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

Diff of /Sprout/ERDB.pm

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

revision 1.16, Tue Jun 28 23:51:06 2005 UTC revision 1.49, Wed Jun 21 03:36:03 2006 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 Digest::MD5 qw(md5_base64);
13        use FIG;
14    
15  =head1 Entity-Relationship Database Package  =head1 Entity-Relationship Database Package
16    
# Line 108  Line 110 
110  compatability with certain database packages), but the only values supported are  compatability with certain database packages), but the only values supported are
111  0 and 1.  0 and 1.
112    
113    =item id-string
114    
115    variable-length string, maximum 25 characters
116    
117  =item key-string  =item key-string
118    
119  variable-length string, maximum 40 characters  variable-length string, maximum 40 characters
# Line 124  Line 130 
130    
131  variable-length string, maximum 255 characters  variable-length string, maximum 255 characters
132    
133    =item hash-string
134    
135    variable-length string, maximum 22 characters
136    
137  =back  =back
138    
139    The hash-string data type has a special meaning. The actual key passed into the loader will
140    be a string, but it will be digested into a 22-character MD5 code to save space. Although the
141    MD5 algorithm is not perfect, it is extremely unlikely two strings will have the same
142    digest. Therefore, it is presumed the keys will be unique. When the database is actually
143    in use, the hashed keys will be presented rather than the original values. For this reason,
144    they should not be used for entities where the key is meaningful.
145    
146  =head3 Global Tags  =head3 Global Tags
147    
148  The entire database definition must be inside a B<Database> tag. The display name of  The entire database definition must be inside a B<Database> tag. The display name of
# Line 300  Line 317 
317  # Table of information about our datatypes. "sqlType" is the corresponding SQL datatype string.  # Table of information about our datatypes. "sqlType" is the corresponding SQL datatype string.
318  # "maxLen" is the maximum permissible length of the incoming string data used to populate a field  # "maxLen" is the maximum permissible length of the incoming string data used to populate a field
319  # of the specified type. "dataGen" is PERL string that will be evaluated if no test data generation  # of the specified type. "dataGen" is PERL string that will be evaluated if no test data generation
320   #string is specified in the field definition.  # string is specified in the field definition. "avgLen" is the average byte length for estimating
321  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            dataGen => "StringGen('A')" },  # record sizes.
322                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           dataGen => "IntGen(0, 99999999)" },  my %TypeTable = ( char =>    { sqlType => 'CHAR(1)',            maxLen => 1,            avgLen =>   1, dataGen => "StringGen('A')" },
323                    string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          dataGen => "StringGen(IntGen(10,250))" },                    int =>     { sqlType => 'INTEGER',            maxLen => 20,           avgLen =>   4, dataGen => "IntGen(0, 99999999)" },
324                    text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   dataGen => "StringGen(IntGen(80,1000))" },                    string =>  { sqlType => 'VARCHAR(255)',       maxLen => 255,          avgLen => 100, dataGen => "StringGen(IntGen(10,250))" },
325                    date =>    { sqlType => 'BIGINT',             maxLen => 80,           dataGen => "DateGen(-7, 7, IntGen(0,1400))" },                    text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, dataGen => "StringGen(IntGen(80,1000))" },
326                    float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           dataGen => "FloatGen(0.0, 100.0)" },                    date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, dataGen => "DateGen(-7, 7, IntGen(0,1400))" },
327                    boolean => { sqlType => 'SMALLINT',           maxLen => 1,            dataGen => "IntGen(0, 1)" },                    float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, dataGen => "FloatGen(0.0, 100.0)" },
328                      boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, dataGen => "IntGen(0, 1)" },
329                     'hash-string' =>
330                                 { sqlType => 'VARCHAR(22)',        maxLen => 22,           avgLen =>  22, dataGen => "SringGen(22)" },
331                     'id-string' =>
332                                 { sqlType => 'VARCHAR(25)',        maxLen => 25,           avgLen =>  25, dataGen => "SringGen(22)" },
333                   'key-string' =>                   'key-string' =>
334                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           dataGen => "StringGen(IntGen(10,40))" },                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, dataGen => "StringGen(IntGen(10,40))" },
335                   'name-string' =>                   'name-string' =>
336                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           dataGen => "StringGen(IntGen(10,80))" },                               { sqlType => 'VARCHAR(80)',        maxLen => 80,           avgLen =>  40, dataGen => "StringGen(IntGen(10,80))" },
337                   'medium-string' =>                   'medium-string' =>
338                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          dataGen => "StringGen(IntGen(10,160))" },                               { sqlType => 'VARCHAR(160)',       maxLen => 160,          avgLen =>  40, dataGen => "StringGen(IntGen(10,160))" },
339                  );                  );
340    
341  # Table translating arities into natural language.  # Table translating arities into natural language.
# Line 369  Line 391 
391    
392  =head3 ShowMetaData  =head3 ShowMetaData
393    
394  C<< $database->ShowMetaData($fileName); >>  C<< $erdb->ShowMetaData($fileName); >>
395    
396  This method outputs a description of the database. This description can be used to help users create  This method outputs a description of the database. This description can be used to help users create
397  the data to be loaded into the relations.  the data to be loaded into the relations.
# Line 400  Line 422 
422      # Write the HTML heading stuff.      # Write the HTML heading stuff.
423      print HTMLOUT "<html>\n<head>\n<title>$title</title>\n";      print HTMLOUT "<html>\n<head>\n<title>$title</title>\n";
424      print HTMLOUT "</head>\n<body>\n";      print HTMLOUT "</head>\n<body>\n";
425        # Write the documentation.
426        print HTMLOUT $self->DisplayMetaData();
427        # Close the document.
428        print HTMLOUT "</body>\n</html>\n";
429        # Close the file.
430        close HTMLOUT;
431    }
432    
433    =head3 DisplayMetaData
434    
435    C<< my $html = $erdb->DisplayMetaData(); >>
436    
437    Return an HTML description of the database. This description can be used to help users create
438    the data to be loaded into the relations and form queries. The output is raw includable HTML
439    without any HEAD or BODY tags.
440    
441    =over 4
442    
443    =item filename
444    
445    The name of the output file.
446    
447    =back
448    
449    =cut
450    
451    sub DisplayMetaData {
452        # Get the parameters.
453        my ($self) = @_;
454        # Get the metadata and the title string.
455        my $metadata = $self->{_metaData};
456        # Get the title string.
457        my $title = $metadata->{Title};
458        # Get the entity and relationship lists.
459        my $entityList = $metadata->{Entities};
460        my $relationshipList = $metadata->{Relationships};
461        # Declare the return variable.
462        my $retVal = "";
463        # Open the output file.
464        Trace("Building MetaData table of contents.") if T(4);
465      # Here we do the table of contents. It starts as an unordered list of section names. Each      # Here we do the table of contents. It starts as an unordered list of section names. Each
466      # section contains an ordered list of entity or relationship subsections.      # section contains an ordered list of entity or relationship subsections.
467      print HTMLOUT "<ul>\n<li><a href=\"#EntitiesSection\">Entities</a>\n<ol>\n";      $retVal .= "<ul>\n<li><a href=\"#EntitiesSection\">Entities</a>\n<ol>\n";
468      # Loop through the Entities, displaying a list item for each.      # Loop through the Entities, displaying a list item for each.
469      foreach my $key (sort keys %{$entityList}) {      foreach my $key (sort keys %{$entityList}) {
470          # Display this item.          # Display this item.
471          print HTMLOUT "<li><a href=\"#$key\">$key</a></li>\n";          $retVal .= "<li><a href=\"#$key\">$key</a></li>\n";
472      }      }
473      # Close off the entity section and start the relationship section.      # Close off the entity section and start the relationship section.
474      print HTMLOUT "</ol></li>\n<li><a href=\"#RelationshipsSection\">Relationships</a>\n<ol>\n";      $retVal .= "</ol></li>\n<li><a href=\"#RelationshipsSection\">Relationships</a>\n<ol>\n";
475      # Loop through the Relationships.      # Loop through the Relationships.
476      foreach my $key (sort keys %{$relationshipList}) {      foreach my $key (sort keys %{$relationshipList}) {
477          # Display this item.          # Display this item.
478          my $relationshipTitle = _ComputeRelationshipSentence($key, $relationshipList->{$key});          my $relationshipTitle = _ComputeRelationshipSentence($key, $relationshipList->{$key});
479          print HTMLOUT "<li><a href=\"#$key\">$relationshipTitle</a></li>\n";          $retVal .= "<li><a href=\"#$key\">$relationshipTitle</a></li>\n";
480      }      }
481      # Close off the relationship section and list the join table section.      # Close off the relationship section and list the join table section.
482      print HTMLOUT "</ol></li>\n<li><a href=\"#JoinTable\">Join Table</a></li>\n";      $retVal .= "</ol></li>\n<li><a href=\"#JoinTable\">Join Table</a></li>\n";
483      # Close off the table of contents itself.      # Close off the table of contents itself.
484      print HTMLOUT "</ul>\n";      $retVal .=  "</ul>\n";
485      # Now we start with the actual data. Denote we're starting the entity section.      # Now we start with the actual data. Denote we're starting the entity section.
486      print HTMLOUT "<a name=\"EntitiesSection\"></a><h2>Entities</h2>\n";      $retVal .= "<a name=\"EntitiesSection\"></a><h2>Entities</h2>\n";
487      # Loop through the entities.      # Loop through the entities.
488      for my $key (sort keys %{$entityList}) {      for my $key (sort keys %{$entityList}) {
489          Trace("Building MetaData entry for $key entity.") if T(4);          Trace("Building MetaData entry for $key entity.") if T(4);
490          # Create the entity header. It contains a bookmark and the entity name.          # Create the entity header. It contains a bookmark and the entity name.
491          print HTMLOUT "<a name=\"$key\"></a><h3>$key</h3>\n";          $retVal .= "<a name=\"$key\"></a><h3>$key</h3>\n";
492          # Get the entity data.          # Get the entity data.
493          my $entityData = $entityList->{$key};          my $entityData = $entityList->{$key};
494          # If there's descriptive text, display it.          # If there's descriptive text, display it.
495          if (my $notes = $entityData->{Notes}) {          if (my $notes = $entityData->{Notes}) {
496              print HTMLOUT "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . _HTMLNote($notes->{content}) . "</p>\n";
497          }          }
498          # Now we want a list of the entity's relationships. First, we set up the relationship subsection.          # Now we want a list of the entity's relationships. First, we set up the relationship subsection.
499          print HTMLOUT "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";          $retVal .= "<h4>Relationships for <b>$key</b></h4>\n<ul>\n";
500          # Loop through the relationships.          # Loop through the relationships.
501          for my $relationship (sort keys %{$relationshipList}) {          for my $relationship (sort keys %{$relationshipList}) {
502              # Get the relationship data.              # Get the relationship data.
# Line 444  Line 506 
506                  # Get the relationship sentence and append the arity.                  # Get the relationship sentence and append the arity.
507                  my $relationshipDescription = _ComputeRelationshipSentence($relationship, $relationshipStructure);                  my $relationshipDescription = _ComputeRelationshipSentence($relationship, $relationshipStructure);
508                  # Display the relationship data.                  # Display the relationship data.
509                  print HTMLOUT "<li><a href=\"#$relationship\">$relationshipDescription</a></li>\n";                  $retVal .= "<li><a href=\"#$relationship\">$relationshipDescription</a></li>\n";
510              }              }
511          }          }
512          # Close off the relationship list.          # Close off the relationship list.
513          print HTMLOUT "</ul>\n";          $retVal .= "</ul>\n";
514          # Get the entity's relations.          # Get the entity's relations.
515          my $relationList = $entityData->{Relations};          my $relationList = $entityData->{Relations};
516          # Create a header for the relation subsection.          # Create a header for the relation subsection.
517          print HTMLOUT "<h4>Relations for <b>$key</b></h4>\n";          $retVal .= "<h4>Relations for <b>$key</b></h4>\n";
518          # Loop through the relations, displaying them.          # Loop through the relations, displaying them.
519          for my $relation (sort keys %{$relationList}) {          for my $relation (sort keys %{$relationList}) {
520              my $htmlString = _ShowRelationTable($relation, $relationList->{$relation});              my $htmlString = _ShowRelationTable($relation, $relationList->{$relation});
521              print HTMLOUT $htmlString;              $retVal .= $htmlString;
522          }          }
523      }      }
524      # Denote we're starting the relationship section.      # Denote we're starting the relationship section.
525      print HTMLOUT "<a name=\"RelationshipsSection\"></a><h2>Relationships</h2>\n";      $retVal .= "<a name=\"RelationshipsSection\"></a><h2>Relationships</h2>\n";
526      # Loop through the relationships.      # Loop through the relationships.
527      for my $key (sort keys %{$relationshipList}) {      for my $key (sort keys %{$relationshipList}) {
528          Trace("Building MetaData entry for $key relationship.") if T(4);          Trace("Building MetaData entry for $key relationship.") if T(4);
# Line 468  Line 530 
530          my $relationshipStructure = $relationshipList->{$key};          my $relationshipStructure = $relationshipList->{$key};
531          # Create the relationship header.          # Create the relationship header.
532          my $headerText = _ComputeRelationshipHeading($key, $relationshipStructure);          my $headerText = _ComputeRelationshipHeading($key, $relationshipStructure);
533          print HTMLOUT "<h3><a name=\"$key\"></a>$headerText</h3>\n";          $retVal .= "<h3><a name=\"$key\"></a>$headerText</h3>\n";
534          # Get the entity names.          # Get the entity names.
535          my $fromEntity = $relationshipStructure->{from};          my $fromEntity = $relationshipStructure->{from};
