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

Diff of /Sprout/ERDB.pm

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

revision 1.18, Sun Aug 14 23:32:08 2005 UTC revision 1.23, Thu Sep 15 01:46:56 2005 UTC
# Line 9  Line 9 
9      use DBObject;      use DBObject;
10      use Stats;      use Stats;
11      use Time::HiRes qw(gettimeofday);      use Time::HiRes qw(gettimeofday);
12        use FIG;
13    
14  =head1 Entity-Relationship Database Package  =head1 Entity-Relationship Database Package
15    
# Line 552  Line 553 
553  sub CreateTables {  sub CreateTables {
554      # Get the parameters.      # Get the parameters.
555      my ($self) = @_;      my ($self) = @_;
556      my $metadata = $self->{_metaData};      # Get the relation names.
557      my $dbh = $self->{_dbh};      my @relNames = $self->GetTableNames();
558      # Loop through the entities.      # Loop through the relations.
559      my $entityHash = $metadata->{Entities};      for my $relationName (@relNames) {
     for my $entityName (keys %{$entityHash}) {  
         my $entityData = $entityHash->{$entityName};  
         # Tell the user what we're doing.  
         Trace("Creating relations for entity $entityName.") if T(1);  
         # Loop through the entity's relations.  
         for my $relationName (keys %{$entityData->{Relations}}) {  
560              # Create a table for this relation.              # Create a table for this relation.
561              $self->CreateTable($relationName);              $self->CreateTable($relationName);
562              Trace("Relation $relationName created.") if T(1);          Trace("Relation $relationName created.") if T(2);
         }  
     }  
     # Loop through the relationships.  
     my $relationshipTable = $metadata->{Relationships};  
     for my $relationshipName (keys %{$metadata->{Relationships}}) {  
         # Create a table for this relationship.  
         Trace("Creating relationship $relationshipName.") if T(1);  
         $self->CreateTable($relationshipName);  
563      }      }
564  }  }
565    
# Line 723  Line 710 
710      $directoryName =~ s!/\\$!!;      $directoryName =~ s!/\\$!!;
711      # Declare the return variable.      # Declare the return variable.
712      my $retVal = Stats->new();      my $retVal = Stats->new();
713      # Get the metadata structure.      # Get the relation names.
714      my $metaData = $self->{_metaData};      my @relNames = $self->GetTableNames();
715      # Loop through the entities.      for my $relationName (@relNames) {
     for my $entity (values %{$metaData->{Entities}}) {  
         # Loop through the entity's relations.  
         for my $relationName (keys %{$entity->{Relations}}) {  
716              # Try to load this relation.              # Try to load this relation.
717              my $result = $self->_LoadRelation($directoryName, $relationName, $rebuild);              my $result = $self->_LoadRelation($directoryName, $relationName, $rebuild);
718              # Accumulate the statistics.              # Accumulate the statistics.
719              $retVal->Accumulate($result);              $retVal->Accumulate($result);
720          }          }
     }  
     # Loop through the relationships.  
     for my $relationshipName (keys %{$metaData->{Relationships}}) {  
         # Try to load this relationship's relation.  
         my $result = $self->_LoadRelation($directoryName, $relationshipName, $rebuild);  
         # Accumulate the statistics.  
         $retVal->Accumulate($result);  
     }  
721      # Add the duration of the load to the statistical object.      # Add the duration of the load to the statistical object.
722      $retVal->Add('duration', gettimeofday - $startTime);      $retVal->Add('duration', gettimeofday - $startTime);
723      # Return the accumulated statistics.      # Return the accumulated statistics.
724      return $retVal;      return $retVal;
725  }  }
726    
727    
728  =head3 GetTableNames  =head3 GetTableNames
729    
730  C<< my @names = $erdb->GetTableNames; >>  C<< my @names = $erdb->GetTableNames; >>
# Line 782  Line 759 
759      return sort keys %{$entityList};      return sort keys %{$entityList};
760  }  }
761    
762    =head3 IsEntity
763    
764    C<< my $flag = $erdb->IsEntity($entityName); >>
765    
766    Return TRUE if the parameter is an entity name, else FALSE.
767    
768    =over 4
769    
770    =item entityName
771    
772    Object name to be tested.
773    
774    =item RETURN
775    
776    Returns TRUE if the specified string is an entity name, else FALSE.
777    
778    =back
779    
780    =cut
781    
782    sub IsEntity {
783        # Get the parameters.
