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

Diff of /Sprout/ERDB.pm

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

revision 1.18, Sun Aug 14 23:32:08 2005 UTC revision 1.59, Fri Jul 7 00:24:50 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 308  Line 325 
325                    text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, dataGen => "StringGen(IntGen(80,1000))" },                    text =>    { sqlType => 'TEXT',               maxLen => 1000000000,   avgLen => 500, dataGen => "StringGen(IntGen(80,1000))" },
326                    date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, dataGen => "DateGen(-7, 7, IntGen(0,1400))" },                    date =>    { sqlType => 'BIGINT',             maxLen => 80,           avgLen =>   8, dataGen => "DateGen(-7, 7, IntGen(0,1400))" },
327                    float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, dataGen => "FloatGen(0.0, 100.0)" },                    float =>   { sqlType => 'DOUBLE PRECISION',   maxLen => 40,           avgLen =>   8, dataGen => "FloatGen(0.0, 100.0)" },
328                    boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   2, dataGen => "IntGen(0, 1)" },                    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,           avgLen =>  10, dataGen => "StringGen(IntGen(10,40))" },                               { sqlType => 'VARCHAR(40)',        maxLen => 40,           avgLen =>  10, dataGen => "StringGen(IntGen(10,40))" },
335                   'name-string' =>                   'name-string' =>
# Line 401  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 445  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 469  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 479  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 507  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 $retVal;
     close HTMLOUT;  
     Trace("Built MetaData web page.") if T(3);  
583  }  }
584    
585  =head3 DumpMetaData  =head3 DumpMetaData
# Line 552  Line 611 
611  sub CreateTables {  sub CreateTables {
612      # Get the parameters.      # Get the parameters.
613      my ($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    
# Line 645  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 of the 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<< $erdb->CreateIndex($relationName); >>  C<< $erdb->CreateIndex($relationName); >>
# Line 673  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    
# Line 723  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 = $erdb->GetTableNames; >>  C<< my @names = $erdb->GetTableNames; >>
# Line 782  Line 950 
950      return sort keys %{$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 = $erdb->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 792  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 = $erdb->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
# Line 809  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 = $erdb->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 842  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 860  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(3);  
     Trace("PARMS: '" . (join "', '", @params) . "'") if (T(4) && (@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 = $erdb->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 1000  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 1045  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 = $erdb->ComputeObjectSentence($objectName); >>  C<< my $sentence = $erdb->ComputeObjectSentence($objectName); >>
# Line 1122  Line 1544 
1544      }      }
1545  }  }
1546    
1547    =head3 InsertValue
1548    
1549    C<< $erdb->InsertValue($entityID, $fieldName, $value); >>
1550    
1551    This method will insert a new value into the database. The value must be one
1552    associated with a secondary relation, since primary values cannot be inserted:
1553    they occur exactly once. Secondary values, on the other hand, can be missing
1554    or multiply-occurring.
1555    
1556    =over 4
1557    
1558    =item entityID
1559    
1560    ID of the object that is to receive the new value.
1561    
1562    =item fieldName
1563    
1564    Field name for the new value-- this includes the entity name, since
1565    field names are of the format I<objectName>C<(>I<fieldName>C<)>.
1566    
1567    =item value
1568    
1569    New value to be put in the field.
1570    
1571    =back
1572    
1573    =cut
1574    
1575    sub InsertValue {
1576        # Get the parameters.
1577        my ($self, $entityID, $fieldName, $value) = @_;
1578        # Parse the entity name and the real field name.
1579        if ($fieldName =~ /^([^(]+)\(([^)]+)\)/) {
1580            my $entityName = $1;
1581            my $fieldTitle = $2;
1582            # Get its descriptor.
1583            if (!$self->IsEntity($entityName)) {
1584                Confess("$entityName is not a valid entity.");
1585            } else {
1586                my $entityData = $self->{_metaData}->{Entities}->{$entityName};
1587                # Find the relation containing this field.
1588                my $fieldHash = $entityData->{Fields};
1589                if (! exists $fieldHash->{$fieldTitle}) {
1590                    Confess("$fieldTitle not found in $entityName.");
1591                } else {
1592                    my $relation = $fieldHash->{$fieldTitle}->{relation};
1593                    if ($relation eq $entityName) {
1594                        Confess("Cannot do InsertValue on primary field $fieldTitle of $entityName.");
1595                    } else {
1596                        # Now we can create an INSERT statement.
1597                        my $dbh = $self->{_dbh};
1598                        my $fixedName = _FixName($fieldTitle);
1599                        my $statement = "INSERT INTO $relation (id, $fixedName) VALUES(?, ?)";
1600                        # Execute the command.