536          my $toEntity = $relationshipStructure->{to};          my $toEntity = $relationshipStructure->{to};
# Line 478  Line 540 
540          # since both sentences will say the same thing.          # since both sentences will say the same thing.
541          my $arity = $relationshipStructure->{arity};          my $arity = $relationshipStructure->{arity};
542          if ($arity eq "11") {          if ($arity eq "11") {
543              print HTMLOUT "<p>Each <b>$fromEntity</b> relates to at most one <b>$toEntity</b>.\n";              $retVal .= "<p>Each <b>$fromEntity</b> relates to at most one <b>$toEntity</b>.\n";
544          } else {          } else {
545              print HTMLOUT "<p>Each <b>$fromEntity</b> relates to multiple <b>$toEntity</b>s.\n";              $retVal .= "<p>Each <b>$fromEntity</b> relates to multiple <b>$toEntity</b>s.\n";
546              if ($arity eq "MM" && $fromEntity ne $toEntity) {              if ($arity eq "MM" && $fromEntity ne $toEntity) {
547                  print HTMLOUT "Each <b>$toEntity</b> relates to multiple <b>$fromEntity</b>s.\n";                  $retVal .= "Each <b>$toEntity</b> relates to multiple <b>$fromEntity</b>s.\n";
548              }              }
549          }          }
550          print HTMLOUT "</p>\n";          $retVal .= "</p>\n";
551          # If there are notes on this relationship, display them.          # If there are notes on this relationship, display them.
552          if (my $notes = $relationshipStructure->{Notes}) {          if (my $notes = $relationshipStructure->{Notes}) {
553              print HTMLOUT "<p>" . _HTMLNote($notes->{content}) . "</p>\n";              $retVal .= "<p>" . _HTMLNote($notes->{content}) . "</p>\n";
554          }          }
555          # Generate the relationship's relation table.          # Generate the relationship's relation table.
556          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});          my $htmlString = _ShowRelationTable($key, $relationshipStructure->{Relations}->{$key});
557          print HTMLOUT $htmlString;          $retVal .= $htmlString;
558      }      }
559      Trace("Building MetaData join table.") if T(4);      Trace("Building MetaData join table.") if T(4);
560      # Denote we're starting the join table.      # Denote we're starting the join table.
561      print HTMLOUT "<a name=\"JoinTable\"></a><h3>Join Table</h3>\n";      $retVal .= "<a name=\"JoinTable\"></a><h3>Join Table</h3>\n";
562      # Create a table header.      # Create a table header.
563      print HTMLOUT _OpenTable("Join Table", "Source", "Target", "Join Condition");      $retVal .= _OpenTable("Join Table", "Source", "Target", "Join Condition");
564      # Loop through the joins.      # Loop through the joins.
565      my $joinTable = $metadata->{Joins};      my $joinTable = $metadata->{Joins};
566      my @joinKeys = keys %{$joinTable};      my @joinKeys = keys %{$joinTable};
# Line 506  Line 568 
568          # Separate out the source, the target, and the join clause.          # Separate out the source, the target, and the join clause.
569          $joinKey =~ m!^([^/]+)/(.+)$!;          $joinKey =~ m!^([^/]+)/(.+)$!;
570          my ($sourceRelation, $targetRelation) = ($1, $2);          my ($sourceRelation, $targetRelation) = ($1, $2);
571          Trace("Join with key $joinKey is from $sourceRelation to $targetRelation.") if T(4);          Trace("Join with key $joinKey is from $sourceRelation to $targetRelation.") if T(Joins => 4);
572          my $source = $self->ComputeObjectSentence($sourceRelation);          my $source = $self->ComputeObjectSentence($sourceRelation);
573          my $target = $self->ComputeObjectSentence($targetRelation);          my $target = $self->ComputeObjectSentence($targetRelation);
574          my $clause = $joinTable->{$joinKey};          my $clause = $joinTable->{$joinKey};
575          # Display them in a table row.          # Display them in a table row.
576          print HTMLOUT "<tr><td>$source</td><td>$target</td><td>$clause</td></tr>\n";          $retVal .= "<tr><td>$source</td><td>$target</td><td>$clause</td></tr>\n";
577      }      }
578      # Close the table.      # Close the table.
579      print HTMLOUT _CloseTable();      $retVal .= _CloseTable();
580      # Close the document.      Trace("Built MetaData HTML.") if T(3);
581      print HTMLOUT "</body>\n</html>\n";      # Return the HTML.
582      # Close the file.      return $retVal;
     close HTMLOUT;  
     Trace("Built MetaData web page.") if T(3);  
583  }  }
584    
585  =head3 DumpMetaData  =head3 DumpMetaData
586    
587  C<< $database->DumpMetaData(); >>  C<< $erdb->DumpMetaData(); >>
588    
589  Return a dump of the metadata structure.  Return a dump of the metadata structure.
590    
# Line 539  Line 599 
599    
600  =head3 CreateTables  =head3 CreateTables
601    
602  C<< $datanase->CreateTables(); >>  C<< $erdb->CreateTables(); >>
603    
604  This method creates the tables for the database from the metadata structure loaded by the  This method creates the tables for the database from the metadata structure loaded by the
605  constructor. It is expected this function will only be used on rare occasions, when the  constructor. It is expected this function will only be used on rare occasions, when the
# Line 551  Line 611 
611  sub CreateTables {  sub CreateTables {
612      # Get the parameters.      # Get the parameters.
613      my ($self) = @_;      my ($self) = @_;
614      my $metadata = $self->{_metaData};      # Get the relation names.
615      my $dbh = $self->{_dbh};      my @relNames = $self->GetTableNames();
616      # Loop through the entities.      # Loop through the relations.
617      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}}) {  
618              # Create a table for this relation.              # Create a table for this relation.
619              $self->CreateTable($relationName);              $self->CreateTable($relationName);
620              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);  
621      }      }
622  }  }
623    
624  =head3 CreateTable  =head3 CreateTable
625    
626  C<< $database->CreateTable($tableName, $indexFlag); >>  C<< $erdb->CreateTable($tableName, $indexFlag, $estimatedRows); >>
627    
628  Create the table for a relation and optionally create its indexes.  Create the table for a relation and optionally create its indexes.
629    
# Line 587  Line 633 
633    
634  Name of the relation (which will also be the table name).  Name of the relation (which will also be the table name).
635    
636  =item $indexFlag  =item indexFlag
637    
638  TRUE if the indexes for the relation should be created, else FALSE. If FALSE,  TRUE if the indexes for the relation should be created, else FALSE. If FALSE,
639  L</CreateIndexes> must be called later to bring the indexes into existence.  L</CreateIndexes> must be called later to bring the indexes into existence.
640    
641    =item estimatedRows (optional)
642    
643    If specified, the estimated maximum number of rows for the relation. This
644    information allows the creation of tables using storage engines that are
645    faster but require size estimates, such as MyISAM.
646    
647  =back  =back
648    
649  =cut  =cut
650    
651  sub CreateTable {  sub CreateTable {
652      # Get the parameters.      # Get the parameters.
653      my ($self, $relationName, $indexFlag) = @_;      my ($self, $relationName, $indexFlag, $estimatedRows) = @_;
654      # Get the database handle.      # Get the database handle.
655      my $dbh = $self->{_dbh};      my $dbh = $self->{_dbh};
656      # Get the relation data and determine whether or not the relation is primary.      # Get the relation data and determine whether or not the relation is primary.
# Line 622  Line 674 
674      # Insure the table is not already there.      # Insure the table is not already there.
675      $dbh->drop_table(tbl => $relationName);      $dbh->drop_table(tbl => $relationName);
676      Trace("Table $relationName dropped.") if T(2);      Trace("Table $relationName dropped.") if T(2);
677        # If there are estimated rows, create an estimate so we can take advantage of
678        # faster DB technologies.
679        my $estimation = undef;
680        if ($estimatedRows) {
681            $estimation = [$self->EstimateRowSize($relationName), $estimatedRows];
682        }
683      # Create the table.      # Create the table.
684      Trace("Creating table $relationName: $fieldThing") if T(2);      Trace("Creating table $relationName: $fieldThing") if T(2);
685      $dbh->create_table(tbl => $relationName, flds => $fieldThing);      $dbh->create_table(tbl => $relationName, flds => $fieldThing, estimates => $estimation);
686      Trace("Relation $relationName created in database.") if T(2);      Trace("Relation $relationName created in database.") if T(2);
687      # If we want to build the indexes, we do it here.      # If we want to build the indexes, we do it here.
688      if ($indexFlag) {      if ($indexFlag) {
# Line 632  Line 690 
690      }      }
691  }  }
692    
693    =head3 VerifyFields
694    
695    C<< my $count = $erdb->VerifyFields($relName, \@fieldList); >>
696    
697    Run through the list of proposed field values, insuring that all the character fields are
698    below the maximum length. If any fields are too long, they will be truncated in place.
699    
700    =over 4
701    
702    =item relName
703    
704    Name of the relation for which the specified fields are destined.
705    
706    =item fieldList
707    
708    Reference to a list, in order, of the fields to be put into the relation.
709    
710    =item RETURN
711    
712    Returns the number of fields truncated.
713    
714    =back
715    
716    =cut
717    
718    sub VerifyFields {
719        # Get the parameters.
720        my ($self, $relName, $fieldList) = @_;
721        # Initialize the return value.
722        my $retVal = 0;
723        # Get the relation definition.
724        my $relData = $self->_FindRelation($relName);
725        # Get the list of field descriptors.
726        my $fieldTypes = $relData->{Fields};
727        my $fieldCount = scalar @{$fieldTypes};
728        # Loop through the two lists.
729        for (my $i = 0; $i < $fieldCount; $i++) {
730            # Get the type of the current field.
731            my $fieldType = $fieldTypes->[$i]->{type};
732            # If it's a character field, verify the length.
733            if ($fieldType =~ /string/) {
734                my $maxLen = $TypeTable{$fieldType}->{maxLen};
735                my $oldString = $fieldList->[$i];
736                if (length($oldString) > $maxLen) {
737                    # Here it's too big, so we truncate it.
738                    Trace("Truncating field $i in relation $relName to $maxLen characters from \"$oldString\".") if T(1);
739                    $fieldList->[$i] = substr $oldString, 0, $maxLen;
740                    $retVal++;
741                }
742            }
743        }
744        # Return the truncation count.
745        return $retVal;
746    }
747    
748    =head3 DigestFields
749    
750    C<< $erdb->DigestFields($relName, $fieldList); >>
751    
752    Digest the strings in the field list that correspond to data type C<hash-string> in the
753    specified relation.
754    
755    =over 4
756    
757    =item relName
758    
759    Name of the relation to which the fields belong.
760    
761    =item fieldList
762    
763    List of field contents to be loaded into the relation.
764    
765    =back
766    
767    =cut
768    #: Return Type ;
769    sub DigestFields {
770        # Get the parameters.
771        my ($self, $relName, $fieldList) = @_;
772        # Get the relation definition.
773        my $relData = $self->_FindRelation($relName);
774        # Get the list of field descriptors.
775        my $fieldTypes = $relData->{Fields};
776        my $fieldCount = scalar @{$fieldTypes};
777        # Loop through the two lists.
778        for (my $i = 0; $i < $fieldCount; $i++) {
779            # Get the type of the current field.
780            my $fieldType = $fieldTypes->[$i]->{type};
781            # If it's a hash string, digest it in place.
782            if ($fieldType eq 'hash-string') {
783                $fieldList->[$i] = $self->DigestKey($fieldList->[$i]);
784            }
785        }
786    }
787    
788    =head3 DigestKey
789    
790    C<< my $digested = $erdb->DigestKey($keyValue); >>
791    
792    Return the digested value of a symbolic key. The digested value can then be plugged into a
793    key-based search into a table with key-type hash-string.
794    
795    Currently the digesting process is independent of the database structure, but that may not
796    always be the case, so this is an instance method instead of a static method.
797    
798    =over 4
799    
800    =item keyValue
801    
802    Key value to digest.
803    
804    =item RETURN
805    
806    Digested value ofthe key.
807    
808    =back
809    
810    =cut
811    
812    sub DigestKey {
813        # Get the parameters.
814        my ($self, $keyValue) = @_;
815        # Compute the digest.
816        my $retVal = md5_base64($keyValue);
817        # Return the result.
818        return $retVal;
819    }
820    
821  =head3 CreateIndex  =head3 CreateIndex
822    
823  C<< $database->CreateIndex($relationName); >>  C<< $erdb->CreateIndex($relationName); >>
824    
825  Create the indexes for a relation. If a table is being loaded from a large source file (as  Create the indexes for a relation. If a table is being loaded from a large source file (as
826  is the case in L</LoadTable>), it is sometimes best to create the indexes after the load.  is the case in L</LoadTable>), it is sometimes best to create the indexes after the load.
# Line 660  Line 846 
846          # Get the index's uniqueness flag.          # Get the index's uniqueness flag.
847          my $unique = (exists $indexData->{Unique} ? $indexData->{Unique} : 'false');          my $unique = (exists $indexData->{Unique} ? $indexData->{Unique} : 'false');
848          # Create the index.          # Create the index.
849          $dbh->create_index(idx => $indexName, tbl => $relationName, flds => $flds, unique => $unique);          my $rv = $dbh->create_index(idx => $indexName, tbl => $relationName,
850                                        flds => $flds, unique => $unique);
851            if ($rv) {
852          Trace("Index created: $indexName for $relationName ($flds)") if T(1);          Trace("Index created: $indexName for $relationName ($flds)") if T(1);
853            } else {
854                Confess("Error creating index $indexName for $relationName using ($flds): " . $dbh->error_message());
855            }
856      }      }
857  }  }
858    
859  =head3 LoadTables  =head3 LoadTables
860    
861  C<< my $stats = $database->LoadTables($directoryName, $rebuild); >>  C<< my $stats = $erdb->LoadTables($directoryName, $rebuild); >>
862    
863  This method will load the database tables from a directory. The tables must already have been created  This method will load the database tables from a directory. The tables must already have been created
864  in the database. (This can be done by calling L</CreateTables>.) The caller passes in a directory name;  in the database. (This can be done by calling L</CreateTables>.) The caller passes in a directory name;
# Line 710  Line 901 
901      $directoryName =~ s!/\\$!!;      $directoryName =~ s!/\\$!!;
902      # Declare the return variable.      # Declare the return variable.
903      my $retVal = Stats->new();      my $retVal = Stats->new();
904      # Get the metadata structure.      # Get the relation names.
905      my $metaData = $self->{_metaData};      my @relNames = $self->GetTableNames();
906      # 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}}) {  
