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

Diff of /Sprout/SproutLoad.pm

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

revision 1.9, Wed Sep 14 11:21:24 2005 UTC revision 1.75, Sun Oct 22 05:17:10 2006 UTC
# Line 10  Line 10 
10      use Sprout;      use Sprout;
11      use Stats;      use Stats;
12      use BasicLocation;      use BasicLocation;
13        use HTML;
14    
15  =head1 Sprout Load Methods  =head1 Sprout Load Methods
16    
# Line 29  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 79  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 93  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 118  Line 120 
120                  # an omitted access code can be defaulted to 1.                  # an omitted access code can be defaulted to 1.
121                  for my $genomeLine (@genomeList) {                  for my $genomeLine (@genomeList) {
122                      my ($genomeID, $accessCode) = split("\t", $genomeLine);                      my ($genomeID, $accessCode) = split("\t", $genomeLine);
123                      if (undef $accessCode) {                          if (! defined($accessCode)) {
124                          $accessCode = 1;                          $accessCode = 1;
125                      }                      }
126                      $genomes{$genomeID} = $accessCode;                      $genomes{$genomeID} = $accessCode;
# Line 128  Line 130 
130              Confess("Invalid genome parameter ($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 usable subsystems. First we get the whole list.
140          %subsystems = map { $_ => 1 } $fig->all_subsystems();              my @subs = $fig->all_subsystems();
141                # Loop through, checking for usability.
142                for my $sub (@subs) {
143                    if ($fig->usable_subsystem($sub)) {
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 152  Line 163 
163              Confess("Invalid subsystem parameter in SproutLoad constructor.");              Confess("Invalid subsystem parameter in SproutLoad constructor.");
164          }          }
165      }      }
166            # Go through the subsys hash again, creating the keyword list for each subsystem.
167            for my $subsystem (keys %subsystems) {
168                my $name = $subsystem;
169                $name =~ s/_/ /g;
170                my $classes = $fig->subsystem_classification($subsystem);
171                my @classList = map { " $_" } @{$classes};
172                $name .= join("", @classList);
173                $subsystems{$subsystem} = $name;
174            }
175        }
176      # Get the data directory from the Sprout object.      # Get the data directory from the Sprout object.
177      my ($directory) = $sprout->LoadInfo();      my ($directory) = $sprout->LoadInfo();
178      # Create the Sprout load object.      # Create the Sprout load object.
# Line 161  Line 182 
182                    subsystems => \%subsystems,                    subsystems => \%subsystems,
183                    sprout => $sprout,                    sprout => $sprout,
184                    loadDirectory => $directory,                    loadDirectory => $directory,
185                    erdb => $sprout->{_erdb},                    erdb => $sprout,
186                    loaders => [],                    loaders => [],
187                    options => $options                    options => $options
188                   };                   };
# Line 170  Line 191 
191      return $retVal;      return $retVal;
192  }  }
193    
194    =head3 LoadOnly
195    
196    C<< my $flag = $spl->LoadOnly; >>
197    
198    Return TRUE if we are in load-only mode, else FALSE.
199    
200    =cut
201    
202    sub LoadOnly {
203        my ($self) = @_;
204        return $self->{options}->{loadOnly};
205    }
206    
207    =head3 PrimaryOnly
208    
209    C<< my $flag = $spl->PrimaryOnly; >>
210    
211    Return TRUE if only the main entity is to be loaded, else FALSE.
212    
213    =cut
214    
215    sub PrimaryOnly {
216        my ($self) = @_;
217        return $self->{options}->{primaryOnly};
218    }
219    
220  =head3 LoadGenomeData  =head3 LoadGenomeData
221    
222  C<< my $stats = $spl->LoadGenomeData(); >>  C<< my $stats = $spl->LoadGenomeData(); >>
# Line 197  Line 244 
244    
245  =back  =back
246    
 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.)  
   
