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

Diff of /Sprout/ERDB.pm

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

revision 1.43, Mon May 15 20:01:35 2006 UTC revision 1.47, Sun Jun 18 05:14:56 2006 UTC
# Line 110  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 324  Line 328 
328                    boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, dataGen => "IntGen(0, 1)" },                    boolean => { sqlType => 'SMALLINT',           maxLen => 1,            avgLen =>   1, dataGen => "IntGen(0, 1)" },
329                   'hash-string' =>                   'hash-string' =>
330                               { sqlType => 'VARCHAR(22)',        maxLen => 22,           avgLen =>  22, dataGen => "SringGen(22)" },                               { 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 416  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 460  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 484  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 494  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 527  Line 573 
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 736  Line 780 
780          my $fieldType = $fieldTypes->[$i]->{type};          my $fieldType = $fieldTypes->[$i]->{type};
781          # If it's a hash string, digest it in place.          # If it's a hash string, digest it in place.
782          if ($fieldType eq 'hash-string') {          if ($fieldType eq 'hash-string') {
783              $fieldList->[$i] = md5_base64($fieldList->[$i]);              $fieldList->[$i] = $self->DigestKey($fieldList->[$i]);
784          }          }
785      }      }
786  }  }
787    
788    =head3 DigestKey
789    
790    C<< my $digested = $erdb->DigestKey($keyValue); >>
791    
792    Return the digested value of a symbolic key. The digested value can then be plugged into a
793    key-based search into a table with key-type hash-string.
794    
795    Currently the digesting process is independent of the database structure, but that may not
796    always be the case, so this is an instance method instead of a static method.
797    
798    =over 4
799    
800    =item keyValue
801    
802    Key value to digest.
803    
804    =item RETURN
805    
806    Digested value ofthe key.
807    
808    =back
809    
810    =cut
811    
812    sub DigestKey {
813        # Get the parameters.
814        my ($self, $keyValue) = @_;
815        # Compute the digest.
816        my $retVal = md5_base64($keyValue);
817        # Return the result.
818        return $retVal;
819    }
820    
821  =head3 CreateIndex  =head3 CreateIndex
822    
823  C<< $erdb->CreateIndex($relationName); >>  C<< $erdb->CreateIndex($relationName); >>
# Line 902  Line 979 
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 910  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 927  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.
# Line 984  Line 1061 
1061    
1062  C<< "LIMIT 10" >>  C<< "LIMIT 10" >>
1063    
1064  =item param1, param2, ..., paramN  =item params
1065    
1066  Parameter values to be substituted into the filter clause.  Reference to a list of parameter values to be substituted into the filter clause.
1067    
1068  =item RETURN  =item RETURN
1069    
# Line 998  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, $params) = @_;
1079      # Adjust the list of object names to account for multiple occurrences of the      # Process the SQL stuff.
1080      # same object. We start with a hash table keyed on object name that will      my ($suffix, $mappedNameListRef, $mappedNameHashRef) =
1081      # return the object suffix. The first time an object is encountered it will          $self->_SetupSQL($objectNames, $filterClause);
1082      # not be found in the hash. The next time the hash will map the object name      # Create the query.
1083      # to 2, then 3, and so forth.      my $command = "SELECT DISTINCT " . join(".*, ", @{$mappedNameListRef}) .
1084      my %objectHash = ();          ".* $suffix";
1085      # This list will contain the object names as they are to appear in the      my $sth = $self->_GetStatementHandle($command, $params);
     # FROM list.  
     my @fromList = ();  
     # This list contains the suffixed object name for each object. It is exactly  
     # parallel to the list in the $objectNames parameter.  
     my @mappedNameList = ();  
     # Finally, this hash translates from a mapped name to its original object name.  
     my %mappedNameHash = ();  
     # Now we create the lists. Note that for every single name we push something into  
     # @fromList and @mappedNameList. This insures that those two arrays are exactly  
     # parallel to $objectNames.  
     for my $objectName (@{$objectNames}) {  
         # Get the next suffix for this object.  
         my $suffix = $objectHash{$objectName};  
         if (! $suffix) {  
             # Here we are seeing the object for the first time. The object name  
             # is used as is.  
             push @mappedNameList, $objectName;  
             push @fromList, $objectName;  
             $mappedNameHash{$objectName} = $objectName;  