907              # Try to load this relation.              # Try to load this relation.
908              my $result = $self->_LoadRelation($directoryName, $relationName, $rebuild);              my $result = $self->_LoadRelation($directoryName, $relationName, $rebuild);
909              # Accumulate the statistics.              # Accumulate the statistics.
910              $retVal->Accumulate($result);              $retVal->Accumulate($result);
911          }          }
     }  
     # 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);  
     }  
912      # Add the duration of the load to the statistical object.      # Add the duration of the load to the statistical object.
913      $retVal->Add('duration', gettimeofday - $startTime);      $retVal->Add('duration', gettimeofday - $startTime);
914      # Return the accumulated statistics.      # Return the accumulated statistics.
915      return $retVal;      return $retVal;
916  }  }
917    
918    
919  =head3 GetTableNames  =head3 GetTableNames
920    
921  C<< my @names = $database->GetTableNames; >>  C<< my @names = $erdb->GetTableNames; >>
922    
923  Return a list of the relations required to implement this database.  Return a list of the relations required to implement this database.
924    
# Line 754  Line 935 
935    
936  =head3 GetEntityTypes  =head3 GetEntityTypes
937    
938  C<< my @names = $database->GetEntityTypes; >>  C<< my @names = $erdb->GetEntityTypes; >>
939    
940  Return a list of the entity type names.  Return a list of the entity type names.
941    
# Line 769  Line 950 
950      return sort keys %{$entityList};      return sort keys %{$entityList};
951  }  }
952    
953    =head3 IsEntity
954    
955    C<< my $flag = $erdb->IsEntity($entityName); >>
956    
957    Return TRUE if the parameter is an entity name, else FALSE.
958    
959    =over 4
960    
961    =item entityName
962    
963    Object name to be tested.
964    
965    =item RETURN
966    
967    Returns TRUE if the specified string is an entity name, else FALSE.
968    
969    =back
970    
971    =cut
972    
973    sub IsEntity {
974        # Get the parameters.
975        my ($self, $entityName) = @_;
976        # Test to see if it's an entity.
977        return exists $self->{_metaData}->{Entities}->{$entityName};
978    }
979    
980  =head3 Get  =head3 Get
981    
982  C<< my $query = $database->Get(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  C<< my $query = $erdb->Get(\@objectNames, $filterClause, \@params); >>
983    
984  This method returns a query object for entities of a specified type using a specified filter.  This method returns a query object for entities of a specified type using a specified filter.
985  The filter is a standard WHERE/ORDER BY clause with question marks as parameter markers and each  The filter is a standard WHERE/ORDER BY clause with question marks as parameter markers and each
# Line 779  Line 987 
987  following call requests all B<Genome> objects for the genus specified in the variable  following call requests all B<Genome> objects for the genus specified in the variable
988  $genus.  $genus.
989    
990  C<< $query = $sprout->Get(['Genome'], "Genome(genus) = ?", $genus); >>  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = ?", [$genus]); >>
991    
992  The WHERE clause contains a single question mark, so there is a single additional  The WHERE clause contains a single question mark, so there is a single additional
993  parameter representing the parameter value. It would also be possible to code  parameter representing the parameter value. It would also be possible to code
994    
995  C<< $query = $sprout->Get(['Genome'], "Genome(genus) = \'$genus\'"); >>  C<< $query = $erdb->Get(['Genome'], "Genome(genus) = \'$genus\'"); >>
996    
997  however, this version of the call would generate a syntax error if there were any quote  however, this version of the call would generate a syntax error if there were any quote
998  characters inside the variable C<$genus>.  characters inside the variable C<$genus>.
# Line 796  Line 1004 
1004  It is possible to specify multiple entity and relationship names in order to retrieve more than  It is possible to specify multiple entity and relationship names in order to retrieve more than
1005  one object's data at the same time, which allows highly complex joined queries. For example,  one object's data at the same time, which allows highly complex joined queries. For example,
1006    
1007  C<< $query = $sprout->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", $genus); >>  C<< $query = $erdb->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", [$genus]); >>
1008    
1009  If multiple names are specified, then the query processor will automatically determine a  If multiple names are specified, then the query processor will automatically determine a
1010  join path between the entities and relationships. The algorithm used is very simplistic.  join path between the entities and relationships. The algorithm used is very simplistic.
1011  In particular, you can't specify any entity or relationship more than once, and if a  In particular, if a relationship is recursive, the path is determined by the order in which
1012  relationship is recursive, the path is determined by the order in which the entity  the entity and the relationship appear. For example, consider a recursive relationship
1013  and the relationship appear. For example, consider a recursive relationship B<IsParentOf>  B<IsParentOf> which relates B<People> objects to other B<People> objects. If the join path is
 which relates B<People> objects to other B<People> objects. If the join path is  
1014  coded as C<['People', 'IsParentOf']>, then the people returned will be parents. If, however,  coded as C<['People', 'IsParentOf']>, then the people returned will be parents. If, however,
1015  the join path is C<['IsParentOf', 'People']>, then the people returned will be children.  the join path is C<['IsParentOf', 'People']>, then the people returned will be children.
1016    
1017    If an entity or relationship is mentioned twice, the name for the second occurrence will
1018    be suffixed with C<2>, the third occurrence will be suffixed with C<3>, and so forth. So,
1019    for example, if we have C<['Feature', 'HasContig', 'Contig', 'HasContig']>, then the
1020    B<to-link> field of the first B<HasContig> is specified as C<HasContig(to-link)>, while
1021    the B<to-link> field of the second B<HasContig> is specified as C<HasContig2(to-link)>.
1022    
1023  =over 4  =over 4
1024    
1025  =item objectNames  =item objectNames
# Line 829  Line 1042 
1042    
1043  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>
1044    
1045    Note that the case is important. Only an uppercase "ORDER BY" with a single space will
1046    be processed. The idea is to make it less likely to find the verb by accident.
1047    
1048  The rules for field references in a sort order are the same as those for field references in the  The rules for field references in a sort order are the same as those for field references in the
1049  filter clause in general; however, odd things may happen if a sort field is from a secondary  filter clause in general; however, odd things may happen if a sort field is from a secondary
1050  relation.  relation.
1051    
1052  =item param1, param2, ..., paramN  Finally, you can limit the number of rows returned by adding a LIMIT clause. The LIMIT must
1053    be the last thing in the filter clause, and it contains only the word "LIMIT" followed by
1054    a positive number. So, for example
1055    
1056    C<< "Genome(genus) = ? ORDER BY Genome(species) LIMIT 10" >>
1057    
1058    will only return the first ten genomes for the specified genus. The ORDER BY clause is not
1059    required. For example, to just get the first 10 genomes in the B<Genome> table, you could
1060    use
1061    
1062  Parameter values to be substituted into the filter clause.  C<< "LIMIT 10" >>
1063    
1064    =item params
1065    
1066    Reference to a list of parameter values to be substituted into the filter clause.
1067    
1068  =item RETURN  =item RETURN
1069    
# Line 847  Line 1075 
1075    
1076  sub Get {  sub Get {
1077      # Get the parameters.      # Get the parameters.
1078      my ($self, $objectNames, $filterClause, @params) = @_;      my ($self, $objectNames, $filterClause, $params) = @_;
1079      # Construct the SELECT statement. The general pattern is      # Process the SQL stuff.
1080      #      my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1081      # SELECT name1.*, name2.*, ... nameN.* FROM name1, name2, ... nameN          $self->_SetupSQL($objectNames, $filterClause);
1082      #      # Create the query.
1083      my $dbh = $self->{_dbh};      my $command = "SELECT DISTINCT " . join(".*, ", @{$mappedNameListRef}) .
1084      my $command = "SELECT DISTINCT " . join('.*, ', @{$objectNames}) . ".* FROM " .          ".* $suffix";
1085                  join(', ', @{$objectNames});      my $sth = $self->_GetStatementHandle($command, $params);
1086      # Check for a filter clause.      # Now we create the relation map, which enables DBQuery to determine the order, name
1087      if ($filterClause) {      # and mapped name for each object in the query.
1088          # Here we have one, so we convert its field names and add it to the query. First,      my @relationMap = ();
1089          # We create a copy of the filter string we can work with.      for my $mappedName (@{$mappedNameListRef}) {
1090          my $filterString = $filterClause;          push @relationMap, [$mappedName, $mappedNameHashRef->{$mappedName}];
         # Next, we sort the object names by length. This helps protect us from finding  
         # object names inside other object names when we're doing our search and replace.  
         my @sortedNames = sort { length($b) - length($a) } @{$objectNames};  
         # We will also keep a list of conditions to add to the WHERE clause in order to link  
         # entities and relationships as well as primary relations to secondary ones.  
         my @joinWhere = ();  
         # The final preparatory step is to create a hash table of relation names. The  
         # table begins with the relation names already in the SELECT command.  
         my %fromNames = ();  
         for my $objectName (@sortedNames) {  
             $fromNames{$objectName} = 1;  
         }  
         # We are ready to begin. We loop through the object names, replacing each  
         # object name's field references by the corresponding SQL field reference.  
         # Along the way, if we find a secondary relation, we will need to add it  
         # to the FROM clause.  
         for my $objectName (@sortedNames) {  
             # Get the length of the object name plus 2. This is the value we add to the  
             # size of the field name to determine the size of the field reference as a  
             # whole.  
             my $nameLength = 2 + length $objectName;  
             # Get the object's field list.  
             my $fieldList = $self->_GetFieldTable($objectName);  
             # Find the field references for this object.  
             while ($filterString =~ m/$objectName\(([^)]*)\)/g) {  
                 # At this point, $1 contains the field name, and the current position  
                 # is set immediately after the final parenthesis. We pull out the name of  
                 # the field and the position and length of the field reference as a whole.  
                 my $fieldName = $1;  
                 my $len = $nameLength + length $fieldName;  
                 my $pos = pos($filterString) - $len;  
                 # Insure the field exists.  
                 if (!exists $fieldList->{$fieldName}) {  
                     Confess("Field $fieldName not found for object $objectName.");  
                 } else {  
                     # Get the field's relation.  
                     my $relationName = $fieldList->{$fieldName}->{relation};  
                     # Insure the relation is in the FROM clause.  
                     if (!exists $fromNames{$relationName}) {  
                         # Add the relation to the FROM clause.  
                         $command .= ", $relationName";  
                         # Create its join sub-clause.  
                         push @joinWhere, "$objectName.id = $relationName.id";  
                         # Denote we have it available for future fields.  
                         $fromNames{$relationName} = 1;  
                     }  
                     # Form an SQL field reference from the relation name and the field name.  
                     my $sqlReference = "$relationName." . _FixName($fieldName);  
                     # Put it into the filter string in place of the old value.  
                     substr($filterString, $pos, $len) = $sqlReference;  
                     # Reposition the search.  
                     pos $filterString = $pos + length $sqlReference;  
                 }  
             }  
         }  
         # The next step is to join the objects together. We only need to do this if there  
         # is more than one object in the object list. We start with the first object and  
         # run through the objects after it. Note also that we make a safety copy of the  
         # list before running through it.  
         my @objectList = @{$objectNames};  
         my $lastObject = shift @objectList;  
         # Get the join table.  
         my $joinTable = $self->{_metaData}->{Joins};  
         # Loop through the object list.  
         for my $thisObject (@objectList) {  
             # Look for a join.  
             my $joinKey = "$lastObject/$thisObject";  
             if (!exists $joinTable->{$joinKey}) {  
                 # Here there's no join, so we throw an error.  
                 Confess("No join exists to connect from $lastObject to $thisObject.");  
             } else {  
                 # Get the join clause and add it to the WHERE list.  
                 push @joinWhere, $joinTable->{$joinKey};  
                 # Save this object as the last object for the next iteration.  
                 $lastObject = $thisObject;  
             }  
         }  
         # Now we need to handle the whole ORDER BY thing. We'll put the order by clause  
         # in the following variable.  
         my $orderClause = "";  
         # Locate the ORDER BY verb (if any).  
         if ($filterString =~ m/^(.*)ORDER BY/g) {  
             # Here we have an ORDER BY verb. Split it off of the filter string.  
             my $pos = pos $filterString;  
             $orderClause = substr($filterString, $pos);  
             $filterString = $1;  
         }  
         # Add the filter and the join clauses (if any) to the SELECT command.  
         if ($filterString) {  
             push @joinWhere, "($filterString)";  
         }  
         if (@joinWhere) {  
             $command .= " WHERE " . join(' AND ', @joinWhere);  
         }  
         # Add the sort clause (if any) to the SELECT command.  
         if ($orderClause) {  
             $command .= " ORDER BY $orderClause";  
         }  
1091      }      }
     Trace("SQL query: $command") if T(2);  
     Trace("PARMS: '" . (join "', '", @params) . "'") if (T(3) && (@params > 0));  
     my $sth = $dbh->prepare_command($command);  
     # Execute it with the parameters bound in.  
     $sth->execute(@params) || Confess("SELECT error" . $sth->errstr());  
1092      # Return the statement object.      # Return the statement object.
1093      my $retVal = DBQuery::_new($self, $sth, @{$objectNames});      my $retVal = DBQuery::_new($self, $sth, \@relationMap);
1094      return $retVal;      return $retVal;
1095  }  }
1096    
1097  =head3 GetList  =head3 GetFlat
   