784        my ($self, $entityName) = @_;
785        # Test to see if it's an entity.
786        return exists $self->{_metaData}->{Entities}->{$entityName};
787    }
788    
789  =head3 Get  =head3 Get
790    
791  C<< my $query = $erdb->Get(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  C<< my $query = $erdb->Get(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>
# Line 1299  Line 1303 
1303      Trace("Loading table $relationName from $fileName") if T(2);      Trace("Loading table $relationName from $fileName") if T(2);
1304      # Get the database handle.      # Get the database handle.
1305      my $dbh = $self->{_dbh};      my $dbh = $self->{_dbh};
1306        # Get the input file size.
1307        my $fileSize = -s $fileName;
1308      # Get the relation data.      # Get the relation data.
1309      my $relation = $self->_FindRelation($relationName);      my $relation = $self->_FindRelation($relationName);
1310      # Check the truncation flag.      # Check the truncation flag.
1311      if ($truncateFlag) {      if ($truncateFlag) {
1312          Trace("Creating table $relationName") if T(2);          Trace("Creating table $relationName") if T(2);
1313            # Compute the row count estimate. We take the size of the load file,
1314            # divide it by the estimated row size, and then multiply by 1.5 to
1315            # leave extra room. We postulate a minimum row count of 1000 to
1316            # prevent problems with incoming empty load files.
1317            my $rowSize = $self->EstimateRowSize($relationName);
1318            my $estimate = FIG::max($fileSize * 1.5 / $rowSize, 1000);
1319          # Re-create the table without its index.          # Re-create the table without its index.
1320          $self->CreateTable($relationName, 0);          $self->CreateTable($relationName, 0, $estimate);
1321          # If this is a pre-index DBMS, create the index here.          # If this is a pre-index DBMS, create the index here.
1322          if ($dbh->{_preIndex}) {          if ($dbh->{_preIndex}) {
1323              eval {              eval {
# Line 1316  Line 1328 
1328              }              }
1329          }          }
1330      }      }
     # Determine whether or not this is a primary relation. Primary relations have an extra  
     # field indicating whether or not a given object is new or was loaded from the flat files.  
     my $primary = $self->_IsPrimary($relationName);  
     # Get the number of fields in this relation.  
     my @fieldList = @{$relation->{Fields}};  
     my $fieldCount = @fieldList;  
     # Start a database transaction.  
     $dbh->begin_tran;  
     # Open the relation file. We need to create a cleaned-up copy before loading.  
     open TABLEIN, '<', $fileName;  
     my $tempName = "$fileName.tbl";  
     open TABLEOUT, '>', $tempName;  
     my $inputCount = 0;  
     # Loop through the file.  
     while (<TABLEIN>) {  
         $inputCount++;  
         # Chop off the new-line character.  
         my $record = Tracer::Strip($_);  
         # Only proceed if the record is non-blank.  
         if ($record) {  
             # Escape all the backslashes found in the line.  
             $record =~ s/\\/\\\\/g;  
             # Insure the number of fields is correct.  
             my @fields = split /\t/, $record;  
             while (@fields > $fieldCount) {  
                 my $extraField = $fields[$#fields];  
                 delete $fields[$#fields];  
                 if ($extraField) {  
                     Trace("Nonblank extra field value \"$extraField\" deleted from record $inputCount of $fileName.") if T(1);  
                 }  
             }  
             while (@fields < $fieldCount) {  
                 push @fields, "";  
             }  
             # If this is a primary relation, add a 0 for the new-record flag (indicating that  
             # this record is not new, but part of the original load).  
             if ($primary) {  
                 push @fields, "0";  
             }  
             # Write the record.  
             $record = join "\t", @fields;  
             print TABLEOUT "$record\n";  
             # Count the record written.  
             my $count = $retVal->Add('records');  
             my $len = length $record;  
             Trace("Record $count written with $len characters.") if T(4);  
         } else {  
             # Here we have a blank record.  
             $retVal->Add('skipped');  
         }  
     }  
     # Close the files.  
     close TABLEIN;  
     close TABLEOUT;  
     Trace("Temporary file $tempName created.") if T(2);  
1331      # Load the table.      # Load the table.