1601                        $dbh->SQL($statement, 0, $entityID, $value);
1602                    }
1603                }
1604            }
1605        } else {
1606            Confess("$fieldName is not a valid field name.");
1607        }
1608    }
1609    
1610  =head3 InsertObject  =head3 InsertObject
1611    
1612  C<< my $ok = $erdb->InsertObject($objectType, \%fieldHash); >>  C<< my $ok = $erdb->InsertObject($objectType, \%fieldHash); >>
# Line 1138  Line 1623 
1623  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
1624  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>.
1625    
1626  C<< $erdb->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'}); >>
1627    
1628  =over 4  =over 4
1629    
# Line 1284  Line 1769 
1769    
1770  =item RETURN  =item RETURN
1771    
1772  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.  
1773    
1774  =back  =back
1775    
# Line 1299  Line 1783 
1783      Trace("Loading table $relationName from $fileName") if T(2);      Trace("Loading table $relationName from $fileName") if T(2);
1784      # Get the database handle.      # Get the database handle.
1785      my $dbh = $self->{_dbh};      my $dbh = $self->{_dbh};
1786        # Get the input file size.
1787        my $fileSize = -s $fileName;
1788      # Get the relation data.      # Get the relation data.
1789      my $relation = $self->_FindRelation($relationName);      my $relation = $self->_FindRelation($relationName);
1790      # Check the truncation flag.      # Check the truncation flag.
1791      if ($truncateFlag) {      if ($truncateFlag) {
1792          Trace("Creating table $relationName") if T(2);          Trace("Creating table $relationName") if T(2);
1793            # Compute the row count estimate. We take the size of the load file,
1794            # divide it by the estimated row size, and then multiply by 1.5 to
1795            # leave extra room. We postulate a minimum row count of 1000 to
1796            # prevent problems with incoming empty load files.
1797            my $rowSize = $self->EstimateRowSize($relationName);
1798            my $estimate = FIG::max($fileSize * 1.5 / $rowSize, 1000);
1799          # Re-create the table without its index.          # Re-create the table without its index.
1800          $self->CreateTable($relationName, 0);          $self->CreateTable($relationName, 0, $estimate);
1801          # If this is a pre-index DBMS, create the index here.          # If this is a pre-index DBMS, create the index here.
1802          if ($dbh->{_preIndex}) {          if ($dbh->{_preIndex}) {
1803              eval {              eval {
# Line 1316  Line 1808 
1808              }              }
1809          }          }
1810      }      }
     # 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);  
1811      # Load the table.      # Load the table.
1812      my $rv;      my $rv;
1813      eval {      eval {
1814          $rv = $dbh->load_table(file => $tempName, tbl => $relationName);          $rv = $dbh->load_table(file => $fileName, tbl => $relationName);
1815      };      };
1816      if (!defined $rv) {      if (!defined $rv) {
1817          $retVal->AddMessage($@) if ($@);          $retVal->AddMessage($@) if ($@);
1818          $retVal->AddMessage("Table load failed for $relationName using $tempName.");          $retVal->AddMessage("Table load failed for $relationName using $fileName.");
1819          Trace("Table load failed for $relationName.") if T(1);          Trace("Table load failed for $relationName.") if T(1);
1820      } else {      } else {
1821          # Here we successfully loaded the table. Trace the number of records loaded.          # Here we successfully loaded the table.
1822          Trace("$retVal->{records} records read for $relationName.") if T(2);          $retVal->Add("tables");
1823            my $size = -s $fileName;
1824            Trace("$size bytes loaded into $relationName.") if T(2);
1825          # If we're rebuilding, we need to create the table indexes.          # If we're rebuilding, we need to create the table indexes.
1826          if ($truncateFlag && ! $dbh->{_preIndex}) {          if ($truncateFlag && ! $dbh->{_preIndex}) {
1827              eval {              eval {
# Line 1392  Line 1831 
1831                  $retVal->AddMessage($@);                  $retVal->AddMessage($@);
1832              }              }
1833          }          }
         # Analyze the table to help optimize tables.  
1834      }      }
1835      # Commit the database changes.      # Analyze the table to improve performance.
     $dbh->commit_tran;  
1836      $dbh->vacuum_it($relationName);      $dbh->vacuum_it($relationName);
1837      # Delete the temporary file.      # Flush the database cache.
1838      unlink $tempName;      $dbh->flush_tables();
1839      # Return the statistics.      # Return the statistics.
1840      return $retVal;      return $retVal;
1841  }  }
# Line 1490  Line 1927 
1927      # Get the parameters.      # Get the parameters.
1928      my ($self, $entityType, $ID) = @_;      my ($self, $entityType, $ID) = @_;
1929      # Create a query.      # Create a query.
1930      my $query = $self->Get([$entityType], "$entityType(id) = ?", $ID);      my $query = $self->Get([$entityType], "$entityType(id) = ?", [$ID]);
1931      # Get the first (and only) object.      # Get the first (and only) object.
