "all_features" because we want all features regardless of type.              # rather than "all_features" because we want all features regardless of type.
932              my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};              my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};
933                my $featureCount = 0;
934                my $propertyCount = 0;
935              # Loop through the features, creating HasProperty records.              # Loop through the features, creating HasProperty records.
936              for my $fid (@features) {              for my $fid (@features) {
                 $loadProperty->Add("featureIn");  
937                  # Get all attributes for this feature. We do this one feature at a time                  # Get all attributes for this feature. We do this one feature at a time
938                  # to insure we do not get any genome attributes.                  # to insure we do not get any genome attributes.
939                  my @attributeList = $fig->get_attributes($fid, '', '', '');                  my @attributeList = $fig->get_attributes($fid, '', '', '');
940                    if (scalar @attributeList) {
941                        $featureCount++;
942                    }
943                  # Loop through the attributes.                  # Loop through the attributes.
944                  for my $tuple (@attributeList) {                  for my $tuple (@attributeList) {
945                        $propertyCount++;
946                      # Get this attribute value's data. Note that we throw away the FID,                      # Get this attribute value's data. Note that we throw away the FID,
947                      # since it will always be the same as the value if "$fid".                      # since it will always be the same as the value if "$fid".
948                      my (undef, $key, $value, $url) = @{$tuple};                      my (undef, $key, $value, $url) = @{$tuple};
# Line 936  Line 964 
964                      $loadHasProperty->Put($fid, $propertyID, $url);                      $loadHasProperty->Put($fid, $propertyID, $url);
965                  }                  }
966              }              }
967                # Update the statistics.
968                Trace("$propertyCount attributes processed for $featureCount features.") if T(3);
969                $loadHasProperty->Add("featuresIn", $featureCount);
970                $loadHasProperty->Add("propertiesIn", $propertyCount);
971          }          }
972      }      }
973      # Finish the load.      # Finish the load.
# Line 979  Line 1011 
1011      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
1012      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1013      my $loadAnnotation = $self->_TableLoader('Annotation');      my $loadAnnotation = $self->_TableLoader('Annotation');
1014      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation');      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation', $self->PrimaryOnly);
1015      my $loadSproutUser = $self->_TableLoader('SproutUser');      my $loadSproutUser = $self->_TableLoader('SproutUser', $self->PrimaryOnly);
1016      my $loadUserAccess = $self->_TableLoader('UserAccess');      my $loadUserAccess = $self->_TableLoader('UserAccess', $self->PrimaryOnly);
1017      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation');      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation', $self->PrimaryOnly);
1018      if ($self->{options}->{loadOnly}) {      if ($self->{options}->{loadOnly}) {
1019          Trace("Loading from existing files.") if T(2);          Trace("Loading from existing files.") if T(2);
1020      } else {      } else {
# Line 1000  Line 1032 
1032          # Loop through the genomes.          # Loop through the genomes.
1033          for my $genomeID (sort keys %{$genomeHash}) {          for my $genomeID (sort keys %{$genomeHash}) {
1034              Trace("Processing $genomeID.") if T(3);              Trace("Processing $genomeID.") if T(3);
             # Get the genome's PEGs.  
             my @pegs = $fig->pegs_of($genomeID);  
             for my $peg (@pegs) {  
                 Trace("Processing $peg.") if T(4);  
1035                  # Create a hash of timestamps. We use this to prevent duplicate time stamps                  # Create a hash of timestamps. We use this to prevent duplicate time stamps
1036                  # from showing up for a single PEG's annotations.                  # from showing up for a single PEG's annotations.
1037                  my %seenTimestamps = ();                  my %seenTimestamps = ();
1038                  # Loop through the annotations.              # Get the genome's annotations.
1039                  for my $tuple ($fig->feature_annotations($peg, "raw")) {              my @annotations = $fig->read_all_annotations($genomeID);
1040                      my ($fid, $timestamp, $user, $text) = @{$tuple};              Trace("Processing annotations.") if T(2);
1041                for my $tuple (@annotations) {
1042                    # Get the annotation tuple.
1043                    my ($peg, $timestamp, $user, $text) = @{$tuple};
1044                      # Here we fix up the annotation text. "\r" is removed,                      # Here we fix up the annotation text. "\r" is removed,
1045                      # and "\t" and "\n" are escaped. Note we use the "s"                      # and "\t" and "\n" are escaped. Note we use the "s"
1046                      # modifier so that new-lines inside the text do not                      # modifier so that new-lines inside the text do not
# Line 1024  Line 1055 
1055                          # Here it's a number. We need to insure the one we use to form                          # Here it's a number. We need to insure the one we use to form
1056                          # the key is unique.                          # the key is unique.
1057                          my $keyStamp = $timestamp;                          my $keyStamp = $timestamp;
1058                          while ($seenTimestamps{$keyStamp}) {                      while ($seenTimestamps{"$peg:$keyStamp"}) {
1059                              $keyStamp++;                              $keyStamp++;
1060                          }                          }
                         $seenTimestamps{$keyStamp} = 1;  
1061                          my $annotationID = "$peg:$keyStamp";                          my $annotationID = "$peg:$keyStamp";
1062                        $seenTimestamps{$annotationID} = 1;
1063                          # Insure the user exists.                          # Insure the user exists.