1332      my $rv;      my $rv;
1333      eval {      eval {
1334          $rv = $dbh->load_table(file => $tempName, tbl => $relationName);          $rv = $dbh->load_table(file => $fileName, tbl => $relationName);
1335      };      };
1336      if (!defined $rv) {      if (!defined $rv) {
1337          $retVal->AddMessage($@) if ($@);          $retVal->AddMessage($@) if ($@);
1338          $retVal->AddMessage("Table load failed for $relationName using $tempName.");          $retVal->AddMessage("Table load failed for $relationName using $fileName.");
1339          Trace("Table load failed for $relationName.") if T(1);          Trace("Table load failed for $relationName.") if T(1);
1340      } else {      } else {
1341          # Here we successfully loaded the table. Trace the number of records loaded.          # Here we successfully loaded the table.
1342          Trace("$retVal->{records} records read for $relationName.") if T(2);          $retVal->Add("tables");
1343            my $size = -s $fileName;
1344            Trace("$size bytes loaded into $relationName.") if T(2);
1345          # If we're rebuilding, we need to create the table indexes.          # If we're rebuilding, we need to create the table indexes.
1346          if ($truncateFlag && ! $dbh->{_preIndex}) {          if ($truncateFlag && ! $dbh->{_preIndex}) {
1347              eval {              eval {
# Line 1392  Line 1351 
1351                  $retVal->AddMessage($@);                  $retVal->AddMessage($@);
1352              }              }
1353          }          }
         # Analyze the table to help optimize tables.  
1354      }      }
1355      # Commit the database changes.      # Commit the database changes.
1356      $dbh->commit_tran;      $dbh->commit_tran;
1357        # Analyze the table to improve performance.
1358      $dbh->vacuum_it($relationName);      $dbh->vacuum_it($relationName);
     # Delete the temporary file.  
     unlink $tempName;  
1359      # Return the statistics.      # Return the statistics.
1360      return $retVal;      return $retVal;
1361  }  }
# Line 2247  Line 2204 
2204          my @fromList = ();          my @fromList = ();
2205          my @toList = ();          my @toList = ();
2206          my @bothList = ();          my @bothList = ();
2207          Trace("Join table build for $entityName.") if T(4);          Trace("Join table build for $entityName.") if T(metadata => 4);
2208          for my $relationshipName (keys %{$relationshipList}) {          for my $relationshipName (keys %{$relationshipList}) {
2209              my $relationship = $relationshipList->{$relationshipName};              my $relationship = $relationshipList->{$relationshipName};
2210              # Determine if this relationship has our entity in one of its link fields.              # Determine if this relationship has our entity in one of its link fields.
# Line 2258  Line 2215 
2215                  if ($toEntity eq $entityName) {                  if ($toEntity eq $entityName) {
2216                      # Here the relationship is recursive.                      # Here the relationship is recursive.
2217                      push @bothList, $relationshipName;                      push @bothList, $relationshipName;
2218                      Trace("Relationship $relationshipName put in both-list.") if T(4);                      Trace("Relationship $relationshipName put in both-list.") if T(metadata => 4);
2219                  } else {                  } else {
2220                      # Here the relationship comes from the entity.                      # Here the relationship comes from the entity.
2221                      push @fromList, $relationshipName;                      push @fromList, $relationshipName;
2222                      Trace("Relationship $relationshipName put in from-list.") if T(4);                      Trace("Relationship $relationshipName put in from-list.") if T(metadata => 4);
2223                  }                  }
2224              } elsif ($toEntity eq $entityName) {              } elsif ($toEntity eq $entityName) {
2225                  # Here the relationship goes to the entity.                  # Here the relationship goes to the entity.
