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

Diff of /Sprout/ERDB.pm

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

revision 1.33, Sat Jan 28 09:36:47 2006 UTC revision 1.50, Wed Jun 21 03:38:36 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;      use FIG;
14    
15  =head1 Entity-Relationship Database Package  =head1 Entity-Relationship Database Package
# Line 109  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 125  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 310  Line 326 
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 =>   1, 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 402  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 446  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 470  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 480  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 513  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 687  Line 745 
745      return $retVal;      return $retVal;
746  }  }
747    
748    =head3 DigestFields
749    
750    C<< $erdb->DigestFields($relName, $fieldList); >>
751    
752    Digest the strings in the field list that correspond to data type C<hash-string> in the
753    specified relation.
754    
755    =over 4
756    
757    =item relName
758    
759    Name of the relation to which the fields belong.
760    
761    =item fieldList
762    
763    List of field contents to be loaded into the relation.
764    
765    =back
766    
767    =cut
768    #: Return Type ;
769    sub DigestFields {
770        # Get the parameters.
771        my ($self, $relName, $fieldList) = @_;
772        # Get the relation definition.
773        my $relData = $self->_FindRelation($relName);
774        # Get the list of field descriptors.
775        my $fieldTypes = $relData->{Fields};
776        my $fieldCount = scalar @{$fieldTypes};
777        # Loop through the two lists.
778        for (my $i = 0; $i < $fieldCount; $i++) {
779            # Get the type of the current field.
780            my $fieldType = $fieldTypes->[$i]->{type};
781            # If it's a hash string, digest it in place.
782            if ($fieldType eq 'hash-string') {
783                $fieldList->[$i] = $self->DigestKey($fieldList->[$i]);
784            }
785        }
786    }
787    
788    =head3 DigestKey
789    
790    C<< my $digested = $erdb->DigestKey($keyValue); >>
791    
792    Return the digested value of a symbolic key. The digested value can then be plugged into a
793    key-based search into a table with key-type hash-string.
794    
795    Currently the digesting process is independent of the database structure, but that may not
796    always be the case, so this is an instance method instead of a static method.
797    
798    =over 4
799    
800    =item keyValue
801    
802    Key value to digest.
803    
804    =item RETURN
805    
806    Digested value ofthe key.
807    
808    =back
809    
810    =cut
811    
812    sub DigestKey {
813        # Get the parameters.
814        my ($self, $keyValue) = @_;
815        # Compute the digest.
816        my $retVal = md5_base64($keyValue);
817        # Return the result.
818        return $retVal;
819    }
820    
821  =head3 CreateIndex  =head3 CreateIndex
822    
823  C<< $erdb->CreateIndex($relationName); >>  C<< $erdb->CreateIndex($relationName); >>
# Line 848  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 856  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 873  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 913  Line 1049 
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    C<< "LIMIT 10" >>
1063    
1064    =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 927  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 / 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) {  
             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";  
         }  
1091      }      }
     Trace("SQL query: $command") if T(SQL => 4);  
     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());  
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 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 1146  Line 1242 
1242                          # the current entity, so we need to stack it.                          # the current entity, so we need to stack it.
1243                          my @stackList = (@augmentedList, $toEntity);                          my @stackList = (@augmentedList, $toEntity);
1244                          push @fromPathList, \@stackList;                          push @fromPathList, \@stackList;
1245                        } else {
1246                            Trace("$toEntity ignored because it occurred previously.") if T(4);
1247                      }                      }
1248                  }                  }
1249              }              }
# Line 1171  Line 1269 
1269      for my $keyName ('to_link', 'from_link') {      for my $keyName ('to_link', 'from_link') {
1270          # Get the list for this key.          # Get the list for this key.
1271          my @pathList = @{$stackList{$keyName}};          my @pathList = @{$stackList{$keyName}};
1272            Trace(scalar(@pathList) . " entries in path list for $keyName.") if T(3);
1273          # Loop through this list.          # Loop through this list.
1274          while (my $path = pop @pathList) {          while (my $path = pop @pathList) {
1275              # Get the table whose rows are to be deleted.              # Get the table whose rows are to be deleted.