             # Denote the next suffix will be 2.  
             $objectHash{$objectName} = 2;  
         } else {  
             # Here we've seen the object before. We construct a new name using  
             # the suffix from the hash and update the hash.  
             my $mappedName = "$objectName$suffix";  
             $objectHash{$objectName} = $suffix + 1;  
             # The FROM list has the object name followed by the mapped name. This  
             # tells SQL it's still the same table, but we're using a different name  
             # for it to avoid confusion.  
             push @fromList, "$objectName $mappedName";  
             # The mapped-name list contains the real mapped name.  
             push @mappedNameList, $mappedName;  
             # Finally, enable us to get back from the mapped name to the object name.  
             $mappedNameHash{$mappedName} = $objectName;  
         }  
     }  
     # Construct the SELECT statement. The general pattern is  
     #  
     # SELECT name1.*, name2.*, ... nameN.* FROM name1, name2, ... nameN  
     #  
     my $dbh = $self->{_dbh};  
     my $command = "SELECT DISTINCT " . join('.*, ', @mappedNameList) . ".* FROM " .  
                 join(', ', @fromList);  
     # Check for a filter clause.  
     if ($filterClause) {  
         # Here we have one, so we convert its field names and add it to the query. First,  
         # We create a copy of the filter string we can work with.  
         my $filterString = $filterClause;  
         # Next, we sort the object names by length. This helps protect us from finding  
         # object names inside other object names when we're doing our search and replace.  
         my @sortedNames = sort { length($b) - length($a) } @mappedNameList;  
         # 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. We may  
         # need to add relations later if there is filtering on a field in a secondary  
         # relation. The secondary relations are the ones that contain multiply-  
         # occurring or optional fields.  
         my %fromNames = map { $_ => 1 } @sortedNames;  
         # 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 $mappedName (@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 $mappedName;  
             # Get the real object name for this mapped name.  
             my $objectName = $mappedNameHash{$mappedName};  
             Trace("Processing $mappedName for object $objectName.") if T(4);  
             # Get the object's field list.  
             my $fieldList = $self->GetFieldTable($objectName);  
             # Find the field references for this object.  
             while ($filterString =~ m/$mappedName\(([^)]*)\)/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 {  
                     Trace("Processing $fieldName at position $pos.") if T(4);  
                     # Get the field's relation.  
                     my $relationName = $fieldList->{$fieldName}->{relation};  
                     # Now we have a secondary relation. We need to insure it matches the  
                     # mapped name of the primary relation. First we peel off the suffix  
                     # from the mapped name.  
                     my $mappingSuffix = substr $mappedName, length($objectName);  
                     # Put the mapping suffix onto the relation name to get the  
                     # mapped relation name.  
                     my $mappedRelationName = "$relationName$mappingSuffix";  
                     # Insure the relation is in the FROM clause.  
                     if (!exists $fromNames{$mappedRelationName}) {  
                         # Add the relation to the FROM clause.  
                         if ($mappedRelationName eq $relationName) {  
                             # The name is un-mapped, so we add it without  
                             # any frills.  
                             $command .= ", $relationName";  
                             push @joinWhere, "$objectName.id = $relationName.id";  
                         } else {  
                             # Here we have a mapping situation.  
                             $command .= ", $relationName $mappedRelationName";  
                             push @joinWhere, "$mappedRelationName.id = $mappedName.id";  