1932      my $retVal = $query->Fetch();      my $retVal = $query->Fetch();
1933      # Return the result.      # Return the result.
# Line 1603  Line 2040 
2040      # list is a scalar we convert it into a singleton list.      # list is a scalar we convert it into a singleton list.
2041      my @parmList = ();      my @parmList = ();
2042      if (ref $parameterList eq "ARRAY") {      if (ref $parameterList eq "ARRAY") {
2043            Trace("GetAll parm list is an array.") if T(4);
2044          @parmList = @{$parameterList};          @parmList = @{$parameterList};
2045      } else {      } else {
2046            Trace("GetAll parm list is a scalar: $parameterList.") if T(4);
2047          push @parmList, $parameterList;          push @parmList, $parameterList;
2048      }      }
     # Create the query.  
     my $query = $self->Get($objectNames, $filterClause, @parmList);  
     # Set up a counter of the number of records read.  
     my $fetched = 0;  
2049      # Insure the counter has a value.      # Insure the counter has a value.
2050      if (!defined $count) {      if (!defined $count) {
2051          $count = 0;          $count = 0;
2052      }      }
2053        # Add the row limit to the filter clause.
2054        if ($count > 0) {
2055            $filterClause .= " LIMIT $count";
2056        }
2057        # Create the query.
2058        my $query = $self->Get($objectNames, $filterClause, \@parmList);
2059        # Set up a counter of the number of records read.
2060        my $fetched = 0;
2061      # Loop through the records returned, extracting the fields. Note that if the      # Loop through the records returned, extracting the fields. Note that if the
2062      # counter is non-zero, we stop when the number of records read hits the count.      # counter is non-zero, we stop when the number of records read hits the count.
2063      my @retVal = ();      my @retVal = ();
# Line 1623  Line 2066 
2066          push @retVal, \@rowData;          push @retVal, \@rowData;
2067          $fetched++;          $fetched++;
2068      }      }
2069        Trace("$fetched rows returned in GetAll.") if T(SQL => 4);
2070      # Return the resulting list.      # Return the resulting list.
2071      return @retVal;      return @retVal;
2072  }  }
2073    
2074    =head3 Exists
2075    
2076    C<< my $found = $sprout->Exists($entityName, $entityID); >>
2077    
2078    Return TRUE if an entity exists, else FALSE.
2079    
2080    =over 4
2081    
2082    =item entityName
2083    
2084    Name of the entity type (e.g. C<Feature>) relevant to the existence check.
2085    
2086    =item entityID
2087    
2088    ID of the entity instance whose existence is to be checked.
2089    
2090    =item RETURN
2091    
2092    Returns TRUE if the entity instance exists, else FALSE.
2093    
2094    =back
2095    
2096    =cut
2097    #: Return Type $;
2098    sub Exists {
2099        # Get the parameters.
2100        my ($self, $entityName, $entityID) = @_;
2101        # Check for the entity instance.
2102        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
2103        my $testInstance = $self->GetEntity($entityName, $entityID);
2104        # Return an existence indicator.
2105        my $retVal = ($testInstance ? 1 : 0);
2106        return $retVal;
2107    }
2108    
2109  =head3 EstimateRowSize  =head3 EstimateRowSize
2110    
2111  C<< my $rowSize = $erdb->EstimateRowSize($relName); >>  C<< my $rowSize = $erdb->EstimateRowSize($relName); >>
# Line 1665  Line 2144 
2144      return $retVal;      return $retVal;
2145  }  }
2146    
2147    =head3 GetFieldTable
2148    
2149    C<< my $fieldHash = $self->GetFieldTable($objectnName); >>
2150    
2151    Get the field structure for a specified entity or relationship.
2152    
2153    =over 4
2154    
2155    =item objectName
2156    
2157    Name of the desired entity or relationship.
2158    
2159    =item RETURN
2160    
2161    The table containing the field descriptors for the specified object.
2162    
2163    =back
2164    
2165    =cut
2166    
2167    sub GetFieldTable {
2168        # Get the parameters.
2169        my ($self, $objectName) = @_;
2170        # Get the descriptor from the metadata.
2171        my $objectData = $self->_GetStructure($objectName);
2172        # Return the object's field table.
2173        return $objectData->{Fields};
2174    }
2175    
2176    =head2 Data Mining Methods
2177    
2178    =head3 GetUsefulCrossValues
2179    
2180    C<< my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship); >>
2181    
2182    Return a list of the useful attributes that would be returned by a B<Cross> call
2183    from an entity of the source entity type through the specified relationship. This
2184    means it will return the fields of the target entity type and the intersection data
2185    fields in the relationship. Only primary table fields are returned. In other words,
2186    the field names returned will be for fields where there is always one and only one
2187    value.