1276              my @pathTables = @{$path};              my @pathTables = @{$path};
1277              # Start the DELETE statement.              # 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];              my $target = $pathTables[$#pathTables];
1280              my $stmt = "DELETE FROM $target";              my $stmt = $db->SetUsing(@pathTables);
             # If there's more than just the one table, we need a USING clause.  
             if (@pathTables > 1) {  
                 $stmt .= " USING " . join(", ", @pathTables[0 .. ($#pathTables - 1)]);  
             }  
1281              # Now start the WHERE. The first thing is the ID field from the starting table. That              # 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              # starting table will either be the entity relation or one of the entity's
1283              # sub-relations.              # sub-relations.
# Line 1191  Line 1287 
1287                  # Connect the current relationship to the preceding entity.                  # Connect the current relationship to the preceding entity.
1288                  my ($entity, $rel) = @pathTables[$i-1,$i];                  my ($entity, $rel) = @pathTables[$i-1,$i];
1289                  # The style of connection depends on the direction of the relationship.                  # The style of connection depends on the direction of the relationship.
1290                  $stmt .= " AND $entity.id = $rel.from_link";                  $stmt .= " AND $entity.id = $rel.$keyName";
1291                  if ($i + 1 <= $#pathTables) {                  if ($i + 1 <= $#pathTables) {
1292                      # Here there's a next entity, so connect that to the relationship's                      # Here there's a next entity, so connect that to the relationship's
1293                      # to-link.                      # to-link.
1294                      my $entity2 = $pathTables[$i+1];                      my $entity2 = $pathTables[$i+1];
1295                      $stmt .= " AND $rel.$keyName = $entity2.id";                      $stmt .= " AND $rel.to_link = $entity2.id";
1296                  }                  }
1297              }              }
1298              # Now we have our desired DELETE statement.              # Now we have our desired DELETE statement.
# Line 1206  Line 1302 
1302              } else {              } else {
1303                  # Here we can delete. Note that the SQL method dies with a confessing                  # 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.                  # if an error occurs, so we just go ahead and do it.
1305                  Trace("Executing delete: $stmt") if T(3);                  Trace("Executing delete from $target using '$objectID'.") if T(3);
1306                  my $rv = $db->SQL($stmt, 0, [$objectID]);                  my $rv = $db->SQL($stmt, 0, $objectID);
1307                  # Accumulate the statistics for this delete. The only rows deleted                  # Accumulate the statistics for this delete. The only rows deleted
1308                  # are from the target table, so we use its name to record the                  # are from the target table, so we use its name to record the
1309                  # statistic.                  # statistic.
# Line 1221  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, $filterClause, \@params); >>
1321    
1322  Return a list of object descriptors for the specified objects as determined by the  Return a list of object descriptors for the specified objects as determined by the
1323  specified filter clause.  specified filter clause.
# Line 1255  Line 1351 
1351  filter clause in general; however, odd things may happen if a sort field is from a secondary  filter clause in general; however, odd things may happen if a sort field is from a secondary
1352  relation.  relation.
1353    
1354  =item param1, param2, ..., paramN  =item params
1355    
1356  Parameter values to be substituted into the filter clause.  Reference to a list of parameter values to be substituted into the filter clause.
1357    
1358  =item RETURN  =item RETURN
1359    
# Line 1269  Line 1365 
1365  #: Return Type @%  #: Return Type @%
1366  sub GetList {  sub GetList {
1367      # Get the parameters.      # Get the parameters.
1368      my ($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 1282  Line 1378 
1378      return @retVal;      return @retVal;
1379  }  }
1380    
1381  =head3 ComputeObjectSentence  =head3 GetCount
1382    
1383  C<< my $sentence = $erdb->ComputeObjectSentence($objectName); >>  C<< my $count = $erdb->GetCount(\@objectNames, $filter, \@params); >>
1384    
1385  Check an object name, and if it is a relationship convert it to a relationship sentence.  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 = $erdb->GetCount(['Genome', 'Feature'], 'Genome(genus-species) LIKE ?',
1401                                    ['homo %']);
1402    
1403    it would return the number of genomes, not the number of genome/feature pairs.