247  =cut  =cut
248  #: Return Type $%;  #: Return Type $%;
249  sub LoadGenomeData {  sub LoadGenomeData {
# Line 215  Line 254 
254      # Get the genome count.      # Get the genome count.
255      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
256      my $genomeCount = (keys %{$genomeHash});      my $genomeCount = (keys %{$genomeHash});
     Trace("Beginning genome data load.") if T(2);  
257      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
258      my $loadGenome = $self->_TableLoader('Genome', $genomeCount);      my $loadGenome = $self->_TableLoader('Genome');
259      my $loadHasContig = $self->_TableLoader('HasContig', $genomeCount * 300);      my $loadHasContig = $self->_TableLoader('HasContig', $self->PrimaryOnly);
260      my $loadContig = $self->_TableLoader('Contig', $genomeCount * 300);      my $loadContig = $self->_TableLoader('Contig', $self->PrimaryOnly);
261      my $loadIsMadeUpOf = $self->_TableLoader('IsMadeUpOf', $genomeCount * 60000);      my $loadIsMadeUpOf = $self->_TableLoader('IsMadeUpOf', $self->PrimaryOnly);
262      my $loadSequence = $self->_TableLoader('Sequence', $genomeCount * 60000);      my $loadSequence = $self->_TableLoader('Sequence', $self->PrimaryOnly);
263        if ($self->{options}->{loadOnly}) {
264            Trace("Loading from existing files.") if T(2);
265        } else {
266            Trace("Generating genome data.") if T(2);
267      # Now we loop through the genomes, generating the data for each one.      # Now we loop through the genomes, generating the data for each one.
268      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
269          Trace("Loading data for genome $genomeID.") if T(3);              Trace("Generating data for genome $genomeID.") if T(3);
270          $loadGenome->Add("genomeIn");          $loadGenome->Add("genomeIn");
271          # The access code comes in via the genome hash.          # The access code comes in via the genome hash.
272          my $accessCode = $genomeHash->{$genomeID};          my $accessCode = $genomeHash->{$genomeID};
273          # 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.  
274          my ($genus, $species, @extraData) = split / /, $self->{fig}->genus_species($genomeID);          my ($genus, $species, @extraData) = split / /, $self->{fig}->genus_species($genomeID);
275          my $extra = join " ", @extraData, "[$genomeID]";              my $extra = join " ", @extraData;
276          # Get the full taxonomy.          # Get the full taxonomy.
277          my $taxonomy = $fig->taxonomy_of($genomeID);          my $taxonomy = $fig->taxonomy_of($genomeID);
278                # Open the NMPDR group file for this genome.
279                my $group;
280                if (open(TMP, "<$FIG_Config::organisms/$genomeID/NMPDR") &&
281                    defined($group = <TMP>)) {
282                    # Clean the line ending.
283                    chomp $group;
284                } else {
285                    # No group, so use the default.
286                    $group = $FIG_Config::otherGroup;
287                }
288                close TMP;
289          # Output the genome record.          # Output the genome record.
290          $loadGenome->Put($genomeID, $accessCode, $fig->is_complete($genomeID), $genus,          $loadGenome->Put($genomeID, $accessCode, $fig->is_complete($genomeID), $genus,
291                           $species, $extra, $taxonomy);                               $group, $species, $extra, $taxonomy);
292          # Now we loop through each of the genome's contigs.          # Now we loop through each of the genome's contigs.
293          my @contigs = $fig->all_contigs($genomeID);          my @contigs = $fig->all_contigs($genomeID);
294          for my $contigID (@contigs) {          for my $contigID (@contigs) {
# Line 267  Line 319 
319              }              }
320          }          }
321      }      }
322        }
323      # Finish the loads.      # Finish the loads.
324      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
325      # Return the result.      # Return the result.
# Line 307  Line 360 
360      my $fig = $self->{fig};      my $fig = $self->{fig};
361      # Get the genome hash.      # Get the genome hash.
362      my $genomeFilter = $self->{genomes};      my $genomeFilter = $self->{genomes};
363      my $genomeCount = (keys %{$genomeFilter});      # Set up an ID counter for the PCHs.
364      my $featureCount = $genomeCount * 4000;      my $pchID = 0;
365      # Start the loads.      # Start the loads.
366      my $loadCoupling = $self->_TableLoader('Coupling', $featureCount * $genomeCount);      my $loadCoupling = $self->_TableLoader('Coupling');
367      my $loadIsEvidencedBy = $self->_TableLoader('IsEvidencedBy', $featureCount * 8000);      my $loadIsEvidencedBy = $self->_TableLoader('IsEvidencedBy', $self->PrimaryOnly);
368      my $loadPCH = $self->_TableLoader('PCH', $featureCount * 2000);      my $loadPCH = $self->_TableLoader('PCH', $self->PrimaryOnly);
369      my $loadParticipatesInCoupling = $self->_TableLoader('ParticipatesInCoupling', $featureCount * 2000);      my $loadParticipatesInCoupling = $self->_TableLoader('ParticipatesInCoupling', $self->PrimaryOnly);
370      my $loadUsesAsEvidence = $self->_TableLoader('UsesAsEvidence', $featureCount * 8000);      my $loadUsesAsEvidence = $self->_TableLoader('UsesAsEvidence', $self->PrimaryOnly);
371      Trace("Beginning coupling data load.") if T(2);      if ($self->{options}->{loadOnly}) {
372            Trace("Loading from existing files.") if T(2);
373        } else {
374            Trace("Generating coupling data.") if T(2);
375      # Loop through the genomes found.      # Loop through the genomes found.
376      for my $genome (sort keys %{$genomeFilter}) {      for my $genome (sort keys %{$genomeFilter}) {
377          Trace("Generating coupling data for $genome.") if T(3);          Trace("Generating coupling data for $genome.") if T(3);
# Line 339  Line 395 
395              for my $coupleData (@couplings) {              for my $coupleData (@couplings) {
396                  my ($peg2, $score) = @{$coupleData};                  my ($peg2, $score) = @{$coupleData};
397                  # Compute the coupling ID.                  # Compute the coupling ID.
398                  my $coupleID = Sprout::CouplingID($peg1, $peg2);                      my $coupleID = $self->{erdb}->CouplingID($peg1, $peg2);
399                  if (! exists $dupHash{$coupleID}) {                  if (! exists $dupHash{$coupleID}) {
400                      $loadCoupling->Add("couplingIn");                      $loadCoupling->Add("couplingIn");
401                      # Here we have a new coupling to store in the load files.                      # Here we have a new coupling to store in the load files.
# Line 367  Line 423 
423                              # We store this evidence in the hash if the usage                              # We store this evidence in the hash if the usage
424                              # is nonzero or no prior evidence has been found. This                              # is nonzero or no prior evidence has been found. This
425                              # insures that if there is duplicate evidence, we                              # insures that if there is duplicate evidence, we
426                              # at least keep the meaningful ones. Only evidence is                                  # at least keep the meaningful ones. Only evidence in
427                              # the hash makes it to the output.                              # the hash makes it to the output.
428                              if ($usage || ! exists $evidenceMap{$evidenceKey}) {                              if ($usage || ! exists $evidenceMap{$evidenceKey}) {
429                                  $evidenceMap{$evidenceKey} = $evidenceData;                                  $evidenceMap{$evidenceKey} = $evidenceData;
# Line 375  Line 431 
431                          }                          }
432                      }                      }
433                      for my $evidenceID (keys %evidenceMap) {                      for my $evidenceID (keys %evidenceMap) {
434                                # Get the ID for this evidence.
435                                $pchID++;
436                          # Create the evidence record.                          # Create the evidence record.
437                          my ($peg3, $peg4, $usage) = @{$evidenceMap{$evidenceID}};                          my ($peg3, $peg4, $usage) = @{$evidenceMap{$evidenceID}};
438                          $loadPCH->Put($evidenceID, $usage);                              $loadPCH->Put($pchID, $usage);
439                          # Connect it to the coupling.                          # Connect it to the coupling.
440                          $loadIsEvidencedBy->Put($coupleID, $evidenceID);                              $loadIsEvidencedBy->Put($coupleID, $pchID);
441                          # Connect it to the features.                          # Connect it to the features.
442                          $loadUsesAsEvidence->Put($evidenceID, $peg3, 1);                              $loadUsesAsEvidence->Put($pchID, $peg3, 1);
443                          $loadUsesAsEvidence->Put($evidenceID, $peg4, 1);                              $loadUsesAsEvidence->Put($pchID, $peg4, 2);
444                            }
445                      }                      }
446                  }                  }
447              }              }
# Line 409  Line 468 
468      FeatureTranslation      FeatureTranslation
469      FeatureUpstream      FeatureUpstream
470      IsLocatedIn      IsLocatedIn
471        HasFeature
472        HasRoleInSubsystem
473    
474  =over 4  =over 4
475    
# Line 423  Line 484 
484  sub LoadFeatureData {  sub LoadFeatureData {
485      # Get this object instance.      # Get this object instance.
486      my ($self) = @_;      my ($self) = @_;
487      # Get the FIG object.      # Get the FIG and Sprout objects.
488      my $fig = $self->{fig};      my $fig = $self->{fig};
489      # Find out if this is a limited run.      my $sprout = $self->{sprout};
     my $limited = $self->{options}->{limitedFeatures};  
490      # Get the table of genome IDs.      # Get the table of genome IDs.
491      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
     my $featureCount = $genomeCount * 4000;  
492      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
493      my $loadFeature = $self->_TableLoader('Feature', $featureCount);      my $loadFeature = $self->_TableLoader('Feature');