 C<< my @dbObjects = $database->GetList(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  
1098    
1099  Return a list of object descriptors for the specified objects as determined by the  C<< my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field); >>
 specified filter clause.  
1100    
1101  This method is essentially the same as L</Get> except it returns a list of objects rather  This is a variation of L</GetAll> that asks for only a single field per record and
1102  than a query object that can be used to get the results one record at a time.  returns a single flattened list.
1103    
1104  =over 4  =over 4
1105    
# Line 987  Line 1109 
1109    
1110  =item filterClause  =item filterClause
1111    
1112  WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can  WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1113  be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be  be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
1114  specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified  B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
1115  in the filter clause should be added to the parameter list as additional parameters. The  parameter list as additional parameters. The fields in a filter clause can come from primary
1116  fields in a filter clause can come from primary entity relations, relationship relations,  entity relations, relationship relations, or secondary entity relations; however, all of the
1117  or secondary entity relations; however, all of the entities and relationships involved must  entities and relationships involved must be included in the list of object names.
 be included in the list of object names.  
   
 The filter clause can also specify a sort order. To do this, simply follow the filter string  
 with an ORDER BY clause. For example, the following filter string gets all genomes for a  
 particular genus and sorts them by species name.  
1118    
1119  C<< "Genome(genus) = ? ORDER BY Genome(species)" >>  =item parameterList
1120    
1121  The rules for field references in a sort order are the same as those for field references in the  List of the parameters to be substituted in for the parameters marks in the filter clause.
 filter clause in general; however, odd things may happen if a sort field is from a secondary  
 relation.  
1122    
1123  =item param1, param2, ..., paramN  =item field
1124    
1125  Parameter values to be substituted into the filter clause.  Name of the field to be used to get the elements of the list returned.
1126    
1127  =item RETURN  =item RETURN
1128    
1129  Returns a list of B<DBObject>s that satisfy the query conditions.  Returns a list of values.
1130    
1131  =back  =back
1132    
1133  =cut  =cut
1134  #: Return Type @%  #: Return Type @;
1135  sub GetList {  sub GetFlat {
1136      # Get the parameters.      # Get the parameters.
1137      my ($self, $objectNames, $filterClause, @params) = @_;      my ($self, $objectNames, $filterClause, $parameterList, $field) = @_;
1138      # Declare the return variable.      # Construct the query.
1139        my $query = $self->Get($objectNames, $filterClause, $parameterList);
1140        # Create the result list.
1141        my @retVal = ();
1142        # Loop through the records, adding the field values found to the result list.
1143        while (my $row = $query->Fetch()) {
1144            push @retVal, $row->Value($field);
1145        }
1146        # Return the list created.
1147        return @retVal;
1148    }
1149    
1150    =head3 Delete
1151    
1152    C<< my $stats = $erdb->Delete($entityName, $objectID); >>
1153    
1154    Delete an entity instance from the database. The instance is deleted along with all entity and
1155    relationship instances dependent on it. The idea of dependence here is recursive. An object is
1156    always dependent on itself. An object is dependent if it is a 1-to-many or many-to-many
1157    relationship connected to a dependent entity or the "to" entity connected to a 1-to-many
1158    dependent relationship.
1159    
1160    =over 4
1161    
1162    =item entityName
1163    
1164    Name of the entity type for the instance being deleted.
1165    
1166    =item objectID
1167    
1168    ID of the entity instance to be deleted. If the ID contains a wild card character (C<%>),
1169    then it is presumed to by a LIKE pattern.
1170    
1171    =item testFlag
1172    
1173    If TRUE, the delete statements will be traced without being executed.
1174    
1175    =item RETURN
1176    
1177    Returns a statistics object indicating how many records of each particular table were
1178    deleted.
1179    
1180    =back
1181    
1182    =cut
1183    #: Return Type $%;
1184    sub Delete {
1185        # Get the parameters.
1186        my ($self, $entityName, $objectID, $testFlag) = @_;
1187        # Declare the return variable.
1188        my $retVal = Stats->new();
1189        # Get the DBKernel object.
1190        my $db = $self->{_dbh};
1191        # We're going to generate all the paths branching out from the starting entity. One of
1192        # the things we have to be careful about is preventing loops. We'll use a hash to
1193        # determine if we've hit a loop.
1194        my %alreadyFound = ();
1195        # These next lists will serve as our result stack. We start by pushing object lists onto
1196        # the stack, and then popping them off to do the deletes. This means the deletes will
1197        # start with the longer paths before getting to the shorter ones. That, in turn, makes
1198        # sure we don't delete records that might be needed to forge relationships back to the
1199        # original item. We have two lists-- one for TO-relationships, and one for
1200        # FROM-relationships and entities.
1201        my @fromPathList = ();
1202        my @toPathList = ();
1203        # This final hash is used to remember what work still needs to be done. We push paths
1204        # onto the list, then pop them off to extend the paths. We prime it with the starting
1205        # point. Note that we will work hard to insure that the last item on a path in the
1206        # TODO list is always an entity.
1207        my @todoList = ([$entityName]);
1208        while (@todoList) {
1209            # Get the current path.
1210            my $current = pop @todoList;
1211            # Copy it into a list.
1212            my @stackedPath = @{$current};
1213            # Pull off the last item on the path. It will always be an entity.
1214            my $entityName = pop @stackedPath;
1215            # Add it to the alreadyFound list.
1216            $alreadyFound{$entityName} = 1;
1217            # Get the entity data.
1218            my $entityData = $self->_GetStructure($entityName);
1219            # The first task is to loop through the entity's relation. A DELETE command will
1220            # be needed for each of them.
1221            my $relations = $entityData->{Relations};
1222            for my $relation (keys %{$relations}) {
1223                my @augmentedList = (@stackedPath, $relation);
1224                push @fromPathList, \@augmentedList;
1225            }
1226            # Now we need to look for relationships connected to this entity.
1227            my $relationshipList = $self->{_metaData}->{Relationships};
1228            for my $relationshipName (keys %{$relationshipList}) {
1229                my $relationship = $relationshipList->{$relationshipName};
1230                # Check the FROM field. We're only interested if it's us.
1231                if ($relationship->{from} eq $entityName) {
1232                    # Add the path to this relationship.
1233                    my @augmentedList = (@stackedPath, $entityName, $relationshipName);
1234                    push @fromPathList, \@augmentedList;
1235                    # Check the arity. If it's MM we're done. If it's 1M
1236                    # and the target hasn't been seen yet, we want to
1237                    # stack the entity for future processing.
1238                    if ($relationship->{arity} eq '1M') {
1239                        my $toEntity = $relationship->{to};
1240                        if (! exists $alreadyFound{$toEntity}) {
1241                            # Here we have a new entity that's dependent on
1242                            # the current entity, so we need to stack it.
1243                            my @stackList = (@augmentedList, $toEntity);
1244                            push @fromPathList, \@stackList;
1245                        } else {
1246                            Trace("$toEntity ignored because it occurred previously.") if T(4);
1247                        }
1248                    }
1249                }
1250                # Now check the TO field. In this case only the relationship needs
1251                # deletion.
1252                if ($relationship->{to} eq $entityName) {
1253                    my @augmentedList = (@stackedPath, $entityName, $relationshipName);
1254                    push @toPathList, \@augmentedList;
1255                }
1256            }
1257        }
1258        # Create the first qualifier for the WHERE clause. This selects the
1259        # keys of the primary entity records to be deleted. When we're deleting
1260        # from a dependent table, we construct a join page from the first qualifier
1261        # to the table containing the dependent records to delete.
1262        my $qualifier = ($objectID =~ /%/ ? "LIKE ?" : "= ?");
1263        # We need to make two passes. The first is through the to-list, and
1264        # the second through the from-list. The from-list is second because
1265        # the to-list may need to pass through some of the entities the
1266        # from-list would delete.
1267        my %stackList = ( from_link => \@fromPathList, to_link => \@toPathList );
1268        # Now it's time to do the deletes. We do it in two passes.
1269        for my $keyName ('to_link', 'from_link') {
1270            # Get the list for this key.
1271            my @pathList = @{$stackList{$keyName}};
1272            Trace(scalar(@pathList) . " entries in path list for $keyName.") if T(3);
1273            # Loop through this list.
1274            while (my $path = pop @pathList) {
1275                # Get the table whose rows are to be deleted.
1276                my @pathTables = @{$path};
1277                # Start the DELETE statement. We need to call DBKernel because the
1278                # syntax of a DELETE-USING varies among DBMSs.
1279                my $target = $pathTables[$#pathTables];
1280                my $stmt = $db->SetUsing(@pathTables);
1281                # Now start the WHERE. The first thing is the ID field from the starting table. That
1282                # starting table will either be the entity relation or one of the entity's
1283                # sub-relations.
1284                $stmt .= " WHERE $pathTables[0].id $qualifier";
1285                # Now we run through the remaining entities in the path, connecting them up.
1286                for (my $i = 1; $i <= $#pathTables; $i += 2) {
1287                    # Connect the current relationship to the preceding entity.
1288                    my ($entity, $rel) = @pathTables[$i-1,$i];
1289                    # The style of connection depends on the direction of the relationship.
1290                    $stmt .= " AND $entity.id = $rel.$keyName";
1291                    if ($i + 1 <= $#pathTables) {
1292                        # Here there's a next entity, so connect that to the relationship's
1293                        # to-link.
1294                        my $entity2 = $pathTables[$i+1];
1295                        $stmt .= " AND $rel.to_link = $entity2.id";
1296                    }
1297                }
1298                # Now we have our desired DELETE statement.
1299                if ($testFlag) {
1300                    # Here the user wants to trace without executing.
1301                    Trace($stmt) if T(0);
1302                } else {
1303                    # Here we can delete. Note that the SQL method dies with a confessing
1304                    # if an error occurs, so we just go ahead and do it.
1305                    Trace("Executing delete from $target using '$objectID'.") if T(3);
1306                    my $rv = $db->SQL($stmt, 0, $objectID);
1307                    # Accumulate the statistics for this delete. The only rows deleted
1308                    # are from the target table, so we use its name to record the
1309                    # statistic.
1310                    $retVal->Add($target, $rv);
1311                }
1312            }
1313        }
1314        # Return the result.
1315        return $retVal;
1316    }
1317    
1318    =head3 GetList
1319    
1320    C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params); >>
1321    
1322    Return a list of object descriptors for the specified objects as determined by the
1323    specified filter clause.
1324    
1325    This method is essentially the same as L</Get> except it returns a list of objects rather
1326    than a query object that can be used to get the results one record at a time.
1327    
1328    =over 4
1329    
1330    =item objectNames
1331    
1332    List containing the names of the entity and relationship objects to be retrieved.
1333    
1334    =item filterClause
1335    
1336    WHERE clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1337    be parameterized with parameter markers (C<?>). Each field used in the WHERE clause must be
1338    specified in the standard form B<I<objectName>(I<fieldName>)>. Any parameters specified
1339    in the filter clause should be added to the parameter list as additional parameters. The
1340    fields in a filter clause can come from primary entity relations, relationship relations,
1341    or secondary entity relations; however, all of the entities and relationships involved must