2188    
2189    =over 4
2190    
2191    =item sourceEntity
2192    
2193    Name of the entity from which the relationship crossing will start.
2194    
2195    =item relationship
2196    
2197    Name of the relationship being crossed.
2198    
2199    =item RETURN
2200    
2201    Returns a list of field names in Sprout field format (I<objectName>C<(>I<fieldName>C<)>.
2202    
2203    =back
2204    
2205    =cut
2206    #: Return Type @;
2207    sub GetUsefulCrossValues {
2208        # Get the parameters.
2209        my ($self, $sourceEntity, $relationship) = @_;
2210        # Declare the return variable.
2211        my @retVal = ();
2212        # Determine the target entity for the relationship. This is whichever entity is not
2213        # the source entity. So, if the source entity is the FROM, we'll get the name of
2214        # the TO, and vice versa.
2215        my $relStructure = $self->_GetStructure($relationship);
2216        my $targetEntityType = ($relStructure->{from} eq $sourceEntity ? "to" : "from");
2217        my $targetEntity = $relStructure->{$targetEntityType};
2218        # Get the field table for the entity.
2219        my $entityFields = $self->GetFieldTable($targetEntity);
2220        # The field table is a hash. The hash key is the field name. The hash value is a structure.
2221        # For the entity fields, the key aspect of the target structure is that the {relation} value
2222        # must match the entity name.
2223        my @fieldList = map { "$targetEntity($_)" } grep { $entityFields->{$_}->{relation} eq $targetEntity }
2224                            keys %{$entityFields};
2225        # Push the fields found onto the return variable.
2226        push @retVal, sort @fieldList;
2227        # Get the field table for the relationship.
2228        my $relationshipFields = $self->GetFieldTable($relationship);
2229        # Here we have a different rule. We want all the fields other than "from-link" and "to-link".
2230        # This may end up being an empty set.
2231        my @fieldList2 = map { "$relationship($_)" } grep { $_ ne "from-link" && $_ ne "to-link" }
2232                            keys %{$relationshipFields};
2233        # Push these onto the return list.
2234        push @retVal, sort @fieldList2;
2235        # Return the result.
2236        return @retVal;
2237    }
2238    
2239    =head3 FindColumn
2240    
2241    C<< my $colIndex = ERDB::FindColumn($headerLine, $columnIdentifier); >>
2242    
2243    Return the location a desired column in a data mining header line. The data
2244    mining header line is a tab-separated list of column names. The column
2245    identifier is either the numerical index of a column or the actual column
2246    name.
2247    
2248    =over 4
2249    
2250    =item headerLine
2251    
2252    The header line from a data mining command, which consists of a tab-separated
2253    list of column names.
2254    
2255    =item columnIdentifier
2256    
2257    Either the ordinal number of the desired column (1-based), or the name of the
2258    desired column.
2259    
2260    =item RETURN
2261    
2262    Returns the array index (0-based) of the desired column.
2263    
2264    =back
2265    
2266    =cut
2267    
2268    sub FindColumn {
2269        # Get the parameters.
2270        my ($headerLine, $columnIdentifier) = @_;
2271        # Declare the return variable.
2272        my $retVal;
2273        # Split the header line into column names.
2274        my @headers = ParseColumns($headerLine);
2275        # Determine whether we have a number or a name.
2276        if ($columnIdentifier =~ /^\d+$/) {
2277            # Here we have a number. Subtract 1 and validate the result.
2278            $retVal = $columnIdentifier - 1;
2279            if ($retVal < 0 || $retVal > $#headers) {
2280                Confess("Invalid column identifer \"$columnIdentifier\": value out of range.");
2281            }
2282        } else {
2283            # Here we have a name. We need to find it in the list.
2284            for (my $i = 0; $i <= $#headers && ! defined($retVal); $i++) {
2285                if ($headers[$i] eq $columnIdentifier) {
2286                    $retVal = $i;
2287                }
2288            }
2289            if (! defined($retVal)) {
2290                Confess("Invalid column identifier \"$columnIdentifier\": value not found.");
2291            }
2292        }
2293        # Return the result.
2294        return $retVal;
2295    }
2296    
2297    =head3 ParseColumns
2298    
2299    C<< my @columns = ERDB::ParseColumns($line); >>
2300    
2301    Convert the specified data line to a list of columns.
2302    
2303    =over 4
2304    
2305    =item line
2306    
2307    A data mining input, consisting of a tab-separated list of columns terminated by a
2308    new-line.
2309    
2310    =item RETURN
2311    
2312    Returns a list consisting of the column values.
2313    
2314    =back
2315    
2316    =cut
2317    
2318    sub ParseColumns {
2319        # Get the parameters.
2320        my ($line) = @_;
2321        # Chop off the line-end.
2322        chomp $line;
2323        # Split it into a list.
2324        my @retVal = split(/\t/, $line);
2325        # Return the result.