494      my $loadIsLocatedIn = $self->_TableLoader('IsLocatedIn', $featureCount);      my $loadIsLocatedIn = $self->_TableLoader('IsLocatedIn', $self->PrimaryOnly);
495      my ($loadFeatureAlias, $loadFeatureLink, $loadFeatureTranslation, $loadFeatureUpstream);      my $loadFeatureAlias = $self->_TableLoader('FeatureAlias');
496      if (! $limited) {      my $loadFeatureLink = $self->_TableLoader('FeatureLink');
497          $loadFeatureAlias = $self->_TableLoader('FeatureAlias', $featureCount * 6);      my $loadFeatureTranslation = $self->_TableLoader('FeatureTranslation');
498          $loadFeatureLink = $self->_TableLoader('FeatureLink', $featureCount * 10);      my $loadFeatureUpstream = $self->_TableLoader('FeatureUpstream');
499          $loadFeatureTranslation = $self->_TableLoader('FeatureTranslation', $featureCount);      my $loadHasFeature = $self->_TableLoader('HasFeature', $self->PrimaryOnly);
500          $loadFeatureUpstream = $self->_TableLoader('FeatureUpstream', $featureCount);      my $loadHasRoleInSubsystem = $self->_TableLoader('HasRoleInSubsystem', $self->PrimaryOnly);
501      }      # Get the subsystem hash.
502        my $subHash = $self->{subsystems};
503      # 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
504      # locations.      # locations.
505      my $chunkSize = $self->{sprout}->MaxSegment();      my $chunkSize = $self->{sprout}->MaxSegment();
506      Trace("Beginning feature data load.") if T(2);      if ($self->{options}->{loadOnly}) {
507            Trace("Loading from existing files.") if T(2);
508        } else {
509            Trace("Generating feature data.") if T(2);
510      # Now we loop through the genomes, generating the data for each one.      # Now we loop through the genomes, generating the data for each one.
511      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
512          Trace("Loading features for genome $genomeID.") if T(3);          Trace("Loading features for genome $genomeID.") if T(3);
513          $loadFeature->Add("genomeIn");          $loadFeature->Add("genomeIn");
514          # Get the feature list for this genome.          # Get the feature list for this genome.
515          my $features = $fig->all_features_detailed($genomeID);          my $features = $fig->all_features_detailed($genomeID);
516                # Sort and count the list.
517                my @featureTuples = sort { $a->[0] cmp $b->[0] } @{$features};
518                my $count = scalar @featureTuples;
519                Trace("$count features found for genome $genomeID.") if T(3);
520                # Set up for our duplicate-feature check.
521                my $oldFeatureID = "";
522          # Loop through the features.          # Loop through the features.
523          for my $featureData (@{$features}) {              for my $featureTuple (@featureTuples) {
             $loadFeature->Add("featureIn");  
524              # Split the tuple.              # Split the tuple.
525              my ($featureID, $locations, $aliases, $type) = @{$featureData};                  my ($featureID, $locations, undef, $type) = @{$featureTuple};
526              # Create the feature record.                  # Check for duplicates.
527              $loadFeature->Put($featureID, 1, $type);                  if ($featureID eq $oldFeatureID) {
528              # The next stuff is for a full load only.                      Trace("Duplicate feature $featureID found.") if T(1);
529              if (! $limited) {                  } else {
530                        $oldFeatureID = $featureID;
531                        # Count this feature.
532                        $loadFeature->Add("featureIn");
533                        # Begin building the keywords.
534                        my @keywords = ($genomeID);
535                        # Get the functional assignment and aliases. This
536                        # depends on the feature type.
537                        my $assignment;
538                        if ($type eq "peg") {
539                            $assignment = $fig->function_of($featureID);
540                  # Create the aliases.                  # Create the aliases.
541                  for my $alias (split /\s*,\s*/, $aliases) {                          for my $alias ($fig->feature_aliases($featureID)) {
542                      $loadFeatureAlias->Put($featureID, $alias);                      $loadFeatureAlias->Put($featureID, $alias);
543                                push @keywords, $alias;
544                            }
545                        } else {
546                            # For other types, the assignment is the first (and ONLY) alias.
547                            ($assignment) = $fig->feature_aliases($featureID);
548                  }                  }
549                        Trace("Assignment for $featureID is: $assignment") if T(4);
550                        # Break the assignment into words and shove it onto the
551                        # keyword list.
552                        push @keywords, split(/\s+/, $assignment);
553                        # Link this feature to the parent genome.
554                        $loadHasFeature->Put($genomeID, $featureID, $type);
555                  # Get the links.                  # Get the links.
556                  my @links = $fig->fid_links($featureID);                  my @links = $fig->fid_links($featureID);
557                  for my $link (@links) {                  for my $link (@links) {
# Line 482  Line 570 
570                          $loadFeatureUpstream->Put($featureID, $upstream);                          $loadFeatureUpstream->Put($featureID, $upstream);
571                      }                      }
572                  }                  }
573                        # Now we need to find the subsystems this feature participates in.
574                        # We also add the subsystems to the keyword list. Before we do that,
575                        # we must convert underscores to spaces and tack on the classifications.
576                        my @subsystems = $fig->peg_to_subsystems($featureID);
577                        for my $subsystem (@subsystems) {
578                            # Only proceed if we like this subsystem.
579                            if (exists $subHash->{$subsystem}) {
580                                # Store the has-role link.
581                                $loadHasRoleInSubsystem->Put($featureID, $subsystem, $genomeID, $type);
582                                # Save the subsystem's keyword data.
583                                my $subKeywords = $subHash->{$subsystem};
584                                push @keywords, split /\s+/, $subKeywords;
585                                # Now we need to get this feature's role in the subsystem.
586                                my $subObject = $fig->get_subsystem($subsystem);
587                                my @roleColumns = $subObject->get_peg_roles($featureID);
588                                my @allRoles = $subObject->get_roles();
589                                for my $col (@roleColumns) {
590                                    my $role = $allRoles[$col];
591                                    push @keywords, split /\s+/, $role;
592                                    push @keywords, $subObject->get_role_abbr($col);
593                                }
594                            }
595                        }
596                        # The final task is to add virulence and essentiality attributes.
597                        if ($fig->virulent($featureID)) {
598                            push @keywords, "virulent";
599                        }
600                        if ($fig->essential($featureID)) {
601                            push @keywords, "essential";
602                        }
603                        # Now we need to bust up hyphenated words in the keyword
604                        # list.
605                        my $keywordString = "";
606                        for my $keyword (@keywords) {
607                            if (length $keyword >= 4) {
608                                $keywordString .= " $keyword";
609                                if ($keyword =~ /-/) {
610                                    my @words = grep { length($_) >= 4 } split /-/, $keyword;
611                                    $keywordString .= join(" ", "", @words);
612                                }
613              }              }
614                        }
615                        # Clean the keyword list.
616                        my $cleanWords = $sprout->CleanKeywords($keywordString);
617                        Trace("Keyword string for $featureID: $cleanWords") if T(4);
618                        # Create the feature record.
619                        $loadFeature->Put($featureID, 1, $type, $assignment, $cleanWords);
620              # This part is the roughest. We need to relate the features to contig              # This part is the roughest. We need to relate the features to contig
621              # locations, and the locations must be split so that none of them exceed              # locations, and the locations must be split so that none of them exceed
622              # the maximum segment size. This simplifies the genes_in_region processing              # the maximum segment size. This simplifies the genes_in_region processing
623              # for Sprout.              # for Sprout.
624              my @locationList = map { "$genomeID:$_" } split /\s*,\s*/, $locations;                      my @locationList = split /\s*,\s*/, $locations;
625              # Create the location position indicator.              # Create the location position indicator.
626              my $i = 1;              my $i = 1;
627              # Loop through the locations.              # Loop through the locations.
628              for my $location (@locationList) {              for my $location (@locationList) {
629                  # Parse the location.                  # Parse the location.
630                  my $locObject = BasicLocation->new($location);                          my $locObject = BasicLocation->new("$genomeID:$location");
631                  # Split it into a list of chunks.                  # Split it into a list of chunks.
632                  my @locOList = ();                  my @locOList = ();
633                  while (my $peeling = $locObject->Peel($chunkSize)) {                  while (my $peeling = $locObject->Peel($chunkSize)) {
# Line 511  Line 645 
645              }              }
646          }          }
647      }      }
     # Finish the loads.  
     my $retVal = $self->_FinishAll();  
     return $retVal;  
 }  
   