1342    be included in the list of object names.
1343    
1344    The filter clause can also specify a sort order. To do this, simply follow the filter string
1345    with an ORDER BY clause. For example, the following filter string gets all genomes for a
1346    particular genus and sorts them by species name.
1347    
1348    C<< "Genome(genus) = ? ORDER BY Genome(species)" >>
1349    
1350    The rules for field references in a sort order are the same as those for field references in the
1351    filter clause in general; however, odd things may happen if a sort field is from a secondary
1352    relation.
1353    
1354    =item params
1355    
1356    Reference to a list of parameter values to be substituted into the filter clause.
1357    
1358    =item RETURN
1359    
1360    Returns a list of B<DBObject>s that satisfy the query conditions.
1361    
1362    =back
1363    
1364    =cut
1365    #: Return Type @%
1366    sub GetList {
1367        # Get the parameters.
1368        my ($self, $objectNames, $filterClause, $params) = @_;
1369        # Declare the return variable.
1370      my @retVal = ();      my @retVal = ();
1371      # Perform the query.      # Perform the query.
1372      my $query = $self->Get($objectNames, $filterClause, @params);      my $query = $self->Get($objectNames, $filterClause, $params);
1373      # Loop through the results.      # Loop through the results.
1374      while (my $object = $query->Fetch) {      while (my $object = $query->Fetch) {
1375          push @retVal, $object;          push @retVal, $object;
# Line 1032  Line 1378 
1378      return @retVal;      return @retVal;
1379  }  }
1380    
1381    =head3 GetCount
1382    
1383    C<< my $count = $erdb->GetCount(\@objectNames, $filter, \@params); >>
1384    
1385    Return the number of rows found by a specified query. This method would
1386    normally be used to count the records in a single table. For example, in a
1387    genetics database
1388    
1389        my $count = $erdb->GetCount(['Genome'], 'Genome(genus-species) LIKE ?', ['homo %']);
1390    
1391    would return the number of genomes for the genus I<homo>. It is conceivable, however,
1392    to use it to return records based on a join. For example,
1393    
1394        my $count = $erdb->GetCount(['HasFeature', 'Genome'], 'Genome(genus-species) LIKE ?',
1395                                    ['homo %']);
1396    
1397    would return the number of features for genomes in the genus I<homo>. Note that
1398    only the rows from the first table are counted. If the above command were
1399    
1400        my $count = $erdb->GetCount(['Genome', 'Feature'], 'Genome(genus-species) LIKE ?',
1401                                    ['homo %']);
1402    
1403    it would return the number of genomes, not the number of genome/feature pairs.
1404    
1405    =over 4
1406    
1407    =item objectNames
1408    
1409    Reference to a list of the objects (entities and relationships) included in the
1410    query.
1411    
1412    =item filter
1413    
1414    A filter clause for restricting the query. The rules are the same as for the L</Get>
1415    method.
1416    
1417    =item params
1418    
1419    Reference to a list of the parameter values to be substituted for the parameter marks
1420    in the filter.
1421    
1422    =item RETURN
1423    
1424    Returns a count of the number of records in the first table that would satisfy
1425    the query.
1426    
1427    =back
1428    
1429    =cut
1430    
1431    sub GetCount {
1432        # Get the parameters.
1433        my ($self, $objectNames, $filter, $params) = @_;
1434        # Declare the return variable.
1435        my $retVal;
1436        # Find out if we're counting an entity or a relationship.
1437        my $countedField;
1438        if ($self->IsEntity($objectNames->[0])) {
1439            $countedField = "id";
1440        } else {
1441            # For a relationship we count the to-link because it's usually more
1442            # numerous. Note we're automatically converting to the SQL form
1443            # of the field name (to_link vs. to-link).
1444            $countedField = "to_link";
1445        }
1446        # Create the SQL command suffix to get the desired records.
1447        my ($suffix, $mappedNameListRef, $mappedNameHashRef) = $self->_SetupSQL($objectNames,
1448                                                                                $filter);
1449        # Prefix it with text telling it we want a record count.
1450        my $firstObject = $mappedNameListRef->[0];
1451        my $command = "SELECT COUNT($firstObject.$countedField) $suffix";
1452        # Prepare and execute the command.
1453        my $sth = $self->_GetStatementHandle($command, $params);
1454        # Get the count value.
1455        ($retVal) = $sth->fetchrow_array();
1456        # Check for a problem.
1457        if (! defined($retVal)) {
1458            if ($sth->err) {
1459                # Here we had an SQL error.
1460                Confess("Error retrieving row count: " . $sth->errstr());
1461            } else {
1462                # Here we have no result.
1463                Confess("No result attempting to retrieve row count.");
1464            }
1465        }
1466        # Return the result.
1467        return $retVal;
1468    }
1469    
1470  =head3 ComputeObjectSentence  =head3 ComputeObjectSentence
1471    
1472  C<< my $sentence = $database->ComputeObjectSentence($objectName); >>  C<< my $sentence = $erdb->ComputeObjectSentence($objectName); >>
1473    
1474  Check an object name, and if it is a relationship convert it to a relationship sentence.  Check an object name, and if it is a relationship convert it to a relationship sentence.
1475    
# Line 1069  Line 1504 
1504    
1505  =head3 DumpRelations  =head3 DumpRelations
1506    
1507  C<< $database->DumpRelations($outputDirectory); >>  C<< $erdb->DumpRelations($outputDirectory); >>
1508    
1509  Write the contents of all the relations to tab-delimited files in the specified directory.  Write the contents of all the relations to tab-delimited files in the specified directory.
1510  Each file will have the same name as the relation dumped, with an extension of DTX.  Each file will have the same name as the relation dumped, with an extension of DTX.
# Line 1111  Line 1546 
1546    
1547  =head3 InsertObject  =head3 InsertObject
1548    
1549  C<< my $ok = $database->InsertObject($objectType, \%fieldHash); >>  C<< my $ok = $erdb->InsertObject($objectType, \%fieldHash); >>
1550    
1551  Insert an object into the database. The object is defined by a type name and then a hash  Insert an object into the database. The object is defined by a type name and then a hash
1552  of field names to values. Field values in the primary relation are represented by scalars.  of field names to values. Field values in the primary relation are represented by scalars.
# Line 1120  Line 1555 
1555  example, the following line inserts an inactive PEG feature named C<fig|188.1.peg.1> with aliases  example, the following line inserts an inactive PEG feature named C<fig|188.1.peg.1> with aliases
1556  C<ZP_00210270.1> and C<gi|46206278>.  C<ZP_00210270.1> and C<gi|46206278>.
1557    
1558  C<< $database->InsertObject('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']}); >>  C<< $erdb->InsertObject('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']}); >>
1559    
1560  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and
1561  property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.  property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.
1562    
1563  C<< $database->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence = 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>  C<< $erdb->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence = 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>
1564    
1565  =over 4  =over 4
1566    
# Line 1250  Line 1685 
1685    
1686  =head3 LoadTable  =head3 LoadTable
1687    
1688  C<< my %results = $database->LoadTable($fileName, $relationName, $truncateFlag); >>  C<< my %results = $erdb->LoadTable($fileName, $relationName, $truncateFlag); >>
1689    
1690  Load data from a tab-delimited file into a specified table, optionally re-creating the table  Load data from a tab-delimited file into a specified table, optionally re-creating the table
1691  first.  first.
# Line 1271  Line 1706 
1706    
1707  =item RETURN  =item RETURN
1708    
1709  Returns a statistical object containing the number of records read and a list of  Returns a statistical object containing a list of the error messages.
 the error messages.  
1710    
1711  =back  =back
1712    
# Line 1286  Line 1720 
1720      Trace("Loading table $relationName from $fileName") if T(2);      Trace("Loading table $relationName from $fileName") if T(2);
1721      # Get the database handle.      # Get the database handle.
1722      my $dbh = $self->{_dbh};      my $dbh = $self->{_dbh};
1723        # Get the input file size.
1724        my $fileSize = -s $fileName;
1725      # Get the relation data.      # Get the relation data.
1726      my $relation = $self->_FindRelation($relationName);      my $relation = $self->_FindRelation($relationName);
1727      # Check the truncation flag.      # Check the truncation flag.
1728      if ($truncateFlag) {      if ($truncateFlag) {
1729          Trace("Creating table $relationName") if T(2);          Trace("Creating table $relationName") if T(2);
1730            # Compute the row count estimate. We take the size of the load file,
1731            # divide it by the estimated row size, and then multiply by 1.5 to
1732            # leave extra room. We postulate a minimum row count of 1000 to
1733            # prevent problems with incoming empty load files.
1734            my $rowSize = $self->EstimateRowSize($relationName);
1735            my $estimate = FIG::max($fileSize * 1.5 / $rowSize, 1000);
1736          # Re-create the table without its index.          # Re-create the table without its index.
1737          $self->CreateTable($relationName, 0);          $self->CreateTable($relationName, 0, $estimate);
1738          # If this is a pre-index DBMS, create the index here.          # If this is a pre-index DBMS, create the index here.
1739          if ($dbh->{_preIndex}) {          if ($dbh->{_preIndex}) {
1740              eval {              eval {
# Line 1303  Line 1745 
1745              }              }
1746          }          }
1747      }      }
     # 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);  
1748      # Load the table.      # Load the table.
1749      my $rv;      my $rv;
1750      eval {      eval {
1751          $rv = $dbh->load_table(file => $tempName, tbl => $relationName);          $rv = $dbh->load_table(file => $fileName, tbl => $relationName);
1752      };      };
1753      if (!defined $rv) {      if (!defined $rv) {
1754          $retVal->AddMessage($@) if ($@);          $retVal->AddMessage($@) if ($@);
1755          $retVal->AddMessage("Table load failed for $relationName using $tempName.");          $retVal->AddMessage("Table load failed for $relationName using $fileName.");
1756          Trace("Table load failed for $relationName.") if T(1);          Trace("Table load failed for $relationName.") if T(1);
1757      } else {      } else {
1758          # Here we successfully loaded the table. Trace the number of records loaded.          # Here we successfully loaded the table.
1759          Trace("$retVal->{records} records read for $relationName.") if T(2);          $retVal->Add("tables");
1760            my $size = -s $fileName;
1761            Trace("$size bytes loaded into $relationName.") if T(2);
1762          # If we're rebuilding, we need to create the table indexes.          # If we're rebuilding, we need to create the table indexes.
1763          if ($truncateFlag && ! $dbh->{_preIndex}) {          if ($truncateFlag && ! $dbh->{_preIndex}) {
1764              eval {              eval {
# Line 1379  Line 1768 
1768                  $retVal->AddMessage($@);                  $retVal->AddMessage($@);
1769              }              }
1770          }          }
         # Analyze the table to help optimize tables.  
1771      }      }
1772      # Commit the database changes.      # Analyze the table to improve performance.
     $dbh->commit_tran;  
1773      $dbh->vacuum_it($relationName);      $dbh->vacuum_it($relationName);
     # Delete the temporary file.  
     unlink $tempName;  
1774      # Return the statistics.      # Return the statistics.
1775      return $retVal;      return $retVal;
1776  }  }
1777    
1778  =head3 GenerateEntity  =head3 GenerateEntity
1779    
1780  C<< my $fieldHash = $database->GenerateEntity($id, $type, \%values); >>  C<< my $fieldHash = $erdb->GenerateEntity($id, $type, \%values); >>
1781    
1782  Generate the data for a new entity instance. This method creates a field hash suitable for  Generate the data for a new entity instance. This method creates a field hash suitable for
1783  passing as a parameter to L</InsertObject>. The ID is specified by the callr, but the rest  passing as a parameter to L</InsertObject>. The ID is specified by the callr, but the rest
# Line 1448  Line 1833 
1833      return $this;      return $this;
1834  }  }
1835    
1836  =head3 GetEntity  =head3 GetEntity
1837    
1838    C<< my $entityObject = $erdb->GetEntity($entityType, $ID); >>
1839    
1840    Return an object describing the entity instance with a specified ID.
1841    
1842    =over 4
1843    
1844    =item entityType
1845    
1846    Entity type name.
1847    
1848    =item ID
1849    
1850    ID of the desired entity.
1851    
1852    =item RETURN
1853    
1854    Returns a B<DBObject> representing the desired entity instance, or an undefined value if no
1855    instance is found with the specified key.
1856    
1857    =back
1858    
1859    =cut
1860    
1861    sub GetEntity {
1862        # Get the parameters.