2326        return @retVal;
2327    }
2328    
2329  =head2 Internal Utility Methods  =head2 Internal Utility Methods
2330    
2331    =head3 SetupSQL
2332    
2333    Process a list of object names and a filter clause so that they can be used to
2334    build an SQL statement. This method takes in a reference to a list of object names
2335    and a filter clause. It will return a corrected filter clause, a list of mapped
2336    names and the mapped name hash.
2337    
2338    This is an instance method.
2339    
2340    =over 4
2341    
2342    =item objectNames
2343    
2344    Reference to a list of the object names to be included in the query.
2345    
2346    =item filterClause
2347    
2348    A string containing the WHERE clause for the query (without the C<WHERE>) and also
2349    optionally the C<ORDER BY> and C<LIMIT> clauses.
2350    
2351    =item RETURN
2352    
2353    Returns a three-element list. The first element is the SQL statement suffix, beginning
2354    with the FROM clause. The second element is a reference to a list of the names to be
2355    used in retrieving the fields. The third element is a hash mapping the names to the
2356    objects they represent.
2357    
2358    =back
2359    
2360    =cut
2361    
2362    sub _SetupSQL {
2363        my ($self, $objectNames, $filterClause) = @_;
2364        # Adjust the list of object names to account for multiple occurrences of the
2365        # same object. We start with a hash table keyed on object name that will
2366        # return the object suffix. The first time an object is encountered it will
2367        # not be found in the hash. The next time the hash will map the object name
2368        # to 2, then 3, and so forth.
2369        my %objectHash = ();
2370        # This list will contain the object names as they are to appear in the
2371        # FROM list.
2372        my @fromList = ();
2373        # This list contains the suffixed object name for each object. It is exactly
2374        # parallel to the list in the $objectNames parameter.
2375        my @mappedNameList = ();
2376        # Finally, this hash translates from a mapped name to its original object name.
2377        my %mappedNameHash = ();
2378        # Now we create the lists. Note that for every single name we push something into
2379        # @fromList and @mappedNameList. This insures that those two arrays are exactly
2380        # parallel to $objectNames.
2381        for my $objectName (@{$objectNames}) {
2382            # Get the next suffix for this object.
2383            my $suffix = $objectHash{$objectName};
2384            if (! $suffix) {
2385                # Here we are seeing the object for the first time. The object name
2386                # is used as is.
2387                push @mappedNameList, $objectName;
2388                push @fromList, $objectName;
2389                $mappedNameHash{$objectName} = $objectName;
2390                # Denote the next suffix will be 2.
2391                $objectHash{$objectName} = 2;
2392            } else {
2393                # Here we've seen the object before. We construct a new name using
2394                # the suffix from the hash and update the hash.
2395                my $mappedName = "$objectName$suffix";
2396                $objectHash{$objectName} = $suffix + 1;
2397                # The FROM list has the object name followed by the mapped name. This
2398                # tells SQL it's still the same table, but we're using a different name
2399                # for it to avoid confusion.
2400                push @fromList, "$objectName $mappedName";
2401                # The mapped-name list contains the real mapped name.
2402                push @mappedNameList, $mappedName;
2403                # Finally, enable us to get back from the mapped name to the object name.
2404                $mappedNameHash{$mappedName} = $objectName;
2405            }
2406        }
2407        # Begin the SELECT suffix. It starts with
2408        #
2409        # FROM name1, name2, ... nameN
2410        #
2411        my $suffix = "FROM " . join(', ', @fromList);
2412        # Check for a filter clause.
2413        if ($filterClause) {
2414            # Here we have one, so we convert its field names and add it to the query. First,
2415            # We create a copy of the filter string we can work with.
2416            my $filterString = $filterClause;
2417            # Next, we sort the object names by length. This helps protect us from finding
2418            # object names inside other object names when we're doing our search and replace.
2419            my @sortedNames = sort { length($b) - length($a) } @mappedNameList;
2420            # We will also keep a list of conditions to add to the WHERE clause in order to link
2421            # entities and relationships as well as primary relations to secondary ones.
2422            my @joinWhere = ();
2423            # The final preparatory step is to create a hash table of relation names. The
2424            # table begins with the relation names already in the SELECT command. We may
2425            # need to add relations later if there is filtering on a field in a secondary
2426            # relation. The secondary relations are the ones that contain multiply-
2427            # occurring or optional fields.
2428            my %fromNames = map { $_ => 1 } @sortedNames;
2429            # We are ready to begin. We loop through the object names, replacing each
2430            # object name's field references by the corresponding SQL field reference.
2431            # Along the way, if we find a secondary relation, we will need to add it
2432            # to the FROM clause.
2433            for my $mappedName (@sortedNames) {
2434                # Get the length of the object name plus 2. This is the value we add to the
2435                # size of the field name to determine the size of the field reference as a
2436                # whole.
2437                my $nameLength = 2 + length $mappedName;
2438                # Get the real object name for this mapped name.