                         }  
                         # Denote we have this relation available for future fields.  
                         $fromNames{$mappedRelationName} = 1;  
                     }  
                     # Form an SQL field reference from the relation name and the field name.  
                     my $sqlReference = "$mappedRelationName." . _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 @mappedObjectList = @mappedNameList;  
         my $lastMappedObject = shift @mappedObjectList;  
         # Get the join table.  
         my $joinTable = $self->{_metaData}->{Joins};  
         # Loop through the object list.  
         for my $thisMappedObject (@mappedObjectList) {  
             # Look for a join using the real object names.  
             my $lastObject = $mappedNameHash{$lastMappedObject};  
             my $thisObject = $mappedNameHash{$thisMappedObject};  
             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 $lastMappedObject to $thisMappedObject.");  
             } else {  
                 # Get the join clause.  
                 my $unMappedJoin = $joinTable->{$joinKey};  
                 # Fix the names.  
                 $unMappedJoin =~ s/$lastObject/$lastMappedObject/;  
                 $unMappedJoin =~ s/$thisObject/$thisMappedObject/;  
                 push @joinWhere, $unMappedJoin;  
                 # Save this object as the last object for the next iteration.  
                 $lastMappedObject = $thisMappedObject;  
             }  
         }  
         # Now we need to handle the whole ORDER BY / LIMIT thing. The important part  
         # here is we want the filter clause to be empty if there's no WHERE filter.  
         # We'll put the ORDER BY / LIMIT clauses in the following variable.  
         my $orderClause = "";  
         # Locate the ORDER BY or LIMIT verbs (if any). We use a non-greedy  
         # operator so that we find the first occurrence of either verb.  
         if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {  
             # Here we have an ORDER BY or LIMIT verb. Split it off of the filter string.  
             my $pos = pos $filterString;  
             $orderClause = $2 . substr($filterString, $pos);  
             $filterString = $1;  
         }  
         # Add the filter and the join clauses (if any) to the SELECT command.  
         if ($filterString) {  
             Trace("Filter string is \"$filterString\".") if T(4);  
             push @joinWhere, "($filterString)";  
         }  
         if (@joinWhere) {  
             $command .= " WHERE " . join(' AND ', @joinWhere);  
         }  
         # Add the sort or limit clause (if any) to the SELECT command.  
         if ($orderClause) {  
             $command .= " $orderClause";  
         }  
     }  
     Trace("SQL query: $command") if T(SQL => 3);  
     Trace("PARMS: '" . (join "', '", @params) . "'") if (T(SQL => 4) && (@params > 0));  
     my $sth = $dbh->prepare_command($command);  
     # Execute it with the parameters bound in.  
     $sth->execute(@params) || Confess("SELECT error" . $sth->errstr());  
1086      # Now we create the relation map, which enables DBQuery to determine the order, name      # Now we create the relation map, which enables DBQuery to determine the order, name
1087      # and mapped name for each object in the query.      # and mapped name for each object in the query.
1088      my @relationMap = ();      my @relationMap = ();
1089      for my $mappedName (@mappedNameList) {      for my $mappedName (@{$mappedNameListRef}) {
1090          push @relationMap, [$mappedName, $mappedNameHash{$mappedName}];          push @relationMap, [$mappedName, $mappedNameHashRef->{$mappedName}];
1091      }      }
1092      # Return the statement object.      # Return the statement object.
1093      my $retVal = DBQuery::_new($self, $sth, \@relationMap);      my $retVal = DBQuery::_new($self, $sth, \@relationMap);
1094      return $retVal;      return $retVal;
1095  }  }
1096    
1097    =head3 GetFlat
1098    
1099    C<< my @list = $erdb->GetFlat(\@objectNames, $filterClause, \@parameterList, $field); >>
1100    
1101    This is a variation of L</GetAll> that asks for only a single field per record and
1102    returns a single flattened list.
1103    
1104    =over 4
1105    
1106    =item objectNames
1107    
1108    List containing the names of the entity and relationship objects to be retrieved.
1109    
1110    =item filterClause
1111    
1112    WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
1113    be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
1114    B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
1115    parameter list as additional parameters. The fields in a filter clause can come from primary
1116    entity relations, relationship relations, or secondary entity relations; however, all of the
1117    entities and relationships involved must be included in the list of object names.