1863        my ($self, $entityType, $ID) = @_;
1864        # Create a query.
1865        my $query = $self->Get([$entityType], "$entityType(id) = ?", [$ID]);
1866        # Get the first (and only) object.
1867        my $retVal = $query->Fetch();
1868        # Return the result.
1869        return $retVal;
1870    }
1871    
1872    =head3 GetEntityValues
1873    
1874    C<< my @values = $erdb->GetEntityValues($entityType, $ID, \@fields); >>
1875    
1876    Return a list of values from a specified entity instance.
1877    
1878    =over 4
1879    
1880    =item entityType
1881    
1882    Entity type name.
1883    
1884    =item ID
1885    
1886    ID of the desired entity.
1887    
1888    =item fields
1889    
1890    List of field names, each of the form I<objectName>C<(>I<fieldName>C<)>.
1891    
1892    =item RETURN
1893    
1894    Returns a flattened list of the values of the specified fields for the specified entity.
1895    
1896    =back
1897    
1898    =cut
1899    
1900    sub GetEntityValues {
1901        # Get the parameters.
1902        my ($self, $entityType, $ID, $fields) = @_;
1903        # Get the specified entity.
1904        my $entity = $self->GetEntity($entityType, $ID);
1905        # Declare the return list.
1906        my @retVal = ();
1907        # If we found the entity, push the values into the return list.
1908        if ($entity) {
1909            push @retVal, $entity->Values($fields);
1910        }
1911        # Return the result.
1912        return @retVal;
1913    }
1914    
1915    =head3 GetAll
1916    
1917    C<< my @list = $erdb->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count); >>
1918    
1919    Return a list of values taken from the objects returned by a query. The first three
1920    parameters correspond to the parameters of the L</Get> method. The final parameter is
1921    a list of the fields desired from each record found by the query. The field name
1922    syntax is the standard syntax used for fields in the B<ERDB> system--
1923    B<I<objectName>(I<fieldName>)>-- where I<objectName> is the name of the relevant entity
1924    or relationship and I<fieldName> is the name of the field.
1925    
1926    The list returned will be a list of lists. Each element of the list will contain
1927    the values returned for the fields specified in the fourth parameter. If one of the
1928    fields specified returns multiple values, they are flattened in with the rest. For
1929    example, the following call will return a list of the features in a particular
1930    spreadsheet cell, and each feature will be represented by a list containing the
1931    feature ID followed by all of its aliases.
1932    
1933    C<< $query = $erdb->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>
1934    
1935    =over 4
1936    
1937    =item objectNames
1938    
1939    List containing the names of the entity and relationship objects to be retrieved.
1940    
1941    =item filterClause
1942    
1943    WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1944    be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
1945    B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
1946    parameter list as additional parameters. The fields in a filter clause can come from primary
1947    entity relations, relationship relations, or secondary entity relations; however, all of the
1948    entities and relationships involved must be included in the list of object names.
1949    
1950    =item parameterList
1951    
1952    List of the parameters to be substituted in for the parameters marks in the filter clause.
1953    
1954    =item fields
1955    
1956    List of the fields to be returned in each element of the list returned.
1957    
1958    =item count
1959    
1960    Maximum number of records to return. If omitted or 0, all available records will be returned.
1961    
1962    =item RETURN
1963    
1964    Returns a list of list references. Each element of the return list contains the values for the
1965    fields specified in the B<fields> parameter.
1966    
1967    =back
1968    
1969    =cut
1970    #: Return Type @@;
1971    sub GetAll {
1972        # Get the parameters.
1973        my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;
1974        # Translate the parameters from a list reference to a list. If the parameter
1975        # list is a scalar we convert it into a singleton list.
1976        my @parmList = ();
1977        if (ref $parameterList eq "ARRAY") {
1978            Trace("GetAll parm list is an array.") if T(4);
1979            @parmList = @{$parameterList};
1980        } else {
1981            Trace("GetAll parm list is a scalar: $parameterList.") if T(4);
1982            push @parmList, $parameterList;
1983        }
1984        # Insure the counter has a value.
1985        if (!defined $count) {
1986            $count = 0;
1987        }
1988        # Add the row limit to the filter clause.
1989        if ($count > 0) {
1990            $filterClause .= " LIMIT $count";
1991        }
1992        # Create the query.
1993        my $query = $self->Get($objectNames, $filterClause, \@parmList);
1994        # Set up a counter of the number of records read.
1995        my $fetched = 0;
1996        # Loop through the records returned, extracting the fields. Note that if the
1997        # counter is non-zero, we stop when the number of records read hits the count.
1998        my @retVal = ();
1999        while (($count == 0 || $fetched < $count) && (my $row = $query->Fetch())) {
2000            my @rowData = $row->Values($fields);
2001            push @retVal, \@rowData;
2002            $fetched++;
2003        }
2004        # Return the resulting list.
2005        return @retVal;
2006    }
2007    
2008    =head3 EstimateRowSize
2009    
2010    C<< my $rowSize = $erdb->EstimateRowSize($relName); >>
2011    
2012    Estimate the row size of the specified relation. The estimated row size is computed by adding
2013    up the average length for each data type.
2014    
2015    =over 4
2016    
2017    =item relName
2018    
2019    Name of the relation whose estimated row size is desired.
2020    
2021    =item RETURN
2022    
2023    Returns an estimate of the row size for the specified relation.
2024    
2025    =back
2026    
2027    =cut
2028    #: Return Type $;
2029    sub EstimateRowSize {
2030        # Get the parameters.
2031        my ($self, $relName) = @_;
2032        # Declare the return variable.
2033        my $retVal = 0;
2034        # Find the relation descriptor.
2035        my $relation = $self->_FindRelation($relName);
2036        # Get the list of fields.
2037        for my $fieldData (@{$relation->{Fields}}) {
2038            # Get the field type and add its length.
2039            my $fieldLen = $TypeTable{$fieldData->{type}}->{avgLen};
2040            $retVal += $fieldLen;
2041        }
2042        # Return the result.
2043        return $retVal;
2044    }
2045    
2046    =head3 GetFieldTable
2047    
2048    C<< my $fieldHash = $self->GetFieldTable($objectnName); >>
2049    
2050    Get the field structure for a specified entity or relationship.
2051    
2052    =over 4
2053    
2054    =item objectName
2055    
2056    Name of the desired entity or relationship.
2057    
2058    =item RETURN
2059    
2060    The table containing the field descriptors for the specified object.
2061    
2062    =back
2063    
2064    =cut
2065    
2066    sub GetFieldTable {
2067        # Get the parameters.
2068        my ($self, $objectName) = @_;
2069        # Get the descriptor from the metadata.
2070        my $objectData = $self->_GetStructure($objectName);
2071        # Return the object's field table.
2072        return $objectData->{Fields};
2073    }
2074    
2075    =head2 Data Mining Methods
2076    
2077    =head3 GetUsefulCrossValues
2078    
2079    C<< my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship); >>
2080    
2081    Return a list of the useful attributes that would be returned by a B<Cross> call
2082    from an entity of the source entity type through the specified relationship. This
2083    means it will return the fields of the target entity type and the intersection data
2084    fields in the relationship. Only primary table fields are returned. In other words,
2085    the field names returned will be for fields where there is always one and only one
2086    value.
2087    
2088    =over 4
2089    
2090    =item sourceEntity
2091    
2092    Name of the entity from which the relationship crossing will start.
2093    
2094    =item relationship
2095    
2096    Name of the relationship being crossed.
2097    
2098    =item RETURN
2099    
2100    Returns a list of field names in Sprout field format (I<objectName>C<(>I<fieldName>C<)>.
2101    
2102    =back
2103    
2104    =cut
2105    #: Return Type @;
2106    sub GetUsefulCrossValues {
2107        # Get the parameters.
2108        my ($self, $sourceEntity, $relationship) = @_;
2109        # Declare the return variable.
2110        my @retVal = ();
2111        # Determine the target entity for the relationship. This is whichever entity is not
2112        # the source entity. So, if the source entity is the FROM, we'll get the name of
2113        # the TO, and vice versa.
2114        my $relStructure = $self->_GetStructure($relationship);
2115        my $targetEntityType = ($relStructure->{from} eq $sourceEntity ? "to" : "from");
2116        my $targetEntity = $relStructure->{$targetEntityType};
2117        # Get the field table for the entity.
2118        my $entityFields = $self->GetFieldTable($targetEntity);
2119        # The field table is a hash. The hash key is the field name. The hash value is a structure.
2120        # For the entity fields, the key aspect of the target structure is that the {relation} value
2121        # must match the entity name.
2122        my @fieldList = map { "$targetEntity($_)" } grep { $entityFields->{$_}->{relation} eq $targetEntity }
2123                            keys %{$entityFields};
2124        # Push the fields found onto the return variable.
2125        push @retVal, sort @fieldList;
2126        # Get the field table for the relationship.
2127        my $relationshipFields = $self->GetFieldTable($relationship);
2128        # Here we have a different rule. We want all the fields other than "from-link" and "to-link".
2129        # This may end up being an empty set.
2130        my @fieldList2 = map { "$relationship($_)" } grep { $_ ne "from-link" && $_ ne "to-link" }
2131                            keys %{$relationshipFields};
2132        # Push these onto the return list.
2133        push @retVal, sort @fieldList2;
2134        # Return the result.
2135        return @retVal;
2136    }
2137    
2138    =head3 FindColumn
2139    
2140  C<< my $entityObject = $sprout->GetEntity($entityType, $ID); >>  C<< my $colIndex = ERDB::FindColumn($headerLine, $columnIdentifier); >>
2141    
2142  Return an object describing the entity instance with a specified ID.  Return the location a desired column in a data mining header line. The data
2143    mining header line is a tab-separated list of column names. The column
2144    identifier is either the numerical index of a column or the actual column
2145    name.
2146    
2147  =over 4  =over 4
2148    
2149  =item entityType  =item headerLine
2150    
2151  Entity type name.  The header line from a data mining command, which consists of a tab-separated
2152    list of column names.
2153    
2154  =item ID  =item columnIdentifier
2155    
2156  ID of the desired entity.  Either the ordinal number of the desired column (1-based), or the name of the
2157    desired column.
2158    
2159  =item RETURN  =item RETURN
2160    
2161  Returns a B<DBObject> representing the desired entity instance, or an undefined value if no  Returns the array index (0-based) of the desired column.
 instance is found with the specified key.  
2162    
2163  =back  =back
2164    
2165  =cut  =cut
2166    
2167  sub GetEntity {  sub FindColumn {
2168      # Get the parameters.      # Get the parameters.
2169      my ($self, $entityType, $ID) = @_;      my ($headerLine, $columnIdentifier) = @_;
2170      # Create a query.      # Declare the return variable.
2171      my $query = $self->Get([$entityType], "$entityType(id) = ?", $ID);      my $retVal;
2172      # Get the first (and only) object.      # Split the header line into column names.
2173      my $retVal = $query->Fetch();      my @headers = ParseColumns($headerLine);
2174        Trace("Column header count is " . scalar(@headers) . ".") if T(4);
2175        # Determine whether we have a number or a name.
2176        if ($columnIdentifier =~ /^\d+$/) {
2177            # Here we have a number. Subtract 1 and validate the result.
2178            $retVal = $columnIdentifier - 1;
2179            if ($retVal < 0 || $retVal > $#headers) {
2180                Confess("Invalid column identifer \"$columnIdentifier\": value out of range.");
2181            }
2182        } else {
2183            # Here we have a name. We need to find it in the list.
2184            for (my $i = 0; $i <= $#headers && ! defined($retVal); $i++) {
2185                if ($headers[$i] eq $columnIdentifier) {
2186                    $retVal = $i;
2187                }
2188            }
2189            if (! defined($retVal)) {
2190                Confess("Invalid column identifier \"$columnIdentifier\": value not found.");
2191            }
2192        }
2193      # Return the result.      # Return the result.
2194      return $retVal;      return $retVal;
2195  }  }
2196    
2197  =head3 GetEntityValues  =head3 ParseColumns
2198    
2199  C<< my @values = GetEntityValues($entityType, $ID, \@fields); >>  C<< my @columns = ERDB->ParseColumns($line); >>
2200    
2201  Return a list of values from a specified entity instance.  Convert the specified data line to a list of columns.
2202    
2203  =over 4  =over 4
2204    
2205  =item entityType  =item line
   