2439                my $objectName = $mappedNameHash{$mappedName};
2440                Trace("Processing $mappedName for object $objectName.") if T(4);
2441                # Get the object's field list.
2442                my $fieldList = $self->GetFieldTable($objectName);
2443                # Find the field references for this object.
2444                while ($filterString =~ m/$mappedName\(([^)]*)\)/g) {
2445                    # At this point, $1 contains the field name, and the current position
2446                    # is set immediately after the final parenthesis. We pull out the name of
2447                    # the field and the position and length of the field reference as a whole.
2448                    my $fieldName = $1;
2449                    my $len = $nameLength + length $fieldName;
2450                    my $pos = pos($filterString) - $len;
2451                    # Insure the field exists.
2452                    if (!exists $fieldList->{$fieldName}) {
2453                        Confess("Field $fieldName not found for object $objectName.");
2454                    } else {
2455                        Trace("Processing $fieldName at position $pos.") if T(4);
2456                        # Get the field's relation.
2457                        my $relationName = $fieldList->{$fieldName}->{relation};
2458                        # Now we have a secondary relation. We need to insure it matches the
2459                        # mapped name of the primary relation. First we peel off the suffix
2460                        # from the mapped name.
2461                        my $mappingSuffix = substr $mappedName, length($objectName);
2462                        # Put the mapping suffix onto the relation name to get the
2463                        # mapped relation name.
2464                        my $mappedRelationName = "$relationName$mappingSuffix";
2465                        # Insure the relation is in the FROM clause.
2466                        if (!exists $fromNames{$mappedRelationName}) {
2467                            # Add the relation to the FROM clause.
2468                            if ($mappedRelationName eq $relationName) {
2469                                # The name is un-mapped, so we add it without
2470                                # any frills.
2471                                $suffix .= ", $relationName";
2472                                push @joinWhere, "$objectName.id = $relationName.id";
2473                            } else {
2474                                # Here we have a mapping situation.
2475                                $suffix .= ", $relationName $mappedRelationName";
2476                                push @joinWhere, "$mappedRelationName.id = $mappedName.id";
2477                            }
2478                            # Denote we have this relation available for future fields.
2479                            $fromNames{$mappedRelationName} = 1;
2480                        }
2481                        # Form an SQL field reference from the relation name and the field name.
2482                        my $sqlReference = "$mappedRelationName." . _FixName($fieldName);
2483                        # Put it into the filter string in place of the old value.
2484                        substr($filterString, $pos, $len) = $sqlReference;
2485                        # Reposition the search.
2486                        pos $filterString = $pos + length $sqlReference;
2487                    }
2488                }
2489            }
2490            # The next step is to join the objects together. We only need to do this if there
2491            # is more than one object in the object list. We start with the first object and
2492            # run through the objects after it. Note also that we make a safety copy of the
2493            # list before running through it.
2494            my @mappedObjectList = @mappedNameList;
2495            my $lastMappedObject = shift @mappedObjectList;
2496            # Get the join table.
2497            my $joinTable = $self->{_metaData}->{Joins};
2498            # Loop through the object list.
2499            for my $thisMappedObject (@mappedObjectList) {
2500                # Look for a join using the real object names.
2501                my $lastObject = $mappedNameHash{$lastMappedObject};
2502                my $thisObject = $mappedNameHash{$thisMappedObject};
2503                my $joinKey = "$lastObject/$thisObject";
2504                if (!exists $joinTable->{$joinKey}) {
2505                    # Here there's no join, so we throw an error.
2506                    Confess("No join exists to connect from $lastMappedObject to $thisMappedObject.");
2507                } else {
2508                    # Get the join clause.
2509                    my $unMappedJoin = $joinTable->{$joinKey};
2510                    # Fix the names.
2511                    $unMappedJoin =~ s/$lastObject/$lastMappedObject/;
2512                    $unMappedJoin =~ s/$thisObject/$thisMappedObject/;
2513                    push @joinWhere, $unMappedJoin;
2514                    # Save this object as the last object for the next iteration.
2515                    $lastMappedObject = $thisMappedObject;
2516                }
2517            }
2518            # Now we need to handle the whole ORDER BY / LIMIT thing. The important part
2519            # here is we want the filter clause to be empty if there's no WHERE filter.
2520            # We'll put the ORDER BY / LIMIT clauses in the following variable.
2521            my $orderClause = "";
2522            # Locate the ORDER BY or LIMIT verbs (if any). We use a non-greedy
2523            # operator so that we find the first occurrence of either verb.
2524            if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {
2525                # Here we have an ORDER BY or LIMIT verb. Split it off of the filter string.
2526                my $pos = pos $filterString;
2527                $orderClause = $2 . substr($filterString, $pos);
2528                $filterString = $1;
2529            }
2530            # Add the filter and the join clauses (if any) to the SELECT command.