1118    
1119    =item parameterList
1120    
1121    List of the parameters to be substituted in for the parameters marks in the filter clause.
1122    
1123    =item field
1124    
1125    Name of the field to be used to get the elements of the list returned.
1126    
1127    =item RETURN
1128    
1129    Returns a list of values.
1130    
1131    =back
1132    
1133    =cut
1134    #: Return Type @;
1135    sub GetFlat {
1136        # Get the parameters.
1137        my ($self, $objectNames, $filterClause, $parameterList, $field) = @_;
1138        # 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  =head3 Delete
1151    
1152  C<< my $stats = $erdb->Delete($entityName, $objectID); >>  C<< my $stats = $erdb->Delete($entityName, $objectID); >>
# Line 1366  Line 1317 
1317    
1318  =head3 GetList  =head3 GetList
1319    
1320  C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, $param1, $param2, ..., $paramN); >>  C<< my @dbObjects = $erdb->GetList(\@objectNames, $filterClause, \@params); >>
1321    
1322  Return a list of object descriptors for the specified objects as determined by the  Return a list of object descriptors for the specified objects as determined by the
1323  specified filter clause.  specified filter clause.
# Line 1400  Line 1351 
1351  filter clause in general; however, odd things may happen if a sort field is from a secondary  filter clause in general; however, odd things may happen if a sort field is from a secondary
1352  relation.  relation.
1353    
1354  =item param1, param2, ..., paramN  =item params
1355    
1356  Parameter values to be substituted into the filter clause.  Reference to a list of parameter values to be substituted into the filter clause.
1357    
1358  =item RETURN  =item RETURN
1359    
# Line 1414  Line 1365 
1365  #: Return Type @%  #: Return Type @%
1366  sub GetList {  sub GetList {
1367      # Get the parameters.      # Get the parameters.
1368      my ($self, $objectNames, $filterClause, @params) = @_;      my ($self, $objectNames, $filterClause, $params) = @_;
1369      # Declare the return variable.      # 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 1427  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 1822  Line 1862 
1862      # Get the parameters.      # Get the parameters.
1863      my ($self, $entityType, $ID) = @_;      my ($self, $entityType, $ID) = @_;
1864      # Create a query.      # Create a query.
1865      my $query = $self->Get([$entityType], "$entityType(id) = ?", $ID);      my $query = $self->Get([$entityType], "$entityType(id) = ?", [$ID]);
1866      # Get the first (and only) object.      # Get the first (and only) object.
1867      my $retVal = $query->Fetch();      my $retVal = $query->Fetch();
1868      # Return the result.      # Return the result.
# Line 1935  Line 1975 
1975      # list is a scalar we convert it into a singleton list.      # list is a scalar we convert it into a singleton list.
1976      my @parmList = ();      my @parmList = ();
1977      if (ref $parameterList eq "ARRAY") {      if (ref $parameterList eq "ARRAY") {
1978            Trace("GetAll parm list is an array.") if T(4);
1979          @parmList = @{$parameterList};          @parmList = @{$parameterList};
1980      } else {      } else {
1981            Trace("GetAll parm list is a scalar: $parameterList.") if T(4);
1982          push @parmList, $parameterList;          push @parmList, $parameterList;
1983      }      }
1984      # Insure the counter has a value.      # Insure the counter has a value.
# Line 1948  Line 1990 
1990          $filterClause .= " LIMIT $count";          $filterClause .= " LIMIT $count";
1991      }      }
1992      # Create the query.      # Create the query.
1993      my $query = $self->Get($objectNames, $filterClause, @parmList);      my $query = $self->Get($objectNames, $filterClause, \@parmList);
1994      # Set up a counter of the number of records read.      # Set up a counter of the number of records read.