1404    
1405  =over 4  =over 4
1406    
1407  =item objectName  =item objectNames
1408    
1409  Name of the entity or relationship.  Reference to a list of the objects (entities and relationships) included in the
1410    query.
1411    
1412    =item filter
1413    
1414    A filter clause for restricting the query. The rules are the same as for the L</Get>
1415    method.
1416    
1417    =item params
1418    
1419    Reference to a list of the parameter values to be substituted for the parameter marks
1420    in the filter.
1421    
1422  =item RETURN  =item RETURN
1423    
1424  Returns a string containing the entity name or a relationship sentence.  Returns a count of the number of records in the first table that would satisfy
1425    the query.
1426    
1427  =back  =back
1428    
1429  =cut  =cut
1430    
1431  sub ComputeObjectSentence {  sub GetCount {
1432      # Get the parameters.      # Get the parameters.
1433      my ($self, $objectName) = @_;      my ($self, $objectNames, $filter, $params) = @_;
1434      # Set the default return value.      # Declare the return variable.
1435      my $retVal = $objectName;      my $retVal;
1436      # Look for the object as a relationship.      # Find out if we're counting an entity or a relationship.
1437      my $relTable = $self->{_metaData}->{Relationships};      my $countedField;
1438      if (exists $relTable->{$objectName}) {      if ($self->IsEntity($objectNames->[0])) {
1439          # Get the relationship sentence.          $countedField = "id";
1440          $retVal = _ComputeRelationshipSentence($objectName, $relTable->{$objectName});      } 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.      # Return the result.
1467      return $retVal;      return $retVal;
1468  }  }
1469    
1470  =head3 DumpRelations  =head3 ComputeObjectSentence
1471    
1472  C<< $erdb->DumpRelations($outputDirectory); >>  C<< my $sentence = $erdb->ComputeObjectSentence($objectName); >>
1473    
1474    Check an object name, and if it is a relationship convert it to a relationship sentence.
1475    
1476    =over 4
1477    
1478    =item objectName
1479    
1480    Name of the entity or relationship.
1481    
1482    =item RETURN
1483    
1484    Returns a string containing the entity name or a relationship sentence.
1485    
1486    =back
1487    
1488    =cut
1489    
1490    sub ComputeObjectSentence {
1491        # Get the parameters.
1492        my ($self, $objectName) = @_;
1493        # Set the default return value.
1494        my $retVal = $objectName;
1495        # Look for the object as a relationship.
1496        my $relTable = $self->{_metaData}->{Relationships};
1497        if (exists $relTable->{$objectName}) {
1498            # Get the relationship sentence.
1499            $retVal = _ComputeRelationshipSentence($objectName, $relTable->{$objectName});
1500        }
1501        # Return the result.
1502        return $retVal;
1503    }
1504    
1505    =head3 DumpRelations
1506    
1507    C<< $erdb->DumpRelations($outputDirectory); >>
1508    
1509  Write the contents of all the relations to tab-delimited files in the specified directory.  Write the contents of all the relations to tab-delimited files in the specified directory.
1510  Each file will have the same name as the relation dumped, with an extension of DTX.  Each file will have the same name as the relation dumped, with an extension of DTX.
# Line 1677  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 1790  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 1803  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 1856  Line 2043 
2043      return $retVal;      return $retVal;
2044  }  }
2045    
2046    =head3 GetFieldTable
2047    
2048    C<< my $fieldHash = $self->GetFieldTable($objectnName); >>
2049    
2050    Get the field structure for a specified entity or relationship.
2051    
2052    =over 4
2053    
2054    =item objectName
2055    
2056    Name of the desired entity or relationship.
2057    
2058    =item RETURN
2059    
2060    The table containing the field descriptors for the specified object.
2061    
2062    =back
2063    
2064    =cut
2065    
2066    sub GetFieldTable {
2067        # Get the parameters.
2068        my ($self, $objectName) = @_;
2069        # Get the descriptor from the metadata.