 Entity type name.  
   
 =item ID  
   
 ID of the desired entity.  
   
 =item fields  
2206    
2207  List of field names, each of the form I<objectName>C<(>I<fieldName>C<)>.  A data mining input, consisting of a tab-separated list of columns terminated by a
2208    new-line.
2209    
2210  =item RETURN  =item RETURN
2211    
2212  Returns a flattened list of the values of the specified fields for the specified entity.  Returns a list consisting of the column values.
2213    
2214  =back  =back
2215    
2216  =cut  =cut
2217    
2218  sub GetEntityValues {  sub ParseColumns {
2219      # Get the parameters.      # Get the parameters.
2220      my ($self, $entityType, $ID, $fields) = @_;      my ($self, $line) = @_;
2221      # Get the specified entity.      # Chop off the line-end.
2222      my $entity = $self->GetEntity($entityType, $ID);      chomp $line;
2223      # Declare the return list.      # Split it into a list.
2224      my @retVal = ();      my @retVal = split(/\t/, $line);
     # If we found the entity, push the values into the return list.  
     if ($entity) {  
         push @retVal, $entity->Values($fields);  
     }  
2225      # Return the result.      # Return the result.
2226      return @retVal;      return @retVal;
2227  }  }
2228    
2229  =head3 GetAll  =head2 Internal Utility Methods
   
 C<< my @list = $sprout->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count); >>  
2230    
2231  Return a list of values taken from the objects returned by a query. The first three  =head3 SetupSQL
 parameters correspond to the parameters of the L</Get> method. The final parameter is  
 a list of the fields desired from each record found by the query. The field name  
 syntax is the standard syntax used for fields in the B<ERDB> system--  
 B<I<objectName>(I<fieldName>)>-- where I<objectName> is the name of the relevant entity  
 or relationship and I<fieldName> is the name of the field.  
2232    
2233  The list returned will be a list of lists. Each element of the list will contain  Process a list of object names and a filter clause so that they can be used to
2234  the values returned for the fields specified in the fourth parameter. If one of the  build an SQL statement. This method takes in a reference to a list of object names
2235  fields specified returns multiple values, they are flattened in with the rest. For  and a filter clause. It will return a corrected filter clause, a list of mapped
2236  example, the following call will return a list of the features in a particular  names and the mapped name hash.
 spreadsheet cell, and each feature will be represented by a list containing the  
 feature ID followed by all of its aliases.  
2237    
2238  C<< $query = $sprout->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>  This is an instance method.
2239    
2240  =over 4  =over 4
2241    
2242  =item objectNames  =item objectNames
2243    
2244  List containing the names of the entity and relationship objects to be retrieved.  Reference to a list of the object names to be included in the query.
2245    
2246  =item filterClause  =item filterClause
2247    
2248  WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can  A string containing the WHERE clause for the query (without the C<WHERE>) and also
2249  be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form  optionally the C<ORDER BY> and C<LIMIT> clauses.
 B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the  
 parameter list as additional parameters. The fields in a filter clause can come from primary  
 entity relations, relationship relations, or secondary entity relations; however, all of the  
 entities and relationships involved must be included in the list of object names.  
2250    
2251  =item parameterList  =item RETURN
2252    
2253  List of the parameters to be substituted in for the parameters marks in the filter clause.  Returns a three-element list. The first element is the SQL statement suffix, beginning
2254    with the FROM clause. The second element is a reference to a list of the names to be
2255    used in retrieving the fields. The third element is a hash mapping the names to the
2256    objects they represent.
2257    
2258  =item fields  =back
2259    
2260  List of the fields to be returned in each element of the list returned.  =cut
2261    
2262  =item count  sub _SetupSQL {
2263        my ($self, $objectNames, $filterClause) = @_;
2264        # Adjust the list of object names to account for multiple occurrences of the
2265        # same object. We start with a hash table keyed on object name that will
2266        # return the object suffix. The first time an object is encountered it will
2267        # not be found in the hash. The next time the hash will map the object name
2268        # to 2, then 3, and so forth.
2269        my %objectHash = ();
2270        # This list will contain the object names as they are to appear in the
2271        # FROM list.
2272        my @fromList = ();
2273        # This list contains the suffixed object name for each object. It is exactly
2274        # parallel to the list in the $objectNames parameter.
2275        my @mappedNameList = ();
2276        # Finally, this hash translates from a mapped name to its original object name.
2277        my %mappedNameHash = ();
2278        # Now we create the lists. Note that for every single name we push something into
2279        # @fromList and @mappedNameList. This insures that those two arrays are exactly
2280        # parallel to $objectNames.
2281        for my $objectName (@{$objectNames}) {
2282            # Get the next suffix for this object.
2283            my $suffix = $objectHash{$objectName};
2284            if (! $suffix) {
2285                # Here we are seeing the object for the first time. The object name
2286                # is used as is.
2287                push @mappedNameList, $objectName;
2288                push @fromList, $objectName;
2289                $mappedNameHash{$objectName} = $objectName;
2290                # Denote the next suffix will be 2.
2291                $objectHash{$objectName} = 2;
2292            } else {
2293                # Here we've seen the object before. We construct a new name using
2294                # the suffix from the hash and update the hash.
2295                my $mappedName = "$objectName$suffix";
2296                $objectHash{$objectName} = $suffix + 1;
2297                # The FROM list has the object name followed by the mapped name. This
2298                # tells SQL it's still the same table, but we're using a different name
2299                # for it to avoid confusion.
2300                push @fromList, "$objectName $mappedName";
2301                # The mapped-name list contains the real mapped name.
2302                push @mappedNameList, $mappedName;
2303                # Finally, enable us to get back from the mapped name to the object name.
2304                $mappedNameHash{$mappedName} = $objectName;
2305            }
2306        }
2307        # Begin the SELECT suffix. It starts with
2308        #
2309        # FROM name1, name2, ... nameN
2310        #
2311        my $suffix = "FROM " . join(', ', @fromList);
2312        # Check for a filter clause.
2313        if ($filterClause) {
2314            # Here we have one, so we convert its field names and add it to the query. First,
2315            # We create a copy of the filter string we can work with.
2316            my $filterString = $filterClause;
2317            # Next, we sort the object names by length. This helps protect us from finding
2318            # object names inside other object names when we're doing our search and replace.
2319            my @sortedNames = sort { length($b) - length($a) } @mappedNameList;
2320            # We will also keep a list of conditions to add to the WHERE clause in order to link
2321            # entities and relationships as well as primary relations to secondary ones.
2322            my @joinWhere = ();
2323            # The final preparatory step is to create a hash table of relation names. The
2324            # table begins with the relation names already in the SELECT command. We may
2325            # need to add relations later if there is filtering on a field in a secondary
2326            # relation. The secondary relations are the ones that contain multiply-
2327            # occurring or optional fields.
2328            my %fromNames = map { $_ => 1 } @sortedNames;
2329            # We are ready to begin. We loop through the object names, replacing each
2330            # object name's field references by the corresponding SQL field reference.
2331            # Along the way, if we find a secondary relation, we will need to add it
2332            # to the FROM clause.
2333            for my $mappedName (@sortedNames) {
2334                # Get the length of the object name plus 2. This is the value we add to the
2335                # size of the field name to determine the size of the field reference as a
2336                # whole.
2337                my $nameLength = 2 + length $mappedName;
2338                # Get the real object name for this mapped name.
2339                my $objectName = $mappedNameHash{$mappedName};
2340                Trace("Processing $mappedName for object $objectName.") if T(4);
2341                # Get the object's field list.
2342                my $fieldList = $self->GetFieldTable($objectName);
2343                # Find the field references for this object.
2344                while ($filterString =~ m/$mappedName\(([^)]*)\)/g) {
2345                    # At this point, $1 contains the field name, and the current position
2346                    # is set immediately after the final parenthesis. We pull out the name of
2347                    # the field and the position and length of the field reference as a whole.
2348                    my $fieldName = $1;
2349                    my $len = $nameLength + length $fieldName;
2350                    my $pos = pos($filterString) - $len;
2351                    # Insure the field exists.
2352                    if (!exists $fieldList->{$fieldName}) {
2353                        Confess("Field $fieldName not found for object $objectName.");
2354                    } else {
2355                        Trace("Processing $fieldName at position $pos.") if T(4);
2356                        # Get the field's relation.
2357                        my $relationName = $fieldList->{$fieldName}->{relation};
2358                        # Now we have a secondary relation. We need to insure it matches the
2359                        # mapped name of the primary relation. First we peel off the suffix
2360                        # from the mapped name.
2361                        my $mappingSuffix = substr $mappedName, length($objectName);
2362                        # Put the mapping suffix onto the relation name to get the
2363                        # mapped relation name.
2364                        my $mappedRelationName = "$relationName$mappingSuffix";
2365                        # Insure the relation is in the FROM clause.
2366                        if (!exists $fromNames{$mappedRelationName}) {
2367                            # Add the relation to the FROM clause.
2368                            if ($mappedRelationName eq $relationName) {
2369                                # The name is un-mapped, so we add it without
2370                                # any frills.
2371                                $suffix .= ", $relationName";
2372                                push @joinWhere, "$objectName.id = $relationName.id";
2373                            } else {
2374                                # Here we have a mapping situation.
2375                                $suffix .= ", $relationName $mappedRelationName";
2376                                push @joinWhere, "$mappedRelationName.id = $mappedName.id";
2377                            }
2378                            # Denote we have this relation available for future fields.
2379                            $fromNames{$mappedRelationName} = 1;
2380                        }
2381                        # Form an SQL field reference from the relation name and the field name.
2382                        my $sqlReference = "$mappedRelationName." . _FixName($fieldName);
2383                        # Put it into the filter string in place of the old value.
2384                        substr($filterString, $pos, $len) = $sqlReference;
2385                        # Reposition the search.
2386                        pos $filterString = $pos + length $sqlReference;
2387                    }
2388                }
2389            }
2390            # The next step is to join the objects together. We only need to do this if there
2391            # is more than one object in the object list. We start with the first object and
2392            # run through the objects after it. Note also that we make a safety copy of the
2393            # list before running through it.
2394            my @mappedObjectList = @mappedNameList;
2395            my $lastMappedObject = shift @mappedObjectList;
2396            # Get the join table.
2397            my $joinTable = $self->{_metaData}->{Joins};
2398            # Loop through the object list.
2399            for my $thisMappedObject (@mappedObjectList) {
2400                # Look for a join using the real object names.
2401                my $lastObject = $mappedNameHash{$lastMappedObject};
2402                my $thisObject = $mappedNameHash{$thisMappedObject};
2403                my $joinKey = "$lastObject/$thisObject";
2404                if (!exists $joinTable->{$joinKey}) {
2405                    # Here there's no join, so we throw an error.
2406                    Confess("No join exists to connect from $lastMappedObject to $thisMappedObject.");
2407                } else {
2408                    # Get the join clause.
2409                    my $unMappedJoin = $joinTable->{$joinKey};
2410                    # Fix the names.
2411                    $unMappedJoin =~ s/$lastObject/$lastMappedObject/;
2412                    $unMappedJoin =~ s/$thisObject/$thisMappedObject/;
2413                    push @joinWhere, $unMappedJoin;
2414                    # Save this object as the last object for the next iteration.
2415                    $lastMappedObject = $thisMappedObject;
2416                }
2417            }
2418            # Now we need to handle the whole ORDER BY / LIMIT thing. The important part
2419            # here is we want the filter clause to be empty if there's no WHERE filter.
2420            # We'll put the ORDER BY / LIMIT clauses in the following variable.
2421            my $orderClause = "";
2422            # Locate the ORDER BY or LIMIT verbs (if any). We use a non-greedy
2423            # operator so that we find the first occurrence of either verb.
2424            if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {
2425                # Here we have an ORDER BY or LIMIT verb. Split it off of the filter string.
2426                my $pos = pos $filterString;
2427                $orderClause = $2 . substr($filterString, $pos);
2428                $filterString = $1;
2429            }
2430            # Add the filter and the join clauses (if any) to the SELECT command.
2431            if ($filterString) {
2432                Trace("Filter string is \"$filterString\".") if T(4);
2433                push @joinWhere, "($filterString)";
2434            }
2435            if (@joinWhere) {
2436                $suffix .= " WHERE " . join(' AND ', @joinWhere);
2437            }
2438            # Add the sort or limit clause (if any) to the SELECT command.
2439            if ($orderClause) {
2440                $suffix .= " $orderClause";
2441            }
2442        }
2443        # Return the suffix, the mapped name list, and the mapped name hash.
2444        return ($suffix, \@mappedNameList, \%mappedNameHash);
2445    }
2446    
2447  Maximum number of records to return. If omitted or 0, all available records will be returned.  =head3 GetStatementHandle
2448    
2449    This method will prepare and execute an SQL query, returning the statement handle.
2450    The main reason for doing this here is so that everybody who does SQL queries gets
2451    the benefit of tracing.
2452    
2453    This is an instance method.
2454    
2455    =over 4
2456    
2457    =item command
2458    
2459    Command to prepare and execute.
2460    
2461    =item params
2462    
2463    Reference to a list of the values to be substituted in for the parameter marks.
2464    
2465  =item RETURN  =item RETURN
2466    
2467  Returns a list of list references. Each element of the return list contains the values for the  Returns a prepared and executed statement handle from which the caller can extract
2468  fields specified in the B<fields> parameter.  results.
2469    
2470  =back  =back
2471    
2472  =cut  =cut
2473  #: Return Type @@;  
2474  sub GetAll {  sub _GetStatementHandle {
2475      # Get the parameters.      # Get the parameters.
2476      my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;      my ($self, $command, $params) = @_;
2477      # Translate the parameters from a list reference to a list. If the parameter      # Trace the query.
2478      # list is a scalar we convert it into a singleton list.      Trace("SQL query: $command") if T(SQL => 3);
2479      my @parmList = ();      Trace("PARMS: '" . (join "', '", @{$params}) . "'") if (T(SQL => 4) && (@{$params} > 0));
2480      if (ref $parameterList eq "ARRAY") {      # Get the database handle.
2481          @parmList = @{$parameterList};      my $dbh = $self->{_dbh};
2482      } else {      # Prepare the command.
2483          push @parmList, $parameterList;      my $sth = $dbh->prepare_command($command);
2484      }      # Execute it with the parameters bound in.
2485      # Create the query.      $sth->execute(@{$params}) || Confess("SELECT error" . $sth->errstr());
2486      my $query = $self->Get($objectNames, $filterClause, @parmList);      # Return the statement handle.
2487      # Set up a counter of the number of records read.      return $sth;
     my $fetched = 0;  
     # Insure the counter has a value.  
     if (!defined $count) {  
         $count = 0;  
     }  
     # Loop through the records returned, extracting the fields. Note that if the  
     # counter is non-zero, we stop when the number of records read hits the count.  
     my @retVal = ();  
     while (($count == 0 || $fetched < $count) && (my $row = $query->Fetch())) {  
         my @rowData = $row->Values($fields);  
         push @retVal, \@rowData;  
         $fetched++;  
     }  
     # Return the resulting list.  
     return @retVal;  
2488  }  }
2489    
 =head2 Internal Utility Methods  
   