1995      my $fetched = 0;      my $fetched = 0;
1996      # Loop through the records returned, extracting the fields. Note that if the      # Loop through the records returned, extracting the fields. Note that if the
# Line 2093  Line 2135 
2135    
2136  =head2 Internal Utility Methods  =head2 Internal Utility Methods
2137    
2138    =head3 SetupSQL
2139    
2140    Process a list of object names and a filter clause so that they can be used to
2141    build an SQL statement. This method takes in a reference to a list of object names
2142    and a filter clause. It will return a corrected filter clause, a list of mapped
2143    names and the mapped name hash.
2144    
2145    This is an instance method.
2146    
2147    =over 4
2148    
2149    =item objectNames
2150    
2151    Reference to a list of the object names to be included in the query.
2152    
2153    =item filterClause
2154    
2155    A string containing the WHERE clause for the query (without the C<WHERE>) and also
2156    optionally the C<ORDER BY> and C<LIMIT> clauses.
2157    
2158    =item RETURN
2159    
2160    Returns a three-element list. The first element is the SQL statement suffix, beginning
2161    with the FROM clause. The second element is a reference to a list of the names to be
2162    used in retrieving the fields. The third element is a hash mapping the names to the
2163    objects they represent.
2164    
2165    =back
2166    
2167    =cut
2168    
2169    sub _SetupSQL {
2170        my ($self, $objectNames, $filterClause) = @_;
2171        # Adjust the list of object names to account for multiple occurrences of the
2172        # same object. We start with a hash table keyed on object name that will
2173        # return the object suffix. The first time an object is encountered it will
2174        # not be found in the hash. The next time the hash will map the object name
2175        # to 2, then 3, and so forth.
2176        my %objectHash = ();
2177        # This list will contain the object names as they are to appear in the
2178        # FROM list.
2179        my @fromList = ();
2180        # This list contains the suffixed object name for each object. It is exactly
2181        # parallel to the list in the $objectNames parameter.
2182        my @mappedNameList = ();
2183        # Finally, this hash translates from a mapped name to its original object name.
2184        my %mappedNameHash = ();
2185        # Now we create the lists. Note that for every single name we push something into
2186        # @fromList and @mappedNameList. This insures that those two arrays are exactly
2187        # parallel to $objectNames.
2188        for my $objectName (@{$objectNames}) {
2189            # Get the next suffix for this object.
2190            my $suffix = $objectHash{$objectName};
2191            if (! $suffix) {
2192                # Here we are seeing the object for the first time. The object name
2193                # is used as is.
2194                push @mappedNameList, $objectName;
2195                push @fromList, $objectName;
2196                $mappedNameHash{$objectName} = $objectName;
2197                # Denote the next suffix will be 2.
2198                $objectHash{$objectName} = 2;
2199            } else {
2200                # Here we've seen the object before. We construct a new name using
2201                # the suffix from the hash and update the hash.
2202                my $mappedName = "$objectName$suffix";
2203                $objectHash{$objectName} = $suffix + 1;
2204                # The FROM list has the object name followed by the mapped name. This
2205                # tells SQL it's still the same table, but we're using a different name
2206                # for it to avoid confusion.
2207                push @fromList, "$objectName $mappedName";
2208                # The mapped-name list contains the real mapped name.
2209                push @mappedNameList, $mappedName;
2210                # Finally, enable us to get back from the mapped name to the object name.
2211                $mappedNameHash{$mappedName} = $objectName;
2212            }
2213        }
2214        # Begin the SELECT suffix. It starts with
2215        #
2216        # FROM name1, name2, ... nameN
2217        #
2218        my $suffix = "FROM " . join(', ', @fromList);
2219        # Check for a filter clause.
2220        if ($filterClause) {
2221            # Here we have one, so we convert its field names and add it to the query. First,
2222            # We create a copy of the filter string we can work with.
2223            my $filterString = $filterClause;
2224            # Next, we sort the object names by length. This helps protect us from finding
2225            # object names inside other object names when we're doing our search and replace.
2226            my @sortedNames = sort { length($b) - length($a) } @mappedNameList;
2227            # We will also keep a list of conditions to add to the WHERE clause in order to link
2228            # entities and relationships as well as primary relations to secondary ones.