2070        my $objectData = $self->_GetStructure($objectName);
2071        # Return the object's field table.
2072        return $objectData->{Fields};
2073    }
2074    
2075    =head2 Data Mining Methods
2076    
2077    =head3 GetUsefulCrossValues
2078    
2079    C<< my @attrNames = $sprout->GetUsefulCrossValues($sourceEntity, $relationship); >>
2080    
2081    Return a list of the useful attributes that would be returned by a B<Cross> call
2082    from an entity of the source entity type through the specified relationship. This
2083    means it will return the fields of the target entity type and the intersection data
2084    fields in the relationship. Only primary table fields are returned. In other words,
2085    the field names returned will be for fields where there is always one and only one
2086    value.
2087    
2088    =over 4
2089    
2090    =item sourceEntity
2091    
2092    Name of the entity from which the relationship crossing will start.
2093    
2094    =item relationship
2095    
2096    Name of the relationship being crossed.
2097    
2098    =item RETURN
2099    
2100    Returns a list of field names in Sprout field format (I<objectName>C<(>I<fieldName>C<)>.
2101    
2102    =back
2103    
2104    =cut
2105    #: Return Type @;
2106    sub GetUsefulCrossValues {
2107        # Get the parameters.
2108        my ($self, $sourceEntity, $relationship) = @_;
2109        # Declare the return variable.
2110        my @retVal = ();
2111        # Determine the target entity for the relationship. This is whichever entity is not
2112        # the source entity. So, if the source entity is the FROM, we'll get the name of
2113        # the TO, and vice versa.
2114        my $relStructure = $self->_GetStructure($relationship);
2115        my $targetEntityType = ($relStructure->{from} eq $sourceEntity ? "to" : "from");
2116        my $targetEntity = $relStructure->{$targetEntityType};
2117        # Get the field table for the entity.
2118        my $entityFields = $self->GetFieldTable($targetEntity);
2119        # The field table is a hash. The hash key is the field name. The hash value is a structure.
2120        # For the entity fields, the key aspect of the target structure is that the {relation} value
2121        # must match the entity name.
2122        my @fieldList = map { "$targetEntity($_)" } grep { $entityFields->{$_}->{relation} eq $targetEntity }
2123                            keys %{$entityFields};
2124        # Push the fields found onto the return variable.
2125        push @retVal, sort @fieldList;
2126        # Get the field table for the relationship.
2127        my $relationshipFields = $self->GetFieldTable($relationship);
2128        # Here we have a different rule. We want all the fields other than "from-link" and "to-link".
2129        # This may end up being an empty set.
2130        my @fieldList2 = map { "$relationship($_)" } grep { $_ ne "from-link" && $_ ne "to-link" }
2131                            keys %{$relationshipFields};
2132        # Push these onto the return list.
2133        push @retVal, sort @fieldList2;
2134        # Return the result.
2135        return @retVal;
2136    }
2137    
2138    =head3 FindColumn
2139    
2140    C<< my $colIndex = ERDB::FindColumn($headerLine, $columnIdentifier); >>
2141    
2142    Return the location a desired column in a data mining header line. The data
2143    mining header line is a tab-separated list of column names. The column
2144    identifier is either the numerical index of a column or the actual column
2145    name.
2146    
2147    =over 4
2148    
2149    =item headerLine
2150    
2151    The header line from a data mining command, which consists of a tab-separated
2152    list of column names.
2153    
2154    =item columnIdentifier
2155    
2156    Either the ordinal number of the desired column (1-based), or the name of the
2157    desired column.
2158    
2159    =item RETURN
2160    
2161    Returns the array index (0-based) of the desired column.
2162    
2163    =back
2164    
2165    =cut
2166    
2167    sub FindColumn {
2168        # Get the parameters.
2169        my ($headerLine, $columnIdentifier) = @_;
2170        # Declare the return variable.
2171        my $retVal;
2172        # Split the header line into column names.
2173        my @headers = ParseColumns($headerLine);
2174        # Determine whether we have a number or a name.