 =head3 LoadBBHData  
   
 C<< my $stats = $spl->LoadBBHData(); >>  
   
 Load the bidirectional best hit data from FIG into Sprout.  
   
 Sprout does not store information on similarities. Instead, it has only the  
 bi-directional best hits. Even so, the BBH table is one of the largest in  
 the database.  
   
 The following relations are loaded by this method.  
   
     IsBidirectionalBestHitOf  
   
 =over 4  
   
 =item RETURNS  
   
 Returns a statistics object for the loads.  
   
 =back  
   
 =cut  
 #: Return Type $%;  
 sub LoadBBHData {  
     # Get this object instance.  
     my ($self) = @_;  
     # Get the FIG object.  
     my $fig = $self->{fig};  
     # Get the table of genome IDs.  
     my $genomeHash = $self->{genomes};  
     my $genomeCount = (keys %{$genomeHash});  
     my $featureCount = $genomeCount * 4000;  
     # Create load objects for each of the tables we're loading.  
     my $loadIsBidirectionalBestHitOf = $self->_TableLoader('IsBidirectionalBestHitOf',  
                                                            $featureCount * $genomeCount);  
     Trace("Beginning BBH load.") if T(2);  
     # Now we loop through the genomes, generating the data for each one.  
     for my $genomeID (sort keys %{$genomeHash}) {  
         $loadIsBidirectionalBestHitOf->Add("genomeIn");  
         Trace("Processing features for genome $genomeID.") if T(3);  
         # Get the feature list for this genome.  
         my $features = $fig->all_features_detailed($genomeID);  
         # Loop through the features.  
         for my $featureData (@{$features}) {  
             # Split the tuple.  
             my ($featureID, $locations, $aliases, $type) = @{$featureData};  
             # Get the bi-directional best hits.  
             my @bbhList = $fig->bbhs($featureID);  
             for my $bbhEntry (@bbhList) {  
                 # Get the target feature ID and the score.  
                 my ($targetID, $score) = @{$bbhEntry};  
                 # Check the target feature's genome.  
                 my $targetGenomeID = $fig->genome_of($targetID);  
                 # Only proceed if it's one of our genomes.  
                 if ($genomeHash->{$targetGenomeID}) {  
                     $loadIsBidirectionalBestHitOf->Put($featureID, $targetID, $targetGenomeID,  
                                                        $score);  
                 }  
             }  
648          }          }
649      }      }
650      # Finish the loads.      # Finish the loads.
# Line 598  Line 667 
667  The following relations are loaded by this method.  The following relations are loaded by this method.
668    
669      Subsystem      Subsystem
670        SubsystemClass
671      Role      Role
672        RoleEC
673      SSCell      SSCell
674      ContainsFeature      ContainsFeature
675      IsGenomeOf      IsGenomeOf
# Line 606  Line 677 
677      OccursInSubsystem      OccursInSubsystem
678      ParticipatesIn      ParticipatesIn
679      HasSSCell      HasSSCell
680        ConsistsOfRoles
681        RoleSubset
682        HasRoleSubset
683        ConsistsOfGenomes
684        GenomeSubset
685        HasGenomeSubset
686        Catalyzes
687        Diagram
688        RoleOccursIn
689    
690  =over 4  =over 4
691    
# Line 615  Line 695 
695    
696  =back  =back
697    
 B<TO DO>  
   
 Generate RoleName table?  
   