2531            if ($filterString) {
2532                Trace("Filter string is \"$filterString\".") if T(4);
2533                push @joinWhere, "($filterString)";
2534            }
2535            if (@joinWhere) {
2536                $suffix .= " WHERE " . join(' AND ', @joinWhere);
2537            }
2538            # Add the sort or limit clause (if any) to the SELECT command.
2539            if ($orderClause) {
2540                $suffix .= " $orderClause";
2541            }
2542        }
2543        # Return the suffix, the mapped name list, and the mapped name hash.
2544        return ($suffix, \@mappedNameList, \%mappedNameHash);
2545    }
2546    
2547    =head3 GetStatementHandle
2548    
2549    This method will prepare and execute an SQL query, returning the statement handle.
2550    The main reason for doing this here is so that everybody who does SQL queries gets
2551    the benefit of tracing.
2552    
2553    This is an instance method.
2554    
2555    =over 4
2556    
2557    =item command
2558    
2559    Command to prepare and execute.
2560    
2561    =item params
2562    
2563    Reference to a list of the values to be substituted in for the parameter marks.
2564    
2565    =item RETURN
2566    
2567    Returns a prepared and executed statement handle from which the caller can extract
2568    results.
2569    
2570    =back
2571    
2572    =cut
2573    
2574    sub _GetStatementHandle {
2575        # Get the parameters.
2576        my ($self, $command, $params) = @_;
2577        # Trace the query.
2578        Trace("SQL query: $command") if T(SQL => 3);
2579        Trace("PARMS: '" . (join "', '", @{$params}) . "'") if (T(SQL => 4) && (@{$params} > 0));
2580        # Get the database handle.
2581        my $dbh = $self->{_dbh};
2582        # Prepare the command.
2583        my $sth = $dbh->prepare_command($command);
2584        # Execute it with the parameters bound in.
2585        $sth->execute(@{$params}) || Confess("SELECT error" . $sth->errstr());
2586        # Return the statement handle.
2587        return $sth;
2588    }
2589    
2590  =head3 GetLoadStats  =head3 GetLoadStats
2591    
2592  Return a blank statistics object for use by the load methods.  Return a blank statistics object for use by the load methods.
# Line 1676  Line 2596 
2596  =cut  =cut
2597    
2598  sub _GetLoadStats {  sub _GetLoadStats {
2599      return Stats->new('records');      return Stats->new();
2600  }  }
2601    
2602  =head3 GenerateFields  =head3 GenerateFields
# Line 1871  Line 2791 
2791      return $objectData->{Relations};      return $objectData->{Relations};
2792  }  }
2793    
 =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};  
 }  
   
2794  =head3 ValidateFieldNames  =head3 ValidateFieldNames
2795    
2796  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 2247  Line 3138 
3138          my @fromList = ();          my @fromList = ();
3139          my @toList = ();          my @toList = ();
3140          my @bothList = ();          my @bothList = ();
3141          Trace("Join table build for $entityName.") if T(4);          Trace("Join table build for $entityName.") if T(metadata => 4);
3142          for my $relationshipName (keys %{$relationshipList}) {          for my $relationshipName (keys %{$relationshipList}) {
3143              my $relationship = $relationshipList->{$relationshipName};              my $relationship = $relationshipList->{$relationshipName};
3144              # 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.
3145              my $fromEntity = $relationship->{from};              my $fromEntity = $relationship->{from};
3146              my $toEntity = $relationship->{to};              my $toEntity = $relationship->{to};
3147              Trace("Join check for relationship $relationshipName from $fromEntity to $toEntity.") if T(4);              Trace("Join check for relationship $relationshipName from $fromEntity to $toEntity.") if T(Joins => 4);
3148              if ($fromEntity eq $entityName) {              if ($fromEntity eq $entityName) {
3149                  if ($toEntity eq $entityName) {                  if ($toEntity eq $entityName) {
3150                      # Here the relationship is recursive.                      # Here the relationship is recursive.
3151                      push @bothList, $relationshipName;                      push @bothList, $relationshipName;
3152                      Trace("Relationship $relationshipName put in both-list.") if T(4);                      Trace("Relationship $relationshipName put in both-list.") if T(metadata => 4);
3153                  } else {                  } else {
3154                      # Here the relationship comes from the entity.                      # Here the relationship comes from the entity.
3155                      push @fromList, $relationshipName;                      push @fromList, $relationshipName;
3156                      Trace("Relationship $relationshipName put in from-list.") if T(4);                      Trace("Relationship $relationshipName put in from-list.") if T(metadata => 4);
3157                  }                  }
3158              } elsif ($toEntity eq $entityName) {              } elsif ($toEntity eq $entityName) {
3159                  # Here the relationship goes to the entity.                  # Here the relationship goes to the entity.