2175        if ($columnIdentifier =~ /^\d+$/) {
2176            # Here we have a number. Subtract 1 and validate the result.
2177            $retVal = $columnIdentifier - 1;
2178            if ($retVal < 0 || $retVal > $#headers) {
2179                Confess("Invalid column identifer \"$columnIdentifier\": value out of range.");
2180            }
2181        } else {
2182            # Here we have a name. We need to find it in the list.
2183            for (my $i = 0; $i <= $#headers && ! defined($retVal); $i++) {
2184                if ($headers[$i] eq $columnIdentifier) {
2185                    $retVal = $i;
2186                }
2187            }
2188            if (! defined($retVal)) {
2189                Confess("Invalid column identifier \"$columnIdentifier\": value not found.");
2190            }
2191        }
2192        # Return the result.
2193        return $retVal;
2194    }
2195    
2196    =head3 ParseColumns
2197    
2198    C<< my @columns = ERDB::ParseColumns($line); >>
2199    
2200    Convert the specified data line to a list of columns.
2201    
2202    =over 4
2203    
2204    =item line
2205    
2206    A data mining input, consisting of a tab-separated list of columns terminated by a
2207    new-line.
2208    
2209    =item RETURN
2210    
2211    Returns a list consisting of the column values.
2212    
2213    =back
2214    
2215    =cut
2216    
2217    sub ParseColumns {
2218        # Get the parameters.
2219        my ($line) = @_;
2220        # Chop off the line-end.
2221        chomp $line;
2222        # Split it into a list.
2223        my @retVal = split(/\t/, $line);
2224        # Return the result.
2225        return @retVal;
2226    }
2227    
2228  =head2 Internal Utility Methods  =head2 Internal Utility Methods
2229    
2230    =head3 SetupSQL
2231    
2232    Process a list of object names and a filter clause so that they can be used to
2233    build an SQL statement. This method takes in a reference to a list of object names
2234    and a filter clause. It will return a corrected filter clause, a list of mapped
2235    names and the mapped name hash.
2236    
2237    This is an instance method.
2238    
2239    =over 4
2240    
2241    =item objectNames
2242    
2243    Reference to a list of the object names to be included in the query.
2244    
2245    =item filterClause
2246    
2247    A string containing the WHERE clause for the query (without the C<WHERE>) and also
2248    optionally the C<ORDER BY> and C<LIMIT> clauses.
2249    
2250    =item RETURN
2251    
2252    Returns a three-element list. The first element is the SQL statement suffix, beginning
2253    with the FROM clause. The second element is a reference to a list of the names to be
2254    used in retrieving the fields. The third element is a hash mapping the names to the
2255    objects they represent.
2256    
2257    =back
2258    
2259    =cut
2260    
2261    sub _SetupSQL {
2262        my ($self, $objectNames, $filterClause) = @_;
2263        # Adjust the list of object names to account for multiple occurrences of the
2264        # same object. We start with a hash table keyed on object name that will
2265        # return the object suffix. The first time an object is encountered it will
2266        # not be found in the hash. The next time the hash will map the object name
2267        # to 2, then 3, and so forth.
2268        my %objectHash = ();
2269        # This list will contain the object names as they are to appear in the
2270        # FROM list.
2271        my @fromList = ();
2272        # This list contains the suffixed object name for each object. It is exactly
2273        # parallel to the list in the $objectNames parameter.
2274        my @mappedNameList = ();
2275        # Finally, this hash translates from a mapped name to its original object name.
2276        my %mappedNameHash = ();
2277        # Now we create the lists. Note that for every single name we push something into
2278        # @fromList and @mappedNameList. This insures that those two arrays are exactly
2279        # parallel to $objectNames.
2280        for my $objectName (@{$objectNames}) {
2281            # Get the next suffix for this object.
2282            my $suffix = $objectHash{$objectName};
2283            if (! $suffix) {
2284                # Here we are seeing the object for the first time. The object name
2285                # is used as is.
2286                push @mappedNameList, $objectName;
2287                push @fromList, $objectName;
2288                $mappedNameHash{$objectName} = $objectName;
2289                # Denote the next suffix will be 2.