698  =cut  =cut
699  #: Return Type $%;  #: Return Type $%;
700  sub LoadSubsystemData {  sub LoadSubsystemData {
# Line 632  Line 708 
708      # Get the subsystem hash. This lists the subsystems we'll process.      # Get the subsystem hash. This lists the subsystems we'll process.
709      my $subsysHash = $self->{subsystems};      my $subsysHash = $self->{subsystems};
710      my @subsysIDs = sort keys %{$subsysHash};      my @subsysIDs = sort keys %{$subsysHash};
711      my $subsysCount = @subsysIDs;      # Get the map list.
712      my $genomeCount = (keys %{$genomeHash});      my @maps = $fig->all_maps;
     my $featureCount = $genomeCount * 4000;  
713      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
714      my $loadSubsystem = $self->_TableLoader('Subsystem', $subsysCount);      my $loadDiagram = $self->_TableLoader('Diagram', $self->PrimaryOnly);
715      my $loadRole = $self->_TableLoader('Role', $featureCount * 6);      my $loadRoleOccursIn = $self->_TableLoader('RoleOccursIn', $self->PrimaryOnly);
716      my $loadSSCell = $self->_TableLoader('SSCell', $featureCount * $genomeCount);      my $loadSubsystem = $self->_TableLoader('Subsystem');
717      my $loadContainsFeature = $self->_TableLoader('ContainsFeature', $featureCount * $subsysCount);      my $loadRole = $self->_TableLoader('Role', $self->PrimaryOnly);
718      my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf', $featureCount * $genomeCount);      my $loadRoleEC = $self->_TableLoader('RoleEC', $self->PrimaryOnly);
719      my $loadIsRoleOf = $self->_TableLoader('IsRoleOf', $featureCount * $genomeCount);      my $loadCatalyzes = $self->_TableLoader('Catalyzes', $self->PrimaryOnly);
720      my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem', $featureCount * 6);      my $loadSSCell = $self->_TableLoader('SSCell', $self->PrimaryOnly);
721      my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn', $subsysCount * $genomeCount);      my $loadContainsFeature = $self->_TableLoader('ContainsFeature', $self->PrimaryOnly);
722      my $loadHasSSCell = $self->_TableLoader('HasSSCell', $featureCount * $genomeCount);      my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf', $self->PrimaryOnly);
723      Trace("Beginning subsystem data load.") if T(2);      my $loadIsRoleOf = $self->_TableLoader('IsRoleOf', $self->PrimaryOnly);
724        my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem', $self->PrimaryOnly);
725        my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn', $self->PrimaryOnly);
726        my $loadHasSSCell = $self->_TableLoader('HasSSCell', $self->PrimaryOnly);
727        my $loadRoleSubset = $self->_TableLoader('RoleSubset', $self->PrimaryOnly);
728        my $loadGenomeSubset = $self->_TableLoader('GenomeSubset', $self->PrimaryOnly);
729        my $loadConsistsOfRoles = $self->_TableLoader('ConsistsOfRoles', $self->PrimaryOnly);
730        my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes', $self->PrimaryOnly);
731        my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset', $self->PrimaryOnly);
732        my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset', $self->PrimaryOnly);
733        my $loadSubsystemClass = $self->_TableLoader('SubsystemClass', $self->PrimaryOnly);
734        if ($self->{options}->{loadOnly}) {
735            Trace("Loading from existing files.") if T(2);
736        } else {
737            Trace("Generating subsystem data.") if T(2);
738            # This hash will contain the role for each EC. When we're done, this
739            # information will be used to generate the Catalyzes table.
740            my %ecToRoles = ();
741      # Loop through the subsystems. Our first task will be to create the      # Loop through the subsystems. Our first task will be to create the
742      # roles. We do this by looping through the subsystems and creating a      # roles. We do this by looping through the subsystems and creating a
743      # role hash. The hash tracks each role ID so that we don't create      # role hash. The hash tracks each role ID so that we don't create
744      # duplicates. As we move along, we'll connect the roles and subsystems.          # duplicates. As we move along, we'll connect the roles and subsystems
745            # and memorize up the reactions.
746            my ($genomeID, $roleID);
747      my %roleData = ();      my %roleData = ();
748      for my $subsysID (@subsysIDs) {      for my $subsysID (@subsysIDs) {
749                # Get the subsystem object.
750                my $sub = $fig->get_subsystem($subsysID);
751                # Only proceed if the subsystem has a spreadsheet.
752                if (! $sub->{empty_ss}) {
753          Trace("Creating subsystem $subsysID.") if T(3);          Trace("Creating subsystem $subsysID.") if T(3);
754          $loadSubsystem->Add("subsystemIn");          $loadSubsystem->Add("subsystemIn");
755          # Create the subsystem record.          # Create the subsystem record.
756          $loadSubsystem->Put($subsysID);                  my $curator = $sub->get_curator();
757          # Get the subsystem's roles.                  my $notes = $sub->get_notes();
758          my @roles = $fig->subsystem_to_roles($subsysID);                  $loadSubsystem->Put($subsysID, $curator, $notes);
759          # Connect the roles to the subsystem. If a role is new, we create                  # Now for the classification string. This comes back as a list
760          # a role record for it.                  # reference and we convert it to a space-delimited string.
761          for my $roleID (@roles) {                  my $classList = $fig->subsystem_classification($subsysID);
762                    my $classString = join(" : ", grep { $_ } @$classList);
763                    $loadSubsystemClass->Put($subsysID, $classString);
764                    # Connect it to its roles. Each role is a column in the subsystem spreadsheet.
765                    for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
766                        # Connect to this role.
767              $loadOccursInSubsystem->Add("roleIn");              $loadOccursInSubsystem->Add("roleIn");
768              $loadOccursInSubsystem->Put($roleID, $subsysID);                      $loadOccursInSubsystem->Put($roleID, $subsysID, $col);
769                        # If it's a new role, add it to the role table.
770              if (! exists $roleData{$roleID}) {              if (! exists $roleData{$roleID}) {
771                  $loadRole->Put($roleID);                          # Get the role's abbreviation.
772                            my $abbr = $sub->get_role_abbr($col);
773                            # Add the role.
774                            $loadRole->Put($roleID, $abbr);
775                  $roleData{$roleID} = 1;                  $roleData{$roleID} = 1;
776                            # Check for an EC number.
777                            if ($roleID =~ /\(EC ([^.]+\.[^.]+\.[^.]+\.[^)]+)\)\s*$/) {
778                                my $ec = $1;
779                                $loadRoleEC->Put($roleID, $ec);
780                                $ecToRoles{$ec} = $roleID;
781                            }
782              }              }
783          }          }
784          # Now all roles for this subsystem have been filled in. We create the                  # Now we create the spreadsheet for the subsystem by matching roles to
785          # spreadsheet by matches roles to genomes. To do this, we need to                  # genomes. Each genome is a row and each role is a column. We may need
786          # get the genomes on the sheet.                  # to actually create the roles as we find them.
787          Trace("Creating subsystem $subsysID spreadsheet.") if T(3);          Trace("Creating subsystem $subsysID spreadsheet.") if T(3);
788          my @genomes = map { $_->[0] } @{$fig->subsystem_genomes($subsysID)};                  for (my $row = 0; defined($genomeID = $sub->get_genome($row)); $row++) {
789          for my $genomeID (@genomes) {                      # Only proceed if this is one of our genomes.
             # Only process this genome if it's one of ours.  
790              if (exists $genomeHash->{$genomeID}) {              if (exists $genomeHash->{$genomeID}) {
791                  # Connect the genome to the subsystem.                          # Count the PEGs and cells found for verification purposes.
792                  $loadParticipatesIn->Put($genomeID, $subsysID);                          my $pegCount = 0;
793                            my $cellCount = 0;
794                            # Create a list for the PEGs we find. This list will be used
795                            # to generate cluster numbers.
796                            my @pegsFound = ();
797                            # Create a hash that maps spreadsheet IDs to PEGs. We will
798                            # use this to generate the ContainsFeature data after we have
799                            # the cluster numbers.
800                            my %cellPegs = ();
801                            # Get the genome's variant code for this subsystem.
802                            my $variantCode = $sub->get_variant_code($row);
803                  # Loop through the subsystem's roles. We use an index because it is                  # Loop through the subsystem's roles. We use an index because it is
804                  # part of the spreadsheet cell ID.                  # part of the spreadsheet cell ID.
805                  for (my $i = 0; $i <= $#roles; $i++) {                          for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
                     my $role = $roles[$i];  
806                      # Get the features in the spreadsheet cell for this genome and role.                      # Get the features in the spreadsheet cell for this genome and role.
807                      my @pegs = $fig->pegs_in_subsystem_cell($subsysID, $genomeID, $i);                              my @pegs = grep { !$fig->is_deleted_fid($_) } $sub->get_pegs_from_cell($row, $col);
808                      # Only proceed if features exist.                      # Only proceed if features exist.
809                      if (@pegs > 0) {                      if (@pegs > 0) {
810                          # Create the spreadsheet cell.                          # Create the spreadsheet cell.
811                          my $cellID = "$subsysID:$genomeID:$i";                                  $cellCount++;
812                                    my $cellID = "$subsysID:$genomeID:$col";
813                          $loadSSCell->Put($cellID);                          $loadSSCell->Put($cellID);
814                          $loadIsGenomeOf->Put($genomeID, $cellID);                          $loadIsGenomeOf->Put($genomeID, $cellID);
815                          $loadIsRoleOf->Put($role, $cellID);                                  $loadIsRoleOf->Put($roleID, $cellID);
816                          $loadHasSSCell->Put($subsysID, $cellID);                          $loadHasSSCell->Put($subsysID, $cellID);
817                          # Attach the features to it.                                  # Remember its features.
818                          for my $pegID (@pegs) {                                  push @pegsFound, @pegs;
819                              $loadContainsFeature->Put($cellID, $pegID);                                  $cellPegs{$cellID} = \@pegs;
820                                    $pegCount += @pegs;
821                                }
822                            }
823                            # If we found some cells for this genome, we need to compute clusters and
824                            # denote it participates in the subsystem.
825                            if ($pegCount > 0) {
826                                Trace("$pegCount PEGs in $cellCount cells for $genomeID.") if T(3);
827                                $loadParticipatesIn->Put($genomeID, $subsysID, $variantCode);
828                                # Create a hash mapping PEG IDs to cluster numbers.
829                                # We default to -1 for all of them.
830                                my %clusterOf = map { $_ => -1 } @pegsFound;
831                                # Partition the PEGs found into clusters.
832                                my @clusters = $fig->compute_clusters([keys %clusterOf], $sub);
833                                for (my $i = 0; $i <= $#clusters; $i++) {
834                                    my $subList = $clusters[$i];
835                                    for my $peg (@{$subList}) {
836                                        $clusterOf{$peg} = $i;
837                                    }
838                                }
839                                # Create the ContainsFeature data.
840                                for my $cellID (keys %cellPegs) {
841                                    my $cellList = $cellPegs{$cellID};
842                                    for my $cellPeg (@$cellList) {
843                                        $loadContainsFeature->Put($cellID, $cellPeg, $clusterOf{$cellPeg});
844                          }                          }
845                      }                      }
846                  }                  }
847              }              }
848          }          }
849                    # Now we need to generate the subsets. The subset names must be concatenated to
850                    # the subsystem name to make them unique keys. There are two types of subsets:
851                    # genome subsets and role subsets. We do the role subsets first.
852                    my @subsetNames = $sub->get_subset_names();
853                    for my $subsetID (@subsetNames) {
854                        # Create the subset record.
855                        my $actualID = "$subsysID:$subsetID";
856                        $loadRoleSubset->Put($actualID);
857                        # Connect the subset to the subsystem.
858                        $loadHasRoleSubset->Put($subsysID, $actualID);
859                        # Connect the subset to its roles.
860                        my @roles = $sub->get_subsetC_roles($subsetID);
861                        for my $roleID (@roles) {
862                            $loadConsistsOfRoles->Put($actualID, $roleID);
863      }      }
     # Finish the load.  
     my $retVal = $self->_FinishAll();  
     return $retVal;  
864  }  }
865                    # Next the genome subsets.
866  =head3 LoadDiagramData                  @subsetNames = $sub->get_subset_namesR();
867                    for my $subsetID (@subsetNames) {
868  C<< my $stats = $spl->LoadDiagramData(); >>                      # Create the subset record.
869                        my $actualID = "$subsysID:$subsetID";
870  Load the diagram data from FIG into Sprout.                      $loadGenomeSubset->Put($actualID);
871                        # Connect the subset to the subsystem.
872  Diagrams are used to organize functional roles. The diagram shows the                      $loadHasGenomeSubset->Put($subsysID, $actualID);
873  connections between chemicals that interact with a subsystem.                      # Connect the subset to its genomes.
874                        my @genomes = $sub->get_subsetR($subsetID);
875  The following relations are loaded by this method.                      for my $genomeID (@genomes) {
876                            $loadConsistsOfGenomes->Put($actualID, $genomeID);
877      Diagram                      }
878      RoleOccursIn                  }
879                }
880  =over 4          }
881            # Now we loop through the diagrams. We need to create the diagram records
882  =item RETURNS          # and link each diagram to its roles. Note that only roles which occur
883            # in subsystems (and therefore appear in the %ecToRoles hash) are
884  Returns a statistics object for the loads.          # included.
885            for my $map (@maps) {
 =back  
   