3160                  push @toList, $relationshipName;                  push @toList, $relationshipName;
3161                  Trace("Relationship $relationshipName put in to-list.") if T(4);                  Trace("Relationship $relationshipName put in to-list.") if T(metadata => 4);
3162              }              }
3163          }          }
3164          # Create the nonrecursive joins. Note that we build two hashes for running          # Create the nonrecursive joins. Note that we build two hashes for running
# Line 2283  Line 3174 
3174                  # Create joins between the entity and this relationship.                  # Create joins between the entity and this relationship.
3175                  my $linkField = "$relationshipName.${linkType}_link";                  my $linkField = "$relationshipName.${linkType}_link";
3176                  my $joinClause = "$entityName.id = $linkField";                  my $joinClause = "$entityName.id = $linkField";
3177                  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);
3178                  $joinTable{"$entityName/$relationshipName"} = $joinClause;                  $joinTable{"$entityName/$relationshipName"} = $joinClause;
3179                  $joinTable{"$relationshipName/$entityName"} = $joinClause;                  $joinTable{"$relationshipName/$entityName"} = $joinClause;
3180                  # Create joins between this relationship and the other relationships.                  # Create joins between this relationship and the other relationships.
# Line 2304  Line 3195 
3195                              # relationship and itself are prohibited.                              # relationship and itself are prohibited.
3196                              my $relJoinClause = "$otherName.${otherType}_link = $linkField";                              my $relJoinClause = "$otherName.${otherType}_link = $linkField";
3197                              $joinTable{$joinKey} = $relJoinClause;                              $joinTable{$joinKey} = $relJoinClause;
3198                              Trace("Relationship join clause is $relJoinClause for $joinKey.") if T(4);                              Trace("Relationship join clause is $relJoinClause for $joinKey.") if T(metadata => 4);
3199                          }                          }
3200                      }                      }
3201                  }                  }
# Line 2313  Line 3204 
3204                  # relationship can only be ambiguous with another recursive relationship,                  # relationship can only be ambiguous with another recursive relationship,
3205                  # and the incoming relationship from the outer loop is never recursive.                  # and the incoming relationship from the outer loop is never recursive.
3206                  for my $otherName (@bothList) {                  for my $otherName (@bothList) {
3207                      Trace("Setting up relationship joins to recursive relationship $otherName with $relationshipName.") if T(4);                      Trace("Setting up relationship joins to recursive relationship $otherName with $relationshipName.") if T(metadata => 4);
3208                      # Join from the left.                      # Join from the left.
3209                      $joinTable{"$relationshipName/$otherName"} =                      $joinTable{"$relationshipName/$otherName"} =
3210                          "$linkField = $otherName.from_link";                          "$linkField = $otherName.from_link";
# Line 2328  Line 3219 
3219          # 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
3220          # possible to get the same effect using multiple queries.          # possible to get the same effect using multiple queries.
3221          for my $relationshipName (@bothList) {          for my $relationshipName (@bothList) {
3222              Trace("Setting up entity joins to recursive relationship $relationshipName with $entityName.") if T(4);              Trace("Setting up entity joins to recursive relationship $relationshipName with $entityName.") if T(metadata => 4);
3223              # Join to the entity from each direction.              # Join to the entity from each direction.
3224              $joinTable{"$entityName/$relationshipName"} =              $joinTable{"$entityName/$relationshipName"} =
3225                  "$entityName.id = $relationshipName.from_link";                  "$entityName.id = $relationshipName.from_link";
# Line 2342  Line 3233 
3233      return $metadata;      return $metadata;
3234  }  }
3235    
3236    =head3 SortNeeded
3237    
3238    C<< my $flag = $erdb->SortNeeded($relationName); >>
3239    
3240    Return TRUE if the specified relation should be sorted during loading to remove duplicate keys,
3241    else FALSE.
3242    
3243    =over 4
3244    
3245    =item relationName
3246    
3247    Name of the relation to be examined.
3248    
3249    =item RETURN
3250    
3251    Returns TRUE if the relation needs a sort, else FALSE.
3252    
3253    =back
3254    
3255    =cut
3256    #: Return Type $;
3257    sub SortNeeded {
3258        # Get the parameters.
3259        my ($self, $relationName) = @_;
3260        # Declare the return variable.
3261        my $retVal = 0;
3262        # Find out if the relation is a primary entity relation.
3263        my $entityTable = $self->{_metaData}->{Entities};
3264        if (exists $entityTable->{$relationName}) {
3265            $retVal = 1;
3266        }
3267        # Return the result.
3268        return $retVal;
3269    }
3270    
3271  =head3 CreateRelationshipIndex  =head3 CreateRelationshipIndex
3272    
3273  Create an index for a relationship's relation.  Create an index for a relationship's relation.

Legend:
Removed from v.1.18  
changed lines
  Added in v.1.59

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3