2290                $objectHash{$objectName} = 2;
2291            } else {
2292                # Here we've seen the object before. We construct a new name using
2293                # the suffix from the hash and update the hash.
2294                my $mappedName = "$objectName$suffix";
2295                $objectHash{$objectName} = $suffix + 1;
2296                # The FROM list has the object name followed by the mapped name. This
2297                # tells SQL it's still the same table, but we're using a different name
2298                # for it to avoid confusion.
2299                push @fromList, "$objectName $mappedName";
2300                # The mapped-name list contains the real mapped name.
2301                push @mappedNameList, $mappedName;
2302                # Finally, enable us to get back from the mapped name to the object name.
2303                $mappedNameHash{$mappedName} = $objectName;
2304            }
2305        }
2306        # Begin the SELECT suffix. It starts with
2307        #
2308        # FROM name1, name2, ... nameN
2309        #
2310        my $suffix = "FROM " . join(', ', @fromList);
2311        # Check for a filter clause.
2312        if ($filterClause) {
2313            # Here we have one, so we convert its field names and add it to the query. First,
2314            # We create a copy of the filter string we can work with.
2315            my $filterString = $filterClause;
2316            # Next, we sort the object names by length. This helps protect us from finding
2317            # object names inside other object names when we're doing our search and replace.
2318            my @sortedNames = sort { length($b) - length($a) } @mappedNameList;
2319            # We will also keep a list of conditions to add to the WHERE clause in order to link
2320            # entities and relationships as well as primary relations to secondary ones.
2321            my @joinWhere = ();
2322            # The final preparatory step is to create a hash table of relation names. The
2323            # table begins with the relation names already in the SELECT command. We may
2324            # need to add relations later if there is filtering on a field in a secondary
2325            # relation. The secondary relations are the ones that contain multiply-
2326            # occurring or optional fields.
2327            my %fromNames = map { $_ => 1 } @sortedNames;
2328            # We are ready to begin. We loop through the object names, replacing each
2329            # object name's field references by the corresponding SQL field reference.
2330            # Along the way, if we find a secondary relation, we will need to add it
2331            # to the FROM clause.
2332            for my $mappedName (@sortedNames) {
2333                # Get the length of the object name plus 2. This is the value we add to the
2334                # size of the field name to determine the size of the field reference as a
2335                # whole.
2336                my $nameLength = 2 + length $mappedName;
2337                # Get the real object name for this mapped name.
2338                my $objectName = $mappedNameHash{$mappedName};
2339                Trace("Processing $mappedName for object $objectName.") if T(4);
2340                # Get the object's field list.
2341                my $fieldList = $self->GetFieldTable($objectName);
2342                # Find the field references for this object.
2343                while ($filterString =~ m/$mappedName\(([^)]*)\)/g) {
2344                    # At this point, $1 contains the field name, and the current position
2345                    # is set immediately after the final parenthesis. We pull out the name of
2346                    # the field and the position and length of the field reference as a whole.
2347                    my $fieldName = $1;
2348                    my $len = $nameLength + length $fieldName;
2349                    my $pos = pos($filterString) - $len;
2350                    # Insure the field exists.
2351                    if (!exists $fieldList->{$fieldName}) {
2352                        Confess("Field $fieldName not found for object $objectName.");
2353                    } else {
2354                        Trace("Processing $fieldName at position $pos.") if T(4);
2355                        # Get the field's relation.
2356                        my $relationName = $fieldList->{$fieldName}->{relation};
2357                        # Now we have a secondary relation. We need to insure it matches the
2358                        # mapped name of the primary relation. First we peel off the suffix
2359                        # from the mapped name.
2360                        my $mappingSuffix = substr $mappedName, length($objectName);
2361                        # Put the mapping suffix onto the relation name to get the
2362                        # mapped relation name.
2363                        my $mappedRelationName = "$relationName$mappingSuffix";
2364                        # Insure the relation is in the FROM clause.
2365                        if (!exists $fromNames{$mappedRelationName}) {
2366                            # Add the relation to the FROM clause.