 =cut  
 #: Return Type $%;  
 sub LoadDiagramData {  
     # Get this object instance.  
     my ($self) = @_;  
     # Get the FIG object.  
     my $fig = $self->{fig};  
     # Get the map list.  
     my @maps = $fig->all_maps;  
     my $mapCount = @maps;  
     my $genomeCount = (keys %{$self->{genomes}});  
     my $featureCount = $genomeCount * 4000;  
     # Create load objects for each of the tables we're loading.  
     my $loadDiagram = $self->_TableLoader('Diagram', $mapCount);  
     my $loadRoleOccursIn = $self->_TableLoader('RoleOccursIn', $featureCount * 6);  
     Trace("Beginning diagram data load.") if T(2);  
     # Loop through the diagrams.  
     for my $map ($fig->all_maps) {  
886          Trace("Loading diagram $map.") if T(3);          Trace("Loading diagram $map.") if T(3);
887          # Get the diagram's descriptive name.          # Get the diagram's descriptive name.
888          my $name = $fig->map_name($map);          my $name = $fig->map_name($map);
# Line 754  Line 891 
891          # A hash is used to prevent duplicates.          # A hash is used to prevent duplicates.
892          my %roleHash = ();          my %roleHash = ();
893          for my $role ($fig->map_to_ecs($map)) {          for my $role ($fig->map_to_ecs($map)) {
894              if (! $roleHash{$role}) {                  if (exists $ecToRoles{$role} && ! $roleHash{$role}) {
895                  $loadRoleOccursIn->Put($role, $map);                      $loadRoleOccursIn->Put($ecToRoles{$role}, $map);
896                  $roleHash{$role} = 1;                  $roleHash{$role} = 1;
897              }              }
898          }          }
899      }      }
900            # Before we leave, we must create the Catalyzes table. We start with the reactions,
901            # then use the "ecToRoles" table to convert EC numbers to role IDs.
902            my @reactions = $fig->all_reactions();
903            for my $reactionID (@reactions) {
904                # Get this reaction's list of roles. The results will be EC numbers.
905                my @roles = $fig->catalyzed_by($reactionID);
906                # Loop through the roles, creating catalyzation records.
907                for my $thisRole (@roles) {
908                    if (exists $ecToRoles{$thisRole}) {
909                        $loadCatalyzes->Put($ecToRoles{$thisRole}, $reactionID);
910                    }
911                }
912            }
913        }
914      # Finish the load.      # Finish the load.
915      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
916      return $retVal;      return $retVal;
# Line 801  Line 952 
952      my $fig = $self->{fig};      my $fig = $self->{fig};
953      # Get the genome hash.      # Get the genome hash.
954      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
955      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
956      my $loadProperty = $self->_TableLoader('Property', $genomeCount * 1500);      my $loadProperty = $self->_TableLoader('Property');
957      my $loadHasProperty = $self->_TableLoader('HasProperty', $genomeCount * 1500);      my $loadHasProperty = $self->_TableLoader('HasProperty', $self->PrimaryOnly);
958      Trace("Beginning property data load.") if T(2);      if ($self->{options}->{loadOnly}) {
959            Trace("Loading from existing files.") if T(2);
960        } else {
961            Trace("Generating property data.") if T(2);
962      # Create a hash for storing property IDs.      # Create a hash for storing property IDs.
963      my %propertyKeys = ();      my %propertyKeys = ();
964      my $nextID = 1;      my $nextID = 1;
965      # Loop through the genomes.      # Loop through the genomes.
966      for my $genomeID (keys %{$genomeHash}) {          for my $genomeID (sort keys %{$genomeHash}) {
967          $loadProperty->Add("genomeIn");          $loadProperty->Add("genomeIn");
968                Trace("Generating properties for $genomeID.") if T(3);
969          # 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
970          # tuples returned by "all_features_detailed". We use "all_features_detailed"          # tuples returned by "all_features_detailed". We use "all_features_detailed"
971          # rather than "all_features" because we want all features regardless of type.          # rather than "all_features" because we want all features regardless of type.
972          my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};          my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};
973                my $featureCount = 0;
974                my $propertyCount = 0;
975          # Loop through the features, creating HasProperty records.          # Loop through the features, creating HasProperty records.
976          for my $fid (@features) {          for my $fid (@features) {
             $loadProperty->Add("featureIn");  
977              # 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
978              # to insure we do not get any genome attributes.              # to insure we do not get any genome attributes.
979              my @attributeList = $fig->get_attributes($fid, '', '', '');              my @attributeList = $fig->get_attributes($fid, '', '', '');
980                    # Add essentiality and virulence attributes.
981                    if ($fig->essential($fid)) {
982                        push @attributeList, [$fid, 'essential', 1, ''];
983                    }
984                    if ($fig->virulent($fid)) {
985                        push @attributeList, [$fid, 'virulent', 1, ''];
986                    }
987                    if (scalar @attributeList) {
988                        $featureCount++;
989                    }
990              # Loop through the attributes.              # Loop through the attributes.
991              for my $tuple (@attributeList) {              for my $tuple (@attributeList) {
992                        $propertyCount++;
993                  # Get this attribute value's data. Note that we throw away the FID,                  # Get this attribute value's data. Note that we throw away the FID,
994                  # since it will always be the same as the value if "$fid".                  # since it will always be the same as the value if "$fid".
995                  my (undef, $key, $value, $url) = @{$tuple};                  my (undef, $key, $value, $url) = @{$tuple};
# Line 845  Line 1011 
1011                  $loadHasProperty->Put($fid, $propertyID, $url);                  $loadHasProperty->Put($fid, $propertyID, $url);
1012              }              }
1013          }          }
1014                # Update the statistics.
1015                Trace("$propertyCount attributes processed for $featureCount features.") if T(3);
1016                $loadHasProperty->Add("featuresIn", $featureCount);
1017                $loadHasProperty->Add("propertiesIn", $propertyCount);
1018            }
1019      }      }
1020      # Finish the load.      # Finish the load.
1021      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
# Line 885  Line 1056 
1056      my $fig = $self->{fig};      my $fig = $self->{fig};
1057      # Get the genome hash.      # Get the genome hash.
1058      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1059      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1060      my $loadAnnotation = $self->_TableLoader('Annotation', $genomeCount * 4000);      my $loadAnnotation = $self->_TableLoader('Annotation');
1061      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation', $genomeCount * 4000);      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation', $self->PrimaryOnly);
1062      my $loadSproutUser = $self->_TableLoader('SproutUser', 100);      my $loadSproutUser = $self->_TableLoader('SproutUser', $self->PrimaryOnly);
1063      my $loadUserAccess = $self->_TableLoader('UserAccess', 1000);      my $loadUserAccess = $self->_TableLoader('UserAccess', $self->PrimaryOnly);
1064      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation', $genomeCount * 4000);      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation', $self->PrimaryOnly);
1065      Trace("Beginning annotation data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1066            Trace("Loading from existing files.") if T(2);
1067        } else {
1068            Trace("Generating annotation data.") if T(2);
1069      # 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
1070      # user records.      # user records.
1071      my %users = ( FIG => 1, master => 1 );      my %users = ( FIG => 1, master => 1 );
# Line 906  Line 1079 
1079      # Loop through the genomes.      # Loop through the genomes.
1080      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
1081          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);  
1082              # 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
1083              # from showing up for a single PEG's annotations.              # from showing up for a single PEG's annotations.
1084              my %seenTimestamps = ();              my %seenTimestamps = ();
1085              # Check for a functional assignment.              # Get the genome's annotations.
1086              my $func = $fig->function_of($peg);              my @annotations = $fig->read_all_annotations($genomeID);
1087              if ($func) {              Trace("Processing annotations.") if T(2);
1088                  # If this is NOT a hypothetical assignment, we create an              for my $tuple (@annotations) {
1089                  # assignment annotation for it.                  # Get the annotation tuple.
1090                  if (! FIG::hypo($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};  
1091                      # Here we fix up the annotation text. "\r" is removed,                      # Here we fix up the annotation text. "\r" is removed,
1092                      # and "\t" and "\n" are escaped. Note we use the "s"                  # and "\t" and "\n" are escaped. Note we use the "gs"
1093                      # modifier so that new-lines inside the text do not                      # modifier so that new-lines inside the text do not
1094                      # stop the substitution search.                      # stop the substitution search.
1095                      $text =~ s/\r//gs;                      $text =~ s/\r//gs;
# Line 941  Line 1099 
1099                      $text =~ s/Set master function/Set FIG function/s;                      $text =~ s/Set master function/Set FIG function/s;
1100                      # Insure the time stamp is valid.                      # Insure the time stamp is valid.
1101                      if ($timestamp =~ /^\d+$/) {                      if ($timestamp =~ /^\d+$/) {
1102                          # Here it's a number. We need to insure it's unique.                      # Here it's a number. We need to insure the one we use to form
1103                          while ($seenTimestamps{$timestamp}) {                      # the key is unique.
1104                              $timestamp++;                      my $keyStamp = $timestamp;
1105                        while ($seenTimestamps{"$peg:$keyStamp"}) {
1106                            $keyStamp++;
1107                          }                          }
1108                          $seenTimestamps{$timestamp} = 1;                      my $annotationID = "$peg:$keyStamp";
1109                          my $annotationID = "$peg:$timestamp";                      $seenTimestamps{$annotationID} = 1;