2229            my @joinWhere = ();
2230            # The final preparatory step is to create a hash table of relation names. The
2231            # table begins with the relation names already in the SELECT command. We may
2232            # need to add relations later if there is filtering on a field in a secondary
2233            # relation. The secondary relations are the ones that contain multiply-
2234            # occurring or optional fields.
2235            my %fromNames = map { $_ => 1 } @sortedNames;
2236            # We are ready to begin. We loop through the object names, replacing each
2237            # object name's field references by the corresponding SQL field reference.
2238            # Along the way, if we find a secondary relation, we will need to add it
2239            # to the FROM clause.
2240            for my $mappedName (@sortedNames) {
2241                # Get the length of the object name plus 2. This is the value we add to the
2242                # size of the field name to determine the size of the field reference as a
2243                # whole.
2244                my $nameLength = 2 + length $mappedName;
2245                # Get the real object name for this mapped name.
2246                my $objectName = $mappedNameHash{$mappedName};
2247                Trace("Processing $mappedName for object $objectName.") if T(4);
2248                # Get the object's field list.
2249                my $fieldList = $self->GetFieldTable($objectName);
2250                # Find the field references for this object.
2251                while ($filterString =~ m/$mappedName\(([^)]*)\)/g) {
2252                    # At this point, $1 contains the field name, and the current position
2253                    # is set immediately after the final parenthesis. We pull out the name of
2254                    # the field and the position and length of the field reference as a whole.
2255                    my $fieldName = $1;
2256                    my $len = $nameLength + length $fieldName;
2257                    my $pos = pos($filterString) - $len;
2258                    # Insure the field exists.
2259                    if (!exists $fieldList->{$fieldName}) {
2260                        Confess("Field $fieldName not found for object $objectName.");
2261                    } else {
2262                        Trace("Processing $fieldName at position $pos.") if T(4);
2263                        # Get the field's relation.
2264                        my $relationName = $fieldList->{$fieldName}->{relation};
2265                        # Now we have a secondary relation. We need to insure it matches the
2266                        # mapped name of the primary relation. First we peel off the suffix
2267                        # from the mapped name.
2268                        my $mappingSuffix = substr $mappedName, length($objectName);
2269                        # Put the mapping suffix onto the relation name to get the
2270                        # mapped relation name.
2271                        my $mappedRelationName = "$relationName$mappingSuffix";
2272                        # Insure the relation is in the FROM clause.
2273                        if (!exists $fromNames{$mappedRelationName}) {
2274                            # Add the relation to the FROM clause.
2275                            if ($mappedRelationName eq $relationName) {
2276                                # The name is un-mapped, so we add it without
2277                                # any frills.
2278                                $suffix .= ", $relationName";
2279                                push @joinWhere, "$objectName.id = $relationName.id";
2280                            } else {
2281                                # Here we have a mapping situation.
2282                                $suffix .= ", $relationName $mappedRelationName";
2283                                push @joinWhere, "$mappedRelationName.id = $mappedName.id";
2284                            }
2285                            # Denote we have this relation available for future fields.
2286                            $fromNames{$mappedRelationName} = 1;
2287                        }
2288                        # Form an SQL field reference from the relation name and the field name.
2289                        my $sqlReference = "$mappedRelationName." . _FixName($fieldName);
2290                        # Put it into the filter string in place of the old value.
2291                        substr($filterString, $pos, $len) = $sqlReference;
2292                        # Reposition the search.
2293                        pos $filterString = $pos + length $sqlReference;
2294                    }
2295                }
2296            }
2297            # The next step is to join the objects together. We only need to do this if there
2298            # is more than one object in the object list. We start with the first object and
2299            # run through the objects after it. Note also that we make a safety copy of the
2300            # list before running through it.
2301            my @mappedObjectList = @mappedNameList;
2302            my $lastMappedObject = shift @mappedObjectList;
2303            # Get the join table.
2304            my $joinTable = $self->{_metaData}->{Joins};
2305            # Loop through the object list.