2226                  push @toList, $relationshipName;                  push @toList, $relationshipName;
2227                  Trace("Relationship $relationshipName put in to-list.") if T(4);                  Trace("Relationship $relationshipName put in to-list.") if T(metadata => 4);
2228              }              }
2229          }          }
2230          # Create the nonrecursive joins. Note that we build two hashes for running          # Create the nonrecursive joins. Note that we build two hashes for running
# Line 2283  Line 2240 
2240                  # Create joins between the entity and this relationship.                  # Create joins between the entity and this relationship.
2241                  my $linkField = "$relationshipName.${linkType}_link";                  my $linkField = "$relationshipName.${linkType}_link";
2242                  my $joinClause = "$entityName.id = $linkField";                  my $joinClause = "$entityName.id = $linkField";
2243                  Trace("Entity join clause is $joinClause for $entityName and $relationshipName.") if T(4);                  Trace("Entity join clause is $joinClause for $entityName and $relationshipName.") if T(metadata => 4);
2244                  $joinTable{"$entityName/$relationshipName"} = $joinClause;                  $joinTable{"$entityName/$relationshipName"} = $joinClause;
2245                  $joinTable{"$relationshipName/$entityName"} = $joinClause;                  $joinTable{"$relationshipName/$entityName"} = $joinClause;
2246                  # Create joins between this relationship and the other relationships.                  # Create joins between this relationship and the other relationships.
# Line 2304  Line 2261 
2261                              # relationship and itself are prohibited.                              # relationship and itself are prohibited.
2262                              my $relJoinClause = "$otherName.${otherType}_link = $linkField";                              my $relJoinClause = "$otherName.${otherType}_link = $linkField";
2263                              $joinTable{$joinKey} = $relJoinClause;                              $joinTable{$joinKey} = $relJoinClause;
2264                              Trace("Relationship join clause is $relJoinClause for $joinKey.") if T(4);                              Trace("Relationship join clause is $relJoinClause for $joinKey.") if T(metadata => 4);
2265                          }                          }
2266                      }                      }
2267                  }                  }
# Line 2313  Line 2270 
2270                  # relationship can only be ambiguous with another recursive relationship,                  # relationship can only be ambiguous with another recursive relationship,
2271                  # and the incoming relationship from the outer loop is never recursive.                  # and the incoming relationship from the outer loop is never recursive.
2272                  for my $otherName (@bothList) {                  for my $otherName (@bothList) {
2273                      Trace("Setting up relationship joins to recursive relationship $otherName with $relationshipName.") if T(4);                      Trace("Setting up relationship joins to recursive relationship $otherName with $relationshipName.") if T(metadata => 4);
2274                      # Join from the left.                      # Join from the left.
2275                      $joinTable{"$relationshipName/$otherName"} =                      $joinTable{"$relationshipName/$otherName"} =
2276                          "$linkField = $otherName.from_link";                          "$linkField = $otherName.from_link";
# Line 2328  Line 2285 
2285          # rise to situations where we can't create the path we want; however, it is always          # rise to situations where we can't create the path we want; however, it is always
2286          # possible to get the same effect using multiple queries.          # possible to get the same effect using multiple queries.
2287          for my $relationshipName (@bothList) {          for my $relationshipName (@bothList) {
2288              Trace("Setting up entity joins to recursive relationship $relationshipName with $entityName.") if T(4);              Trace("Setting up entity joins to recursive relationship $relationshipName with $entityName.") if T(metadata => 4);
2289              # Join to the entity from each direction.              # Join to the entity from each direction.
2290              $joinTable{"$entityName/$relationshipName"} =              $joinTable{"$entityName/$relationshipName"} =
2291                  "$entityName.id = $relationshipName.from_link";                  "$entityName.id = $relationshipName.from_link";

Legend:
Removed from v.1.18  
changed lines
  Added in v.1.23

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3