1110                          # Insure the user exists.                          # Insure the user exists.
1111                          if (! $users{$user}) {                          if (! $users{$user}) {
1112                              $loadSproutUser->Put($user, "SEED user");                              $loadSproutUser->Put($user, "SEED user");
# Line 954  Line 1114 
1114                              $users{$user} = 1;                              $users{$user} = 1;
1115                          }                          }
1116                          # Generate the annotation.                          # Generate the annotation.
1117                          $loadAnnotation->Put($annotationID, $timestamp, "$user\\n$text");                      $loadAnnotation->Put($annotationID, $timestamp, $text);
1118                          $loadIsTargetOfAnnotation->Put($peg, $annotationID);                          $loadIsTargetOfAnnotation->Put($peg, $annotationID);
1119                          $loadMadeAnnotation->Put($user, $annotationID);                          $loadMadeAnnotation->Put($user, $annotationID);
1120                      } else {                      } else {
# Line 964  Line 1124 
1124                  }                  }
1125              }              }
1126          }          }
     }  
1127      # Finish the load.      # Finish the load.
1128      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1129      return $retVal;      return $retVal;
# Line 1005  Line 1164 
1164      my $fig = $self->{fig};      my $fig = $self->{fig};
1165      # Get the genome hash.      # Get the genome hash.
1166      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1167      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1168      my $loadComesFrom = $self->_TableLoader('ComesFrom', $genomeCount * 4);      my $loadComesFrom = $self->_TableLoader('ComesFrom', $self->PrimaryOnly);
1169      my $loadSource = $self->_TableLoader('Source', $genomeCount * 4);      my $loadSource = $self->_TableLoader('Source');
1170      my $loadSourceURL = $self->_TableLoader('SourceURL', $genomeCount * 8);      my $loadSourceURL = $self->_TableLoader('SourceURL');
1171      Trace("Beginning source data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1172            Trace("Loading from existing files.") if T(2);
1173        } else {
1174            Trace("Generating annotation data.") if T(2);
1175      # Create hashes to collect the Source information.      # Create hashes to collect the Source information.
1176      my %sourceURL = ();      my %sourceURL = ();
1177      my %sourceDesc = ();      my %sourceDesc = ();
# Line 1024  Line 1185 
1185              chomp $line;              chomp $line;
1186              my($sourceID, $desc, $url) = split(/\t/,$line);              my($sourceID, $desc, $url) = split(/\t/,$line);
1187              $loadComesFrom->Put($genomeID, $sourceID);              $loadComesFrom->Put($genomeID, $sourceID);
1188              if ($url && ! exists $sourceURL{$genomeID}) {                  if ($url && ! exists $sourceURL{$sourceID}) {
1189                  $loadSourceURL->Put($sourceID, $url);                  $loadSourceURL->Put($sourceID, $url);
1190                  $sourceURL{$sourceID} = 1;                  $sourceURL{$sourceID} = 1;
1191              }              }
1192              if ($desc && ! exists $sourceDesc{$sourceID}) {                  if ($desc) {
1193                  $loadSource->Put($sourceID, $desc);                      $sourceDesc{$sourceID} = $desc;
1194                  $sourceDesc{$sourceID} = 1;                  } elsif (! exists $sourceDesc{$sourceID}) {
1195                        $sourceDesc{$sourceID} = $sourceID;
1196              }              }
1197          }          }
1198          close TMP;          close TMP;
1199      }      }
1200            # Write the source descriptions.
1201            for my $sourceID (keys %sourceDesc) {
1202                $loadSource->Put($sourceID, $sourceDesc{$sourceID});
1203            }
1204        }
1205      # Finish the load.      # Finish the load.
1206      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1207      return $retVal;      return $retVal;
# Line 1074  Line 1241 
1241      my $fig = $self->{fig};      my $fig = $self->{fig};
1242      # Get the genome hash.      # Get the genome hash.
1243      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1244      # 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
1245      # it the key.      # it the key.
1246      my %speciesHash = map { $fig->genus_species($_) => $_ } (keys %{$genomeHash});      my %speciesHash = map { $fig->genus_species($_) => $_ } (keys %{$genomeHash});
1247      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1248      my $loadExternalAliasFunc = $self->_TableLoader('ExternalAliasFunc', $genomeCount * 4000);      my $loadExternalAliasFunc = $self->_TableLoader('ExternalAliasFunc');
1249      my $loadExternalAliasOrg = $self->_TableLoader('ExternalAliasOrg', $genomeCount * 4000);      my $loadExternalAliasOrg = $self->_TableLoader('ExternalAliasOrg');
1250      Trace("Beginning external data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1251            Trace("Loading from existing files.") if T(2);
1252        } else {
1253            Trace("Generating external data.") if T(2);
1254      # 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.
1255      Open(\*ORGS, "<$FIG_Config::global/ext_org.table");          Open(\*ORGS, "sort +0 -1 -u -t\"\t\" $FIG_Config::global/ext_org.table |");
1256      my $orgLine;      my $orgLine;
1257      while (defined($orgLine = <ORGS>)) {      while (defined($orgLine = <ORGS>)) {
1258          # Clean the input line.          # Clean the input line.
# Line 1095  Line 1264 
1264      close ORGS;      close ORGS;
1265      # Now the function file.      # Now the function file.
1266      my $funcLine;      my $funcLine;
1267      Open(\*FUNCS, "<$FIG_Config::global/ext_func.table");          Open(\*FUNCS, "sort +0 -1 -u -t\"\t\" $FIG_Config::global/ext_func.table |");
1268      while (defined($funcLine = <FUNCS>)) {      while (defined($funcLine = <FUNCS>)) {
1269          # Clean the line ending.          # Clean the line ending.
1270          chomp $funcLine;          chomp $funcLine;
# Line 1111  Line 1280 
1280              $loadExternalAliasFunc->Put(@funcFields[0,1]);              $loadExternalAliasFunc->Put(@funcFields[0,1]);
1281          }          }
1282      }      }
1283        }
1284        # Finish the load.
1285        my $retVal = $self->_FinishAll();
1286        return $retVal;
1287    }
1288    
1289    
1290    =head3 LoadReactionData
1291    
1292    C<< my $stats = $spl->LoadReactionData(); >>
1293    
1294    Load the reaction data from FIG into Sprout.
1295    
1296    Reaction data connects reactions to the compounds that participate in them.
1297    
1298    The following relations are loaded by this method.
1299    
1300        Reaction
1301        ReactionURL
1302        Compound
1303        CompoundName
1304        CompoundCAS
1305        IsAComponentOf
1306    
1307    This method proceeds reaction by reaction rather than genome by genome.
1308    
1309    =over 4
1310    
1311    =item RETURNS
1312    
1313    Returns a statistics object for the loads.
1314    
1315    =back
1316    
1317    =cut
1318    #: Return Type $%;
1319    sub LoadReactionData {
1320        # Get this object instance.
1321        my ($self) = @_;
1322        # Get the FIG object.
1323        my $fig = $self->{fig};
1324        # Create load objects for each of the tables we're loading.
1325        my $loadReaction = $self->_TableLoader('Reaction');
1326        my $loadReactionURL = $self->_TableLoader('ReactionURL', $self->PrimaryOnly);
1327        my $loadCompound = $self->_TableLoader('Compound', $self->PrimaryOnly);
1328        my $loadCompoundName = $self->_TableLoader('CompoundName', $self->PrimaryOnly);
1329        my $loadCompoundCAS = $self->_TableLoader('CompoundCAS', $self->PrimaryOnly);
1330        my $loadIsAComponentOf = $self->_TableLoader('IsAComponentOf', $self->PrimaryOnly);
1331        if ($self->{options}->{loadOnly}) {
1332            Trace("Loading from existing files.") if T(2);
1333        } else {
1334            Trace("Generating annotation data.") if T(2);
1335            # First we create the compounds.
1336            my @compounds = $fig->all_compounds();
1337            for my $cid (@compounds) {
1338                # Check for names.
1339                my @names = $fig->names_of_compound($cid);
1340                # Each name will be given a priority number, starting with 1.
1341                my $prio = 1;
1342                for my $name (@names) {
1343                    $loadCompoundName->Put($cid, $name, $prio++);
1344                }
1345                # Create the main compound record. Note that the first name
1346                # becomes the label.
1347                my $label = (@names > 0 ? $names[0] : $cid);
1348                $loadCompound->Put($cid, $label);
1349                # Check for a CAS ID.
1350                my $cas = $fig->cas($cid);
1351                if ($cas) {
1352                    $loadCompoundCAS->Put($cid, $cas);
1353                }
1354            }
1355            # All the compounds are set up, so we need to loop through the reactions next. First,
1356            # we initialize the discriminator index. This is a single integer used to insure
1357            # duplicate elements in a reaction are not accidentally collapsed.
1358            my $discrim = 0;
1359            my @reactions = $fig->all_reactions();
1360            for my $reactionID (@reactions) {
1361                # Create the reaction record.
1362                $loadReaction->Put($reactionID, $fig->reversible($reactionID));
1363                # Compute the reaction's URL.
1364                my $url = HTML::reaction_link($reactionID);
1365                # Put it in the ReactionURL table.
1366                $loadReactionURL->Put($reactionID, $url);
1367                # Now we need all of the reaction's compounds. We get these in two phases,
1368                # substrates first and then products.
1369                for my $product (0, 1) {
1370                    # Get the compounds of the current type for the current reaction. FIG will
1371                    # give us 3-tuples: [ID, stoichiometry, main-flag]. At this time we do not
1372                    # have location data in SEED, so it defaults to the empty string.
1373                    my @compounds = $fig->reaction2comp($reactionID, $product);
1374                    for my $compData (@compounds) {
1375                        # Extract the compound data from the current tuple.
1376                        my ($cid, $stoich, $main) = @{$compData};
1377                        # Link the compound to the reaction.
1378                        $loadIsAComponentOf->Put($cid, $reactionID, $discrim++, "", $main,
1379                                                 $product, $stoich);
1380                    }
1381                }
1382            }
1383        }
1384      # Finish the load.      # Finish the load.
1385      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1386      return $retVal;      return $retVal;
# Line 1126  Line 1396 
1396    
1397      GenomeGroups      GenomeGroups
1398    