2306            for my $thisMappedObject (@mappedObjectList) {
2307                # Look for a join using the real object names.
2308                my $lastObject = $mappedNameHash{$lastMappedObject};
2309                my $thisObject = $mappedNameHash{$thisMappedObject};
2310                my $joinKey = "$lastObject/$thisObject";
2311                if (!exists $joinTable->{$joinKey}) {
2312                    # Here there's no join, so we throw an error.
2313                    Confess("No join exists to connect from $lastMappedObject to $thisMappedObject.");
2314                } else {
2315                    # Get the join clause.
2316                    my $unMappedJoin = $joinTable->{$joinKey};
2317                    # Fix the names.
2318                    $unMappedJoin =~ s/$lastObject/$lastMappedObject/;
2319                    $unMappedJoin =~ s/$thisObject/$thisMappedObject/;
2320                    push @joinWhere, $unMappedJoin;
2321                    # Save this object as the last object for the next iteration.
2322                    $lastMappedObject = $thisMappedObject;
2323                }
2324            }
2325            # Now we need to handle the whole ORDER BY / LIMIT thing. The important part
2326            # here is we want the filter clause to be empty if there's no WHERE filter.
2327            # We'll put the ORDER BY / LIMIT clauses in the following variable.
2328            my $orderClause = "";
2329            # Locate the ORDER BY or LIMIT verbs (if any). We use a non-greedy
2330            # operator so that we find the first occurrence of either verb.
2331            if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {
2332                # Here we have an ORDER BY or LIMIT verb. Split it off of the filter string.
2333                my $pos = pos $filterString;
2334                $orderClause = $2 . substr($filterString, $pos);
2335                $filterString = $1;
2336            }
2337            # Add the filter and the join clauses (if any) to the SELECT command.
2338            if ($filterString) {
2339                Trace("Filter string is \"$filterString\".") if T(4);
2340                push @joinWhere, "($filterString)";
2341            }
2342            if (@joinWhere) {
2343                $suffix .= " WHERE " . join(' AND ', @joinWhere);
2344            }
2345            # Add the sort or limit clause (if any) to the SELECT command.
2346            if ($orderClause) {
2347                $suffix .= " $orderClause";
2348            }
2349        }
2350        # Return the suffix, the mapped name list, and the mapped name hash.
2351        return ($suffix, \@mappedNameList, \%mappedNameHash);
2352    }
2353    
2354    =head3 GetStatementHandle
2355    
2356    This method will prepare and execute an SQL query, returning the statement handle.
2357    The main reason for doing this here is so that everybody who does SQL queries gets
2358    the benefit of tracing.
2359    
2360    This is an instance method.
2361    
2362    =over 4
2363    
2364    =item command
2365    
2366    Command to prepare and execute.
2367    
2368    =item params
2369    
2370    Reference to a list of the values to be substituted in for the parameter marks.
2371    
2372    =item RETURN
2373    
2374    Returns a prepared and executed statement handle from which the caller can extract
2375    results.
2376    
2377    =back
2378    
2379    =cut
2380    
2381    sub _GetStatementHandle {
2382        # Get the parameters.
2383        my ($self, $command, $params) = @_;
2384        # Trace the query.
2385        Trace("SQL query: $command") if T(SQL => 3);
2386        Trace("PARMS: '" . (join "', '", @{$params}) . "'") if (T(SQL => 4) && (@{$params} > 0));
2387        # Get the database handle.
2388        my $dbh = $self->{_dbh};
2389        # Prepare the command.
2390        my $sth = $dbh->prepare_command($command);
2391        # Execute it with the parameters bound in.
2392        $sth->execute(@{$params}) || Confess("SELECT error" . $sth->errstr());
2393        # Return the statement handle.
2394        return $sth;
2395    }
2396    
2397  =head3 GetLoadStats  =head3 GetLoadStats
2398    
2399  Return a blank statistics object for use by the load methods.  Return a blank statistics object for use by the load methods.

Legend:
Removed from v.1.43  
changed lines
  Added in v.1.47

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3