2490  =head3 GetLoadStats  =head3 GetLoadStats
2491    
2492  Return a blank statistics object for use by the load methods.  Return a blank statistics object for use by the load methods.
# Line 1625  Line 2496 
2496  =cut  =cut
2497    
2498  sub _GetLoadStats {  sub _GetLoadStats {
2499      return Stats->new('records');      return Stats->new();
2500  }  }
2501    
2502  =head3 GenerateFields  =head3 GenerateFields
# Line 1820  Line 2691 
2691      return $objectData->{Relations};      return $objectData->{Relations};
2692  }  }
2693    
 =head3 GetFieldTable  
   
 Get the field structure for a specified entity or relationship.  
   
 This is an instance method.  
   
 =over 4  
   
 =item objectName  
   
 Name of the desired entity or relationship.  
   
 =item RETURN  
   
 The table containing the field descriptors for the specified object.  
   
 =back  
   
 =cut  
   
 sub _GetFieldTable {  
     # Get the parameters.  
     my ($self, $objectName) = @_;  
     # Get the descriptor from the metadata.  
     my $objectData = $self->_GetStructure($objectName);  
     # Return the object's field table.  
     return $objectData->{Fields};  
 }  
   
2694  =head3 ValidateFieldNames  =head3 ValidateFieldNames
2695    
2696  Determine whether or not the field names are valid. A description of the problems with the names  Determine whether or not the field names are valid. A description of the problems with the names
# Line 2196  Line 3038 
3038          my @fromList = ();          my @fromList = ();
3039          my @toList = ();          my @toList = ();
3040          my @bothList = ();          my @bothList = ();
3041          Trace("Join table build for $entityName.") if T(3);          Trace("Join table build for $entityName.") if T(metadata => 4);
3042          for my $relationshipName (keys %{$relationshipList}) {          for my $relationshipName (keys %{$relationshipList}) {
3043              my $relationship = $relationshipList->{$relationshipName};              my $relationship = $relationshipList->{$relationshipName};
3044              # 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.
3045              my $fromEntity = $relationship->{from};              my $fromEntity = $relationship->{from};
3046              my $toEntity = $relationship->{to};              my $toEntity = $relationship->{to};
3047              Trace("Join check for relationship $relationshipName from $fromEntity to $toEntity.") if T(3);              Trace("Join check for relationship $relationshipName from $fromEntity to $toEntity.") if T(Joins => 4);
3048              if ($fromEntity eq $entityName) {              if ($fromEntity eq $entityName) {
3049                  if ($toEntity eq $entityName) {                  if ($toEntity eq $entityName) {
3050                      # Here the relationship is recursive.                      # Here the relationship is recursive.
3051                      push @bothList, $relationshipName;                      push @bothList, $relationshipName;
3052                      Trace("Relationship $relationshipName put in both-list.") if T(3);                      Trace("Relationship $relationshipName put in both-list.") if T(metadata => 4);
3053                  } else {                  } else {
3054                      # Here the relationship comes from the entity.                      # Here the relationship comes from the entity.
3055                      push @fromList, $relationshipName;                      push @fromList, $relationshipName;
3056                      Trace("Relationship $relationshipName put in from-list.") if T(3);                      Trace("Relationship $relationshipName put in from-list.") if T(metadata => 4);
3057                  }                  }
3058              } elsif ($toEntity eq $entityName) {              } elsif ($toEntity eq $entityName) {
3059                  # Here the relationship goes to the entity.                  # Here the relationship goes to the entity.
3060                  push @toList, $relationshipName;                  push @toList, $relationshipName;
3061                  Trace("Relationship $relationshipName put in to-list.") if T(3);                  Trace("Relationship $relationshipName put in to-list.") if T(metadata => 4);
3062              }              }
3063          }          }
3064          # 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 2232  Line 3074 
3074                  # Create joins between the entity and this relationship.                  # Create joins between the entity and this relationship.
3075                  my $linkField = "$relationshipName.${linkType}_link";                  my $linkField = "$relationshipName.${linkType}_link";
3076                  my $joinClause = "$entityName.id = $linkField";                  my $joinClause = "$entityName.id = $linkField";
3077                  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);
3078                  $joinTable{"$entityName/$relationshipName"} = $joinClause;                  $joinTable{"$entityName/$relationshipName"} = $joinClause;
3079                  $joinTable{"$relationshipName/$entityName"} = $joinClause;                  $joinTable{"$relationshipName/$entityName"} = $joinClause;
3080                  # Create joins between this relationship and the other relationships.                  # Create joins between this relationship and the other relationships.
# Line 2253  Line 3095 
3095                              # relationship and itself are prohibited.                              # relationship and itself are prohibited.
3096                              my $relJoinClause = "$otherName.${otherType}_link = $linkField";                              my $relJoinClause = "$otherName.${otherType}_link = $linkField";
3097                              $joinTable{$joinKey} = $relJoinClause;                              $joinTable{$joinKey} = $relJoinClause;
3098                              Trace("Relationship join clause is $relJoinClause for $joinKey.") if T(4);                              Trace("Relationship join clause is $relJoinClause for $joinKey.") if T(metadata => 4);
3099                          }                          }
3100                      }                      }
3101                  }                  }
# Line 2262  Line 3104 
3104                  # relationship can only be ambiguous with another recursive relationship,                  # relationship can only be ambiguous with another recursive relationship,
3105                  # and the incoming relationship from the outer loop is never recursive.                  # and the incoming relationship from the outer loop is never recursive.
3106                  for my $otherName (@bothList) {                  for my $otherName (@bothList) {
3107                      Trace("Setting up relationship joins to recursive relationship $otherName with $relationshipName.") if T(3);                      Trace("Setting up relationship joins to recursive relationship $otherName with $relationshipName.") if T(metadata => 4);
3108                      # Join from the left.                      # Join from the left.
3109                      $joinTable{"$relationshipName/$otherName"} =                      $joinTable{"$relationshipName/$otherName"} =
3110                          "$linkField = $otherName.from_link";                          "$linkField = $otherName.from_link";
# Line 2277  Line 3119 
3119          # 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
3120          # possible to get the same effect using multiple queries.          # possible to get the same effect using multiple queries.
3121          for my $relationshipName (@bothList) {          for my $relationshipName (@bothList) {
3122              Trace("Setting up entity joins to recursive relationship $relationshipName with $entityName.") if T(3);              Trace("Setting up entity joins to recursive relationship $relationshipName with $entityName.") if T(metadata => 4);
3123              # Join to the entity from each direction.              # Join to the entity from each direction.
3124              $joinTable{"$entityName/$relationshipName"} =              $joinTable{"$entityName/$relationshipName"} =
3125                  "$entityName.id = $relationshipName.from_link";                  "$entityName.id = $relationshipName.from_link";
# Line 2291  Line 3133 
3133      return $metadata;      return $metadata;
3134  }  }
3135    
3136    =head3 SortNeeded
3137    
3138    C<< my $flag = $erdb->SortNeeded($relationName); >>
3139    
3140    Return TRUE if the specified relation should be sorted during loading to remove duplicate keys,
3141    else FALSE.
3142    
3143    =over 4
3144    
3145    =item relationName
3146    
3147    Name of the relation to be examined.
3148    
3149    =item RETURN
3150    
3151    Returns TRUE if the relation needs a sort, else FALSE.
3152    
3153    =back
3154    
3155    =cut
3156    #: Return Type $;
3157    sub SortNeeded {
3158        # Get the parameters.
3159        my ($self, $relationName) = @_;
3160        # Declare the return variable.
3161        my $retVal = 0;
3162        # Find out if the relation is a primary entity relation.
3163        my $entityTable = $self->{_metaData}->{Entities};
3164        if (exists $entityTable->{$relationName}) {
3165            my $keyType = $entityTable->{$relationName}->{keyType};
3166            Trace("Relation $relationName found in entity table with key type $keyType.") if T(3);
3167            # If the key is not a hash string, we must do the sort.
3168            if ($keyType ne 'hash-string') {
3169                $retVal = 1;
3170            }
3171        }
3172        # Return the result.
3173        return $retVal;
3174    }
3175    
3176  =head3 CreateRelationshipIndex  =head3 CreateRelationshipIndex
3177    
3178  Create an index for a relationship's relation.  Create an index for a relationship's relation.

Legend:
Removed from v.1.16  
changed lines
  Added in v.1.49

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3