1399  There is no direct support for genome groups in FIG, so we access the SEED  Currently, we do not use groups. We used to use them for NMPDR groups,
1400    butThere is no direct support for genome groups in FIG, so we access the SEED
1401  files directly.  files directly.
1402    
1403  =over 4  =over 4
# Line 1146  Line 1417 
1417      my $fig = $self->{fig};      my $fig = $self->{fig};
1418      # Get the genome hash.      # Get the genome hash.
1419      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1420      # Create a load object for the table we're loading.      # Create a load object for the table we're loading.
1421      my $loadGenomeGroups = $self->_TableLoader('GenomeGroups', $genomeCount * 4);      my $loadGenomeGroups = $self->_TableLoader('GenomeGroups');
1422      Trace("Beginning group data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1423            Trace("Loading from existing files.") if T(2);
1424        } else {
1425            Trace("Generating group data.") if T(2);
1426            # Currently there are no groups.
1427        }
1428        # Finish the load.
1429        my $retVal = $self->_FinishAll();
1430        return $retVal;
1431    }
1432    
1433    =head3 LoadSynonymData
1434    
1435    C<< my $stats = $spl->LoadSynonymData(); >>
1436    
1437    Load the synonym groups into Sprout.
1438    
1439    The following relations are loaded by this method.
1440    
1441        SynonymGroup
1442        IsSynonymGroupFor
1443    
1444    The source information for these relations is taken from the C<maps_to_id> method
1445    of the B<FIG> object. Unfortunately, to make this work, we need to use direct
1446    SQL against the FIG database.
1447    
1448    =over 4
1449    
1450    =item RETURNS
1451    
1452    Returns a statistics object for the loads.
1453    
1454    =back
1455    
1456    =cut
1457    #: Return Type $%;
1458    sub LoadSynonymData {
1459        # Get this object instance.
1460        my ($self) = @_;
1461        # Get the FIG object.
1462        my $fig = $self->{fig};
1463        # Get the genome hash.
1464        my $genomeHash = $self->{genomes};
1465        # Create a load object for the table we're loading.
1466        my $loadSynonymGroup = $self->_TableLoader('SynonymGroup');
1467        my $loadIsSynonymGroupFor = $self->_TableLoader('IsSynonymGroupFor');
1468        if ($self->{options}->{loadOnly}) {
1469            Trace("Loading from existing files.") if T(2);
1470        } else {
1471            Trace("Generating synonym group data.") if T(2);
1472            # Get the database handle.
1473            my $dbh = $fig->db_handle();
1474            # Ask for the synonyms.
1475            my $sth = $dbh->prepare_command("SELECT maps_to, syn_id FROM peg_synonyms ORDER BY maps_to");
1476            my $result = $sth->execute();
1477            if (! defined($result)) {
1478                Confess("Database error in Synonym load: " . $sth->errstr());
1479            } else {
1480                # Remember the current synonym.
1481                my $current_syn = "";
1482                # Count the features.
1483                my $featureCount = 0;
1484                # Loop through the synonym/peg pairs.
1485                while (my @row = $sth->fetchrow()) {
1486                    # Get the synonym ID and feature ID.
1487                    my ($syn_id, $peg) = @row;
1488                    # Insure it's for one of our genomes.
1489                    my $genomeID = FIG::genome_of($peg);
1490                    if (exists $genomeHash->{$genomeID}) {
1491                        # Verify the synonym.
1492                        if ($syn_id ne $current_syn) {
1493                            # It's new, so put it in the group table.
1494                            $loadSynonymGroup->Put($syn_id);
1495                            $current_syn = $syn_id;
1496                        }
1497                        # Connect the synonym to the peg.
1498                        $loadIsSynonymGroupFor->Put($syn_id, $peg);
1499                        # Count this feature.
1500                        $featureCount++;
1501                        if ($featureCount % 1000 == 0) {
1502                            Trace("$featureCount features processed.") if T(3);
1503                        }
1504                    }
1505                }
1506            }
1507        }
1508        # Finish the load.
1509        my $retVal = $self->_FinishAll();
1510        return $retVal;
1511    }
1512    
1513    =head3 LoadFamilyData
1514    
1515    C<< my $stats = $spl->LoadFamilyData(); >>
1516    
1517    Load the protein families into Sprout.
1518    
1519    The following relations are loaded by this method.
1520    
1521        Family
1522        IsFamilyForFeature
1523    
1524    The source information for these relations is taken from the C<families_for_protein>,
1525    C<family_function>, and C<sz_family> methods of the B<FIG> object.
1526    
1527    =over 4
1528    
1529    =item RETURNS
1530    
1531    Returns a statistics object for the loads.
1532    
1533    =back
1534    
1535    =cut
1536    #: Return Type $%;
1537    sub LoadFamilyData {
1538        # Get this object instance.
1539        my ($self) = @_;
1540        # Get the FIG object.
1541        my $fig = $self->{fig};
1542        # Get the genome hash.
1543        my $genomeHash = $self->{genomes};
1544        # Create load objects for the tables we're loading.
1545        my $loadFamily = $self->_TableLoader('Family');
1546        my $loadIsFamilyForFeature = $self->_TableLoader('IsFamilyForFeature');
1547        if ($self->{options}->{loadOnly}) {
1548            Trace("Loading from existing files.") if T(2);
1549        } else {
1550            Trace("Generating family data.") if T(2);
1551            # Create a hash for the family IDs.
1552            my %familyHash = ();
1553      # Loop through the genomes.      # Loop through the genomes.
1554      my $line;          for my $genomeID (sort keys %{$genomeHash}) {
1555      for my $genomeID (keys %{$genomeHash}) {              Trace("Processing features for $genomeID.") if T(2);
1556          Trace("Processing $genomeID.") if T(3);              # Loop through this genome's PEGs.
1557          # Open the NMPDR group file for this genome.              for my $fid ($fig->all_features($genomeID, "peg")) {
1558          if (open(TMP, "<$FIG_Config::organisms/$genomeID/NMPDR") &&                  $loadIsFamilyForFeature->Add("features", 1);
1559              defined($line = <TMP>)) {                  # Get this feature's families.
1560              # Clean the line ending.                  my @families = $fig->families_for_protein($fid);
1561              chomp $line;                  # Loop through the families, connecting them to the feature.
1562              # Add the group to the table. Note that there can only be one group                  for my $family (@families) {
1563              # per genome.                      $loadIsFamilyForFeature->Put($family, $fid);
1564              $loadGenomeGroups->Put($genomeID, $line);                      # If this is a new family, create a record for it.
1565                        if (! exists $familyHash{$family}) {
1566                            $familyHash{$family} = 1;
1567                            $loadFamily->Add("families", 1);
1568                            my $size = $fig->sz_family($family);
1569                            my $func = $fig->family_function($family);
1570                            $loadFamily->Put($family, $size, $func);
1571                        }
1572                    }
1573                }
1574          }          }
         close TMP;  
1575      }      }
1576      # Finish the load.      # Finish the load.
1577      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1578      return $retVal;      return $retVal;
1579  }  }
1580    
1581    
1582    
1583  =head2 Internal Utility Methods  =head2 Internal Utility Methods
1584    
1585  =head3 TableLoader  =head3 TableLoader
# Line 1186  Line 1596 
1596    
1597  Name of the table (relation) being loaded.  Name of the table (relation) being loaded.
1598    
1599  =item rowCount (optional)  =item ignore
1600    
1601  Estimated maximum number of rows in the table.  TRUE if the table should be ignored entirely, else FALSE.
1602    
1603  =item RETURN  =item RETURN
1604    
# Line 1200  Line 1610 
1610    
1611  sub _TableLoader {  sub _TableLoader {
1612      # Get the parameters.      # Get the parameters.
1613      my ($self, $tableName, $rowCount) = @_;      my ($self, $tableName, $ignore) = @_;
1614      # Create the load object.      # Create the load object.
1615      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $rowCount);      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $self->LoadOnly,
1616                                   $ignore);
1617      # Cache it in the loader list.      # Cache it in the loader list.
1618      push @{$self->{loaders}}, $retVal;      push @{$self->{loaders}}, $retVal;
1619      # Return it to the caller.      # Return it to the caller.
# Line 1236  Line 1647 
1647      my $retVal = Stats->new();      my $retVal = Stats->new();
1648      # Get the loader list.      # Get the loader list.
1649      my $loadList = $self->{loaders};      my $loadList = $self->{loaders};
1650        # Create a hash to hold the statistics objects, keyed on relation name.
1651        my %loaderHash = ();
1652      # 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
1653      # 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.
1654      while (my $loader = pop @{$loadList}) {      while (my $loader = pop @{$loadList}) {
1655            # Get the relation name.
1656            my $relName = $loader->RelName;
1657            # Check the ignore flag.
1658            if ($loader->Ignore) {
1659                Trace("Relation $relName not loaded.") if T(2);
1660            } else {
1661                # Here we really need to finish.
1662                Trace("Finishing $relName.") if T(2);
1663          my $stats = $loader->Finish();          my $stats = $loader->Finish();
1664                $loaderHash{$relName} = $stats;
1665            }
1666        }
1667        # Now we loop through again, actually loading the tables. We want to finish before
1668        # loading so that if something goes wrong at this point, all the load files are usable
1669        # and we don't have to redo all that work.
1670        for my $relName (sort keys %loaderHash) {
1671            # Get the statistics for this relation.
1672            my $stats = $loaderHash{$relName};
1673            # Check for a database load.
1674            if ($self->{options}->{dbLoad}) {
1675                # Here we want to use the load file just created to load the database.
1676                Trace("Loading relation $relName.") if T(2);
1677                my $newStats = $self->{sprout}->LoadUpdate(1, [$relName]);
1678                # Accumulate the statistics from the DB load.
1679                $stats->Accumulate($newStats);
1680            }
1681          $retVal->Accumulate($stats);          $retVal->Accumulate($stats);
         my $relName = $loader->RelName;  
1682          Trace("Statistics for $relName:\n" . $stats->Show()) if T(2);          Trace("Statistics for $relName:\n" . $stats->Show()) if T(2);
1683      }      }
1684      # Return the load statistics.      # Return the load statistics.

Legend:
Removed from v.1.9  
changed lines
  Added in v.1.75

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3