1064                          if (! $users{$user}) {                          if (! $users{$user}) {
1065                              $loadSproutUser->Put($user, "SEED user");                              $loadSproutUser->Put($user, "SEED user");
# Line 1046  Line 1077 
1077                  }                  }
1078              }              }
1079          }          }
     }  
1080      # Finish the load.      # Finish the load.
1081      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1082      return $retVal;      return $retVal;
# Line 1088  Line 1118 
1118      # Get the genome hash.      # Get the genome hash.
1119      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
1120      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1121      my $loadComesFrom = $self->_TableLoader('ComesFrom');      my $loadComesFrom = $self->_TableLoader('ComesFrom', $self->PrimaryOnly);
1122      my $loadSource = $self->_TableLoader('Source');      my $loadSource = $self->_TableLoader('Source');
1123      my $loadSourceURL = $self->_TableLoader('SourceURL');      my $loadSourceURL = $self->_TableLoader('SourceURL');
1124      if ($self->{options}->{loadOnly}) {      if ($self->{options}->{loadOnly}) {
# Line 1246  Line 1276 
1276      my $fig = $self->{fig};      my $fig = $self->{fig};
1277      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1278      my $loadReaction = $self->_TableLoader('Reaction');      my $loadReaction = $self->_TableLoader('Reaction');
1279      my $loadReactionURL = $self->_TableLoader('ReactionURL');      my $loadReactionURL = $self->_TableLoader('ReactionURL', $self->PrimaryOnly);
1280      my $loadCompound = $self->_TableLoader('Compound');      my $loadCompound = $self->_TableLoader('Compound', $self->PrimaryOnly);
1281      my $loadCompoundName = $self->_TableLoader('CompoundName');      my $loadCompoundName = $self->_TableLoader('CompoundName', $self->PrimaryOnly);
1282      my $loadCompoundCAS = $self->_TableLoader('CompoundCAS');      my $loadCompoundCAS = $self->_TableLoader('CompoundCAS', $self->PrimaryOnly);
1283      my $loadIsAComponentOf = $self->_TableLoader('IsAComponentOf');      my $loadIsAComponentOf = $self->_TableLoader('IsAComponentOf', $self->PrimaryOnly);
1284      if ($self->{options}->{loadOnly}) {      if ($self->{options}->{loadOnly}) {
1285          Trace("Loading from existing files.") if T(2);          Trace("Loading from existing files.") if T(2);
1286      } else {      } else {
# Line 1382  Line 1412 
1412    
1413  Name of the table (relation) being loaded.  Name of the table (relation) being loaded.
1414    
1415    =item ignore
1416    
1417    TRUE if the table should be ignored entirely, else FALSE.
1418    
1419  =item RETURN  =item RETURN
1420    
1421  Returns an ERDBLoad object for loading the specified table.  Returns an ERDBLoad object for loading the specified table.
# Line 1392  Line 1426 
1426    
1427  sub _TableLoader {  sub _TableLoader {
1428      # Get the parameters.      # Get the parameters.
1429      my ($self, $tableName, $loadOnly) = @_;      my ($self, $tableName, $ignore) = @_;
1430      # Create the load object.      # Create the load object.
1431      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $self->LoadOnly);      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $self->LoadOnly,
1432                                   $ignore);
1433      # Cache it in the loader list.      # Cache it in the loader list.
1434      push @{$self->{loaders}}, $retVal;      push @{$self->{loaders}}, $retVal;
1435      # Return it to the caller.      # Return it to the caller.
# Line 1431  Line 1466 
1466      # Loop through the list, finishing the loads. Note that if the finish fails, we die      # Loop through the list, finishing the loads. Note that if the finish fails, we die
1467      # ignominiously. At some future point, we want to make the loads restartable.      # ignominiously. At some future point, we want to make the loads restartable.
1468      while (my $loader = pop @{$loadList}) {      while (my $loader = pop @{$loadList}) {
1469          # Trace the fact that we're cleaning up.          # Get the relation name.
1470          my $relName = $loader->RelName;          my $relName = $loader->RelName;
1471            # Check the ignore flag.
1472            if ($loader->Ignore) {
1473                Trace("Relation $relName not loaded.") if T(2);
1474            } else {
1475                # Here we really need to finish.
1476          Trace("Finishing $relName.") if T(2);          Trace("Finishing $relName.") if T(2);
1477          my $stats = $loader->Finish();          my $stats = $loader->Finish();
1478          if ($self->{options}->{dbLoad}) {          if ($self->{options}->{dbLoad}) {
# Line 1445  Line 1485 
1485          $retVal->Accumulate($stats);          $retVal->Accumulate($stats);
1486          Trace("Statistics for $relName:\n" . $stats->Show()) if T(2);          Trace("Statistics for $relName:\n" . $stats->Show()) if T(2);
1487      }      }
1488        }
1489      # Return the load statistics.      # Return the load statistics.
1490      return $retVal;      return $retVal;
1491  }  }

Legend:
Removed from v.1.23  
changed lines
  Added in v.1.40

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3