2367                            if ($mappedRelationName eq $relationName) {
2368                                # The name is un-mapped, so we add it without
2369                                # any frills.
2370                                $suffix .= ", $relationName";
2371                                push @joinWhere, "$objectName.id = $relationName.id";
2372                            } else {
2373                                # Here we have a mapping situation.
2374                                $suffix .= ", $relationName $mappedRelationName";
2375                                push @joinWhere, "$mappedRelationName.id = $mappedName.id";
2376                            }
2377                            # Denote we have this relation available for future fields.
2378                            $fromNames{$mappedRelationName} = 1;
2379                        }
2380                        # Form an SQL field reference from the relation name and the field name.
2381                        my $sqlReference = "$mappedRelationName." . _FixName($fieldName);
2382                        # Put it into the filter string in place of the old value.
2383                        substr($filterString, $pos, $len) = $sqlReference;
2384                        # Reposition the search.
2385                        pos $filterString = $pos + length $sqlReference;
2386                    }
2387                }
2388            }
2389            # The next step is to join the objects together. We only need to do this if there
2390            # is more than one object in the object list. We start with the first object and
2391            # run through the objects after it. Note also that we make a safety copy of the
2392            # list before running through it.
2393            my @mappedObjectList = @mappedNameList;
2394            my $lastMappedObject = shift @mappedObjectList;
2395            # Get the join table.
2396            my $joinTable = $self->{_metaData}->{Joins};
2397            # Loop through the object list.
2398            for my $thisMappedObject (@mappedObjectList) {
2399                # Look for a join using the real object names.
2400                my $lastObject = $mappedNameHash{$lastMappedObject};
2401                my $thisObject = $mappedNameHash{$thisMappedObject};
2402                my $joinKey = "$lastObject/$thisObject";
2403                if (!exists $joinTable->{$joinKey}) {
2404                    # Here there's no join, so we throw an error.
2405                    Confess("No join exists to connect from $lastMappedObject to $thisMappedObject.");
2406                } else {
2407                    # Get the join clause.
2408                    my $unMappedJoin = $joinTable->{$joinKey};
2409                    # Fix the names.
2410                    $unMappedJoin =~ s/$lastObject/$lastMappedObject/;
2411                    $unMappedJoin =~ s/$thisObject/$thisMappedObject/;
2412                    push @joinWhere, $unMappedJoin;
2413                    # Save this object as the last object for the next iteration.
2414                    $lastMappedObject = $thisMappedObject;
2415                }
2416            }
2417            # Now we need to handle the whole ORDER BY / LIMIT thing. The important part
2418            # here is we want the filter clause to be empty if there's no WHERE filter.
2419            # We'll put the ORDER BY / LIMIT clauses in the following variable.
2420            my $orderClause = "";
2421            # Locate the ORDER BY or LIMIT verbs (if any). We use a non-greedy
2422            # operator so that we find the first occurrence of either verb.
2423            if ($filterString =~ m/^(.*?)\s*(ORDER BY|LIMIT)/g) {
2424                # Here we have an ORDER BY or LIMIT verb. Split it off of the filter string.
2425                my $pos = pos $filterString;
2426                $orderClause = $2 . substr($filterString, $pos);
2427                $filterString = $1;
2428            }
2429            # Add the filter and the join clauses (if any) to the SELECT command.
2430            if ($filterString) {
2431                Trace("Filter string is \"$filterString\".") if T(4);
2432                push @joinWhere, "($filterString)";
2433            }
2434            if (@joinWhere) {
2435                $suffix .= " WHERE " . join(' AND ', @joinWhere);
2436            }
2437            # Add the sort or limit clause (if any) to the SELECT command.
2438            if ($orderClause) {
2439                $suffix .= " $orderClause";
2440            }
2441        }
2442        # Return the suffix, the mapped name list, and the mapped name hash.
2443        return ($suffix, \@mappedNameList, \%mappedNameHash);
2444    }
2445    
2446    =head3 GetStatementHandle
2447    
2448    This method will prepare and execute an SQL query, returning the statement handle.
2449    The main reason for doing this here is so that everybody who does SQL queries gets
2450    the benefit of tracing.
2451    
2452    This is an instance method.
2453    
2454    =over 4
2455    
2456    =item command
2457    
2458    Command to prepare and execute.
2459    
2460    =item params
2461    
2462    Reference to a list of the values to be substituted in for the parameter marks.
2463    
2464    =item RETURN
2465    
2466    Returns a prepared and executed statement handle from which the caller can extract
2467    results.
2468    
2469    =back
2470    
2471    =cut
2472    
2473    sub _GetStatementHandle {
2474        # Get the parameters.
2475        my ($self, $command, $params) = @_;
2476        # Trace the query.
2477        Trace("SQL query: $command") if T(SQL => 3);
2478        Trace("PARMS: '" . (join "', '", @{$params}) . "'") if (T(SQL => 4) && (@{$params} > 0));
2479        # Get the database handle.
2480        my $dbh = $self->{_dbh};
2481        # Prepare the command.
2482        my $sth = $dbh->prepare_command($command);
2483        # Execute it with the parameters bound in.
2484        $sth->execute(@{$params}) || Confess("SELECT error" . $sth->errstr());
2485        # Return the statement handle.
2486        return $sth;
2487    }
2488    
2489  =head3 GetLoadStats  =head3 GetLoadStats
2490    
2491  Return a blank statistics object for use by the load methods.  Return a blank statistics object for use by the load methods.
# Line 2062  Line 2690 
2690      return $objectData->{Relations};      return $objectData->{Relations};
2691  }  }
2692    
 =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};  
 }  
   
2693  =head3 ValidateFieldNames  =head3 ValidateFieldNames
2694    
2695  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 2444  Line 3043 
3043              # 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.
3044              my $fromEntity = $relationship->{from};              my $fromEntity = $relationship->{from};
3045              my $toEntity = $relationship->{to};              my $toEntity = $relationship->{to};
3046              Trace("Join check for relationship $relationshipName from $fromEntity to $toEntity.") if T(4);              Trace("Join check for relationship $relationshipName from $fromEntity to $toEntity.") if T(Joins => 4);
3047              if ($fromEntity eq $entityName) {              if ($fromEntity eq $entityName) {
3048                  if ($toEntity eq $entityName) {                  if ($toEntity eq $entityName) {
3049                      # Here the relationship is recursive.                      # Here the relationship is recursive.
# Line 2533  Line 3132 
3132      return $metadata;      return $metadata;
3133  }  }
3134    
3135    =head3 SortNeeded
3136    
3137    C<< my $flag = $erdb->SortNeeded($relationName); >>
3138    
3139    Return TRUE if the specified relation should be sorted during loading to remove duplicate keys,
3140    else FALSE.
3141    
3142    =over 4
3143    
3144    =item relationName
3145    
3146    Name of the relation to be examined.
3147    
3148    =item RETURN
3149    
3150    Returns TRUE if the relation needs a sort, else FALSE.
3151    
3152    =back
3153    
3154    =cut
3155    #: Return Type $;
3156    sub SortNeeded {
3157        # Get the parameters.
3158        my ($self, $relationName) = @_;
3159        # Declare the return variable.
3160        my $retVal = 0;
3161        # Find out if the relation is a primary entity relation.
3162        my $entityTable = $self->{_metaData}->{Entities};
3163        if (exists $entityTable->{$relationName}) {
3164            my $keyType = $entityTable->{$relationName}->{keyType};
3165            Trace("Relation $relationName found in entity table with key type $keyType.") if T(3);
3166            # If the key is not a hash string, we must do the sort.
3167            if ($keyType ne 'hash-string') {
3168                $retVal = 1;
3169            }
3170        }
3171        # Return the result.
3172        return $retVal;
3173    }
3174    
3175  =head3 CreateRelationshipIndex  =head3 CreateRelationshipIndex
3176    
3177  Create an index for a relationship's relation.  Create an index for a relationship's relation.

Legend:
Removed from v.1.33  
changed lines
  Added in v.1.50

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3